System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting past sales data, seasonal data, and customer preference data; means for analyzing the collected data and performing a demand prediction of food materials; means for calculating an optimal order quantity based on a prediction result; means for detecting a food material whose best-before date is close and managing information; means for selling the detected food material online; and means for proposing a cooking method of the food material via an online platform.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 restaurants, excessive ordering of ingredients and waste due to unsold food have become serious problems. This problem causes food waste and increased costs, reducing business efficiency. Furthermore, when food is approaching its expiration date, it is often discarded without being properly managed. This results in unnecessary waste and a negative impact on the environment. The present invention aims to solve these problems, reduce food waste, and improve business efficiency in restaurants. [Means for solving the problem]

[0005] The present invention solves the above problems by providing the following means: A data infrastructure is established by providing means for collecting past sales data, seasonal data, and customer preference data. Next, a means for analyzing the collected data and forecasting food ingredient demand is provided, thereby achieving accurate demand forecasting. Furthermore, a means for calculating optimal order quantities based on the forecast results is provided, preventing over-ordering. The present invention aims to improve the efficiency of inventory management by providing means for detecting food ingredients that are close to their expiration date and managing the information. In addition, a means for selling detected food ingredients online is provided, promoting the use of food ingredients. Finally, a means for suggesting cooking methods for food ingredients via an online platform is provided, improving convenience for purchasers. These means reduce food waste and secure new revenue sources.

[0006] "Past sales data" refers to historical data relating to sales, such as the quantity, price, sale date, and customer information of products sold during a specific period.

[0007] "Seasonal data" refers to data on sales trends and demand that fluctuate according to specific seasons or times of the year.

[0008] "Customer preference data" refers to data such as information about products and specific dishes that customers prefer to purchase, as well as purchasing patterns.

[0009] A "collection tool" is a mechanism, program, or method for gathering the necessary information or data.

[0010] An "analysis means" is a mechanism, program, or method for analyzing collected data and extracting useful information.

[0011] "Demand forecasting" refers to predicting future demand based on past data and other relevant factors.

[0012] "Calculating the order quantity" refers to calculating the optimal order quantity for a product based on a demand forecast.

[0013] "Inventory management" refers to the means and methods for understanding and efficiently managing product inventory.

[0014] "Soon-to-be-expired foodstuffs" are foodstuffs that are about to expire and therefore need to be consumed or sold quickly.

[0015] An "online platform" is a digital environment or system for selling products or providing services over the Internet.

[0016] "Cooking suggestions" refers to presenting customers with instructions and recipes for cooking using purchased ingredients. [Brief explanation of the drawings]

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

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

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

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

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

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0038] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. Below, we will create a program for the system and explain its processing in natural language.

[0039] Main component description

[0040] Data collection

[0041] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. For example, it can be configured to collect a week's worth of data every Monday.

[0042] Data analysis and demand forecasting

[0043] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT to generate demand forecasts that take into account weekends, holidays, and seasonal events. For example, it can predict increased demand for chicken and cake ingredients during the Christmas season in December.

[0044] Order quantity optimization

[0045] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. Based on the calculation results, the server then sends an ordering proposal to the restaurant's terminal, where it can be checked by the manager.

[0046] Best before date management

[0047] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the restaurant's terminal.

[0048] Online sales

[0049] The server posts food items that are close to their expiration date on the online platform, allowing users to purchase them. For example, users can access the platform from their home PC or smartphone and purchase tomatoes or lettuce that are close to their expiration date.

[0050] Cooking suggestions

[0051] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, the server will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0052] Specific examples

[0053] Data Collection Example

[0054] The server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores it in the database. At the same time, it can also collect information about the weather and events that day.

[0055] Demand forecast example

[0056] The server uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends that restaurants order 1.2 times the amount of chicken they ordered last year.

[0057] Example of expiration date management

[0058] The server detects from inventory information that the expiration date for the tomatoes is October 15, 2023, and sends an alert notification.The restaurant's terminal then displays an alert saying, "The expiration date for the tomatoes is approaching. Please use or sell them immediately."

[0059] Online sales example

[0060] A user accesses the online platform from their home PC and purchases tomatoes with a best-by date of October 10, 2023 at a discounted price. After the purchase procedure is completed, the server sends the user a recipe for "Pasta with Tomato Sauce."

[0061] In this way, this invention optimizes food supply and demand forecasts and inventory management, reduces waste, and maximizes profits. This invention significantly improves the management efficiency of restaurants and also provides convenient and attractive services to customers.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The server periodically accesses the restaurant's POS system to collect past sales data, seasonal data, and customer preference data. For example, it can be set to retrieve a week's worth of sales data every Monday. This data collection is performed automatically through the API.

[0065] Step 2:

[0066] The server converts and formats the data before storing it in the database. This includes filling in missing values ​​and removing outliers. For example, it filters out data with zero sales volume or other obviously abnormal values.

[0067] Step 3:

[0068] The server stores the formatted data in a database. The stored data includes product name, sales quantity, sales date, and customer attributes (age, gender, etc.). For example, sales data and customer information for October 1, 2023 are recorded in the corresponding tables in the database.

[0069] Step 4:

[0070] The server retrieves historical sales data, seasonal data, and customer preference data from the database. This is a pre-processing step for demand forecasting. The retrieved data covers a certain period (e.g., the past three years).

[0071] Step 5:

[0072] The server preprocesses the data it receives. Specifically, it normalizes and standardizes the data to make it suitable for analysis. For example, it converts sales volume into average values ​​for each week or month.

[0073] Step 6:

[0074] The server analyzes the data using ChatGPT to predict future demand, taking into account seasonality and the influence of specific events (e.g., Christmas and Valentine's Day). The forecast results are output as numerical data for further processing.

[0075] Step 7:

[0076] The server calculates the optimal order quantity based on the forecast results, taking into account current inventory levels and past order history. For example, if demand for chicken is predicted, it compares it with current inventory and calculates the required additional order quantity.

[0077] Step 8:

[0078] The server generates an ordering proposal based on the calculation results and sends a notification to the restaurant's administrator's terminal. The notification includes the specific order quantity and the recommended ordering time. The administrator places the order based on this information.

[0079] Step 9:

[0080] The server identifies ingredients that are close to expiry based on current inventory data. For example, it lists ingredients that are within a week of expiry. This process is important for efficient inventory management.

[0081] Step 10:

[0082] The server sends alerts to restaurant terminals about ingredients that are nearing their expiration date. The notifications include a list of ingredients that need to be used or sold immediately. The administrator can then take appropriate action based on this information.

[0083] Step 11:

[0084] The server posts food items that are nearing their expiration date on an online platform. Users can access the platform from their PCs or smartphones to check and purchase these food items. For example, users can view information about tomatoes and lettuce that are available at discounted prices.

[0085] Step 12:

[0086] A user purchases ingredients through the online platform, and once the purchase is complete, the server records the information in a database and sends a confirmation email to the purchaser.

[0087] Step 13:

[0088] The server generates appropriate cooking methods and recipes based on the purchased ingredients and provides them to the user. For example, if a user purchases tomatoes, the server sends a recipe for "pasta with tomato sauce" to the user for cooking reference.

[0089] In this way, the system optimizes food supply and demand forecasts and inventory management throughout a series of processing steps, reducing food waste and maximizing profits.

[0090] Example 1

[0091] 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."

[0092] In restaurants, predicting supply and demand for ingredients and managing inventory is labor-intensive and difficult to do efficiently. Inaccurate predictions can lead to shortages or surpluses of ingredients, resulting in economic losses and increased waste. Furthermore, there is a lack of mechanisms for managing ingredients approaching their expiration date or for encouraging their consumption at the appropriate time. The objective of this invention is to provide a system that solves these problems and achieves optimal supply and demand prediction and inventory management.

[0093] 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.

[0094] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for preprocessing the collected data to remove outliers and impute missing values, means for analyzing the collected data and using a generative AI model to predict demand for ingredients, means for calculating optimal order quantities based on the prediction results, means for detecting ingredients with approaching expiration dates and managing information, means for listing the detected ingredients on an online platform so that users can purchase them, and means for suggesting cooking methods for the ingredients via the online platform.This enables restaurants to efficiently and accurately predict supply and demand and manage inventory, thereby reducing food waste and maximizing profits.

[0095] "Past sales data" refers to data that records the past sales performance of a restaurant.

[0096] "Seasonal data" is data relating to a particular season, time of year, or event, such as fluctuations in demand for a particular product during a particular season.

[0097] "Customer preference data" refers to data related to a customer's purchasing behavior and preferences. For example, it includes information about a customer's favorite dishes and frequently purchased products.

[0098] "Collection means" refers to the methods and devices used to acquire and store data.

[0099] "Preprocessing" is a data cleansing process that removes outliers from collected data and fills in missing values.

[0100] An "outlier" is a value in the data that is significantly different from the other data.

[0101] "Missing values" are pieces of data that are missing or incomplete.

[0102] A "generative AI model" is a type of artificial intelligence model that learns patterns from large amounts of data and makes predictions and classifications. Specifically, this applies to models that use machine learning or deep learning.

[0103] "Order quantity" refers to the amount of ingredients purchased by a restaurant.

[0104] "Best before date" refers to the date by which food ingredients can be consumed while still maintaining their quality.

[0105] An "online platform" is a service or application provided over the Internet.

[0106] An "alert" is a warning or caution mechanism that notifies you when certain conditions are met.

[0107] "Cooking method" refers to the steps and recipes for processing and cooking ingredients.

[0108] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. Below, we will create a program for this system and explain its processing in natural language.

[0109] Data collection

[0110] The server periodically collects data from the restaurant's POS system. This collection is automated and can be set to retrieve a week's worth of sales data, weather data, event data, etc., every Monday at 2:00 AM. The specific hardware used is a POS system and a server. This allows data on past sales, seasonality, and customer preferences to be collected.

[0111] Data analysis and demand forecasting

[0112] The server preprocesses the collected data. Specifically, it removes outliers and fills in missing values. Then, it uses the generative AI model to make a demand forecast. Seasons and special events are taken into account when making demand forecasts. Specifically, the server detects and deletes or corrects abnormal data, and fills in missing data based on past trends. The following prompt statement is used to make a demand forecast for the generative AI model:

[0113] Example: "Based on the past three years of data, please predict demand for the third week of December."

[0114] Order quantity optimization

[0115] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. The specific hardware used is a database and calculation algorithms that run on the server. The calculation results are sent to the restaurant's terminal, where they can be viewed by the manager.

[0116] Best before date management

[0117] The server searches inventory data for ingredients with an approaching expiration date and lists them. This information is then sent to the restaurant's terminal as an alert notification. Specifically, the server queries the inventory database, identifies items with an approaching expiration date, generates an alert for the identified ingredients, and sends it to the terminal. The terminal displays a message saying, "The tomatoes are nearing their expiration date. Please use or sell them immediately."

[0118] Online sales

[0119] The server posts food items with approaching expiration dates on the online platform, making them available for purchase by users. Specifically, the server connects to the online platform's database, adds new product information, and lists the product's expiration date, price, quantity, etc. Users access the platform from their home PC or smartphone, select products, and complete the purchase process.

[0120] Cooking suggestions

[0121] The server suggests optimal cooking methods and recipes based on the purchased ingredients. Specifically, the server checks the purchase history, searches the database for corresponding recipes, and notifies the user of the found recipes. The user can then enjoy cooking using the suggested recipes as a reference.

[0122] In this way, this system enables efficient and accurate forecasting of food supply and demand and inventory management, allowing restaurants to reduce food waste and maximize profits. It also improves customer satisfaction by providing convenient and attractive services to users.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1:

[0125] The server periodically collects data from the restaurant's POS system. The input data is past sales data, seasonal data, and customer preference data. Specifically, the server sends an API request to the POS system to obtain sales data. The obtained data is stored in a database. The output is the collected data.

[0126] Step 2:

[0127] The server preprocesses the collected data. The input data are the sales data, seasonal data, and customer preference data collected in step 1. Specifically, the server detects anomalous data and deletes or corrects it. Missing data is complemented based on past trends. The output is the preprocessed data.

[0128] Step 3:

[0129] The server analyzes the preprocessed data and uses the generative AI model to make demand forecasts. The input data are preprocessed sales data, seasonal data, and customer preference data. Specifically, the server sends a prompt to the generative AI model to request a supply and demand forecast. For example, a prompt such as "Please predict demand for the third week of December based on data from the past three years" is used. The output is the demand forecast results.

[0130] Step 4:

[0131] The server calculates the optimal order quantity based on the demand forecast results. The input data is the demand forecast results, current inventory levels, and past order history. Specifically, the server calculates the optimal order quantity based on this data and sends the result to the restaurant's terminal. The output is a proposal for the optimal order quantity.

[0132] Step 5:

[0133] The server detects ingredients that are close to their expiration date from inventory data and manages the information. The input data is the current inventory data. Specifically, the server queries the inventory database to identify ingredients that are close to their expiration date. It generates an alert for the identified ingredients and sends it to the terminal. The terminal displays, "Tomatoes are close to their expiration date. Please use or sell them immediately." The output is an inventory alert.

[0134] Step 6:

[0135] The server posts food items with approaching expiration dates on an online platform so that users can purchase them. The input data is information about food items with approaching expiration dates. Specifically, the server connects to the online platform's database and adds new product information. Product information includes expiration dates, prices, quantities, etc. Users access the platform, select products, and complete the purchase process. The output is online sales information.

[0136] Step 7:

[0137] The server suggests optimal cooking methods and recipes based on purchased ingredients. The input data is the purchase history. Specifically, the server checks the purchase history and searches the database for corresponding recipes. It notifies the user of the recipes found, and the user can enjoy cooking using the suggested recipes as a reference. The output is cooking methods and recipe information.

[0138] (Application example 1)

[0139] 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."

[0140] Forecasting supply and demand and managing inventory for ingredients in restaurants is extremely complex, and if not done efficiently, food waste and shortages are likely to occur. Furthermore, inadequate management of ingredients with approaching expiration dates can lead to increased food waste. These issues are also common in delivery services, where efficient operation is essential, as it is particularly difficult to respond to fluctuations in demand.

[0141] 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.

[0142] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for analyzing the collected data and forecasting demand for ingredients, means for calculating optimal order quantities based on the forecast results, means for detecting ingredients with approaching expiration dates and managing information, means for selling the detected ingredients online, means for suggesting cooking methods for ingredients via an online platform, a smartphone application means for supporting demand forecasting and inventory management for food delivery services, and means for suggesting optimal recipes based on ingredients purchased by customers. This enables optimal ingredient demand forecasting and inventory management at restaurants and delivery services, reducing food waste and enabling efficient inventory management.

[0143] "Past sales data" refers to records of the quantity and value of products sold in the past by restaurants and delivery services.

[0144] "Seasonal data" is information about fluctuations in sales or demand during particular seasons or times of the year.

[0145] "Customer preference data" refers to data relating to a customer's purchasing history and preferences.

[0146] "Food demand forecast" is a calculation aimed at predicting future food consumption based on past data and current conditions.

[0147] The "optimal order quantity" is the appropriate order quantity of a specified ingredient based on predicted demand.

[0148] "Shorting shelf life ingredients" are ingredients that are approaching the date when they are suitable for use or consumption.

[0149] "Online sales" means trading goods over the Internet.

[0150] An "online platform" is a collection of basic infrastructure and services for providing products and services over the Internet.

[0151] "Suggesting a cooking method" means providing a dish and steps to make it using specific ingredients.

[0152] A "smartphone application" is application software that runs on a smartphone.

[0153] "Suggesting the best recipe based on the ingredients purchased by the customer" means providing cooking procedures and methods that are best suited to the ingredients acquired by the customer.

[0154] MODE FOR CARRYING OUT THE INVENTION

[0155] This invention is a system for optimizing food supply and demand forecasting and inventory management in restaurants and delivery services. This system consists of the following main components and processing steps:

[0156] Key Components

[0157] server

[0158] The server runs a program that includes the following means:

[0159] 1. Data collection methods:

[0160] The server periodically collects past sales data, seasonal data, and customer preference data from the POS systems of restaurants and delivery services. For example, it can be configured to collect a week's worth of data every Monday.

[0161] 2. Data analysis and demand forecasting tools:

[0162] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses a generative AI model (such as ChatGPT) to forecast demand. For example, it can predict that demand for chicken and cake ingredients will increase during the Christmas season in December.

[0163] 3. Measures to optimize order quantity:

[0164] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history.

[0165] 4. Best before date control measures:

[0166] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the terminals of restaurants and delivery services.

[0167] 5. Online sales channels:

[0168] The server places ingredients that are nearing their expiry date on an online platform for users to purchase.

[0169] 6. Suggested cooking methods for ingredients:

[0170] The server will suggest the best cooking method and recipe based on the ingredients purchased.

[0171] 7. Smartphone application means:

[0172] Users can access these functions through a smartphone application that forecasts food supply and demand, assists with inventory management, and also sells food that is nearing its expiration date and suggests cooking methods.

[0173] Specific examples

[0174] For example, the server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores this information in the database. At the same time, weather and event information for that day can also be collected.

[0175] The server then uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends ordering 1.2 times the amount of chicken ordered last year.

[0176] Regarding expiration date management, the server will detect from inventory information that the expiration date for tomatoes is October 15, 2023, and send an alert notification. The smartphone application will then display the message, "The expiration date for tomatoes is approaching. Please use or sell them immediately."

[0177] In the online sales example, a user can access the online platform from their smartphone at home and purchase tomatoes with a best-by date of October 10, 2023 at a discounted price. After completing the purchase process, a recipe for "Pasta with Tomato Sauce" is provided to the user through the app.

[0178] Prompt Sentence Examples

[0179] The following prompts can be used to provide input to the generative AI model:

[0180] Please use the following data to forecast supply and demand for the next week and calculate the optimal order quantity:

[0181] Sales data: 50 tomatoes, 30 lettuce, 20 chicken.

[0182] Current inventory: 30 tomatoes, 20 lettuces, 10 chicken.

[0183] Average sales data for the past three years: 45 tomatoes, 35 lettuce, 25 chicken.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The server collects historical sales data, seasonal data, and customer preference data from the POS system. This data is collected periodically by the server and stored in a database. Inputs include sales data (e.g., Dish A: 50 units, Dish B: 30 units), weather information, event information, etc. As an output, an organized dataset is stored in the database.

[0187] Step 2:

[0188] The server preprocesses the collected data, removing outliers and imputing missing values. It uses data analysis software to remove inaccurate data from the input dataset and impute missing values. The output is a clean dataset. Specific operations include identifying and removing outlier data points and imputing missing values ​​using the mean or median.

[0189] Step 3:

[0190] The server uses a generative AI model based on the preprocessed data to make demand forecasts, taking into account weekends, holidays, seasonal events, etc. Past sales data, seasonal data, and customer preference data are used as input. The output is the predicted demand volume. Specific operations involve entering a prompt into ChatGPT and receiving the prediction results. For example, the prediction result may be, "Demand for chicken will increase by 20% year-on-year in the third week of December."

[0191] Step 4:

[0192] The server calculates the optimal order quantity based on the demand forecast. At this time, it also takes into account the current inventory level and past order history. The inputs are the predicted demand, current inventory level, and past order history. The output is the specific order quantity. The specific operation is to calculate the optimal order quantity using a calculation algorithm. For example, the result may be, "We suggest ordering 1.2 times the previous year's order quantity for chicken."

[0193] Step 5:

[0194] The server searches through inventory data for ingredients with upcoming expiration dates and lists them. The inputs are inventory data and expiration date data. The output is a list of ingredients with upcoming expiration dates. Specifically, it checks the expiration date of each ingredient and identifies ingredients whose expiration date is within one week. For example, it obtains information such as "the expiration date of tomatoes is October 15, 2023."

[0195] Step 6:

[0196] The server posts ingredients with upcoming expiration dates on an online platform, allowing users to purchase them. The input is a list of ingredients with upcoming expiration dates. The output is the item information posted on the online platform. Specific operations include uploading information about each ingredient to an online database and making it accessible to users. For example, the server may post information such as "Tomatoes available at a discount."

[0197] Step 7:

[0198] Based on the purchased ingredients, the server suggests the most suitable cooking method and recipe. The information on the purchased ingredients is used as input. The recipe information is provided to the user as output. Specifically, the server searches for the most suitable recipe from a pre-registered recipe database based on the purchased ingredients and notifies the user of the recipe. For example, it suggests a recipe such as "pasta with tomato sauce."

[0199] 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.

[0200] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, reducing food waste, and providing more personalized service by recognizing user emotions. Below, we will create a system program and explain its processing in natural language.

[0201] Main component description

[0202] Data collection

[0203] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. For example, it can be configured to retrieve a week's worth of sales data every Monday. This data collection is performed automatically through an API.

[0204] Data analysis and demand forecasting

[0205] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT to generate demand forecasts that take into account weekends, holidays, and seasonal events. For example, it can predict increased demand for chicken and cake ingredients during the Christmas season in December.

[0206] Order quantity optimization

[0207] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. Based on the calculation results, the server then sends an ordering proposal to the restaurant's terminal, where it can be reviewed by the manager.

[0208] Best before date management

[0209] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the restaurant's terminal.

[0210] Online sales

[0211] The server posts food items that are close to their expiration date on the online platform, allowing users to purchase them. For example, users can access the platform from their home PC or smartphone and purchase tomatoes or lettuce that are close to their expiration date.

[0212] Cooking suggestions

[0213] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, the server will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0214] Introducing the Emotion Engine

[0215] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if the user gave feedback indicating dissatisfaction with their previous order, the emotion engine will take that into consideration and suggest products that will provide greater satisfaction the next time.

[0216] Specific examples

[0217] Data Collection Example

[0218] The server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores it in the database. At the same time, it can also collect information about the weather and events that day.

[0219] Demand forecast example

[0220] The server uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends that restaurants order 1.2 times the amount of chicken they ordered last year.

[0221] Example of expiration date management

[0222] The server detects from inventory information that the expiration date for the tomatoes is October 15, 2023, and sends an alert notification.The restaurant's terminal then displays an alert saying, "The expiration date for the tomatoes is approaching. Please use or sell them immediately."

[0223] Online sales example

[0224] A user accesses the online platform from their home PC and purchases tomatoes with a best-by date of October 10, 2023 at a discounted price. After the purchase procedure is completed, the server sends the user a recipe for "Pasta with Tomato Sauce."

[0225] Example of using the emotion engine

[0226] If a user previously ordered pasta with tomato sauce and gave feedback that it was "bland," the emotion engine would analyze that feedback and suggest a recipe for "pasta with spicy tomato sauce" the next time the user buys tomatoes, thereby improving user satisfaction.

[0227] In this way, this invention not only optimizes food supply and demand forecasts and inventory management, reduces waste, and maximizes profits, but also provides personalized services that take into account user emotions. Therefore, the invention not only significantly improves the management efficiency of restaurants, but also increases customer satisfaction.

[0228] The processing flow will be explained below.

[0229] Step 1:

[0230] The server periodically accesses the POS system to collect past sales data, seasonal data, and customer preference data. For example, you can set it to retrieve a week's worth of sales data every Monday. The data is then automatically collected via API.

[0231] Step 2:

[0232] The server converts the format of the acquired data and stores it in a database. Data conversion involves standardizing dates, categorizing data, filling in missing values, and removing outliers. For example, data with zero or negative sales volume is filtered out.

[0233] Step 3:

[0234] The server retrieves the saved data from the database and performs pre-processing for analysis. Here, sales figures are aggregated daily, weekly, and monthly, and formatted into a form suitable for analysis. For example, the sales figures for a specific product can be aggregated for each day of the week.

[0235] Step 4:

[0236] The server uses ChatGPT to analyze the collected data and predict demand for the next month. Forecasts are based on past sales patterns, seasonal data, and campaign information. For example, it predicts that demand for chicken will increase by 20% year-on-year during the Christmas season in December.

[0237] Step 5:

[0238] The server calculates the optimal order quantity based on the forecast results. It also takes into account current inventory and past order history to calculate the required additional order quantity. For example, if there are 50 chickens in stock and the forecast demand is 80, an additional 30 units will need to be ordered.

[0239] Step 6:

[0240] The server then sends the calculated ordering suggestions to the restaurant's administrator's terminal, which displays the specific order quantity and recommended ordering time, allowing the administrator to proceed with the ordering process based on that information.

[0241] Step 7:

[0242] The server periodically checks inventory data to identify ingredients that are close to their expiration date. For example, it detects ingredients that are within a week of their expiration date and generates a list of them.

[0243] Step 8:

[0244] The server sends alerts to restaurant terminals about ingredients that are nearing their expiration date. The terminals display a message saying, "The tomatoes are nearing their expiration date. Please use or sell them as soon as possible." The administrator can then take prompt action based on this information.

[0245] Step 9:

[0246] The server posts food items that are close to their expiration date on the online platform. Users can access the platform from their home PC or smartphone and purchase the food items. For example, users can purchase tomatoes that are close to their expiration date at a discounted price.

[0247] Step 10:

[0248] A user purchases ingredients through the online platform. Once the purchase is complete, the server records the information in a database and sends the user a purchase confirmation email.

[0249] Step 11:

[0250] The server provides appropriate cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, it generates a recipe for "pasta with tomato sauce" and sends it by email.

[0251] Step 12:

[0252] The server uses an emotion engine to analyze the user's past purchase history and feedback. For example, if the user gave feedback that they were dissatisfied with their previous order, the emotion engine will take that into account the next time and suggest products or recipes that will be more satisfying.

[0253] Step 13:

[0254] The server provides services according to the user's emotional state based on the results of the emotion engine's analysis. If the user's feedback last time was that the tomato sauce pasta was "bland," the server will suggest a recipe for "spicy tomato sauce pasta" next time. This will improve user satisfaction.

[0255] In this way, the system can optimize supply and demand forecasts and inventory management throughout a series of processing steps, reducing food waste and maximizing profits, as well as providing personalized service that takes user emotions into account.

[0256] Example 2

[0257] 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."

[0258] It is important for restaurants to forecast food supply and demand and manage inventory more efficiently to reduce food waste. Another challenge is to improve customer satisfaction by recognizing user emotions and providing personalized services. Conventional systems have difficulty meeting these multifaceted requirements, so a new system that can solve these challenges is needed.

[0259] The identification processing 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 past data, means for preprocessing the collected data, means for analyzing the preprocessed data and predicting demand for ingredients, means for calculating optimal order quantities based on the prediction results, means for detecting ingredients that are close to their expiration date and issuing alerts, means for selling the detected ingredients online, means for suggesting cooking methods for the ingredients via an online platform, and means for analyzing users' past purchase histories and feedback and providing personalized services. This enables optimization of ingredient supply and demand predictions and inventory management, reducing ingredient waste and improving customer satisfaction.

[0260] "Past data" refers to information accumulated in the past, such as a restaurant's sales history, seasonal data, and customer preference data.

[0261] "Means of collection" refers to a device or system that automatically acquires the necessary data using APIs, sensors, etc.

[0262] A "preprocessing means" is a device or system that removes outliers and fills in missing values ​​in order to convert data into a format that is easier to analyze.

[0263] "Means of analysis" refers to algorithms and software that predict future demand, etc. based on collected and preprocessed data.

[0264] A "demand forecasting means" is a device or system that forecasts the demand for food ingredients at a specific time based on collected data.

[0265] The "means for calculating the optimal order quantity" refers to an algorithm or device that calculates the effective order quantity based on the demand forecast results and the current inventory status.

[0266] The "means for detecting food ingredients approaching their expiration date and issuing an alert notification" is a system that identifies products approaching their expiration date from inventory data and issues a warning to the administrator.

[0267] The "means for selling detected food ingredients online" is a system that posts food ingredients that are close to their expiration date on an internet platform, allowing users to purchase them.

[0268] The "means for suggesting cooking methods" is a device or system for providing users with optimal cooking methods and recipes based on specific ingredients.

[0269] "Means of analyzing past purchase history and feedback to provide personalized services" refers to a system that analyzes a user's preferences and emotions based on the purchases and feedback information they have made to date, and makes personalized suggestions.

[0270] This invention is a system for optimizing food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. It also aims to recognize user emotions and provide personalized services. A specific embodiment of the system is described below.

[0271] Data collection

[0272] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. This data is automatically retrieved through an API. For example, it can be configured to retrieve a week's worth of sales data every Monday. After collecting this data, the server stores the necessary information in a database.

[0273] Data Preprocessing

[0274] The collected data is preprocessed by the server. Data cleaning is performed, such as removing outliers and filling in missing values. Specifically, outliers are removed from the collected sales data, and missing data is filled in appropriately.

[0275] Demand forecasting

[0276] The server uses a generative AI model (e.g., ChatGPT) to forecast demand based on the preprocessed data. For example, the server uses data from the past three years to predict that demand for chicken will increase by 20% year-on-year in the third week of December. This forecast result is stored in a database and used in the next step.

[0277] Order quantity optimization

[0278] The server calculates the optimal order quantity based on the demand forecast results and current inventory information. For example, if the forecasted demand is expected to increase by 20% compared to the previous year, it will suggest ordering 1.2 times the previous year's amount. This suggestion is sent to the restaurant's terminal and can be confirmed by the manager.

[0279] Best before date management

[0280] The server searches inventory data for ingredients with upcoming expiration dates and lists them. For example, it might identify that tomatoes have an expiration date of October 15, 2023, and send an alert to the restaurant's terminal saying, "The expiration date of the tomatoes is approaching. Please use or sell them immediately."

[0281] Online sales

[0282] The server posts food items with upcoming expiration dates on the online platform, allowing users to purchase them. For example, a user can access the online platform from their home PC or smartphone and purchase tomatoes with an expiration date of October 10, 2023, at a discounted price.

[0283] Cooking suggestions

[0284] The server suggests the best cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, it will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0285] Introducing the Emotion Engine

[0286] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if a user previously ordered pasta with tomato sauce and gave feedback that it was "bland," the emotion engine would analyze that feedback and suggest a recipe for "pasta with spicy tomato sauce" the next time the user purchases tomatoes. This can improve user satisfaction.

[0287] Prompt Sentence Examples

[0288] Demand forecast prompt

[0289] "Using sales data from the past three years, please forecast the demand for chicken for the third week of December. Based on that, please propose an order quantity that is 1.2 times the previous year's order quantity."

[0290] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0291] Step 1: Data collection

[0292] The server automatically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system using an API. For example, you can set it to retrieve a week's worth of sales data every Monday and store data such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units" in a database. In this case, the input data is sales information from the POS system, and the output is the sales data stored in the database.

[0293] Step 2: Data Preprocessing

[0294] The server preprocesses the collected data. Specifically, it removes outliers and fills in missing values. For example, if sales data contains abnormal values ​​(outliers), it removes them and fills in missing data by inferring it from other data. The input in this step is the collected raw data, and the output is preprocessed, clean data.

[0295] Step 3: Demand forecast

[0296] The server uses a generative AI model (for example, ChatGPT) to make a demand forecast based on the preprocessed data. The prompt text input to the generative AI model is, "Using sales data from the past three years, please predict the demand for chicken in the third week of December. Also, based on that, please suggest an order quantity that is 1.2 times the previous year's order quantity." This results in a prediction that demand for chicken in the third week of December will increase by 20% compared to the previous year. This prediction result is saved in a database.

[0297] Step 4: Optimize order quantity

[0298] The server calculates the optimal order quantity based on the demand forecast results and current inventory information. For example, based on a forecasted demand increase of 20% compared to the previous year, it calculates 1.2 times the order quantity from the previous year and proposes a new order quantity. The inputs in this step are the demand forecast results and inventory data, and the outputs are the calculated order quantity and its proposed order.

[0299] Step 5: Submitting an order proposal

[0300] The server sends an ordering proposal based on the calculation results to the restaurant's terminal. The administrator checks the ordering proposal on the terminal and approves or modifies it as necessary. The input in this step is the optimized order quantity, and the output is the ordering proposal displayed on the restaurant's terminal.

[0301] Step 6: Best before date management

[0302] The server searches through inventory data for ingredients with upcoming expiration dates and lists them. For example, it identifies that "the expiration date for tomatoes is October 15, 2023," and based on that information, it sends an alert notification to the restaurant's terminal saying, "The expiration date for tomatoes is approaching. Please use or sell them immediately." The input in this step is inventory data, and the output is an alert notification displayed on the terminal.

[0303] Step 7: Sell online

[0304] The server posts food items with an approaching expiration date on an online platform. Users can access the online platform from their home PC or smartphone and purchase tomatoes with an expiration date of October 10, 2023 at a discounted price. The input in this step is information about food items with an approaching expiration date, and the output is the information posted on the online platform.

[0305] Step 8: Cooking suggestions

[0306] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if the user purchases tomatoes, it will provide recipes such as pasta with tomato sauce or Caprese. The input in this step is the purchased ingredients, and the output is the recipe information provided to the user.

[0307] Step 9: Implementing the Emotion Engine

[0308] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if a user previously ordered pasta with tomato sauce and provided feedback that it was "bland," the emotion engine analyzes that feedback and suggests a recipe for "pasta with spicy tomato sauce" the next time the user purchases tomatoes. The input in this step is the user's past purchase history and feedback information, and the output is personalized service suggestions.

[0309] (Application example 2)

[0310] 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."

[0311] Conventional restaurant supply and demand forecasting and inventory management systems make it difficult to reduce food waste and are unable to provide personalized service to customers. Furthermore, because services are provided without taking into account customer emotions, it is not possible to increase customer satisfaction.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0313] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for analyzing the collected data and forecasting demand for ingredients, means for calculating optimal order quantities based on the forecast results, means for detecting ingredients with approaching expiration dates and managing information, means for selling the detected ingredients online, means for suggesting cooking methods for the ingredients via an online platform, and means for collecting emotion data and providing personalized services based on the user's emotions, thereby making it possible to reduce food waste and provide personalized services to users.

[0314] "Past sales data" refers to the sales performance of products recorded in the past by a restaurant, and includes details such as the specific sales quantity and the date and time of the sales.

[0315] "Seasonal data" refers to sales data or data that shows consumer behavior patterns that fluctuate based on specific seasons or events.

[0316] "Customer preference data" is data that represents the tendencies of individual customers, such as their purchase history, ratings, and favorite dishes and ingredients.

[0317] "Emotional data" is data that indicates customer emotions and reactions, extracted from feedback, reviews, etc. provided by customers.

[0318] "Supply and demand forecasting" is the process of predicting future demand for ingredients and products based on collected data.

[0319] The "optimal order quantity" is an efficient and appropriate order quantity calculated based on supply and demand forecast data to prevent unnecessary inventory and stockouts.

[0320] The "best before" date refers to the period during which the quality of ingredients or products can be maintained, and after this period the value of the product may decrease.

[0321] "Online sales" refers to the general process of selling goods over the Internet, allowing customers to purchase goods from the comfort of their own home or remotely.

[0322] "Cooking suggestions" is the process of providing recipes and cooking procedures that will make the most delicious and efficient use of purchased ingredients.

[0323] "Personalized service" refers to a service that provides optimal products and services to individual customers based on their characteristics, preferences, and emotions.

[0324] The present invention is a system that optimizes food supply and demand forecasts and inventory management in restaurants, reducing food waste and providing more personalized services by recognizing user emotions. A detailed description of the system that realizes this application example is provided below.

[0325] The system has a means for the server to collect historical sales data, seasonal data, and customer preference data. This data collection is done periodically, for example, every Monday, by obtaining a week's worth of sales data from the POS system via an API.

[0326] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT, a generative AI model, to forecast supply and demand based on this data. For example, based on past sales data and seasonality data, it can predict that demand for chicken in the third week of December will increase by 20% compared to the previous year.

[0327] Based on the results of the supply and demand forecast, the server calculates the optimal order quantity. Here, it also takes into account current inventory levels and past order history to determine the necessary order quantity. The ordering proposal is sent to the restaurant's terminal so that the manager can check it.

[0328] Furthermore, the server has a means of detecting food ingredients that are close to their expiration date. Based on inventory data, if there are tomatoes with an expiration date of less than a week, for example, it sends an alert to the terminal saying, "The expiration date of the tomatoes is approaching. Please use or sell them immediately."

[0329] Food items that are close to their expiration date are sold online. Users can access the online platform using their PC or smartphone and purchase food items that are close to their expiration date at a discounted price.

[0330] The server also suggests optimal cooking methods and recipes based on the ingredients purchased. For example, if a user purchases tomatoes, it will suggest recipes such as "pasta with tomato sauce" and "caprese."

[0331] Emotional data is also utilized. The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, allowing it to provide services that reflect the user's emotions. For example, if a user gives feedback that their last order was "bland," the server can suggest a recipe for "pasta with spicy tomato sauce" for the next order.

[0332] In this way, the system of the present invention not only optimizes food supply and demand forecasts and inventory management, reducing food waste, but also significantly improves the management efficiency of restaurants by providing personalized services to users. Furthermore, it is possible to improve customer satisfaction by making suggestions using emotion data.

[0333] An example prompt could be, "Based on your past feedback and purchase history, what improvements or new suggestions would you consider making a purchase with us again?"

[0334] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0335] Step 1:

[0336] The server collects past sales data, seasonal data, and customer preference data from the POS system via API. The input is the POS system's API endpoint, and the output is the collected dataset. A specific example of data collection is to obtain a week's worth of sales data every Monday and store it in a database.

[0337] Step 2:

[0338] The server preprocesses the collected data, removing outliers and filling in missing values ​​to prepare the data for analysis. The input is the collected dataset, and the output is the preprocessed dataset. Specifically, it uses the Python pandas library to fill in missing values ​​with the mean and exclude clearly erroneous data.

[0339] Step 3:

[0340] The server uses a generative AI model (ChatGPT) to perform supply and demand forecasts using the preprocessed data. The input is the preprocessed dataset, and the output is the prediction results. Specifically, it sends prompts to ChatGPT to perform demand forecasts. For example, it sends a prompt such as, "What is the demand for chicken in the third week of December?"

[0341] Step 4:

[0342] The server calculates the optimal order quantity based on the forecast results. The inputs are the supply and demand forecast results, current inventory data, and past order history, and the output is the optimal order quantity. Specifically, the server uses an algorithm to calculate the most efficient order quantity, taking into account inventory levels and past order history.

[0343] Step 5:

[0344] The server detects ingredients that are close to their expiration date and manages the information. The input is inventory data, and the output is a list of ingredients that are close to their expiration date. For example, the server detects from the inventory data that "the expiration date for tomatoes is October 15, 2023" and lists that information.

[0345] Step 6:

[0346] The terminal notifies inventory alerts for ingredients that are nearing their expiration date. The input is a list of ingredients that are nearing their expiration date, and the output is an alert notification. Specifically, the terminal displays an alert saying, "The tomatoes are nearing their expiration date. Please use or sell them immediately."

[0347] Step 7:

[0348] The server sells food items with an approaching expiration date on an online platform. The input is a list of food items with an approaching expiration date, and the output is a sales page for the online shop. Specifically, the server automatically posts information about food items with an approaching expiration date on the online platform.

[0349] Step 8:

[0350] A user purchases ingredients at a discounted price through an online platform. The input is the customer's order information from the online shop, and the output is a notification that the purchase has been completed. Specifically, the user selects ingredients and completes the purchase procedure using a smartphone or PC.

[0351] Step 9:

[0352] The server provides cooking methods and recipes based on purchased ingredients. The input is information about the purchased ingredients, and the output is a suggested recipe. For example, if a user purchases tomatoes, the server generates a recipe for "pasta with tomato sauce" and sends it to the user.

[0353] Step 10:

[0354] The server analyzes the emotional data and provides personalized services based on the user's emotions. The input is the user's feedback and purchase history, and the output is personalized service suggestions. Specifically, the system analyzes the feedback using an emotion engine and suggests a recipe, for example, "pasta with spicy tomato sauce."

[0355] Step 11:

[0356] The user enjoys cooking using the suggested recipes and cooking methods. The input is the suggested recipe and cooking method, and the output is the finished dish. Specific operations involve cooking by following the instructions on the smart glasses and the voice assistant.

[0357] 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.

[0358] 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.

[0359] 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.

[0360] [Second embodiment]

[0361] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0362] 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.

[0363] 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).

[0364] 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.

[0365] 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.

[0366] 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).

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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.

[0372] 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."

[0373] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. Below, we will create a program for the system and explain its processing in natural language.

[0374] Main component description

[0375] Data collection

[0376] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. For example, it can be configured to collect a week's worth of data every Monday.

[0377] Data analysis and demand forecasting

[0378] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT to generate demand forecasts that take into account weekends, holidays, and seasonal events. For example, it can predict increased demand for chicken and cake ingredients during the Christmas season in December.

[0379] Order quantity optimization

[0380] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. Based on the calculation results, the server then sends an ordering proposal to the restaurant's terminal, where it can be checked by the manager.

[0381] Best before date management

[0382] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the restaurant's terminal.

[0383] Online sales

[0384] The server posts food items that are close to their expiration date on the online platform, allowing users to purchase them. For example, users can access the platform from their home PC or smartphone and purchase tomatoes or lettuce that are close to their expiration date.

[0385] Cooking suggestions

[0386] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, the server will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0387] Specific examples

[0388] Data Collection Example

[0389] The server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores it in the database. At the same time, it can also collect information about the weather and events that day.

[0390] Demand forecast example

[0391] The server uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends that restaurants order 1.2 times the amount of chicken they ordered last year.

[0392] Example of expiration date management

[0393] The server detects from inventory information that the expiration date for the tomatoes is October 15, 2023, and sends an alert notification.The restaurant's terminal then displays an alert saying, "The expiration date for the tomatoes is approaching. Please use or sell them immediately."

[0394] Online sales example

[0395] A user accesses the online platform from their home PC and purchases tomatoes with a best-by date of October 10, 2023 at a discounted price. After the purchase procedure is completed, the server sends the user a recipe for "Pasta with Tomato Sauce."

[0396] In this way, this invention optimizes food supply and demand forecasts and inventory management, reduces waste, and maximizes profits. This invention significantly improves the management efficiency of restaurants and also provides convenient and attractive services to customers.

[0397] The processing flow will be explained below.

[0398] Step 1:

[0399] The server periodically accesses the restaurant's POS system to collect past sales data, seasonal data, and customer preference data. For example, it can be set to retrieve a week's worth of sales data every Monday. This data collection is performed automatically through the API.

[0400] Step 2:

[0401] The server converts and formats the data before storing it in the database. This includes filling in missing values ​​and removing outliers. For example, it filters out data with zero sales volume or other obviously abnormal values.

[0402] Step 3:

[0403] The server stores the formatted data in a database. The stored data includes product name, sales quantity, sales date, and customer attributes (age, gender, etc.). For example, sales data and customer information for October 1, 2023 are recorded in the corresponding tables in the database.

[0404] Step 4:

[0405] The server retrieves historical sales data, seasonal data, and customer preference data from the database. This is a pre-processing step for demand forecasting. The retrieved data covers a certain period (e.g., the past three years).

[0406] Step 5:

[0407] The server preprocesses the data it receives. Specifically, it normalizes and standardizes the data to make it suitable for analysis. For example, it converts sales volume into average values ​​for each week or month.

[0408] Step 6:

[0409] The server analyzes the data using ChatGPT to predict future demand, taking into account seasonality and the influence of specific events (e.g., Christmas and Valentine's Day). The forecast results are output as numerical data for further processing.

[0410] Step 7:

[0411] The server calculates the optimal order quantity based on the forecast results, taking into account current inventory levels and past order history. For example, if demand for chicken is predicted, it compares it with current inventory and calculates the required additional order quantity.

[0412] Step 8:

[0413] The server generates an ordering proposal based on the calculation results and sends a notification to the restaurant's administrator's terminal. The notification includes the specific order quantity and the recommended ordering time. The administrator places the order based on this information.

[0414] Step 9:

[0415] The server identifies ingredients that are close to expiry based on current inventory data. For example, it lists ingredients that are within a week of expiry. This process is important for efficient inventory management.

[0416] Step 10:

[0417] The server sends alerts to restaurant terminals about ingredients that are nearing their expiration date. The notifications include a list of ingredients that need to be used or sold immediately. The administrator can then take appropriate action based on this information.

[0418] Step 11:

[0419] The server posts food items that are nearing their expiration date on an online platform. Users can access the platform from their PCs or smartphones to check and purchase these food items. For example, users can view information about tomatoes and lettuce that are available at discounted prices.

[0420] Step 12:

[0421] A user purchases ingredients through the online platform, and once the purchase is complete, the server records the information in a database and sends a confirmation email to the purchaser.

[0422] Step 13:

[0423] The server generates appropriate cooking methods and recipes based on the purchased ingredients and provides them to the user. For example, if a user purchases tomatoes, the server sends a recipe for "pasta with tomato sauce" to the user for cooking reference.

[0424] In this way, the system optimizes food supply and demand forecasts and inventory management throughout a series of processing steps, reducing food waste and maximizing profits.

[0425] Example 1

[0426] 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."

[0427] In restaurants, predicting supply and demand for ingredients and managing inventory is labor-intensive and difficult to do efficiently. Inaccurate predictions can lead to shortages or surpluses of ingredients, resulting in economic losses and increased waste. Furthermore, there is a lack of mechanisms for managing ingredients approaching their expiration date or for encouraging their consumption at the appropriate time. The objective of this invention is to provide a system that solves these problems and achieves optimal supply and demand prediction and inventory management.

[0428] 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.

[0429] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for preprocessing the collected data to remove outliers and impute missing values, means for analyzing the collected data and using a generative AI model to predict demand for ingredients, means for calculating optimal order quantities based on the prediction results, means for detecting ingredients with approaching expiration dates and managing information, means for listing the detected ingredients on an online platform so that users can purchase them, and means for suggesting cooking methods for the ingredients via the online platform.This enables restaurants to efficiently and accurately predict supply and demand and manage inventory, thereby reducing food waste and maximizing profits.

[0430] "Past sales data" refers to data that records the past sales performance of a restaurant.

[0431] "Seasonal data" is data relating to a particular season, time of year, or event, such as fluctuations in demand for a particular product during a particular season.

[0432] "Customer preference data" refers to data related to a customer's purchasing behavior and preferences. For example, it includes information about a customer's favorite dishes and frequently purchased products.

[0433] "Collection means" refers to the methods and devices used to acquire and store data.

[0434] "Preprocessing" is a data cleansing process that removes outliers from collected data and fills in missing values.

[0435] An "outlier" is a value in the data that is significantly different from the other data.

[0436] "Missing values" are pieces of data that are missing or incomplete.

[0437] A "generative AI model" is a type of artificial intelligence model that learns patterns from large amounts of data and makes predictions and classifications. Specifically, this applies to models that use machine learning or deep learning.

[0438] "Order quantity" refers to the amount of ingredients purchased by a restaurant.

[0439] "Best before date" refers to the date by which food ingredients can be consumed while still maintaining their quality.

[0440] An "online platform" is a service or application provided over the Internet.

[0441] An "alert" is a warning or caution mechanism that notifies you when certain conditions are met.

[0442] "Cooking method" refers to the steps and recipes for processing and cooking ingredients.

[0443] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. Below, we will create a program for this system and explain its processing in natural language.

[0444] Data collection

[0445] The server periodically collects data from the restaurant's POS system. This collection is automated and can be set to retrieve a week's worth of sales data, weather data, event data, etc., every Monday at 2:00 AM. The specific hardware used is a POS system and a server. This allows data on past sales, seasonality, and customer preferences to be collected.

[0446] Data analysis and demand forecasting

[0447] The server preprocesses the collected data. Specifically, it removes outliers and fills in missing values. Then, it uses the generative AI model to make a demand forecast. Seasons and special events are taken into account when making demand forecasts. Specifically, the server detects and deletes or corrects abnormal data, and fills in missing data based on past trends. The following prompt statement is used to make a demand forecast for the generative AI model:

[0448] Example: "Based on the past three years of data, please predict demand for the third week of December."

[0449] Order quantity optimization

[0450] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. The specific hardware used is a database and calculation algorithms that run on the server. The calculation results are sent to the restaurant's terminal, where they can be viewed by the manager.

[0451] Best before date management

[0452] The server searches inventory data for ingredients with an approaching expiration date and lists them. This information is then sent to the restaurant's terminal as an alert notification. Specifically, the server queries the inventory database, identifies items with an approaching expiration date, generates an alert for the identified ingredients, and sends it to the terminal. The terminal displays a message saying, "The tomatoes are nearing their expiration date. Please use or sell them immediately."

[0453] Online sales

[0454] The server posts food items with approaching expiration dates on the online platform, making them available for purchase by users. Specifically, the server connects to the online platform's database, adds new product information, and lists the product's expiration date, price, quantity, etc. Users access the platform from their home PC or smartphone, select products, and complete the purchase process.

[0455] Cooking suggestions

[0456] The server suggests optimal cooking methods and recipes based on the purchased ingredients. Specifically, the server checks the purchase history, searches the database for corresponding recipes, and notifies the user of the found recipes. The user can then enjoy cooking using the suggested recipes as a reference.

[0457] In this way, this system enables efficient and accurate forecasting of food supply and demand and inventory management, allowing restaurants to reduce food waste and maximize profits. It also improves customer satisfaction by providing convenient and attractive services to users.

[0458] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0459] Step 1:

[0460] The server periodically collects data from the restaurant's POS system. The input data is past sales data, seasonal data, and customer preference data. Specifically, the server sends an API request to the POS system to obtain sales data. The obtained data is stored in a database. The output is the collected data.

[0461] Step 2:

[0462] The server preprocesses the collected data. The input data are the sales data, seasonal data, and customer preference data collected in step 1. Specifically, the server detects anomalous data and deletes or corrects it. Missing data is complemented based on past trends. The output is the preprocessed data.

[0463] Step 3:

[0464] The server analyzes the preprocessed data and uses the generative AI model to make demand forecasts. The input data are preprocessed sales data, seasonal data, and customer preference data. Specifically, the server sends a prompt to the generative AI model to request a supply and demand forecast. For example, a prompt such as "Please predict demand for the third week of December based on data from the past three years" is used. The output is the demand forecast results.

[0465] Step 4:

[0466] The server calculates the optimal order quantity based on the demand forecast results. The input data is the demand forecast results, current inventory levels, and past order history. Specifically, the server calculates the optimal order quantity based on this data and sends the result to the restaurant's terminal. The output is a proposal for the optimal order quantity.

[0467] Step 5:

[0468] The server detects ingredients that are close to their expiration date from inventory data and manages the information. The input data is the current inventory data. Specifically, the server queries the inventory database to identify ingredients that are close to their expiration date. It generates an alert for the identified ingredients and sends it to the terminal. The terminal displays, "Tomatoes are close to their expiration date. Please use or sell them immediately." The output is an inventory alert.

[0469] Step 6:

[0470] The server posts food items with approaching expiration dates on an online platform so that users can purchase them. The input data is information about food items with approaching expiration dates. Specifically, the server connects to the online platform's database and adds new product information. Product information includes expiration dates, prices, quantities, etc. Users access the platform, select products, and complete the purchase process. The output is online sales information.

[0471] Step 7:

[0472] The server suggests optimal cooking methods and recipes based on purchased ingredients. The input data is the purchase history. Specifically, the server checks the purchase history and searches the database for corresponding recipes. It notifies the user of the recipes found, and the user can enjoy cooking using the suggested recipes as a reference. The output is cooking methods and recipe information.

[0473] (Application example 1)

[0474] 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."

[0475] Forecasting supply and demand and managing inventory for ingredients in restaurants is extremely complex, and if not done efficiently, food waste and shortages are likely to occur. Furthermore, inadequate management of ingredients with approaching expiration dates can lead to increased food waste. These issues are also common in delivery services, where efficient operation is essential, as it is particularly difficult to respond to fluctuations in demand.

[0476] 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.

[0477] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for analyzing the collected data and forecasting demand for ingredients, means for calculating optimal order quantities based on the forecast results, means for detecting ingredients with approaching expiration dates and managing information, means for selling the detected ingredients online, means for suggesting cooking methods for ingredients via an online platform, a smartphone application means for supporting demand forecasting and inventory management for food delivery services, and means for suggesting optimal recipes based on ingredients purchased by customers. This enables optimal ingredient demand forecasting and inventory management at restaurants and delivery services, reducing food waste and enabling efficient inventory management.

[0478] "Past sales data" refers to records of the quantity and value of products sold in the past by restaurants and delivery services.

[0479] "Seasonal data" is information about fluctuations in sales or demand during particular seasons or times of the year.

[0480] "Customer preference data" refers to data relating to a customer's purchasing history and preferences.

[0481] "Food demand forecast" is a calculation aimed at predicting future food consumption based on past data and current conditions.

[0482] The "optimal order quantity" is the appropriate order quantity of a specified ingredient based on predicted demand.

[0483] "Shorting shelf life ingredients" are ingredients that are approaching the date when they are suitable for use or consumption.

[0484] "Online sales" means trading goods over the Internet.

[0485] An "online platform" is a collection of basic infrastructure and services for providing products and services over the Internet.

[0486] "Suggesting a cooking method" means providing a dish and steps to make it using specific ingredients.

[0487] A "smartphone application" is application software that runs on a smartphone.

[0488] "Suggesting the best recipe based on the ingredients purchased by the customer" means providing cooking procedures and methods that are best suited to the ingredients acquired by the customer.

[0489] MODE FOR CARRYING OUT THE INVENTION

[0490] This invention is a system for optimizing food supply and demand forecasting and inventory management in restaurants and delivery services. This system consists of the following main components and processing steps:

[0491] Key Components

[0492] server

[0493] The server runs a program that includes the following means:

[0494] 1. Data collection methods:

[0495] The server periodically collects past sales data, seasonal data, and customer preference data from the POS systems of restaurants and delivery services. For example, it can be configured to collect a week's worth of data every Monday.

[0496] 2. Data analysis and demand forecasting tools:

[0497] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses a generative AI model (such as ChatGPT) to forecast demand. For example, it can predict that demand for chicken and cake ingredients will increase during the Christmas season in December.

[0498] 3. Measures to optimize order quantity:

[0499] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history.

[0500] 4. Best before date control measures:

[0501] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the terminals of restaurants and delivery services.

[0502] 5. Online sales channels:

[0503] The server places ingredients that are nearing their expiry date on an online platform for users to purchase.

[0504] 6. Suggested cooking methods for ingredients:

[0505] The server will suggest the best cooking method and recipe based on the ingredients purchased.

[0506] 7. Smartphone application means:

[0507] Users can access these functions through a smartphone application that forecasts food supply and demand, assists with inventory management, and also sells food that is nearing its expiration date and suggests cooking methods.

[0508] Specific examples

[0509] For example, the server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores this information in the database. At the same time, weather and event information for that day can also be collected.

[0510] The server then uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends ordering 1.2 times the amount of chicken ordered last year.

[0511] Regarding expiration date management, the server will detect from inventory information that the expiration date for tomatoes is October 15, 2023, and send an alert notification. The smartphone application will then display the message, "The expiration date for tomatoes is approaching. Please use or sell them immediately."

[0512] In the online sales example, a user can access the online platform from their smartphone at home and purchase tomatoes with a best-by date of October 10, 2023 at a discounted price. After completing the purchase process, a recipe for "Pasta with Tomato Sauce" is provided to the user through the app.

[0513] Prompt Sentence Examples

[0514] The following prompts can be used to provide input to the generative AI model:

[0515] Please use the following data to forecast supply and demand for the next week and calculate the optimal order quantity:

[0516] Sales data: 50 tomatoes, 30 lettuce, 20 chicken.

[0517] Current inventory: 30 tomatoes, 20 lettuces, 10 chicken.

[0518] Average sales data for the past three years: 45 tomatoes, 35 lettuce, 25 chicken.

[0519] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0520] Step 1:

[0521] The server collects historical sales data, seasonal data, and customer preference data from the POS system. This data is collected periodically by the server and stored in a database. Inputs include sales data (e.g., Dish A: 50 units, Dish B: 30 units), weather information, event information, etc. As an output, an organized dataset is stored in the database.

[0522] Step 2:

[0523] The server preprocesses the collected data, removing outliers and imputing missing values. It uses data analysis software to remove inaccurate data from the input dataset and impute missing values. The output is a clean dataset. Specific operations include identifying and removing outlier data points and imputing missing values ​​using the mean or median.

[0524] Step 3:

[0525] The server uses a generative AI model based on the preprocessed data to make demand forecasts, taking into account weekends, holidays, seasonal events, etc. Past sales data, seasonal data, and customer preference data are used as input. The output is the predicted demand volume. Specific operations involve entering a prompt into ChatGPT and receiving the prediction results. For example, the prediction result may be, "Demand for chicken will increase by 20% year-on-year in the third week of December."

[0526] Step 4:

[0527] The server calculates the optimal order quantity based on the demand forecast. At this time, it also takes into account the current inventory level and past order history. The inputs are the predicted demand, current inventory level, and past order history. The output is the specific order quantity. The specific operation is to calculate the optimal order quantity using a calculation algorithm. For example, the result may be, "We suggest ordering 1.2 times the previous year's order quantity for chicken."

[0528] Step 5:

[0529] The server searches through inventory data for ingredients with upcoming expiration dates and lists them. The inputs are inventory data and expiration date data. The output is a list of ingredients with upcoming expiration dates. Specifically, it checks the expiration date of each ingredient and identifies ingredients whose expiration date is within one week. For example, it obtains information such as "the expiration date of tomatoes is October 15, 2023."

[0530] Step 6:

[0531] The server posts ingredients with upcoming expiration dates on an online platform, allowing users to purchase them. The input is a list of ingredients with upcoming expiration dates. The output is the item information posted on the online platform. Specific operations include uploading information about each ingredient to an online database and making it accessible to users. For example, the server may post information such as "Tomatoes available at a discount."

[0532] Step 7:

[0533] Based on the purchased ingredients, the server suggests the most suitable cooking method and recipe. The information on the purchased ingredients is used as input. The recipe information is provided to the user as output. Specifically, the server searches for the most suitable recipe from a pre-registered recipe database based on the purchased ingredients and notifies the user of the recipe. For example, it suggests a recipe such as "pasta with tomato sauce."

[0534] 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.

[0535] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, reducing food waste, and providing more personalized service by recognizing user emotions. Below, we will create a system program and explain its processing in natural language.

[0536] Main component description

[0537] Data collection

[0538] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. For example, it can be configured to retrieve a week's worth of sales data every Monday. This data collection is performed automatically through an API.

[0539] Data analysis and demand forecasting

[0540] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT to generate demand forecasts that take into account weekends, holidays, and seasonal events. For example, it can predict increased demand for chicken and cake ingredients during the Christmas season in December.

[0541] Order quantity optimization

[0542] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. Based on the calculation results, the server then sends an ordering proposal to the restaurant's terminal, where it can be reviewed by the manager.

[0543] Best before date management

[0544] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the restaurant's terminal.

[0545] Online sales

[0546] The server posts food items that are close to their expiration date on the online platform, allowing users to purchase them. For example, users can access the platform from their home PC or smartphone and purchase tomatoes or lettuce that are close to their expiration date.

[0547] Cooking suggestions

[0548] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, the server will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0549] Introducing the Emotion Engine

[0550] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if the user gave feedback indicating dissatisfaction with their previous order, the emotion engine will take that into consideration and suggest products that will provide greater satisfaction the next time.

[0551] Specific examples

[0552] Data Collection Example

[0553] The server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores it in the database. At the same time, it can also collect information about the weather and events that day.

[0554] Demand forecast example

[0555] The server uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends that restaurants order 1.2 times the amount of chicken they ordered last year.

[0556] Example of expiration date management

[0557] The server detects from inventory information that the expiration date for the tomatoes is October 15, 2023, and sends an alert notification.The restaurant's terminal then displays an alert saying, "The expiration date for the tomatoes is approaching. Please use or sell them immediately."

[0558] Online sales example

[0559] A user accesses the online platform from their home PC and purchases tomatoes with a best-by date of October 10, 2023 at a discounted price. After the purchase procedure is completed, the server sends the user a recipe for "Pasta with Tomato Sauce."

[0560] Example of using the emotion engine

[0561] If a user previously ordered pasta with tomato sauce and gave feedback that it was "bland," the emotion engine would analyze that feedback and suggest a recipe for "pasta with spicy tomato sauce" the next time the user buys tomatoes, thereby improving user satisfaction.

[0562] In this way, this invention not only optimizes food supply and demand forecasts and inventory management, reduces waste, and maximizes profits, but also provides personalized services that take into account user emotions. Therefore, the invention not only significantly improves the management efficiency of restaurants, but also increases customer satisfaction.

[0563] The processing flow will be explained below.

[0564] Step 1:

[0565] The server periodically accesses the POS system to collect past sales data, seasonal data, and customer preference data. For example, you can set it to retrieve a week's worth of sales data every Monday. The data is then automatically collected via API.

[0566] Step 2:

[0567] The server converts the format of the acquired data and stores it in a database. Data conversion involves standardizing dates, categorizing data, filling in missing values, and removing outliers. For example, data with zero or negative sales volume is filtered out.

[0568] Step 3:

[0569] The server retrieves the saved data from the database and performs pre-processing for analysis. Here, sales figures are aggregated daily, weekly, and monthly, and formatted into a form suitable for analysis. For example, the sales figures for a specific product can be aggregated for each day of the week.

[0570] Step 4:

[0571] The server uses ChatGPT to analyze the collected data and predict demand for the next month. Forecasts are based on past sales patterns, seasonal data, and campaign information. For example, it predicts that demand for chicken will increase by 20% year-on-year during the Christmas season in December.

[0572] Step 5:

[0573] The server calculates the optimal order quantity based on the forecast results. It also takes into account current inventory and past order history to calculate the required additional order quantity. For example, if there are 50 chickens in stock and the forecast demand is 80, an additional 30 units will need to be ordered.

[0574] Step 6:

[0575] The server then sends the calculated ordering suggestions to the restaurant's administrator's terminal, which displays the specific order quantity and recommended ordering time, allowing the administrator to proceed with the ordering process based on that information.

[0576] Step 7:

[0577] The server periodically checks inventory data to identify ingredients that are close to their expiration date. For example, it detects ingredients that are within a week of their expiration date and generates a list of them.

[0578] Step 8:

[0579] The server sends alerts to restaurant terminals about ingredients that are nearing their expiration date. The terminals display a message saying, "The tomatoes are nearing their expiration date. Please use or sell them as soon as possible." The administrator can then take prompt action based on this information.

[0580] Step 9:

[0581] The server posts food items that are close to their expiration date on the online platform. Users can access the platform from their home PC or smartphone and purchase the food items. For example, users can purchase tomatoes that are close to their expiration date at a discounted price.

[0582] Step 10:

[0583] A user purchases ingredients through the online platform. Once the purchase is complete, the server records the information in a database and sends the user a purchase confirmation email.

[0584] Step 11:

[0585] The server provides appropriate cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, it generates a recipe for "pasta with tomato sauce" and sends it by email.

[0586] Step 12:

[0587] The server uses an emotion engine to analyze the user's past purchase history and feedback. For example, if the user gave feedback that they were dissatisfied with their previous order, the emotion engine will take that into account the next time and suggest products or recipes that will be more satisfying.

[0588] Step 13:

[0589] The server provides services according to the user's emotional state based on the results of the emotion engine's analysis. If the user's feedback last time was that the tomato sauce pasta was "bland," the server will suggest a recipe for "spicy tomato sauce pasta" next time. This will improve user satisfaction.

[0590] In this way, the system can optimize supply and demand forecasts and inventory management throughout a series of processing steps, reducing food waste and maximizing profits, as well as providing personalized service that takes user emotions into account.

[0591] Example 2

[0592] 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."

[0593] It is important for restaurants to forecast food supply and demand and manage inventory more efficiently to reduce food waste. Another challenge is to improve customer satisfaction by recognizing user emotions and providing personalized services. Conventional systems have difficulty meeting these multifaceted requirements, so a new system that can solve these challenges is needed.

[0594] The identification processing 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 past data, means for preprocessing the collected data, means for analyzing the preprocessed data and predicting demand for ingredients, means for calculating optimal order quantities based on the prediction results, means for detecting ingredients that are close to their expiration date and issuing alerts, means for selling the detected ingredients online, means for suggesting cooking methods for the ingredients via an online platform, and means for analyzing users' past purchase histories and feedback and providing personalized services. This enables optimization of ingredient supply and demand predictions and inventory management, reducing ingredient waste and improving customer satisfaction.

[0595] "Past data" refers to information accumulated in the past, such as a restaurant's sales history, seasonal data, and customer preference data.

[0596] "Means of collection" refers to a device or system that automatically acquires the necessary data using APIs, sensors, etc.

[0597] A "preprocessing means" is a device or system that removes outliers and fills in missing values ​​in order to convert data into a format that is easier to analyze.

[0598] "Means of analysis" refers to algorithms and software that predict future demand, etc. based on collected and preprocessed data.

[0599] A "demand forecasting means" is a device or system that forecasts the demand for food ingredients at a specific time based on collected data.

[0600] The "means for calculating the optimal order quantity" refers to an algorithm or device that calculates the effective order quantity based on the demand forecast results and the current inventory status.

[0601] The "means for detecting food ingredients approaching their expiration date and issuing an alert notification" is a system that identifies products approaching their expiration date from inventory data and issues a warning to the administrator.

[0602] The "means for selling detected food ingredients online" is a system that posts food ingredients that are close to their expiration date on an internet platform, allowing users to purchase them.

[0603] The "means for suggesting cooking methods" is a device or system for providing users with optimal cooking methods and recipes based on specific ingredients.

[0604] "Means of analyzing past purchase history and feedback to provide personalized services" refers to a system that analyzes a user's preferences and emotions based on the purchases and feedback information they have made to date, and makes personalized suggestions.

[0605] This invention is a system for optimizing food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. It also aims to recognize user emotions and provide personalized services. A specific embodiment of the system is described below.

[0606] Data collection

[0607] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. This data is automatically retrieved through an API. For example, it can be configured to retrieve a week's worth of sales data every Monday. After collecting this data, the server stores the necessary information in a database.

[0608] Data Preprocessing

[0609] The collected data is preprocessed by the server. Data cleaning is performed, such as removing outliers and filling in missing values. Specifically, outliers are removed from the collected sales data, and missing data is filled in appropriately.

[0610] Demand forecasting

[0611] The server uses a generative AI model (e.g., ChatGPT) to forecast demand based on the preprocessed data. For example, the server uses data from the past three years to predict that demand for chicken will increase by 20% year-on-year in the third week of December. This forecast result is stored in a database and used in the next step.

[0612] Order quantity optimization

[0613] The server calculates the optimal order quantity based on the demand forecast results and current inventory information. For example, if the forecasted demand is expected to increase by 20% compared to the previous year, it will suggest ordering 1.2 times the previous year's amount. This suggestion is sent to the restaurant's terminal and can be confirmed by the manager.

[0614] Best before date management

[0615] The server searches inventory data for ingredients with upcoming expiration dates and lists them. For example, it might identify that tomatoes have an expiration date of October 15, 2023, and send an alert to the restaurant's terminal saying, "The expiration date of the tomatoes is approaching. Please use or sell them immediately."

[0616] Online sales

[0617] The server posts food items with upcoming expiration dates on the online platform, allowing users to purchase them. For example, a user can access the online platform from their home PC or smartphone and purchase tomatoes with an expiration date of October 10, 2023, at a discounted price.

[0618] Cooking suggestions

[0619] The server suggests the best cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, it will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0620] Introducing the Emotion Engine

[0621] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if a user previously ordered pasta with tomato sauce and gave feedback that it was "bland," the emotion engine would analyze that feedback and suggest a recipe for "pasta with spicy tomato sauce" the next time the user purchases tomatoes. This can improve user satisfaction.

[0622] Prompt Sentence Examples

[0623] Demand forecast prompt

[0624] "Using sales data from the past three years, please forecast the demand for chicken for the third week of December. Based on that, please propose an order quantity that is 1.2 times the previous year's order quantity."

[0625] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0626] Step 1: Data collection

[0627] The server automatically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system using an API. For example, you can set it to retrieve a week's worth of sales data every Monday and store data such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units" in a database. In this case, the input data is sales information from the POS system, and the output is the sales data stored in the database.

[0628] Step 2: Data Preprocessing

[0629] The server preprocesses the collected data. Specifically, it removes outliers and fills in missing values. For example, if sales data contains abnormal values ​​(outliers), it removes them and fills in missing data by inferring it from other data. The input in this step is the collected raw data, and the output is preprocessed, clean data.

[0630] Step 3: Demand forecast

[0631] The server uses a generative AI model (for example, ChatGPT) to make a demand forecast based on the preprocessed data. The prompt text input to the generative AI model is, "Using sales data from the past three years, please predict the demand for chicken in the third week of December. Also, based on that, please suggest an order quantity that is 1.2 times the previous year's order quantity." This results in a prediction that demand for chicken in the third week of December will increase by 20% compared to the previous year. This prediction result is saved in a database.

[0632] Step 4: Optimize order quantity

[0633] The server calculates the optimal order quantity based on the demand forecast results and current inventory information. For example, based on a forecasted demand increase of 20% compared to the previous year, it calculates 1.2 times the order quantity from the previous year and proposes a new order quantity. The inputs in this step are the demand forecast results and inventory data, and the outputs are the calculated order quantity and its proposed order.

[0634] Step 5: Submitting an order proposal

[0635] The server sends an ordering proposal based on the calculation results to the restaurant's terminal. The administrator checks the ordering proposal on the terminal and approves or modifies it as necessary. The input in this step is the optimized order quantity, and the output is the ordering proposal displayed on the restaurant's terminal.

[0636] Step 6: Best before date management

[0637] The server searches through inventory data for ingredients with upcoming expiration dates and lists them. For example, it identifies that "the expiration date for tomatoes is October 15, 2023," and based on that information, it sends an alert notification to the restaurant's terminal saying, "The expiration date for tomatoes is approaching. Please use or sell them immediately." The input in this step is inventory data, and the output is an alert notification displayed on the terminal.

[0638] Step 7: Sell online

[0639] The server posts food items with an approaching expiration date on an online platform. Users can access the online platform from their home PC or smartphone and purchase tomatoes with an expiration date of October 10, 2023 at a discounted price. The input in this step is information about food items with an approaching expiration date, and the output is the information posted on the online platform.

[0640] Step 8: Cooking suggestions

[0641] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if the user purchases tomatoes, it will provide recipes such as pasta with tomato sauce or Caprese. The input in this step is the purchased ingredients, and the output is the recipe information provided to the user.

[0642] Step 9: Implementing the Emotion Engine

[0643] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if a user previously ordered pasta with tomato sauce and provided feedback that it was "bland," the emotion engine analyzes that feedback and suggests a recipe for "pasta with spicy tomato sauce" the next time the user purchases tomatoes. The input in this step is the user's past purchase history and feedback information, and the output is personalized service suggestions.

[0644] (Application example 2)

[0645] 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."

[0646] Conventional restaurant supply and demand forecasting and inventory management systems make it difficult to reduce food waste and are unable to provide personalized service to customers. Furthermore, because services are provided without taking into account customer emotions, it is not possible to increase customer satisfaction.

[0647] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0648] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for analyzing the collected data and forecasting demand for ingredients, means for calculating optimal order quantities based on the forecast results, means for detecting ingredients with approaching expiration dates and managing information, means for selling the detected ingredients online, means for suggesting cooking methods for the ingredients via an online platform, and means for collecting emotion data and providing personalized services based on the user's emotions, thereby making it possible to reduce food waste and provide personalized services to users.

[0649] "Past sales data" refers to the sales performance of products recorded in the past by a restaurant, and includes details such as the specific sales quantity and the date and time of the sales.

[0650] "Seasonal data" refers to sales data or data that shows consumer behavior patterns that fluctuate based on specific seasons or events.

[0651] "Customer preference data" is data that represents the tendencies of individual customers, such as their purchase history, ratings, and favorite dishes and ingredients.

[0652] "Emotional data" is data that indicates customer emotions and reactions, extracted from feedback, reviews, etc. provided by customers.

[0653] "Supply and demand forecasting" is the process of predicting future demand for ingredients and products based on collected data.

[0654] The "optimal order quantity" is an efficient and appropriate order quantity calculated based on supply and demand forecast data to prevent unnecessary inventory and stockouts.

[0655] The "best before" date refers to the period during which the quality of ingredients or products can be maintained, and after this period the value of the product may decrease.

[0656] "Online sales" refers to the general process of selling goods over the Internet, allowing customers to purchase goods from the comfort of their own home or remotely.

[0657] "Cooking suggestions" is the process of providing recipes and cooking procedures that will make the most delicious and efficient use of purchased ingredients.

[0658] "Personalized service" refers to a service that provides optimal products and services to individual customers based on their characteristics, preferences, and emotions.

[0659] The present invention is a system that optimizes food supply and demand forecasts and inventory management in restaurants, reducing food waste and providing more personalized services by recognizing user emotions. A detailed description of the system that realizes this application example is provided below.

[0660] The system has a means for the server to collect historical sales data, seasonal data, and customer preference data. This data collection is done periodically, for example, every Monday, by obtaining a week's worth of sales data from the POS system via an API.

[0661] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT, a generative AI model, to forecast supply and demand based on this data. For example, based on past sales data and seasonality data, it can predict that demand for chicken in the third week of December will increase by 20% compared to the previous year.

[0662] Based on the results of the supply and demand forecast, the server calculates the optimal order quantity. Here, it also takes into account current inventory levels and past order history to determine the necessary order quantity. The ordering proposal is sent to the restaurant's terminal so that the manager can check it.

[0663] Furthermore, the server has a means of detecting food ingredients that are close to their expiration date. Based on inventory data, if there are tomatoes with an expiration date of less than a week, for example, it sends an alert to the terminal saying, "The expiration date of the tomatoes is approaching. Please use or sell them immediately."

[0664] Food items that are close to their expiration date are sold online. Users can access the online platform using their PC or smartphone and purchase food items that are close to their expiration date at a discounted price.

[0665] The server also suggests optimal cooking methods and recipes based on the ingredients purchased. For example, if a user purchases tomatoes, it will suggest recipes such as "pasta with tomato sauce" and "caprese."

[0666] Emotional data is also utilized. The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, allowing it to provide services that reflect the user's emotions. For example, if a user gives feedback that their last order was "bland," the server can suggest a recipe for "pasta with spicy tomato sauce" for the next order.

[0667] In this way, the system of the present invention not only optimizes food supply and demand forecasts and inventory management, reducing food waste, but also significantly improves the management efficiency of restaurants by providing personalized services to users. Furthermore, it is possible to improve customer satisfaction by making suggestions using emotion data.

[0668] An example prompt could be, "Based on your past feedback and purchase history, what improvements or new suggestions would you consider making a purchase with us again?"

[0669] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0670] Step 1:

[0671] The server collects past sales data, seasonal data, and customer preference data from the POS system via API. The input is the POS system's API endpoint, and the output is the collected dataset. A specific example of data collection is to obtain a week's worth of sales data every Monday and store it in a database.

[0672] Step 2:

[0673] The server preprocesses the collected data, removing outliers and filling in missing values ​​to prepare the data for analysis. The input is the collected dataset, and the output is the preprocessed dataset. Specifically, it uses the Python pandas library to fill in missing values ​​with the mean and exclude clearly erroneous data.

[0674] Step 3:

[0675] The server uses a generative AI model (ChatGPT) to perform supply and demand forecasts using the preprocessed data. The input is the preprocessed dataset, and the output is the prediction results. Specifically, it sends prompts to ChatGPT to perform demand forecasts. For example, it sends a prompt such as, "What is the demand for chicken in the third week of December?"

[0676] Step 4:

[0677] The server calculates the optimal order quantity based on the forecast results. The inputs are the supply and demand forecast results, current inventory data, and past order history, and the output is the optimal order quantity. Specifically, the server uses an algorithm to calculate the most efficient order quantity, taking into account inventory levels and past order history.

[0678] Step 5:

[0679] The server detects ingredients that are close to their expiration date and manages the information. The input is inventory data, and the output is a list of ingredients that are close to their expiration date. For example, the server detects from the inventory data that "the expiration date for tomatoes is October 15, 2023" and lists that information.

[0680] Step 6:

[0681] The terminal notifies inventory alerts for ingredients that are nearing their expiration date. The input is a list of ingredients that are nearing their expiration date, and the output is an alert notification. Specifically, the terminal displays an alert saying, "The tomatoes are nearing their expiration date. Please use or sell them immediately."

[0682] Step 7:

[0683] The server sells food items with an approaching expiration date on an online platform. The input is a list of food items with an approaching expiration date, and the output is a sales page for the online shop. Specifically, the server automatically posts information about food items with an approaching expiration date on the online platform.

[0684] Step 8:

[0685] A user purchases ingredients at a discounted price through an online platform. The input is the customer's order information from the online shop, and the output is a notification that the purchase has been completed. Specifically, the user selects ingredients and completes the purchase procedure using a smartphone or PC.

[0686] Step 9:

[0687] The server provides cooking methods and recipes based on purchased ingredients. The input is information about the purchased ingredients, and the output is a suggested recipe. For example, if a user purchases tomatoes, the server generates a recipe for "pasta with tomato sauce" and sends it to the user.

[0688] Step 10:

[0689] The server analyzes the emotional data and provides personalized services based on the user's emotions. The input is the user's feedback and purchase history, and the output is personalized service suggestions. Specifically, the system analyzes the feedback using an emotion engine and suggests a recipe, for example, "pasta with spicy tomato sauce."

[0690] Step 11:

[0691] The user enjoys cooking using the suggested recipes and cooking methods. The input is the suggested recipe and cooking method, and the output is the finished dish. Specific operations involve cooking by following the instructions on the smart glasses and the voice assistant.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] [Third embodiment]

[0696] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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).

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] 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."

[0708] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. Below, we will create a program for the system and explain its processing in natural language.

[0709] Main component description

[0710] Data collection

[0711] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. For example, it can be configured to collect a week's worth of data every Monday.

[0712] Data analysis and demand forecasting

[0713] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT to generate demand forecasts that take into account weekends, holidays, and seasonal events. For example, it can predict increased demand for chicken and cake ingredients during the Christmas season in December.

[0714] Order quantity optimization

[0715] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. Based on the calculation results, the server then sends an ordering proposal to the restaurant's terminal, where it can be checked by the manager.

[0716] Best before date management

[0717] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the restaurant's terminal.

[0718] Online sales

[0719] The server posts food items that are close to their expiration date on the online platform, allowing users to purchase them. For example, users can access the platform from their home PC or smartphone and purchase tomatoes or lettuce that are close to their expiration date.

[0720] Cooking suggestions

[0721] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, the server will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0722] Specific examples

[0723] Data Collection Example

[0724] The server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores it in the database. At the same time, it can also collect information about the weather and events that day.

[0725] Demand forecast example

[0726] The server uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends that restaurants order 1.2 times the amount of chicken they ordered last year.

[0727] Example of expiration date management

[0728] The server detects from inventory information that the expiration date for the tomatoes is October 15, 2023, and sends an alert notification.The restaurant's terminal then displays an alert saying, "The expiration date for the tomatoes is approaching. Please use or sell them immediately."

[0729] Online sales example

[0730] A user accesses the online platform from their home PC and purchases tomatoes with a best-by date of October 10, 2023 at a discounted price. After the purchase procedure is completed, the server sends the user a recipe for "Pasta with Tomato Sauce."

[0731] In this way, this invention optimizes food supply and demand forecasts and inventory management, reduces waste, and maximizes profits. This invention significantly improves the management efficiency of restaurants and also provides convenient and attractive services to customers.

[0732] The processing flow will be explained below.

[0733] Step 1:

[0734] The server periodically accesses the restaurant's POS system to collect past sales data, seasonal data, and customer preference data. For example, it can be set to retrieve a week's worth of sales data every Monday. This data collection is performed automatically through the API.

[0735] Step 2:

[0736] The server converts and formats the data before storing it in the database. This includes filling in missing values ​​and removing outliers. For example, it filters out data with zero sales volume or other obviously abnormal values.

[0737] Step 3:

[0738] The server stores the formatted data in a database. The stored data includes product name, sales quantity, sales date, and customer attributes (age, gender, etc.). For example, sales data and customer information for October 1, 2023 are recorded in the corresponding tables in the database.

[0739] Step 4:

[0740] The server retrieves historical sales data, seasonal data, and customer preference data from the database. This is a pre-processing step for demand forecasting. The retrieved data covers a certain period (e.g., the past three years).

[0741] Step 5:

[0742] The server preprocesses the data it receives. Specifically, it normalizes and standardizes the data to make it suitable for analysis. For example, it converts sales volume into average values ​​for each week or month.

[0743] Step 6:

[0744] The server analyzes the data using ChatGPT to predict future demand, taking into account seasonality and the influence of specific events (e.g., Christmas and Valentine's Day). The forecast results are output as numerical data for further processing.

[0745] Step 7:

[0746] The server calculates the optimal order quantity based on the forecast results, taking into account current inventory levels and past order history. For example, if demand for chicken is predicted, it compares it with current inventory and calculates the required additional order quantity.

[0747] Step 8:

[0748] The server generates an ordering proposal based on the calculation results and sends a notification to the restaurant's administrator's terminal. The notification includes the specific order quantity and the recommended ordering time. The administrator places the order based on this information.

[0749] Step 9:

[0750] The server identifies ingredients that are close to expiry based on current inventory data. For example, it lists ingredients that are within a week of expiry. This process is important for efficient inventory management.

[0751] Step 10:

[0752] The server sends alerts to restaurant terminals about ingredients that are nearing their expiration date. The notifications include a list of ingredients that need to be used or sold immediately. The administrator can then take appropriate action based on this information.

[0753] Step 11:

[0754] The server posts food items that are nearing their expiration date on an online platform. Users can access the platform from their PCs or smartphones to check and purchase these food items. For example, users can view information about tomatoes and lettuce that are available at discounted prices.

[0755] Step 12:

[0756] A user purchases ingredients through the online platform, and once the purchase is complete, the server records the information in a database and sends a confirmation email to the purchaser.

[0757] Step 13:

[0758] The server generates appropriate cooking methods and recipes based on the purchased ingredients and provides them to the user. For example, if a user purchases tomatoes, the server sends a recipe for "pasta with tomato sauce" to the user for cooking reference.

[0759] In this way, the system optimizes food supply and demand forecasts and inventory management throughout a series of processing steps, reducing food waste and maximizing profits.

[0760] Example 1

[0761] 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."

[0762] In restaurants, predicting supply and demand for ingredients and managing inventory is labor-intensive and difficult to do efficiently. Inaccurate predictions can lead to shortages or surpluses of ingredients, resulting in economic losses and increased waste. Furthermore, there is a lack of mechanisms for managing ingredients approaching their expiration date or for encouraging their consumption at the appropriate time. The objective of this invention is to provide a system that solves these problems and achieves optimal supply and demand prediction and inventory management.

[0763] 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.

[0764] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for preprocessing the collected data to remove outliers and impute missing values, means for analyzing the collected data and using a generative AI model to predict demand for ingredients, means for calculating optimal order quantities based on the prediction results, means for detecting ingredients with approaching expiration dates and managing information, means for listing the detected ingredients on an online platform so that users can purchase them, and means for suggesting cooking methods for the ingredients via the online platform.This enables restaurants to efficiently and accurately predict supply and demand and manage inventory, thereby reducing food waste and maximizing profits.

[0765] "Past sales data" refers to data that records the past sales performance of a restaurant.

[0766] "Seasonal data" is data relating to a particular season, time of year, or event, such as fluctuations in demand for a particular product during a particular season.

[0767] "Customer preference data" refers to data related to a customer's purchasing behavior and preferences. For example, it includes information about a customer's favorite dishes and frequently purchased products.

[0768] "Collection means" refers to the methods and devices used to acquire and store data.

[0769] "Preprocessing" is a data cleansing process that removes outliers from collected data and fills in missing values.

[0770] An "outlier" is a value in the data that is significantly different from the other data.

[0771] "Missing values" are pieces of data that are missing or incomplete.

[0772] A "generative AI model" is a type of artificial intelligence model that learns patterns from large amounts of data and makes predictions and classifications. Specifically, this applies to models that use machine learning or deep learning.

[0773] "Order quantity" refers to the amount of ingredients purchased by a restaurant.

[0774] "Best before date" refers to the date by which food ingredients can be consumed while still maintaining their quality.

[0775] An "online platform" is a service or application provided over the Internet.

[0776] An "alert" is a warning or caution mechanism that notifies you when certain conditions are met.

[0777] "Cooking method" refers to the steps and recipes for processing and cooking ingredients.

[0778] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. Below, we will create a program for this system and explain its processing in natural language.

[0779] Data collection

[0780] The server periodically collects data from the restaurant's POS system. This collection is automated and can be set to retrieve a week's worth of sales data, weather data, event data, etc., every Monday at 2:00 AM. The specific hardware used is a POS system and a server. This allows data on past sales, seasonality, and customer preferences to be collected.

[0781] Data analysis and demand forecasting

[0782] The server preprocesses the collected data. Specifically, it removes outliers and fills in missing values. Then, it uses the generative AI model to make a demand forecast. Seasons and special events are taken into account when making demand forecasts. Specifically, the server detects and deletes or corrects abnormal data, and fills in missing data based on past trends. The following prompt statement is used to make a demand forecast for the generative AI model:

[0783] Example: "Based on the past three years of data, please predict demand for the third week of December."

[0784] Order quantity optimization

[0785] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. The specific hardware used is a database and calculation algorithms that run on the server. The calculation results are sent to the restaurant's terminal, where they can be viewed by the manager.

[0786] Best before date management

[0787] The server searches inventory data for ingredients with an approaching expiration date and lists them. This information is then sent to the restaurant's terminal as an alert notification. Specifically, the server queries the inventory database, identifies items with an approaching expiration date, generates an alert for the identified ingredients, and sends it to the terminal. The terminal displays a message saying, "The tomatoes are nearing their expiration date. Please use or sell them immediately."

[0788] Online sales

[0789] The server posts food items with approaching expiration dates on the online platform, making them available for purchase by users. Specifically, the server connects to the online platform's database, adds new product information, and lists the product's expiration date, price, quantity, etc. Users access the platform from their home PC or smartphone, select products, and complete the purchase process.

[0790] Cooking suggestions

[0791] The server suggests optimal cooking methods and recipes based on the purchased ingredients. Specifically, the server checks the purchase history, searches the database for corresponding recipes, and notifies the user of the found recipes. The user can then enjoy cooking using the suggested recipes as a reference.

[0792] In this way, this system enables efficient and accurate forecasting of food supply and demand and inventory management, allowing restaurants to reduce food waste and maximize profits. It also improves customer satisfaction by providing convenient and attractive services to users.

[0793] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0794] Step 1:

[0795] The server periodically collects data from the restaurant's POS system. The input data is past sales data, seasonal data, and customer preference data. Specifically, the server sends an API request to the POS system to obtain sales data. The obtained data is stored in a database. The output is the collected data.

[0796] Step 2:

[0797] The server preprocesses the collected data. The input data are the sales data, seasonal data, and customer preference data collected in step 1. Specifically, the server detects anomalous data and deletes or corrects it. Missing data is complemented based on past trends. The output is the preprocessed data.

[0798] Step 3:

[0799] The server analyzes the preprocessed data and uses the generative AI model to make demand forecasts. The input data are preprocessed sales data, seasonal data, and customer preference data. Specifically, the server sends a prompt to the generative AI model to request a supply and demand forecast. For example, a prompt such as "Please predict demand for the third week of December based on data from the past three years" is used. The output is the demand forecast results.

[0800] Step 4:

[0801] The server calculates the optimal order quantity based on the demand forecast results. The input data is the demand forecast results, current inventory levels, and past order history. Specifically, the server calculates the optimal order quantity based on this data and sends the result to the restaurant's terminal. The output is a proposal for the optimal order quantity.

[0802] Step 5:

[0803] The server detects ingredients that are close to their expiration date from inventory data and manages the information. The input data is the current inventory data. Specifically, the server queries the inventory database to identify ingredients that are close to their expiration date. It generates an alert for the identified ingredients and sends it to the terminal. The terminal displays, "Tomatoes are close to their expiration date. Please use or sell them immediately." The output is an inventory alert.

[0804] Step 6:

[0805] The server posts food items with approaching expiration dates on an online platform so that users can purchase them. The input data is information about food items with approaching expiration dates. Specifically, the server connects to the online platform's database and adds new product information. Product information includes expiration dates, prices, quantities, etc. Users access the platform, select products, and complete the purchase process. The output is online sales information.

[0806] Step 7:

[0807] The server suggests optimal cooking methods and recipes based on purchased ingredients. The input data is the purchase history. Specifically, the server checks the purchase history and searches the database for corresponding recipes. It notifies the user of the recipes found, and the user can enjoy cooking using the suggested recipes as a reference. The output is cooking methods and recipe information.

[0808] (Application example 1)

[0809] 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."

[0810] Forecasting supply and demand and managing inventory for ingredients in restaurants is extremely complex, and if not done efficiently, food waste and shortages are likely to occur. Furthermore, inadequate management of ingredients with approaching expiration dates can lead to increased food waste. These issues are also common in delivery services, where efficient operation is essential, as it is particularly difficult to respond to fluctuations in demand.

[0811] 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.

[0812] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for analyzing the collected data and forecasting demand for ingredients, means for calculating optimal order quantities based on the forecast results, means for detecting ingredients with approaching expiration dates and managing information, means for selling the detected ingredients online, means for suggesting cooking methods for ingredients via an online platform, a smartphone application means for supporting demand forecasting and inventory management for food delivery services, and means for suggesting optimal recipes based on ingredients purchased by customers. This enables optimal ingredient demand forecasting and inventory management at restaurants and delivery services, reducing food waste and enabling efficient inventory management.

[0813] "Past sales data" refers to records of the quantity and value of products sold in the past by restaurants and delivery services.

[0814] "Seasonal data" is information about fluctuations in sales or demand during particular seasons or times of the year.

[0815] "Customer preference data" refers to data relating to a customer's purchasing history and preferences.

[0816] "Food demand forecast" is a calculation aimed at predicting future food consumption based on past data and current conditions.

[0817] The "optimal order quantity" is the appropriate order quantity of a specified ingredient based on predicted demand.

[0818] "Shorting shelf life ingredients" are ingredients that are approaching the date when they are suitable for use or consumption.

[0819] "Online sales" means trading goods over the Internet.

[0820] An "online platform" is a collection of basic infrastructure and services for providing products and services over the Internet.

[0821] "Suggesting a cooking method" means providing a dish and steps to make it using specific ingredients.

[0822] A "smartphone application" is application software that runs on a smartphone.

[0823] "Suggesting the best recipe based on the ingredients purchased by the customer" means providing cooking procedures and methods that are best suited to the ingredients acquired by the customer.

[0824] MODE FOR CARRYING OUT THE INVENTION

[0825] This invention is a system for optimizing food supply and demand forecasting and inventory management in restaurants and delivery services. This system consists of the following main components and processing steps:

[0826] Key Components

[0827] server

[0828] The server runs a program that includes the following means:

[0829] 1. Data collection methods:

[0830] The server periodically collects past sales data, seasonal data, and customer preference data from the POS systems of restaurants and delivery services. For example, it can be configured to collect a week's worth of data every Monday.

[0831] 2. Data analysis and demand forecasting tools:

[0832] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses a generative AI model (such as ChatGPT) to forecast demand. For example, it can predict that demand for chicken and cake ingredients will increase during the Christmas season in December.

[0833] 3. Measures to optimize order quantity:

[0834] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history.

[0835] 4. Best before date control measures:

[0836] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the terminals of restaurants and delivery services.

[0837] 5. Online sales channels:

[0838] The server places ingredients that are nearing their expiry date on an online platform for users to purchase.

[0839] 6. Suggested cooking methods for ingredients:

[0840] The server will suggest the best cooking method and recipe based on the ingredients purchased.

[0841] 7. Smartphone application means:

[0842] Users can access these functions through a smartphone application that forecasts food supply and demand, assists with inventory management, and also sells food that is nearing its expiration date and suggests cooking methods.

[0843] Specific examples

[0844] For example, the server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores this information in the database. At the same time, weather and event information for that day can also be collected.

[0845] The server then uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends ordering 1.2 times the amount of chicken ordered last year.

[0846] Regarding expiration date management, the server will detect from inventory information that the expiration date for tomatoes is October 15, 2023, and send an alert notification. The smartphone application will then display the message, "The expiration date for tomatoes is approaching. Please use or sell them immediately."

[0847] In the online sales example, a user can access the online platform from their smartphone at home and purchase tomatoes with a best-by date of October 10, 2023 at a discounted price. After completing the purchase process, a recipe for "Pasta with Tomato Sauce" is provided to the user through the app.

[0848] Prompt Sentence Examples

[0849] The following prompts can be used to provide input to the generative AI model:

[0850] Please use the following data to forecast supply and demand for the next week and calculate the optimal order quantity:

[0851] Sales data: 50 tomatoes, 30 lettuce, 20 chicken.

[0852] Current inventory: 30 tomatoes, 20 lettuces, 10 chicken.

[0853] Average sales data for the past three years: 45 tomatoes, 35 lettuce, 25 chicken.

[0854] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0855] Step 1:

[0856] The server collects historical sales data, seasonal data, and customer preference data from the POS system. This data is collected periodically by the server and stored in a database. Inputs include sales data (e.g., Dish A: 50 units, Dish B: 30 units), weather information, event information, etc. As an output, an organized dataset is stored in the database.

[0857] Step 2:

[0858] The server preprocesses the collected data, removing outliers and imputing missing values. It uses data analysis software to remove inaccurate data from the input dataset and impute missing values. The output is a clean dataset. Specific operations include identifying and removing outlier data points and imputing missing values ​​using the mean or median.

[0859] Step 3:

[0860] The server uses a generative AI model based on the preprocessed data to make demand forecasts, taking into account weekends, holidays, seasonal events, etc. Past sales data, seasonal data, and customer preference data are used as input. The output is the predicted demand volume. Specific operations involve entering a prompt into ChatGPT and receiving the prediction results. For example, the prediction result may be, "Demand for chicken will increase by 20% year-on-year in the third week of December."

[0861] Step 4:

[0862] The server calculates the optimal order quantity based on the demand forecast. At this time, it also takes into account the current inventory level and past order history. The inputs are the predicted demand, current inventory level, and past order history. The output is the specific order quantity. The specific operation is to calculate the optimal order quantity using a calculation algorithm. For example, the result may be, "We suggest ordering 1.2 times the previous year's order quantity for chicken."

[0863] Step 5:

[0864] The server searches through inventory data for ingredients with upcoming expiration dates and lists them. The inputs are inventory data and expiration date data. The output is a list of ingredients with upcoming expiration dates. Specifically, it checks the expiration date of each ingredient and identifies ingredients whose expiration date is within one week. For example, it obtains information such as "the expiration date of tomatoes is October 15, 2023."

[0865] Step 6:

[0866] The server posts ingredients with upcoming expiration dates on an online platform, allowing users to purchase them. The input is a list of ingredients with upcoming expiration dates. The output is the item information posted on the online platform. Specific operations include uploading information about each ingredient to an online database and making it accessible to users. For example, the server may post information such as "Tomatoes available at a discount."

[0867] Step 7:

[0868] Based on the purchased ingredients, the server suggests the most suitable cooking method and recipe. The information on the purchased ingredients is used as input. The recipe information is provided to the user as output. Specifically, the server searches for the most suitable recipe from a pre-registered recipe database based on the purchased ingredients and notifies the user of the recipe. For example, it suggests a recipe such as "pasta with tomato sauce."

[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 relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, reducing food waste, and providing more personalized service by recognizing user emotions. Below, we will create a system program and explain its processing in natural language.

[0871] Main component description

[0872] Data collection

[0873] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. For example, it can be configured to retrieve a week's worth of sales data every Monday. This data collection is performed automatically through an API.

[0874] Data analysis and demand forecasting

[0875] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT to generate demand forecasts that take into account weekends, holidays, and seasonal events. For example, it can predict increased demand for chicken and cake ingredients during the Christmas season in December.

[0876] Order quantity optimization

[0877] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. Based on the calculation results, the server then sends an ordering proposal to the restaurant's terminal, where it can be reviewed by the manager.

[0878] Best before date management

[0879] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the restaurant's terminal.

[0880] Online sales

[0881] The server posts food items that are close to their expiration date on the online platform, allowing users to purchase them. For example, users can access the platform from their home PC or smartphone and purchase tomatoes or lettuce that are close to their expiration date.

[0882] Cooking suggestions

[0883] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, the server will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0884] Introducing the Emotion Engine

[0885] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if the user gave feedback indicating dissatisfaction with their previous order, the emotion engine will take that into consideration and suggest products that will provide greater satisfaction the next time.

[0886] Specific examples

[0887] Data Collection Example

[0888] The server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores it in the database. At the same time, it can also collect information about the weather and events that day.

[0889] Demand forecast example

[0890] The server uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends that restaurants order 1.2 times the amount of chicken they ordered last year.

[0891] Example of expiration date management

[0892] The server detects from inventory information that the expiration date for the tomatoes is October 15, 2023, and sends an alert notification.The restaurant's terminal then displays an alert saying, "The expiration date for the tomatoes is approaching. Please use or sell them immediately."

[0893] Online sales example

[0894] A user accesses the online platform from their home PC and purchases tomatoes with a best-by date of October 10, 2023 at a discounted price. After the purchase procedure is completed, the server sends the user a recipe for "Pasta with Tomato Sauce."

[0895] Example of using the emotion engine

[0896] If a user previously ordered pasta with tomato sauce and gave feedback that it was "bland," the emotion engine would analyze that feedback and suggest a recipe for "pasta with spicy tomato sauce" the next time the user buys tomatoes, thereby improving user satisfaction.

[0897] In this way, this invention not only optimizes food supply and demand forecasts and inventory management, reduces waste, and maximizes profits, but also provides personalized services that take into account user emotions. Therefore, the invention not only significantly improves the management efficiency of restaurants, but also increases customer satisfaction.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] The server periodically accesses the POS system to collect past sales data, seasonal data, and customer preference data. For example, you can set it to retrieve a week's worth of sales data every Monday. The data is then automatically collected via API.

[0901] Step 2:

[0902] The server converts the format of the acquired data and stores it in a database. Data conversion involves standardizing dates, categorizing data, filling in missing values, and removing outliers. For example, data with zero or negative sales volume is filtered out.

[0903] Step 3:

[0904] The server retrieves the saved data from the database and performs pre-processing for analysis. Here, sales figures are aggregated daily, weekly, and monthly, and formatted into a form suitable for analysis. For example, the sales figures for a specific product can be aggregated for each day of the week.

[0905] Step 4:

[0906] The server uses ChatGPT to analyze the collected data and predict demand for the next month. Forecasts are based on past sales patterns, seasonal data, and campaign information. For example, it predicts that demand for chicken will increase by 20% year-on-year during the Christmas season in December.

[0907] Step 5:

[0908] The server calculates the optimal order quantity based on the forecast results. It also takes into account current inventory and past order history to calculate the required additional order quantity. For example, if there are 50 chickens in stock and the forecast demand is 80, an additional 30 units will need to be ordered.

[0909] Step 6:

[0910] The server then sends the calculated ordering suggestions to the restaurant's administrator's terminal, which displays the specific order quantity and recommended ordering time, allowing the administrator to proceed with the ordering process based on that information.

[0911] Step 7:

[0912] The server periodically checks inventory data to identify ingredients that are close to their expiration date. For example, it detects ingredients that are within a week of their expiration date and generates a list of them.

[0913] Step 8:

[0914] The server sends alerts to restaurant terminals about ingredients that are nearing their expiration date. The terminals display a message saying, "The tomatoes are nearing their expiration date. Please use or sell them as soon as possible." The administrator can then take prompt action based on this information.

[0915] Step 9:

[0916] The server posts food items that are close to their expiration date on the online platform. Users can access the platform from their home PC or smartphone and purchase the food items. For example, users can purchase tomatoes that are close to their expiration date at a discounted price.

[0917] Step 10:

[0918] A user purchases ingredients through the online platform. Once the purchase is complete, the server records the information in a database and sends the user a purchase confirmation email.

[0919] Step 11:

[0920] The server provides appropriate cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, it generates a recipe for "pasta with tomato sauce" and sends it by email.

[0921] Step 12:

[0922] The server uses an emotion engine to analyze the user's past purchase history and feedback. For example, if the user gave feedback that they were dissatisfied with their previous order, the emotion engine will take that into account the next time and suggest products or recipes that will be more satisfying.

[0923] Step 13:

[0924] The server provides services according to the user's emotional state based on the results of the emotion engine's analysis. If the user's feedback last time was that the tomato sauce pasta was "bland," the server will suggest a recipe for "spicy tomato sauce pasta" next time. This will improve user satisfaction.

[0925] In this way, the system can optimize supply and demand forecasts and inventory management throughout a series of processing steps, reducing food waste and maximizing profits, as well as providing personalized service that takes user emotions into account.

[0926] Example 2

[0927] 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."

[0928] It is important for restaurants to forecast food supply and demand and manage inventory more efficiently to reduce food waste. Another challenge is to improve customer satisfaction by recognizing user emotions and providing personalized services. Conventional systems have difficulty meeting these multifaceted requirements, so a new system that can solve these challenges is needed.

[0929] The identification processing 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 past data, means for preprocessing the collected data, means for analyzing the preprocessed data and predicting demand for ingredients, means for calculating optimal order quantities based on the prediction results, means for detecting ingredients that are close to their expiration date and issuing alerts, means for selling the detected ingredients online, means for suggesting cooking methods for the ingredients via an online platform, and means for analyzing users' past purchase histories and feedback and providing personalized services. This enables optimization of ingredient supply and demand predictions and inventory management, reducing ingredient waste and improving customer satisfaction.

[0930] "Past data" refers to information accumulated in the past, such as a restaurant's sales history, seasonal data, and customer preference data.

[0931] "Means of collection" refers to a device or system that automatically acquires the necessary data using APIs, sensors, etc.

[0932] A "preprocessing means" is a device or system that removes outliers and fills in missing values ​​in order to convert data into a format that is easier to analyze.

[0933] "Means of analysis" refers to algorithms and software that predict future demand, etc. based on collected and preprocessed data.

[0934] A "demand forecasting means" is a device or system that forecasts the demand for food ingredients at a specific time based on collected data.

[0935] The "means for calculating the optimal order quantity" refers to an algorithm or device that calculates the effective order quantity based on the demand forecast results and the current inventory status.

[0936] The "means for detecting food ingredients approaching their expiration date and issuing an alert notification" is a system that identifies products approaching their expiration date from inventory data and issues a warning to the administrator.

[0937] The "means for selling detected food ingredients online" is a system that posts food ingredients that are close to their expiration date on an internet platform, allowing users to purchase them.

[0938] The "means for suggesting cooking methods" is a device or system for providing users with optimal cooking methods and recipes based on specific ingredients.

[0939] "Means of analyzing past purchase history and feedback to provide personalized services" refers to a system that analyzes a user's preferences and emotions based on the purchases and feedback information they have made to date, and makes personalized suggestions.

[0940] This invention is a system for optimizing food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. It also aims to recognize user emotions and provide personalized services. A specific embodiment of the system is described below.

[0941] Data collection

[0942] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. This data is automatically retrieved through an API. For example, it can be configured to retrieve a week's worth of sales data every Monday. After collecting this data, the server stores the necessary information in a database.

[0943] Data Preprocessing

[0944] The collected data is preprocessed by the server. Data cleaning is performed, such as removing outliers and filling in missing values. Specifically, outliers are removed from the collected sales data, and missing data is filled in appropriately.

[0945] Demand forecasting

[0946] The server uses a generative AI model (e.g., ChatGPT) to forecast demand based on the preprocessed data. For example, the server uses data from the past three years to predict that demand for chicken will increase by 20% year-on-year in the third week of December. This forecast result is stored in a database and used in the next step.

[0947] Order quantity optimization

[0948] The server calculates the optimal order quantity based on the demand forecast results and current inventory information. For example, if the forecasted demand is expected to increase by 20% compared to the previous year, it will suggest ordering 1.2 times the previous year's amount. This suggestion is sent to the restaurant's terminal and can be confirmed by the manager.

[0949] Best before date management

[0950] The server searches inventory data for ingredients with upcoming expiration dates and lists them. For example, it might identify that tomatoes have an expiration date of October 15, 2023, and send an alert to the restaurant's terminal saying, "The expiration date of the tomatoes is approaching. Please use or sell them immediately."

[0951] Online sales

[0952] The server posts food items with upcoming expiration dates on the online platform, allowing users to purchase them. For example, a user can access the online platform from their home PC or smartphone and purchase tomatoes with an expiration date of October 10, 2023, at a discounted price.

[0953] Cooking suggestions

[0954] The server suggests the best cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, it will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[0955] Introducing the Emotion Engine

[0956] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if a user previously ordered pasta with tomato sauce and gave feedback that it was "bland," the emotion engine would analyze that feedback and suggest a recipe for "pasta with spicy tomato sauce" the next time the user purchases tomatoes. This can improve user satisfaction.

[0957] Prompt Sentence Examples

[0958] Demand forecast prompt

[0959] "Using sales data from the past three years, please forecast the demand for chicken for the third week of December. Based on that, please propose an order quantity that is 1.2 times the previous year's order quantity."

[0960] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0961] Step 1: Data collection

[0962] The server automatically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system using an API. For example, you can set it to retrieve a week's worth of sales data every Monday and store data such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units" in a database. In this case, the input data is sales information from the POS system, and the output is the sales data stored in the database.

[0963] Step 2: Data Preprocessing

[0964] The server preprocesses the collected data. Specifically, it removes outliers and fills in missing values. For example, if sales data contains abnormal values ​​(outliers), it removes them and fills in missing data by inferring it from other data. The input in this step is the collected raw data, and the output is preprocessed, clean data.

[0965] Step 3: Demand forecast

[0966] The server uses a generative AI model (for example, ChatGPT) to make a demand forecast based on the preprocessed data. The prompt text input to the generative AI model is, "Using sales data from the past three years, please predict the demand for chicken in the third week of December. Also, based on that, please suggest an order quantity that is 1.2 times the previous year's order quantity." This results in a prediction that demand for chicken in the third week of December will increase by 20% compared to the previous year. This prediction result is saved in a database.

[0967] Step 4: Optimize order quantity

[0968] The server calculates the optimal order quantity based on the demand forecast results and current inventory information. For example, based on a forecasted demand increase of 20% compared to the previous year, it calculates 1.2 times the order quantity from the previous year and proposes a new order quantity. The inputs in this step are the demand forecast results and inventory data, and the outputs are the calculated order quantity and its proposed order.

[0969] Step 5: Submitting an order proposal

[0970] The server sends an ordering proposal based on the calculation results to the restaurant's terminal. The administrator checks the ordering proposal on the terminal and approves or modifies it as necessary. The input in this step is the optimized order quantity, and the output is the ordering proposal displayed on the restaurant's terminal.

[0971] Step 6: Best before date management

[0972] The server searches through inventory data for ingredients with upcoming expiration dates and lists them. For example, it identifies that "the expiration date for tomatoes is October 15, 2023," and based on that information, it sends an alert notification to the restaurant's terminal saying, "The expiration date for tomatoes is approaching. Please use or sell them immediately." The input in this step is inventory data, and the output is an alert notification displayed on the terminal.

[0973] Step 7: Sell online

[0974] The server posts food items with an approaching expiration date on an online platform. Users can access the online platform from their home PC or smartphone and purchase tomatoes with an expiration date of October 10, 2023 at a discounted price. The input in this step is information about food items with an approaching expiration date, and the output is the information posted on the online platform.

[0975] Step 8: Cooking suggestions

[0976] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if the user purchases tomatoes, it will provide recipes such as pasta with tomato sauce or Caprese. The input in this step is the purchased ingredients, and the output is the recipe information provided to the user.

[0977] Step 9: Implementing the Emotion Engine

[0978] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if a user previously ordered pasta with tomato sauce and provided feedback that it was "bland," the emotion engine analyzes that feedback and suggests a recipe for "pasta with spicy tomato sauce" the next time the user purchases tomatoes. The input in this step is the user's past purchase history and feedback information, and the output is personalized service suggestions.

[0979] (Application example 2)

[0980] 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."

[0981] Conventional restaurant supply and demand forecasting and inventory management systems make it difficult to reduce food waste and are unable to provide personalized service to customers. Furthermore, because services are provided without taking into account customer emotions, it is not possible to increase customer satisfaction.

[0982] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0983] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for analyzing the collected data and forecasting demand for ingredients, means for calculating optimal order quantities based on the forecast results, means for detecting ingredients with approaching expiration dates and managing information, means for selling the detected ingredients online, means for suggesting cooking methods for the ingredients via an online platform, and means for collecting emotion data and providing personalized services based on the user's emotions, thereby making it possible to reduce food waste and provide personalized services to users.

[0984] "Past sales data" refers to the sales performance of products recorded in the past by a restaurant, and includes details such as the specific sales quantity and the date and time of the sales.

[0985] "Seasonal data" refers to sales data or data that shows consumer behavior patterns that fluctuate based on specific seasons or events.

[0986] "Customer preference data" is data that represents the tendencies of individual customers, such as their purchase history, ratings, and favorite dishes and ingredients.

[0987] "Emotional data" is data that indicates customer emotions and reactions, extracted from feedback, reviews, etc. provided by customers.

[0988] "Supply and demand forecasting" is the process of predicting future demand for ingredients and products based on collected data.

[0989] The "optimal order quantity" is an efficient and appropriate order quantity calculated based on supply and demand forecast data to prevent unnecessary inventory and stockouts.

[0990] The "best before" date refers to the period during which the quality of ingredients or products can be maintained, and after this period the value of the product may decrease.

[0991] "Online sales" refers to the general process of selling goods over the Internet, allowing customers to purchase goods from the comfort of their own home or remotely.

[0992] "Cooking suggestions" is the process of providing recipes and cooking procedures that will make the most delicious and efficient use of purchased ingredients.

[0993] "Personalized service" refers to a service that provides optimal products and services to individual customers based on their characteristics, preferences, and emotions.

[0994] The present invention is a system that optimizes food supply and demand forecasts and inventory management in restaurants, reducing food waste and providing more personalized services by recognizing user emotions. A detailed description of the system that realizes this application example is provided below.

[0995] The system has a means for the server to collect historical sales data, seasonal data, and customer preference data. This data collection is done periodically, for example, every Monday, by obtaining a week's worth of sales data from the POS system via an API.

[0996] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT, a generative AI model, to forecast supply and demand based on this data. For example, based on past sales data and seasonality data, it can predict that demand for chicken in the third week of December will increase by 20% compared to the previous year.

[0997] Based on the results of the supply and demand forecast, the server calculates the optimal order quantity. Here, it also takes into account current inventory levels and past order history to determine the necessary order quantity. The ordering proposal is sent to the restaurant's terminal so that the manager can check it.

[0998] Furthermore, the server has a means of detecting food ingredients that are close to their expiration date. Based on inventory data, if there are tomatoes with an expiration date of less than a week, for example, it sends an alert to the terminal saying, "The expiration date of the tomatoes is approaching. Please use or sell them immediately."

[0999] Food items that are close to their expiration date are sold online. Users can access the online platform using their PC or smartphone and purchase food items that are close to their expiration date at a discounted price.

[1000] The server also suggests optimal cooking methods and recipes based on the ingredients purchased. For example, if a user purchases tomatoes, it will suggest recipes such as "pasta with tomato sauce" and "caprese."

[1001] Emotional data is also utilized. The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, allowing it to provide services that reflect the user's emotions. For example, if a user gives feedback that their last order was "bland," the server can suggest a recipe for "pasta with spicy tomato sauce" for the next order.

[1002] In this way, the system of the present invention not only optimizes food supply and demand forecasts and inventory management, reducing food waste, but also significantly improves the management efficiency of restaurants by providing personalized services to users. Furthermore, it is possible to improve customer satisfaction by making suggestions using emotion data.

[1003] An example prompt could be, "Based on your past feedback and purchase history, what improvements or new suggestions would you consider making a purchase with us again?"

[1004] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1005] Step 1:

[1006] The server collects past sales data, seasonal data, and customer preference data from the POS system via API. The input is the POS system's API endpoint, and the output is the collected dataset. A specific example of data collection is to obtain a week's worth of sales data every Monday and store it in a database.

[1007] Step 2:

[1008] The server preprocesses the collected data, removing outliers and filling in missing values ​​to prepare the data for analysis. The input is the collected dataset, and the output is the preprocessed dataset. Specifically, it uses the Python pandas library to fill in missing values ​​with the mean and exclude clearly erroneous data.

[1009] Step 3:

[1010] The server uses a generative AI model (ChatGPT) to perform supply and demand forecasts using the preprocessed data. The input is the preprocessed dataset, and the output is the prediction results. Specifically, it sends prompts to ChatGPT to perform demand forecasts. For example, it sends a prompt such as, "What is the demand for chicken in the third week of December?"

[1011] Step 4:

[1012] The server calculates the optimal order quantity based on the forecast results. The inputs are the supply and demand forecast results, current inventory data, and past order history, and the output is the optimal order quantity. Specifically, the server uses an algorithm to calculate the most efficient order quantity, taking into account inventory levels and past order history.

[1013] Step 5:

[1014] The server detects ingredients that are close to their expiration date and manages the information. The input is inventory data, and the output is a list of ingredients that are close to their expiration date. For example, the server detects from the inventory data that "the expiration date for tomatoes is October 15, 2023" and lists that information.

[1015] Step 6:

[1016] The terminal notifies inventory alerts for ingredients that are nearing their expiration date. The input is a list of ingredients that are nearing their expiration date, and the output is an alert notification. Specifically, the terminal displays an alert saying, "The tomatoes are nearing their expiration date. Please use or sell them immediately."

[1017] Step 7:

[1018] The server sells food items with an approaching expiration date on an online platform. The input is a list of food items with an approaching expiration date, and the output is a sales page for the online shop. Specifically, the server automatically posts information about food items with an approaching expiration date on the online platform.

[1019] Step 8:

[1020] A user purchases ingredients at a discounted price through an online platform. The input is the customer's order information from the online shop, and the output is a notification that the purchase has been completed. Specifically, the user selects ingredients and completes the purchase procedure using a smartphone or PC.

[1021] Step 9:

[1022] The server provides cooking methods and recipes based on purchased ingredients. The input is information about the purchased ingredients, and the output is a suggested recipe. For example, if a user purchases tomatoes, the server generates a recipe for "pasta with tomato sauce" and sends it to the user.

[1023] Step 10:

[1024] The server analyzes the emotional data and provides personalized services based on the user's emotions. The input is the user's feedback and purchase history, and the output is personalized service suggestions. Specifically, the system analyzes the feedback using an emotion engine and suggests a recipe, for example, "pasta with spicy tomato sauce."

[1025] Step 11:

[1026] The user enjoys cooking using the suggested recipes and cooking methods. The input is the suggested recipe and cooking method, and the output is the finished dish. Specific operations involve cooking by following the instructions on the smart glasses and the voice assistant.

[1027] 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.

[1028] 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.

[1029] 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.

[1030] [Fourth embodiment]

[1031] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1032] 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.

[1033] 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).

[1034] 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.

[1035] 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.

[1036] 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).

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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.

[1041] 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.

[1042] 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.

[1043] 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."

[1044] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. Below, we will create a program for the system and explain its processing in natural language.

[1045] Main component description

[1046] Data collection

[1047] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. For example, it can be configured to collect a week's worth of data every Monday.

[1048] Data analysis and demand forecasting

[1049] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT to generate demand forecasts that take into account weekends, holidays, and seasonal events. For example, it can predict increased demand for chicken and cake ingredients during the Christmas season in December.

[1050] Order quantity optimization

[1051] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. Based on the calculation results, the server then sends an ordering proposal to the restaurant's terminal, where it can be checked by the manager.

[1052] Best before date management

[1053] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the restaurant's terminal.

[1054] Online sales

[1055] The server posts food items that are close to their expiration date on the online platform, allowing users to purchase them. For example, users can access the platform from their home PC or smartphone and purchase tomatoes or lettuce that are close to their expiration date.

[1056] Cooking suggestions

[1057] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, the server will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[1058] Specific examples

[1059] Data Collection Example

[1060] The server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores it in the database. At the same time, it can also collect information about the weather and events that day.

[1061] Demand forecast example

[1062] The server uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends that restaurants order 1.2 times the amount of chicken they ordered last year.

[1063] Example of expiration date management

[1064] The server detects from inventory information that the expiration date for the tomatoes is October 15, 2023, and sends an alert notification.The restaurant's terminal then displays an alert saying, "The expiration date for the tomatoes is approaching. Please use or sell them immediately."

[1065] Online sales example

[1066] A user accesses the online platform from their home PC and purchases tomatoes with a best-by date of October 10, 2023 at a discounted price. After the purchase procedure is completed, the server sends the user a recipe for "Pasta with Tomato Sauce."

[1067] In this way, this invention optimizes food supply and demand forecasts and inventory management, reduces waste, and maximizes profits. This invention significantly improves the management efficiency of restaurants and also provides convenient and attractive services to customers.

[1068] The processing flow will be explained below.

[1069] Step 1:

[1070] The server periodically accesses the restaurant's POS system to collect past sales data, seasonal data, and customer preference data. For example, it can be set to retrieve a week's worth of sales data every Monday. This data collection is performed automatically through the API.

[1071] Step 2:

[1072] The server converts and formats the data before storing it in the database. This includes filling in missing values ​​and removing outliers. For example, it filters out data with zero sales volume or other obviously abnormal values.

[1073] Step 3:

[1074] The server stores the formatted data in a database. The stored data includes product name, sales quantity, sales date, and customer attributes (age, gender, etc.). For example, sales data and customer information for October 1, 2023 are recorded in the corresponding tables in the database.

[1075] Step 4:

[1076] The server retrieves historical sales data, seasonal data, and customer preference data from the database. This is a pre-processing step for demand forecasting. The retrieved data covers a certain period (e.g., the past three years).

[1077] Step 5:

[1078] The server preprocesses the data it receives. Specifically, it normalizes and standardizes the data to make it suitable for analysis. For example, it converts sales volume into average values ​​for each week or month.

[1079] Step 6:

[1080] The server analyzes the data using ChatGPT to predict future demand, taking into account seasonality and the influence of specific events (e.g., Christmas and Valentine's Day). The forecast results are output as numerical data for further processing.

[1081] Step 7:

[1082] The server calculates the optimal order quantity based on the forecast results, taking into account current inventory levels and past order history. For example, if demand for chicken is predicted, it compares it with current inventory and calculates the required additional order quantity.

[1083] Step 8:

[1084] The server generates an ordering proposal based on the calculation results and sends a notification to the restaurant's administrator's terminal. The notification includes the specific order quantity and the recommended ordering time. The administrator places the order based on this information.

[1085] Step 9:

[1086] The server identifies ingredients that are close to expiry based on current inventory data. For example, it lists ingredients that are within a week of expiry. This process is important for efficient inventory management.

[1087] Step 10:

[1088] The server sends alerts to restaurant terminals about ingredients that are nearing their expiration date. The notifications include a list of ingredients that need to be used or sold immediately. The administrator can then take appropriate action based on this information.

[1089] Step 11:

[1090] The server posts food items that are nearing their expiration date on an online platform. Users can access the platform from their PCs or smartphones to check and purchase these food items. For example, users can view information about tomatoes and lettuce that are available at discounted prices.

[1091] Step 12:

[1092] A user purchases ingredients through the online platform, and once the purchase is complete, the server records the information in a database and sends a confirmation email to the purchaser.

[1093] Step 13:

[1094] The server generates appropriate cooking methods and recipes based on the purchased ingredients and provides them to the user. For example, if a user purchases tomatoes, the server sends a recipe for "pasta with tomato sauce" to the user for cooking reference.

[1095] In this way, the system optimizes food supply and demand forecasts and inventory management throughout a series of processing steps, reducing food waste and maximizing profits.

[1096] Example 1

[1097] 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."

[1098] In restaurants, predicting supply and demand for ingredients and managing inventory is labor-intensive and difficult to do efficiently. Inaccurate predictions can lead to shortages or surpluses of ingredients, resulting in economic losses and increased waste. Furthermore, there is a lack of mechanisms for managing ingredients approaching their expiration date or for encouraging their consumption at the appropriate time. The objective of this invention is to provide a system that solves these problems and achieves optimal supply and demand prediction and inventory management.

[1099] 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.

[1100] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for preprocessing the collected data to remove outliers and impute missing values, means for analyzing the collected data and using a generative AI model to predict demand for ingredients, means for calculating optimal order quantities based on the prediction results, means for detecting ingredients with approaching expiration dates and managing information, means for listing the detected ingredients on an online platform so that users can purchase them, and means for suggesting cooking methods for the ingredients via the online platform.This enables restaurants to efficiently and accurately predict supply and demand and manage inventory, thereby reducing food waste and maximizing profits.

[1101] "Past sales data" refers to data that records the past sales performance of a restaurant.

[1102] "Seasonal data" is data relating to a particular season, time of year, or event, such as fluctuations in demand for a particular product during a particular season.

[1103] "Customer preference data" refers to data related to a customer's purchasing behavior and preferences. For example, it includes information about a customer's favorite dishes and frequently purchased products.

[1104] "Collection means" refers to the methods and devices used to acquire and store data.

[1105] "Preprocessing" is a data cleansing process that removes outliers from collected data and fills in missing values.

[1106] An "outlier" is a value in the data that is significantly different from the other data.

[1107] "Missing values" are pieces of data that are missing or incomplete.

[1108] A "generative AI model" is a type of artificial intelligence model that learns patterns from large amounts of data and makes predictions and classifications. Specifically, this applies to models that use machine learning or deep learning.

[1109] "Order quantity" refers to the amount of ingredients purchased by a restaurant.

[1110] "Best before date" refers to the date by which food ingredients can be consumed while still maintaining their quality.

[1111] An "online platform" is a service or application provided over the Internet.

[1112] An "alert" is a warning or caution mechanism that notifies you when certain conditions are met.

[1113] "Cooking method" refers to the steps and recipes for processing and cooking ingredients.

[1114] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. Below, we will create a program for this system and explain its processing in natural language.

[1115] Data collection

[1116] The server periodically collects data from the restaurant's POS system. This collection is automated and can be set to retrieve a week's worth of sales data, weather data, event data, etc., every Monday at 2:00 AM. The specific hardware used is a POS system and a server. This allows data on past sales, seasonality, and customer preferences to be collected.

[1117] Data analysis and demand forecasting

[1118] The server preprocesses the collected data. Specifically, it removes outliers and fills in missing values. Then, it uses the generative AI model to make a demand forecast. Seasons and special events are taken into account when making demand forecasts. Specifically, the server detects and deletes or corrects abnormal data, and fills in missing data based on past trends. The following prompt statement is used to make a demand forecast for the generative AI model:

[1119] Example: "Based on the past three years of data, please predict demand for the third week of December."

[1120] Order quantity optimization

[1121] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. The specific hardware used is a database and calculation algorithms that run on the server. The calculation results are sent to the restaurant's terminal, where they can be viewed by the manager.

[1122] Best before date management

[1123] The server searches inventory data for ingredients with an approaching expiration date and lists them. This information is then sent to the restaurant's terminal as an alert notification. Specifically, the server queries the inventory database, identifies items with an approaching expiration date, generates an alert for the identified ingredients, and sends it to the terminal. The terminal displays a message saying, "The tomatoes are nearing their expiration date. Please use or sell them immediately."

[1124] Online sales

[1125] The server posts food items with approaching expiration dates on the online platform, making them available for purchase by users. Specifically, the server connects to the online platform's database, adds new product information, and lists the product's expiration date, price, quantity, etc. Users access the platform from their home PC or smartphone, select products, and complete the purchase process.

[1126] Cooking suggestions

[1127] The server suggests optimal cooking methods and recipes based on the purchased ingredients. Specifically, the server checks the purchase history, searches the database for corresponding recipes, and notifies the user of the found recipes. The user can then enjoy cooking using the suggested recipes as a reference.

[1128] In this way, this system enables efficient and accurate forecasting of food supply and demand and inventory management, allowing restaurants to reduce food waste and maximize profits. It also improves customer satisfaction by providing convenient and attractive services to users.

[1129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1130] Step 1:

[1131] The server periodically collects data from the restaurant's POS system. The input data is past sales data, seasonal data, and customer preference data. Specifically, the server sends an API request to the POS system to obtain sales data. The obtained data is stored in a database. The output is the collected data.

[1132] Step 2:

[1133] The server preprocesses the collected data. The input data are the sales data, seasonal data, and customer preference data collected in step 1. Specifically, the server detects anomalous data and deletes or corrects it. Missing data is complemented based on past trends. The output is the preprocessed data.

[1134] Step 3:

[1135] The server analyzes the preprocessed data and uses the generative AI model to make demand forecasts. The input data are preprocessed sales data, seasonal data, and customer preference data. Specifically, the server sends a prompt to the generative AI model to request a supply and demand forecast. For example, a prompt such as "Please predict demand for the third week of December based on data from the past three years" is used. The output is the demand forecast results.

[1136] Step 4:

[1137] The server calculates the optimal order quantity based on the demand forecast results. The input data is the demand forecast results, current inventory levels, and past order history. Specifically, the server calculates the optimal order quantity based on this data and sends the result to the restaurant's terminal. The output is a proposal for the optimal order quantity.

[1138] Step 5:

[1139] The server detects ingredients that are close to their expiration date from inventory data and manages the information. The input data is the current inventory data. Specifically, the server queries the inventory database to identify ingredients that are close to their expiration date. It generates an alert for the identified ingredients and sends it to the terminal. The terminal displays, "Tomatoes are close to their expiration date. Please use or sell them immediately." The output is an inventory alert.

[1140] Step 6:

[1141] The server posts food items with approaching expiration dates on an online platform so that users can purchase them. The input data is information about food items with approaching expiration dates. Specifically, the server connects to the online platform's database and adds new product information. Product information includes expiration dates, prices, quantities, etc. Users access the platform, select products, and complete the purchase process. The output is online sales information.

[1142] Step 7:

[1143] The server suggests optimal cooking methods and recipes based on purchased ingredients. The input data is the purchase history. Specifically, the server checks the purchase history and searches the database for corresponding recipes. It notifies the user of the recipes found, and the user can enjoy cooking using the suggested recipes as a reference. The output is cooking methods and recipe information.

[1144] (Application example 1)

[1145] 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."

[1146] Forecasting supply and demand and managing inventory for ingredients in restaurants is extremely complex, and if not done efficiently, food waste and shortages are likely to occur. Furthermore, inadequate management of ingredients with approaching expiration dates can lead to increased food waste. These issues are also common in delivery services, where efficient operation is essential, as it is particularly difficult to respond to fluctuations in demand.

[1147] 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.

[1148] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for analyzing the collected data and forecasting demand for ingredients, means for calculating optimal order quantities based on the forecast results, means for detecting ingredients with approaching expiration dates and managing information, means for selling the detected ingredients online, means for suggesting cooking methods for ingredients via an online platform, a smartphone application means for supporting demand forecasting and inventory management for food delivery services, and means for suggesting optimal recipes based on ingredients purchased by customers. This enables optimal ingredient demand forecasting and inventory management at restaurants and delivery services, reducing food waste and enabling efficient inventory management.

[1149] "Past sales data" refers to records of the quantity and value of products sold in the past by restaurants and delivery services.

[1150] "Seasonal data" is information about fluctuations in sales or demand during particular seasons or times of the year.

[1151] "Customer preference data" refers to data relating to a customer's purchasing history and preferences.

[1152] "Food demand forecast" is a calculation aimed at predicting future food consumption based on past data and current conditions.

[1153] The "optimal order quantity" is the appropriate order quantity of a specified ingredient based on predicted demand.

[1154] "Shorting shelf life ingredients" are ingredients that are approaching the date when they are suitable for use or consumption.

[1155] "Online sales" means trading goods over the Internet.

[1156] An "online platform" is a collection of basic infrastructure and services for providing products and services over the Internet.

[1157] "Suggesting a cooking method" means providing a dish and steps to make it using specific ingredients.

[1158] A "smartphone application" is application software that runs on a smartphone.

[1159] "Suggesting the best recipe based on the ingredients purchased by the customer" means providing cooking procedures and methods that are best suited to the ingredients acquired by the customer.

[1160] MODE FOR CARRYING OUT THE INVENTION

[1161] This invention is a system for optimizing food supply and demand forecasting and inventory management in restaurants and delivery services. This system consists of the following main components and processing steps:

[1162] Key Components

[1163] server

[1164] The server runs a program that includes the following means:

[1165] 1. Data collection methods:

[1166] The server periodically collects past sales data, seasonal data, and customer preference data from the POS systems of restaurants and delivery services. For example, it can be configured to collect a week's worth of data every Monday.

[1167] 2. Data analysis and demand forecasting tools:

[1168] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses a generative AI model (such as ChatGPT) to forecast demand. For example, it can predict that demand for chicken and cake ingredients will increase during the Christmas season in December.

[1169] 3. Measures to optimize order quantity:

[1170] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history.

[1171] 4. Best before date control measures:

[1172] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the terminals of restaurants and delivery services.

[1173] 5. Online sales channels:

[1174] The server places ingredients that are nearing their expiry date on an online platform for users to purchase.

[1175] 6. Suggested cooking methods for ingredients:

[1176] The server will suggest the best cooking method and recipe based on the ingredients purchased.

[1177] 7. Smartphone application means:

[1178] Users can access these functions through a smartphone application that forecasts food supply and demand, assists with inventory management, and also sells food that is nearing its expiration date and suggests cooking methods.

[1179] Specific examples

[1180] For example, the server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores this information in the database. At the same time, weather and event information for that day can also be collected.

[1181] The server then uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends ordering 1.2 times the amount of chicken ordered last year.

[1182] Regarding expiration date management, the server will detect from inventory information that the expiration date for tomatoes is October 15, 2023, and send an alert notification. The smartphone application will then display the message, "The expiration date for tomatoes is approaching. Please use or sell them immediately."

[1183] In the online sales example, a user can access the online platform from their smartphone at home and purchase tomatoes with a best-by date of October 10, 2023 at a discounted price. After completing the purchase process, a recipe for "Pasta with Tomato Sauce" is provided to the user through the app.

[1184] Prompt Sentence Examples

[1185] The following prompts can be used to provide input to the generative AI model:

[1186] Please use the following data to forecast supply and demand for the next week and calculate the optimal order quantity:

[1187] Sales data: 50 tomatoes, 30 lettuce, 20 chicken.

[1188] Current inventory: 30 tomatoes, 20 lettuces, 10 chicken.

[1189] Average sales data for the past three years: 45 tomatoes, 35 lettuce, 25 chicken.

[1190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1191] Step 1:

[1192] The server collects historical sales data, seasonal data, and customer preference data from the POS system. This data is collected periodically by the server and stored in a database. Inputs include sales data (e.g., Dish A: 50 units, Dish B: 30 units), weather information, event information, etc. As an output, an organized dataset is stored in the database.

[1193] Step 2:

[1194] The server preprocesses the collected data, removing outliers and imputing missing values. It uses data analysis software to remove inaccurate data from the input dataset and impute missing values. The output is a clean dataset. Specific operations include identifying and removing outlier data points and imputing missing values ​​using the mean or median.

[1195] Step 3:

[1196] The server uses a generative AI model based on the preprocessed data to make demand forecasts, taking into account weekends, holidays, seasonal events, etc. Past sales data, seasonal data, and customer preference data are used as input. The output is the predicted demand volume. Specific operations involve entering a prompt into ChatGPT and receiving the prediction results. For example, the prediction result may be, "Demand for chicken will increase by 20% year-on-year in the third week of December."

[1197] Step 4:

[1198] The server calculates the optimal order quantity based on the demand forecast. At this time, it also takes into account the current inventory level and past order history. The inputs are the predicted demand, current inventory level, and past order history. The output is the specific order quantity. The specific operation is to calculate the optimal order quantity using a calculation algorithm. For example, the result may be, "We suggest ordering 1.2 times the previous year's order quantity for chicken."

[1199] Step 5:

[1200] The server searches through inventory data for ingredients with upcoming expiration dates and lists them. The inputs are inventory data and expiration date data. The output is a list of ingredients with upcoming expiration dates. Specifically, it checks the expiration date of each ingredient and identifies ingredients whose expiration date is within one week. For example, it obtains information such as "the expiration date of tomatoes is October 15, 2023."

[1201] Step 6:

[1202] The server posts ingredients with upcoming expiration dates on an online platform, allowing users to purchase them. The input is a list of ingredients with upcoming expiration dates. The output is the item information posted on the online platform. Specific operations include uploading information about each ingredient to an online database and making it accessible to users. For example, the server may post information such as "Tomatoes available at a discount."

[1203] Step 7:

[1204] Based on the purchased ingredients, the server suggests the most suitable cooking method and recipe. The information on the purchased ingredients is used as input. The recipe information is provided to the user as output. Specifically, the server searches for the most suitable recipe from a pre-registered recipe database based on the purchased ingredients and notifies the user of the recipe. For example, it suggests a recipe such as "pasta with tomato sauce."

[1205] 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.

[1206] This invention relates to a system that optimizes food supply and demand forecasts and inventory management in restaurants, reducing food waste, and providing more personalized service by recognizing user emotions. Below, we will create a system program and explain its processing in natural language.

[1207] Main component description

[1208] Data collection

[1209] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. For example, it can be configured to retrieve a week's worth of sales data every Monday. This data collection is performed automatically through an API.

[1210] Data analysis and demand forecasting

[1211] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT to generate demand forecasts that take into account weekends, holidays, and seasonal events. For example, it can predict increased demand for chicken and cake ingredients during the Christmas season in December.

[1212] Order quantity optimization

[1213] The server calculates the optimal order quantity based on the demand forecast, taking into account current inventory levels and past order history. Based on the calculation results, the server then sends an ordering proposal to the restaurant's terminal, where it can be reviewed by the manager.

[1214] Best before date management

[1215] The server searches through inventory data to find ingredients with an approaching expiration date and lists them. For example, it can identify ingredients with an expiration date within a week and send an alert to the restaurant's terminal.

[1216] Online sales

[1217] The server posts food items that are close to their expiration date on the online platform, allowing users to purchase them. For example, users can access the platform from their home PC or smartphone and purchase tomatoes or lettuce that are close to their expiration date.

[1218] Cooking suggestions

[1219] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, the server will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[1220] Introducing the Emotion Engine

[1221] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if the user gave feedback indicating dissatisfaction with their previous order, the emotion engine will take that into consideration and suggest products that will provide greater satisfaction the next time.

[1222] Specific examples

[1223] Data Collection Example

[1224] The server obtains sales data for October 1st from the POS system, such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units," and stores it in the database. At the same time, it can also collect information about the weather and events that day.

[1225] Demand forecast example

[1226] The server uses data from the past three years to forecast demand and predicts that demand for chicken will increase by 20% year-on-year in the third week of December. Based on this, it recommends that restaurants order 1.2 times the amount of chicken they ordered last year.

[1227] Example of expiration date management

[1228] The server detects from inventory information that the expiration date for the tomatoes is October 15, 2023, and sends an alert notification.The restaurant's terminal then displays an alert saying, "The expiration date for the tomatoes is approaching. Please use or sell them immediately."

[1229] Online sales example

[1230] A user accesses the online platform from their home PC and purchases tomatoes with a best-by date of October 10, 2023 at a discounted price. After the purchase procedure is completed, the server sends the user a recipe for "Pasta with Tomato Sauce."

[1231] Example of using the emotion engine

[1232] If a user previously ordered pasta with tomato sauce and gave feedback that it was "bland," the emotion engine would analyze that feedback and suggest a recipe for "pasta with spicy tomato sauce" the next time the user buys tomatoes, thereby improving user satisfaction.

[1233] In this way, this invention not only optimizes food supply and demand forecasts and inventory management, reduces waste, and maximizes profits, but also provides personalized services that take into account user emotions. Therefore, the invention not only significantly improves the management efficiency of restaurants, but also increases customer satisfaction.

[1234] The processing flow will be explained below.

[1235] Step 1:

[1236] The server periodically accesses the POS system to collect past sales data, seasonal data, and customer preference data. For example, you can set it to retrieve a week's worth of sales data every Monday. The data is then automatically collected via API.

[1237] Step 2:

[1238] The server converts the format of the acquired data and stores it in a database. Data conversion involves standardizing dates, categorizing data, filling in missing values, and removing outliers. For example, data with zero or negative sales volume is filtered out.

[1239] Step 3:

[1240] The server retrieves the saved data from the database and performs pre-processing for analysis. Here, sales figures are aggregated daily, weekly, and monthly, and formatted into a form suitable for analysis. For example, the sales figures for a specific product can be aggregated for each day of the week.

[1241] Step 4:

[1242] The server uses ChatGPT to analyze the collected data and predict demand for the next month. Forecasts are based on past sales patterns, seasonal data, and campaign information. For example, it predicts that demand for chicken will increase by 20% year-on-year during the Christmas season in December.

[1243] Step 5:

[1244] The server calculates the optimal order quantity based on the forecast results. It also takes into account current inventory and past order history to calculate the required additional order quantity. For example, if there are 50 chickens in stock and the forecast demand is 80, an additional 30 units will need to be ordered.

[1245] Step 6:

[1246] The server then sends the calculated ordering suggestions to the restaurant's administrator's terminal, which displays the specific order quantity and recommended ordering time, allowing the administrator to proceed with the ordering process based on that information.

[1247] Step 7:

[1248] The server periodically checks inventory data to identify ingredients that are close to their expiration date. For example, it detects ingredients that are within a week of their expiration date and generates a list of them.

[1249] Step 8:

[1250] The server sends alerts to restaurant terminals about ingredients that are nearing their expiration date. The terminals display a message saying, "The tomatoes are nearing their expiration date. Please use or sell them as soon as possible." The administrator can then take prompt action based on this information.

[1251] Step 9:

[1252] The server posts food items that are close to their expiration date on the online platform. Users can access the platform from their home PC or smartphone and purchase the food items. For example, users can purchase tomatoes that are close to their expiration date at a discounted price.

[1253] Step 10:

[1254] A user purchases ingredients through the online platform. Once the purchase is complete, the server records the information in a database and sends the user a purchase confirmation email.

[1255] Step 11:

[1256] The server provides appropriate cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, it generates a recipe for "pasta with tomato sauce" and sends it by email.

[1257] Step 12:

[1258] The server uses an emotion engine to analyze the user's past purchase history and feedback. For example, if the user gave feedback that they were dissatisfied with their previous order, the emotion engine will take that into account the next time and suggest products or recipes that will be more satisfying.

[1259] Step 13:

[1260] The server provides services according to the user's emotional state based on the results of the emotion engine's analysis. If the user's feedback last time was that the tomato sauce pasta was "bland," the server will suggest a recipe for "spicy tomato sauce pasta" next time. This will improve user satisfaction.

[1261] In this way, the system can optimize supply and demand forecasts and inventory management throughout a series of processing steps, reducing food waste and maximizing profits, as well as providing personalized service that takes user emotions into account.

[1262] Example 2

[1263] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1264] It is important for restaurants to forecast food supply and demand and manage inventory more efficiently to reduce food waste. Another challenge is to improve customer satisfaction by recognizing user emotions and providing personalized services. Conventional systems have difficulty meeting these multifaceted requirements, so a new system that can solve these challenges is needed.

[1265] The identification processing 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 past data, means for preprocessing the collected data, means for analyzing the preprocessed data and predicting demand for ingredients, means for calculating optimal order quantities based on the prediction results, means for detecting ingredients that are close to their expiration date and issuing alerts, means for selling the detected ingredients online, means for suggesting cooking methods for the ingredients via an online platform, and means for analyzing users' past purchase histories and feedback and providing personalized services. This enables optimization of ingredient supply and demand predictions and inventory management, reducing ingredient waste and improving customer satisfaction.

[1266] "Past data" refers to information accumulated in the past, such as a restaurant's sales history, seasonal data, and customer preference data.

[1267] "Means of collection" refers to a device or system that automatically acquires the necessary data using APIs, sensors, etc.

[1268] A "preprocessing means" is a device or system that removes outliers and fills in missing values ​​in order to convert data into a format that is easier to analyze.

[1269] "Means of analysis" refers to algorithms and software that predict future demand, etc. based on collected and preprocessed data.

[1270] A "demand forecasting means" is a device or system that forecasts the demand for food ingredients at a specific time based on collected data.

[1271] The "means for calculating the optimal order quantity" refers to an algorithm or device that calculates the effective order quantity based on the demand forecast results and the current inventory status.

[1272] The "means for detecting food ingredients approaching their expiration date and issuing an alert notification" is a system that identifies products approaching their expiration date from inventory data and issues a warning to the administrator.

[1273] The "means for selling detected food ingredients online" is a system that posts food ingredients that are close to their expiration date on an internet platform, allowing users to purchase them.

[1274] The "means for suggesting cooking methods" is a device or system for providing users with optimal cooking methods and recipes based on specific ingredients.

[1275] "Means of analyzing past purchase history and feedback to provide personalized services" refers to a system that analyzes a user's preferences and emotions based on the purchases and feedback information they have made to date, and makes personalized suggestions.

[1276] This invention is a system for optimizing food supply and demand forecasts and inventory management in restaurants, thereby reducing food waste. It also aims to recognize user emotions and provide personalized services. A specific embodiment of the system is described below.

[1277] Data collection

[1278] The server periodically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system. This data is automatically retrieved through an API. For example, it can be configured to retrieve a week's worth of sales data every Monday. After collecting this data, the server stores the necessary information in a database.

[1279] Data Preprocessing

[1280] The collected data is preprocessed by the server. Data cleaning is performed, such as removing outliers and filling in missing values. Specifically, outliers are removed from the collected sales data, and missing data is filled in appropriately.

[1281] Demand forecasting

[1282] The server uses a generative AI model (e.g., ChatGPT) to forecast demand based on the preprocessed data. For example, the server uses data from the past three years to predict that demand for chicken will increase by 20% year-on-year in the third week of December. This forecast result is stored in a database and used in the next step.

[1283] Order quantity optimization

[1284] The server calculates the optimal order quantity based on the demand forecast results and current inventory information. For example, if the forecasted demand is expected to increase by 20% compared to the previous year, it will suggest ordering 1.2 times the previous year's amount. This suggestion is sent to the restaurant's terminal and can be confirmed by the manager.

[1285] Best before date management

[1286] The server searches inventory data for ingredients with upcoming expiration dates and lists them. For example, it might identify that tomatoes have an expiration date of October 15, 2023, and send an alert to the restaurant's terminal saying, "The expiration date of the tomatoes is approaching. Please use or sell them immediately."

[1287] Online sales

[1288] The server posts food items with upcoming expiration dates on the online platform, allowing users to purchase them. For example, a user can access the online platform from their home PC or smartphone and purchase tomatoes with an expiration date of October 10, 2023, at a discounted price.

[1289] Cooking suggestions

[1290] The server suggests the best cooking methods and recipes based on the purchased ingredients. For example, if a user purchases tomatoes, it will provide recipes such as pasta with tomato sauce or Caprese. Users can enjoy cooking using the suggested recipes.

[1291] Introducing the Emotion Engine

[1292] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if a user previously ordered pasta with tomato sauce and gave feedback that it was "bland," the emotion engine would analyze that feedback and suggest a recipe for "pasta with spicy tomato sauce" the next time the user purchases tomatoes. This can improve user satisfaction.

[1293] Prompt Sentence Examples

[1294] Demand forecast prompt

[1295] "Using sales data from the past three years, please forecast the demand for chicken for the third week of December. Based on that, please propose an order quantity that is 1.2 times the previous year's order quantity."

[1296] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1297] Step 1: Data collection

[1298] The server automatically collects past sales data, seasonal data, and customer preference data from the restaurant's POS system using an API. For example, you can set it to retrieve a week's worth of sales data every Monday and store data such as "Dish A: 50 units, Dish B: 30 units, Dish C: 20 units" in a database. In this case, the input data is sales information from the POS system, and the output is the sales data stored in the database.

[1299] Step 2: Data Preprocessing

[1300] The server preprocesses the collected data. Specifically, it removes outliers and fills in missing values. For example, if sales data contains abnormal values ​​(outliers), it removes them and fills in missing data by inferring it from other data. The input in this step is the collected raw data, and the output is preprocessed, clean data.

[1301] Step 3: Demand forecast

[1302] The server uses a generative AI model (for example, ChatGPT) to make a demand forecast based on the preprocessed data. The prompt text input to the generative AI model is, "Using sales data from the past three years, please predict the demand for chicken in the third week of December. Also, based on that, please suggest an order quantity that is 1.2 times the previous year's order quantity." This results in a prediction that demand for chicken in the third week of December will increase by 20% compared to the previous year. This prediction result is saved in a database.

[1303] Step 4: Optimize order quantity

[1304] The server calculates the optimal order quantity based on the demand forecast results and current inventory information. For example, based on a forecasted demand increase of 20% compared to the previous year, it calculates 1.2 times the order quantity from the previous year and proposes a new order quantity. The inputs in this step are the demand forecast results and inventory data, and the outputs are the calculated order quantity and its proposed order.

[1305] Step 5: Submitting an order proposal

[1306] The server sends an ordering proposal based on the calculation results to the restaurant's terminal. The administrator checks the ordering proposal on the terminal and approves or modifies it as necessary. The input in this step is the optimized order quantity, and the output is the ordering proposal displayed on the restaurant's terminal.

[1307] Step 6: Best before date management

[1308] The server searches through inventory data for ingredients with upcoming expiration dates and lists them. For example, it identifies that "the expiration date for tomatoes is October 15, 2023," and based on that information, it sends an alert notification to the restaurant's terminal saying, "The expiration date for tomatoes is approaching. Please use or sell them immediately." The input in this step is inventory data, and the output is an alert notification displayed on the terminal.

[1309] Step 7: Sell online

[1310] The server posts food items with an approaching expiration date on an online platform. Users can access the online platform from their home PC or smartphone and purchase tomatoes with an expiration date of October 10, 2023 at a discounted price. The input in this step is information about food items with an approaching expiration date, and the output is the information posted on the online platform.

[1311] Step 8: Cooking suggestions

[1312] The server suggests optimal cooking methods and recipes based on the purchased ingredients. For example, if the user purchases tomatoes, it will provide recipes such as pasta with tomato sauce or Caprese. The input in this step is the purchased ingredients, and the output is the recipe information provided to the user.

[1313] Step 9: Implementing the Emotion Engine

[1314] The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, and provides services according to the user's emotions. For example, if a user previously ordered pasta with tomato sauce and provided feedback that it was "bland," the emotion engine analyzes that feedback and suggests a recipe for "pasta with spicy tomato sauce" the next time the user purchases tomatoes. The input in this step is the user's past purchase history and feedback information, and the output is personalized service suggestions.

[1315] (Application example 2)

[1316] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1317] Conventional restaurant supply and demand forecasting and inventory management systems make it difficult to reduce food waste and are unable to provide personalized service to customers. Furthermore, because services are provided without taking into account customer emotions, it is not possible to increase customer satisfaction.

[1318] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1319] In this invention, the server includes means for collecting past sales data, seasonal data, and customer preference data, means for analyzing the collected data and forecasting demand for ingredients, means for calculating optimal order quantities based on the forecast results, means for detecting ingredients with approaching expiration dates and managing information, means for selling the detected ingredients online, means for suggesting cooking methods for the ingredients via an online platform, and means for collecting emotion data and providing personalized services based on the user's emotions, thereby making it possible to reduce food waste and provide personalized services to users.

[1320] "Past sales data" refers to the sales performance of products recorded in the past by a restaurant, and includes details such as the specific sales quantity and the date and time of the sales.

[1321] "Seasonal data" refers to sales data or data that shows consumer behavior patterns that fluctuate based on specific seasons or events.

[1322] "Customer preference data" is data that represents the tendencies of individual customers, such as their purchase history, ratings, and favorite dishes and ingredients.

[1323] "Emotional data" is data that indicates customer emotions and reactions, extracted from feedback, reviews, etc. provided by customers.

[1324] "Supply and demand forecasting" is the process of predicting future demand for ingredients and products based on collected data.

[1325] The "optimal order quantity" is an efficient and appropriate order quantity calculated based on supply and demand forecast data to prevent unnecessary inventory and stockouts.

[1326] The "best before" date refers to the period during which the quality of ingredients or products can be maintained, and after this period the value of the product may decrease.

[1327] "Online sales" refers to the general process of selling goods over the Internet, allowing customers to purchase goods from the comfort of their own home or remotely.

[1328] "Cooking suggestions" is the process of providing recipes and cooking procedures that will make the most delicious and efficient use of purchased ingredients.

[1329] "Personalized service" refers to a service that provides optimal products and services to individual customers based on their characteristics, preferences, and emotions.

[1330] The present invention is a system that optimizes food supply and demand forecasts and inventory management in restaurants, reducing food waste and providing more personalized services by recognizing user emotions. A detailed description of the system that realizes this application example is provided below.

[1331] The system has a means for the server to collect historical sales data, seasonal data, and customer preference data. This data collection is done periodically, for example, every Monday, by obtaining a week's worth of sales data from the POS system via an API.

[1332] The server preprocesses the collected data, removing outliers and filling in missing values. It then uses ChatGPT, a generative AI model, to forecast supply and demand based on this data. For example, based on past sales data and seasonality data, it can predict that demand for chicken in the third week of December will increase by 20% compared to the previous year.

[1333] Based on the results of the supply and demand forecast, the server calculates the optimal order quantity. Here, it also takes into account current inventory levels and past order history to determine the necessary order quantity. The ordering proposal is sent to the restaurant's terminal so that the manager can check it.

[1334] Furthermore, the server has a means of detecting food ingredients that are close to their expiration date. Based on inventory data, if there are tomatoes with an expiration date of less than a week, for example, it sends an alert to the terminal saying, "The expiration date of the tomatoes is approaching. Please use or sell them immediately."

[1335] Food items that are close to their expiration date are sold online. Users can access the online platform using their PC or smartphone and purchase food items that are close to their expiration date at a discounted price.

[1336] The server also suggests optimal cooking methods and recipes based on the ingredients purchased. For example, if a user purchases tomatoes, it will suggest recipes such as "pasta with tomato sauce" and "caprese."

[1337] Emotional data is also utilized. The server is equipped with an emotion engine that analyzes the user's past purchase history and feedback, allowing it to provide services that reflect the user's emotions. For example, if a user gives feedback that their last order was "bland," the server can suggest a recipe for "pasta with spicy tomato sauce" for the next order.

[1338] In this way, the system of the present invention not only optimizes food supply and demand forecasts and inventory management, reducing food waste, but also significantly improves the management efficiency of restaurants by providing personalized services to users. Furthermore, it is possible to improve customer satisfaction by making suggestions using emotion data.

[1339] An example prompt could be, "Based on your past feedback and purchase history, what improvements or new suggestions would you consider making a purchase with us again?"

[1340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1341] Step 1:

[1342] The server collects past sales data, seasonal data, and customer preference data from the POS system via API. The input is the POS system's API endpoint, and the output is the collected dataset. A specific example of data collection is to obtain a week's worth of sales data every Monday and store it in a database.

[1343] Step 2:

[1344] The server preprocesses the collected data, removing outliers and filling in missing values ​​to prepare the data for analysis. The input is the collected dataset, and the output is the preprocessed dataset. Specifically, it uses the Python pandas library to fill in missing values ​​with the mean and exclude clearly erroneous data.

[1345] Step 3:

[1346] The server uses a generative AI model (ChatGPT) to perform supply and demand forecasts using the preprocessed data. The input is the preprocessed dataset, and the output is the prediction results. Specifically, it sends prompts to ChatGPT to perform demand forecasts. For example, it sends a prompt such as, "What is the demand for chicken in the third week of December?"

[1347] Step 4:

[1348] The server calculates the optimal order quantity based on the forecast results. The inputs are the supply and demand forecast results, current inventory data, and past order history, and the output is the optimal order quantity. Specifically, the server uses an algorithm to calculate the most efficient order quantity, taking into account inventory levels and past order history.

[1349] Step 5:

[1350] The server detects ingredients that are close to their expiration date and manages the information. The input is inventory data, and the output is a list of ingredients that are close to their expiration date. For example, the server detects from the inventory data that "the expiration date for tomatoes is October 15, 2023" and lists that information.

[1351] Step 6:

[1352] The terminal notifies inventory alerts for ingredients that are nearing their expiration date. The input is a list of ingredients that are nearing their expiration date, and the output is an alert notification. Specifically, the terminal displays an alert saying, "The tomatoes are nearing their expiration date. Please use or sell them immediately."

[1353] Step 7:

[1354] The server sells food items with an approaching expiration date on an online platform. The input is a list of food items with an approaching expiration date, and the output is a sales page for the online shop. Specifically, the server automatically posts information about food items with an approaching expiration date on the online platform.

[1355] Step 8:

[1356] A user purchases ingredients at a discounted price through an online platform. The input is the customer's order information from the online shop, and the output is a notification that the purchase has been completed. Specifically, the user selects ingredients and completes the purchase procedure using a smartphone or PC.

[1357] Step 9:

[1358] The server provides cooking methods and recipes based on purchased ingredients. The input is information about the purchased ingredients, and the output is a suggested recipe. For example, if a user purchases tomatoes, the server generates a recipe for "pasta with tomato sauce" and sends it to the user.

[1359] Step 10:

[1360] The server analyzes the emotional data and provides personalized services based on the user's emotions. The input is the user's feedback and purchase history, and the output is personalized service suggestions. Specifically, the system analyzes the feedback using an emotion engine and suggests a recipe, for example, "pasta with spicy tomato sauce."

[1361] Step 11:

[1362] The user enjoys cooking using the suggested recipes and cooking methods. The input is the suggested recipe and cooking method, and the output is the finished dish. Specific operations involve cooking by following the instructions on the smart glasses and the voice assistant.

[1363] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1364] 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.

[1365] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1366] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1367] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1368] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1369] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1370] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1371] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1372] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1373] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1374] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1375] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1376] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1377] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1378] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1379] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1380] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1381] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1382] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1383] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1384] The following is further disclosed regarding the above embodiment.

[1385] (Claim 1)

[1386] A means of collecting historical sales data, seasonality data, and customer preference data;

[1387] A means for analyzing the collected data and forecasting demand for ingredients;

[1388] A means for calculating an optimal order quantity based on the prediction result;

[1389] A means for detecting food ingredients that are close to their expiration date and managing the information;

[1390] A means to sell the detected ingredients online;

[1391] A means of suggesting cooking methods for ingredients via an online platform;

[1392] A system including:

[1393] (Claim 2)

[1394] 10. The system of claim 1, wherein the analysis means uses artificial intelligence to analyze historical sales data, seasonal data, and customer preference data.

[1395] (Claim 3)

[1396] The system according to claim 1, characterized in that the management means issues an inventory alert for food ingredients whose expiration date is approaching.

[1397] "Example 1"

[1398] (Claim 1)

[1399] A means of collecting historical sales data, seasonality data, and customer preference data;

[1400] A means of preprocessing the collected data to remove outliers and impute missing values;

[1401] By analyzing the collected data and using a generative AI model to forecast food demand,

[1402] A means for calculating an optimal order quantity based on the prediction result;

[1403] A means for detecting food ingredients that are close to their expiration date and managing the information;

[1404] a means for listing the detected ingredients on an online platform so that users can purchase them;

[1405] A means of suggesting cooking methods for ingredients via an online platform;

[1406] A system including:

[1407] (Claim 2)

[1408] 2. The system of claim 1, wherein the analysis means analyzes historical sales data, seasonality data, and customer preference data using a generative AI model.

[1409] (Claim 3)

[1410] The system according to claim 1, characterized in that the management means issues an inventory alert for food ingredients whose expiration date is approaching.

[1411] "Application Example 1"

[1412] (Claim 1)

[1413] A means of collecting historical sales data, seasonality data, and customer preference data;

[1414] A means for analyzing the collected data and forecasting demand for ingredients;

[1415] A means for calculating an optimal order quantity based on the prediction result;

[1416] a means for detecting ingredients approaching their expiration date and managing the information;

[1417] a means of selling the detected materials online;

[1418] A means to suggest cooking methods for ingredients via an online platform;

[1419] A smartphone application that supports demand forecasting and inventory management for food delivery services,

[1420] A way to suggest the best recipes based on the ingredients purchased by the customer;

[1421] A system including:

[1422] (Claim 2)

[1423] 10. The system of claim 1, wherein the analysis means uses artificial intelligence to analyze historical sales data, seasonal data, and customer preference data.

[1424] (Claim 3)

[1425] 2. The system according to claim 1, wherein the management means issues an inventory alert for ingredients that are nearing their expiration date.

[1426] "Example 2: Combining Emotion Engines"

[1427] (Claim 1)

[1428] a means of collecting historical data;

[1429] a means for pre-processing the collected data;

[1430] A means for analyzing the preprocessed data and forecasting demand for ingredients;

[1431] A means for calculating an optimal order quantity based on the prediction result;

[1432] A means for detecting food ingredients that are close to their expiration date and sending an alert notification;

[1433] A means to sell the detected ingredients online;

[1434] A means of suggesting cooking methods for ingredients via an online platform;

[1435] A means for analyzing users' past purchase history and feedback to provide personalized services;

[1436] A system including:

[1437] (Claim 2)

[1438] 2. The system of claim 1, wherein the analysis means analyzes past data using a generative AI model.

[1439] (Claim 3)

[1440] The system according to claim 1, characterized in that the alert notification means issues an inventory alert for food ingredients whose expiration date is approaching.

[1441] "Application example 2 when combining emotion engines"

[1442] (Claim 1)

[1443] A means of collecting historical sales data, seasonality data, and customer preference data;

[1444] A means for analyzing the collected data and forecasting demand for ingredients;

[1445] A means for calculating an optimal order quantity based on the prediction result;

[1446] A means for detecting food ingredients that are close to their expiration date and managing the information;

[1447] A means to sell the detected ingredients online;

[1448] A means of suggesting cooking methods for ingredients via an online platform;

[1449] means for collecting emotion data and providing personalized services based on the emotion of the user;

[1450] A system including:

[1451] (Claim 2)

[1452] 2. The system of claim 1, wherein the analysis means uses artificial intelligence to analyze historical sales data, seasonal data, customer preference data, and sentiment data.

[1453] (Claim 3)

[1454] The system according to claim 1, characterized in that the management means issues an inventory alert for food ingredients whose expiration date is approaching. [Explanation of symbols]

[1455] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting historical sales data, seasonality data, and customer preference data; A means for analyzing the collected data and forecasting demand for ingredients; A means for calculating an optimal order quantity based on the prediction result; A means for detecting food ingredients that are close to their expiration date and managing the information; A means to sell the detected ingredients online; A means of suggesting cooking methods for ingredients via an online platform; A system including:

2. 10. The system of claim 1, wherein the analysis means uses artificial intelligence to analyze historical sales data, seasonal data, and customer preference data.

3. The system according to claim 1, wherein the management means issues an inventory alert for food ingredients whose expiration date is approaching.

Images