System

Abstract

A system is provided.SOLUTION: This system includes a means for collecting production information and storing it in a database, a means for collecting the purchase history of a user and analyzing taste, a means for analyzing the demand and supply balance of a market and optimizing a price, a means for proposing a food material pack based on a generated taste profile, and a means for presenting the proposed food material pack to the user and supporting a purchase procedure.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 today's food supply chain, waste due to oversupply and the resulting economic losses are serious problems. Consumers also face challenges due to the burden imposed by intermediary fees and the difficulty of directly connecting producers and consumers, making it difficult for them to obtain information about the safety and production background of food ingredients. There is also a lack of personalized services that respond to consumers' purchasing history and preferences, resulting in food waste. This invention aims to solve these problems and improve supply chain efficiency and consumer satisfaction. [Means for solving the problem]

[0005] This invention is a system that includes the following means: a means for collecting production information and storing it in a database, a means for collecting user purchasing histories and analyzing preferences, a means for analyzing the market supply-demand balance and optimizing prices, a means for proposing food packs based on the generated preference profile, and a means for presenting the proposed food packs to the user and supporting the purchasing process. This optimizes the supply-demand balance and reduces food waste. It also meets the specific needs of consumers by providing individual food packs tailored to their preferences. Furthermore, by directly connecting producers and consumers, it is possible to improve reliability regarding the production background and safety of food ingredients.

[0006] "Production information" refers to detailed data provided by producers, such as the type of crop or food ingredient, harvest yield, and harvest time.

[0007] A "database" is a structured and systematic collection of data for efficiently storing, retrieving, and managing large amounts of data.

[0008] "Purchase history" is a record of ingredients and products purchased by a user in the past, as well as the dates and quantities associated with those purchases.

[0009] "Preferences" refers to the user's tastes and tendencies, and is data that indicates the user's predilection for specific ingredients or dishes.

[0010] "Analysis" is the process of examining collected data in detail to find hidden patterns and relationships.

[0011] "Supply and demand balance" refers to the state of equilibrium between supply and demand in the market, and is a concept that represents the degree to which supply meets demand.

[0012] "Price optimization" is the process of adjusting market prices based on the supply and demand balance to achieve optimal profits and consumer satisfaction.

[0013] "Generative AI" is a system that uses artificial intelligence technology to automatically analyze data and generate optimal solutions and suggestions for specific tasks.

[0014] A "preference profile" is a collection of information about a user's unique preferences that is created based on the user's past data.

[0015] A "food pack" is a package containing a set of multiple ingredients selected based on the consumer's preferences and needs.

[0016] "Suggestion" refers to the act of the generating AI selecting and presenting the most suitable products or food packs based on the user's preferences and past purchasing history.

[0017] The "purchase procedure" is a series of processes in which a user selects products and food packs, specifies a payment method and delivery address, and confirms an order. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0026] [First embodiment]

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

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

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

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

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

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

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

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

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

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

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0039] This invention is a system that makes the process of fresh ingredients from production to consumption transparent and optimizes supply and demand and prices using AI technology. By directly connecting producers and consumers, this system reduces food waste and proposes food packs tailored to consumer preferences.

[0040] Server Processing

[0041] Collection and analysis of purchase history:

[0042] The server periodically collects user purchase history data and stores it in a database. Based on the collected data, machine learning algorithms are used to analyze user preferences and generate a preference profile for each user. This preference profile is then used to make personalized recommendations.

[0043] Supply and demand balance analysis and price optimization:

[0044] The server receives production data provided by producers and analyzes it along with market consumption patterns. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. This price information is stored in a database and provided to user devices.

[0045] Generate personalized food pack suggestions:

[0046] The server uses AI to generate food packs based on the user's preference profile and supply-demand balance data. The food packs are optimized for the user's past consumption patterns and preferences. The information on the suggested food packs is stored in a database and later provided to the user's device.

[0047] Terminal handling

[0048] Providing a user interface:

[0049] The terminal displays to the user a food pack suggestion based on the user's purchasing history. When the user accesses the terminal, the terminal retrieves the suggested personalized food pack information from the server and displays it to the user.

[0050] Real-time pricing information:

[0051] The terminal receives real-time price information from the server and presents it to the user, who can then make a purchasing decision based on it.

[0052] Purchase assistance:

[0053] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the purchase information to the server, which then confirms the order.

[0054] User Behavior

[0055] Providing purchase history:

[0056] The user purchases ingredients in the same way as with regular online shopping, and the information is sent to the server.

[0057] Check out our ingredient pack suggestions:

[0058] The user can then view the personalized food packs suggested to them through the device, determine whether the displayed contents match their tastes and whether the price is reasonable, and then decide whether to purchase.

[0059] Purchasing decision:

[0060] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the order is sent to the server.

[0061] Specific examples

[0062] For example, suppose that data on ingredients purchased by User A multiple times in the past is stored. User A goes online shopping on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and understands User A's preferences.

[0063] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User A.

[0064] When User A views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User A can confirm the purchase with one click and receive fresh ingredients. This process reduces food waste while providing ingredients tailored to User A's preferences.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The server collects the user's purchase history data, specifically, the ingredients and products the user has purchased in the past, as well as the dates and quantities associated with those purchases.

[0068] Step 2:

[0069] The server stores the collected purchase history data in a database, which stores purchasing pattern data for each user.

[0070] Step 3:

[0071] The server analyzes the accumulated purchase history data and uses machine learning algorithms to extract user preferences and trends and generate a preference profile that specifically identifies each user's tastes and consumption tendencies.

[0072] Step 4:

[0073] The server receives production information provided by producers and stores it in a database, including detailed data such as the type of crop or ingredient, harvest yield, and harvest time.

[0074] Step 5:

[0075] The server analyzes market consumption patterns and production information to determine the market supply and demand balance. Based on the supply and demand balance data, it runs an algorithm to optimize market prices in real time. The optimized price information is also stored in a database.

[0076] Step 6:

[0077] The server uses AI to generate food packs based on the user's preference profile and supply-demand balance data. The generated food packs are optimized for the user's past consumption patterns and preferences.

[0078] Step 7:

[0079] The terminal displays to the user a food pack suggestion based on the user's purchasing history. The terminal obtains the suggested personalized food pack information from the server and visually displays it to the user.

[0080] Step 8:

[0081] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[0082] Step 9:

[0083] The user reviews the personalized food pack displayed, decides whether the suggestions match their tastes and the price is reasonable, and if they decide to purchase, clicks the purchase button.

[0084] Step 10:

[0085] The terminal receives the user's intention to purchase and transmits the purchase information to the server.

[0086] Step 11:

[0087] The server confirms the order based on the received purchase information. After the order is confirmed, it notifies the producer of the order details.

[0088] Step 12:

[0089] The server stores the order details and delivery information in a database.

[0090] Step 13:

[0091] The producer prepares ingredients based on the order details notified by the server.

[0092] Step 14:

[0093] The producer will send the ingredients to the specified delivery address, and the user can receive the delivered ingredients and use the suggested ingredient pack.

[0094] These steps enable the entire system to optimize the process of fresh ingredients from production to consumption and reduce food waste.

[0095] Example 1

[0096] 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."

[0097] In the conventional food distribution system, there are many intermediaries between producers and consumers, which leads to problems such as supply-demand imbalances, price fluctuations, and food waste. There is also a lack of personalized proposals tailored to consumer preferences, resulting in low consumer satisfaction. To solve these issues, a system is needed that makes the entire process from production to consumption transparent and optimizes supply-demand and prices.

[0098] 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.

[0099] In this invention, the server includes a means for collecting production information and storing it in a database, a means for collecting user purchase history data and analyzing user preferences using a machine learning algorithm, and a means for analyzing the market supply and demand balance and optimizing prices in real time, thereby optimizing the supply and demand balance of ingredients and proposing ingredient packs that suit users' preferences.

[0100] "Production information" refers to various data provided by producers, such as harvest volume, quality, and supply forecasts for agricultural and livestock products.

[0101] "Database accumulation" refers to the process of storing collected information in a digital format and making it available for access and analysis.

[0102] "Purchase history" is detailed data such as the products a user has purchased in the past, the purchase date and time, the purchase amount, and the price.

[0103] A "machine learning algorithm" is a computational method for finding patterns and regularities in large amounts of data and making predictions and classifications.

[0104] "Analyzing preferences" means using machine learning algorithms to analyze what products a user prefers and create a profile of the user's unique preferences.

[0105] "Supply and demand balance" refers to the relationship between the amount of goods supplied and the amount of goods consumed in the market, which allows us to understand oversupply and shortages.

[0106] "Optimizing prices in real time" means instantly calculating product prices and setting optimal prices based on the current supply and demand balance and market conditions.

[0107] "Generative AI" is a computer program that uses artificial intelligence technology to automatically generate new data and suggestions based on specific input conditions.

[0108] A "food pack" is a set of ingredients selected to suit a particular user's preferences or market conditions.

[0109] A "user terminal" is a digital device that allows a user to view and manipulate information, and examples include personal computers and smartphones.

[0110] The "purchase procedure" is a series of operations and confirmation processes for purchasing the product selected by the user.

[0111] "Confirming an order" is the process by which the user's intention to purchase is finally recognized and the transaction is officially registered in the system.

[0112] MODE FOR CARRYING OUT THE INVENTION

[0113] This invention is a system that makes the process of fresh ingredients from production to consumption transparent and optimizes supply and demand and prices using AI technology. By directly connecting producers and consumers, this system reduces food waste and proposes food packs tailored to consumer preferences.

[0114] System Overview

[0115] This system consists of three main components: a server, a terminal, and a user. The specific roles of each component are as follows:

[0116] Server Roles

[0117] The server performs the following functions:

[0118] 1. Collecting production information and storing it in a database

[0119] The server collects production data (such as harvest volume, quality, and supply forecasts) provided by producers and stores it in a database using a database system such as MySQL (registered trademark) or PostgreSQL.

[0120] 2. Collecting and analyzing user purchase history data

[0121] The server collects the user's purchase history data and analyzes the user's preferences using machine learning algorithms (e.g., TENSORFLOW (registered trademark) or Scikit-learn). The analyzed preference profile is stored in a database.

[0122] 3. Supply and demand balance analysis and price optimization

[0123] The server combines consumption and production data provided by the market to analyze the supply and demand balance and optimize prices in real time, using time series analysis techniques such as the ARIMA model.

[0124] 4. Proposal generation of food packs

[0125] The server uses a generative AI model (e.g., GPT-3 (registered trademark)) to generate ingredient packs based on the user's preference profile and supply and demand balance data.

[0126] Device Role

[0127] The terminal provides the user with the following features:

[0128] 1. Providing a user interface

[0129] The device displays personalized food pack suggestions to the user, using web application technologies such as React and Vue.js.

[0130] 2. Real-time price information

[0131] The terminal receives real-time price information from the server and presents it to the user, using technologies such as WebSocket and AJAX.

[0132] 3. Purchase procedure support

[0133] The terminal helps users purchase the suggested food packs with one click. The purchase information is sent to the server and the order is confirmed. HTTPS is used for secure communication.

[0134] User Roles

[0135] Users interact with the system as follows:

[0136] 1. Providing purchase history

[0137] The user purchases ingredients in the same way as with regular online shopping, and the purchase information is sent to the server.

[0138] 2. Check the food pack suggestions

[0139] The user checks the proposed personalized food pack through the terminal and decides whether to purchase it.

[0140] 3. Purchasing Decision

[0141] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the information is sent to the server.

[0142] Specific examples

[0143] For example, suppose that data on ingredients purchased by User A multiple times in the past is stored. User A goes online shopping on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and understands User A's preferences.

[0144] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User A.

[0145] When User A views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is right. User A can confirm the purchase with one click and receive fresh ingredients.

[0146] Prompt Sentence Examples

[0147] Below are some examples of specific prompts to input to a generative AI model:

[0148] Prompt: "Based on purchasing history data, please recommend a fresh food pack suitable for User A. Past purchases have always included fresh vegetables and chicken. Please also consider the supply-demand balance and market price when making your recommendation."

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1: Collect purchase history data

[0151] The server collects purchase history data every time a user makes an online purchase. Specifically, when a user adds an item to their shopping cart and clicks the "Purchase" button on the purchase confirmation screen, the details (purchase date and time, purchased item, purchase quantity, price, etc.) are sent to the database. The input is the user's purchase information, and the output is the purchase history data stored in the database.

[0152] Step 2: User preference analysis

[0153] The server analyzes user preferences based on the accumulated purchase history data. Specifically, it uses a machine learning algorithm (e.g., Scikit-learn's clustering method) to identify the specific ingredients that the user prefers. The input is the purchase history data collected in step 1, and the output is a preference profile for each user. The server stores the analysis results in a database.

[0154] Step 3: Collect and store production data

[0155] The server collects real-time production data provided by producers and stores it in a database. Specifically, producers send data from dedicated terminals to the server, which then stores it in the database. The input is production data from producers, and the output is production information stored in the database.

[0156] Step 4: Analyze the supply and demand balance

[0157] The server analyzes the supply and demand balance based on market consumption and production data. Specifically, it obtains market consumption and production data from the database and calculates the supply and demand balance using time series analysis and statistical methods (e.g., ARIMA model). The input is market consumption and production data, and the output is real-time supply and demand balance information.

[0158] Step 5: Price optimization

[0159] The server optimizes prices in real time based on supply and demand balance information. Specifically, it applies a pricing algorithm based on supply and demand balance information to calculate the optimal price. The input is real-time supply and demand balance information, and the output is optimized price information. The server stores this price information in a database.

[0160] Step 6: Generate ingredient pack suggestions

[0161] The server uses a generative AI model to generate a food pack based on the user's preference profile and supply-demand balance data. Specifically, it generates a prompt sentence using the preference profile and supply-demand balance data as input, and inputs it into the generative AI model. The generated food pack suggestions are saved in a database. The input is the preference profile and supply-demand balance data, and the output is the suggested food pack.

[0162] Prompt: "Based on purchasing history data, please recommend a fresh food pack suitable for User A. Past purchases have always included fresh vegetables and chicken. Please also consider the supply-demand balance and market price when making your recommendation."

[0163] Step 7: Providing a User Interface

[0164] The terminal displays the personalized food pack suggested to the user. Specifically, the terminal obtains the suggested information from the server and displays it on the screen. The user checks it and decides whether to purchase it or not, if necessary. The input is the suggested information obtained from the server, and the output is the food pack suggestion displayed on the terminal.

[0165] Step 8: Support with checkout

[0166] The terminal allows the user to purchase the selected food pack with one click. Specifically, when the user clicks the purchase button, the purchase information is sent to the server. The input is the user's purchase intention, and the output is the purchase information sent to the server.

[0167] Step 9: Confirm your order and update your data

[0168] The server confirms the order based on the transmitted purchase information and updates the database. Specifically, it records the order information in the database and updates inventory information and the user's purchase history data. The input is the user's purchase information, and the output is the updated information recorded in the database.

[0169] (Application example 1)

[0170] 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."

[0171] Modern food delivery services face challenges such as food waste, a lack of transparency in the supply chain, and a lack of methods for providing products that meet consumer preferences. They also face difficulties in effectively utilizing user purchasing data to optimize the supply-demand balance. This makes it difficult to provide ingredients at the best price for consumers, and there is a lack of an effective system for realizing personalized recommendations.

[0172] 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.

[0173] In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchase histories and analyzing preferences, means for analyzing the market supply-demand balance and optimizing prices, means for proposing food packs based on the generated preference profile, means for presenting the proposed food packs to the user and supporting the purchase process, and means for providing an application to be installed on a smartphone and displaying proposals and price information in real time, thereby making it possible to provide personalized food packs based on the user's preferences at optimal prices.

[0174] "Production information" refers to data provided by food producers regarding the yield, quality, and supply period of crops and products.

[0175] "Means of storing in a database" refers to systems or software for efficiently storing collected production information and purchase history information.

[0176] "Purchase history" refers to detailed information about products a user has purchased in the past, such as the purchase date and time, quantity, and price.

[0177] "Means for analyzing preferences" refers to algorithms and machine learning models that analyze users' preferences and purchasing patterns based on their purchase history.

[0178] "Supply and demand balance" refers to the state of supply and demand for a particular product or ingredient in the market.

[0179] "Price optimization tools" are algorithms or models that calculate the optimal selling price for ingredients or products based on the market supply and demand balance.

[0180] A "preference profile" is a collection of data that shows each user's preferences and purchasing patterns.

[0181] A "food pack" is a package of multiple ingredients suggested based on the user's preference profile.

[0182] "Means to support the purchasing process" refers to a system or interface that allows users to easily purchase the suggested food packs.

[0183] The "application installed on a smartphone" is software that runs on a smartphone and provides users with personalized food pack suggestions and price information.

[0184] "Means for displaying in real time" refers to an interface that has the function of instantly displaying to the user the latest offers and price information provided by the server.

[0185] A "user terminal" is a device used by an end user, such as a smartphone or tablet.

[0186] "One-click order confirmation" refers to a function or system that allows users to complete the purchase process with a single click.

[0187]

[0188] This invention is a system that makes the process from food production to consumption transparent and optimizes supply and demand and prices using AI technology. A specific example is shown below.

[0189] The server first collects production information provided by producers and stores it in a database. This production information includes information such as the yield, quality, and supply period of crops and products. Next, it periodically collects users' purchase histories and uses machine learning algorithms to analyze their preferences and generate a preference profile. The server then analyzes the market supply and demand balance and optimizes market prices in real time based on this analysis. This information is stored in the database and provided to users via an application installed on their smartphones.

[0190] The server uses a generative AI model to generate a food pack based on the user's preference profile and supply-demand balance data. This food pack is optimized based on the user's past consumption patterns and preferences. The device retrieves the personalized food pack information suggested by the server and presents it to the user in real time. Real-time price information from the server is also presented to the user through the device. The user can make a purchasing decision based on this information.

[0191] Once the user confirms the food pack suggestions and decides to purchase, the device sends the purchase information to the server, which then confirms the order. Furthermore, the system is designed to allow users to complete the purchase process with just one click, making it extremely convenient for users.

[0192] As an example, consider a case where data on ingredients purchased multiple times by a user has been accumulated. For example, if a user purchases fresh vegetables and domestically produced chicken online on Monday, the server analyzes this data to understand the user's preferences. The server analyzes agricultural production information and the market supply and demand balance to optimize the price of chicken and vegetables in real time. The generative AI model proposes an optimized vegetable and chicken ingredient pack for the user. When the user checks the proposed pack on their home device, they determine that it contains their favorite vegetables and chicken and is reasonably priced. The user can confirm the purchase with one click and receive fresh ingredients. This process makes it possible to provide ingredients tailored to the user's preferences while reducing food waste.

[0193] Example prompt sentence:

[0194] "Design a system that analyzes user preferences based on their purchasing history and suggests food packs that optimize the supply-demand balance. For example, for a user who purchases a lot of fresh tomatoes and domestic chicken, suggest a set of fresh tomatoes and chicken at the optimal price."

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] The server collects production information provided by producers and stores it in a database. The input is production data from producers, which includes detailed information on crops and products, such as yield, quality, and supply timing. The server efficiently stores this data in a database for future analysis.

[0198] Step 2:

[0199] The server periodically collects users' purchase history and analyzes their preferences using a machine learning algorithm. The input is the user's purchase history data, and the output is the user's preference profile. The server analyzes this data to understand each user's preferences and generate an individual preference profile.

[0200] Step 3:

[0201] The server analyzes the market supply and demand balance and optimizes prices. The input is market supply and demand data and supply data from producers, and the output is the optimized price of ingredients. The server analyzes this data and optimizes market prices in real time.

[0202] Step 4:

[0203] The server uses a generative AI model to generate food packs based on the user's preference profile and supply-demand balance data. The input is the preference profile and supply-demand balance data, and the output is a personalized food pack proposal. The server integrates this data and generates a food pack optimized for the user.

[0204] Step 5:

[0205] The terminal obtains personalized food pack information suggested by the server and presents it to the user. The input is food pack suggestion data from the server, and the output is food pack information displayed on the user's terminal screen. The terminal displays the suggestions to the user in real time and prompts for confirmation.

[0206] Step 6:

[0207] The terminal presents real-time price information from the server to the user. The input is price information from the server, and the output is an optimized price displayed on the user's terminal screen. The user makes a purchasing decision based on this information.

[0208] Step 7:

[0209] The user checks the food pack suggestions and decides to purchase. The input is the food pack information and price information displayed on the terminal, and the output is the user's intention to purchase. When the user decides to purchase, the terminal sends the purchase information to the server.

[0210] Step 8:

[0211] The server receives the user's purchase intention and confirms the order. The input is the user's purchase information, and the output is the confirmed order data. Based on this, the server carries out the appropriate delivery procedures.

[0212] Step 9:

[0213] The terminal supports one-click purchase procedures. The input is the user's purchase decision, and the output is the transmission of purchase information to the server. The purchase procedure is completed when the user confirms the purchase with one click on the terminal.

[0214] 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.

[0215] This invention combines a system that makes the process of fresh ingredients from production to consumption transparent, optimizes supply and demand and prices using AI technology, and an emotion engine that recognizes user emotions. By directly connecting producers and consumers, this system can reduce food waste and suggest food packs that suit consumers' preferences.

[0216] Server Processing

[0217] Collection and analysis of purchase history:

[0218] The server periodically collects user purchase history data and stores it in a database. Based on the collected data, machine learning algorithms are used to analyze user preferences and generate a preference profile for each user. This preference profile is then used to make personalized recommendations.

[0219] Supply and demand balance analysis and price optimization:

[0220] The server receives production data provided by producers and analyzes it along with market consumption patterns. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. This price information is stored in a database and provided to user devices.

[0221] Introducing the Emotion Engine:

[0222] The emotion engine collects user emotional data and uses it to generate a preference profile. Specifically, the emotion engine analyzes emotions from the user's facial expressions, tone of voice, text input, etc. to understand the user's state of mind. This emotional data is added to the preference profile and helps make more accurate suggestions.

[0223] Generate personalized food pack suggestions:

[0224] The server uses generative AI to generate food packs based on the user's preference profile and supply-demand balance data. The food packs are optimized for the user's past consumption patterns, preferences, and even emotional data. The information on the suggested food packs is stored in a database and later provided to the user's device.

[0225] Terminal handling

[0226] Providing a user interface:

[0227] The terminal displays to the user food pack suggestions based on the user's purchasing history. The terminal obtains the suggested personalized food pack information from the server and visually displays it to the user.

[0228] Emotion data collection:

[0229] The device works in conjunction with an emotion engine to collect emotional data from the user's facial expressions, tone of voice, text input, etc. This emotional data is sent to the server in real time.

[0230] Real-time pricing information:

[0231] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[0232] Purchase assistance:

[0233] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the purchase information to the server, which then confirms the order.

[0234] User Behavior

[0235] Providing purchase history:

[0236] The user purchases ingredients in the same way as with regular online shopping, and the information is sent to the server.

[0237] Check out our ingredient pack suggestions:

[0238] The user can then view the personalized food packs suggested to them through the device, determine whether the displayed contents match their tastes and whether the price is reasonable, and then decide whether to purchase.

[0239] Purchasing decision:

[0240] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the order is sent to the server.

[0241] Specific examples

[0242] For example, suppose that data on ingredients purchased by User B has been accumulated. User B shops online on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and determines User B's preferences.

[0243] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User B.

[0244] Furthermore, the device's emotion engine analyzes User B's facial expressions and tone of voice to understand their emotional state for that day. For example, if User B is feeling stressed, it can suggest ingredients and menu items that have a relaxing effect, making it possible to provide suggestions that are in tune with the user's emotions.

[0245] When User B views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User B can confirm the purchase with one click and receive fresh ingredients. This process reduces food waste while providing ingredients that match User B's preferences and emotions.

[0246] The processing flow will be explained below.

[0247] Step 1:

[0248] The server collects the user's purchase history data, specifically, the ingredients and products the user has purchased in the past, as well as the dates and quantities associated with those purchases.

[0249] Step 2:

[0250] The server stores the collected purchase history data in a database, which stores purchasing pattern data for each user.

[0251] Step 3:

[0252] The server analyzes the accumulated purchase history data and uses machine learning algorithms to extract user preferences and trends and generate a preference profile that specifically identifies each user's tastes and consumption tendencies.

[0253] Step 4:

[0254] The server receives production information provided by producers and stores it in a database, including detailed data such as the type of crop or ingredient, harvest yield, and harvest time.

[0255] Step 5:

[0256] The server analyzes market consumption patterns and production information to determine the market supply and demand balance. Based on the supply and demand balance data, it runs an algorithm to optimize market prices in real time. The optimized price information is also stored in a database.

[0257] Step 6:

[0258] The device collects the user's emotional data, and the device's emotion engine analyzes the user's facial expressions, tone of voice, text input, etc. to understand the user's current emotional state.

[0259] Step 7:

[0260] The device transmits the collected user emotion data to the server in real time.

[0261] Step 8:

[0262] The server receives the user's emotional data and uses it to update the user's preference profile. Specifically, if the user is feeling stressed, the server will suggest foods that have a relaxing effect, and make recommendations based on the user's emotional state.

[0263] Step 9:

[0264] The server uses generative AI to generate food packs based on the user's preference profile, supply-demand balance data, and emotional data. This food pack is optimized based on the user's past consumption patterns, preferences, and emotional data.

[0265] Step 10:

[0266] The device displays food pack suggestions based on the user's purchasing history and emotional state. The device retrieves the suggested personalized food pack information from the server and visually displays it to the user.

[0267] Step 11:

[0268] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[0269] Step 12:

[0270] The user reviews the personalized food pack displayed, decides whether the suggestions match their tastes and the price is reasonable, and if they decide to purchase, clicks the purchase button.

[0271] Step 13:

[0272] The terminal receives the user's intention to purchase and transmits the purchase information to the server.

[0273] Step 14:

[0274] The server confirms the order based on the received purchase information. After the order is confirmed, it notifies the producer of the order details.

[0275] Step 15:

[0276] The server stores the order details and delivery information in a database.

[0277] Step 16:

[0278] The producer prepares ingredients based on the order details notified by the server.

[0279] Step 17:

[0280] The producer will send the ingredients to the specified delivery address, and the user can receive the delivered ingredients and use the suggested ingredient pack.

[0281] Through these steps, the entire system optimizes the process of fresh ingredients from production to consumption, and reduces food waste by making suggestions that are in line with the user's emotions.

[0282] Example 2

[0283] 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."

[0284] In today's consumer market, there is a need to optimize the balance between supply and demand for ingredients and make personalized recommendations based on consumer preferences and emotions. However, conventional systems only analyze ingredient purchasing and production data, and do not fully utilize consumer emotional data to make recommendations, making it difficult to make recommendations that are tailored to individual consumer preferences and emotions. Furthermore, it is difficult to analyze the appropriate supply and demand balance, resulting in increased food waste.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0286] In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchasing history and analyzing preferences, means for analyzing the market supply and demand balance and optimizing prices, means for collecting user emotional data and analyzing it to suggest food packs based on a preference profile, and means for presenting the suggested food packs to the user and supporting the purchase process.

[0287] This will enable more personalized suggestions based on consumer preferences and emotions, optimize the supply and demand balance in real time, and reduce food waste.

[0288] "Production information" refers to detailed data on crop and product production provided by producers.

[0289] A "database" is an information system for systematically storing, managing, and analyzing collected information.

[0290] A "purchase history" is a detailed record of the purchases a user has made in the past.

[0291] "Preferences" refers to the preferences and tendencies that a user has toward specific products or ingredients.

[0292] "Analyzing" means analyzing user behavior and patterns based on accumulated data.

[0293] "Supply and demand balance" refers to the equilibrium between the supply of goods and services offered and the demand of consumers.

[0294] "Price optimization" means setting the most appropriate price by taking into account the supply and demand balance in the market.

[0295] "Emotion data" is data that represents the user's emotional state, and includes facial expressions, tone of voice, text input, and the like.

[0296] A "preference profile" is detailed information about a user's preferences and consumption patterns that is generated based on analysis.

[0297] A "food pack" is a product package that combines multiple ingredients and is suggested based on the user's preferences and emotional data.

[0298] "Suggesting" means presenting the user with the best options or products based on the analysis results.

[0299] "Presenting" means that the system shows information to the user visually or audibly.

[0300] "Supporting the purchase procedure" means assisting the user with a series of operations when purchasing a suggested product.

[0301] This invention combines a system that makes the process of fresh ingredients from production to consumption transparent, optimizes supply and demand and prices using generative AI models, and an emotion engine that recognizes user emotions. By directly connecting producers and consumers, this system can reduce food waste and suggest food packs tailored to consumer preferences.

[0302] Hardware and Software Configuration

[0303] The servers are equipped with high-performance processors and use database management systems (e.g., MySQL or PostgreSQL) to analyze large amounts of data in real time. Additionally, machine learning algorithms are implemented using Python scripts and libraries such as TensorFlow or PyTorch. Advanced generative AI models, such as GPT-3, are also used.

[0304] The device refers to a smartphone, tablet, or PC operated by the user, and is equipped with an emotion engine. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice, and employs analysis tools such as OpenCV and Google® Cloud Speech-to-Text API. The user interface is built using a JavaScript® framework such as React or Vue.js.

[0305] System processing overview

[0306] The server first collects production information provided by producers and stores it in a database. It also periodically collects users' purchase history and uses machine learning algorithms to generate a user preference profile, which includes details such as purchase date and time, item name, quantity, and price.

[0307] The server then analyzes production information and market consumption data to determine the supply and demand balance, optimizes market prices in real time based on this information, and stores the price information in a database.

[0308] The server also collects the user's emotional data. The emotion engine analyzes the user's facial expressions, tone of voice, and text input to understand the user's state of mind. This emotional data is added to the user's preference profile to improve the accuracy of suggestions.

[0309] The server uses generative AI to generate a food pack based on the user's preference profile, supply-demand balance data, and emotional data. This proposal is stored in a database and later provided to the user's device. Specifically, the following prompt sentence is input into the generative AI model:

[0310] "Recommend optimal food packs based on the user's past purchase history and emotional data. For example, if the user is feeling stressed, include ingredients that will help them relax."

[0311] The device displays personalized food pack suggestions retrieved from the server to the user, and the user interface provides information in a visually easy-to-understand format, allowing the user to easily understand the suggestions.

[0312] The device works in conjunction with an emotion engine to collect emotional data in real time from the user's facial expressions, tone of voice, text input, etc., and sends this data to the server. When the user checks the suggested food pack and decides to purchase it, the device sends this information to the server, which then confirms the order.

[0313] Specific examples

[0314] For example, suppose that data on ingredients purchased by User B has been accumulated. User B shops online on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and determines User B's preferences.

[0315] Next, the server analyzes production information and the market supply and demand balance to optimize the price of chicken and vegetables in real time. Once the price is determined, the generation AI proposes an optimized vegetable and chicken food pack to User B.

[0316] Furthermore, the device's emotion engine analyzes User B's facial expressions and tone of voice to understand their emotional state for that day. For example, if User B is feeling stressed, it can suggest ingredients and menu items that have a relaxing effect, making it possible to provide suggestions that are in tune with the user's emotions.

[0317] When User B views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User B can confirm the purchase with one click and receive fresh ingredients. This reduces food waste while providing ingredients that match User B's preferences and emotions.

[0318] As described above, this invention makes it possible to efficiently manage the process of fresh ingredients from production to consumption, and to realize personalized suggestions that are in tune with the user's emotions.

[0319] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0320] Step 1:

[0321] Collecting purchase history data and storing it in a database

[0322] The server periodically collects information about ingredients purchased by users on an online shopping site. It uses a REST API to collect the data and stores the acquired data in a database. Purchase history data, such as the user ID, purchase date and time, product name, quantity, and price, is provided as input. The server inserts this data into a "purchase history" table.

[0323] Specific behavior:

[0324] Every time a user buys an ingredient, the details are sent to the server via an API and added as a new record to the database using an SQL query.

[0325] Step 2:

[0326] Generating a preference profile

[0327] The server uses a machine learning algorithm to generate a preference profile for each user based on the collected purchase history data. This uses a clustering algorithm and collaborative filtering. The data in the "Purchase History" table is used as input, and the generated preference profile is saved as output in the "Preference Profile" table.

[0328] Specific behavior:

[0329] Run a Python script to cluster the data using the Scikit-learn library to identify patterns of user preferences, and store the results in a database.

[0330] Step 3:

[0331] Analysis of production and market consumption data

[0332] The server receives production data provided by producers and analyzes it together with market consumption data. The ETL tool is used to import the data and store it in a database. The CSV file from the producer is used as input, and a "production data" table and a "consumption data" table are created as output.

[0333] Specific behavior:

[0334] Data files from producers are periodically uploaded to the server and imported into the database through batch processing using an ETL tool (e.g., Apache (registered trademark) Nifi).

[0335] Step 4:

[0336] Supply and demand balance analysis and price optimization

[0337] The server analyzes the supply and demand balance based on the collected production and consumption data. Time series analysis and linear regression models are used for price optimization. The "production data" and "consumption data" tables are used as input, and the optimized market price is saved as output in the "market price" table.

[0338] Specific behavior:

[0339] Run time series analysis scripts in Python or R to forecast supply and demand balance and optimize prices. Update the results to a "market price" table using SQL queries.

[0340] Step 5:

[0341] Emotion data collection and analysis

[0342] The device uses an emotion engine to collect emotional data such as the user's facial expressions, tone of voice, and text input. This emotional data is sent to the server in real time. Data from the camera, microphone, and keyboard is used as input, and the analyzed emotional data is stored in an "emotion data" table as output.

[0343] Specific behavior:

[0344] The device uses OpenCV and the Google Cloud Speech-to-Text API to analyze emotions in real time, and the analyzed data is sent to the server via a REST API.

[0345] Step 6:

[0346] Generate personalized food packs

[0347] The server uses the generative AI model to generate food packs based on the user's preference profile, emotional data, and supply-demand balance data. The "preference profile," "emotion data," and "market price" tables are used as input, and the generated food packs are saved in the "suggested pack" table as output.

[0348] Specific behavior:

[0349] Enter the following prompt into a generative AI model (e.g., GPT-3) and get a response: "Suggest the optimal ingredient pack based on the user's past purchasing history data and emotional data. For example, if the user is feeling stressed, include ingredients that will help them relax." Save this response in a "Suggested Pack" table.

[0350] Step 7:

[0351] Displaying the proposed content on the user's device

[0352] The terminal displays the personalized food pack suggestions received from the server to the user. The data in the "Suggested Packs" table is used as input. The output is reflected in the user interface.

[0353] Specific behavior:

[0354] The device retrieves data from the server via a REST API and displays it in a UI using React and Vue.js, for example, creating attractive visualizations of ingredient lists and pricing information.

[0355] Step 8:

[0356] Collecting user reaction data and continuously learning for new suggestions

[0357] The device records how the user reacts to the suggestions. This reaction data is sent to the server to help improve future suggestions. The input is the user's reaction, and the output is stored in a "reaction data" table.

[0358] Specific behavior:

[0359] It records whether the user accepts or rejects the suggestion and sends the result to the server via a REST API, which will be used as training data for future generative AI models.

[0360] (Application example 2)

[0361] 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."

[0362] In today's food distribution system, the process from production to consumption is complex, making it difficult for consumers to obtain fresh ingredients. Furthermore, there is a lack of personalized food packs that take into account consumers' preferences and emotions, resulting in a lower satisfaction level in the purchasing experience. Furthermore, there are issues such as increased food waste and difficulty in optimizing the supply and demand balance.

[0363] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchase histories and analyzing preferences, means for analyzing the market supply and demand balance and optimizing prices, means for proposing ingredient packs based on the generated preference profile, means for presenting the proposed ingredient packs to the user and supporting the purchase process, means for collecting emotional data from the user's facial expressions and tone of voice, means for analyzing the collected emotional data and reflecting it in the preference profile, and means for proposing personalized ingredient packs based on the emotional data. This makes it possible to propose ingredient packs that are optimally tailored to the consumer's emotional state and preferences, improving the purchasing experience and reducing food waste.

[0364] "Production information" refers to data related to the production of food ingredients such as agricultural and livestock products, and includes information such as production area, harvest time, quantity, and quality.

[0365] A "database" is a collection of data that is structured so that specific data can be efficiently managed, searched, and retrieved.

[0366] "Purchase history" is a record of products purchased by a user in the past, and includes information such as purchase date and time, product name, quantity, and price.

[0367] A "preference profile" is a collection of information about a user's individual preferences and tastes, obtained by analyzing the user's past purchasing history and behavioral data.

[0368] "Supply and demand balance" refers to the relationship between supply and demand in the market, which determines market trends and prices.

[0369] "Price optimization" is the process of efficiently determining sales prices based on information on the supply and demand balance, and is an adjustment that maximizes profits.

[0370] "Suggestion" refers to the act of recommending a particular product or service to a user, and in this case refers to presenting a personalized food pack to the user.

[0371] The "purchase procedure" refers to a series of operations and processes required to purchase the product selected by the user, including payment, delivery arrangements, etc.

[0372] "Emotion data" refers to data relating to individual emotional states obtained from the user's facial expressions, tone of voice, text input, and the like.

[0373] "Personalization" refers to the process of optimizing the content of a service or product to suit the preferences and characteristics of each individual user.

[0374] A "food pack" is a set of ingredients combined according to a specific recipe or menu.

[0375] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze user data and generate new suggestions or predictions.

[0376] A "prompt" is an instruction used when inputting data into a generative AI model, and is intended to clarify what kind of output is expected.

[0377] This invention realizes a system that collects user purchasing history and emotional data, and proposes and provides personalized food packs based on that data. This system is composed of a server and a user terminal.

[0378] Server processing overview

[0379] The server performs its processing using the following hardware and software:

[0380] Hardware: High-speed server

[0381] Software: Database Management Systems (DBMS), machine learning algorithms (e.g., TensorFlow, Scikit-learn), emotion recognition engines, generative AI models

[0382] 1. Collecting production information

[0383] The server collects agricultural and livestock production information from external data sources and stores it in a database. The collected data includes information on production area, harvest time, quantity, quality, etc.

[0384] 2. Collecting purchase history and analyzing preferences

[0385] The server collects the user's purchase history and analyzes their preferences based on that information. The analyzed data is stored in a database as a preference profile for each user.

[0386] 3. Analysis of market supply and demand balance and price optimization

[0387] The server analyzes market consumption patterns and production data. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. The optimized price information is stored in a database.

[0388] 4. Emotional Data Collection and Analysis

[0389] The server uses an emotion recognition engine to collect emotional data from the user's facial expressions, tone of voice, and text input, which is then sent to the server in real time for analysis.

[0390] 5. Generate personalized food pack suggestions

[0391] The server uses a generative AI model to generate food packs based on the user's preference profile, real-time emotional data, and supply-demand balance data. The generated food packs are optimized to the user's preferences and emotional state at the time.

[0392] Terminal processing overview

[0393] The device performs its processing using the following hardware and software:

[0394] Hardware: Smartphones, tablets, smart glasses

[0395] Software: User interface software, emotion recognition engine

[0396] 1. Providing a user interface

[0397] The device visually displays to the user a food pack recommendation based on the user's purchasing history, and the user can check the personalized food pack recommendation information on the device screen.

[0398] 2. Collecting Emotional Data

[0399] The device works in conjunction with an emotion recognition engine to collect emotional data in real time from the user's facial expressions, tone of voice, text input, etc. This emotional data is immediately sent to the server.

[0400] 3. Real-time price information

[0401] The terminal presents the user with real-time market price information received from the server, allowing the user to make a price-based purchasing decision.

[0402] 4. Purchase procedure support

[0403] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the information to the server, which then confirms the order.

[0404] Examples of concrete examples and prompts

[0405] As a concrete example, consider a case where a user is feeling stressed. In this case, the emotion recognition engine detects the stressed state and suggests a meal pack containing foods with a relaxing effect (e.g., herbal tea and nuts).

[0406] Example prompt sentence:

[0407] "If the user is currently feeling stressed, suggest a food pack containing foods that have a relaxing effect."

[0408] In this way, it becomes possible to propose the most suitable food pack that matches the consumer's emotional state and preferences, improving the purchasing experience and reducing food waste.

[0409] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0410] Step 1:

[0411] The server collects production information from external data sources and stores it in a database. The input includes production information data such as production area, harvest time, quantity, and quality. Data processing involves converting this information into a database format and saving it in the database. This allows the server to always have the latest production information. The output is an updated database.

[0412] Step 2:

[0413] The server collects user purchase history data. Input includes purchase history data such as purchase date and time, product name, quantity, and price. Data processing involves analyzing the user's preferences from this purchase history and creating a preference profile. As a specific example, the server analyzes past purchase frequency and patterns. The output is a preference profile for each user.

[0414] Step 3:

[0415] The server analyzes the market supply and demand balance. Inputs include production data and consumption pattern data. Data processing involves calculating the market supply and demand balance based on these data and optimizing real-time prices. Specifically, a machine learning algorithm is used to draw a supply and demand curve and calculate the optimal price. The output is optimized market price information.

[0416] Step 4:

[0417] The device collects emotional data from the user's facial expressions and tone of voice. Inputs include real-time data from the camera and microphone. Data processing involves analyzing this data using an emotion recognition engine to identify the user's emotional state. For example, emotions such as joy or sadness can be detected from the user's facial expressions. The output is the analyzed emotional data.

[0418] Step 5:

[0419] The server analyzes the collected emotional data and reflects it in the preference profile. The input includes emotional data and an existing preference profile. The data is processed by updating the preference profile according to the emotional state. Specifically, it takes into account the tendency of stressed users to prefer foods with a relaxing effect. The output is the updated preference profile.

[0420] Step 6:

[0421] The server uses a generative AI model to suggest a personalized food pack based on emotional data and a preference profile. The input includes emotional data, a preference profile, and optimized market price information. For data processing, the generative AI model is used to generate an optimal food pack. A specific prompt is used: "If the user is currently feeling stressed, please suggest a food pack that includes foods that have a relaxing effect." The output is a personalized food pack suggestion.

[0422] Step 7:

[0423] The terminal receives the suggested ingredient pack information from the server and visually displays it to the user. The input includes the personalized ingredient pack suggestion information. Specific operations include displaying ingredient pack contents and price information on the terminal screen. The output is the personalized ingredient pack information presented to the user.

[0424] Step 8:

[0425] The user checks the suggested food packs on the terminal and makes a decision to purchase. The input includes information about the suggested food packs. The specific action is to click the purchase button. The output is the user's purchase intention information.

[0426] Step 9:

[0427] The terminal transmits the user's purchase intention information to the server. The input includes the purchase intention information. Specifically, after the purchase is confirmed, the purchase information is transmitted to the server. The output is the purchase information received by the server.

[0428] Step 10:

[0429] The server processes the received purchase information and confirms the order. The input includes the user's purchase information. Specific operations include saving the order in a database and arranging for delivery. The output is the confirmed order information. As a result, the user can receive the specified food pack.

[0430] 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.

[0431] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0432] 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.

[0433] [Second embodiment]

[0434] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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."

[0446] This invention is a system that makes the process of fresh ingredients from production to consumption transparent and optimizes supply and demand and prices using AI technology. By directly connecting producers and consumers, this system reduces food waste and proposes food packs tailored to consumer preferences.

[0447] Server Processing

[0448] Collection and analysis of purchase history:

[0449] The server periodically collects user purchase history data and stores it in a database. Based on the collected data, machine learning algorithms are used to analyze user preferences and generate a preference profile for each user. This preference profile is then used to make personalized recommendations.

[0450] Supply and demand balance analysis and price optimization:

[0451] The server receives production data provided by producers and analyzes it along with market consumption patterns. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. This price information is stored in a database and provided to user devices.

[0452] Generate personalized food pack suggestions:

[0453] The server uses AI to generate food packs based on the user's preference profile and supply-demand balance data. The food packs are optimized for the user's past consumption patterns and preferences. The information on the suggested food packs is stored in a database and later provided to the user's device.

[0454] Terminal handling

[0455] Providing a user interface:

[0456] The terminal displays to the user a food pack suggestion based on the user's purchasing history. When the user accesses the terminal, the terminal retrieves the suggested personalized food pack information from the server and displays it to the user.

[0457] Real-time pricing information:

[0458] The terminal receives real-time price information from the server and presents it to the user, who can then make a purchasing decision based on it.

[0459] Purchase assistance:

[0460] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the purchase information to the server, which then confirms the order.

[0461] User Behavior

[0462] Providing purchase history:

[0463] The user purchases ingredients in the same way as with regular online shopping, and the information is sent to the server.

[0464] Check out our ingredient pack suggestions:

[0465] The user can then view the personalized food packs suggested to them through the device, determine whether the displayed contents match their tastes and whether the price is reasonable, and then decide whether to purchase.

[0466] Purchasing decision:

[0467] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the order is sent to the server.

[0468] Specific examples

[0469] For example, suppose that data on ingredients purchased by User A multiple times in the past is stored. User A goes online shopping on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and understands User A's preferences.

[0470] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User A.

[0471] When User A views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User A can confirm the purchase with one click and receive fresh ingredients. This process reduces food waste while providing ingredients tailored to User A's preferences.

[0472] The processing flow will be explained below.

[0473] Step 1:

[0474] The server collects the user's purchase history data, specifically, the ingredients and products the user has purchased in the past, as well as the dates and quantities associated with those purchases.

[0475] Step 2:

[0476] The server stores the collected purchase history data in a database, which stores purchasing pattern data for each user.

[0477] Step 3:

[0478] The server analyzes the accumulated purchase history data and uses machine learning algorithms to extract user preferences and trends and generate a preference profile that specifically identifies each user's tastes and consumption tendencies.

[0479] Step 4:

[0480] The server receives production information provided by producers and stores it in a database, including detailed data such as the type of crop or ingredient, harvest yield, and harvest time.

[0481] Step 5:

[0482] The server analyzes market consumption patterns and production information to determine the market supply and demand balance. Based on the supply and demand balance data, it runs an algorithm to optimize market prices in real time. The optimized price information is also stored in a database.

[0483] Step 6:

[0484] The server uses AI to generate food packs based on the user's preference profile and supply-demand balance data. The generated food packs are optimized for the user's past consumption patterns and preferences.

[0485] Step 7:

[0486] The terminal displays to the user a food pack suggestion based on the user's purchasing history. The terminal obtains the suggested personalized food pack information from the server and visually displays it to the user.

[0487] Step 8:

[0488] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[0489] Step 9:

[0490] The user reviews the personalized food pack displayed, decides whether the suggestions match their tastes and the price is reasonable, and if they decide to purchase, clicks the purchase button.

[0491] Step 10:

[0492] The terminal receives the user's intention to purchase and transmits the purchase information to the server.

[0493] Step 11:

[0494] The server confirms the order based on the received purchase information. After the order is confirmed, it notifies the producer of the order details.

[0495] Step 12:

[0496] The server stores the order details and delivery information in a database.

[0497] Step 13:

[0498] The producer prepares ingredients based on the order details notified by the server.

[0499] Step 14:

[0500] The producer will send the ingredients to the specified delivery address, and the user can receive the delivered ingredients and use the suggested ingredient pack.

[0501] These steps enable the entire system to optimize the process of fresh ingredients from production to consumption and reduce food waste.

[0502] Example 1

[0503] 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."

[0504] In the conventional food distribution system, there are many intermediaries between producers and consumers, which leads to problems such as supply-demand imbalances, price fluctuations, and food waste. There is also a lack of personalized proposals tailored to consumer preferences, resulting in low consumer satisfaction. To solve these issues, a system is needed that makes the entire process from production to consumption transparent and optimizes supply-demand and prices.

[0505] 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.

[0506] In this invention, the server includes a means for collecting production information and storing it in a database, a means for collecting user purchase history data and analyzing user preferences using a machine learning algorithm, and a means for analyzing the market supply and demand balance and optimizing prices in real time, thereby optimizing the supply and demand balance of ingredients and proposing ingredient packs that suit users' preferences.

[0507] "Production information" refers to various data provided by producers, such as harvest volume, quality, and supply forecasts for agricultural and livestock products.

[0508] "Database accumulation" refers to the process of storing collected information in a digital format and making it available for access and analysis.

[0509] "Purchase history" is detailed data such as the products a user has purchased in the past, the purchase date and time, the purchase amount, and the price.

[0510] A "machine learning algorithm" is a computational method for finding patterns and regularities in large amounts of data and making predictions and classifications.

[0511] "Analyzing preferences" means using machine learning algorithms to analyze what products a user prefers and create a profile of the user's unique preferences.

[0512] "Supply and demand balance" refers to the relationship between the amount of goods supplied and the amount of goods consumed in the market, which allows us to understand oversupply and shortages.

[0513] "Optimizing prices in real time" means instantly calculating product prices and setting optimal prices based on the current supply and demand balance and market conditions.

[0514] "Generative AI" is a computer program that uses artificial intelligence technology to automatically generate new data and suggestions based on specific input conditions.

[0515] A "food pack" is a set of ingredients selected to suit a particular user's preferences or market conditions.

[0516] A "user terminal" is a digital device that allows a user to view and manipulate information, and examples include personal computers and smartphones.

[0517] The "purchase procedure" is a series of operations and confirmation processes for purchasing the product selected by the user.

[0518] "Confirming an order" is the process by which the user's intention to purchase is finally recognized and the transaction is officially registered in the system.

[0519] MODE FOR CARRYING OUT THE INVENTION

[0520] This invention is a system that makes the process of fresh ingredients from production to consumption transparent and optimizes supply and demand and prices using AI technology. By directly connecting producers and consumers, this system reduces food waste and proposes food packs tailored to consumer preferences.

[0521] System Overview

[0522] This system consists of three main components: a server, a terminal, and a user. The specific roles of each component are as follows:

[0523] Server Roles

[0524] The server performs the following functions:

[0525] 1. Collecting production information and storing it in a database

[0526] The server collects production data provided by producers (e.g., harvest volume, quality, supply forecast, etc.) and stores it in a database using a database system such as MySQL or PostgreSQL.

[0527] 2. Collecting and analyzing user purchase history data

[0528] The server collects the user's purchase history data and analyzes the user's preferences using machine learning algorithms (e.g., TensorFlow or Scikit-learn). The analyzed preference profile is stored in a database.

[0529] 3. Supply and demand balance analysis and price optimization

[0530] The server combines consumption and production data provided by the market to analyze the supply and demand balance and optimize prices in real time, using time series analysis techniques such as the ARIMA model.

[0531] 4. Proposal generation of food packs

[0532] The server uses a generative AI model (e.g., GPT-3) to generate food packs based on the user's preference profile and supply-demand balance data.

[0533] Device Role

[0534] The terminal provides the user with the following features:

[0535] 1. Providing a user interface

[0536] The device displays personalized food pack suggestions to the user, using web application technologies such as React and Vue.js.

[0537] 2. Real-time price information

[0538] The terminal receives real-time price information from the server and presents it to the user, using technologies such as WebSocket and AJAX.

[0539] 3. Purchase procedure support

[0540] The terminal helps users purchase the suggested food packs with one click. The purchase information is sent to the server and the order is confirmed. HTTPS is used for secure communication.

[0541] User Roles

[0542] Users interact with the system as follows:

[0543] 1. Providing purchase history

[0544] The user purchases ingredients in the same way as with regular online shopping, and the purchase information is sent to the server.

[0545] 2. Check the food pack suggestions

[0546] The user checks the proposed personalized food pack through the terminal and decides whether to purchase it.

[0547] 3. Purchasing Decision

[0548] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the information is sent to the server.

[0549] Specific examples

[0550] For example, suppose that data on ingredients purchased by User A multiple times in the past is stored. User A goes online shopping on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and understands User A's preferences.

[0551] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User A.

[0552] When User A views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is right. User A can confirm the purchase with one click and receive fresh ingredients.

[0553] Prompt Sentence Examples

[0554] Below are some examples of specific prompts to input to a generative AI model:

[0555] Prompt: "Based on purchasing history data, please recommend a fresh food pack suitable for User A. Past purchases have always included fresh vegetables and chicken. Please also consider the supply-demand balance and market price when making your recommendation."

[0556] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0557] Step 1: Collect purchase history data

[0558] The server collects purchase history data every time a user makes an online purchase. Specifically, when a user adds an item to their shopping cart and clicks the "Purchase" button on the purchase confirmation screen, the details (purchase date and time, purchased item, purchase quantity, price, etc.) are sent to the database. The input is the user's purchase information, and the output is the purchase history data stored in the database.

[0559] Step 2: User preference analysis

[0560] The server analyzes user preferences based on the accumulated purchase history data. Specifically, it uses a machine learning algorithm (e.g., Scikit-learn's clustering method) to identify the specific ingredients that the user prefers. The input is the purchase history data collected in step 1, and the output is a preference profile for each user. The server stores the analysis results in a database.

[0561] Step 3: Collect and store production data

[0562] The server collects real-time production data provided by producers and stores it in a database. Specifically, producers send data from dedicated terminals to the server, which then stores it in the database. The input is production data from producers, and the output is production information stored in the database.

[0563] Step 4: Analyze the supply and demand balance

[0564] The server analyzes the supply and demand balance based on market consumption and production data. Specifically, it obtains market consumption and production data from the database and calculates the supply and demand balance using time series analysis and statistical methods (e.g., ARIMA model). The input is market consumption and production data, and the output is real-time supply and demand balance information.

[0565] Step 5: Price optimization

[0566] The server optimizes prices in real time based on supply and demand balance information. Specifically, it applies a pricing algorithm based on supply and demand balance information to calculate the optimal price. The input is real-time supply and demand balance information, and the output is optimized price information. The server stores this price information in a database.

[0567] Step 6: Generate ingredient pack suggestions

[0568] The server uses a generative AI model to generate a food pack based on the user's preference profile and supply-demand balance data. Specifically, it generates a prompt sentence using the preference profile and supply-demand balance data as input, and inputs it into the generative AI model. The generated food pack suggestions are saved in a database. The input is the preference profile and supply-demand balance data, and the output is the suggested food pack.

[0569] Prompt: "Based on purchasing history data, please recommend a fresh food pack suitable for User A. Past purchases have always included fresh vegetables and chicken. Please also consider the supply-demand balance and market price when making your recommendation."

[0570] Step 7: Providing a User Interface

[0571] The terminal displays the personalized food pack suggested to the user. Specifically, the terminal obtains the suggested information from the server and displays it on the screen. The user checks it and decides whether to purchase it or not, if necessary. The input is the suggested information obtained from the server, and the output is the food pack suggestion displayed on the terminal.

[0572] Step 8: Support with checkout

[0573] The terminal allows the user to purchase the selected food pack with one click. Specifically, when the user clicks the purchase button, the purchase information is sent to the server. The input is the user's purchase intention, and the output is the purchase information sent to the server.

[0574] Step 9: Confirm your order and update your data

[0575] The server confirms the order based on the transmitted purchase information and updates the database. Specifically, it records the order information in the database and updates inventory information and the user's purchase history data. The input is the user's purchase information, and the output is the updated information recorded in the database.

[0576] (Application example 1)

[0577] 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."

[0578] Modern food delivery services face challenges such as food waste, a lack of transparency in the supply chain, and a lack of methods for providing products that meet consumer preferences. They also face difficulties in effectively utilizing user purchasing data to optimize the supply-demand balance. This makes it difficult to provide ingredients at the best price for consumers, and there is a lack of an effective system for realizing personalized recommendations.

[0579] 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.

[0580] In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchase histories and analyzing preferences, means for analyzing the market supply-demand balance and optimizing prices, means for proposing food packs based on the generated preference profile, means for presenting the proposed food packs to the user and supporting the purchase process, and means for providing an application to be installed on a smartphone and displaying proposals and price information in real time, thereby making it possible to provide personalized food packs based on the user's preferences at optimal prices.

[0581] "Production information" refers to data provided by food producers regarding the yield, quality, and supply period of crops and products.

[0582] "Means of storing in a database" refers to systems or software for efficiently storing collected production information and purchase history information.

[0583] "Purchase history" refers to detailed information about products a user has purchased in the past, such as the purchase date and time, quantity, and price.

[0584] "Means for analyzing preferences" refers to algorithms and machine learning models that analyze users' preferences and purchasing patterns based on their purchase history.

[0585] "Supply and demand balance" refers to the state of supply and demand for a particular product or ingredient in the market.

[0586] "Price optimization tools" are algorithms or models that calculate the optimal selling price for ingredients or products based on the market supply and demand balance.

[0587] A "preference profile" is a collection of data that shows each user's preferences and purchasing patterns.

[0588] A "food pack" is a package of multiple ingredients suggested based on the user's preference profile.

[0589] "Means to support the purchasing process" refers to a system or interface that allows users to easily purchase the suggested food packs.

[0590] The "application installed on a smartphone" is software that runs on a smartphone and provides users with personalized food pack suggestions and price information.

[0591] "Means for displaying in real time" refers to an interface that has the function of instantly displaying to the user the latest offers and price information provided by the server.

[0592] A "user terminal" is a device used by an end user, such as a smartphone or tablet.

[0593] "One-click order confirmation" refers to a function or system that allows users to complete the purchase process with a single click.

[0594]

[0595] This invention is a system that makes the process from food production to consumption transparent and optimizes supply and demand and prices using AI technology. A specific example is shown below.

[0596] The server first collects production information provided by producers and stores it in a database. This production information includes information such as the yield, quality, and supply period of crops and products. Next, it periodically collects users' purchase histories and uses machine learning algorithms to analyze their preferences and generate a preference profile. The server then analyzes the market supply and demand balance and optimizes market prices in real time based on this analysis. This information is stored in the database and provided to users via an application installed on their smartphones.

[0597] The server uses a generative AI model to generate a food pack based on the user's preference profile and supply-demand balance data. This food pack is optimized based on the user's past consumption patterns and preferences. The device retrieves the personalized food pack information suggested by the server and presents it to the user in real time. Real-time price information from the server is also presented to the user through the device. The user can make a purchasing decision based on this information.

[0598] Once the user confirms the food pack suggestions and decides to purchase, the device sends the purchase information to the server, which then confirms the order. Furthermore, the system is designed to allow users to complete the purchase process with just one click, making it extremely convenient for users.

[0599] As an example, consider a case where data on ingredients purchased multiple times by a user has been accumulated. For example, if a user purchases fresh vegetables and domestically produced chicken online on Monday, the server analyzes this data to understand the user's preferences. The server analyzes agricultural production information and the market supply and demand balance to optimize the price of chicken and vegetables in real time. The generative AI model proposes an optimized vegetable and chicken ingredient pack for the user. When the user checks the proposed pack on their home device, they determine that it contains their favorite vegetables and chicken and is reasonably priced. The user can confirm the purchase with one click and receive fresh ingredients. This process makes it possible to provide ingredients tailored to the user's preferences while reducing food waste.

[0600] Example prompt sentence:

[0601] "Design a system that analyzes user preferences based on their purchasing history and suggests food packs that optimize the supply-demand balance. For example, for a user who purchases a lot of fresh tomatoes and domestic chicken, suggest a set of fresh tomatoes and chicken at the optimal price."

[0602] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0603] Step 1:

[0604] The server collects production information provided by producers and stores it in a database. The input is production data from producers, which includes detailed information on crops and products, such as yield, quality, and supply timing. The server efficiently stores this data in a database for future analysis.

[0605] Step 2:

[0606] The server periodically collects users' purchase history and analyzes their preferences using a machine learning algorithm. The input is the user's purchase history data, and the output is the user's preference profile. The server analyzes this data to understand each user's preferences and generate an individual preference profile.

[0607] Step 3:

[0608] The server analyzes the market supply and demand balance and optimizes prices. The input is market supply and demand data and supply data from producers, and the output is the optimized price of ingredients. The server analyzes this data and optimizes market prices in real time.

[0609] Step 4:

[0610] The server uses a generative AI model to generate food packs based on the user's preference profile and supply-demand balance data. The input is the preference profile and supply-demand balance data, and the output is a personalized food pack proposal. The server integrates this data and generates a food pack optimized for the user.

[0611] Step 5:

[0612] The terminal obtains personalized food pack information suggested by the server and presents it to the user. The input is food pack suggestion data from the server, and the output is food pack information displayed on the user's terminal screen. The terminal displays the suggestions to the user in real time and prompts for confirmation.

[0613] Step 6:

[0614] The terminal presents real-time price information from the server to the user. The input is price information from the server, and the output is an optimized price displayed on the user's terminal screen. The user makes a purchasing decision based on this information.

[0615] Step 7:

[0616] The user checks the food pack suggestions and decides to purchase. The input is the food pack information and price information displayed on the terminal, and the output is the user's intention to purchase. When the user decides to purchase, the terminal sends the purchase information to the server.

[0617] Step 8:

[0618] The server receives the user's purchase intention and confirms the order. The input is the user's purchase information, and the output is the confirmed order data. Based on this, the server carries out the appropriate delivery procedures.

[0619] Step 9:

[0620] The terminal supports one-click purchase procedures. The input is the user's purchase decision, and the output is the transmission of purchase information to the server. The purchase procedure is completed when the user confirms the purchase with one click on the terminal.

[0621] 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.

[0622] This invention combines a system that makes the process of fresh ingredients from production to consumption transparent, optimizes supply and demand and prices using AI technology, and an emotion engine that recognizes user emotions. By directly connecting producers and consumers, this system can reduce food waste and suggest food packs that suit consumers' preferences.

[0623] Server Processing

[0624] Collection and analysis of purchase history:

[0625] The server periodically collects user purchase history data and stores it in a database. Based on the collected data, machine learning algorithms are used to analyze user preferences and generate a preference profile for each user. This preference profile is then used to make personalized recommendations.

[0626] Supply and demand balance analysis and price optimization:

[0627] The server receives production data provided by producers and analyzes it along with market consumption patterns. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. This price information is stored in a database and provided to user devices.

[0628] Introducing the Emotion Engine:

[0629] The emotion engine collects user emotional data and uses it to generate a preference profile. Specifically, the emotion engine analyzes emotions from the user's facial expressions, tone of voice, text input, etc. to understand the user's state of mind. This emotional data is added to the preference profile and helps make more accurate suggestions.

[0630] Generate personalized food pack suggestions:

[0631] The server uses generative AI to generate food packs based on the user's preference profile and supply-demand balance data. The food packs are optimized for the user's past consumption patterns, preferences, and even emotional data. The information on the suggested food packs is stored in a database and later provided to the user's device.

[0632] Terminal handling

[0633] Providing a user interface:

[0634] The terminal displays to the user food pack suggestions based on the user's purchasing history. The terminal obtains the suggested personalized food pack information from the server and visually displays it to the user.

[0635] Emotion data collection:

[0636] The device works in conjunction with an emotion engine to collect emotional data from the user's facial expressions, tone of voice, text input, etc. This emotional data is sent to the server in real time.

[0637] Real-time pricing information:

[0638] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[0639] Purchase assistance:

[0640] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the purchase information to the server, which then confirms the order.

[0641] User Behavior

[0642] Providing purchase history:

[0643] The user purchases ingredients in the same way as with regular online shopping, and the information is sent to the server.

[0644] Check out our ingredient pack suggestions:

[0645] The user can then view the personalized food packs suggested to them through the device, determine whether the displayed contents match their tastes and whether the price is reasonable, and then decide whether to purchase.

[0646] Purchasing decision:

[0647] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the order is sent to the server.

[0648] Specific examples

[0649] For example, suppose that data on ingredients purchased by User B has been accumulated. User B shops online on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and determines User B's preferences.

[0650] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User B.

[0651] Furthermore, the device's emotion engine analyzes User B's facial expressions and tone of voice to understand their emotional state for that day. For example, if User B is feeling stressed, it can suggest ingredients and menu items that have a relaxing effect, making it possible to provide suggestions that are in tune with the user's emotions.

[0652] When User B views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User B can confirm the purchase with one click and receive fresh ingredients. This process reduces food waste while providing ingredients that match User B's preferences and emotions.

[0653] The processing flow will be explained below.

[0654] Step 1:

[0655] The server collects the user's purchase history data, specifically, the ingredients and products the user has purchased in the past, as well as the dates and quantities associated with those purchases.

[0656] Step 2:

[0657] The server stores the collected purchase history data in a database, which stores purchasing pattern data for each user.

[0658] Step 3:

[0659] The server analyzes the accumulated purchase history data and uses machine learning algorithms to extract user preferences and trends and generate a preference profile that specifically identifies each user's tastes and consumption tendencies.

[0660] Step 4:

[0661] The server receives production information provided by producers and stores it in a database, including detailed data such as the type of crop or ingredient, harvest yield, and harvest time.

[0662] Step 5:

[0663] The server analyzes market consumption patterns and production information to determine the market supply and demand balance. Based on the supply and demand balance data, it runs an algorithm to optimize market prices in real time. The optimized price information is also stored in a database.

[0664] Step 6:

[0665] The device collects the user's emotional data, and the device's emotion engine analyzes the user's facial expressions, tone of voice, text input, etc. to understand the user's current emotional state.

[0666] Step 7:

[0667] The device transmits the collected user emotion data to the server in real time.

[0668] Step 8:

[0669] The server receives the user's emotional data and uses it to update the user's preference profile. Specifically, if the user is feeling stressed, the server will suggest foods that have a relaxing effect, and make recommendations based on the user's emotional state.

[0670] Step 9:

[0671] The server uses generative AI to generate food packs based on the user's preference profile, supply-demand balance data, and emotional data. This food pack is optimized based on the user's past consumption patterns, preferences, and emotional data.

[0672] Step 10:

[0673] The device displays food pack suggestions based on the user's purchasing history and emotional state. The device retrieves the suggested personalized food pack information from the server and visually displays it to the user.

[0674] Step 11:

[0675] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[0676] Step 12:

[0677] The user reviews the personalized food pack displayed, decides whether the suggestions match their tastes and the price is reasonable, and if they decide to purchase, clicks the purchase button.

[0678] Step 13:

[0679] The terminal receives the user's intention to purchase and transmits the purchase information to the server.

[0680] Step 14:

[0681] The server confirms the order based on the received purchase information. After the order is confirmed, it notifies the producer of the order details.

[0682] Step 15:

[0683] The server stores the order details and delivery information in a database.

[0684] Step 16:

[0685] The producer prepares ingredients based on the order details notified by the server.

[0686] Step 17:

[0687] The producer will send the ingredients to the specified delivery address, and the user can receive the delivered ingredients and use the suggested ingredient pack.

[0688] Through these steps, the entire system optimizes the process of fresh ingredients from production to consumption, and reduces food waste by making suggestions that are in line with the user's emotions.

[0689] Example 2

[0690] 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."

[0691] In today's consumer market, there is a need to optimize the balance between supply and demand for ingredients and make personalized recommendations based on consumer preferences and emotions. However, conventional systems only analyze ingredient purchasing and production data, and do not fully utilize consumer emotional data to make recommendations, making it difficult to make recommendations that are tailored to individual consumer preferences and emotions. Furthermore, it is difficult to analyze the appropriate supply and demand balance, resulting in increased food waste.

[0692] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0693] In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchasing history and analyzing preferences, means for analyzing the market supply and demand balance and optimizing prices, means for collecting user emotional data and analyzing it to suggest food packs based on a preference profile, and means for presenting the suggested food packs to the user and supporting the purchase process.

[0694] This will enable more personalized suggestions based on consumer preferences and emotions, optimize the supply and demand balance in real time, and reduce food waste.

[0695] "Production information" refers to detailed data on crop and product production provided by producers.

[0696] A "database" is an information system for systematically storing, managing, and analyzing collected information.

[0697] A "purchase history" is a detailed record of the purchases a user has made in the past.

[0698] "Preferences" refers to the preferences and tendencies that a user has toward specific products or ingredients.

[0699] "Analyzing" means analyzing user behavior and patterns based on accumulated data.

[0700] "Supply and demand balance" refers to the equilibrium between the supply of goods and services offered and the demand of consumers.

[0701] "Price optimization" means setting the most appropriate price by taking into account the supply and demand balance in the market.

[0702] "Emotion data" is data that represents the user's emotional state, and includes facial expressions, tone of voice, text input, and the like.

[0703] A "preference profile" is detailed information about a user's preferences and consumption patterns that is generated based on analysis.

[0704] A "food pack" is a product package that combines multiple ingredients and is suggested based on the user's preferences and emotional data.

[0705] "Suggesting" means presenting the user with the best options or products based on the analysis results.

[0706] "Presenting" means that the system shows information to the user visually or audibly.

[0707] "Supporting the purchase procedure" means assisting the user with a series of operations when purchasing a suggested product.

[0708] This invention combines a system that makes the process of fresh ingredients from production to consumption transparent, optimizes supply and demand and prices using generative AI models, and an emotion engine that recognizes user emotions. By directly connecting producers and consumers, this system can reduce food waste and suggest food packs tailored to consumer preferences.

[0709] Hardware and Software Configuration

[0710] The servers are equipped with high-performance processors and use database management systems (e.g., MySQL or PostgreSQL) to analyze large amounts of data in real time. Additionally, machine learning algorithms are implemented using Python scripts and libraries such as TensorFlow or PyTorch. Advanced generative AI models, such as GPT-3, are also used.

[0711] The device refers to the smartphone, tablet, or PC operated by the user, and is equipped with an emotion engine. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice, and employs analysis tools such as OpenCV and Google Cloud Speech-to-Text API. The user interface is built using JavaScript frameworks such as React and Vue.js.

[0712] System processing overview

[0713] The server first collects production information provided by producers and stores it in a database. It also periodically collects users' purchase history and uses machine learning algorithms to generate a user preference profile, which includes details such as purchase date and time, item name, quantity, and price.

[0714] The server then analyzes production information and market consumption data to determine the supply and demand balance, optimizes market prices in real time based on this information, and stores the price information in a database.

[0715] The server also collects the user's emotional data. The emotion engine analyzes the user's facial expressions, tone of voice, and text input to understand the user's state of mind. This emotional data is added to the user's preference profile to improve the accuracy of suggestions.

[0716] The server uses generative AI to generate a food pack based on the user's preference profile, supply-demand balance data, and emotional data. This proposal is stored in a database and later provided to the user's device. Specifically, the following prompt sentence is input into the generative AI model:

[0717] "Recommend optimal food packs based on the user's past purchase history and emotional data. For example, if the user is feeling stressed, include ingredients that will help them relax."

[0718] The device displays personalized food pack suggestions retrieved from the server to the user, and the user interface provides information in a visually easy-to-understand format, allowing the user to easily understand the suggestions.

[0719] The device works in conjunction with an emotion engine to collect emotional data in real time from the user's facial expressions, tone of voice, text input, etc., and sends this data to the server. When the user checks the suggested food pack and decides to purchase it, the device sends this information to the server, which then confirms the order.

[0720] Specific examples

[0721] For example, suppose that data on ingredients purchased by User B has been accumulated. User B shops online on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and determines User B's preferences.

[0722] Next, the server analyzes production information and the market supply and demand balance to optimize the price of chicken and vegetables in real time. Once the price is determined, the generation AI proposes an optimized vegetable and chicken food pack to User B.

[0723] Furthermore, the device's emotion engine analyzes User B's facial expressions and tone of voice to understand their emotional state for that day. For example, if User B is feeling stressed, it can suggest ingredients and menu items that have a relaxing effect, making it possible to provide suggestions that are in tune with the user's emotions.

[0724] When User B views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User B can confirm the purchase with one click and receive fresh ingredients. This reduces food waste while providing ingredients that match User B's preferences and emotions.

[0725] As described above, this invention makes it possible to efficiently manage the process of fresh ingredients from production to consumption, and to realize personalized suggestions that are in tune with the user's emotions.

[0726] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0727] Step 1:

[0728] Collecting purchase history data and storing it in a database

[0729] The server periodically collects information about ingredients purchased by users on an online shopping site. It uses a REST API to collect the data and stores the acquired data in a database. Purchase history data, such as the user ID, purchase date and time, product name, quantity, and price, is provided as input. The server inserts this data into a "purchase history" table.

[0730] Specific behavior:

[0731] Every time a user buys an ingredient, the details are sent to the server via an API and added as a new record to the database using an SQL query.

[0732] Step 2:

[0733] Generating a preference profile

[0734] The server uses a machine learning algorithm to generate a preference profile for each user based on the collected purchase history data. This uses a clustering algorithm and collaborative filtering. The data in the "Purchase History" table is used as input, and the generated preference profile is saved as output in the "Preference Profile" table.

[0735] Specific behavior:

[0736] Run a Python script to cluster the data using the Scikit-learn library to identify patterns of user preferences, and store the results in a database.

[0737] Step 3:

[0738] Analysis of production and market consumption data

[0739] The server receives production data provided by producers and analyzes it together with market consumption data. The ETL tool is used to import the data and store it in a database. The CSV file from the producer is used as input, and a "production data" table and a "consumption data" table are created as output.

[0740] Specific behavior:

[0741] Data files from producers are periodically uploaded to the server and imported into the database through batch processing using an ETL tool (e.g., Apache NiFi).

[0742] Step 4:

[0743] Supply and demand balance analysis and price optimization

[0744] The server analyzes the supply and demand balance based on the collected production and consumption data. Time series analysis and linear regression models are used for price optimization. The "production data" and "consumption data" tables are used as input, and the optimized market price is saved as output in the "market price" table.

[0745] Specific behavior:

[0746] Run time series analysis scripts in Python or R to forecast supply and demand balance and optimize prices. Update the results to a "market price" table using SQL queries.

[0747] Step 5:

[0748] Emotion data collection and analysis

[0749] The device uses an emotion engine to collect emotional data such as the user's facial expressions, tone of voice, and text input. This emotional data is sent to the server in real time. Data from the camera, microphone, and keyboard is used as input, and the analyzed emotional data is stored in an "emotion data" table as output.

[0750] Specific behavior:

[0751] The device uses OpenCV and the Google Cloud Speech-to-Text API to analyze emotions in real time, and the analyzed data is sent to the server via a REST API.

[0752] Step 6:

[0753] Generate personalized food packs

[0754] The server uses the generative AI model to generate food packs based on the user's preference profile, emotional data, and supply-demand balance data. The "preference profile," "emotion data," and "market price" tables are used as input, and the generated food packs are saved in the "suggested pack" table as output.

[0755] Specific behavior:

[0756] Enter the following prompt into a generative AI model (e.g., GPT-3) and get a response: "Suggest the optimal ingredient pack based on the user's past purchasing history data and emotional data. For example, if the user is feeling stressed, include ingredients that will help them relax." Save this response in a "Suggested Pack" table.

[0757] Step 7:

[0758] Displaying the proposed content on the user's device

[0759] The terminal displays the personalized food pack suggestions received from the server to the user. The data in the "Suggested Packs" table is used as input. The output is reflected in the user interface.

[0760] Specific behavior:

[0761] The device retrieves data from the server via a REST API and displays it in a UI using React and Vue.js, for example, creating attractive visualizations of ingredient lists and pricing information.

[0762] Step 8:

[0763] Collecting user reaction data and continuously learning for new suggestions

[0764] The device records how the user reacts to the suggestions. This reaction data is sent to the server to help improve future suggestions. The input is the user's reaction, and the output is stored in a "reaction data" table.

[0765] Specific behavior:

[0766] It records whether the user accepts or rejects the suggestion and sends the result to the server via a REST API, which will be used as training data for future generative AI models.

[0767] (Application example 2)

[0768] 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."

[0769] In today's food distribution system, the process from production to consumption is complex, making it difficult for consumers to obtain fresh ingredients. Furthermore, there is a lack of personalized food packs that take into account consumers' preferences and emotions, resulting in a lower satisfaction level in the purchasing experience. Furthermore, there are issues such as increased food waste and difficulty in optimizing the supply and demand balance.

[0770] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchase histories and analyzing preferences, means for analyzing the market supply and demand balance and optimizing prices, means for proposing ingredient packs based on the generated preference profile, means for presenting the proposed ingredient packs to the user and supporting the purchase process, means for collecting emotional data from the user's facial expressions and tone of voice, means for analyzing the collected emotional data and reflecting it in the preference profile, and means for proposing personalized ingredient packs based on the emotional data. This makes it possible to propose ingredient packs that are optimally tailored to the consumer's emotional state and preferences, improving the purchasing experience and reducing food waste.

[0771] "Production information" refers to data related to the production of food ingredients such as agricultural and livestock products, and includes information such as production area, harvest time, quantity, and quality.

[0772] A "database" is a collection of data that is structured so that specific data can be efficiently managed, searched, and retrieved.

[0773] "Purchase history" is a record of products purchased by a user in the past, and includes information such as purchase date and time, product name, quantity, and price.

[0774] A "preference profile" is a collection of information about a user's individual preferences and tastes, obtained by analyzing the user's past purchasing history and behavioral data.

[0775] "Supply and demand balance" refers to the relationship between supply and demand in the market, which determines market trends and prices.

[0776] "Price optimization" is the process of efficiently determining sales prices based on information on the supply and demand balance, and is an adjustment that maximizes profits.

[0777] "Suggestion" refers to the act of recommending a particular product or service to a user, and in this case refers to presenting a personalized food pack to the user.

[0778] The "purchase procedure" refers to a series of operations and processes required to purchase the product selected by the user, including payment, delivery arrangements, etc.

[0779] "Emotion data" refers to data relating to individual emotional states obtained from the user's facial expressions, tone of voice, text input, and the like.

[0780] "Personalization" refers to the process of optimizing the content of a service or product to suit the preferences and characteristics of each individual user.

[0781] A "food pack" is a set of ingredients combined according to a specific recipe or menu.

[0782] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze user data and generate new suggestions or predictions.

[0783] A "prompt" is an instruction used when inputting data into a generative AI model, and is intended to clarify what kind of output is expected.

[0784] This invention realizes a system that collects user purchasing history and emotional data, and proposes and provides personalized food packs based on that data. This system is composed of a server and a user terminal.

[0785] Server processing overview

[0786] The server performs its processing using the following hardware and software:

[0787] Hardware: High-speed server

[0788] Software: Database Management Systems (DBMS), machine learning algorithms (e.g., TensorFlow, Scikit-learn), emotion recognition engines, generative AI models

[0789] 1. Collecting production information

[0790] The server collects agricultural and livestock production information from external data sources and stores it in a database. The collected data includes information on production area, harvest time, quantity, quality, etc.

[0791] 2. Collecting purchase history and analyzing preferences

[0792] The server collects the user's purchase history and analyzes their preferences based on that information. The analyzed data is stored in a database as a preference profile for each user.

[0793] 3. Analysis of market supply and demand balance and price optimization

[0794] The server analyzes market consumption patterns and production data. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. The optimized price information is stored in a database.

[0795] 4. Emotional Data Collection and Analysis

[0796] The server uses an emotion recognition engine to collect emotional data from the user's facial expressions, tone of voice, and text input, which is then sent to the server in real time for analysis.

[0797] 5. Generate personalized food pack suggestions

[0798] The server uses a generative AI model to generate food packs based on the user's preference profile, real-time emotional data, and supply-demand balance data. The generated food packs are optimized to the user's preferences and emotional state at the time.

[0799] Terminal processing overview

[0800] The device performs its processing using the following hardware and software:

[0801] Hardware: Smartphones, tablets, smart glasses

[0802] Software: User interface software, emotion recognition engine

[0803] 1. Providing a user interface

[0804] The device visually displays to the user a food pack recommendation based on the user's purchasing history, and the user can check the personalized food pack recommendation information on the device screen.

[0805] 2. Collecting Emotional Data

[0806] The device works in conjunction with an emotion recognition engine to collect emotional data in real time from the user's facial expressions, tone of voice, text input, etc. This emotional data is immediately sent to the server.

[0807] 3. Real-time price information

[0808] The terminal presents the user with real-time market price information received from the server, allowing the user to make a price-based purchasing decision.

[0809] 4. Purchase procedure support

[0810] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the information to the server, which then confirms the order.

[0811] Examples of concrete examples and prompts

[0812] As a concrete example, consider a case where a user is feeling stressed. In this case, the emotion recognition engine detects the stressed state and suggests a meal pack containing foods with a relaxing effect (e.g., herbal tea and nuts).

[0813] Example prompt sentence:

[0814] "If the user is currently feeling stressed, suggest a food pack containing foods that have a relaxing effect."

[0815] In this way, it becomes possible to propose the most suitable food pack that matches the consumer's emotional state and preferences, improving the purchasing experience and reducing food waste.

[0816] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0817] Step 1:

[0818] The server collects production information from external data sources and stores it in a database. The input includes production information data such as production area, harvest time, quantity, and quality. Data processing involves converting this information into a database format and saving it in the database. This allows the server to always have the latest production information. The output is an updated database.

[0819] Step 2:

[0820] The server collects user purchase history data. Input includes purchase history data such as purchase date and time, product name, quantity, and price. Data processing involves analyzing the user's preferences from this purchase history and creating a preference profile. As a specific example, the server analyzes past purchase frequency and patterns. The output is a preference profile for each user.

[0821] Step 3:

[0822] The server analyzes the market supply and demand balance. Inputs include production data and consumption pattern data. Data processing involves calculating the market supply and demand balance based on these data and optimizing real-time prices. Specifically, a machine learning algorithm is used to draw a supply and demand curve and calculate the optimal price. The output is optimized market price information.

[0823] Step 4:

[0824] The device collects emotional data from the user's facial expressions and tone of voice. Inputs include real-time data from the camera and microphone. Data processing involves analyzing this data using an emotion recognition engine to identify the user's emotional state. For example, emotions such as joy or sadness can be detected from the user's facial expressions. The output is the analyzed emotional data.

[0825] Step 5:

[0826] The server analyzes the collected emotional data and reflects it in the preference profile. The input includes emotional data and an existing preference profile. The data is processed by updating the preference profile according to the emotional state. Specifically, it takes into account the tendency of stressed users to prefer foods with a relaxing effect. The output is the updated preference profile.

[0827] Step 6:

[0828] The server uses a generative AI model to suggest a personalized food pack based on emotional data and a preference profile. The input includes emotional data, a preference profile, and optimized market price information. For data processing, the generative AI model is used to generate an optimal food pack. A specific prompt is used: "If the user is currently feeling stressed, please suggest a food pack that includes foods that have a relaxing effect." The output is a personalized food pack suggestion.

[0829] Step 7:

[0830] The terminal receives the suggested ingredient pack information from the server and visually displays it to the user. The input includes the personalized ingredient pack suggestion information. Specific operations include displaying ingredient pack contents and price information on the terminal screen. The output is the personalized ingredient pack information presented to the user.

[0831] Step 8:

[0832] The user checks the suggested food packs on the terminal and makes a decision to purchase. The input includes information about the suggested food packs. The specific action is to click the purchase button. The output is the user's purchase intention information.

[0833] Step 9:

[0834] The terminal transmits the user's purchase intention information to the server. The input includes the purchase intention information. Specifically, after the purchase is confirmed, the purchase information is transmitted to the server. The output is the purchase information received by the server.

[0835] Step 10:

[0836] The server processes the received purchase information and confirms the order. The input includes the user's purchase information. Specific operations include saving the order in a database and arranging for delivery. The output is the confirmed order information. As a result, the user can receive the specified food pack.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] [Third embodiment]

[0841] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0842] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0843] 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).

[0844] 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.

[0845] 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.

[0846] 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).

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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."

[0853] This invention is a system that makes the process of fresh ingredients from production to consumption transparent and optimizes supply and demand and prices using AI technology. By directly connecting producers and consumers, this system reduces food waste and proposes food packs tailored to consumer preferences.

[0854] Server Processing

[0855] Collection and analysis of purchase history:

[0856] The server periodically collects user purchase history data and stores it in a database. Based on the collected data, machine learning algorithms are used to analyze user preferences and generate a preference profile for each user. This preference profile is then used to make personalized recommendations.

[0857] Supply and demand balance analysis and price optimization:

[0858] The server receives production data provided by producers and analyzes it along with market consumption patterns. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. This price information is stored in a database and provided to user devices.

[0859] Generate personalized food pack suggestions:

[0860] The server uses AI to generate food packs based on the user's preference profile and supply-demand balance data. The food packs are optimized for the user's past consumption patterns and preferences. The information on the suggested food packs is stored in a database and later provided to the user's device.

[0861] Terminal handling

[0862] Providing a user interface:

[0863] The terminal displays to the user a food pack suggestion based on the user's purchasing history. When the user accesses the terminal, the terminal retrieves the suggested personalized food pack information from the server and displays it to the user.

[0864] Real-time pricing information:

[0865] The terminal receives real-time price information from the server and presents it to the user, who can then make a purchasing decision based on it.

[0866] Purchase assistance:

[0867] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the purchase information to the server, which then confirms the order.

[0868] User Behavior

[0869] Providing purchase history:

[0870] The user purchases ingredients in the same way as with regular online shopping, and the information is sent to the server.

[0871] Check out our ingredient pack suggestions:

[0872] The user can then view the personalized food packs suggested to them through the device, determine whether the displayed contents match their tastes and whether the price is reasonable, and then decide whether to purchase.

[0873] Purchasing decision:

[0874] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the order is sent to the server.

[0875] Specific examples

[0876] For example, suppose that data on ingredients purchased by User A multiple times in the past is stored. User A goes online shopping on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and understands User A's preferences.

[0877] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User A.

[0878] When User A views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User A can confirm the purchase with one click and receive fresh ingredients. This process reduces food waste while providing ingredients tailored to User A's preferences.

[0879] The processing flow will be explained below.

[0880] Step 1:

[0881] The server collects the user's purchase history data, specifically, the ingredients and products the user has purchased in the past, as well as the dates and quantities associated with those purchases.

[0882] Step 2:

[0883] The server stores the collected purchase history data in a database, which stores purchasing pattern data for each user.

[0884] Step 3:

[0885] The server analyzes the accumulated purchase history data and uses machine learning algorithms to extract user preferences and trends and generate a preference profile that specifically identifies each user's tastes and consumption tendencies.

[0886] Step 4:

[0887] The server receives production information provided by producers and stores it in a database, including detailed data such as the type of crop or ingredient, harvest yield, and harvest time.

[0888] Step 5:

[0889] The server analyzes market consumption patterns and production information to determine the market supply and demand balance. Based on the supply and demand balance data, it runs an algorithm to optimize market prices in real time. The optimized price information is also stored in a database.

[0890] Step 6:

[0891] The server uses AI to generate food packs based on the user's preference profile and supply-demand balance data. The generated food packs are optimized for the user's past consumption patterns and preferences.

[0892] Step 7:

[0893] The terminal displays to the user a food pack suggestion based on the user's purchasing history. The terminal obtains the suggested personalized food pack information from the server and visually displays it to the user.

[0894] Step 8:

[0895] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[0896] Step 9:

[0897] The user reviews the personalized food pack displayed, decides whether the suggestions match their tastes and the price is reasonable, and if they decide to purchase, clicks the purchase button.

[0898] Step 10:

[0899] The terminal receives the user's intention to purchase and transmits the purchase information to the server.

[0900] Step 11:

[0901] The server confirms the order based on the received purchase information. After the order is confirmed, it notifies the producer of the order details.

[0902] Step 12:

[0903] The server stores the order details and delivery information in a database.

[0904] Step 13:

[0905] The producer prepares ingredients based on the order details notified by the server.

[0906] Step 14:

[0907] The producer will send the ingredients to the specified delivery address, and the user can receive the delivered ingredients and use the suggested ingredient pack.

[0908] These steps enable the entire system to optimize the process of fresh ingredients from production to consumption and reduce food waste.

[0909] Example 1

[0910] 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."

[0911] In the conventional food distribution system, there are many intermediaries between producers and consumers, which leads to problems such as supply-demand imbalances, price fluctuations, and food waste. There is also a lack of personalized proposals tailored to consumer preferences, resulting in low consumer satisfaction. To solve these issues, a system is needed that makes the entire process from production to consumption transparent and optimizes supply-demand and prices.

[0912] 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.

[0913] In this invention, the server includes a means for collecting production information and storing it in a database, a means for collecting user purchase history data and analyzing user preferences using a machine learning algorithm, and a means for analyzing the market supply and demand balance and optimizing prices in real time, thereby optimizing the supply and demand balance of ingredients and proposing ingredient packs that suit users' preferences.

[0914] "Production information" refers to various data provided by producers, such as harvest volume, quality, and supply forecasts for agricultural and livestock products.

[0915] "Database accumulation" refers to the process of storing collected information in a digital format and making it available for access and analysis.

[0916] "Purchase history" is detailed data such as the products a user has purchased in the past, the purchase date and time, the purchase amount, and the price.

[0917] A "machine learning algorithm" is a computational method for finding patterns and regularities in large amounts of data and making predictions and classifications.

[0918] "Analyzing preferences" means using machine learning algorithms to analyze what products a user prefers and create a profile of the user's unique preferences.

[0919] "Supply and demand balance" refers to the relationship between the amount of goods supplied and the amount of goods consumed in the market, which allows us to understand oversupply and shortages.

[0920] "Optimizing prices in real time" means instantly calculating product prices and setting optimal prices based on the current supply and demand balance and market conditions.

[0921] "Generative AI" is a computer program that uses artificial intelligence technology to automatically generate new data and suggestions based on specific input conditions.

[0922] A "food pack" is a set of ingredients selected to suit a particular user's preferences or market conditions.

[0923] A "user terminal" is a digital device that allows a user to view and manipulate information, and examples include personal computers and smartphones.

[0924] The "purchase procedure" is a series of operations and confirmation processes for purchasing the product selected by the user.

[0925] "Confirming an order" is the process by which the user's intention to purchase is finally recognized and the transaction is officially registered in the system.

[0926] MODE FOR CARRYING OUT THE INVENTION

[0927] This invention is a system that makes the process of fresh ingredients from production to consumption transparent and optimizes supply and demand and prices using AI technology. By directly connecting producers and consumers, this system reduces food waste and proposes food packs tailored to consumer preferences.

[0928] System Overview

[0929] This system consists of three main components: a server, a terminal, and a user. The specific roles of each component are as follows:

[0930] Server Roles

[0931] The server performs the following functions:

[0932] 1. Collecting production information and storing it in a database

[0933] The server collects production data provided by producers (e.g., harvest volume, quality, supply forecast, etc.) and stores it in a database using a database system such as MySQL or PostgreSQL.

[0934] 2. Collecting and analyzing user purchase history data

[0935] The server collects the user's purchase history data and analyzes the user's preferences using machine learning algorithms (e.g., TensorFlow or Scikit-learn). The analyzed preference profile is stored in a database.

[0936] 3. Supply and demand balance analysis and price optimization

[0937] The server combines consumption and production data provided by the market to analyze the supply and demand balance and optimize prices in real time, using time series analysis techniques such as the ARIMA model.

[0938] 4. Proposal generation of food packs

[0939] The server uses a generative AI model (e.g., GPT-3) to generate food packs based on the user's preference profile and supply-demand balance data.

[0940] Device Role

[0941] The terminal provides the user with the following features:

[0942] 1. Providing a user interface

[0943] The device displays personalized food pack suggestions to the user, using web application technologies such as React and Vue.js.

[0944] 2. Real-time price information

[0945] The terminal receives real-time price information from the server and presents it to the user, using technologies such as WebSocket and AJAX.

[0946] 3. Purchase procedure support

[0947] The terminal helps users purchase the suggested food packs with one click. The purchase information is sent to the server and the order is confirmed. HTTPS is used for secure communication.

[0948] User Roles

[0949] Users interact with the system as follows:

[0950] 1. Providing purchase history

[0951] The user purchases ingredients in the same way as with regular online shopping, and the purchase information is sent to the server.

[0952] 2. Check the food pack suggestions

[0953] The user checks the proposed personalized food pack through the terminal and decides whether to purchase it.

[0954] 3. Purchasing Decision

[0955] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the information is sent to the server.

[0956] Specific examples

[0957] For example, suppose that data on ingredients purchased by User A multiple times in the past is stored. User A goes online shopping on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and understands User A's preferences.

[0958] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User A.

[0959] When User A views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is right. User A can confirm the purchase with one click and receive fresh ingredients.

[0960] Prompt Sentence Examples

[0961] Below are some examples of specific prompts to input to a generative AI model:

[0962] Prompt: "Based on purchasing history data, please recommend a fresh food pack suitable for User A. Past purchases have always included fresh vegetables and chicken. Please also consider the supply-demand balance and market price when making your recommendation."

[0963] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0964] Step 1: Collect purchase history data

[0965] The server collects purchase history data every time a user makes an online purchase. Specifically, when a user adds an item to their shopping cart and clicks the "Purchase" button on the purchase confirmation screen, the details (purchase date and time, purchased item, purchase quantity, price, etc.) are sent to the database. The input is the user's purchase information, and the output is the purchase history data stored in the database.

[0966] Step 2: User preference analysis

[0967] The server analyzes user preferences based on the accumulated purchase history data. Specifically, it uses a machine learning algorithm (e.g., Scikit-learn's clustering method) to identify the specific ingredients that the user prefers. The input is the purchase history data collected in step 1, and the output is a preference profile for each user. The server stores the analysis results in a database.

[0968] Step 3: Collect and store production data

[0969] The server collects real-time production data provided by producers and stores it in a database. Specifically, producers send data from dedicated terminals to the server, which then stores it in the database. The input is production data from producers, and the output is production information stored in the database.

[0970] Step 4: Analyze the supply and demand balance

[0971] The server analyzes the supply and demand balance based on market consumption and production data. Specifically, it obtains market consumption and production data from the database and calculates the supply and demand balance using time series analysis and statistical methods (e.g., ARIMA model). The input is market consumption and production data, and the output is real-time supply and demand balance information.

[0972] Step 5: Price optimization

[0973] The server optimizes prices in real time based on supply and demand balance information. Specifically, it applies a pricing algorithm based on supply and demand balance information to calculate the optimal price. The input is real-time supply and demand balance information, and the output is optimized price information. The server stores this price information in a database.

[0974] Step 6: Generate ingredient pack suggestions

[0975] The server uses a generative AI model to generate a food pack based on the user's preference profile and supply-demand balance data. Specifically, it generates a prompt sentence using the preference profile and supply-demand balance data as input, and inputs it into the generative AI model. The generated food pack suggestions are saved in a database. The input is the preference profile and supply-demand balance data, and the output is the suggested food pack.

[0976] Prompt: "Based on purchasing history data, please recommend a fresh food pack suitable for User A. Past purchases have always included fresh vegetables and chicken. Please also consider the supply-demand balance and market price when making your recommendation."

[0977] Step 7: Providing a User Interface

[0978] The terminal displays the personalized food pack suggested to the user. Specifically, the terminal obtains the suggested information from the server and displays it on the screen. The user checks it and decides whether to purchase it or not, if necessary. The input is the suggested information obtained from the server, and the output is the food pack suggestion displayed on the terminal.

[0979] Step 8: Support with checkout

[0980] The terminal allows the user to purchase the selected food pack with one click. Specifically, when the user clicks the purchase button, the purchase information is sent to the server. The input is the user's purchase intention, and the output is the purchase information sent to the server.

[0981] Step 9: Confirm your order and update your data

[0982] The server confirms the order based on the transmitted purchase information and updates the database. Specifically, it records the order information in the database and updates inventory information and the user's purchase history data. The input is the user's purchase information, and the output is the updated information recorded in the database.

[0983] (Application example 1)

[0984] 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."

[0985] Modern food delivery services face challenges such as food waste, a lack of transparency in the supply chain, and a lack of methods for providing products that meet consumer preferences. They also face difficulties in effectively utilizing user purchasing data to optimize the supply-demand balance. This makes it difficult to provide ingredients at the best price for consumers, and there is a lack of an effective system for realizing personalized recommendations.

[0986] 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.

[0987] In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchase histories and analyzing preferences, means for analyzing the market supply-demand balance and optimizing prices, means for proposing food packs based on the generated preference profile, means for presenting the proposed food packs to the user and supporting the purchase process, and means for providing an application to be installed on a smartphone and displaying proposals and price information in real time, thereby making it possible to provide personalized food packs based on the user's preferences at optimal prices.

[0988] "Production information" refers to data provided by food producers regarding the yield, quality, and supply period of crops and products.

[0989] "Means of storing in a database" refers to systems or software for efficiently storing collected production information and purchase history information.

[0990] "Purchase history" refers to detailed information about products a user has purchased in the past, such as the purchase date and time, quantity, and price.

[0991] "Means for analyzing preferences" refers to algorithms and machine learning models that analyze users' preferences and purchasing patterns based on their purchase history.

[0992] "Supply and demand balance" refers to the state of supply and demand for a particular product or ingredient in the market.

[0993] "Price optimization tools" are algorithms or models that calculate the optimal selling price for ingredients or products based on the market supply and demand balance.

[0994] A "preference profile" is a collection of data that shows each user's preferences and purchasing patterns.

[0995] A "food pack" is a package of multiple ingredients suggested based on the user's preference profile.

[0996] "Means to support the purchasing process" refers to a system or interface that allows users to easily purchase the suggested food packs.

[0997] The "application installed on a smartphone" is software that runs on a smartphone and provides users with personalized food pack suggestions and price information.

[0998] "Means for displaying in real time" refers to an interface that has the function of instantly displaying to the user the latest offers and price information provided by the server.

[0999] A "user terminal" is a device used by an end user, such as a smartphone or tablet.

[1000] "One-click order confirmation" refers to a function or system that allows users to complete the purchase process with a single click.

[1001]

[1002] This invention is a system that makes the process from food production to consumption transparent and optimizes supply and demand and prices using AI technology. A specific example is shown below.

[1003] The server first collects production information provided by producers and stores it in a database. This production information includes information such as the yield, quality, and supply period of crops and products. Next, it periodically collects users' purchase histories and uses machine learning algorithms to analyze their preferences and generate a preference profile. The server then analyzes the market supply and demand balance and optimizes market prices in real time based on this analysis. This information is stored in the database and provided to users via an application installed on their smartphones.

[1004] The server uses a generative AI model to generate a food pack based on the user's preference profile and supply-demand balance data. This food pack is optimized based on the user's past consumption patterns and preferences. The device retrieves the personalized food pack information suggested by the server and presents it to the user in real time. Real-time price information from the server is also presented to the user through the device. The user can make a purchasing decision based on this information.

[1005] Once the user confirms the food pack suggestions and decides to purchase, the device sends the purchase information to the server, which then confirms the order. Furthermore, the system is designed to allow users to complete the purchase process with just one click, making it extremely convenient for users.

[1006] As an example, consider a case where data on ingredients purchased multiple times by a user has been accumulated. For example, if a user purchases fresh vegetables and domestically produced chicken online on Monday, the server analyzes this data to understand the user's preferences. The server analyzes agricultural production information and the market supply and demand balance to optimize the price of chicken and vegetables in real time. The generative AI model proposes an optimized vegetable and chicken ingredient pack for the user. When the user checks the proposed pack on their home device, they determine that it contains their favorite vegetables and chicken and is reasonably priced. The user can confirm the purchase with one click and receive fresh ingredients. This process makes it possible to provide ingredients tailored to the user's preferences while reducing food waste.

[1007] Example prompt sentence:

[1008] "Design a system that analyzes user preferences based on their purchasing history and suggests food packs that optimize the supply-demand balance. For example, for a user who purchases a lot of fresh tomatoes and domestic chicken, suggest a set of fresh tomatoes and chicken at the optimal price."

[1009] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1010] Step 1:

[1011] The server collects production information provided by producers and stores it in a database. The input is production data from producers, which includes detailed information on crops and products, such as yield, quality, and supply timing. The server efficiently stores this data in a database for future analysis.

[1012] Step 2:

[1013] The server periodically collects users' purchase history and analyzes their preferences using a machine learning algorithm. The input is the user's purchase history data, and the output is the user's preference profile. The server analyzes this data to understand each user's preferences and generate an individual preference profile.

[1014] Step 3:

[1015] The server analyzes the market supply and demand balance and optimizes prices. The input is market supply and demand data and supply data from producers, and the output is the optimized price of ingredients. The server analyzes this data and optimizes market prices in real time.

[1016] Step 4:

[1017] The server uses a generative AI model to generate food packs based on the user's preference profile and supply-demand balance data. The input is the preference profile and supply-demand balance data, and the output is a personalized food pack proposal. The server integrates this data and generates a food pack optimized for the user.

[1018] Step 5:

[1019] The terminal obtains personalized food pack information suggested by the server and presents it to the user. The input is food pack suggestion data from the server, and the output is food pack information displayed on the user's terminal screen. The terminal displays the suggestions to the user in real time and prompts for confirmation.

[1020] Step 6:

[1021] The terminal presents real-time price information from the server to the user. The input is price information from the server, and the output is an optimized price displayed on the user's terminal screen. The user makes a purchasing decision based on this information.

[1022] Step 7:

[1023] The user checks the food pack suggestions and decides to purchase. The input is the food pack information and price information displayed on the terminal, and the output is the user's intention to purchase. When the user decides to purchase, the terminal sends the purchase information to the server.

[1024] Step 8:

[1025] The server receives the user's purchase intention and confirms the order. The input is the user's purchase information, and the output is the confirmed order data. Based on this, the server carries out the appropriate delivery procedures.

[1026] Step 9:

[1027] The terminal supports one-click purchase procedures. The input is the user's purchase decision, and the output is the transmission of purchase information to the server. The purchase procedure is completed when the user confirms the purchase with one click on the terminal.

[1028] 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.

[1029] This invention combines a system that makes the process of fresh ingredients from production to consumption transparent, optimizes supply and demand and prices using AI technology, and an emotion engine that recognizes user emotions. By directly connecting producers and consumers, this system can reduce food waste and suggest food packs that suit consumers' preferences.

[1030] Server Processing

[1031] Collection and analysis of purchase history:

[1032] The server periodically collects user purchase history data and stores it in a database. Based on the collected data, machine learning algorithms are used to analyze user preferences and generate a preference profile for each user. This preference profile is then used to make personalized recommendations.

[1033] Supply and demand balance analysis and price optimization:

[1034] The server receives production data provided by producers and analyzes it along with market consumption patterns. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. This price information is stored in a database and provided to user devices.

[1035] Introducing the Emotion Engine:

[1036] The emotion engine collects user emotional data and uses it to generate a preference profile. Specifically, the emotion engine analyzes emotions from the user's facial expressions, tone of voice, text input, etc. to understand the user's state of mind. This emotional data is added to the preference profile and helps make more accurate suggestions.

[1037] Generate personalized food pack suggestions:

[1038] The server uses generative AI to generate food packs based on the user's preference profile and supply-demand balance data. The food packs are optimized for the user's past consumption patterns, preferences, and even emotional data. The information on the suggested food packs is stored in a database and later provided to the user's device.

[1039] Terminal handling

[1040] Providing a user interface:

[1041] The terminal displays to the user food pack suggestions based on the user's purchasing history. The terminal obtains the suggested personalized food pack information from the server and visually displays it to the user.

[1042] Emotion data collection:

[1043] The device works in conjunction with an emotion engine to collect emotional data from the user's facial expressions, tone of voice, text input, etc. This emotional data is sent to the server in real time.

[1044] Real-time pricing information:

[1045] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[1046] Purchase assistance:

[1047] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the purchase information to the server, which then confirms the order.

[1048] User Behavior

[1049] Providing purchase history:

[1050] The user purchases ingredients in the same way as with regular online shopping, and the information is sent to the server.

[1051] Check out our ingredient pack suggestions:

[1052] The user can then view the personalized food packs suggested to them through the device, determine whether the displayed contents match their tastes and whether the price is reasonable, and then decide whether to purchase.

[1053] Purchasing decision:

[1054] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the order is sent to the server.

[1055] Specific examples

[1056] For example, suppose that data on ingredients purchased by User B has been accumulated. User B shops online on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and determines User B's preferences.

[1057] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User B.

[1058] Furthermore, the device's emotion engine analyzes User B's facial expressions and tone of voice to understand their emotional state for that day. For example, if User B is feeling stressed, it can suggest ingredients and menu items that have a relaxing effect, making it possible to provide suggestions that are in tune with the user's emotions.

[1059] When User B views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User B can confirm the purchase with one click and receive fresh ingredients. This process reduces food waste while providing ingredients that match User B's preferences and emotions.

[1060] The processing flow will be explained below.

[1061] Step 1:

[1062] The server collects the user's purchase history data, specifically, the ingredients and products the user has purchased in the past, as well as the dates and quantities associated with those purchases.

[1063] Step 2:

[1064] The server stores the collected purchase history data in a database, which stores purchasing pattern data for each user.

[1065] Step 3:

[1066] The server analyzes the accumulated purchase history data and uses machine learning algorithms to extract user preferences and trends and generate a preference profile that specifically identifies each user's tastes and consumption tendencies.

[1067] Step 4:

[1068] The server receives production information provided by producers and stores it in a database, including detailed data such as the type of crop or ingredient, harvest yield, and harvest time.

[1069] Step 5:

[1070] The server analyzes market consumption patterns and production information to determine the market supply and demand balance. Based on the supply and demand balance data, it runs an algorithm to optimize market prices in real time. The optimized price information is also stored in a database.

[1071] Step 6:

[1072] The device collects the user's emotional data, and the device's emotion engine analyzes the user's facial expressions, tone of voice, text input, etc. to understand the user's current emotional state.

[1073] Step 7:

[1074] The device transmits the collected user emotion data to the server in real time.

[1075] Step 8:

[1076] The server receives the user's emotional data and uses it to update the user's preference profile. Specifically, if the user is feeling stressed, the server will suggest foods that have a relaxing effect, and make recommendations based on the user's emotional state.

[1077] Step 9:

[1078] The server uses generative AI to generate food packs based on the user's preference profile, supply-demand balance data, and emotional data. This food pack is optimized based on the user's past consumption patterns, preferences, and emotional data.

[1079] Step 10:

[1080] The device displays food pack suggestions based on the user's purchasing history and emotional state. The device retrieves the suggested personalized food pack information from the server and visually displays it to the user.

[1081] Step 11:

[1082] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[1083] Step 12:

[1084] The user reviews the personalized food pack displayed, decides whether the suggestions match their tastes and the price is reasonable, and if they decide to purchase, clicks the purchase button.

[1085] Step 13:

[1086] The terminal receives the user's intention to purchase and transmits the purchase information to the server.

[1087] Step 14:

[1088] The server confirms the order based on the received purchase information. After the order is confirmed, it notifies the producer of the order details.

[1089] Step 15:

[1090] The server stores the order details and delivery information in a database.

[1091] Step 16:

[1092] The producer prepares ingredients based on the order details notified by the server.

[1093] Step 17:

[1094] The producer will send the ingredients to the specified delivery address, and the user can receive the delivered ingredients and use the suggested ingredient pack.

[1095] Through these steps, the entire system optimizes the process of fresh ingredients from production to consumption, and reduces food waste by making suggestions that are in line with the user's emotions.

[1096] Example 2

[1097] 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."

[1098] In today's consumer market, there is a need to optimize the balance between supply and demand for ingredients and make personalized recommendations based on consumer preferences and emotions. However, conventional systems only analyze ingredient purchasing and production data, and do not fully utilize consumer emotional data to make recommendations, making it difficult to make recommendations that are tailored to individual consumer preferences and emotions. Furthermore, it is difficult to analyze the appropriate supply and demand balance, resulting in increased food waste.

[1099] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1100] In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchasing history and analyzing preferences, means for analyzing the market supply and demand balance and optimizing prices, means for collecting user emotional data and analyzing it to suggest food packs based on a preference profile, and means for presenting the suggested food packs to the user and supporting the purchase process.

[1101] This will enable more personalized suggestions based on consumer preferences and emotions, optimize the supply and demand balance in real time, and reduce food waste.

[1102] "Production information" refers to detailed data on crop and product production provided by producers.

[1103] A "database" is an information system for systematically storing, managing, and analyzing collected information.

[1104] A "purchase history" is a detailed record of the purchases a user has made in the past.

[1105] "Preferences" refers to the preferences and tendencies that a user has toward specific products or ingredients.

[1106] "Analyzing" means analyzing user behavior and patterns based on accumulated data.

[1107] "Supply and demand balance" refers to the equilibrium between the supply of goods and services offered and the demand of consumers.

[1108] "Price optimization" means setting the most appropriate price by taking into account the supply and demand balance in the market.

[1109] "Emotion data" is data that represents the user's emotional state, and includes facial expressions, tone of voice, text input, and the like.

[1110] A "preference profile" is detailed information about a user's preferences and consumption patterns that is generated based on analysis.

[1111] A "food pack" is a product package that combines multiple ingredients and is suggested based on the user's preferences and emotional data.

[1112] "Suggesting" means presenting the user with the best options or products based on the analysis results.

[1113] "Presenting" means that the system shows information to the user visually or audibly.

[1114] "Supporting the purchase procedure" means assisting the user with a series of operations when purchasing a suggested product.

[1115] This invention combines a system that makes the process of fresh ingredients from production to consumption transparent, optimizes supply and demand and prices using generative AI models, and an emotion engine that recognizes user emotions. By directly connecting producers and consumers, this system can reduce food waste and suggest food packs tailored to consumer preferences.

[1116] Hardware and Software Configuration

[1117] The servers are equipped with high-performance processors and use database management systems (e.g., MySQL or PostgreSQL) to analyze large amounts of data in real time. Additionally, machine learning algorithms are implemented using Python scripts and libraries such as TensorFlow or PyTorch. Advanced generative AI models, such as GPT-3, are also used.

[1118] The device refers to the smartphone, tablet, or PC operated by the user, and is equipped with an emotion engine. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice, and employs analysis tools such as OpenCV and Google Cloud Speech-to-Text API. The user interface is built using JavaScript frameworks such as React and Vue.js.

[1119] System processing overview

[1120] The server first collects production information provided by producers and stores it in a database. It also periodically collects users' purchase history and uses machine learning algorithms to generate a user preference profile, which includes details such as purchase date and time, item name, quantity, and price.

[1121] The server then analyzes production information and market consumption data to determine the supply and demand balance, optimizes market prices in real time based on this information, and stores the price information in a database.

[1122] The server also collects the user's emotional data. The emotion engine analyzes the user's facial expressions, tone of voice, and text input to understand the user's state of mind. This emotional data is added to the user's preference profile to improve the accuracy of suggestions.

[1123] The server uses generative AI to generate a food pack based on the user's preference profile, supply-demand balance data, and emotional data. This proposal is stored in a database and later provided to the user's device. Specifically, the following prompt sentence is input into the generative AI model:

[1124] "Recommend optimal food packs based on the user's past purchase history and emotional data. For example, if the user is feeling stressed, include ingredients that will help them relax."

[1125] The device displays personalized food pack suggestions retrieved from the server to the user, and the user interface provides information in a visually easy-to-understand format, allowing the user to easily understand the suggestions.

[1126] The device works in conjunction with an emotion engine to collect emotional data in real time from the user's facial expressions, tone of voice, text input, etc., and sends this data to the server. When the user checks the suggested food pack and decides to purchase it, the device sends this information to the server, which then confirms the order.

[1127] Specific examples

[1128] For example, suppose that data on ingredients purchased by User B has been accumulated. User B shops online on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and determines User B's preferences.

[1129] Next, the server analyzes production information and the market supply and demand balance to optimize the price of chicken and vegetables in real time. Once the price is determined, the generation AI proposes an optimized vegetable and chicken food pack to User B.

[1130] Furthermore, the device's emotion engine analyzes User B's facial expressions and tone of voice to understand their emotional state for that day. For example, if User B is feeling stressed, it can suggest ingredients and menu items that have a relaxing effect, making it possible to provide suggestions that are in tune with the user's emotions.

[1131] When User B views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User B can confirm the purchase with one click and receive fresh ingredients. This reduces food waste while providing ingredients that match User B's preferences and emotions.

[1132] As described above, this invention makes it possible to efficiently manage the process of fresh ingredients from production to consumption, and to realize personalized suggestions that are in tune with the user's emotions.

[1133] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1134] Step 1:

[1135] Collecting purchase history data and storing it in a database

[1136] The server periodically collects information about ingredients purchased by users on an online shopping site. It uses a REST API to collect the data and stores the acquired data in a database. Purchase history data, such as the user ID, purchase date and time, product name, quantity, and price, is provided as input. The server inserts this data into a "purchase history" table.

[1137] Specific behavior:

[1138] Every time a user buys an ingredient, the details are sent to the server via an API and added as a new record to the database using an SQL query.

[1139] Step 2:

[1140] Generating a preference profile

[1141] The server uses a machine learning algorithm to generate a preference profile for each user based on the collected purchase history data. This uses a clustering algorithm and collaborative filtering. The data in the "Purchase History" table is used as input, and the generated preference profile is saved as output in the "Preference Profile" table.

[1142] Specific behavior:

[1143] Run a Python script to cluster the data using the Scikit-learn library to identify patterns of user preferences, and store the results in a database.

[1144] Step 3:

[1145] Analysis of production and market consumption data

[1146] The server receives production data provided by producers and analyzes it together with market consumption data. The ETL tool is used to import the data and store it in a database. The CSV file from the producer is used as input, and a "production data" table and a "consumption data" table are created as output.

[1147] Specific behavior:

[1148] Data files from producers are periodically uploaded to the server and imported into the database through batch processing using an ETL tool (e.g., Apache NiFi).

[1149] Step 4:

[1150] Supply and demand balance analysis and price optimization

[1151] The server analyzes the supply and demand balance based on the collected production and consumption data. Time series analysis and linear regression models are used for price optimization. The "production data" and "consumption data" tables are used as input, and the optimized market price is saved as output in the "market price" table.

[1152] Specific behavior:

[1153] Run time series analysis scripts in Python or R to forecast supply and demand balance and optimize prices. Update the results to a "market price" table using SQL queries.

[1154] Step 5:

[1155] Emotion data collection and analysis

[1156] The device uses an emotion engine to collect emotional data such as the user's facial expressions, tone of voice, and text input. This emotional data is sent to the server in real time. Data from the camera, microphone, and keyboard is used as input, and the analyzed emotional data is stored in an "emotion data" table as output.

[1157] Specific behavior:

[1158] The device uses OpenCV and the Google Cloud Speech-to-Text API to analyze emotions in real time, and the analyzed data is sent to the server via a REST API.

[1159] Step 6:

[1160] Generate personalized food packs

[1161] The server uses the generative AI model to generate food packs based on the user's preference profile, emotional data, and supply-demand balance data. The "preference profile," "emotion data," and "market price" tables are used as input, and the generated food packs are saved in the "suggested pack" table as output.

[1162] Specific behavior:

[1163] Enter the following prompt into a generative AI model (e.g., GPT-3) and get a response: "Suggest the optimal ingredient pack based on the user's past purchasing history data and emotional data. For example, if the user is feeling stressed, include ingredients that will help them relax." Save this response in a "Suggested Pack" table.

[1164] Step 7:

[1165] Displaying the proposed content on the user's device

[1166] The terminal displays the personalized food pack suggestions received from the server to the user. The data in the "Suggested Packs" table is used as input. The output is reflected in the user interface.

[1167] Specific behavior:

[1168] The device retrieves data from the server via a REST API and displays it in a UI using React and Vue.js, for example, creating attractive visualizations of ingredient lists and pricing information.

[1169] Step 8:

[1170] Collecting user reaction data and continuously learning for new suggestions

[1171] The device records how the user reacts to the suggestions. This reaction data is sent to the server to help improve future suggestions. The input is the user's reaction, and the output is stored in a "reaction data" table.

[1172] Specific behavior:

[1173] It records whether the user accepts or rejects the suggestion and sends the result to the server via a REST API, which will be used as training data for future generative AI models.

[1174] (Application example 2)

[1175] 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."

[1176] In today's food distribution system, the process from production to consumption is complex, making it difficult for consumers to obtain fresh ingredients. Furthermore, there is a lack of personalized food packs that take into account consumers' preferences and emotions, resulting in a lower satisfaction level in the purchasing experience. Furthermore, there are issues such as increased food waste and difficulty in optimizing the supply and demand balance.

[1177] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchase histories and analyzing preferences, means for analyzing the market supply and demand balance and optimizing prices, means for proposing ingredient packs based on the generated preference profile, means for presenting the proposed ingredient packs to the user and supporting the purchase process, means for collecting emotional data from the user's facial expressions and tone of voice, means for analyzing the collected emotional data and reflecting it in the preference profile, and means for proposing personalized ingredient packs based on the emotional data. This makes it possible to propose ingredient packs that are optimally tailored to the consumer's emotional state and preferences, improving the purchasing experience and reducing food waste.

[1178] "Production information" refers to data related to the production of food ingredients such as agricultural and livestock products, and includes information such as production area, harvest time, quantity, and quality.

[1179] A "database" is a collection of data that is structured so that specific data can be efficiently managed, searched, and retrieved.

[1180] "Purchase history" is a record of products purchased by a user in the past, and includes information such as purchase date and time, product name, quantity, and price.

[1181] A "preference profile" is a collection of information about a user's individual preferences and tastes, obtained by analyzing the user's past purchasing history and behavioral data.

[1182] "Supply and demand balance" refers to the relationship between supply and demand in the market, which determines market trends and prices.

[1183] "Price optimization" is the process of efficiently determining sales prices based on information on the supply and demand balance, and is an adjustment that maximizes profits.

[1184] "Suggestion" refers to the act of recommending a particular product or service to a user, and in this case refers to presenting a personalized food pack to the user.

[1185] The "purchase procedure" refers to a series of operations and processes required to purchase the product selected by the user, including payment, delivery arrangements, etc.

[1186] "Emotion data" refers to data relating to individual emotional states obtained from the user's facial expressions, tone of voice, text input, and the like.

[1187] "Personalization" refers to the process of optimizing the content of a service or product to suit the preferences and characteristics of each individual user.

[1188] A "food pack" is a set of ingredients combined according to a specific recipe or menu.

[1189] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze user data and generate new suggestions or predictions.

[1190] A "prompt" is an instruction used when inputting data into a generative AI model, and is intended to clarify what kind of output is expected.

[1191] This invention realizes a system that collects user purchasing history and emotional data, and proposes and provides personalized food packs based on that data. This system is composed of a server and a user terminal.

[1192] Server processing overview

[1193] The server performs its processing using the following hardware and software:

[1194] Hardware: High-speed server

[1195] Software: Database Management Systems (DBMS), machine learning algorithms (e.g., TensorFlow, Scikit-learn), emotion recognition engines, generative AI models

[1196] 1. Collecting production information

[1197] The server collects agricultural and livestock production information from external data sources and stores it in a database. The collected data includes information on production area, harvest time, quantity, quality, etc.

[1198] 2. Collecting purchase history and analyzing preferences

[1199] The server collects the user's purchase history and analyzes their preferences based on that information. The analyzed data is stored in a database as a preference profile for each user.

[1200] 3. Analysis of market supply and demand balance and price optimization

[1201] The server analyzes market consumption patterns and production data. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. The optimized price information is stored in a database.

[1202] 4. Emotional Data Collection and Analysis

[1203] The server uses an emotion recognition engine to collect emotional data from the user's facial expressions, tone of voice, and text input, which is then sent to the server in real time for analysis.

[1204] 5. Generate personalized food pack suggestions

[1205] The server uses a generative AI model to generate food packs based on the user's preference profile, real-time emotional data, and supply-demand balance data. The generated food packs are optimized to the user's preferences and emotional state at the time.

[1206] Terminal processing overview

[1207] The device performs its processing using the following hardware and software:

[1208] Hardware: Smartphones, tablets, smart glasses

[1209] Software: User interface software, emotion recognition engine

[1210] 1. Providing a user interface

[1211] The device visually displays to the user a food pack recommendation based on the user's purchasing history, and the user can check the personalized food pack recommendation information on the device screen.

[1212] 2. Collecting Emotional Data

[1213] The device works in conjunction with an emotion recognition engine to collect emotional data in real time from the user's facial expressions, tone of voice, text input, etc. This emotional data is immediately sent to the server.

[1214] 3. Real-time price information

[1215] The terminal presents the user with real-time market price information received from the server, allowing the user to make a price-based purchasing decision.

[1216] 4. Purchase procedure support

[1217] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the information to the server, which then confirms the order.

[1218] Examples of concrete examples and prompts

[1219] As a concrete example, consider a case where a user is feeling stressed. In this case, the emotion recognition engine detects the stressed state and suggests a meal pack containing foods with a relaxing effect (e.g., herbal tea and nuts).

[1220] Example prompt sentence:

[1221] "If the user is currently feeling stressed, suggest a food pack containing foods that have a relaxing effect."

[1222] In this way, it becomes possible to propose the most suitable food pack that matches the consumer's emotional state and preferences, improving the purchasing experience and reducing food waste.

[1223] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1224] Step 1:

[1225] The server collects production information from external data sources and stores it in a database. The input includes production information data such as production area, harvest time, quantity, and quality. Data processing involves converting this information into a database format and saving it in the database. This allows the server to always have the latest production information. The output is an updated database.

[1226] Step 2:

[1227] The server collects user purchase history data. Input includes purchase history data such as purchase date and time, product name, quantity, and price. Data processing involves analyzing the user's preferences from this purchase history and creating a preference profile. As a specific example, the server analyzes past purchase frequency and patterns. The output is a preference profile for each user.

[1228] Step 3:

[1229] The server analyzes the market supply and demand balance. Inputs include production data and consumption pattern data. Data processing involves calculating the market supply and demand balance based on these data and optimizing real-time prices. Specifically, a machine learning algorithm is used to draw a supply and demand curve and calculate the optimal price. The output is optimized market price information.

[1230] Step 4:

[1231] The device collects emotional data from the user's facial expressions and tone of voice. Inputs include real-time data from the camera and microphone. Data processing involves analyzing this data using an emotion recognition engine to identify the user's emotional state. For example, emotions such as joy or sadness can be detected from the user's facial expressions. The output is the analyzed emotional data.

[1232] Step 5:

[1233] The server analyzes the collected emotional data and reflects it in the preference profile. The input includes emotional data and an existing preference profile. The data is processed by updating the preference profile according to the emotional state. Specifically, it takes into account the tendency of stressed users to prefer foods with a relaxing effect. The output is the updated preference profile.

[1234] Step 6:

[1235] The server uses a generative AI model to suggest a personalized food pack based on emotional data and a preference profile. The input includes emotional data, a preference profile, and optimized market price information. For data processing, the generative AI model is used to generate an optimal food pack. A specific prompt is used: "If the user is currently feeling stressed, please suggest a food pack that includes foods that have a relaxing effect." The output is a personalized food pack suggestion.

[1236] Step 7:

[1237] The terminal receives the suggested ingredient pack information from the server and visually displays it to the user. The input includes the personalized ingredient pack suggestion information. Specific operations include displaying ingredient pack contents and price information on the terminal screen. The output is the personalized ingredient pack information presented to the user.

[1238] Step 8:

[1239] The user checks the suggested food packs on the terminal and makes a decision to purchase. The input includes information about the suggested food packs. The specific action is to click the purchase button. The output is the user's purchase intention information.

[1240] Step 9:

[1241] The terminal transmits the user's purchase intention information to the server. The input includes the purchase intention information. Specifically, after the purchase is confirmed, the purchase information is transmitted to the server. The output is the purchase information received by the server.

[1242] Step 10:

[1243] The server processes the received purchase information and confirms the order. The input includes the user's purchase information. Specific operations include saving the order in a database and arranging for delivery. The output is the confirmed order information. As a result, the user can receive the specified food pack.

[1244] 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.

[1245] 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.

[1246] 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.

[1247] [Fourth embodiment]

[1248] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1249] 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.

[1250] 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).

[1251] 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.

[1252] 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.

[1253] 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).

[1254] 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.

[1255] 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.

[1256] 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.

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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."

[1261] This invention is a system that makes the process of fresh ingredients from production to consumption transparent and optimizes supply and demand and prices using AI technology. By directly connecting producers and consumers, this system reduces food waste and proposes food packs tailored to consumer preferences.

[1262] Server Processing

[1263] Collection and analysis of purchase history:

[1264] The server periodically collects user purchase history data and stores it in a database. Based on the collected data, machine learning algorithms are used to analyze user preferences and generate a preference profile for each user. This preference profile is then used to make personalized recommendations.

[1265] Supply and demand balance analysis and price optimization:

[1266] The server receives production data provided by producers and analyzes it along with market consumption patterns. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. This price information is stored in a database and provided to user devices.

[1267] Generate personalized food pack suggestions:

[1268] The server uses AI to generate food packs based on the user's preference profile and supply-demand balance data. The food packs are optimized for the user's past consumption patterns and preferences. The information on the suggested food packs is stored in a database and later provided to the user's device.

[1269] Terminal handling

[1270] Providing a user interface:

[1271] The terminal displays to the user a food pack suggestion based on the user's purchasing history. When the user accesses the terminal, the terminal retrieves the suggested personalized food pack information from the server and displays it to the user.

[1272] Real-time pricing information:

[1273] The terminal receives real-time price information from the server and presents it to the user, who can then make a purchasing decision based on it.

[1274] Purchase assistance:

[1275] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the purchase information to the server, which then confirms the order.

[1276] User Behavior

[1277] Providing purchase history:

[1278] The user purchases ingredients in the same way as with regular online shopping, and the information is sent to the server.

[1279] Check out our ingredient pack suggestions:

[1280] The user can then view the personalized food packs suggested to them through the device, determine whether the displayed contents match their tastes and whether the price is reasonable, and then decide whether to purchase.

[1281] Purchasing decision:

[1282] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the order is sent to the server.

[1283] Specific examples

[1284] For example, suppose that data on ingredients purchased by User A multiple times in the past is stored. User A goes online shopping on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and understands User A's preferences.

[1285] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User A.

[1286] When User A views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User A can confirm the purchase with one click and receive fresh ingredients. This process reduces food waste while providing ingredients tailored to User A's preferences.

[1287] The processing flow will be explained below.

[1288] Step 1:

[1289] The server collects the user's purchase history data, specifically, the ingredients and products the user has purchased in the past, as well as the dates and quantities associated with those purchases.

[1290] Step 2:

[1291] The server stores the collected purchase history data in a database, which stores purchasing pattern data for each user.

[1292] Step 3:

[1293] The server analyzes the accumulated purchase history data and uses machine learning algorithms to extract user preferences and trends and generate a preference profile that specifically identifies each user's tastes and consumption tendencies.

[1294] Step 4:

[1295] The server receives production information provided by producers and stores it in a database, including detailed data such as the type of crop or ingredient, harvest yield, and harvest time.

[1296] Step 5:

[1297] The server analyzes market consumption patterns and production information to determine the market supply and demand balance. Based on the supply and demand balance data, it runs an algorithm to optimize market prices in real time. The optimized price information is also stored in a database.

[1298] Step 6:

[1299] The server uses AI to generate food packs based on the user's preference profile and supply-demand balance data. The generated food packs are optimized for the user's past consumption patterns and preferences.

[1300] Step 7:

[1301] The terminal displays to the user a food pack suggestion based on the user's purchasing history. The terminal obtains the suggested personalized food pack information from the server and visually displays it to the user.

[1302] Step 8:

[1303] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[1304] Step 9:

[1305] The user reviews the personalized food pack displayed, decides whether the suggestions match their tastes and the price is reasonable, and if they decide to purchase, clicks the purchase button.

[1306] Step 10:

[1307] The terminal receives the user's intention to purchase and transmits the purchase information to the server.

[1308] Step 11:

[1309] The server confirms the order based on the received purchase information. After the order is confirmed, it notifies the producer of the order details.

[1310] Step 12:

[1311] The server stores the order details and delivery information in a database.

[1312] Step 13:

[1313] The producer prepares ingredients based on the order details notified by the server.

[1314] Step 14:

[1315] The producer will send the ingredients to the specified delivery address, and the user can receive the delivered ingredients and use the suggested ingredient pack.

[1316] These steps enable the entire system to optimize the process of fresh ingredients from production to consumption and reduce food waste.

[1317] Example 1

[1318] 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."

[1319] In the conventional food distribution system, there are many intermediaries between producers and consumers, which leads to problems such as supply-demand imbalances, price fluctuations, and food waste. There is also a lack of personalized proposals tailored to consumer preferences, resulting in low consumer satisfaction. To solve these issues, a system is needed that makes the entire process from production to consumption transparent and optimizes supply-demand and prices.

[1320] 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.

[1321] In this invention, the server includes a means for collecting production information and storing it in a database, a means for collecting user purchase history data and analyzing user preferences using a machine learning algorithm, and a means for analyzing the market supply and demand balance and optimizing prices in real time, thereby optimizing the supply and demand balance of ingredients and proposing ingredient packs that suit users' preferences.

[1322] "Production information" refers to various data provided by producers, such as harvest volume, quality, and supply forecasts for agricultural and livestock products.

[1323] "Database accumulation" refers to the process of storing collected information in a digital format and making it available for access and analysis.

[1324] "Purchase history" is detailed data such as the products a user has purchased in the past, the purchase date and time, the purchase amount, and the price.

[1325] A "machine learning algorithm" is a computational method for finding patterns and regularities in large amounts of data and making predictions and classifications.

[1326] "Analyzing preferences" means using machine learning algorithms to analyze what products a user prefers and create a profile of the user's unique preferences.

[1327] "Supply and demand balance" refers to the relationship between the amount of goods supplied and the amount of goods consumed in the market, which allows us to understand oversupply and shortages.

[1328] "Optimizing prices in real time" means instantly calculating product prices and setting optimal prices based on the current supply and demand balance and market conditions.

[1329] "Generative AI" is a computer program that uses artificial intelligence technology to automatically generate new data and suggestions based on specific input conditions.

[1330] A "food pack" is a set of ingredients selected to suit a particular user's preferences or market conditions.

[1331] A "user terminal" is a digital device that allows a user to view and manipulate information, and examples include personal computers and smartphones.

[1332] The "purchase procedure" is a series of operations and confirmation processes for purchasing the product selected by the user.

[1333] "Confirming an order" is the process by which the user's intention to purchase is finally recognized and the transaction is officially registered in the system.

[1334] MODE FOR CARRYING OUT THE INVENTION

[1335] This invention is a system that makes the process of fresh ingredients from production to consumption transparent and optimizes supply and demand and prices using AI technology. By directly connecting producers and consumers, this system reduces food waste and proposes food packs tailored to consumer preferences.

[1336] System Overview

[1337] This system consists of three main components: a server, a terminal, and a user. The specific roles of each component are as follows:

[1338] Server Roles

[1339] The server performs the following functions:

[1340] 1. Collecting production information and storing it in a database

[1341] The server collects production data provided by producers (e.g., harvest volume, quality, supply forecast, etc.) and stores it in a database using a database system such as MySQL or PostgreSQL.

[1342] 2. Collecting and analyzing user purchase history data

[1343] The server collects the user's purchase history data and analyzes the user's preferences using machine learning algorithms (e.g., TensorFlow or Scikit-learn). The analyzed preference profile is stored in a database.

[1344] 3. Supply and demand balance analysis and price optimization

[1345] The server combines consumption and production data provided by the market to analyze the supply and demand balance and optimize prices in real time, using time series analysis techniques such as the ARIMA model.

[1346] 4. Proposal generation of food packs

[1347] The server uses a generative AI model (e.g., GPT-3) to generate food packs based on the user's preference profile and supply-demand balance data.

[1348] Device Role

[1349] The terminal provides the user with the following features:

[1350] 1. Providing a user interface

[1351] The device displays personalized food pack suggestions to the user, using web application technologies such as React and Vue.js.

[1352] 2. Real-time price information

[1353] The terminal receives real-time price information from the server and presents it to the user, using technologies such as WebSocket and AJAX.

[1354] 3. Purchase procedure support

[1355] The terminal helps users purchase the suggested food packs with one click. The purchase information is sent to the server and the order is confirmed. HTTPS is used for secure communication.

[1356] User Roles

[1357] Users interact with the system as follows:

[1358] 1. Providing purchase history

[1359] The user purchases ingredients in the same way as with regular online shopping, and the purchase information is sent to the server.

[1360] 2. Check the food pack suggestions

[1361] The user checks the proposed personalized food pack through the terminal and decides whether to purchase it.

[1362] 3. Purchasing Decision

[1363] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the information is sent to the server.

[1364] Specific examples

[1365] For example, suppose that data on ingredients purchased by User A multiple times in the past is stored. User A goes online shopping on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and understands User A's preferences.

[1366] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User A.

[1367] When User A views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is right. User A can confirm the purchase with one click and receive fresh ingredients.

[1368] Prompt Sentence Examples

[1369] Below are some examples of specific prompts to input to a generative AI model:

[1370] Prompt: "Based on purchasing history data, please recommend a fresh food pack suitable for User A. Past purchases have always included fresh vegetables and chicken. Please also consider the supply-demand balance and market price when making your recommendation."

[1371] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1372] Step 1: Collect purchase history data

[1373] The server collects purchase history data every time a user makes an online purchase. Specifically, when a user adds an item to their shopping cart and clicks the "Purchase" button on the purchase confirmation screen, the details (purchase date and time, purchased item, purchase quantity, price, etc.) are sent to the database. The input is the user's purchase information, and the output is the purchase history data stored in the database.

[1374] Step 2: User preference analysis

[1375] The server analyzes user preferences based on the accumulated purchase history data. Specifically, it uses a machine learning algorithm (e.g., Scikit-learn's clustering method) to identify the specific ingredients that the user prefers. The input is the purchase history data collected in step 1, and the output is a preference profile for each user. The server stores the analysis results in a database.

[1376] Step 3: Collect and store production data

[1377] The server collects real-time production data provided by producers and stores it in a database. Specifically, producers send data from dedicated terminals to the server, which then stores it in the database. The input is production data from producers, and the output is production information stored in the database.

[1378] Step 4: Analyze the supply and demand balance

[1379] The server analyzes the supply and demand balance based on market consumption and production data. Specifically, it obtains market consumption and production data from the database and calculates the supply and demand balance using time series analysis and statistical methods (e.g., ARIMA model). The input is market consumption and production data, and the output is real-time supply and demand balance information.

[1380] Step 5: Price optimization

[1381] The server optimizes prices in real time based on supply and demand balance information. Specifically, it applies a pricing algorithm based on supply and demand balance information to calculate the optimal price. The input is real-time supply and demand balance information, and the output is optimized price information. The server stores this price information in a database.

[1382] Step 6: Generate ingredient pack suggestions

[1383] The server uses a generative AI model to generate a food pack based on the user's preference profile and supply-demand balance data. Specifically, it generates a prompt sentence using the preference profile and supply-demand balance data as input, and inputs it into the generative AI model. The generated food pack suggestions are saved in a database. The input is the preference profile and supply-demand balance data, and the output is the suggested food pack.

[1384] Prompt: "Based on purchasing history data, please recommend a fresh food pack suitable for User A. Past purchases have always included fresh vegetables and chicken. Please also consider the supply-demand balance and market price when making your recommendation."

[1385] Step 7: Providing a User Interface

[1386] The terminal displays the personalized food pack suggested to the user. Specifically, the terminal obtains the suggested information from the server and displays it on the screen. The user checks it and decides whether to purchase it or not, if necessary. The input is the suggested information obtained from the server, and the output is the food pack suggestion displayed on the terminal.

[1387] Step 8: Support with checkout

[1388] The terminal allows the user to purchase the selected food pack with one click. Specifically, when the user clicks the purchase button, the purchase information is sent to the server. The input is the user's purchase intention, and the output is the purchase information sent to the server.

[1389] Step 9: Confirm your order and update your data

[1390] The server confirms the order based on the transmitted purchase information and updates the database. Specifically, it records the order information in the database and updates inventory information and the user's purchase history data. The input is the user's purchase information, and the output is the updated information recorded in the database.

[1391] (Application example 1)

[1392] 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."

[1393] Modern food delivery services face challenges such as food waste, a lack of transparency in the supply chain, and a lack of methods for providing products that meet consumer preferences. They also face difficulties in effectively utilizing user purchasing data to optimize the supply-demand balance. This makes it difficult to provide ingredients at the best price for consumers, and there is a lack of an effective system for realizing personalized recommendations.

[1394] 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.

[1395] In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchase histories and analyzing preferences, means for analyzing the market supply-demand balance and optimizing prices, means for proposing food packs based on the generated preference profile, means for presenting the proposed food packs to the user and supporting the purchase process, and means for providing an application to be installed on a smartphone and displaying proposals and price information in real time, thereby making it possible to provide personalized food packs based on the user's preferences at optimal prices.

[1396] "Production information" refers to data provided by food producers regarding the yield, quality, and supply period of crops and products.

[1397] "Means of storing in a database" refers to systems or software for efficiently storing collected production information and purchase history information.

[1398] "Purchase history" refers to detailed information about products a user has purchased in the past, such as the purchase date and time, quantity, and price.

[1399] "Means for analyzing preferences" refers to algorithms and machine learning models that analyze users' preferences and purchasing patterns based on their purchase history.

[1400] "Supply and demand balance" refers to the state of supply and demand for a particular product or ingredient in the market.

[1401] "Price optimization tools" are algorithms or models that calculate the optimal selling price for ingredients or products based on the market supply and demand balance.

[1402] A "preference profile" is a collection of data that shows each user's preferences and purchasing patterns.

[1403] A "food pack" is a package of multiple ingredients suggested based on the user's preference profile.

[1404] "Means to support the purchasing process" refers to a system or interface that allows users to easily purchase the suggested food packs.

[1405] The "application installed on a smartphone" is software that runs on a smartphone and provides users with personalized food pack suggestions and price information.

[1406] "Means for displaying in real time" refers to an interface that has the function of instantly displaying to the user the latest offers and price information provided by the server.

[1407] A "user terminal" is a device used by an end user, such as a smartphone or tablet.

[1408] "One-click order confirmation" refers to a function or system that allows users to complete the purchase process with a single click.

[1409]

[1410] This invention is a system that makes the process from food production to consumption transparent and optimizes supply and demand and prices using AI technology. A specific example is shown below.

[1411] The server first collects production information provided by producers and stores it in a database. This production information includes information such as the yield, quality, and supply period of crops and products. Next, it periodically collects users' purchase histories and uses machine learning algorithms to analyze their preferences and generate a preference profile. The server then analyzes the market supply and demand balance and optimizes market prices in real time based on this analysis. This information is stored in the database and provided to users via an application installed on their smartphones.

[1412] The server uses a generative AI model to generate a food pack based on the user's preference profile and supply-demand balance data. This food pack is optimized based on the user's past consumption patterns and preferences. The device retrieves the personalized food pack information suggested by the server and presents it to the user in real time. Real-time price information from the server is also presented to the user through the device. The user can make a purchasing decision based on this information.

[1413] Once the user confirms the food pack suggestions and decides to purchase, the device sends the purchase information to the server, which then confirms the order. Furthermore, the system is designed to allow users to complete the purchase process with just one click, making it extremely convenient for users.

[1414] As an example, consider a case where data on ingredients purchased multiple times by a user has been accumulated. For example, if a user purchases fresh vegetables and domestically produced chicken online on Monday, the server analyzes this data to understand the user's preferences. The server analyzes agricultural production information and the market supply and demand balance to optimize the price of chicken and vegetables in real time. The generative AI model proposes an optimized vegetable and chicken ingredient pack for the user. When the user checks the proposed pack on their home device, they determine that it contains their favorite vegetables and chicken and is reasonably priced. The user can confirm the purchase with one click and receive fresh ingredients. This process makes it possible to provide ingredients tailored to the user's preferences while reducing food waste.

[1415] Example prompt sentence:

[1416] "Design a system that analyzes user preferences based on their purchasing history and suggests food packs that optimize the supply-demand balance. For example, for a user who purchases a lot of fresh tomatoes and domestic chicken, suggest a set of fresh tomatoes and chicken at the optimal price."

[1417] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1418] Step 1:

[1419] The server collects production information provided by producers and stores it in a database. The input is production data from producers, which includes detailed information on crops and products, such as yield, quality, and supply timing. The server efficiently stores this data in a database for future analysis.

[1420] Step 2:

[1421] The server periodically collects users' purchase history and analyzes their preferences using a machine learning algorithm. The input is the user's purchase history data, and the output is the user's preference profile. The server analyzes this data to understand each user's preferences and generate an individual preference profile.

[1422] Step 3:

[1423] The server analyzes the market supply and demand balance and optimizes prices. The input is market supply and demand data and supply data from producers, and the output is the optimized price of ingredients. The server analyzes this data and optimizes market prices in real time.

[1424] Step 4:

[1425] The server uses a generative AI model to generate food packs based on the user's preference profile and supply-demand balance data. The input is the preference profile and supply-demand balance data, and the output is a personalized food pack proposal. The server integrates this data and generates a food pack optimized for the user.

[1426] Step 5:

[1427] The terminal obtains personalized food pack information suggested by the server and presents it to the user. The input is food pack suggestion data from the server, and the output is food pack information displayed on the user's terminal screen. The terminal displays the suggestions to the user in real time and prompts for confirmation.

[1428] Step 6:

[1429] The terminal presents real-time price information from the server to the user. The input is price information from the server, and the output is an optimized price displayed on the user's terminal screen. The user makes a purchasing decision based on this information.

[1430] Step 7:

[1431] The user checks the food pack suggestions and decides to purchase. The input is the food pack information and price information displayed on the terminal, and the output is the user's intention to purchase. When the user decides to purchase, the terminal sends the purchase information to the server.

[1432] Step 8:

[1433] The server receives the user's purchase intention and confirms the order. The input is the user's purchase information, and the output is the confirmed order data. Based on this, the server carries out the appropriate delivery procedures.

[1434] Step 9:

[1435] The terminal supports one-click purchase procedures. The input is the user's purchase decision, and the output is the transmission of purchase information to the server. The purchase procedure is completed when the user confirms the purchase with one click on the terminal.

[1436] 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.

[1437] This invention combines a system that makes the process of fresh ingredients from production to consumption transparent, optimizes supply and demand and prices using AI technology, and an emotion engine that recognizes user emotions. By directly connecting producers and consumers, this system can reduce food waste and suggest food packs that suit consumers' preferences.

[1438] Server Processing

[1439] Collection and analysis of purchase history:

[1440] The server periodically collects user purchase history data and stores it in a database. Based on the collected data, machine learning algorithms are used to analyze user preferences and generate a preference profile for each user. This preference profile is then used to make personalized recommendations.

[1441] Supply and demand balance analysis and price optimization:

[1442] The server receives production data provided by producers and analyzes it along with market consumption patterns. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. This price information is stored in a database and provided to user devices.

[1443] Introducing the Emotion Engine:

[1444] The emotion engine collects user emotional data and uses it to generate a preference profile. Specifically, the emotion engine analyzes emotions from the user's facial expressions, tone of voice, text input, etc. to understand the user's state of mind. This emotional data is added to the preference profile and helps make more accurate suggestions.

[1445] Generate personalized food pack suggestions:

[1446] The server uses generative AI to generate food packs based on the user's preference profile and supply-demand balance data. The food packs are optimized for the user's past consumption patterns, preferences, and even emotional data. The information on the suggested food packs is stored in a database and later provided to the user's device.

[1447] Terminal handling

[1448] Providing a user interface:

[1449] The terminal displays to the user food pack suggestions based on the user's purchasing history. The terminal obtains the suggested personalized food pack information from the server and visually displays it to the user.

[1450] Emotion data collection:

[1451] The device works in conjunction with an emotion engine to collect emotional data from the user's facial expressions, tone of voice, text input, etc. This emotional data is sent to the server in real time.

[1452] Real-time pricing information:

[1453] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[1454] Purchase assistance:

[1455] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the purchase information to the server, which then confirms the order.

[1456] User Behavior

[1457] Providing purchase history:

[1458] The user purchases ingredients in the same way as with regular online shopping, and the information is sent to the server.

[1459] Check out our ingredient pack suggestions:

[1460] The user can then view the personalized food packs suggested to them through the device, determine whether the displayed contents match their tastes and whether the price is reasonable, and then decide whether to purchase.

[1461] Purchasing decision:

[1462] The user clicks the purchase button for the suggested food pack on the terminal, and once the purchase is confirmed, the order is sent to the server.

[1463] Specific examples

[1464] For example, suppose that data on ingredients purchased by User B has been accumulated. User B shops online on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and determines User B's preferences.

[1465] Next, the server analyzes agricultural production information and the market supply and demand balance to optimize the prices of chicken and vegetables in real time. Once the prices are determined, the generation AI proposes an optimized vegetable and chicken food pack to User B.

[1466] Furthermore, the device's emotion engine analyzes User B's facial expressions and tone of voice to understand their emotional state for that day. For example, if User B is feeling stressed, it can suggest ingredients and menu items that have a relaxing effect, making it possible to provide suggestions that are in tune with the user's emotions.

[1467] When User B views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User B can confirm the purchase with one click and receive fresh ingredients. This process reduces food waste while providing ingredients that match User B's preferences and emotions.

[1468] The processing flow will be explained below.

[1469] Step 1:

[1470] The server collects the user's purchase history data, specifically, the ingredients and products the user has purchased in the past, as well as the dates and quantities associated with those purchases.

[1471] Step 2:

[1472] The server stores the collected purchase history data in a database, which stores purchasing pattern data for each user.

[1473] Step 3:

[1474] The server analyzes the accumulated purchase history data and uses machine learning algorithms to extract user preferences and trends and generate a preference profile that specifically identifies each user's tastes and consumption tendencies.

[1475] Step 4:

[1476] The server receives production information provided by producers and stores it in a database, including detailed data such as the type of crop or ingredient, harvest yield, and harvest time.

[1477] Step 5:

[1478] The server analyzes market consumption patterns and production information to determine the market supply and demand balance. Based on the supply and demand balance data, it runs an algorithm to optimize market prices in real time. The optimized price information is also stored in a database.

[1479] Step 6:

[1480] The device collects the user's emotional data, and the device's emotion engine analyzes the user's facial expressions, tone of voice, text input, etc. to understand the user's current emotional state.

[1481] Step 7:

[1482] The device transmits the collected user emotion data to the server in real time.

[1483] Step 8:

[1484] The server receives the user's emotional data and uses it to update the user's preference profile. Specifically, if the user is feeling stressed, the server will suggest foods that have a relaxing effect, and make recommendations based on the user's emotional state.

[1485] Step 9:

[1486] The server uses generative AI to generate food packs based on the user's preference profile, supply-demand balance data, and emotional data. This food pack is optimized based on the user's past consumption patterns, preferences, and emotional data.

[1487] Step 10:

[1488] The device displays food pack suggestions based on the user's purchasing history and emotional state. The device retrieves the suggested personalized food pack information from the server and visually displays it to the user.

[1489] Step 11:

[1490] The terminal receives real-time price information from the server and presents it to the user, who can then decide whether to purchase the product based on the price information.

[1491] Step 12:

[1492] The user reviews the personalized food pack displayed, decides whether the suggestions match their tastes and the price is reasonable, and if they decide to purchase, clicks the purchase button.

[1493] Step 13:

[1494] The terminal receives the user's intention to purchase and transmits the purchase information to the server.

[1495] Step 14:

[1496] The server confirms the order based on the received purchase information. After the order is confirmed, it notifies the producer of the order details.

[1497] Step 15:

[1498] The server stores the order details and delivery information in a database.

[1499] Step 16:

[1500] The producer prepares ingredients based on the order details notified by the server.

[1501] Step 17:

[1502] The producer will send the ingredients to the specified delivery address, and the user can receive the delivered ingredients and use the suggested ingredient pack.

[1503] Through these steps, the entire system optimizes the process of fresh ingredients from production to consumption, and reduces food waste by making suggestions that are in line with the user's emotions.

[1504] Example 2

[1505] 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."

[1506] In today's consumer market, there is a need to optimize the balance between supply and demand for ingredients and make personalized recommendations based on consumer preferences and emotions. However, conventional systems only analyze ingredient purchasing and production data, and do not fully utilize consumer emotional data to make recommendations, making it difficult to make recommendations that are tailored to individual consumer preferences and emotions. Furthermore, it is difficult to analyze the appropriate supply and demand balance, resulting in increased food waste.

[1507] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1508] In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchasing history and analyzing preferences, means for analyzing the market supply and demand balance and optimizing prices, means for collecting user emotional data and analyzing it to suggest food packs based on a preference profile, and means for presenting the suggested food packs to the user and supporting the purchase process.

[1509] This will enable more personalized suggestions based on consumer preferences and emotions, optimize the supply and demand balance in real time, and reduce food waste.

[1510] "Production information" refers to detailed data on crop and product production provided by producers.

[1511] A "database" is an information system for systematically storing, managing, and analyzing collected information.

[1512] A "purchase history" is a detailed record of the purchases a user has made in the past.

[1513] "Preferences" refers to the preferences and tendencies that a user has toward specific products or ingredients.

[1514] "Analyzing" means analyzing user behavior and patterns based on accumulated data.

[1515] "Supply and demand balance" refers to the equilibrium between the supply of goods and services offered and the demand of consumers.

[1516] "Price optimization" means setting the most appropriate price by taking into account the supply and demand balance in the market.

[1517] "Emotion data" is data that represents the user's emotional state, and includes facial expressions, tone of voice, text input, and the like.

[1518] A "preference profile" is detailed information about a user's preferences and consumption patterns that is generated based on analysis.

[1519] A "food pack" is a product package that combines multiple ingredients and is suggested based on the user's preferences and emotional data.

[1520] "Suggesting" means presenting the user with the best options or products based on the analysis results.

[1521] "Presenting" means that the system shows information to the user visually or audibly.

[1522] "Supporting the purchase procedure" means assisting the user with a series of operations when purchasing a suggested product.

[1523] This invention combines a system that makes the process of fresh ingredients from production to consumption transparent, optimizes supply and demand and prices using generative AI models, and an emotion engine that recognizes user emotions. By directly connecting producers and consumers, this system can reduce food waste and suggest food packs tailored to consumer preferences.

[1524] Hardware and Software Configuration

[1525] The servers are equipped with high-performance processors and use database management systems (e.g., MySQL or PostgreSQL) to analyze large amounts of data in real time. Additionally, machine learning algorithms are implemented using Python scripts and libraries such as TensorFlow or PyTorch. Advanced generative AI models, such as GPT-3, are also used.

[1526] The device refers to the smartphone, tablet, or PC operated by the user, and is equipped with an emotion engine. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice, and employs analysis tools such as OpenCV and Google Cloud Speech-to-Text API. The user interface is built using JavaScript frameworks such as React and Vue.js.

[1527] System processing overview

[1528] The server first collects production information provided by producers and stores it in a database. It also periodically collects users' purchase history and uses machine learning algorithms to generate a user preference profile, which includes details such as purchase date and time, item name, quantity, and price.

[1529] The server then analyzes production information and market consumption data to determine the supply and demand balance, optimizes market prices in real time based on this information, and stores the price information in a database.

[1530] The server also collects the user's emotional data. The emotion engine analyzes the user's facial expressions, tone of voice, and text input to understand the user's state of mind. This emotional data is added to the user's preference profile to improve the accuracy of suggestions.

[1531] The server uses generative AI to generate a food pack based on the user's preference profile, supply-demand balance data, and emotional data. This proposal is stored in a database and later provided to the user's device. Specifically, the following prompt sentence is input into the generative AI model:

[1532] "Recommend optimal food packs based on the user's past purchase history and emotional data. For example, if the user is feeling stressed, include ingredients that will help them relax."

[1533] The device displays personalized food pack suggestions retrieved from the server to the user, and the user interface provides information in a visually easy-to-understand format, allowing the user to easily understand the suggestions.

[1534] The device works in conjunction with an emotion engine to collect emotional data in real time from the user's facial expressions, tone of voice, text input, etc., and sends this data to the server. When the user checks the suggested food pack and decides to purchase it, the device sends this information to the server, which then confirms the order.

[1535] Specific examples

[1536] For example, suppose that data on ingredients purchased by User B has been accumulated. User B shops online on Mondays and always buys fresh vegetables and chicken. The server analyzes this data and determines User B's preferences.

[1537] Next, the server analyzes production information and the market supply and demand balance to optimize the price of chicken and vegetables in real time. Once the price is determined, the generation AI proposes an optimized vegetable and chicken food pack to User B.

[1538] Furthermore, the device's emotion engine analyzes User B's facial expressions and tone of voice to understand their emotional state for that day. For example, if User B is feeling stressed, it can suggest ingredients and menu items that have a relaxing effect, making it possible to provide suggestions that are in tune with the user's emotions.

[1539] When User B views the proposed pack on their home device, they can see that it contains their favorite vegetables and chicken, and that the price is reasonable. User B can confirm the purchase with one click and receive fresh ingredients. This reduces food waste while providing ingredients that match User B's preferences and emotions.

[1540] As described above, this invention makes it possible to efficiently manage the process of fresh ingredients from production to consumption, and to realize personalized suggestions that are in tune with the user's emotions.

[1541] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1542] Step 1:

[1543] Collecting purchase history data and storing it in a database

[1544] The server periodically collects information about ingredients purchased by users on an online shopping site. It uses a REST API to collect the data and stores the acquired data in a database. Purchase history data, such as the user ID, purchase date and time, product name, quantity, and price, is provided as input. The server inserts this data into a "purchase history" table.

[1545] Specific behavior:

[1546] Every time a user buys an ingredient, the details are sent to the server via an API and added as a new record to the database using an SQL query.

[1547] Step 2:

[1548] Generating a preference profile

[1549] The server uses a machine learning algorithm to generate a preference profile for each user based on the collected purchase history data. This uses a clustering algorithm and collaborative filtering. The data in the "Purchase History" table is used as input, and the generated preference profile is saved as output in the "Preference Profile" table.

[1550] Specific behavior:

[1551] Run a Python script to cluster the data using the Scikit-learn library to identify patterns of user preferences, and store the results in a database.

[1552] Step 3:

[1553] Analysis of production and market consumption data

[1554] The server receives production data provided by producers and analyzes it together with market consumption data. The ETL tool is used to import the data and store it in a database. The CSV file from the producer is used as input, and a "production data" table and a "consumption data" table are created as output.

[1555] Specific behavior:

[1556] Data files from producers are periodically uploaded to the server and imported into the database through batch processing using an ETL tool (e.g., Apache NiFi).

[1557] Step 4:

[1558] Supply and demand balance analysis and price optimization

[1559] The server analyzes the supply and demand balance based on the collected production and consumption data. Time series analysis and linear regression models are used for price optimization. The "production data" and "consumption data" tables are used as input, and the optimized market price is saved as output in the "market price" table.

[1560] Specific behavior:

[1561] Run time series analysis scripts in Python or R to forecast supply and demand balance and optimize prices. Update the results to a "market price" table using SQL queries.

[1562] Step 5:

[1563] Emotion data collection and analysis

[1564] The device uses an emotion engine to collect emotional data such as the user's facial expressions, tone of voice, and text input. This emotional data is sent to the server in real time. Data from the camera, microphone, and keyboard is used as input, and the analyzed emotional data is stored in an "emotion data" table as output.

[1565] Specific behavior:

[1566] The device uses OpenCV and the Google Cloud Speech-to-Text API to analyze emotions in real time, and the analyzed data is sent to the server via a REST API.

[1567] Step 6:

[1568] Generate personalized food packs

[1569] The server uses the generative AI model to generate food packs based on the user's preference profile, emotional data, and supply-demand balance data. The "preference profile," "emotion data," and "market price" tables are used as input, and the generated food packs are saved in the "suggested pack" table as output.

[1570] Specific behavior:

[1571] Enter the following prompt into a generative AI model (e.g., GPT-3) and get a response: "Suggest the optimal ingredient pack based on the user's past purchasing history data and emotional data. For example, if the user is feeling stressed, include ingredients that will help them relax." Save this response in a "Suggested Pack" table.

[1572] Step 7:

[1573] Displaying the proposed content on the user's device

[1574] The terminal displays the personalized food pack suggestions received from the server to the user. The data in the "Suggested Packs" table is used as input. The output is reflected in the user interface.

[1575] Specific behavior:

[1576] The device retrieves data from the server via a REST API and displays it in a UI using React and Vue.js, for example, creating attractive visualizations of ingredient lists and pricing information.

[1577] Step 8:

[1578] Collecting user reaction data and continuously learning for new suggestions

[1579] The device records how the user reacts to the suggestions. This reaction data is sent to the server to help improve future suggestions. The input is the user's reaction, and the output is stored in a "reaction data" table.

[1580] Specific behavior:

[1581] It records whether the user accepts or rejects the suggestion and sends the result to the server via a REST API, which will be used as training data for future generative AI models.

[1582] (Application example 2)

[1583] 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."

[1584] In today's food distribution system, the process from production to consumption is complex, making it difficult for consumers to obtain fresh ingredients. Furthermore, there is a lack of personalized food packs that take into account consumers' preferences and emotions, resulting in a lower satisfaction level in the purchasing experience. Furthermore, there are issues such as increased food waste and difficulty in optimizing the supply and demand balance.

[1585] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting production information and storing it in a database, means for collecting user purchase histories and analyzing preferences, means for analyzing the market supply and demand balance and optimizing prices, means for proposing ingredient packs based on the generated preference profile, means for presenting the proposed ingredient packs to the user and supporting the purchase process, means for collecting emotional data from the user's facial expressions and tone of voice, means for analyzing the collected emotional data and reflecting it in the preference profile, and means for proposing personalized ingredient packs based on the emotional data. This makes it possible to propose ingredient packs that are optimally tailored to the consumer's emotional state and preferences, improving the purchasing experience and reducing food waste.

[1586] "Production information" refers to data related to the production of food ingredients such as agricultural and livestock products, and includes information such as production area, harvest time, quantity, and quality.

[1587] A "database" is a collection of data that is structured so that specific data can be efficiently managed, searched, and retrieved.

[1588] "Purchase history" is a record of products purchased by a user in the past, and includes information such as purchase date and time, product name, quantity, and price.

[1589] A "preference profile" is a collection of information about a user's individual preferences and tastes, obtained by analyzing the user's past purchasing history and behavioral data.

[1590] "Supply and demand balance" refers to the relationship between supply and demand in the market, which determines market trends and prices.

[1591] "Price optimization" is the process of efficiently determining sales prices based on information on the supply and demand balance, and is an adjustment that maximizes profits.

[1592] "Suggestion" refers to the act of recommending a particular product or service to a user, and in this case refers to presenting a personalized food pack to the user.

[1593] The "purchase procedure" refers to a series of operations and processes required to purchase the product selected by the user, including payment, delivery arrangements, etc.

[1594] "Emotion data" refers to data relating to individual emotional states obtained from the user's facial expressions, tone of voice, text input, and the like.

[1595] "Personalization" refers to the process of optimizing the content of a service or product to suit the preferences and characteristics of each individual user.

[1596] A "food pack" is a set of ingredients combined according to a specific recipe or menu.

[1597] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze user data and generate new suggestions or predictions.

[1598] A "prompt" is an instruction used when inputting data into a generative AI model, and is intended to clarify what kind of output is expected.

[1599] This invention realizes a system that collects user purchasing history and emotional data, and proposes and provides personalized food packs based on that data. This system is composed of a server and a user terminal.

[1600] Server processing overview

[1601] The server performs its processing using the following hardware and software:

[1602] Hardware: High-speed server

[1603] Software: Database Management Systems (DBMS), machine learning algorithms (e.g., TensorFlow, Scikit-learn), emotion recognition engines, generative AI models

[1604] 1. Collecting production information

[1605] The server collects agricultural and livestock production information from external data sources and stores it in a database. The collected data includes information on production area, harvest time, quantity, quality, etc.

[1606] 2. Collecting purchase history and analyzing preferences

[1607] The server collects the user's purchase history and analyzes their preferences based on that information. The analyzed data is stored in a database as a preference profile for each user.

[1608] 3. Analysis of market supply and demand balance and price optimization

[1609] The server analyzes market consumption patterns and production data. Based on this analysis, the server grasps the supply and demand balance and optimizes market prices in real time. The optimized price information is stored in a database.

[1610] 4. Emotional Data Collection and Analysis

[1611] The server uses an emotion recognition engine to collect emotional data from the user's facial expressions, tone of voice, and text input, which is then sent to the server in real time for analysis.

[1612] 5. Generate personalized food pack suggestions

[1613] The server uses a generative AI model to generate food packs based on the user's preference profile, real-time emotional data, and supply-demand balance data. The generated food packs are optimized to the user's preferences and emotional state at the time.

[1614] Terminal processing overview

[1615] The device performs its processing using the following hardware and software:

[1616] Hardware: Smartphones, tablets, smart glasses

[1617] Software: User interface software, emotion recognition engine

[1618] 1. Providing a user interface

[1619] The device visually displays to the user a food pack recommendation based on the user's purchasing history, and the user can check the personalized food pack recommendation information on the device screen.

[1620] 2. Collecting Emotional Data

[1621] The device works in conjunction with an emotion recognition engine to collect emotional data in real time from the user's facial expressions, tone of voice, text input, etc. This emotional data is immediately sent to the server.

[1622] 3. Real-time price information

[1623] The terminal presents the user with real-time market price information received from the server, allowing the user to make a price-based purchasing decision.

[1624] 4. Purchase procedure support

[1625] The terminal allows the user to purchase the suggested food pack with one click. Once the user decides to purchase, the terminal sends the information to the server, which then confirms the order.

[1626] Examples of concrete examples and prompts

[1627] As a concrete example, consider a case where a user is feeling stressed. In this case, the emotion recognition engine detects the stressed state and suggests a meal pack containing foods with a relaxing effect (e.g., herbal tea and nuts).

[1628] Example prompt sentence:

[1629] "If the user is currently feeling stressed, suggest a food pack containing foods that have a relaxing effect."

[1630] In this way, it becomes possible to propose the most suitable food pack that matches the consumer's emotional state and preferences, improving the purchasing experience and reducing food waste.

[1631] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1632] Step 1:

[1633] The server collects production information from external data sources and stores it in a database. The input includes production information data such as production area, harvest time, quantity, and quality. Data processing involves converting this information into a database format and saving it in the database. This allows the server to always have the latest production information. The output is an updated database.

[1634] Step 2:

[1635] The server collects user purchase history data. Input includes purchase history data such as purchase date and time, product name, quantity, and price. Data processing involves analyzing the user's preferences from this purchase history and creating a preference profile. As a specific example, the server analyzes past purchase frequency and patterns. The output is a preference profile for each user.

[1636] Step 3:

[1637] The server analyzes the market supply and demand balance. Inputs include production data and consumption pattern data. Data processing involves calculating the market supply and demand balance based on these data and optimizing real-time prices. Specifically, a machine learning algorithm is used to draw a supply and demand curve and calculate the optimal price. The output is optimized market price information.

[1638] Step 4:

[1639] The device collects emotional data from the user's facial expressions and tone of voice. Inputs include real-time data from the camera and microphone. Data processing involves analyzing this data using an emotion recognition engine to identify the user's emotional state. For example, emotions such as joy or sadness can be detected from the user's facial expressions. The output is the analyzed emotional data.

[1640] Step 5:

[1641] The server analyzes the collected emotional data and reflects it in the preference profile. The input includes emotional data and an existing preference profile. The data is processed by updating the preference profile according to the emotional state. Specifically, it takes into account the tendency of stressed users to prefer foods with a relaxing effect. The output is the updated preference profile.

[1642] Step 6:

[1643] The server uses a generative AI model to suggest a personalized food pack based on emotional data and a preference profile. The input includes emotional data, a preference profile, and optimized market price information. For data processing, the generative AI model is used to generate an optimal food pack. A specific prompt is used: "If the user is currently feeling stressed, please suggest a food pack that includes foods that have a relaxing effect." The output is a personalized food pack suggestion.

[1644] Step 7:

[1645] The terminal receives the suggested ingredient pack information from the server and visually displays it to the user. The input includes the personalized ingredient pack suggestion information. Specific operations include displaying ingredient pack contents and price information on the terminal screen. The output is the personalized ingredient pack information presented to the user.

[1646] Step 8:

[1647] The user checks the suggested food packs on the terminal and makes a decision to purchase. The input includes information about the suggested food packs. The specific action is to click the purchase button. The output is the user's purchase intention information.

[1648] Step 9:

[1649] The terminal transmits the user's purchase intention information to the server. The input includes the purchase intention information. Specifically, after the purchase is confirmed, the purchase information is transmitted to the server. The output is the purchase information received by the server.

[1650] Step 10:

[1651] The server processes the received purchase information and confirms the order. The input includes the user's purchase information. Specific operations include saving the order in a database and arranging for delivery. The output is the confirmed order information. As a result, the user can receive the specified food pack.

[1652] 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.

[1653] 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.

[1654] 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.

[1655] 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.

[1656] FIG. 9 illustrates 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 behaviors 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.

[1657] 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.

[1658] 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).

[1659] 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.

[1660] 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."

[1661] 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.

[1662] 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).

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] 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.

[1668] 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.

[1669] 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.

[1670] 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.

[1671] 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 t...

Claims

1. A means for collecting production information and storing it in a database; A means for collecting user purchase history and analyzing preferences; Analyzing the market supply and demand balance and optimizing prices; a means for suggesting food packs based on the generated preference profile; a means for presenting the suggested food pack to the user and assisting the user in the purchase process; A system including:

2. The system of claim 1 further comprising means for generating ingredient packs based on the generated preference profile.

3. The system of claim 1 further comprising means for receiving a user's purchase intent and confirming the order.

Images