system

Abstract

We provide the system. [Solution] A means of using AI to diagnose the data and demand for items listed on a flea market application, A means for users to input detailed information such as the product name, size, and color of the item they are listing, The means of providing users with the optimal listing time, price, and quantity based on the analysis results of the generating AI, A method for collecting the results of actual user listings and using them as training data for generating AI, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a free market application, in order for a user to effectively buy and sell goods, it is necessary to grasp at which time period, at which price, and which goods have high demand. However, at present, the means for users to know this information are limited, and it is difficult to find the optimal timing and price for buying and selling. In addition, since there is no mechanism to utilize past trading data for the next listing or purchase, users cannot conduct transactions efficiently. As a result, problems such as unsold listed goods or inability to find desired goods have occurred. Solving such problems and providing effective trading support for users is an object of the present invention.

Means for Solving the Problems

[0005] This invention provides a system that uses AI to analyze data and demand generated from items listed on a flea market application, enabling users to buy and sell efficiently. Specifically, it provides the following means:

[0006] 1. A means of collecting listing data and demand data from a flea market application, and having a generating AI diagnose it.

[0007] 2. A means for users to input detailed information such as the product name, size, and color of the item they are listing.

[0008] 3. A means of presenting users with the optimal listing time, price, and quantity based on the analysis results of the generating AI.

[0009] 4. A means of collecting the results of actual user listings and using them as training data for generating AI.

[0010] This allows users to list and purchase products at the most effective time and at a fair price, improving overall transaction efficiency.

[0011] A "flea market application" is an application that allows users to list and purchase goods online.

[0012] "Generative AI" refers to artificial intelligence that performs predictive analysis of supply and demand based on collected data.

[0013] "Listing data" refers to information about products listed by users in a flea market application, including product name, price, category, and listing time.

[0014] "Demand data" refers to data based on the search behavior and purchase history of potential buyers in a flea market application.

[0015] "Diagnosis" is the act of analyzing data using generative AI to predict the relationship between supply and demand.

[0016] "User" refers to an individual or a corporation that uses a free market application to list or purchase goods.

[0017] "Optimal listing time" refers to the time period when the sales of a product are predicted to be the best.

[0018] "Optimal price" refers to the price range set to maximize the sales and profit of a product.

[0019] "Detailed information" refers to the specific information provided about the product listed by the user, including the product name, size, color, etc.

[0020] "Learning data" refers to the past data used by the generative AI to improve the accuracy of predictive analysis.

Brief Description of Drawings

[0021] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9]This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0022] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0023] First, let's explain the terminology used in the following explanation.

[0024] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0025] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0026] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0027] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0029] [First Embodiment]

[0030] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0031] As shown in Figure 1, the 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.

[0032] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0034] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0035] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0037] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0041] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0042] This invention is a system that uses AI to analyze listing data and demand data in a flea market application, enabling users to buy and sell efficiently. Specific embodiments of this system are described below.

[0043] The server works with the provider of the flea market application to collect listing and purchase data via API. This collected data includes product name, price, category, listing time, and purchase time.

[0044] The server converts the collected data into a format for storage in a centralized database. This format is used for listing data and demand data, and missing or outlier values ​​are added or removed.

[0045] Next, the server uses generative AI to analyze this data. The generative AI analyzes past sales history and demand trends to predict demand for specific products. For example, the generative AI analyzes "black T-shirts" and predicts the seasons when demand will be highest and the optimal price range.

[0046] Users access the system using a device (e.g., a smartphone or computer) through a dedicated app or web portal. Users enter detailed information about the items they intend to list (product name, size, color, etc.). This information is sent to the server, which, based on the analysis results of the generated AI, suggests the optimal listing time, appropriate price, and appropriate quantity to the user.

[0047] For example, if a user tries to list a "black T-shirt," the system might suggest that "listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate." Furthermore, the user's sales performance based on these suggestions is then fed back to the server.

[0048] The server uses this feedback data as training data for the generating AI. For example, if a user lists an item at a fair price and it sells quickly, that performance data is input back into the generating AI, improving the accuracy of the next predictive analysis.

[0049] This system allows users to understand the best time to sell and the appropriate price, enabling them to buy and sell products efficiently. As a result, it is expected that the overall efficiency of the flea market application will improve, and user satisfaction will increase.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The server works with the provider of the flea market application to collect listing and purchase data via API. Specifically, it calls the API daily or at regular intervals to retrieve data such as product name, price, category, listing time, and purchase time.

[0053] Step 2:

[0054] The server converts the collected data into a format for storage in a centralized database. For example, it parses data received in JSON format to match the table structure of the relational database and maps it to fields such as listing date, product name, and price.

[0055] Step 3:

[0056] The server uses a generative AI to analyze this data. The server extracts historical listing and purchase data from the database and inputs it into the generative AI. The generative AI creates a demand forecasting model based on the historical data and analyzes the demand trends for each product.

[0057] Step 4:

[0058] Users access a dedicated app or web portal using their device and enter detailed information about the items they want to list. For example, if a user wants to list a "black T-shirt," they would enter the product name, category, size, color, and desired price.

[0059] Step 5:

[0060] The terminal sends the product information entered by the user to the server. Specifically, it submits an input form and includes the product information in the payload of an HTTP request, which is then sent to the server.

[0061] Step 6:

[0062] The server receives product information submitted by the user and searches for the results of the generated AI analysis based on that information. For example, it retrieves the latest demand forecast data for "black T-shirts" from the cache.

[0063] Step 7:

[0064] The server calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI, and formats it into a report. For example, it might conclude that "listing black T-shirts on Saturday evenings is most effective, and the appropriate price is between 2,000 and 2,500 yen."

[0065] Step 8:

[0066] The device displays the analysis results generated by the AI, received from the server, to the user. The user then checks the optimal listing timing and appropriate pricing suggestions on the app or web portal screen.

[0067] Step 9:

[0068] Users list items based on the server's suggestions. Once a user lists an item, they provide feedback to the server about the result (whether it sold, when it sold, and at what price).

[0069] Step 10:

[0070] The server collects feedback data as training data for the generating AI and uses it to improve the accuracy of future predictive analyses. The collected feedback data is stored in the "Sales Data" table and used to retrain the generating AI.

[0071] This series of processing steps provides users with optimal information for effectively buying and selling goods, improving the overall efficiency of the flea market application.

[0072] (Example 1)

[0073] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0074] Traditional flea market applications made it difficult for users to determine the optimal timing for listing items and fair pricing, hindering efficient buying and selling. Furthermore, they lacked a system for efficiently analyzing listing and demand data and providing rapid feedback to users. As a result, the efficiency of transactions decreased, leading to low user satisfaction.

[0075] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0076] In this invention, the server includes means for diagnosing data and demand for items listed on a flea market application using a generating AI model, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI model, means for collecting the results of items actually listed by the user and using them as training data for the generating AI model, and means for data formatting to impute missing values ​​and remove outliers. As a result, users can understand the best time to sell and the appropriate price, enabling them to buy and sell goods efficiently.

[0077] A "flea market application" is an online marketplace that provides a platform where users can list items for sale and buyers can purchase those items.

[0078] A "generative AI model" is an artificial intelligence algorithm that analyzes trends and patterns based on collected data to make predictions and suggestions.

[0079] "Listing data" refers to information that users provide when listing items on a flea market application, such as product name, size, color, price, and listing time.

[0080] "Demand data" refers to information that indicates the demand for a product, such as a buyer's purchase history, purchase time, and purchase frequency.

[0081] A "server" is a computer system that collects, manages, and analyzes data from a flea market application and provides the necessary information to users.

[0082] "Data formatting means" refers to functions that process collected data to impart missing values, remove outliers, and convert it into a format suitable for analysis.

[0083] "Analysis results" refer to suggested information such as listing timing, appropriate price, and optimal quantity, obtained as a result of data diagnosis by a generated AI model.

[0084] "Training data" refers to past sales performance and feedback data that the generating AI model uses to improve its accuracy.

[0085] This invention is a system that uses an AI model to analyze listing data and demand data in a flea market application, enabling users to buy and sell efficiently. Specific embodiments of this system are described below.

[0086] The server works with the provider of the flea market application to collect listing and purchase data via API. This collected data includes product name, price, category, listing time, and purchase time. The server retrieves this data using HTTP requests.

[0087] Next, the server converts the collected data into a format for storage in a centralized database. This format is adapted to the listing data and demand data, and missing or outlier values ​​are imputed or removed. The Python Pandas library can be used for this purpose. The data is then converted to CSV or SQL format for storage in the database.

[0088] The server then uses generative AI (e.g., OpenAI's GPT-4 model) to analyze this data. The generative AI analyzes past sales history and demand trends to forecast demand for specific products. Specifically, based on data such as product name, price, and category, the generative AI predicts the season and optimal price range for "black T-shirts" when demand will be high.

[0089] Users access the system using their own devices (smartphones or computers) through a dedicated app or web portal. Users enter detailed information about the products they intend to list (product name, size, color, etc.). This entered information is sent to the server.

[0090] The server receives information sent by the user and, based on the analysis results of the generating AI, suggests the optimal listing time, price, and quantity to the user. For example, if a user tries to list a "black T-shirt," the system suggests that "listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate."

[0091] When a user lists an item based on a suggested product, its sales performance is fed back to the server. The server uses this feedback data as training data for its generating AI model to improve the accuracy of future predictive analyses. For example, if a user lists an item at a reasonable price and it sells quickly, that sales data is input back into the generating AI, improving the model's prediction accuracy.

[0092] This system allows users to understand the best time to sell and the appropriate price, enabling them to buy and sell products efficiently. As a result, it is expected that the overall efficiency of the flea market application will improve, and user satisfaction will increase.

[0093] Examples of prompt statements include:

[0094] "I'm planning to list a black, size L T-shirt for sale. Could you tell me the most popular time slots and the best price to set?"

[0095] In this way, the system uses a generated AI model to analyze listing data and demand data, and provides users with the optimal listing strategy. This enables users to buy and sell efficiently.

[0096] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0097] Step 1:

[0098] The server collects listing and purchase data through the flea market application's API. Specifically, the server sends an HTTP request and receives JSON data as a response. The input is the flea market application's API endpoint, and the output is a dataset containing information such as product name, price, category, listing time, and purchase time.

[0099] Step 2:

[0100] The server converts the collected data into a format suitable for storage in a centralized database. Specifically, the server uses the Python Pandas library to read the data and impute and remove missing and outlier values. The input is the data collected in step 1, and the output is the formatted data with missing and outlier values ​​imputed and removed.

[0101] Step 3:

[0102] The server uses a generative AI model to analyze the formatted data. Specifically, the server inputs the formatted data into a generative AI model (e.g., GPT-4), and the model performs trend analysis and demand forecasting. The input is the formatted data, and the output is the analysis results, such as demand forecasts for each product, optimal listing timing, and price range.

[0103] Step 4:

[0104] Users access the system using their devices via a dedicated app or web portal. Specifically, users input detailed information such as product name, size, and color. The input is the user's product details, and the output is a processing request to the server.

[0105] Step 5:

[0106] The server receives information sent by the user and, based on the analysis results of the generating AI model, presents the user with the optimal listing time, price, and quantity. Specifically, the server refers to the analysis results of the generating AI model and uses them to provide the user with an appropriate listing strategy. The input is detailed information provided by the user and the analysis results of the generating AI model, and the output is suggested information for the user (optimal listing time, price, and quantity).

[0107] Step 6:

[0108] Users list products based on the suggestions provided and receive sales results. Specifically, users list products according to the system's suggestions, and when a product sells, the result is sent to the server. The inputs are the server's suggestion information and the user's actions, and the output is sales result data.

[0109] Step 7:

[0110] The server uses sales results data as training data for a generative AI model to improve the model's prediction accuracy. Specifically, the server collects sales results data and uses it to retrain the generative AI model. The input is sales results data, and the output is an improved generative AI model and increased prediction accuracy.

[0111] Through the steps outlined above, users can obtain the optimal listing strategy, and it is expected that the overall buying and selling efficiency of the flea market application will improve.

[0112] (Application Example 1)

[0113] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0114] Modern flea market applications and e-commerce sites face the problem of users having difficulty obtaining the right information to efficiently buy and sell goods. In particular, the lack of means to predict the optimal listing time, price, and quantity of items to sell often leads to users missing out on opportunities and losses. Furthermore, the inefficiency of the user interface and the lack of accurate demand forecasting contribute to a decrease in overall sales efficiency.

[0115] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0116] In this invention, the server includes means for using a generating AI to diagnose data and demand for items listed on a flea market application, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI, means for collecting the results of items actually listed by the user and using them as training data for the generating AI, and means for providing a user interface via a smartphone application for collecting and analyzing data on an e-commerce site and proposing the optimal sales strategy. This enables users to list items at the most effective time and price, and to buy and sell items quickly and efficiently.

[0117] Definition of Terms

[0118] A "flea market application" is an online platform where users can freely list items for sale and buyers can conduct transactions directly with them.

[0119] "Generative AI" refers to a system that uses machine learning models and artificial intelligence to analyze data and generate information.

[0120] "Product name" refers to the identifying name of the product being offered for sale, and is the name that users use to identify the product.

[0121] "Size" refers to information that indicates the specific dimensions or scale of a product.

[0122] "Color" refers to information that indicates the colors a product possesses.

[0123] "Detailed information" refers to specific and detailed data about the product, including product name, size, color, etc.

[0124] "Analysis results" refer to the information obtained after the generating AI analyzes the listing data and demand data.

[0125] "Optimal listing time" refers to the most effective timing for listing an item.

[0126] "Price" refers to the amount a user sets when listing an item for sale.

[0127] "Quantity" refers to the number of items a user lists for sale.

[0128] "Collection" refers to the process of gathering information and data after a user has listed an item for sale.

[0129] "Training data" refers to a collection of historical data that a generative AI uses to improve its performance.

[0130] An "online shopping site" is an online platform for selling products over the internet.

[0131] "User interface" refers to the screens and means of operation that users use to interact with a system.

[0132] A "smartphone application" is a software program that runs on a smartphone.

[0133] "Data collection" is the process of gathering data from specific sources.

[0134] "Analysis" is the process of examining collected data and deriving useful information.

[0135] A "sales strategy" is a plan or method for effectively selling a product.

[0136] Modes for carrying out the invention

[0137] This invention relates to a system for users to efficiently buy and sell goods in flea market applications and online shopping sites. Specific embodiments thereof are described below.

[0138] (Overall system configuration)

[0139] The system primarily consists of a server and user terminals. The server analyzes data using a generative AI model, while the user terminals operate as smartphone applications. The following details each component of the system and its function.

[0140] Hardware to use

[0141] Server: Performs data collection, database management, and execution of generated AI models.

[0142] User device: Smartphone (device capable of running smartphone applications).

[0143] Software to use

[0144] Django is a Python®-based web framework used for API servers and data transformation / correction.

[0145] SQLite: A database management system used to centrally manage collected data.

[0146] TENSORFLOW® is a machine learning library used to build and run generative AI models.

[0147] Flutter®: A smartphone application development framework used to build user interfaces.

[0148] Data flow and processing

[0149] 1. Data acquisition and format conversion

[0150] The server collects listing and purchase data through APIs for e-commerce sites and flea market applications. This includes information such as product name, price, category, listing time, and purchase time. The collected data is formatted using Django and stored in an SQLite database. Missing or outlier data are imputed or removed at this stage.

[0151] 2. Data analysis using generated AI

[0152] The server uses TensorFlow to build a generative AI model based on data stored in an SQLite database. This generative AI model analyzes past sales history and demand trend data to predict demand for a specific product. This prediction includes the optimal listing time, price, and quantity.

[0153] 3. Proposals based on user interface

[0154] Users enter product information (product name, size, color, etc.) for items they intend to list using a smartphone application built with Flutter. The entered information is sent to a server, and based on the analysis results of a generated AI model, the optimal listing time, price, and quantity are presented to the user.

[0155] 4. Collecting and generating feedback data for AI training

[0156] Based on the suggestions provided by the user, products are listed for sale, and as a result, sales performance data is fed back to the server. This feedback data is used as training data for the generating AI model, improving the accuracy of future predictive analyses.

[0157] Specific example

[0158] When a user uses a smartphone application to list old books for sale, they enter the book's information (title, author, condition, price) into the application. This information is sent to the server, where a generating AI calculates the optimal listing time (e.g., weekday evenings), appropriate price (around 2000 yen), and recommended quantity (depending on inventory) and suggests them to the user. When the user lists the item based on the suggestion, the sales performance is used to train the generating AI.

[0159] Examples of prompts to input into a generative AI model

[0160] The user enters the product data they plan to list in the following format:

[0161] Product name: Book name

[0162] Category: Books, Magazines

[0163] Price: 2000 yen

[0164] Listing timing: Weekday evenings

[0165] Based on this data, please analyze past purchase data from the e-commerce site and use AI to propose the optimal listing timing, appropriate price, and recommended quantity.

[0166] This allows users to list their products at the most effective time and price, enabling efficient buying and selling.

[0167] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0168] Program processing steps

[0169] Step 1: Data Collection

[0170] The server retrieves listing and purchase data via APIs for e-commerce sites and flea market applications.

[0171] Input: Data such as product name, price, category, listing time, and purchase time.

[0172] Process: Use Django to retrieve data from the API and convert it to the appropriate data format.

[0173] Output: A well-formatted dataset.

[0174] Step 2: Storing in the database

[0175] The server stores the collected data in a centralized management database. It also handles the processing of missing and outlier data.

[0176] Input: Data collected in Step 1.

[0177] Processing: Data is stored in a database using Django and SQLite, and missing or outlier values ​​are handled.

[0178] Output: Clean data centrally managed in a database.

[0179] Step 3: Data diagnosis using generated AI

[0180] The server uses a generative AI to perform data analysis based on the data stored in the SQLite database.

[0181] Input: A clean database.

[0182] Processing: Train a generative AI model using TensorFlow to forecast demand (calculating optimal listing time, appropriate price range, and recommended quantity).

[0183] Output: Demand forecast results (optimal listing time, appropriate price, recommended quantity).

[0184] Step 4: Entering product information via the user interface

[0185] Users enter product information for items they plan to list for sale using a smartphone application.

[0186] Input: Product name, size, color, price, and other detailed information.

[0187] Processing: Enter product information into the input form and send it to the server.

[0188] Output: The entered product information.

[0189] Step 5: Presentation of the Generative AI's Proposal Results

[0190] The server provides the user with prediction results generated by AI based on the entered product information.

[0191] Input: Entered product information and the demand forecast results generated by the AI.

[0192] Processing: The prediction results generated by the AI ​​are linked to product information and presented to the user.

[0193] Output: Suggestions for optimal listing time, appropriate price, and recommended quantity.

[0194] Step 6: Collect listing and sales data

[0195] Users list products based on suggestions from the generating AI, and sales results are collected by the server.

[0196] Input: Listing information, sales results (sales time, sales price, number of units sold, etc.).

[0197] Processing: After listing an item, the sales results are sent to the server and stored in the database.

[0198] Output: Feedback data (sales performance).

[0199] Step 7: Training the Generative AI

[0200] The server uses the collected feedback data as training data for the generated AI model.

[0201] Input: Feedback data.

[0202] Processing: Retrain the generative AI model using TensorFlow to improve prediction accuracy.

[0203] Output: Improved generative AI model.

[0204] In this way, users can list their products at the optimal time and price, enabling efficient buying and selling.

[0205] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0206] This invention is a system that enables users to efficiently buy and sell items by using AI to analyze listing data and demand data in a flea market application, and further combining this with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0207] The server collaborates with the provider of the flea market application to collect listing and purchase data via API. This data includes product name, price, category, listing time, and purchase time. The collected data is converted into an appropriate format for storage in a centralized management database.

[0208] Next, the server uses a generative AI to analyze this data. The generative AI analyzes past sales history and demand trends to make demand forecasts for each product. For example, it predicts the demand for "black T-shirts" in a particular season and calculates the appropriate price range and timing for sales.

[0209] Users access the system using a device (e.g., a smartphone or computer) through a dedicated app or web portal. Users enter detailed information about the items they intend to list (product name, size, color, etc.). The device then sends this information to the server.

[0210] When the server receives product information submitted by a user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. At the same time, the server uses an emotion engine to collect emotional data from the user's input and incorporates this information into the generating AI's training data. For example, if a user expresses joy when listing a "black T-shirt," the generating AI uses that emotional data for its analysis.

[0211] The server integrates the output of the emotion engine and the analysis results of the generative AI to present the user with the most suitable listing information. For example, it might present the user with results such as, "Listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate. Furthermore, based on the user's emotion data, a high level of satisfaction with this prediction can be expected."

[0212] Users list their items based on the suggested listing timing and price. The listing results (whether or not it sold, the timing and price of the sale) are fed back to the server. The server uses this feedback data as training data for its generating AI and sentiment engine to improve the accuracy of future predictive analysis.

[0213] For example, if a user lists a "black T-shirt" at the offered price and it sells quickly, that sales data and the user's sentiment data are re-inputted into the generative AI. This process continuously improves the generative AI's predictive model, enabling more accurate predictions.

[0214] By utilizing this system, users will be provided with optimal information for effectively buying and selling goods, which is expected to improve the overall efficiency of the flea market application and increase user satisfaction.

[0215] The following describes the processing flow.

[0216] Step 1:

[0217] The server collaborates with the provider of the flea market application to collect listing and purchase data via API. Specifically, it calls the API daily or at regular intervals to retrieve data such as product name, price, category, listing time, and purchase time. This data is received in JSON format.

[0218] Step 2:

[0219] The server converts the collected listing and purchase data into a format for storage in a centralized database. For example, it parses data received in JSON format to match the table structure of the relational database and maps it to fields such as listing date, product name, and price.

[0220] Step 3:

[0221] The server uses a generative AI to analyze this data. The server extracts historical listing and purchase data from the database and inputs it into the generative AI. Based on the historical data, the generative AI creates a demand forecasting model and analyzes demand trends for each product. For example, it predicts the demand for "black T-shirts" in a particular season and calculates the appropriate price range and sales timing.

[0222] Step 4:

[0223] Users access a dedicated app or web portal using their device and enter detailed information about the items they want to list. For example, if a user wants to list a "black T-shirt," they would enter the product name, category, size, color, and desired price. The device then sends this information to the server.

[0224] Step 5:

[0225] The device uses an emotion engine to collect user emotion data when the user enters detailed information. The device also uses a camera and voice recognition system to analyze the user's facial expressions and tone of voice to obtain emotion data.

[0226] Step 6:

[0227] The server receives product information and sentiment data sent by the user. The server incorporates the sentiment data into the training data of the generating AI and analyzes it by comparing it with past sentiment data.

[0228] Step 7:

[0229] The server calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. User sentiment data is also reflected in this. For example, it might derive a result such as, "Listing a black T-shirt on Saturday evening is most effective, and the appropriate price is 2,000 to 2,500 yen. Based on user sentiment data, a high level of satisfaction can be expected with this prediction."

[0230] Step 8:

[0231] The device displays to the user the analysis results and sentiment data from the generated AI received from the server. The user can then review suggestions for optimal listing timing and appropriate pricing on the app or web portal screen. Because the suggestions are tailored to the user's emotions, they are easier to understand intuitively.

[0232] Step 9:

[0233] The user lists their items based on the suggested listing timing and price. The device then feeds back the listing results (whether the item was sold, the timing of the sale, and the price) to the server.

[0234] Step 10:

[0235] The server uses the feedback data as training data for the generative AI and sentiment engine, and utilizes it to improve the accuracy of future predictive analyses. The collected feedback data is stored in the "Sales Data" table and used to retrain the generative AI. This allows the generative AI to continuously improve and build more accurate predictive models.

[0236] This series of processing steps is expected to provide users with optimal information for effectively buying and selling goods, improve the overall efficiency of the flea market application, and increase user satisfaction.

[0237] (Example 2)

[0238] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0239] Traditional flea market applications struggle to predict the optimal timing and price for listing items to effectively buy and sell goods. Furthermore, they fail to consider user sentiment when presenting listings, leading to decreased user satisfaction. Additionally, the lack of sufficient utilization of past sales data and user feedback hinders improvements in analytical accuracy.

[0240] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0241] In this invention, the server includes means for using a generating AI to diagnose data and demand for items listed on the flea market application; means for inputting detailed information such as the product name, size, and color of items listed by the user; means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI; means for collecting the results of items actually listed by the user and using them as training data for the generating AI; and means for collecting user sentiment data, adding it to the training data of the generating AI, and presenting listing information that takes the user's sentiment into consideration based on the analysis results. As a result, users are provided with optimal information for effective buying and selling, improving the overall buying and selling efficiency of the flea market application and increasing user satisfaction.

[0242] A "flea market application" is an online platform where users can list and buy / sell goods.

[0243] "Generative AI" is a type of artificial intelligence technology that uses algorithms to recognize patterns based on data and perform predictions and generation.

[0244] "Diagnosis" is the process of analyzing collected data to identify specific patterns and trends.

[0245] "Listing data" refers to information that users provide when listing items on a flea market application, and includes the product name, price, size, color, and listing time.

[0246] "Demand data" is information obtained from buyer behavior and trends, and it shows what kinds of products are purchased, when, and at what prices.

[0247] A "user" is an individual or group that uses a flea market application to list or purchase goods.

[0248] "Emotional data" refers to information that quantifies or qualitatively evaluates a user's emotional state, and can be obtained, for example, through facial expression analysis or voice analysis.

[0249] An "emotion engine" is a software or hardware system used to analyze a user's emotional data.

[0250] "Listing time" refers to the specific date and time when a user lists an item on a flea market application.

[0251] "Price" refers to the amount set when a product is sold.

[0252] "Quantity" refers to the number of items listed on the flea market application.

[0253] "Feedback data" refers to data that records the results of users actually listing and selling products, and is used to improve the accuracy of future analyses and predictions.

[0254] This invention is a system that enables users to efficiently buy and sell by combining a generating AI that diagnoses listing data and demand data in a flea market application with an emotion engine that recognizes user emotions. A specific embodiment of this system is described in detail below.

[0255] The server first collaborates with the provider of the flea market application to collect listing and purchase data via API. This data includes product name, price, category, listing time, and purchase time. The collected data is stored in a centralized database and converted to an appropriate format. This conversion uses a Python script to format the data into JSON.

[0256] Next, the server passes the collected data to a generative AI model for analysis. The generative AI model is built using, for example, TensorFlow, and analyzes past sales history and external data sources (for example, Google® Trends). This allows it to predict demand for each product and calculate the appropriate price range and sales timing. A concrete example would be predicting the demand for "black T-shirts" in a specific season and calculating the appropriate price range and sales timing.

[0257] Users access this system using devices such as smartphones and computers. Access is done through a dedicated application or web portal. When a user enters product information (product name, size, color, etc.) for an item they plan to list, the device sends this information to the server. The information is transmitted via API Gateway and processed by an AWS® Lambda function.

[0258] When the server receives product information sent by the user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. At the same time, it uses an emotion engine to collect user emotion data and adds this information as training data for the generating AI. The emotion engine uses OpenCV and IBM Watson® emotion analysis APIs to analyze the user's facial expressions and tone of voice to obtain emotion data.

[0259] The analysis results might present users with information such as, "Listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate. Furthermore, emotional data suggests a high level of customer satisfaction." This notification is delivered via app push notifications or email.

[0260] Users list items based on the suggested listing timing and price. Listing results (success or failure of sales, timing and price of sales) are fed back to the server in real time via the device. This feedback data is used as training data for the generative AI and sentiment engine to improve the accuracy of future predictive analyses.

[0261] For example, if a user lists a "black T-shirt" at the offered price and it sells quickly, that sales data and the user's sentiment data are re-inputted into the generative AI. This process continuously improves the generative AI's predictive model, enabling more accurate predictions.

[0262] An example of a prompt message would be: "A user is trying to list an item using their smartphone. Build a system that uses a generative AI and an emotion engine to suggest the optimal listing timing and price." This system is expected to provide users with optimal information for effectively buying and selling items, improve the overall efficiency of the flea market application, and increase user satisfaction.

[0263] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0264] The processing flow of this system's program

[0265] Step 1:

[0266] The server collects listing and purchase data from the provider of the flea market application via an API. This data includes product name, price, category, listing time, and purchase time. The collected data is converted to JSON format using a Python script. The input is data obtained from the application API endpoint, and the output is data in JSON format.

[0267] Step 2:

[0268] The server stores the collected data in a centralized database. This database uses common database management systems such as MySQL® or PostgreSQL. Input data is converted to JSON format, and output data is in the format stored in the database.

[0269] Step 3:

[0270] The server passes the format-converted data to a generating AI model for analysis. TensorFlow is used for the generating AI model, which analyzes past trading history and external data sources (such as Google Trends). The input is data read from a database, and the output is the analysis results of demand forecasts and appropriate price ranges. Specifically, the server periodically executes queries to retrieve data and passes it to the TensorFlow model.

[0271] Step 4:

[0272] Users access the flea market application or web portal using their smartphone or computer. Users enter information about the items they intend to sell (product name, size, color, etc.). The device sends this information to the server via API Gateway. The input is the product information entered by the user, and the output is data sent to the server in JSON format.

[0273] Step 5:

[0274] When the server receives product information submitted by the user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generated AI model. At the same time, it also collects user sentiment data using a sentiment engine. The sentiment engine uses OpenCV or IBM Watson's sentiment analysis API. The input is the user's listing information and sentiment data obtained in real time, and the output is the analysis results and optimal listing information based on sentiment. Specifically, the server passes the data from the user to the analysis module and obtains the analysis results.

[0275] Step 6:

[0276] The server integrates the analysis results of the generation AI model and the output of the emotion engine to present the user with the most suitable listing information. Notifications are sent via app push notifications and email. The input is the analysis results and emotion evaluation results, and the output is the optimal listing information sent to the user.

[0277] Step 7:

[0278] Users list items based on the suggested listing timing and price. The listing results (success or failure of the sale, timing and price of the sale) are fed back to the server in real time via the device. The input is the listing actually made by the user and its result, and the output is the feedback data sent to the server.

[0279] Step 8:

[0280] The server uses feedback data as training data for the generating AI model and the emotion engine to improve the accuracy of predictive analytics. The input is the feedback data, and the output is the updated parameters of the AI ​​model and the emotion engine. Specifically, the server periodically refeeds this data to the AI ​​model to retrain it.

[0281] With this process, the user is provided with optimal information for effectively selling and buying products, improving the overall trading efficiency of the system and enhancing user satisfaction.

[0282] (Application Example 2)

[0283] Next, Application Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0284] In current free-market applications, there is a problem that it is difficult for users to effectively predict the optimal listing time, price, and quantity for the products they list. Also, there is a demand for improving trading efficiency considering users' emotions. Thus, it is necessary to improve user satisfaction and enhance the overall transaction efficiency.

[0285] <\ 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 diagnosing data and demand produced in the free-market application using a generation AI, means for inputting detailed information such as the product name, size, color, etc. that the user lists, means for presenting the optimal listing time, price, and quantity to the user based on the analysis results of the generation AI, means for collecting the results of what the user actually listed and using them as learning data for the generation AI, means for collecting emotion data at the time of input using an emotion engine that recognizes the user's emotions, and means for taking the emotion data into account in the learning data of the generation AI and making an optimal proposal. This enables the provision of optimal listing information reflecting the user's emotions and the improvement of trading efficiency and user satisfaction.

[0286] The "free-market application" is an online platform where users can list products and other users can purchase those products.

[0287] "Data" refers to various types of information necessary for analysis, such as product information, user behavior history, price, listing time, purchase time, etc.

[0288] "Demand" refers to the desire to purchase a particular product, and the level of demand influences buying and selling.

[0289] "Generative AI" is an artificial intelligence technology that predicts future demand and appropriate prices based on past data.

[0290] A "user" refers to an individual who uses a flea market application to list or purchase goods.

[0291] An "emotion engine" is a technology that recognizes a user's emotions and collects that data.

[0292] "Product name" refers to the name of the item being offered for sale.

[0293] "Size" refers to information about the dimensions and size of the product being offered for sale.

[0294] "Color" refers to the color of the product being offered for sale.

[0295] "Detailed information" refers to specific information used to describe the characteristics of the product being offered for sale.

[0296] "Listing time" refers to the time it takes for a user to list an item on a flea market application.

[0297] "Price" refers to the amount of money spent on the item being offered for sale.

[0298] "Quantity" refers to the number of items being offered for sale.

[0299] "Training data" refers to data that generative AI uses to improve the accuracy of its predictive models.

[0300] "Generative AI analysis results" refer to the predictions and optimizations derived by the generative AI after analyzing the data.

[0301] "Optimal listing information" refers to information about the optimal listing timing, price, and quantity presented to the user based on the analysis results of the generating AI and the output of the emotion engine.

[0302] This invention relates to a flea market application system that enables users to efficiently buy and sell goods, and its main components include a server, terminals, a generative AI, and an emotion engine. The objective of this system is to provide users with optimal listing information and improve overall transaction efficiency.

[0303] First, the server interacts with the provider of the flea market application via an API to collect listing and demand data. This data includes product name, price, category, listing time, and purchase time. The collected data is converted into an appropriate format and stored in a centralized management database.

[0304] Next, the server uses a generative AI to analyze past sales history and demand trends. The generative AI predicts demand for each product and calculates the optimal price range and timing for sale. For example, it predicts the demand for "black shirts" in a particular season and suggests an appropriate price and listing time.

[0305] Users access a dedicated application or web portal using their device and enter detailed information about the items they intend to list for sale (product name, size, color, etc.). While the entered information is sent to the server, a sentiment engine is also used to collect emotional data that the user exhibits while entering the information. For example, if a user expresses joy while entering the listing information for a "black shirt," that emotion is also recorded as data.

[0306] The server calculates the optimal listing time, price, and quantity that reflect the analysis results of the generative AI based on the received product information and sentiment data. At the same time, the sentiment data obtained from the sentiment engine is incorporated into the learning data of the generative AI, and based on this information, an optimal proposal is made to the user. For example, the server presents the user with a result such as "It is most effective to list the black shirt in the evening on Saturday, and the appropriate price range is 2,000 yen to 2,500 yen. Furthermore, judging from the user's sentiment data, a high level of satisfaction can be expected for this prediction."

[0307] Based on these proposals, the user lists the product, and the results (whether it was sold, the timing and price of the sale) are fed back to the server again. The server uses this feedback data as learning data for the generative AI and the sentiment engine to improve the accuracy of the next predictive analysis.

[0308] As a specific example, when the user attempts to list a black shirt, the server proposes the optimal listing timing and price range predicted by the generative AI at the time of listing. At the same time, based on the user's sentiment data, it also predicts how satisfied the user will be with the proposal. With this system, the user is provided with optimal information for effectively selling and buying products.

[0309] As an example of a prompt sentence, the following sentence is proposed:

[0310] "It is most effective to list the black shirt in the evening on Saturday, and the appropriate price range is 2,000 yen to 2,500 yen. Furthermore, judging from the user's sentiment data, a high level of satisfaction can be expected for this prediction."

[0311] The flow of the specific process in Application Example 2 will be described using FIG. 14.

[0312] Step 1:

[0313] The server collaborates with the provider of the flea market application to collect listing and demand data via API. Input data includes product name, price, category, listing time, and purchase time. This data is converted to an appropriate format and stored in a centralized database. The output is the database entry after format conversion.

[0314] Step 2:

[0315] The server analyzes this collected data using a generative AI. Input data includes historical sales history and demand trends. The generative AI forecasts demand for each product and calculates the appropriate price range and sales timing. The output includes the demand forecast results, optimal price range, and sales timing.

[0316] Step 3:

[0317] Users access a dedicated application or web portal using their device and enter detailed information about the items they intend to list (product name, size, color, etc.). This input data is sent to the server. Furthermore, sentiment data displayed by the user during input is collected via a sentiment engine. The output consists of the user's detailed information and sentiment data.

[0318] Step 4:

[0319] The server calculates the optimal listing time, price, and quantity based on the received product information and sentiment data, reflecting the analysis results of the generating AI. The input data consists of the analysis results of the generating AI, detailed user information, and sentiment data. The output is the optimal listing information (listing time, price, and quantity) presented to the user.

[0320] Step 5:

[0321] The server integrates the analysis results from the generated AI with sentiment data to present the user with the most suitable listing information. The input data consists of the integrated analysis results and sentiment data. The output is specific suggestions displayed to the user (e.g., listing timing, price range, quantity, etc.).

[0322] Step 6:

[0323] Users list their products based on the optimal listing information provided by the server. The input is the listing information provided by the server, and the output is the actual listing result. This listing result (whether it was sold, when it was sold, and the price) is fed back to the server.

[0324] Step 7:

[0325] The server uses this feedback data as training data for its generative AI and sentiment engine. The input data is the user's listing results, and the output is updates and accuracy improvements for the generative AI model and sentiment engine. This improves the accuracy of the next predictive analysis.

[0326] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0327] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0328] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0329] [Second Embodiment]

[0330] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0331] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0332] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0333] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0334] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0335] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0336] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0337] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0338] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0339] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0340] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0341] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0342] This invention is a system that uses AI to analyze listing data and demand data in a flea market application, enabling users to buy and sell efficiently. Specific embodiments of this system are described below.

[0343] The server works with the provider of the flea market application to collect listing and purchase data via API. This collected data includes product name, price, category, listing time, and purchase time.

[0344] The server converts the collected data into a format for storage in a centralized database. This format is used for listing data and demand data, and missing or outlier values ​​are added or removed.

[0345] Next, the server uses generative AI to analyze this data. The generative AI analyzes past sales history and demand trends to predict demand for specific products. For example, the generative AI analyzes "black T-shirts" and predicts the seasons when demand will be highest and the optimal price range.

[0346] Users access the system using a device (e.g., a smartphone or computer) through a dedicated app or web portal. Users enter detailed information about the items they intend to list (product name, size, color, etc.). This information is sent to the server, which, based on the analysis results of the generated AI, suggests the optimal listing time, appropriate price, and appropriate quantity to the user.

[0347] For example, if a user tries to list a "black T-shirt," the system might suggest that "listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate." Furthermore, the user's sales performance based on these suggestions is then fed back to the server.

[0348] The server uses this feedback data as training data for the generating AI. For example, if a user lists an item at a fair price and it sells quickly, that performance data is input back into the generating AI, improving the accuracy of the next predictive analysis.

[0349] This system allows users to understand the best time to sell and the appropriate price, enabling them to buy and sell products efficiently. As a result, it is expected that the overall efficiency of the flea market application will improve, and user satisfaction will increase.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] The server works with the provider of the flea market application to collect listing and purchase data via API. Specifically, it calls the API daily or at regular intervals to retrieve data such as product name, price, category, listing time, and purchase time.

[0353] Step 2:

[0354] The server converts the collected data into a format for storage in a centralized database. For example, it parses data received in JSON format to match the table structure of the relational database and maps it to fields such as listing date, product name, and price.

[0355] Step 3:

[0356] The server uses a generative AI to analyze this data. The server extracts historical listing and purchase data from the database and inputs it into the generative AI. The generative AI creates a demand forecasting model based on the historical data and analyzes the demand trends for each product.

[0357] Step 4:

[0358] Users access a dedicated app or web portal using their device and enter detailed information about the items they want to list. For example, if a user wants to list a "black T-shirt," they would enter the product name, category, size, color, and desired price.

[0359] Step 5:

[0360] The terminal sends the product information entered by the user to the server. Specifically, it submits an input form and includes the product information in the payload of an HTTP request, which is then sent to the server.

[0361] Step 6:

[0362] The server receives product information submitted by the user and searches for the results of the generated AI analysis based on that information. For example, it retrieves the latest demand forecast data for "black T-shirts" from the cache.

[0363] Step 7:

[0364] The server calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI, and formats it into a report. For example, it might conclude that "listing black T-shirts on Saturday evenings is most effective, and the appropriate price is between 2,000 and 2,500 yen."

[0365] Step 8:

[0366] The device displays the analysis results generated by the AI, received from the server, to the user. The user then checks the optimal listing timing and appropriate pricing suggestions on the app or web portal screen.

[0367] Step 9:

[0368] Users list items based on the server's suggestions. Once a user lists an item, they provide feedback to the server about the result (whether it sold, when it sold, and at what price).

[0369] Step 10:

[0370] The server collects feedback data as training data for the generating AI and uses it to improve the accuracy of future predictive analyses. The collected feedback data is stored in the "Sales Data" table and used to retrain the generating AI.

[0371] This series of processing steps provides users with optimal information for effectively buying and selling goods, improving the overall efficiency of the flea market application.

[0372] (Example 1)

[0373] Next, we will describe Example 1. 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."

[0374] Traditional flea market applications made it difficult for users to determine the optimal timing for listing items and fair pricing, hindering efficient buying and selling. Furthermore, they lacked a system for efficiently analyzing listing and demand data and providing rapid feedback to users. As a result, the efficiency of transactions decreased, leading to low user satisfaction.

[0375] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0376] In this invention, the server includes means for diagnosing data and demand for items listed on a flea market application using a generating AI model, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI model, means for collecting the results of items actually listed by the user and using them as training data for the generating AI model, and means for data formatting to impute missing values ​​and remove outliers. As a result, users can understand the best time to sell and the appropriate price, enabling them to buy and sell goods efficiently.

[0377] A "flea market application" is an online marketplace that provides a platform where users can list items for sale and buyers can purchase those items.

[0378] A "generative AI model" is an artificial intelligence algorithm that analyzes trends and patterns based on collected data to make predictions and suggestions.

[0379] "Listing data" refers to information that users provide when listing items on a flea market application, such as product name, size, color, price, and listing time.

[0380] "Demand data" refers to information that indicates the demand for a product, such as a buyer's purchase history, purchase time, and purchase frequency.

[0381] A "server" is a computer system that collects, manages, and analyzes data from a flea market application and provides the necessary information to users.

[0382] "Data formatting means" refers to functions that process collected data to impart missing values, remove outliers, and convert it into a format suitable for analysis.

[0383] "Analysis results" refer to suggested information such as listing timing, appropriate price, and optimal quantity, obtained as a result of data diagnosis by a generated AI model.

[0384] "Training data" refers to past sales performance and feedback data that the generating AI model uses to improve its accuracy.

[0385] This invention is a system that uses an AI model to analyze listing data and demand data in a flea market application, enabling users to buy and sell efficiently. Specific embodiments of this system are described below.

[0386] The server works with the provider of the flea market application to collect listing and purchase data via API. This collected data includes product name, price, category, listing time, and purchase time. The server retrieves this data using HTTP requests.

[0387] Next, the server converts the collected data into a format for storage in a centralized database. This format is adapted to the listing data and demand data, and missing or outlier values ​​are imputed or removed. The Python Pandas library can be used for this purpose. The data is then converted to CSV or SQL format for storage in the database.

[0388] The server then uses generative AI (e.g., OpenAI's GPT-4 model) to analyze this data. The generative AI analyzes past sales history and demand trends to predict demand for specific products. Specifically, based on data such as product name, price, and category, the generative AI predicts the season and optimal price range for "black t-shirts" when demand will be high.

[0389] Users access the system using their own devices (smartphones or computers) through a dedicated app or web portal. Users enter detailed information about the products they intend to list (product name, size, color, etc.). This entered information is sent to the server.

[0390] The server receives information sent by the user and, based on the analysis results of the generating AI, suggests the optimal listing time, price, and quantity to the user. For example, if a user tries to list a "black T-shirt," the system suggests that "listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate."

[0391] When a user lists an item based on a suggested product, its sales performance is fed back to the server. The server uses this feedback data as training data for its generating AI model to improve the accuracy of future predictive analyses. For example, if a user lists an item at a reasonable price and it sells quickly, that sales data is input back into the generating AI, improving the model's prediction accuracy.

[0392] This system allows users to understand the best time to sell and the appropriate price, enabling them to buy and sell products efficiently. As a result, it is expected that the overall efficiency of the flea market application will improve, and user satisfaction will increase.

[0393] Examples of prompt statements include:

[0394] "I'm planning to list a black, size L T-shirt for sale. Could you tell me the most popular time slots and the best price to set?"

[0395] In this way, the system uses a generated AI model to analyze listing data and demand data, and provides users with the optimal listing strategy. This enables users to buy and sell efficiently.

[0396] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0397] Step 1:

[0398] The server collects listing and purchase data through the flea market application's API. Specifically, the server sends an HTTP request and receives JSON data as a response. The input is the flea market application's API endpoint, and the output is a dataset containing information such as product name, price, category, listing time, and purchase time.

[0399] Step 2:

[0400] The server converts the collected data into a format suitable for storage in a centralized database. Specifically, the server uses the Python Pandas library to read the data and impute and remove missing and outlier values. The input is the data collected in step 1, and the output is the formatted data with missing and outlier values ​​imputed and removed.

[0401] Step 3:

[0402] The server uses a generative AI model to analyze the formatted data. Specifically, the server inputs the formatted data into a generative AI model (e.g., GPT-4), and the model performs trend analysis and demand forecasting. The input is the formatted data, and the output is the analysis results, such as demand forecasts for each product, optimal listing timing, and price range.

[0403] Step 4:

[0404] Users access the system using their devices via a dedicated app or web portal. Specifically, users input detailed information such as product name, size, and color. The input is the user's product details, and the output is a processing request to the server.

[0405] Step 5:

[0406] The server receives information sent by the user and, based on the analysis results of the generating AI model, presents the user with the optimal listing time, price, and quantity. Specifically, the server refers to the analysis results of the generating AI model and uses them to provide the user with an appropriate listing strategy. The input is detailed information provided by the user and the analysis results of the generating AI model, and the output is suggested information for the user (optimal listing time, price, and quantity).

[0407] Step 6:

[0408] Users list products based on the suggestions provided and receive sales results. Specifically, users list products according to the system's suggestions, and when a product sells, the result is sent to the server. The inputs are the server's suggestion information and the user's actions, and the output is sales result data.

[0409] Step 7:

[0410] The server uses sales results data as training data for a generative AI model to improve the model's prediction accuracy. Specifically, the server collects sales results data and uses it to retrain the generative AI model. The input is sales results data, and the output is an improved generative AI model and increased prediction accuracy.

[0411] Through the steps outlined above, users can obtain the optimal listing strategy, and it is expected that the overall buying and selling efficiency of the flea market application will improve.

[0412] (Application Example 1)

[0413] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0414] Modern flea market applications and e-commerce sites face the problem of users having difficulty obtaining the right information to efficiently buy and sell goods. In particular, the lack of means to predict the optimal listing time, price, and quantity of items to sell often leads to users missing out on opportunities and losses. Furthermore, the inefficiency of the user interface and the lack of accurate demand forecasting contribute to a decrease in overall sales efficiency.

[0415] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0416] In this invention, the server includes means for using a generating AI to diagnose data and demand for items listed on a flea market application, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI, means for collecting the results of items actually listed by the user and using them as training data for the generating AI, and means for providing a user interface via a smartphone application for collecting and analyzing data on an e-commerce site and proposing the optimal sales strategy. This enables users to list items at the most effective time and price, and to buy and sell items quickly and efficiently.

[0417] Definition of Terms

[0418] A "flea market application" is an online platform where users can freely list items for sale and buyers can conduct transactions directly with them.

[0419] "Generative AI" refers to a system that uses machine learning models and artificial intelligence to analyze data and generate information.

[0420] "Product name" refers to the identifying name of the product being offered for sale, and is the name that users use to identify the product.

[0421] "Size" refers to information that indicates the specific dimensions or scale of a product.

[0422] "Color" refers to information that indicates the colors a product possesses.

[0423] "Detailed information" refers to specific and detailed data about the product, including product name, size, color, etc.

[0424] "Analysis results" refer to the information obtained after the generating AI analyzes the listing data and demand data.

[0425] "Optimal listing time" refers to the most effective timing for listing an item.

[0426] "Price" refers to the amount a user sets when listing an item for sale.

[0427] "Quantity" refers to the number of items a user lists for sale.

[0428] "Collection" refers to the process of gathering information and data after a user has listed an item for sale.

[0429] "Training data" refers to a collection of historical data that a generative AI uses to improve its performance.

[0430] An "online shopping site" is an online platform for selling products over the internet.

[0431] "User interface" refers to the screens and means of operation that users use to interact with a system.

[0432] A "smartphone application" is a software program that runs on a smartphone.

[0433] "Data collection" is the process of gathering data from specific sources.

[0434] "Analysis" is the process of examining collected data and deriving useful information.

[0435] A "sales strategy" is a plan or method for effectively selling a product.

[0436] Modes for carrying out the invention

[0437] This invention relates to a system for users to efficiently buy and sell goods in flea market applications and online shopping sites. Specific embodiments thereof are described below.

[0438] (Overall system configuration)

[0439] The system primarily consists of a server and user terminals. The server analyzes data using a generative AI model, while the user terminals operate as smartphone applications. The following details each component of the system and its function.

[0440] Hardware to use

[0441] Server: Performs data collection, database management, and execution of generated AI models.

[0442] User device: Smartphone (device capable of running smartphone applications).

[0443] Software to use

[0444] Django: A Python-based web framework used for API servers and data transformation / correction.

[0445] SQLite: A database management system used to centrally manage collected data.

[0446] TensorFlow: A machine learning library used to build and run generative AI models.

[0447] Flutter: A smartphone application development framework used to build user interfaces.

[0448] Data flow and processing

[0449] 1. Data acquisition and format conversion

[0450] The server collects listing and purchase data through APIs for e-commerce sites and flea market applications. This includes information such as product name, price, category, listing time, and purchase time. The collected data is formatted using Django and stored in an SQLite database. Missing or outlier data are imputed or removed at this stage.

[0451] 2. Data analysis using generated AI

[0452] The server uses TensorFlow to build a generative AI model based on data stored in an SQLite database. This generative AI model analyzes past sales history and demand trend data to predict demand for a specific product. This prediction includes the optimal listing time, price, and quantity.

[0453] 3. Proposals based on user interface

[0454] Users enter product information (product name, size, color, etc.) for items they intend to list using a smartphone application built with Flutter. The entered information is sent to a server, and based on the analysis results of a generated AI model, the optimal listing time, price, and quantity are presented to the user.

[0455] 4. Collecting and generating feedback data for AI training

[0456] Based on the suggestions provided by the user, products are listed for sale, and as a result, sales performance data is fed back to the server. This feedback data is used as training data for the generating AI model, improving the accuracy of future predictive analyses.

[0457] Specific example

[0458] When a user uses a smartphone application to list old books for sale, they enter the book's information (title, author, condition, price) into the application. This information is sent to the server, where a generating AI calculates the optimal listing time (e.g., weekday evenings), appropriate price (around 2000 yen), and recommended quantity (depending on inventory) and suggests them to the user. When the user lists the item based on the suggestion, the sales performance is used to train the generating AI.

[0459] Examples of prompts to input into a generative AI model

[0460] The user enters the product data they plan to list in the following format:

[0461] Product name: Book name

[0462] Category: Books, Magazines

[0463] Price: 2000 yen

[0464] Listing timing: Weekday evenings

[0465] Based on this data, please analyze past purchase data from the e-commerce site and use AI to propose the optimal listing timing, appropriate price, and recommended quantity.

[0466] This allows users to list their products at the most effective time and price, enabling efficient buying and selling.

[0467] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0468] Program processing steps

[0469] Step 1: Data Collection

[0470] The server retrieves listing and purchase data via APIs for e-commerce sites and flea market applications.

[0471] Input: Data such as product name, price, category, listing time, and purchase time.

[0472] Process: Use Django to retrieve data from the API and convert it to the appropriate data format.

[0473] Output: A well-formatted dataset.

[0474] Step 2: Storing in the database

[0475] The server stores the collected data in a centralized management database. It also handles the processing of missing and outlier data.

[0476] Input: Data collected in Step 1.

[0477] Processing: Data is stored in a database using Django and SQLite, and missing or outlier values ​​are handled.

[0478] Output: Clean data centrally managed in a database.

[0479] Step 3: Data diagnosis using generated AI

[0480] The server uses a generative AI to perform data analysis based on the data stored in the SQLite database.

[0481] Input: A clean database.

[0482] Processing: Train a generative AI model using TensorFlow to forecast demand (calculating optimal listing time, appropriate price range, and recommended quantity).

[0483] Output: Demand forecast results (optimal listing time, appropriate price, recommended quantity).

[0484] Step 4: Entering product information via the user interface

[0485] Users enter product information for items they plan to list for sale using a smartphone application.

[0486] Input: Product name, size, color, price, and other detailed information.

[0487] Processing: Enter product information into the input form and send it to the server.

[0488] Output: The entered product information.

[0489] Step 5: Presentation of the Generative AI's Proposal Results

[0490] The server provides the user with prediction results generated by AI based on the entered product information.

[0491] Input: Entered product information and the demand forecast results generated by the AI.

[0492] Processing: The prediction results generated by the AI ​​are linked to product information and presented to the user.

[0493] Output: Suggestions for optimal listing time, appropriate price, and recommended quantity.

[0494] Step 6: Collect listing and sales data

[0495] Users list products based on suggestions from the generating AI, and sales results are collected by the server.

[0496] Input: Listing information, sales results (sales time, sales price, number of units sold, etc.).

[0497] Processing: After listing an item, the sales results are sent to the server and stored in the database.

[0498] Output: Feedback data (sales performance).

[0499] Step 7: Training the Generative AI

[0500] The server uses the collected feedback data as training data for the generated AI model.

[0501] Input: Feedback data.

[0502] Processing: Retrain the generative AI model using TensorFlow to improve prediction accuracy.

[0503] Output: Improved generative AI model.

[0504] In this way, users can list their products at the optimal time and price, enabling efficient buying and selling.

[0505] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0506] This invention is a system that enables users to efficiently buy and sell items by using AI to analyze listing data and demand data in a flea market application, and further combining this with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0507] The server collaborates with the provider of the flea market application to collect listing and purchase data via API. This data includes product name, price, category, listing time, and purchase time. The collected data is converted into an appropriate format for storage in a centralized management database.

[0508] Next, the server uses a generative AI to analyze this data. The generative AI analyzes past sales history and demand trends to make demand forecasts for each product. For example, it predicts the demand for "black T-shirts" in a particular season and calculates the appropriate price range and timing for sales.

[0509] Users access the system using a device (e.g., a smartphone or computer) through a dedicated app or web portal. Users enter detailed information about the items they intend to list (product name, size, color, etc.). The device then sends this information to the server.

[0510] When the server receives product information submitted by a user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. At the same time, the server uses an emotion engine to collect emotional data from the user's input and incorporates this information into the generating AI's training data. For example, if a user expresses joy when listing a "black T-shirt," the generating AI uses that emotional data for its analysis.

[0511] The server integrates the output of the emotion engine and the analysis results of the generative AI to present the user with the most suitable listing information. For example, it might present the user with results such as, "Listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate. Furthermore, based on the user's emotion data, a high level of satisfaction with this prediction can be expected."

[0512] Users list their items based on the suggested listing timing and price. The listing results (whether or not it sold, the timing and price of the sale) are fed back to the server. The server uses this feedback data as training data for its generating AI and sentiment engine to improve the accuracy of future predictive analysis.

[0513] For example, if a user lists a "black T-shirt" at the offered price and it sells quickly, that sales data and the user's sentiment data are re-inputted into the generative AI. This process continuously improves the generative AI's predictive model, enabling more accurate predictions.

[0514] By utilizing this system, users will be provided with optimal information for effectively buying and selling goods, which is expected to improve the overall efficiency of the flea market application and increase user satisfaction.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] The server collaborates with the provider of the flea market application to collect listing and purchase data via API. Specifically, it calls the API daily or at regular intervals to retrieve data such as product name, price, category, listing time, and purchase time. This data is received in JSON format.

[0518] Step 2:

[0519] The server converts the collected listing and purchase data into a format for storage in a centralized database. For example, it parses data received in JSON format to match the table structure of the relational database and maps it to fields such as listing date, product name, and price.

[0520] Step 3:

[0521] The server uses a generative AI to analyze this data. The server extracts historical listing and purchase data from the database and inputs it into the generative AI. Based on the historical data, the generative AI creates a demand forecasting model and analyzes demand trends for each product. For example, it predicts the demand for "black T-shirts" in a particular season and calculates the appropriate price range and sales timing.

[0522] Step 4:

[0523] Users access a dedicated app or web portal using their device and enter detailed information about the items they want to list. For example, if a user wants to list a "black T-shirt," they would enter the product name, category, size, color, and desired price. The device then sends this information to the server.

[0524] Step 5:

[0525] The device uses an emotion engine to collect user emotion data when the user enters detailed information. The device also uses a camera and voice recognition system to analyze the user's facial expressions and tone of voice to obtain emotion data.

[0526] Step 6:

[0527] The server receives product information and sentiment data sent by the user. The server incorporates the sentiment data into the training data of the generating AI and analyzes it by comparing it with past sentiment data.

[0528] Step 7:

[0529] The server calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. User sentiment data is also reflected in this. For example, it might derive a result such as, "Listing a black T-shirt on Saturday evening is most effective, and the appropriate price is 2,000 to 2,500 yen. Based on user sentiment data, a high level of satisfaction can be expected with this prediction."

[0530] Step 8:

[0531] The device displays to the user the analysis results and sentiment data from the generated AI received from the server. The user can then review suggestions for optimal listing timing and appropriate pricing on the app or web portal screen. Because the suggestions are tailored to the user's emotions, they are easier to understand intuitively.

[0532] Step 9:

[0533] The user lists their items based on the suggested listing timing and price. The device then feeds back the listing results (whether the item was sold, the timing of the sale, and the price) to the server.

[0534] Step 10:

[0535] The server uses the feedback data as training data for the generative AI and sentiment engine, and utilizes it to improve the accuracy of future predictive analyses. The collected feedback data is stored in the "Sales Data" table and used to retrain the generative AI. This allows the generative AI to continuously improve and build more accurate predictive models.

[0536] This series of processing steps is expected to provide users with optimal information for effectively buying and selling goods, improve the overall efficiency of the flea market application, and increase user satisfaction.

[0537] (Example 2)

[0538] Next, we will describe Example 2. 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".

[0539] Traditional flea market applications struggle to predict the optimal timing and price for listing items to effectively buy and sell goods. Furthermore, they fail to consider user sentiment when presenting listings, leading to decreased user satisfaction. Additionally, the lack of sufficient utilization of past sales data and user feedback hinders improvements in analytical accuracy.

[0540] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0541] In this invention, the server includes means for using a generating AI to diagnose data and demand for items listed on the flea market application; means for inputting detailed information such as the product name, size, and color of items listed by the user; means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI; means for collecting the results of items actually listed by the user and using them as training data for the generating AI; and means for collecting user sentiment data, adding it to the training data of the generating AI, and presenting listing information that takes the user's sentiment into consideration based on the analysis results. As a result, users are provided with optimal information for effective buying and selling, improving the overall buying and selling efficiency of the flea market application and increasing user satisfaction.

[0542] A "flea market application" is an online platform where users can list and buy / sell goods.

[0543] "Generative AI" is a type of artificial intelligence technology that uses algorithms to recognize patterns based on data and perform predictions and generation.

[0544] "Diagnosis" is the process of analyzing collected data to identify specific patterns and trends.

[0545] "Listing data" refers to information that users provide when listing items on a flea market application, and includes the product name, price, size, color, and listing time.

[0546] "Demand data" is information obtained from buyer behavior and trends, and it shows what kinds of products are purchased, when, and at what prices.

[0547] A "user" is an individual or group that uses a flea market application to list or purchase goods.

[0548] "Emotional data" refers to information that quantifies or qualitatively evaluates a user's emotional state, and can be obtained, for example, through facial expression analysis or voice analysis.

[0549] An "emotion engine" is a software or hardware system used to analyze a user's emotional data.

[0550] "Listing time" refers to the specific date and time when a user lists an item on a flea market application.

[0551] "Price" refers to the amount set when a product is sold.

[0552] "Quantity" refers to the number of items listed on the flea market application.

[0553] "Feedback data" refers to data that records the results of users actually listing and selling products, and is used to improve the accuracy of future analyses and predictions.

[0554] This invention is a system that enables users to efficiently buy and sell by combining a generating AI that diagnoses listing data and demand data in a flea market application with an emotion engine that recognizes user emotions. A specific embodiment of this system is described in detail below.

[0555] The server first collaborates with the provider of the flea market application to collect listing and purchase data via API. This data includes product name, price, category, listing time, and purchase time. The collected data is stored in a centralized database and converted to an appropriate format. This conversion uses a Python script to format the data into JSON.

[0556] Next, the server passes the collected data to a generative AI model for analysis. The generative AI model is built using, for example, TensorFlow, and analyzes past sales history and external data sources (such as Google Trends). This allows it to predict demand for each product and calculate appropriate price ranges and sales timings. A concrete example would be predicting the demand for "black T-shirts" in a specific season and calculating appropriate price ranges and sales timings.

[0557] Users access this system using devices such as smartphones and computers. Access is done through a dedicated application or web portal. When a user enters product information (product name, size, color, etc.) for an item they plan to list, the device sends this information to the server. The information is sent via API Gateway and processed by an AWS Lambda function.

[0558] When the server receives product information sent by the user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. At the same time, it uses an emotion engine to collect user emotion data and adds this information as training data for the generating AI. The emotion engine uses OpenCV and IBM Watson's emotion analysis API to obtain emotion data by analyzing the user's facial expressions and tone of voice.

[0559] The analysis results might present users with information such as, "Listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate. Furthermore, emotional data suggests a high level of customer satisfaction." This notification is delivered via app push notifications or email.

[0560] Users list items based on the suggested listing timing and price. Listing results (success or failure of sales, timing and price of sales) are fed back to the server in real time via the device. This feedback data is used as training data for the generative AI and sentiment engine to improve the accuracy of future predictive analyses.

[0561] For example, if a user lists a "black T-shirt" at the offered price and it sells quickly, that sales data and the user's sentiment data are re-inputted into the generative AI. This process continuously improves the generative AI's predictive model, enabling more accurate predictions.

[0562] An example of a prompt message would be: "A user is trying to list an item using their smartphone. Build a system that uses a generative AI and an emotion engine to suggest the optimal listing timing and price." This system is expected to provide users with optimal information for effectively buying and selling items, improve the overall efficiency of the flea market application, and increase user satisfaction.

[0563] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0564] The processing flow of this system's program

[0565] Step 1:

[0566] The server collects listing and purchase data from the provider of the flea market application via an API. This data includes product name, price, category, listing time, and purchase time. The collected data is converted to JSON format using a Python script. The input is data obtained from the application API endpoint, and the output is data in JSON format.

[0567] Step 2:

[0568] The server stores the collected data in a centralized database. This database uses common database management systems such as MySQL or PostgreSQL. Input is data converted to JSON format, and output is the format stored in the database.

[0569] Step 3:

[0570] The server passes the format-converted data to a generating AI model for analysis. TensorFlow is used for the generating AI model, which analyzes past trading history and external data sources (such as Google Trends). The input is data read from a database, and the output is the analysis results of demand forecasts and appropriate price ranges. Specifically, the server periodically executes queries to retrieve data and passes it to the TensorFlow model.

[0571] Step 4:

[0572] Users access the flea market application or web portal using their smartphone or computer. Users enter information about the items they intend to sell (product name, size, color, etc.). The device sends this information to the server via API Gateway. The input is the product information entered by the user, and the output is data sent to the server in JSON format.

[0573] Step 5:

[0574] When the server receives product information submitted by the user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generated AI model. At the same time, it also collects user sentiment data using a sentiment engine. The sentiment engine uses OpenCV or IBM Watson's sentiment analysis API. The input is the user's listing information and sentiment data obtained in real time, and the output is the analysis results and optimal listing information based on sentiment. Specifically, the server passes the data from the user to the analysis module and obtains the analysis results.

[0575] Step 6:

[0576] The server integrates the analysis results of the generation AI model and the output of the emotion engine to present the user with the most suitable listing information. Notifications are sent via app push notifications and email. The input is the analysis results and emotion evaluation results, and the output is the optimal listing information sent to the user.

[0577] Step 7:

[0578] Users list items based on the suggested listing timing and price. The listing results (success or failure of the sale, timing and price of the sale) are fed back to the server in real time via the device. The input is the listing actually made by the user and its result, and the output is the feedback data sent to the server.

[0579] Step 8:

[0580] The server uses feedback data as training data for the generating AI model and the emotion engine to improve the accuracy of predictive analytics. The input is the feedback data, and the output is the updated parameters of the AI ​​model and the emotion engine. Specifically, the server periodically refeeds this data to the AI ​​model to retrain it.

[0581] This process provides users with optimal information for effectively buying and selling products, improving the overall efficiency of the system and increasing user satisfaction.

[0582] (Application Example 2)

[0583] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0584] Current flea market applications face the challenge of not being able to effectively predict the optimal listing time, price, and quantity for items that users will be selling. Furthermore, there is a need to improve buying and selling efficiency by considering user emotions. This necessitates increasing user satisfaction and improving overall transaction efficiency.

[0585] The specific processing performed 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 using a generation AI to diagnose data and demand for items to be listed on the flea market application, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generation AI, means for collecting the results of items actually listed by the user and using them as training data for the generation AI, means for collecting emotional data at the time of input using an emotional engine that recognizes the user's emotions, and means for adding the emotional data to the training data of the generation AI to make optimal suggestions. This makes it possible to provide optimal listing information that reflects the user's emotions, thereby improving buying and selling efficiency and user satisfaction.

[0586] A "flea market application" is an online platform where users can list items for sale and other users can purchase those items.

[0587] "Data" refers to various types of information necessary for analysis, such as product information, user behavior history, price, listing time, and purchase time.

[0588] "Demand" refers to the desire to purchase a particular product, and the level of demand influences buying and selling.

[0589] "Generative AI" is an artificial intelligence technology that predicts future demand and appropriate prices based on past data.

[0590] A "user" refers to an individual who uses a flea market application to list or purchase goods.

[0591] An "emotion engine" is a technology that recognizes a user's emotions and collects that data.

[0592] "Product name" refers to the name of the item being offered for sale.

[0593] "Size" refers to information about the dimensions and size of the product being offered for sale.

[0594] "Color" refers to the color of the product being offered for sale.

[0595] "Detailed information" refers to specific information used to describe the characteristics of the product being offered for sale.

[0596] "Listing time" refers to the time it takes for a user to list an item on a flea market application.

[0597] "Price" refers to the amount of money spent on the item being offered for sale.

[0598] "Quantity" refers to the number of items being offered for sale.

[0599] "Training data" refers to data that generative AI uses to improve the accuracy of its predictive models.

[0600] "Generative AI analysis results" refer to the predictions and optimizations derived by the generative AI after analyzing the data.

[0601] "Optimal listing information" refers to information about the optimal listing timing, price, and quantity presented to the user based on the analysis results of the generating AI and the output of the emotion engine.

[0602] This invention relates to a flea market application system that enables users to efficiently buy and sell goods, and its main components include a server, terminals, a generative AI, and an emotion engine. The objective of this system is to provide users with optimal listing information and improve overall transaction efficiency.

[0603] First, the server interacts with the provider of the flea market application via an API to collect listing and demand data. This data includes product name, price, category, listing time, and purchase time. The collected data is converted into an appropriate format and stored in a centralized management database.

[0604] Next, the server uses a generative AI to analyze past sales history and demand trends. The generative AI predicts demand for each product and calculates the optimal price range and timing for sale. For example, it predicts the demand for "black shirts" in a particular season and suggests an appropriate price and listing time.

[0605] Users access a dedicated application or web portal using their device and enter detailed information about the items they intend to list for sale (product name, size, color, etc.). While the entered information is sent to the server, a sentiment engine is also used to collect emotional data that the user exhibits while entering the information. For example, if a user expresses joy while entering the listing information for a "black shirt," that emotion is also recorded as data.

[0606] The server calculates the optimal listing time, price, and quantity based on the received product information and sentiment data, reflecting the analysis results of the generating AI. Simultaneously, it incorporates sentiment data obtained from the sentiment engine into the generating AI's training data, and uses this information to make optimal suggestions to the user. For example, it might present the user with results such as, "Listing a black shirt on Saturday evening is most effective, and a price of 2000 to 2500 yen is appropriate. Furthermore, judging from the user's sentiment data, a high level of satisfaction with this prediction can be expected."

[0607] Users list items based on these suggestions, and the results (whether they were sold, when they were sold, and at what price) are fed back to the server. The server uses this feedback data as training data for its generating AI and sentiment engine to improve the accuracy of future predictive analyses.

[0608] As a concrete example, when a user tries to list a black shirt for sale, the server, using AI-generated data, suggests the optimal listing timing and price range. Simultaneously, based on the user's sentiment data, it also predicts how satisfied the user will be with the suggestion. This system provides users with optimal information for effectively buying and selling goods.

[0609] The following sentences are suggested as examples of prompts:

[0610] "The most effective time to list a black shirt is Saturday evening, and a price of 2000 to 2500 yen is appropriate. Furthermore, based on user sentiment data, a high level of satisfaction can be expected with this prediction."

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] The server collaborates with the provider of the flea market application to collect listing and demand data via API. Input data includes product name, price, category, listing time, and purchase time. This data is converted to an appropriate format and stored in a centralized database. The output is the database entry after format conversion.

[0614] Step 2:

[0615] The server analyzes this collected data using a generative AI. Input data includes historical sales history and demand trends. The generative AI forecasts demand for each product and calculates the appropriate price range and sales timing. The output includes the demand forecast results, optimal price range, and sales timing.

[0616] Step 3:

[0617] Users access a dedicated application or web portal using their device and enter detailed information about the items they intend to list (product name, size, color, etc.). This input data is sent to the server. Furthermore, sentiment data displayed by the user during input is collected via a sentiment engine. The output consists of the user's detailed information and sentiment data.

[0618] Step 4:

[0619] The server calculates the optimal listing time, price, and quantity based on the received product information and sentiment data, reflecting the analysis results of the generating AI. The input data consists of the analysis results of the generating AI, detailed user information, and sentiment data. The output is the optimal listing information (listing time, price, and quantity) presented to the user.

[0620] Step 5:

[0621] The server integrates the analysis results from the generated AI with sentiment data to present the user with the most suitable listing information. The input data consists of the integrated analysis results and sentiment data. The output is specific suggestions displayed to the user (e.g., listing timing, price range, quantity, etc.).

[0622] Step 6:

[0623] Users list their products based on the optimal listing information provided by the server. The input is the listing information provided by the server, and the output is the actual listing result. This listing result (whether it was sold, when it was sold, and the price) is fed back to the server.

[0624] Step 7:

[0625] The server uses this feedback data as training data for its generative AI and sentiment engine. The input data is the user's listing results, and the output is updates and accuracy improvements for the generative AI model and sentiment engine. This improves the accuracy of the next predictive analysis.

[0626] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0627] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0628] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0629] [Third Embodiment]

[0630] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0631] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0632] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0633] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0634] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0635] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0636] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0637] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0638] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0639] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0640] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0641] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0642] This invention is a system that uses AI to analyze listing data and demand data in a flea market application, enabling users to buy and sell efficiently. Specific embodiments of this system are described below.

[0643] The server works with the provider of the flea market application to collect listing and purchase data via API. This collected data includes product name, price, category, listing time, and purchase time.

[0644] The server converts the collected data into a format for storage in a centralized database. This format is used for listing data and demand data, and missing or outlier values ​​are added or removed.

[0645] Next, the server uses generative AI to analyze this data. The generative AI analyzes past sales history and demand trends to predict demand for specific products. For example, the generative AI analyzes "black T-shirts" and predicts the seasons when demand will be highest and the optimal price range.

[0646] Users access the system using a device (e.g., a smartphone or computer) through a dedicated app or web portal. Users enter detailed information about the items they intend to list (product name, size, color, etc.). This information is sent to the server, which, based on the analysis results of the generated AI, suggests the optimal listing time, appropriate price, and appropriate quantity to the user.

[0647] For example, if a user tries to list a "black T-shirt," the system might suggest that "listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate." Furthermore, the user's sales performance based on these suggestions is then fed back to the server.

[0648] The server uses this feedback data as training data for the generating AI. For example, if a user lists an item at a fair price and it sells quickly, that performance data is input back into the generating AI, improving the accuracy of the next predictive analysis.

[0649] This system allows users to understand the best time to sell and the appropriate price, enabling them to buy and sell products efficiently. As a result, it is expected that the overall efficiency of the flea market application will improve, and user satisfaction will increase.

[0650] The following describes the processing flow.

[0651] Step 1:

[0652] The server works with the provider of the flea market application to collect listing and purchase data via API. Specifically, it calls the API daily or at regular intervals to retrieve data such as product name, price, category, listing time, and purchase time.

[0653] Step 2:

[0654] The server converts the collected data into a format for storage in a centralized database. For example, it parses data received in JSON format to match the table structure of the relational database and maps it to fields such as listing date, product name, and price.

[0655] Step 3:

[0656] The server uses a generative AI to analyze this data. The server extracts historical listing and purchase data from the database and inputs it into the generative AI. The generative AI creates a demand forecasting model based on the historical data and analyzes the demand trends for each product.

[0657] Step 4:

[0658] Users access a dedicated app or web portal using their device and enter detailed information about the items they want to list. For example, if a user wants to list a "black T-shirt," they would enter the product name, category, size, color, and desired price.

[0659] Step 5:

[0660] The terminal sends the product information entered by the user to the server. Specifically, it submits an input form and includes the product information in the payload of an HTTP request, which is then sent to the server.

[0661] Step 6:

[0662] The server receives product information submitted by the user and searches for the results of the generated AI analysis based on that information. For example, it retrieves the latest demand forecast data for "black T-shirts" from the cache.

[0663] Step 7:

[0664] The server calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI, and formats it into a report. For example, it might conclude that "listing black T-shirts on Saturday evenings is most effective, and the appropriate price is between 2,000 and 2,500 yen."

[0665] Step 8:

[0666] The device displays the analysis results generated by the AI, received from the server, to the user. The user then checks the optimal listing timing and appropriate pricing suggestions on the app or web portal screen.

[0667] Step 9:

[0668] Users list items based on the server's suggestions. Once a user lists an item, they provide feedback to the server about the result (whether it sold, when it sold, and at what price).

[0669] Step 10:

[0670] The server collects feedback data as training data for the generating AI and uses it to improve the accuracy of future predictive analyses. The collected feedback data is stored in the "Sales Data" table and used to retrain the generating AI.

[0671] This series of processing steps provides users with optimal information for effectively buying and selling goods, improving the overall efficiency of the flea market application.

[0672] (Example 1)

[0673] Next, we will describe Example 1. 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."

[0674] Traditional flea market applications made it difficult for users to determine the optimal timing for listing items and fair pricing, hindering efficient buying and selling. Furthermore, they lacked a system for efficiently analyzing listing and demand data and providing rapid feedback to users. As a result, the efficiency of transactions decreased, leading to low user satisfaction.

[0675] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0676] In this invention, the server includes means for diagnosing data and demand for items listed on a flea market application using a generating AI model, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI model, means for collecting the results of items actually listed by the user and using them as training data for the generating AI model, and means for data formatting to impute missing values ​​and remove outliers. As a result, users can understand the best time to sell and the appropriate price, enabling them to buy and sell goods efficiently.

[0677] A "flea market application" is an online marketplace that provides a platform where users can list items for sale and buyers can purchase those items.

[0678] A "generative AI model" is an artificial intelligence algorithm that analyzes trends and patterns based on collected data to make predictions and suggestions.

[0679] "Listing data" refers to information that users provide when listing items on a flea market application, such as product name, size, color, price, and listing time.

[0680] "Demand data" refers to information that indicates the demand for a product, such as a buyer's purchase history, purchase time, and purchase frequency.

[0681] A "server" is a computer system that collects, manages, and analyzes data from a flea market application and provides the necessary information to users.

[0682] "Data formatting means" refers to functions that process collected data to impart missing values, remove outliers, and convert it into a format suitable for analysis.

[0683] "Analysis results" refer to suggested information such as listing timing, appropriate price, and optimal quantity, obtained as a result of data diagnosis by a generated AI model.

[0684] "Training data" refers to past sales performance and feedback data that the generating AI model uses to improve its accuracy.

[0685] This invention is a system that uses an AI model to analyze listing data and demand data in a flea market application, enabling users to buy and sell efficiently. Specific embodiments of this system are described below.

[0686] The server works with the provider of the flea market application to collect listing and purchase data via API. This collected data includes product name, price, category, listing time, and purchase time. The server retrieves this data using HTTP requests.

[0687] Next, the server converts the collected data into a format for storage in a centralized database. This format is adapted to the listing data and demand data, and missing or outlier values ​​are imputed or removed. The Python Pandas library can be used for this purpose. The data is then converted to CSV or SQL format for storage in the database.

[0688] The server then uses generative AI (e.g., OpenAI's GPT-4 model) to analyze this data. The generative AI analyzes past sales history and demand trends to predict demand for specific products. Specifically, based on data such as product name, price, and category, the generative AI predicts the season and optimal price range for "black t-shirts" when demand will be high.

[0689] Users access the system using their own devices (smartphones or computers) through a dedicated app or web portal. Users enter detailed information about the products they intend to list (product name, size, color, etc.). This entered information is sent to the server.

[0690] The server receives information sent by the user and, based on the analysis results of the generating AI, suggests the optimal listing time, price, and quantity to the user. For example, if a user tries to list a "black T-shirt," the system suggests that "listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate."

[0691] When a user lists an item based on a suggested product, its sales performance is fed back to the server. The server uses this feedback data as training data for its generating AI model to improve the accuracy of future predictive analyses. For example, if a user lists an item at a reasonable price and it sells quickly, that sales data is input back into the generating AI, improving the model's prediction accuracy.

[0692] This system allows users to understand the best time to sell and the appropriate price, enabling them to buy and sell products efficiently. As a result, it is expected that the overall efficiency of the flea market application will improve, and user satisfaction will increase.

[0693] Examples of prompt statements include:

[0694] "I'm planning to list a black, size L T-shirt for sale. Could you tell me the most popular time slots and the best price to set?"

[0695] In this way, the system uses a generated AI model to analyze listing data and demand data, and provides users with the optimal listing strategy. This enables users to buy and sell efficiently.

[0696] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0697] Step 1:

[0698] The server collects listing and purchase data through the flea market application's API. Specifically, the server sends an HTTP request and receives JSON data as a response. The input is the flea market application's API endpoint, and the output is a dataset containing information such as product name, price, category, listing time, and purchase time.

[0699] Step 2:

[0700] The server converts the collected data into a format suitable for storage in a centralized database. Specifically, the server uses the Python Pandas library to read the data and impute and remove missing and outlier values. The input is the data collected in step 1, and the output is the formatted data with missing and outlier values ​​imputed and removed.

[0701] Step 3:

[0702] The server uses a generative AI model to analyze the formatted data. Specifically, the server inputs the formatted data into a generative AI model (e.g., GPT-4), and the model performs trend analysis and demand forecasting. The input is the formatted data, and the output is the analysis results, such as demand forecasts for each product, optimal listing timing, and price range.

[0703] Step 4:

[0704] Users access the system using their devices via a dedicated app or web portal. Specifically, users input detailed information such as product name, size, and color. The input is the user's product details, and the output is a processing request to the server.

[0705] Step 5:

[0706] The server receives information sent by the user and, based on the analysis results of the generating AI model, presents the user with the optimal listing time, price, and quantity. Specifically, the server refers to the analysis results of the generating AI model and uses them to provide the user with an appropriate listing strategy. The input is detailed information provided by the user and the analysis results of the generating AI model, and the output is suggested information for the user (optimal listing time, price, and quantity).

[0707] Step 6:

[0708] Users list products based on the suggestions provided and receive sales results. Specifically, users list products according to the system's suggestions, and when a product sells, the result is sent to the server. The inputs are the server's suggestion information and the user's actions, and the output is sales result data.

[0709] Step 7:

[0710] The server uses sales results data as training data for a generative AI model to improve the model's prediction accuracy. Specifically, the server collects sales results data and uses it to retrain the generative AI model. The input is sales results data, and the output is an improved generative AI model and increased prediction accuracy.

[0711] Through the steps outlined above, users can obtain the optimal listing strategy, and it is expected that the overall buying and selling efficiency of the flea market application will improve.

[0712] (Application Example 1)

[0713] Next, we will explain Application Example 1. In the following explanation, 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."

[0714] Modern flea market applications and e-commerce sites face the problem of users having difficulty obtaining the right information to efficiently buy and sell goods. In particular, the lack of means to predict the optimal listing time, price, and quantity of items to sell often leads to users missing out on opportunities and losses. Furthermore, the inefficiency of the user interface and the lack of accurate demand forecasting contribute to a decrease in overall sales efficiency.

[0715] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0716] In this invention, the server includes means for using a generating AI to diagnose data and demand for items listed on a flea market application, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI, means for collecting the results of items actually listed by the user and using them as training data for the generating AI, and means for providing a user interface via a smartphone application for collecting and analyzing data on an e-commerce site and proposing the optimal sales strategy. This enables users to list items at the most effective time and price, and to buy and sell items quickly and efficiently.

[0717] Definition of Terms

[0718] A "flea market application" is an online platform where users can freely list items for sale and buyers can conduct transactions directly with them.

[0719] "Generative AI" refers to a system that uses machine learning models and artificial intelligence to analyze data and generate information.

[0720] "Product name" refers to the identifying name of the product being offered for sale, and is the name that users use to identify the product.

[0721] "Size" refers to information that indicates the specific dimensions or scale of a product.

[0722] "Color" refers to information that indicates the colors a product possesses.

[0723] "Detailed information" refers to specific and detailed data about the product, including product name, size, color, etc.

[0724] "Analysis results" refer to the information obtained after the generating AI analyzes the listing data and demand data.

[0725] "Optimal listing time" refers to the most effective timing for listing an item.

[0726] "Price" refers to the amount a user sets when listing an item for sale.

[0727] "Quantity" refers to the number of items a user lists for sale.

[0728] "Collection" refers to the process of gathering information and data after a user has listed an item for sale.

[0729] "Training data" refers to a collection of historical data that a generative AI uses to improve its performance.

[0730] An "online shopping site" is an online platform for selling products over the internet.

[0731] "User interface" refers to the screens and means of operation that users use to interact with a system.

[0732] A "smartphone application" is a software program that runs on a smartphone.

[0733] "Data collection" is the process of gathering data from specific sources.

[0734] "Analysis" is the process of examining collected data and deriving useful information.

[0735] A "sales strategy" is a plan or method for effectively selling a product.

[0736] Modes for carrying out the invention

[0737] This invention relates to a system for users to efficiently buy and sell goods in flea market applications and online shopping sites. Specific embodiments thereof are described below.

[0738] (Overall system configuration)

[0739] The system primarily consists of a server and user terminals. The server analyzes data using a generative AI model, while the user terminals operate as smartphone applications. The following details each component of the system and its function.

[0740] Hardware to use

[0741] Server: Performs data collection, database management, and execution of generated AI models.

[0742] User device: Smartphone (device capable of running smartphone applications).

[0743] Software to use

[0744] Django: A Python-based web framework used for API servers and data transformation / correction.

[0745] SQLite: A database management system used to centrally manage collected data.

[0746] TensorFlow: A machine learning library used to build and run generative AI models.

[0747] Flutter: A smartphone application development framework used to build user interfaces.

[0748] Data flow and processing

[0749] 1. Data acquisition and format conversion

[0750] The server collects listing and purchase data through APIs for e-commerce sites and flea market applications. This includes information such as product name, price, category, listing time, and purchase time. The collected data is formatted using Django and stored in an SQLite database. Missing or outlier data are imputed or removed at this stage.

[0751] 2. Data analysis using generated AI

[0752] The server uses TensorFlow to build a generative AI model based on data stored in an SQLite database. This generative AI model analyzes past sales history and demand trend data to predict demand for a specific product. This prediction includes the optimal listing time, price, and quantity.

[0753] 3. Proposals based on user interface

[0754] Users enter product information (product name, size, color, etc.) for items they intend to list using a smartphone application built with Flutter. The entered information is sent to a server, and based on the analysis results of a generated AI model, the optimal listing time, price, and quantity are presented to the user.

[0755] 4. Collecting and generating feedback data for AI training

[0756] Based on the suggestions provided by the user, products are listed for sale, and as a result, sales performance data is fed back to the server. This feedback data is used as training data for the generating AI model, improving the accuracy of future predictive analyses.

[0757] Specific example

[0758] When a user uses a smartphone application to list old books for sale, they enter the book's information (title, author, condition, price) into the application. This information is sent to the server, where a generating AI calculates the optimal listing time (e.g., weekday evenings), appropriate price (around 2000 yen), and recommended quantity (depending on inventory) and suggests them to the user. When the user lists the item based on the suggestion, the sales performance is used to train the generating AI.

[0759] Examples of prompts to input into a generative AI model

[0760] The user enters the product data they plan to list in the following format:

[0761] Product name: Book name

[0762] Category: Books, Magazines

[0763] Price: 2000 yen

[0764] Listing timing: Weekday evenings

[0765] Based on this data, please analyze past purchase data from the e-commerce site and use AI to propose the optimal listing timing, appropriate price, and recommended quantity.

[0766] This allows users to list their products at the most effective time and price, enabling efficient buying and selling.

[0767] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0768] Program processing steps

[0769] Step 1: Data Collection

[0770] The server retrieves listing and purchase data via APIs for e-commerce sites and flea market applications.

[0771] Input: Data such as product name, price, category, listing time, and purchase time.

[0772] Process: Use Django to retrieve data from the API and convert it to the appropriate data format.

[0773] Output: A well-formatted dataset.

[0774] Step 2: Storing in the database

[0775] The server stores the collected data in a centralized management database. It also handles the processing of missing and outlier data.

[0776] Input: Data collected in Step 1.

[0777] Processing: Data is stored in a database using Django and SQLite, and missing or outlier values ​​are handled.

[0778] Output: Clean data centrally managed in a database.

[0779] Step 3: Data diagnosis using generated AI

[0780] The server uses a generative AI to perform data analysis based on the data stored in the SQLite database.

[0781] Input: A clean database.

[0782] Processing: Train a generative AI model using TensorFlow to forecast demand (calculating optimal listing time, appropriate price range, and recommended quantity).

[0783] Output: Demand forecast results (optimal listing time, appropriate price, recommended quantity).

[0784] Step 4: Entering product information via the user interface

[0785] Users enter product information for items they plan to list for sale using a smartphone application.

[0786] Input: Product name, size, color, price, and other detailed information.

[0787] Processing: Enter product information into the input form and send it to the server.

[0788] Output: The entered product information.

[0789] Step 5: Presentation of the Generative AI's Proposal Results

[0790] The server provides the user with prediction results generated by AI based on the entered product information.

[0791] Input: Entered product information and the demand forecast results generated by the AI.

[0792] Processing: The prediction results generated by the AI ​​are linked to product information and presented to the user.

[0793] Output: Suggestions for optimal listing time, appropriate price, and recommended quantity.

[0794] Step 6: Collect listing and sales data

[0795] Users list products based on suggestions from the generating AI, and sales results are collected by the server.

[0796] Input: Listing information, sales results (sales time, sales price, number of units sold, etc.).

[0797] Processing: After listing an item, the sales results are sent to the server and stored in the database.

[0798] Output: Feedback data (sales performance).

[0799] Step 7: Training the Generative AI

[0800] The server uses the collected feedback data as training data for the generated AI model.

[0801] Input: Feedback data.

[0802] Processing: Retrain the generative AI model using TensorFlow to improve prediction accuracy.

[0803] Output: Improved generative AI model.

[0804] In this way, users can list their products at the optimal time and price, enabling efficient buying and selling.

[0805] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0806] This invention is a system that enables users to efficiently buy and sell items by using AI to analyze listing data and demand data in a flea market application, and further combining this with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0807] The server collaborates with the provider of the flea market application to collect listing and purchase data via API. This data includes product name, price, category, listing time, and purchase time. The collected data is converted into an appropriate format for storage in a centralized management database.

[0808] Next, the server uses a generative AI to analyze this data. The generative AI analyzes past sales history and demand trends to make demand forecasts for each product. For example, it predicts the demand for "black T-shirts" in a particular season and calculates the appropriate price range and timing for sales.

[0809] Users access the system using a device (e.g., a smartphone or computer) through a dedicated app or web portal. Users enter detailed information about the items they intend to list (product name, size, color, etc.). The device then sends this information to the server.

[0810] When the server receives product information submitted by a user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. At the same time, the server uses an emotion engine to collect emotional data from the user's input and incorporates this information into the generating AI's training data. For example, if a user expresses joy when listing a "black T-shirt," the generating AI uses that emotional data for its analysis.

[0811] The server integrates the output of the emotion engine and the analysis results of the generative AI to present the user with the most suitable listing information. For example, it might present the user with results such as, "Listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate. Furthermore, based on the user's emotion data, a high level of satisfaction with this prediction can be expected."

[0812] Users list their items based on the suggested listing timing and price. The listing results (whether or not it sold, the timing and price of the sale) are fed back to the server. The server uses this feedback data as training data for its generating AI and sentiment engine to improve the accuracy of future predictive analysis.

[0813] For example, if a user lists a "black T-shirt" at the offered price and it sells quickly, that sales data and the user's sentiment data are re-inputted into the generative AI. This process continuously improves the generative AI's predictive model, enabling more accurate predictions.

[0814] By utilizing this system, users will be provided with optimal information for effectively buying and selling goods, which is expected to improve the overall efficiency of the flea market application and increase user satisfaction.

[0815] The following describes the processing flow.

[0816] Step 1:

[0817] The server collaborates with the provider of the flea market application to collect listing and purchase data via API. Specifically, it calls the API daily or at regular intervals to retrieve data such as product name, price, category, listing time, and purchase time. This data is received in JSON format.

[0818] Step 2:

[0819] The server converts the collected listing and purchase data into a format for storage in a centralized database. For example, it parses data received in JSON format to match the table structure of the relational database and maps it to fields such as listing date, product name, and price.

[0820] Step 3:

[0821] The server uses a generative AI to analyze this data. The server extracts historical listing and purchase data from the database and inputs it into the generative AI. Based on the historical data, the generative AI creates a demand forecasting model and analyzes demand trends for each product. For example, it predicts the demand for "black T-shirts" in a particular season and calculates the appropriate price range and sales timing.

[0822] Step 4:

[0823] Users access a dedicated app or web portal using their device and enter detailed information about the items they want to list. For example, if a user wants to list a "black T-shirt," they would enter the product name, category, size, color, and desired price. The device then sends this information to the server.

[0824] Step 5:

[0825] The device uses an emotion engine to collect user emotion data when the user enters detailed information. The device also uses a camera and voice recognition system to analyze the user's facial expressions and tone of voice to obtain emotion data.

[0826] Step 6:

[0827] The server receives product information and sentiment data sent by the user. The server incorporates the sentiment data into the training data of the generating AI and analyzes it by comparing it with past sentiment data.

[0828] Step 7:

[0829] The server calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. User sentiment data is also reflected in this. For example, it might derive a result such as, "Listing a black T-shirt on Saturday evening is most effective, and the appropriate price is 2,000 to 2,500 yen. Based on user sentiment data, a high level of satisfaction can be expected with this prediction."

[0830] Step 8:

[0831] The device displays to the user the analysis results and sentiment data from the generated AI received from the server. The user can then review suggestions for optimal listing timing and appropriate pricing on the app or web portal screen. Because the suggestions are tailored to the user's emotions, they are easier to understand intuitively.

[0832] Step 9:

[0833] The user lists their items based on the suggested listing timing and price. The device then feeds back the listing results (whether the item was sold, the timing of the sale, and the price) to the server.

[0834] Step 10:

[0835] The server uses the feedback data as training data for the generative AI and sentiment engine, and utilizes it to improve the accuracy of future predictive analyses. The collected feedback data is stored in the "Sales Data" table and used to retrain the generative AI. This allows the generative AI to continuously improve and build more accurate predictive models.

[0836] This series of processing steps is expected to provide users with optimal information for effectively buying and selling goods, improve the overall efficiency of the flea market application, and increase user satisfaction.

[0837] (Example 2)

[0838] Next, we will describe Example 2. 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."

[0839] Traditional flea market applications struggle to predict the optimal timing and price for listing items to effectively buy and sell goods. Furthermore, they fail to consider user sentiment when presenting listings, leading to decreased user satisfaction. Additionally, the lack of sufficient utilization of past sales data and user feedback hinders improvements in analytical accuracy.

[0840] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0841] In this invention, the server includes means for using a generating AI to diagnose data and demand for items listed on the flea market application; means for inputting detailed information such as the product name, size, and color of items listed by the user; means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI; means for collecting the results of items actually listed by the user and using them as training data for the generating AI; and means for collecting user sentiment data, adding it to the training data of the generating AI, and presenting listing information that takes the user's sentiment into consideration based on the analysis results. As a result, users are provided with optimal information for effective buying and selling, improving the overall buying and selling efficiency of the flea market application and increasing user satisfaction.

[0842] A "flea market application" is an online platform where users can list and buy / sell goods.

[0843] "Generative AI" is a type of artificial intelligence technology that uses algorithms to recognize patterns based on data and perform predictions and generation.

[0844] "Diagnosis" is the process of analyzing collected data to identify specific patterns and trends.

[0845] "Listing data" refers to information that users provide when listing items on a flea market application, and includes the product name, price, size, color, and listing time.

[0846] "Demand data" is information obtained from buyer behavior and trends, and it shows what kinds of products are purchased, when, and at what prices.

[0847] A "user" is an individual or group that uses a flea market application to list or purchase goods.

[0848] "Emotional data" refers to information that quantifies or qualitatively evaluates a user's emotional state, and can be obtained, for example, through facial expression analysis or voice analysis.

[0849] An "emotion engine" is a software or hardware system used to analyze a user's emotional data.

[0850] "Listing time" refers to the specific date and time when a user lists an item on a flea market application.

[0851] "Price" refers to the amount set when a product is sold.

[0852] "Quantity" refers to the number of items listed on the flea market application.

[0853] "Feedback data" refers to data that records the results of users actually listing and selling products, and is used to improve the accuracy of future analyses and predictions.

[0854] This invention is a system that enables users to efficiently buy and sell by combining a generating AI that diagnoses listing data and demand data in a flea market application with an emotion engine that recognizes user emotions. A specific embodiment of this system is described in detail below.

[0855] The server first collaborates with the provider of the flea market application to collect listing and purchase data via API. This data includes product name, price, category, listing time, and purchase time. The collected data is stored in a centralized database and converted to an appropriate format. This conversion uses a Python script to format the data into JSON.

[0856] Next, the server passes the collected data to a generative AI model for analysis. The generative AI model is built using, for example, TensorFlow, and analyzes past sales history and external data sources (such as Google Trends). This allows it to predict demand for each product and calculate appropriate price ranges and sales timings. A concrete example would be predicting the demand for "black T-shirts" in a specific season and calculating appropriate price ranges and sales timings.

[0857] Users access this system using devices such as smartphones and computers. Access is done through a dedicated application or web portal. When a user enters product information (product name, size, color, etc.) for an item they plan to list, the device sends this information to the server. The information is sent via API Gateway and processed by an AWS Lambda function.

[0858] When the server receives product information sent by the user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. At the same time, it uses an emotion engine to collect user emotion data and adds this information as training data for the generating AI. The emotion engine uses OpenCV and IBM Watson's emotion analysis API to obtain emotion data by analyzing the user's facial expressions and tone of voice.

[0859] The analysis results might present users with information such as, "Listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate. Furthermore, emotional data suggests a high level of customer satisfaction." This notification is delivered via app push notifications or email.

[0860] Users list items based on the suggested listing timing and price. Listing results (success or failure of sales, timing and price of sales) are fed back to the server in real time via the device. This feedback data is used as training data for the generative AI and sentiment engine to improve the accuracy of future predictive analyses.

[0861] For example, if a user lists a "black T-shirt" at the offered price and it sells quickly, that sales data and the user's sentiment data are re-inputted into the generative AI. This process continuously improves the generative AI's predictive model, enabling more accurate predictions.

[0862] An example of a prompt message would be: "A user is trying to list an item using their smartphone. Build a system that uses a generative AI and an emotion engine to suggest the optimal listing timing and price." This system is expected to provide users with optimal information for effectively buying and selling items, improve the overall efficiency of the flea market application, and increase user satisfaction.

[0863] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0864] The processing flow of this system's program

[0865] Step 1:

[0866] The server collects listing and purchase data from the provider of the flea market application via an API. This data includes product name, price, category, listing time, and purchase time. The collected data is converted to JSON format using a Python script. The input is data obtained from the application API endpoint, and the output is data in JSON format.

[0867] Step 2:

[0868] The server stores the collected data in a centralized database. This database uses common database management systems such as MySQL or PostgreSQL. Input is data converted to JSON format, and output is the format stored in the database.

[0869] Step 3:

[0870] The server passes the format-converted data to a generating AI model for analysis. TensorFlow is used for the generating AI model, which analyzes past trading history and external data sources (such as Google Trends). The input is data read from a database, and the output is the analysis results of demand forecasts and appropriate price ranges. Specifically, the server periodically executes queries to retrieve data and passes it to the TensorFlow model.

[0871] Step 4:

[0872] Users access the flea market application or web portal using their smartphone or computer. Users enter information about the items they intend to sell (product name, size, color, etc.). The device sends this information to the server via API Gateway. The input is the product information entered by the user, and the output is data sent to the server in JSON format.

[0873] Step 5:

[0874] When the server receives product information submitted by the user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generated AI model. At the same time, it also collects user sentiment data using a sentiment engine. The sentiment engine uses OpenCV or IBM Watson's sentiment analysis API. The input is the user's listing information and sentiment data obtained in real time, and the output is the analysis results and optimal listing information based on sentiment. Specifically, the server passes the data from the user to the analysis module and obtains the analysis results.

[0875] Step 6:

[0876] The server integrates the analysis results of the generation AI model and the output of the emotion engine to present the user with the most suitable listing information. Notifications are sent via app push notifications and email. The input is the analysis results and emotion evaluation results, and the output is the optimal listing information sent to the user.

[0877] Step 7:

[0878] Users list items based on the suggested listing timing and price. The listing results (success or failure of the sale, timing and price of the sale) are fed back to the server in real time via the device. The input is the listing actually made by the user and its result, and the output is the feedback data sent to the server.

[0879] Step 8:

[0880] The server uses feedback data as training data for the generating AI model and the emotion engine to improve the accuracy of predictive analytics. The input is the feedback data, and the output is the updated parameters of the AI ​​model and the emotion engine. Specifically, the server periodically refeeds this data to the AI ​​model to retrain it.

[0881] This process provides users with optimal information for effectively buying and selling products, improving the overall efficiency of the system and increasing user satisfaction.

[0882] (Application Example 2)

[0883] Next, we will explain application example 2. In the following explanation, 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."

[0884] Current flea market applications face the challenge of not being able to effectively predict the optimal listing time, price, and quantity for items that users will be selling. Furthermore, there is a need to improve buying and selling efficiency by considering user emotions. This necessitates increasing user satisfaction and improving overall transaction efficiency.

[0885] The specific processing performed 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 using a generation AI to diagnose data and demand for items to be listed on the flea market application, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generation AI, means for collecting the results of items actually listed by the user and using them as training data for the generation AI, means for collecting emotional data at the time of input using an emotional engine that recognizes the user's emotions, and means for adding the emotional data to the training data of the generation AI to make optimal suggestions. This makes it possible to provide optimal listing information that reflects the user's emotions, thereby improving buying and selling efficiency and user satisfaction.

[0886] A "flea market application" is an online platform where users can list items for sale and other users can purchase those items.

[0887] "Data" refers to various types of information necessary for analysis, such as product information, user behavior history, price, listing time, and purchase time.

[0888] "Demand" refers to the desire to purchase a particular product, and the level of demand influences buying and selling.

[0889] "Generative AI" is an artificial intelligence technology that predicts future demand and appropriate prices based on past data.

[0890] A "user" refers to an individual who uses a flea market application to list or purchase goods.

[0891] An "emotion engine" is a technology that recognizes a user's emotions and collects that data.

[0892] "Product name" refers to the name of the item being offered for sale.

[0893] "Size" refers to information about the dimensions and size of the product being offered for sale.

[0894] "Color" refers to the color of the product being offered for sale.

[0895] "Detailed information" refers to specific information used to describe the characteristics of the product being offered for sale.

[0896] "Listing time" refers to the time it takes for a user to list an item on a flea market application.

[0897] "Price" refers to the amount of money spent on the item being offered for sale.

[0898] "Quantity" refers to the number of items being offered for sale.

[0899] "Training data" refers to data that generative AI uses to improve the accuracy of its predictive models.

[0900] "Generative AI analysis results" refer to the predictions and optimizations derived by the generative AI after analyzing the data.

[0901] "Optimal listing information" refers to information about the optimal listing timing, price, and quantity presented to the user based on the analysis results of the generating AI and the output of the emotion engine.

[0902] This invention relates to a flea market application system that enables users to efficiently buy and sell goods, and its main components include a server, terminals, a generative AI, and an emotion engine. The objective of this system is to provide users with optimal listing information and improve overall transaction efficiency.

[0903] First, the server interacts with the provider of the flea market application via an API to collect listing and demand data. This data includes product name, price, category, listing time, and purchase time. The collected data is converted into an appropriate format and stored in a centralized management database.

[0904] Next, the server uses a generative AI to analyze past sales history and demand trends. The generative AI predicts demand for each product and calculates the optimal price range and timing for sale. For example, it predicts the demand for "black shirts" in a particular season and suggests an appropriate price and listing time.

[0905] Users access a dedicated application or web portal using their device and enter detailed information about the items they intend to list for sale (product name, size, color, etc.). While the entered information is sent to the server, a sentiment engine is also used to collect emotional data that the user exhibits while entering the information. For example, if a user expresses joy while entering the listing information for a "black shirt," that emotion is also recorded as data.

[0906] The server calculates the optimal listing time, price, and quantity based on the received product information and sentiment data, reflecting the analysis results of the generating AI. Simultaneously, it incorporates sentiment data obtained from the sentiment engine into the generating AI's training data, and uses this information to make optimal suggestions to the user. For example, it might present the user with results such as, "Listing a black shirt on Saturday evening is most effective, and a price of 2000 to 2500 yen is appropriate. Furthermore, judging from the user's sentiment data, a high level of satisfaction with this prediction can be expected."

[0907] Users list items based on these suggestions, and the results (whether they were sold, when they were sold, and at what price) are fed back to the server. The server uses this feedback data as training data for its generating AI and sentiment engine to improve the accuracy of future predictive analyses.

[0908] As a concrete example, when a user tries to list a black shirt for sale, the server, using AI-generated data, suggests the optimal listing timing and price range. Simultaneously, based on the user's sentiment data, it also predicts how satisfied the user will be with the suggestion. This system provides users with optimal information for effectively buying and selling goods.

[0909] The following sentences are suggested as examples of prompts:

[0910] "The most effective time to list a black shirt is Saturday evening, and a price of 2000 to 2500 yen is appropriate. Furthermore, based on user sentiment data, a high level of satisfaction can be expected with this prediction."

[0911] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0912] Step 1:

[0913] The server collaborates with the provider of the flea market application to collect listing and demand data via API. Input data includes product name, price, category, listing time, and purchase time. This data is converted to an appropriate format and stored in a centralized database. The output is the database entry after format conversion.

[0914] Step 2:

[0915] The server analyzes this collected data using a generative AI. Input data includes historical sales history and demand trends. The generative AI forecasts demand for each product and calculates the appropriate price range and sales timing. The output includes the demand forecast results, optimal price range, and sales timing.

[0916] Step 3:

[0917] Users access a dedicated application or web portal using their device and enter detailed information about the items they intend to list (product name, size, color, etc.). This input data is sent to the server. Furthermore, sentiment data displayed by the user during input is collected via a sentiment engine. The output consists of the user's detailed information and sentiment data.

[0918] Step 4:

[0919] The server calculates the optimal listing time, price, and quantity based on the received product information and sentiment data, reflecting the analysis results of the generating AI. The input data consists of the analysis results of the generating AI, detailed user information, and sentiment data. The output is the optimal listing information (listing time, price, and quantity) presented to the user.

[0920] Step 5:

[0921] The server integrates the analysis results from the generated AI with sentiment data to present the user with the most suitable listing information. The input data consists of the integrated analysis results and sentiment data. The output is specific suggestions displayed to the user (e.g., listing timing, price range, quantity, etc.).

[0922] Step 6:

[0923] Users list their products based on the optimal listing information provided by the server. The input is the listing information provided by the server, and the output is the actual listing result. This listing result (whether it was sold, when it was sold, and the price) is fed back to the server.

[0924] Step 7:

[0925] The server uses this feedback data as training data for its generative AI and sentiment engine. The input data is the user's listing results, and the output is updates and accuracy improvements for the generative AI model and sentiment engine. This improves the accuracy of the next predictive analysis.

[0926] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0927] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0928] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0929] [Fourth Embodiment]

[0930] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0931] As shown in Figure 7, the 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.

[0932] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0933] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0934] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0935] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0936] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0937] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0938] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0939] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0940] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0941] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0942] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0943] This invention is a system that uses AI to analyze listing data and demand data in a flea market application, enabling users to buy and sell efficiently. Specific embodiments of this system are described below.

[0944] The server works with the provider of the flea market application to collect listing and purchase data via API. This collected data includes product name, price, category, listing time, and purchase time.

[0945] The server converts the collected data into a format for storage in a centralized database. This format is used for listing data and demand data, and missing or outlier values ​​are added or removed.

[0946] Next, the server uses generative AI to analyze this data. The generative AI analyzes past sales history and demand trends to predict demand for specific products. For example, the generative AI analyzes "black T-shirts" and predicts the seasons when demand will be highest and the optimal price range.

[0947] Users access the system using a device (e.g., a smartphone or computer) through a dedicated app or web portal. Users enter detailed information about the items they intend to list (product name, size, color, etc.). This information is sent to the server, which, based on the analysis results of the generated AI, suggests the optimal listing time, appropriate price, and appropriate quantity to the user.

[0948] For example, if a user tries to list a "black T-shirt," the system might suggest that "listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate." Furthermore, the user's sales performance based on these suggestions is then fed back to the server.

[0949] The server uses this feedback data as training data for the generating AI. For example, if a user lists an item at a fair price and it sells quickly, that performance data is input back into the generating AI, improving the accuracy of the next predictive analysis.

[0950] This system allows users to understand the best time to sell and the appropriate price, enabling them to buy and sell products efficiently. As a result, it is expected that the overall efficiency of the flea market application will improve, and user satisfaction will increase.

[0951] The following describes the processing flow.

[0952] Step 1:

[0953] The server works with the provider of the flea market application to collect listing and purchase data via API. Specifically, it calls the API daily or at regular intervals to retrieve data such as product name, price, category, listing time, and purchase time.

[0954] Step 2:

[0955] The server converts the collected data into a format for storage in a centralized database. For example, it parses data received in JSON format to match the table structure of the relational database and maps it to fields such as listing date, product name, and price.

[0956] Step 3:

[0957] The server uses a generative AI to analyze this data. The server extracts historical listing and purchase data from the database and inputs it into the generative AI. The generative AI creates a demand forecasting model based on the historical data and analyzes the demand trends for each product.

[0958] Step 4:

[0959] Users access a dedicated app or web portal using their device and enter detailed information about the items they want to list. For example, if a user wants to list a "black T-shirt," they would enter the product name, category, size, color, and desired price.

[0960] Step 5:

[0961] The terminal sends the product information entered by the user to the server. Specifically, it submits an input form and includes the product information in the payload of an HTTP request, which is then sent to the server.

[0962] Step 6:

[0963] The server receives product information submitted by the user and searches for the results of the generated AI analysis based on that information. For example, it retrieves the latest demand forecast data for "black T-shirts" from the cache.

[0964] Step 7:

[0965] The server calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI, and formats it into a report. For example, it might conclude that "listing black T-shirts on Saturday evenings is most effective, and the appropriate price is between 2,000 and 2,500 yen."

[0966] Step 8:

[0967] The device displays the analysis results generated by the AI, received from the server, to the user. The user then checks the optimal listing timing and appropriate pricing suggestions on the app or web portal screen.

[0968] Step 9:

[0969] Users list items based on the server's suggestions. Once a user lists an item, they provide feedback to the server about the result (whether it sold, when it sold, and at what price).

[0970] Step 10:

[0971] The server collects feedback data as training data for the generating AI and uses it to improve the accuracy of future predictive analyses. The collected feedback data is stored in the "Sales Data" table and used to retrain the generating AI.

[0972] This series of processing steps provides users with optimal information for effectively buying and selling goods, improving the overall efficiency of the flea market application.

[0973] (Example 1)

[0974] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0975] Traditional flea market applications made it difficult for users to determine the optimal timing for listing items and fair pricing, hindering efficient buying and selling. Furthermore, they lacked a system for efficiently analyzing listing and demand data and providing rapid feedback to users. As a result, the efficiency of transactions decreased, leading to low user satisfaction.

[0976] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0977] In this invention, the server includes means for diagnosing data and demand for items listed on a flea market application using a generating AI model, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI model, means for collecting the results of items actually listed by the user and using them as training data for the generating AI model, and means for data formatting to impute missing values ​​and remove outliers. As a result, users can understand the best time to sell and the appropriate price, enabling them to buy and sell goods efficiently.

[0978] A "flea market application" is an online marketplace that provides a platform where users can list items for sale and buyers can purchase those items.

[0979] A "generative AI model" is an artificial intelligence algorithm that analyzes trends and patterns based on collected data to make predictions and suggestions.

[0980] "Listing data" refers to information that users provide when listing items on a flea market application, such as product name, size, color, price, and listing time.

[0981] "Demand data" refers to information that indicates the demand for a product, such as a buyer's purchase history, purchase time, and purchase frequency.

[0982] A "server" is a computer system that collects, manages, and analyzes data from a flea market application and provides the necessary information to users.

[0983] "Data formatting means" refers to functions that process collected data to impart missing values, remove outliers, and convert it into a format suitable for analysis.

[0984] "Analysis results" refer to suggested information such as listing timing, appropriate price, and optimal quantity, obtained as a result of data diagnosis by a generated AI model.

[0985] "Training data" refers to past sales performance and feedback data that the generating AI model uses to improve its accuracy.

[0986] This invention is a system that uses an AI model to analyze listing data and demand data in a flea market application, enabling users to buy and sell efficiently. Specific embodiments of this system are described below.

[0987] The server works with the provider of the flea market application to collect listing and purchase data via API. This collected data includes product name, price, category, listing time, and purchase time. The server retrieves this data using HTTP requests.

[0988] Next, the server converts the collected data into a format for storage in a centralized database. This format is adapted to the listing data and demand data, and missing or outlier values ​​are imputed or removed. The Python Pandas library can be used for this purpose. The data is then converted to CSV or SQL format for storage in the database.

[0989] The server then uses generative AI (e.g., OpenAI's GPT-4 model) to analyze this data. The generative AI analyzes past sales history and demand trends to predict demand for specific products. Specifically, based on data such as product name, price, and category, the generative AI predicts the season and optimal price range for "black t-shirts" when demand will be high.

[0990] Users access the system using their own devices (smartphones or computers) through a dedicated app or web portal. Users enter detailed information about the products they intend to list (product name, size, color, etc.). This entered information is sent to the server.

[0991] The server receives information sent by the user and, based on the analysis results of the generating AI, suggests the optimal listing time, price, and quantity to the user. For example, if a user tries to list a "black T-shirt," the system suggests that "listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate."

[0992] When a user lists an item based on a suggested product, its sales performance is fed back to the server. The server uses this feedback data as training data for its generating AI model to improve the accuracy of future predictive analyses. For example, if a user lists an item at a reasonable price and it sells quickly, that sales data is input back into the generating AI, improving the model's prediction accuracy.

[0993] This system allows users to understand the best time to sell and the appropriate price, enabling them to buy and sell products efficiently. As a result, it is expected that the overall efficiency of the flea market application will improve, and user satisfaction will increase.

[0994] Examples of prompt statements include:

[0995] "I'm planning to list a black, size L T-shirt for sale. Could you tell me the most popular time slots and the best price to set?"

[0996] In this way, the system uses a generated AI model to analyze listing data and demand data, and provides users with the optimal listing strategy. This enables users to buy and sell efficiently.

[0997] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0998] Step 1:

[0999] The server collects listing and purchase data through the flea market application's API. Specifically, the server sends an HTTP request and receives JSON data as a response. The input is the flea market application's API endpoint, and the output is a dataset containing information such as product name, price, category, listing time, and purchase time.

[1000] Step 2:

[1001] The server converts the collected data into a format suitable for storage in a centralized database. Specifically, the server uses the Python Pandas library to read the data and impute and remove missing and outlier values. The input is the data collected in step 1, and the output is the formatted data with missing and outlier values ​​imputed and removed.

[1002] Step 3:

[1003] The server uses a generative AI model to analyze the formatted data. Specifically, the server inputs the formatted data into a generative AI model (e.g., GPT-4), and the model performs trend analysis and demand forecasting. The input is the formatted data, and the output is the analysis results, such as demand forecasts for each product, optimal listing timing, and price range.

[1004] Step 4:

[1005] Users access the system using their devices via a dedicated app or web portal. Specifically, users input detailed information such as product name, size, and color. The input is the user's product details, and the output is a processing request to the server.

[1006] Step 5:

[1007] The server receives information sent by the user and, based on the analysis results of the generating AI model, presents the user with the optimal listing time, price, and quantity. Specifically, the server refers to the analysis results of the generating AI model and uses them to provide the user with an appropriate listing strategy. The input is detailed information provided by the user and the analysis results of the generating AI model, and the output is suggested information for the user (optimal listing time, price, and quantity).

[1008] Step 6:

[1009] Users list products based on the suggestions provided and receive sales results. Specifically, users list products according to the system's suggestions, and when a product sells, the result is sent to the server. The inputs are the server's suggestion information and the user's actions, and the output is sales result data.

[1010] Step 7:

[1011] The server uses sales results data as training data for a generative AI model to improve the model's prediction accuracy. Specifically, the server collects sales results data and uses it to retrain the generative AI model. The input is sales results data, and the output is an improved generative AI model and increased prediction accuracy.

[1012] Through the steps outlined above, users can obtain the optimal listing strategy, and it is expected that the overall buying and selling efficiency of the flea market application will improve.

[1013] (Application Example 1)

[1014] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1015] Modern flea market applications and e-commerce sites face the problem of users having difficulty obtaining the right information to efficiently buy and sell goods. In particular, the lack of means to predict the optimal listing time, price, and quantity of items to sell often leads to users missing out on opportunities and losses. Furthermore, the inefficiency of the user interface and the lack of accurate demand forecasting contribute to a decrease in overall sales efficiency.

[1016] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1017] In this invention, the server includes means for using a generating AI to diagnose data and demand for items listed on a flea market application, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI, means for collecting the results of items actually listed by the user and using them as training data for the generating AI, and means for providing a user interface via a smartphone application for collecting and analyzing data on an e-commerce site and proposing the optimal sales strategy. This enables users to list items at the most effective time and price, and to buy and sell items quickly and efficiently.

[1018] Definition of Terms

[1019] A "flea market application" is an online platform where users can freely list items for sale and buyers can conduct transactions directly with them.

[1020] "Generative AI" refers to a system that uses machine learning models and artificial intelligence to analyze data and generate information.

[1021] "Product name" refers to the identifying name of the product being offered for sale, and is the name that users use to identify the product.

[1022] "Size" refers to information that indicates the specific dimensions or scale of a product.

[1023] "Color" refers to information that indicates the colors a product possesses.

[1024] "Detailed information" refers to specific and detailed data about the product, including product name, size, color, etc.

[1025] "Analysis results" refer to the information obtained after the generating AI analyzes the listing data and demand data.

[1026] "Optimal listing time" refers to the most effective timing for listing an item.

[1027] "Price" refers to the amount a user sets when listing an item for sale.

[1028] "Quantity" refers to the number of items a user lists for sale.

[1029] "Collection" refers to the process of gathering information and data after a user has listed an item for sale.

[1030] "Training data" refers to a collection of historical data that a generative AI uses to improve its performance.

[1031] An "online shopping site" is an online platform for selling products over the internet.

[1032] "User interface" refers to the screens and means of operation that users use to interact with a system.

[1033] A "smartphone application" is a software program that runs on a smartphone.

[1034] "Data collection" is the process of gathering data from specific sources.

[1035] "Analysis" is the process of examining collected data and deriving useful information.

[1036] A "sales strategy" is a plan or method for effectively selling a product.

[1037] Modes for carrying out the invention

[1038] This invention relates to a system for users to efficiently buy and sell goods in flea market applications and online shopping sites. Specific embodiments thereof are described below.

[1039] (Overall system configuration)

[1040] The system primarily consists of a server and user terminals. The server analyzes data using a generative AI model, while the user terminals operate as smartphone applications. The following details each component of the system and its function.

[1041] Hardware to use

[1042] Server: Performs data collection, database management, and execution of generated AI models.

[1043] User device: Smartphone (device capable of running smartphone applications).

[1044] Software to use

[1045] Django: A Python-based web framework used for API servers and data transformation / correction.

[1046] SQLite: A database management system used to centrally manage collected data.

[1047] TensorFlow: A machine learning library used to build and run generative AI models.

[1048] Flutter: A smartphone application development framework used to build user interfaces.

[1049] Data flow and processing

[1050] 1. Data acquisition and format conversion

[1051] The server collects listing and purchase data through APIs for e-commerce sites and flea market applications. This includes information such as product name, price, category, listing time, and purchase time. The collected data is formatted using Django and stored in an SQLite database. Missing or outlier data are imputed or removed at this stage.

[1052] 2. Data analysis using generated AI

[1053] The server uses TensorFlow to build a generative AI model based on data stored in an SQLite database. This generative AI model analyzes past sales history and demand trend data to predict demand for a specific product. This prediction includes the optimal listing time, price, and quantity.

[1054] 3. Proposals based on user interface

[1055] Users enter product information (product name, size, color, etc.) for items they intend to list using a smartphone application built with Flutter. The entered information is sent to a server, and based on the analysis results of a generated AI model, the optimal listing time, price, and quantity are presented to the user.

[1056] 4. AI training through the collection and generation of feedback data

[1057] Based on the suggestions provided by the user, products are listed for sale, and as a result, sales performance data is fed back to the server. This feedback data is used as training data for the generating AI model, improving the accuracy of future predictive analyses.

[1058] Specific example

[1059] When a user uses a smartphone application to list old books for sale, they enter the book's information (title, author, condition, price) into the application. This information is sent to the server, where a generating AI calculates the optimal listing time (e.g., weekday evenings), appropriate price (around 2000 yen), and recommended quantity (depending on inventory) and suggests them to the user. When the user lists the item based on the suggestion, the sales performance is used to train the generating AI.

[1060] Examples of prompts to input into a generative AI model

[1061] The user enters the product data they plan to list in the following format:

[1062] Product name: Book name

[1063] Category: Books, Magazines

[1064] Price: 2000 yen

[1065] Listing timing: Weekday evenings

[1066] Based on this data, please analyze past purchase data from the e-commerce site and use AI to propose the optimal listing timing, appropriate price, and recommended quantity.

[1067] This allows users to list their products at the most effective time and price, enabling efficient buying and selling.

[1068] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1069] Program processing steps

[1070] Step 1: Data Collection

[1071] The server retrieves listing and purchase data via APIs for e-commerce sites and flea market applications.

[1072] Input: Data such as product name, price, category, listing time, and purchase time.

[1073] Process: Use Django to retrieve data from the API and convert it to the appropriate data format.

[1074] Output: A well-formatted dataset.

[1075] Step 2: Storing in the database

[1076] The server stores the collected data in a centralized management database. It also handles the processing of missing and outlier data.

[1077] Input: Data collected in Step 1.

[1078] Processing: Data is stored in a database using Django and SQLite, and missing or outlier values ​​are handled.

[1079] Output: Clean data centrally managed in a database.

[1080] Step 3: Data diagnosis using generated AI

[1081] The server uses a generative AI to perform data analysis based on the data stored in the SQLite database.

[1082] Input: A clean database.

[1083] Processing: Train a generative AI model using TensorFlow to forecast demand (calculating optimal listing time, appropriate price range, and recommended quantity).

[1084] Output: Demand forecast results (optimal listing time, appropriate price, recommended quantity).

[1085] Step 4: Entering product information via the user interface

[1086] Users enter product information for items they plan to list for sale using a smartphone application.

[1087] Input: Product name, size, color, price, and other detailed information.

[1088] Processing: Enter product information into the input form and send it to the server.

[1089] Output: The entered product information.

[1090] Step 5: Presentation of the Generative AI's Proposal Results

[1091] The server provides the user with prediction results generated by AI based on the entered product information.

[1092] Input: Entered product information and the demand forecast results generated by the AI.

[1093] Processing: The prediction results generated by the AI ​​are linked to product information and presented to the user.

[1094] Output: Suggestions for optimal listing time, appropriate price, and recommended quantity.

[1095] Step 6: Collect listing and sales data

[1096] Users list products based on suggestions from the generating AI, and sales results are collected by the server.

[1097] Input: Listing information, sales results (sales time, sales price, number of units sold, etc.).

[1098] Processing: After listing an item, the sales results are sent to the server and stored in the database.

[1099] Output: Feedback data (sales performance).

[1100] Step 7: Training the Generative AI

[1101] The server uses the collected feedback data as training data for the generated AI model.

[1102] Input: Feedback data.

[1103] Processing: Retrain the generative AI model using TensorFlow to improve prediction accuracy.

[1104] Output: Improved generative AI model.

[1105] In this way, users can list their products at the optimal time and price, enabling efficient buying and selling.

[1106] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1107] This invention is a system that enables users to efficiently buy and sell items by using AI to analyze listing data and demand data in a flea market application, and further combining this with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1108] The server collaborates with the provider of the flea market application to collect listing and purchase data via API. This data includes product name, price, category, listing time, and purchase time. The collected data is converted into an appropriate format for storage in a centralized management database.

[1109] Next, the server uses a generative AI to analyze this data. The generative AI analyzes past sales history and demand trends to make demand forecasts for each product. For example, it predicts the demand for "black T-shirts" in a particular season and calculates the appropriate price range and timing for sales.

[1110] Users access the system using a device (e.g., a smartphone or computer) through a dedicated app or web portal. Users enter detailed information about the items they intend to list (product name, size, color, etc.). The device then sends this information to the server.

[1111] When the server receives product information submitted by a user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. At the same time, the server uses an emotion engine to collect emotional data from the user's input and incorporates this information into the generating AI's training data. For example, if a user expresses joy when listing a "black T-shirt," the generating AI uses that emotional data for its analysis.

[1112] The server integrates the output of the emotion engine and the analysis results of the generative AI to present the user with the most suitable listing information. For example, it might present the user with results such as, "Listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate. Furthermore, based on the user's emotion data, a high level of satisfaction with this prediction can be expected."

[1113] Users list their items based on the suggested listing timing and price. The listing results (whether or not it sold, the timing and price of the sale) are fed back to the server. The server uses this feedback data as training data for its generating AI and sentiment engine to improve the accuracy of future predictive analysis.

[1114] For example, if a user lists a "black T-shirt" at the offered price and it sells quickly, that sales data and the user's sentiment data are re-inputted into the generative AI. This process continuously improves the generative AI's predictive model, enabling more accurate predictions.

[1115] By utilizing this system, users will be provided with optimal information for effectively buying and selling goods, which is expected to improve the overall efficiency of the flea market application and increase user satisfaction.

[1116] The following describes the processing flow.

[1117] Step 1:

[1118] The server collaborates with the provider of the flea market application to collect listing and purchase data via API. Specifically, it calls the API daily or at regular intervals to retrieve data such as product name, price, category, listing time, and purchase time. This data is received in JSON format.

[1119] Step 2:

[1120] The server converts the collected listing and purchase data into a format for storage in a centralized database. For example, it parses data received in JSON format to match the table structure of the relational database and maps it to fields such as listing date, product name, and price.

[1121] Step 3:

[1122] The server uses a generative AI to analyze this data. The server extracts historical listing and purchase data from the database and inputs it into the generative AI. Based on the historical data, the generative AI creates a demand forecasting model and analyzes demand trends for each product. For example, it predicts the demand for "black T-shirts" in a particular season and calculates the appropriate price range and sales timing.

[1123] Step 4:

[1124] Users access a dedicated app or web portal using their device and enter detailed information about the items they want to list. For example, if a user wants to list a "black T-shirt," they would enter the product name, category, size, color, and desired price. The device then sends this information to the server.

[1125] Step 5:

[1126] The device uses an emotion engine to collect user emotion data when the user enters detailed information. The device also uses a camera and voice recognition system to analyze the user's facial expressions and tone of voice to obtain emotion data.

[1127] Step 6:

[1128] The server receives product information and sentiment data sent by the user. The server incorporates the sentiment data into the training data of the generating AI and analyzes it by comparing it with past sentiment data.

[1129] Step 7:

[1130] The server calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. User sentiment data is also reflected in this. For example, it might derive a result such as, "Listing a black T-shirt on Saturday evening is most effective, and the appropriate price is 2,000 to 2,500 yen. Based on user sentiment data, a high level of satisfaction can be expected with this prediction."

[1131] Step 8:

[1132] The device displays to the user the analysis results and sentiment data from the generated AI received from the server. The user can then review suggestions for optimal listing timing and appropriate pricing on the app or web portal screen. Because the suggestions are tailored to the user's emotions, they are easier to understand intuitively.

[1133] Step 9:

[1134] The user lists their items based on the suggested listing timing and price. The device then feeds back the listing results (whether the item was sold, the timing of the sale, and the price) to the server.

[1135] Step 10:

[1136] The server uses the feedback data as training data for the generative AI and sentiment engine, and utilizes it to improve the accuracy of future predictive analyses. The collected feedback data is stored in the "Sales Data" table and used to retrain the generative AI. This allows the generative AI to continuously improve and build more accurate predictive models.

[1137] This series of processing steps is expected to provide users with optimal information for effectively buying and selling goods, improve the overall efficiency of the flea market application, and increase user satisfaction.

[1138] (Example 2)

[1139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1140] Traditional flea market applications struggle to predict the optimal timing and price for listing items to effectively buy and sell goods. Furthermore, they fail to consider user sentiment when presenting listings, leading to decreased user satisfaction. Additionally, the lack of sufficient utilization of past sales data and user feedback hinders improvements in analytical accuracy.

[1141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1142] In this invention, the server includes means for using a generating AI to diagnose data and demand for items listed on the flea market application; means for inputting detailed information such as the product name, size, and color of items listed by the user; means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generating AI; means for collecting the results of items actually listed by the user and using them as training data for the generating AI; and means for collecting user sentiment data, adding it to the training data of the generating AI, and presenting listing information that takes the user's sentiment into consideration based on the analysis results. As a result, users are provided with optimal information for effective buying and selling, improving the overall buying and selling efficiency of the flea market application and increasing user satisfaction.

[1143] A "flea market application" is an online platform where users can list and buy / sell goods.

[1144] "Generative AI" is a type of artificial intelligence technology that uses algorithms to recognize patterns based on data and perform predictions and generation.

[1145] "Diagnosis" is the process of analyzing collected data to identify specific patterns and trends.

[1146] "Listing data" refers to information that users provide when listing items on a flea market application, and includes the product name, price, size, color, and listing time.

[1147] "Demand data" is information obtained from buyer behavior and trends, and it shows what kinds of products are purchased, when, and at what prices.

[1148] A "user" is an individual or group that uses a flea market application to list or purchase goods.

[1149] "Emotional data" refers to information that quantifies or qualitatively evaluates a user's emotional state, and can be obtained, for example, through facial expression analysis or voice analysis.

[1150] An "emotion engine" is a software or hardware system used to analyze a user's emotional data.

[1151] "Listing time" refers to the specific date and time when a user lists an item on a flea market application.

[1152] "Price" refers to the amount set when a product is sold.

[1153] "Quantity" refers to the number of items listed on the flea market application.

[1154] "Feedback data" refers to data that records the results of users actually listing and selling products, and is used to improve the accuracy of future analyses and predictions.

[1155] This invention is a system that enables users to efficiently buy and sell by combining a generating AI that diagnoses listing data and demand data in a flea market application with an emotion engine that recognizes user emotions. A specific embodiment of this system is described in detail below.

[1156] The server first collaborates with the provider of the flea market application to collect listing and purchase data via API. This data includes product name, price, category, listing time, and purchase time. The collected data is stored in a centralized database and converted to an appropriate format. This conversion uses a Python script to format the data into JSON.

[1157] Next, the server passes the collected data to a generative AI model for analysis. The generative AI model is built using, for example, TensorFlow, and analyzes past sales history and external data sources (such as Google Trends). This allows it to predict demand for each product and calculate appropriate price ranges and sales timings. A concrete example would be predicting the demand for "black T-shirts" in a specific season and calculating appropriate price ranges and sales timings.

[1158] Users access this system using devices such as smartphones and computers. Access is done through a dedicated application or web portal. When a user enters product information (product name, size, color, etc.) for an item they plan to list, the device sends this information to the server. The information is sent via API Gateway and processed by an AWS Lambda function.

[1159] When the server receives product information sent by the user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generating AI. At the same time, it uses an emotion engine to collect user emotion data and adds this information as training data for the generating AI. The emotion engine uses OpenCV and IBM Watson's emotion analysis API to obtain emotion data by analyzing the user's facial expressions and tone of voice.

[1160] The analysis results might present users with information such as, "Listing a black T-shirt on Saturday evening is most effective, and a price of 2,000 to 2,500 yen is appropriate. Furthermore, emotional data suggests a high level of customer satisfaction." This notification is delivered via app push notifications or email.

[1161] Users list items based on the suggested listing timing and price. Listing results (success or failure of sales, timing and price of sales) are fed back to the server in real time via the device. This feedback data is used as training data for the generative AI and sentiment engine to improve the accuracy of future predictive analyses.

[1162] For example, if a user lists a "black T-shirt" at the offered price and it sells quickly, that sales data and the user's sentiment data are re-inputted into the generative AI. This process continuously improves the generative AI's predictive model, enabling more accurate predictions.

[1163] An example of a prompt message would be: "A user is trying to list an item using their smartphone. Build a system that uses a generative AI and an emotion engine to suggest the optimal listing timing and price." This system is expected to provide users with optimal information for effectively buying and selling items, improve the overall efficiency of the flea market application, and increase user satisfaction.

[1164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1165] The processing flow of this system's program

[1166] Step 1:

[1167] The server collects listing and purchase data from the provider of the flea market application via an API. This data includes product name, price, category, listing time, and purchase time. The collected data is converted to JSON format using a Python script. The input is data obtained from the application API endpoint, and the output is data in JSON format.

[1168] Step 2:

[1169] The server stores the collected data in a centralized database. This database uses common database management systems such as MySQL or PostgreSQL. Input is data converted to JSON format, and output is the format stored in the database.

[1170] Step 3:

[1171] The server passes the format-converted data to a generating AI model for analysis. TensorFlow is used for the generating AI model, which analyzes past trading history and external data sources (such as Google Trends). The input is data read from a database, and the output is the analysis results of demand forecasts and appropriate price ranges. Specifically, the server periodically executes queries to retrieve data and passes it to the TensorFlow model.

[1172] Step 4:

[1173] Users access the flea market application or web portal using their smartphone or computer. Users enter information about the items they intend to sell (product name, size, color, etc.). The device sends this information to the server via API Gateway. The input is the product information entered by the user, and the output is data sent to the server in JSON format.

[1174] Step 5:

[1175] When the server receives product information submitted by the user, it calculates the optimal listing time, appropriate price, and appropriate quantity based on the analysis results of the generated AI model. At the same time, it also collects user sentiment data using a sentiment engine. The sentiment engine uses OpenCV or IBM Watson's sentiment analysis API. The input is the user's listing information and sentiment data obtained in real time, and the output is the analysis results and optimal listing information based on sentiment. Specifically, the server passes the data from the user to the analysis module and obtains the analysis results.

[1176] Step 6:

[1177] The server integrates the analysis results of the generation AI model and the output of the emotion engine to present the user with the most suitable listing information. Notifications are sent via app push notifications and email. The input is the analysis results and emotion evaluation results, and the output is the optimal listing information sent to the user.

[1178] Step 7:

[1179] Users list items based on the suggested listing timing and price. The listing results (success or failure of the sale, timing and price of the sale) are fed back to the server in real time via the device. The input is the listing actually made by the user and its result, and the output is the feedback data sent to the server.

[1180] Step 8:

[1181] The server uses feedback data as training data for the generating AI model and the emotion engine to improve the accuracy of predictive analytics. The input is the feedback data, and the output is the updated parameters of the AI ​​model and the emotion engine. Specifically, the server periodically refeeds this data to the AI ​​model to retrain it.

[1182] This process provides users with optimal information for effectively buying and selling products, improving the overall efficiency of the system and increasing user satisfaction.

[1183] (Application Example 2)

[1184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1185] Current flea market applications face the challenge of not being able to effectively predict the optimal listing time, price, and quantity for items that users will be selling. Furthermore, there is a need to improve buying and selling efficiency by considering user emotions. This necessitates increasing user satisfaction and improving overall transaction efficiency.

[1186] The specific processing performed 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 using a generation AI to diagnose data and demand for items to be listed on the flea market application, means for inputting detailed information such as the product name, size, and color of items listed by the user, means for presenting the user with the optimal listing time, price, and quantity based on the analysis results of the generation AI, means for collecting the results of items actually listed by the user and using them as training data for the generation AI, means for collecting emotional data at the time of input using an emotional engine that recognizes the user's emotions, and means for adding the emotional data to the training data of the generation AI to make optimal suggestions. This makes it possible to provide optimal listing information that reflects the user's emotions, thereby improving buying and selling efficiency and user satisfaction.

[1187] A "flea market application" is an online platform where users can list items for sale and other users can purchase those items.

[1188] "Data" refers to various types of information necessary for analysis, such as product information, user behavior history, price, listing time, and purchase time.

[1189] "Demand" refers to the desire to purchase a particular product, and the level of demand influences buying and selling.

[1190] "Generative AI" is an artificial intelligence technology that predicts future demand and appropriate prices based on past data.

[1191] A "user" refers to an individual who uses a flea market application to list or purchase goods.

[1192] An "emotion engine" is a technology that recognizes a user's emotions and collects that data.

[1193] "Product name" refers to the name of the item being offered for sale.

[1194] "Size" refers to information about the dimensions and size of the product being offered for sale.

[1195] "Color" refers to the color of the product being offered for sale.

[1196] "Detailed information" refers to specific information used to describe the characteristics of the product being offered for sale.

[1197] "Listing time" refers to the time it takes for a user to list an item on a flea market application.

[1198] "Price" refers to the amount of money spent on the item being offered for sale.

[1199] "Quantity" refers to the number of items being offered for sale.

[1200] "Training data" refers to data that generative AI uses to improve the accuracy of its predictive models.

[1201] "Generative AI analysis results" refer to the predictions and optimizations derived by the generative AI after analyzing the data.

[1202] "Optimal listing information" refers to information about the optimal listing timing, price, and quantity presented to the user based on the analysis results of the generating AI and the output of the emotion engine.

[1203] This invention relates to a flea market application system that enables users to efficiently buy and sell goods, and its main components include a server, terminals, a generative AI, and an emotion engine. The objective of this system is to provide users with optimal listing information and improve overall transaction efficiency.

[1204] First, the server interacts with the provider of the flea market application via an API to collect listing and demand data. This data includes product name, price, category, listing time, and purchase time. The collected data is converted into an appropriate format and stored in a centralized management database.

[1205] Next, the server uses a generative AI to analyze past sales history and demand trends. The generative AI predicts demand for each product and calculates the optimal price range and timing for sale. For example, it predicts the demand for "black shirts" in a particular season and suggests an appropriate price and listing time.

[1206] Users access a dedicated application or web portal using their device and enter detailed information about the items they intend to list for sale (product name, size, color, etc.). While the entered information is sent to the server, a sentiment engine is also used to collect emotional data that the user exhibits while entering the information. For example, if a user expresses joy while entering the listing information for a "black shirt," that emotion is also recorded as data.

[1207] The server calculates the optimal listing time, price, and quantity based on the received product information and sentiment data, reflecting the analysis results of the generating AI. Simultaneously, it incorporates sentiment data obtained from the sentiment engine into the generating AI's training data, and uses this information to make optimal suggestions to the user. For example, it might present the user with results such as, "Listing a black shirt on Saturday evening is most effective, and a price of 2000 to 2500 yen is appropriate. Furthermore, judging from the user's sentiment data, a high level of satisfaction with this prediction can be expected."

[1208] Users list items based on these suggestions, and the results (whether they were sold, when they were sold, and at what price) are fed back to the server. The server uses this feedback data as training data for its generating AI and sentiment engine to improve the accuracy of future predictive analyses.

[1209] As a concrete example, when a user tries to list a black shirt for sale, the server, using AI-generated data, suggests the optimal listing timing and price range. Simultaneously, based on the user's sentiment data, it also predicts how satisfied the user will be with the suggestion. This system provides users with optimal information for effectively buying and selling goods.

[1210] The following sentences are suggested as examples of prompts:

[1211] "The most effective time to list a black shirt is Saturday evening, and a price of 2000 to 2500 yen is appropriate. Furthermore, based on user sentiment data, a high level of satisfaction can be expected with this prediction."

[1212] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1213] Step 1:

[1214] The server collaborates with the provider of the flea market application to collect listing and demand data via API. Input data includes product name, price, category, listing time, and purchase time. This data is converted to an appropriate format and stored in a centralized database. The output is the database entry after format conversion.

[1215] Step 2:

[1216] The server analyzes this collected data using a generative AI. Input data includes historical sales history and demand trends. The generative AI forecasts demand for each product and calculates the appropriate price range and sales timing. The output includes the demand forecast results, optimal price range, and sales timing.

[1217] Step 3:

[1218] Users access a dedicated application or web portal using their device and enter detailed information about the items they intend to list (product name, size, color, etc.). This input data is sent to the server. Furthermore, sentiment data displayed by the user during input is collected via a sentiment engine. The output consists of the user's detailed information and sentiment data.

[1219] Step 4:

[1220] The server calculates the optimal listing time, price, and quantity based on the received product information and sentiment data, reflecting the analysis results of the generating AI. The input data consists of the analysis results of the generating AI, detailed user information, and sentiment data. The output is the optimal listing information (listing time, price, and quantity) presented to the user.

[1221] Step 5:

[1222] The server integrates the analysis results from the generated AI with sentiment data to present the user with the most suitable listing information. The input data consists of the integrated analysis results and sentiment data. The output is specific suggestions displayed to the user (e.g., listing timing, price range, quantity, etc.).

[1223] Step 6:

[1224] Users list their products based on the optimal listing information provided by the server. The input is the listing information provided by the server, and the output is the actual listing result. This listing result (whether it was sold, when it was sold, and the price) is fed back to the server.

[1225] Step 7:

[1226] The server uses this feedback data as training data for its generative AI and sentiment engine. The input data is the user's listing results, and the output is updates and accuracy improvements for the generative AI model and sentiment engine. This improves the accuracy of the next predictive analysis.

[1227] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1228] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1230] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1231] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1232] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1233] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1234] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1235] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1236] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1237] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1238] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1239] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1240] 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.

[1241] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1242] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1243] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1244] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1245] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1246] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1247] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1248] The following is further disclosed regarding the embodiments described above.

[1249] (Claim 1)

[1250] A method for using AI to analyze data and demand generated from items listed on a flea market application,

[1251] A means for users to input detailed information such as the product name, size, and color of the item they are listing,

[1252] The means of providing users with the optimal listing time, price, and quantity based on the analysis results of the generating AI,

[1253] A method for collecting the results of actual user listings and using them as training data for generating AI,

[1254] A system that includes this.

[1255] (Claim 2)

[1256] The system according to claim 1, which collects data from a flea market application and stores it in a database.

[1257] (Claim 3)

[1258] The system according to claim 1, in which a generating AI analyzes data to predict the appropriate price range, sales timing, and popular sizes and colors.

[1259] "Example 1"

[1260] (Claim 1)

[1261] A method for diagnosing data and demand generated from items listed on a flea market application using an AI model,

[1262] A means for users to input detailed information such as the product name, size, and color of the item they are listing,

[1263] A means of presenting users with the optimal listing time, price, and quantity based on the analysis results of a generated AI model,

[1264] A means of collecting the results of actual user listings and using them as training data for a generative AI model,

[1265] A data formatting method that imputes missing values ​​and removes outliers,

[1266] A system that includes this.

[1267] (Claim 2)

[1268] The system according to claim 1, which collects data from a flea market application and stores it in a database.

[1269] (Claim 3)

[1270] The system according to claim 1, in which a generative AI model analyzes data to predict appropriate price ranges, sales timing, and popular sizes and colors.

[1271] "Application Example 1"

[1272] Claims

[1273] (Claim 1)

[1274] A method for using AI to analyze data and demand generated from items listed on a flea market application,

[1275] A means for users to input detailed information such as the product name, size, and color of the item they are listing,

[1276] A means of presenting users with the optimal listing time, price, and quantity based on the analysis results of the generating AI,

[1277] A method for collecting the results of actual user listings and using them as training data for generating AI,

[1278] A means of providing a smartphone application user interface for collecting and analyzing data on e-commerce sites and proposing optimal sales strategies,

[1279] A system that includes this.

[1280] (Claim 2)

[1281] The system according to claim 1, which collects data from a flea market application and stores it in a database.

[1282] (Claim 3)

[1283] The system according to claim 1, in which a generating AI analyzes data to predict the appropriate price range, sales timing, and popular sizes and colors.

[1284] "Example 2 of combining an emotion engine"

[1285] (Claim 1)

[1286] A method for using AI to analyze data and demand generated from items listed on a flea market application,

[1287] A means for users to input detailed information such as the product name, size, and color of the item they are listing,

[1288] A means of presenting users with the optimal listing time, price, and quantity based on the analysis results of the generating AI,

[1289] A method for collecting the results of actual user listings and using them as training data for generating AI,

[1290] A means of collecting user sentiment data, adding it to the training data of a generating AI, and presenting listing information that takes user sentiment into consideration based on the analysis results,

[1291] A system that includes this.

[1292] (Claim 2)

[1293] The system according to claim 1, which collects data from a flea market application and stores it in a database.

[1294] (Claim 3)

[1295] The system according to claim 1, in which a generating AI analyzes data to predict the appropriate price range, sales timing, and popular sizes and colors.

[1296] "Application example 2 when combining with an emotional engine"

[1297] (Claim 1)

[1298] A method for using AI to analyze data and demand generated from items listed on a flea market application,

[1299] A means for users to input detailed information such as the product name, size, and color of the item they are listing,

[1300] The means of providing users with the optimal listing time, price, and quantity based on the analysis results of the generating AI,

[1301] A method for collecting the results of actual user listings and using them as training data for generating AI,

[1302] A means of collecting emotional data at the time of input using an emotion engine that recognizes the user's emotions,

[1303] A method for generating optimal suggestions by incorporating emotional data into the training data of an AI,

[1304] A system that includes this.

[1305] (Claim 2)

[1306] The system according to claim 1, which collects data from a flea market application and stores it in a database.

[1307] (Claim 3)

[1308] The system according to claim 1, in which a generating AI analyzes data to predict the appropriate price range, sales timing, and popular sizes and colors. [Explanation of Symbols]

[1309] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A method for using AI to analyze data and demand generated from items listed on a flea market application, A means for users to input detailed information such as the product name, size, and color of the item they are listing, The means of providing users with the optimal listing time, price, and quantity based on the analysis results of the generating AI, A method for collecting the results of actual user listings and using them as training data for generating AI, A system that includes this.

2. The system according to claim 1, which collects data from a flea market application and stores it in a database.

3. The system according to claim 1, in which a generating AI analyzes data to predict the appropriate price range, sales timing, and popular sizes and colors.

Images