System

Abstract

A system is provided.SOLUTION: A system comprising: a data-collection unit that acquires item information from online stores, freemarkets, auction sites, and real stores; a data-preprocessing unit that cleanses and standardizes the acquired item information; a value-calculation unit that uses a generative AI to calculate a market value of an item based on the item information; a user-interface unit that provides the calculated market value to a user; and a feedback-collection unit that collects feedback from the user and uses the feedback to improve the system.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, value assessments vary across stores, online auctions, flea markets, pawn shops, and other locations, making it difficult for users to determine the legitimacy of value. Users are forced to rely on the arbitrary valuation of each provider, and must select information within a limited time frame. This increases the risk that users will make inappropriate value judgments. There is a need to solve this issue and enable users to make fair value judgments based on more information. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a data collection means for acquiring product information from various online stores, flea markets, auction sites, and brick-and-mortar stores, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generation AI to calculate the market value of a product based on the product information, a user interface means for providing the calculated market value to users, and a feedback collection means for collecting feedback from users and utilizing it to improve the system. The product information includes price information, product ratings, reviews, and transaction history, and the generation AI uses a machine learning model to score the product information and calculate a fair market value. This allows users to obtain a fair value assessment based on a variety of information, enabling more appropriate value judgments.

[0006] "Data collection means" refers to the means for obtaining product information from each online store, flea market, auction site, and brick-and-mortar store.

[0007] The "data preprocessing means" is a means for cleansing and standardizing the acquired product information.

[0008] "Generative AI" is artificial intelligence used to calculate the market value of a product based on collected and pre-processed product information.

[0009] A "value calculation method" is a method for using generation AI to score each indicator of product information and calculate a fair market value.

[0010] The "user interface means" refers to an interface for providing the calculated market value to the user.

[0011] "Feedback collection means" refers to a means for collecting feedback from users and using it to improve the system.

[0012] "Product information" is a general term for various information related to products, such as price information, product ratings, reviews, and transaction history.

[0013] "Price information" refers to information about the prices set for products at each online store or physical store.

[0014] "Product evaluation" is information about evaluations and evaluation scores of products from users and experts.

[0015] A "review" is information about impressions and evaluation comments written by users about a product.

[0016] "Transaction history" refers to information relating to the past buying and selling history and transaction data of a product.

[0017] A "machine learning model" is an algorithm or mathematical model used to score product information and determine fair market value. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0026] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0039] The present invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, and calculates and provides a fair market value. How the system program works is explained below with specific examples.

[0040] System Program

[0041] Data collection

[0042] server

[0043] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores, specifically price information, rating data, reviews, transaction history, etc. This allows the collection of the latest information from a variety of data sources.

[0044] Data Preprocessing

[0045] server

[0046] The server cleans the collected data, removing outliers and missing values, standardizing currency units, and removing duplicate data. It then standardizes the data to make it consistent. It also analyzes the condition of products to categorize them into categories such as "new," "like new," "good," and "used." The data is then indexed, allowing the information in the database to be quickly searched.

[0047] Value estimation using generative AI

[0048] server

[0049] The server uses a machine learning model to score each indicator of product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs).

[0050] User Interface

[0051] Terminal (user)

[0052] The user accesses the system through a terminal and inputs information about the product for which they want to know the value, such as the product name, model, and condition. The terminal then sends this information to the server in real time.

[0053] Delivering value and gathering feedback

[0054] server

[0055] Based on the information received from the user, the server calculates the fair market value of the item and sends the result back to the terminal. The terminal displays this calculation result to the user. After checking the displayed value assessment, the user can enter their thoughts on the assessment and requests for improvement. This feedback is sent back to the server and used to improve the system.

[0056] Specific examples

[0057] For example, suppose you want to know the market value of a used smartphone.

[0058] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from major online markets and flea markets.

[0059] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[0060] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of "15,000 yen" based on the price, valuation, and transaction history.

[0061] 4. The user enters the model and condition of the used smartphone from their own device.

[0062] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0063] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user. The user can use this value as a reference when considering buying or selling.

[0064] This allows users to quickly and accurately determine the fair market value based on data from a variety of sources, enabling them to make more appropriate value judgments.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it collects price information, product ratings, reviews, transaction history, etc. Since the data may be sent in different formats, a buffer area is set up to temporarily store the obtained data.

[0068] Step 2:

[0069] The server cleans the data stored in the buffer area. For example, it detects outliers (data with extremely high or low prices) and missing values ​​(data with no ratings) and deletes or corrects them. It also standardizes the currency unit of the data and converts it to Japanese yen. It also analyzes the content of text reviews and tags them as necessary.

[0070] Step 3:

[0071] The server stores the cleaned data in a database: price information in the Price table, rating data in the Rating table, reviews in the Review table, and transaction history in the Transaction table. At the same time, it runs an algorithm to classify the product condition into categories such as "new," "like new," "good," and "used."

[0072] Step 4:

[0073] The server trains a machine learning model based on the stored data. During this process, it assigns scores based on indicators such as price, ratings, reviews, and transaction history. For example, it calculates the balance of supply and demand based on the product's condition and past transaction history, and generates a score that evaluates the relative value of each product. The generating AI then combines these scores to calculate a fair market value.

[0074] Step 5:

[0075] The user inputs information about the product they want to know the value of from their device. For example, they provide information in input fields such as "product name," "model," and "condition." The information entered by the user is sent to the server in real time.

[0076] Step 6:

[0077] The server analyzes the product information received from the user and matches it with the corresponding product in its database. Once the match is complete, it recalculates the fair market value of the product based on past transaction data, reviews, and ratings. The recalculated value is converted into data that can be presented to the user in numerical and graphical formats.

[0078] Step 7:

[0079] The terminal displays the fair market value sent from the server to the user in the form of numbers, graphs, or rankings, making it easy for the user to understand.

[0080] Step 8:

[0081] Users can enter their thoughts on the provided market value and suggestions for improvement in a feedback form, including opinions on the accuracy of the displayed value assessment and requests for additional features.

[0082] Step 9:

[0083] The server receives feedback from users and stores it in a database. The collected feedback is periodically analyzed and used to improve the machine learning model and update the entire system. For example, if many users rate a particular product highly, that factor can be fed back into the machine learning model to improve the accuracy of value calculations.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] Currently, many online stores, flea markets, and auction sites often have different prices and ratings for the same product, making it difficult for consumers and businesses to determine its fair market value. Furthermore, manual data cleaning is required to address outliers and missing values, which is extremely time-consuming. Furthermore, there is a lack of a system that uniformly evaluates the condition of each product and provides it in a format that is easy for users to understand.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes a data collection means for acquiring product information from online stores, flea markets, auction sites, and brick-and-mortar stores, a data preprocessing means for cleaning and standardizing the acquired product information, and a value calculation means for scoring each indicator of the product information using a generative AI model to calculate a fair market value, enabling consumers and businesses to quickly and accurately grasp fair market value based on the latest data acquired from various information sources.

[0089] An "online store" is a website that sells products over the Internet.

[0090] A "flea market" is an online platform where individuals can buy and sell goods.

[0091] An "auction site" is an internet website that sells goods through competitive bidding.

[0092] A "brick and mortar store" is a store that sells products in a physical location.

[0093] "Product information" refers to data including product price information, evaluation data, reviews, transaction history, etc.

[0094] "Data collection means" refers to the methods and functions for obtaining product information from each source.

[0095] "Data preprocessing means" refers to methods and functions for cleaning and standardizing collected data.

[0096] A "generative AI model" refers to an artificial intelligence algorithm that learns from collected data and performs specific tasks.

[0097] "Valuation method" refers to a method or function for calculating the market value of a product using a generative AI model.

[0098] "User interface means" refers to the methods and functions by which a user accesses a system to input information and display results.

[0099] "Feedback collection means" refers to methods and functions for collecting feedback from users and using it to improve the system.

[0100] "Scoring" refers to evaluating data based on specific criteria or indicators and assigning a score.

[0101] "Fair market value" refers to the fair value of an item calculated based on data collected from various sources.

[0102] The present invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, and calculates and provides a fair market value. This system is implemented in the following steps.

[0103] First, the server is responsible for collecting data. It periodically calls APIs to obtain data from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it obtains product information such as price information, rating data, reviews, and transaction history. For example, it collects the latest price and rating data from major online markets every day.

[0104] Next, the server performs data preprocessing. It cleans the collected data and removes outliers and missing values. It also standardizes currency units and removes duplicate data. For example, it converts prices expressed in different currencies into Japanese yen and stores them in a consistent format in the database. It also categorizes the condition of products into categories such as "new," "like new," "good," and "used," and indexes them in the database, enabling quick data searches.

[0105] The server then uses the generative AI model to calculate the market value of each product. Specifically, it uses a machine learning model to score each product's indicators (price, rating, number of reviews, transaction frequency, etc.). The generative AI combines these scores to calculate the product's fair market value and converts the results into easy-to-understand formats (numbers and graphs). For example, products with high ratings and frequent transactions tend to have higher market values.

[0106] Users access the system using their own devices and enter information about the product they want to know the value of, such as "Product name: iPhone 11, Condition: Like new." The device then sends this information to the server in real time.

[0107] The server recalculates the market value of the item based on the information received from the user and returns the result to the device. The device can then display the calculation result to the user. For example, if the market value of an "iPhone 11, like new" is calculated to be "50,000 yen," the user's device will display "The fair market value is 50,000 yen." The user can use this market value as a reference when making a purchase or sale decision.

[0108] Furthermore, users can provide feedback on the displayed market value. For example, they can input their impressions such as "It sold for this price" or requests for improvement. This feedback is sent back to the server and used to improve the system.

[0109] As a result, the system of the present invention allows consumers and businesses to quickly and accurately determine fair market value based on the latest data obtained from a variety of sources, and the system can be continuously improved based on user feedback.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1: Data collection

[0112] server

[0113] The server runs scheduled jobs to retrieve product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it calls APIs to retrieve price information, rating data, reviews, and transaction history. For example, it collects the latest data from Amazon and other major marketplaces at 2:00 AM every day. The input is the data request from each site, and the output is the collected product information.

[0114] Step 2: Data Preprocessing

[0115] server

[0116] The server cleans the collected data by removing outliers and missing values, standardizing currency units, and deleting duplicate data. For example, it automatically filters out abnormally high or low price data and converts prices expressed in various currencies into a single currency unit. The input is the collected raw data, and the output is cleansed, clean data. It also categorizes the condition of products into categories such as "new," "like new," "good," and "used," generating data in a consistent format.

[0117] Step 3: Standardize and index the data

[0118] server

[0119] The server standardizes the cleaned data and stores it in a database. Specifically, it converts data such as price, rating, and number of reviews into a standard format. It also indexes the data to enable quick subsequent searches and analysis. The input is the cleansed data, and the output is standardized, indexed database entries.

[0120] Step 4: Valuation

[0121] server

[0122] The server uses a generative AI model to calculate the fair market value of the product based on the collected and pre-processed data. Specifically, it uses a machine learning algorithm to score each indicator (price, rating, number of reviews, transaction frequency, etc.) and then combines them to calculate the market value. The input is standardized and indexed database data, and the output is the calculated market value (e.g., in numerical or graphical form).

[0123] Step 5: Enter user data

[0124] User

[0125] The user inputs information about the product they want to know the value of through their device. Specifically, they enter the product name, model, condition, etc. into an input form. For example, the user might enter "Product name: iPhone 11, Condition: Like new." The input is the product information the user enters into the device, and the output is the request data sent to the server.

[0126] Step 6: Sending and Receiving Data

[0127] Terminal

[0128] The terminal transmits the information input by the user to the server in real time. The server receives the input information and performs appropriate processing. The input is the product information sent by the user, and the output is a data request to the server.

[0129] Step 7: Providing market value

[0130] server

[0131] The server calculates the market value of the product based on the information received from the user and returns the result to the device. For example, if the market value of an "iPhone 11, like new" is calculated to be "50,000 yen," the result is sent to the device. The input is the product information sent by the user, and the output is the calculated market value data.

[0132] Step 8: Display Market Value

[0133] Terminal

[0134] The terminal displays the calculation results received from the server to the user. Specifically, it displays a message on the screen such as "The fair market value is 50,000 yen." The input is the market value data returned from the server, and the output is the information displayed to the user.

[0135] Step 9: Gather feedback

[0136] User

[0137] The user provides feedback on the displayed market value. Specifically, the user enters their thoughts on the evaluation and requests for improvement into an input form. For example, they provide feedback such as "It sold for this price." The input is the feedback information that the user enters into the terminal, and the output is the feedback data sent to the server.

[0138] Step 10: Use feedback

[0139] server

[0140] The server collects feedback received from users and uses it to improve the system. Specifically, it analyzes the feedback data and makes necessary adjustments to the algorithm or improves the entire system. The input is the feedback data sent by the users, and the output is the improved system function.

[0141] (Application example 1)

[0142] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0143] Currently, when users buy or sell products, it is difficult to determine whether the product has a fair market value. In addition, price and valuation information provided by different online and physical stores is inconsistent, making it difficult for users to make appropriate value judgments. Therefore, a system that allows users to quickly and accurately determine market value is needed.

[0144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0145] In this invention, the server includes a data collection means for acquiring product information from online stores, flea markets, auction sites, and physical stores, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generative AI model to calculate the market value of the product based on the product information, a user interface means for providing the calculated market value to the user, and a feedback collection means for collecting feedback from the user and utilizing it to improve the system. This allows the user to quickly and accurately know the fair market value based on data from various information sources.

[0146] "Data collection means" refers to the means for obtaining product information from each online store, flea market, auction site, and physical store.

[0147] "Data preprocessing means" refers to means for cleansing (cleansing: removing outliers and missing values ​​in data) and standardizing (standardizing data format and units) the acquired product information.

[0148] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to calculate the market value of a product based on product information.

[0149] A "value calculation means" is a means for calculating the market value of a product based on product information using a generative AI model.

[0150] The "user interface means" is an interface for providing the calculated market value to the user, and typically refers to a smartphone application or a web page.

[0151] "Feedback collection means" refers to a means for collecting feedback from users and using it to improve the system.

[0152] "Price data" is price information for each product.

[0153] "Product evaluation" is evaluation information regarding the quality and performance of a product.

[0154] A "review" is an evaluation or comment posted by a user based on their experience using a product.

[0155] "Transaction history" is data showing the past buying and selling history and trading performance of a product.

[0156] "Scoring" is the process of calculating a product's evaluation score based on various evaluation indicators.

[0157] The following describes in detail the mode for implementing this invention. This invention is a system that organizes and analyzes product information obtained from various online stores, flea markets, auction sites, and physical stores, and calculates a fair market value using a generative AI model. The implementation method of this system is described in detail below.

[0158] Hardware and Software Configuration

[0159] 1. Server:

[0160] The server is the central function that performs all major tasks, including data collection, preprocessing, value calculation, result delivery, and feedback collection. The main technology stack used is Python, Flask, scikit-learn, Pandas, and Requests.

[0161] 2. User Device:

[0162] A smartphone or other device that acts as an interface for users to operate applications. The user interface is implemented in a browser or mobile application.

[0163] Detailed explanation of the process

[0164] 1. Data Collection:

[0165] The server periodically retrieves product information from online stores, flea markets, auction sites, and physical stores by calling public APIs. The collected data mainly includes price data, product ratings, reviews, and transaction history.

[0166] 2. Data Preprocessing:

[0167] The acquired data is cleansed and standardized on the server. Outliers and missing values ​​are removed, currency units are standardized, and duplicate data is deleted. The data is also classified according to the product's condition. The standardized data is then indexed into a database, enabling quick searches.

[0168] 3. Value estimation using generative AI models:

[0169] The server uses the collected and pre-processed data to train a generative AI model (machine learning algorithm) to calculate the fair market value of the product, which is scored based on indicators such as price, ratings, number of reviews, and transaction frequency.

[0170] 4. User Interface:

[0171] The user terminal communicates with the server via a user interface. The user inputs the product information they want to know (e.g., product name, model, condition, etc.), and the information is sent to the server in real time. The server calculates the market value and returns the result to the user terminal.

[0172] 5. Feedback Collection and System Improvement:

[0173] Users can check the displayed market value assessment and enter their thoughts and suggestions for improvement. This feedback is sent back to the server and used to improve the system.

[0174] Specific examples

[0175] For example, if a user wants to know the market value of a used smartphone, they can enter and submit the following information on their device:

[0176] Price: 15,000 yen

[0177] Rating: 4.5

[0178] Number of reviews: 50

[0179] Trading Frequency: 10

[0180] The server receives this information, calculates the market value using a generative AI model, and returns the result to the user's device: "The fair market value of this smartphone is 16,000 yen."

[0181] This allows users to quickly and accurately determine the fair market value based on data from different sources, enabling them to make appropriate value judgments.

[0182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0183] Step 1: Data collection

[0184] The server periodically retrieves product information from various online stores, flea markets, auction sites, and physical stores. Specifically, it uses APIs to access these sources and collect data such as price data, product ratings, reviews, and transaction history. For example, it calls an API endpoint and receives a JSON-formatted response. The input is the API URL, and the output is the retrieved product information.

[0185] Step 2: Data Preprocessing

[0186] The server cleanses and standardizes the collected product information. This involves removing outliers and missing values, standardizing currency units, and deleting duplicate data. It also classifies the product condition into categories such as "new," "like new," "good," and "used." Specifically, it uses the Pandas library to remove NaN values ​​and standardizes currency units through string manipulation. The input is the product information obtained in step 1, and the output is the cleansed and standardized data.

[0187] Step 3: Data Standardization

[0188] To standardize the cleansed data, the server converts each attribute (price, rating, etc.) to a certain scale. Specifically, it uses scikit-learn's StandardScaler. This allows attributes with different units to be compared on a common scale. The input is the data processed in step 2, and the output is the standardized data.

[0189] Step 4: Training the generative AI model

[0190] The server uses the standardized data to train a generative AI model. Specifically, it trains a machine learning model (e.g., a linear regression model) using features such as the product price, rating, number of reviews, and transaction frequency. The input is the standardized data obtained in step 3, and the output is the trained generative AI model.

[0191] Step 5: Receiving User Input

[0192] The user inputs information about the target product (price, rating, number of reviews, transaction frequency, etc.) from a terminal (such as a smartphone). The terminal collects this information and sends it to the server in real time. The input is the product information entered on the terminal, and the output is the data sent to the server.

[0193] Step 6: Calculate market value

[0194] The server calculates the market value of the product using a trained generative AI model based on the information received from the user. Specifically, it inputs the features entered by the user into the model and predicts the market value. The inputs are the data sent by the user and the generative AI model, and the output is the calculated market value.

[0195] Step 7: Deliver value

[0196] The server returns the calculated market value to the user's terminal. The terminal receives the market value and displays it to the user through a user interface, whose input is the market value calculated in step 6 and whose output is the market value information displayed on the user's terminal.

[0197] Step 8: Gather feedback

[0198] The user inputs their evaluation impressions and requests for improvement based on the displayed market value. The terminal sends this feedback to the server. The server collects this feedback and uses it to improve the system. The input is the user's feedback information, and the output is the collected feedback data.

[0199] Through the above steps, the present invention allows users to quickly and accurately determine the fair market value of an item.

[0200] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0201] This invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, calculates and provides a fair market value, and by combining it with an emotion engine that recognizes user emotions, achieves more accurate value provision and feedback analysis. Below, we will explain how the system program works, using specific examples.

[0202] System Program

[0203] Data collection

[0204] server

[0205] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores, specifically price information, rating data, reviews, transaction history, etc. This allows the collection of the latest information from a variety of data sources.

[0206] Data Preprocessing

[0207] server

[0208] The server cleans the collected data, removing outliers and missing values, standardizing currency units, and removing duplicate data. It then standardizes the data to make it consistent. It also analyzes the condition of products to categorize them into categories such as "new," "like new," "good," and "used." The data is then indexed, allowing the information in the database to be quickly searched.

[0209] Value estimation using generative AI

[0210] server

[0211] The server uses a machine learning model to score each indicator of product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs).

[0212] User Interface

[0213] Terminal (user)

[0214] The user accesses the system through a terminal and inputs information about the product for which they want to know the value, such as the product name, model, and condition. The terminal then sends this information to the server in real time.

[0215] Delivering value and gathering feedback

[0216] server

[0217] Based on the information received from the user, the server calculates the fair market value of the item and returns the result to the terminal. The terminal then displays this calculation result to the user. After checking the displayed value assessment, the user can enter their thoughts on the assessment and requests for improvement. This feedback is sent back to the server and used to improve the system. In addition, the emotion engine uses text analysis and voice recognition technology on the user's feedback to recognize the user's emotions.

[0218] Emotion recognition by emotion engine

[0219] server

[0220] The server recognizes the user's emotions by analyzing the text and voice data of the feedback using an emotion engine. Text analysis identifies positive, negative, and neutral emotions from the user's written feedback. It also uses speech recognition technology to understand emotional nuances from the tone, speed, and intonation of the voice.

[0221] Feedback analysis and system improvement

[0222] server

[0223] The server stores the user emotion data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotion data is reflected in improvements to the system. For example, if many users express negative emotions toward a particular product, the system may consider adjusting the evaluation algorithm for that product.

[0224] Specific examples

[0225] For example, consider the case where a user wants to know the market value of a used smartphone.

[0226] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from major online markets and flea markets.

[0227] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[0228] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of "15,000 yen" based on the price, valuation, and transaction history.

[0229] 4. The user enters the model and condition of the used smartphone from their own device.

[0230] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0231] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user.

[0232] 7. Users can enter their thoughts on the value assessment and requests for improvements in the feedback form. They can provide feedback via text and voice.

[0233] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if there are a lot of negative emotions, it adjusts the evaluation algorithm.

[0234] This allows users to quickly and accurately determine fair market value based on data from a variety of sources, and the system is continuously improved through feedback analysis based on user sentiment.

[0235] The processing flow will be explained below.

[0236] Step 1:

[0237] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it collects price information, product ratings, reviews, and transaction history. This information is temporarily stored in a buffer area.

[0238] Step 2:

[0239] The server cleans the data stored in the buffer area. This includes detecting and deleting or correcting outliers (e.g., extreme prices) and missing values ​​(e.g., data with no evaluations). At the same time, it unifies different currency units and converts them to Japanese yen.

[0240] Step 3:

[0241] The server stores the cleaned data in a database: price information in the Price table, rating data in the Rating table, reviews in the Review table, and transaction history in the Transaction table. It also runs an algorithm to classify the condition of the products into categories of "new," "like new," "good," and "used."

[0242] Step 4:

[0243] The server uses machine learning models to score each metric of the stored product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI then combines these scores to calculate the fair market value of the product, which is then converted into numerical and graphical formats.

[0244] Step 5:

[0245] The user uses the device's user interface to input information about the product for which they want to know the value. Input fields include the product name, model, and condition. The information entered by the user is sent to the server in real time.

[0246] Step 6:

[0247] The server analyzes the product information received from the user and compares it with the corresponding product data in the database. Based on the comparison results, it recalculates the fair market value. This recalculated market value is converted into data to be sent to the terminal.

[0248] Step 7:

[0249] The terminal displays the fair market value sent from the server to the user in the form of numbers, graphs, or rankings, making it easy for the user to understand.

[0250] Step 8:

[0251] Users can enter their thoughts on the displayed market value and requests for improvement in a feedback form. Feedback can be given not only by text but also by voice. Once feedback is complete, the device sends the data to the server.

[0252] Step 9:

[0253] The server receives the feedback data sent by the user and analyzes it with an emotion engine. Text analysis is used to identify positive, negative, neutral, and other emotions from the feedback text. At the same time, voice data is analyzed to understand the user's emotions from the tone, speed, and intonation of the voice.

[0254] Step 10:

[0255] The server stores the recognized emotion data in a database and periodically analyzes it. The analysis results are used to improve the machine learning model and update the system as a whole. For example, if many users express negative emotions in rating a particular product, the rating algorithm for that product will be revised.

[0256] This detailed flow enables the present invention to provide fair market value based on diverse data and continuously improve the system through feedback analysis that takes into account user sentiment.

[0257] Example 2

[0258] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0259] Conventional market value calculation systems did not adequately address inconsistencies, duplications, or missing product information obtained from a wide variety of data sources, resulting in inaccurate market values. Furthermore, user feedback was not fully utilized to improve the system, resulting in a lack of improvement in the quality of the user experience. Furthermore, there was a lack of technology to recognize user emotions and reflect them in system improvements, making it difficult to increase user satisfaction.

[0260] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0261] In this invention, the server includes a data collection means for acquiring product information from various online stores, online markets, e-commerce platforms, and physical stores, a data preprocessing means for cleaning and standardizing the acquired product information, and a value calculation means using generative AI to calculate the market value of the product based on the product information. This makes it possible to organize inconsistent data from various sources into a consistent form and calculate a fair market value using a machine learning model. Furthermore, by applying a user interface means for users to input product information and provide the calculated market value, an emotion engine for collecting user feedback and recognizing the emotion of the feedback, and a feedback collection means for improving the system based on the collected feedback, user feedback can be effectively utilized to improve the system.

[0262] An "online store" is an e-commerce platform that sells goods and services over the Internet.

[0263] An "online market" is an online commercial platform where multiple sellers come together to offer products and services.

[0264] An "e-commerce platform" is an online system for buying and selling goods and services electronically.

[0265] A "physical store" is a physical building where goods or services are sold in person.

[0266] "Data collection means" means the mechanism or technology used to obtain product information from various data sources.

[0267] "Data pre-processing means" refers to the process of cleaning and standardizing acquired data.

[0268] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0269] A "value calculation means" is a method or system for calculating the market value of a commodity based on commodity information.

[0270] The "user interface means" is an interface through which a user interacts with the system, and is a means for inputting data and displaying output.

[0271] A "feedback collection means" is a method or system for collecting user ratings and opinions.

[0272] An "emotion engine" is a technology for analyzing and recognizing emotions from user feedback data.

[0273] A "machine learning model" is an artificial intelligence algorithm that learns from training data and makes predictions or classifications based on new data.

[0274] This invention is a system that collects product information from online stores, online markets, e-commerce platforms, and physical stores, calculates and provides fair market value, and by combining it with an emotion engine that recognizes user emotions, it achieves more accurate value provision and feedback analysis.

[0275] System configuration

[0276] The system uses the following hardware and software components:

[0277] server

[0278] Data collection methods

[0279] Data preprocessing measures

[0280] Value calculation method using generative AI

[0281] Feedback collection methods

[0282] Emotion Engine

[0283] Terminal (user device)

[0284] User Interface Means

[0285] Data collection methods

[0286] The server collects product information from online stores, online markets, e-commerce platforms, and physical stores using common API endpoints. For example, to get information from Amazon, eBay, and local online markets, it calls the API endpoints of each platform. Data collection is scheduled periodically, and the latest data is retrieved regularly.

[0287] Data preprocessing measures

[0288] The server cleans and standardizes the acquired data. It removes outliers and missing values, standardizes currency units, and deletes duplicate data. Specifically, it uses the Python Pandas library to clean and standardize the data. It also analyzes the product condition to classify it into "new," "like new," "good," and "used."

[0289] Value calculation method using generative AI

[0290] The server uses a machine learning model to score product information and calculate a fair market value. This uses machine learning libraries such as TensorFlow. Variables such as price information, product ratings, number of reviews, and transaction frequency are used as inputs to generate the AI.

[0291] User Interface Means

[0292] Users access the system using their own devices (such as smartphones or computers) and enter product information. For example, they enter information such as "product name," "model," and "condition" in real time. The entered information is immediately sent to the server.

[0293] Delivering value and gathering feedback

[0294] The server analyzes the product information received from the user and calculates a fair market value. The result is sent back to the terminal, which displays it to the user. The user checks the displayed market value and enters their thoughts and requests for improvement in a feedback form. The feedback entered by the user is sent back to the server and analyzed by the emotion engine.

[0295] Emotion Engine

[0296] The server analyzes the feedback collected from users using an emotion engine. Text analysis is used to identify positive, negative, or neutral emotions from the feedback written by the user. Speech recognition technology is also used to understand emotional nuances from the tone and intonation of the voice.

[0297] Feedback analysis and system improvement

[0298] The server stores the emotional data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotional data is reflected in improvements to the system. For example, if many users express negative emotions about a particular product, the system may consider adjusting the evaluation algorithm for that product.

[0299] Specific examples

[0300] For example, consider the case where a user wants to know the market value of a used smartphone.

[0301] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from each online market.

[0302] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[0303] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of 15,000 yen based on the price, valuation, and transaction history.

[0304] 4. The user enters the model and condition of the used smartphone from their own device.

[0305] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0306] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user.

[0307] 7. Users can enter their thoughts on the value assessment and requests for improvement in the feedback form. They can provide feedback via text and voice.

[0308] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if there are a lot of negative emotions, it adjusts the evaluation algorithm.

[0309] The system allows users to quickly and accurately determine fair market value based on data from a variety of sources, and feedback analysis based on user sentiment allows for continuous improvement of the system.

[0310] Prompt Sentence Examples

[0311] The following prompt sentences are used to provide examples of how to input specific system behavior into the model:

[0312] "You are developing a program to calculate the market value of smartphones based on price information collected from online stores, flea markets, and auction sites. Using the information below, explain how you would collect, preprocess, and analyze the data to calculate a fair market value. Then, explain how you would improve the system based on user feedback."

[0313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0314] Step 1: Data collection

[0315] The server retrieves product information from various online stores, online markets, e-commerce platforms, and physical stores. This process involves sending a request to an API endpoint, such as "GET / products?category=electronics&condition=used" to retrieve price information, rating data, reviews, transaction history, etc. The input is the API request, and the output is the response data with product information.

[0316] Specifically, the server sends a "GET / products" request to Amazon's API and stores the received data.

[0317] Step 2: Data Preprocessing

[0318] The server cleans and standardizes the acquired product information. In this step, outliers and missing values ​​are removed, currency units are standardized, and duplicate data is deleted. The Python Pandas library is used for data frame operations. The input is the product information data acquired in step 1, and the output is the cleaned and standardized product information data.

[0319] Specifically, the server uses Pandas to remove records with zero prices in the data frame and convert all currency units to USD.

[0320] Step 3: Value estimation using generative AI

[0321] The server uses a machine learning model to score product information and calculate market value. Standardized product information data obtained through data preprocessing is used as input. Generative AI (such as TensorFlow) is used to score price, rating, number of reviews, transaction frequency, etc. to calculate a fair market value. The output is the market value of each product.

[0322] Specifically, the server loads the TensorFlow model, inputs the price, rating, and number of reviews, and calculates the market value as "15,000 yen."

[0323] Step 4: Entering information in the user interface

[0324] The user inputs information about the product they wish to have appraised from their terminal. For example, they input information such as "product name," "model," and "condition," and this information is sent to the server in real time. The input is information from the user's terminal, and the output is data sent to the server.

[0325] Specifically, the user enters "iPhone 11, used, good condition" into the device's web form and clicks the submit button.

[0326] Step 5: Deliver value and gather feedback

[0327] The server calculates the market value based on the information from the user and returns the result to the terminal. The terminal displays this result to the user. The user checks the displayed market value and enters their thoughts and requests for improvement in a feedback form. The input is the market value calculation by the server and the user's feedback, and the output is the market value display and feedback transmission to the user.

[0328] Specifically, the server calculates the market value of "15,000 yen" and returns it to the terminal, which then displays it to the user. The user then enters "The accuracy is high and I'm satisfied" in the feedback form.

[0329] Step 6: Emotion Recognition with the Emotion Engine

[0330] The server analyzes the user feedback with an emotion engine to recognize emotions. The input is the user feedback data, and the output is the emotion analysis result. Text analysis and speech recognition technologies are used to identify the user's emotions.

[0331] Specifically, the server uses an NLP library to recognize positive emotions from feedback such as "I'm happy."

[0332] Step 7: Feedback analysis and system improvement

[0333] The server stores the emotion data analyzed by the emotion engine in a database and periodically analyzes it. The input is the emotion analysis results, and the output is a proposal for improving the system. Based on the analysis results, issues with the system are identified and the system is improved.

[0334] Specifically, the server analyzes the feedback emotion data every month and adjusts the algorithm when many users show negative emotions.

[0335] The above is a concrete explanation of the program processing of this system, broken down into steps.

[0336] (Application example 2)

[0337] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0338] In recent years, with the diversification of content distribution services, users are required to select what to watch from a vast amount of content. However, the lack of reliable information for users is a problem, as it is difficult to fairly grasp the ratings and market value of content. In addition, there is a lack of personalized recommendations based on viewing history and feedback, and innovations are needed to improve the user experience.

[0339] The identification processing by the identification 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 a data collection means for acquiring product information from each content distribution service, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generative AI for calculating the market value of the product based on the product information, a user interface means for providing the calculated market value to the user, a feedback collection means for collecting feedback from the user and using it to improve the system, an emotion analysis means for analyzing the user feedback and recognizing the user's emotions, and a means for improving the system based on the analyzed emotion data. This makes it easier for users to obtain reliable market value information and enables personalized content recommendations based on individual preferences.

[0340] The "data collection means" is a part that has the function of acquiring product information from each content distribution service.

[0341] The "data preprocessing means" is a part that has the function of cleansing and standardizing the acquired product information.

[0342] The "value calculation means" is the part that has the function of calculating the market value of a product based on product information using a generation AI.

[0343] The "user interface means" is a part having a function of providing the calculated market value to the user.

[0344] The "feedback collection means" is a part that has the function of collecting feedback from users and utilizing it to improve the system.

[0345] The "emotion analysis means" is a part that has the function of analyzing user feedback and recognizing the user's emotions.

[0346] The "means for improving the system" is a part that has the function of improving the system based on the analyzed emotion data.

[0347] "Product Information" refers to information related to the content, such as number of views, ratings, reviews, and viewing history.

[0348] "Generative AI" refers to artificial intelligence technology used to calculate market value based on product information.

[0349] The present invention is a system that acquires product information from a content distribution service, calculates a fair market value based on that information, provides it to users, and analyzes user feedback to improve the system. Below, we will explain how the program for this system works, using specific examples.

[0350] System Program

[0351] Data collection

[0352] server

[0353] The server periodically calls APIs to obtain product information from each content distribution service (e.g., video services, music distribution platforms, etc.). Specifically, the information being obtained includes the number of views, ratings, reviews, and viewing history. This allows the latest information to be collected from a variety of data sources.

[0354] Data Preprocessing

[0355] server

[0356] The server cleans and standardizes the collected data. This includes removing outliers and missing values, standardizing the data, normalizing view counts, standardizing rating scores, and analyzing the text of reviews. The data is then indexed, allowing for quick searches of information in the database. The software used for this is the Python libraries Pandas and NumPy.

[0357] Value estimation using generative AI

[0358] server

[0359] The server uses a machine learning model to score each indicator of product information (number of views, rating, number of reviews, viewing frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs). The software used here includes TensorFlow and Scikit-Learn.

[0360] User Interface

[0361] Terminal (user)

[0362] Users access the service through their device (smartphone, PC, smart TV, etc.) and enter information about the content they want to know the value of, such as the content name, platform, and rating. The device then sends this information to the server in real time.

[0363] Delivering value and gathering feedback

[0364] server

[0365] Based on the information received from the user, the server calculates the fair market value of the content and sends the result back to the terminal. The terminal displays this calculation result to the user. The user can check the displayed value assessment and then enter their thoughts on the assessment or requests for improvement. This feedback is sent back to the server and used to improve the system.

[0366] Emotion recognition by emotion engine

[0367] server

[0368] The server recognizes the user's emotions by analyzing the text and voice data of the feedback with an emotion engine. It uses the Natural Language Toolkit (NLTK) for text analysis and Google Cloud Speech-to-Text for voice recognition. This allows it to identify positive, negative, or neutral emotions from the user's description.

[0369] Feedback analysis and system improvement

[0370] server

[0371] The server stores the user's emotional data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotional data is reflected in improvements to the system. For example, if many users have a positive reaction to a particular piece of content, the server may consider increasing the frequency with which that content is recommended.

[0372] Specific examples

[0373] For example, suppose a user wants to know the market value of a movie.

[0374] 1. The server collects movie view counts, ratings, reviews, and viewing history from major content distribution services.

[0375] 2. The server cleans and standardizes the collected data, normalizing view counts and standardizing rating scores.

[0376] 3. The server uses a machine learning model to score the metrics of each piece of content. The AI ​​generator calculates a fair market value of 8.5 / 10 based on the number of views, ratings, and reviews.

[0377] 4. The user enters the movie title and platform on their device.

[0378] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0379] 6. The terminal displays the fair market value received from the server, "8.5 / 10", to the user.

[0380] 7. Users can enter their thoughts on the value assessment and requests for improvements in the feedback form. They can provide feedback via text and voice.

[0381] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if many users express positive emotions, the system adjusts its recommendation algorithm based on that information.

[0382] Prompt Sentence Examples

[0383] Title: Inception

[0384] Platform: Streaming Service

[0385] Rating: 9.5

[0386] User Reviews: Positive

[0387] User Comments: "Amazing plot and visual effects!"

[0388] Calculate fair market value and provide summary score.

[0389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0390] Step 1: Data collection

[0391] The server periodically collects product information from each content distribution service (video service, music distribution platform, etc.) via API. Specifically, it obtains information such as the number of views, ratings, reviews, and viewing history. The input is the response data from the API, and the output is the collected raw data.

[0392] Step 2: Data Preprocessing

[0393] The server cleans and standardizes the data collected in step 1. Data cleaning involves removing outliers and missing values. Next, it normalizes the number of views and rating scores, and performs text analysis on the reviews to categorize them. The input is raw data, and the output is cleansed and standardized data.

[0394] Step 3: Index the data

[0395] The server indexes the preprocessed data, allowing for quick searches of information in the database. The software used is MySQL or MongoDB. The input is the preprocessed data, and the output is the indexed data.

[0396] Step 4: Valuation

[0397] The server uses a machine learning model to score each indicator of product information (number of views, rating, number of reviews, viewing frequency, etc.). A generative AI model combines these scores to calculate a fair market value. The software used is TensorFlow and Scikit-Learn. The input is the indexed data, and the output is the calculated market value.

[0398] Step 5: Provide a user interface

[0399] The terminal provides an interface for users to input information about the content they want to know the value of. The user inputs information such as the "content name," "platform," and "rating," and the terminal sends this information to the server. The input is the information entered by the user, and the output is the data to be sent to the server.

[0400] Step 6: Delivering valuation results

[0401] The server calculates the market value based on the information received from the user and returns the result to the terminal. The terminal displays the calculation result to the user. The input is the user information and the calculation result, and the output is the market value displayed to the user.

[0402] Step 7: Gather feedback

[0403] The terminal allows the user to input their thoughts and requests for improvement about the displayed market value into a feedback form. The user provides feedback by text or voice, and the terminal sends this information to the server. The input is the user's feedback, and the output is data to be sent to the server.

[0404] Step 8: Sentiment Analysis

[0405] The server analyzes the feedback text and audio data using an emotion engine. It uses the Natural Language Toolkit (NLTK) and Google Cloud Speech-to-Text to identify the user's emotions. The input is the feedback data, and the output is the analysis result.

[0406] Step 9: System Improvement

[0407] The server stores the analyzed emotional data in a database and periodically analyzes it. This information is used to improve the system. For example, it adjusts the algorithm to prioritize recommending content with a high number of positive reactions. The input is emotional data, and the output is improved system parameters.

[0408] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0409] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0410] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0411] [Second embodiment]

[0412] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0413] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0414] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0415] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0416] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0417] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0418] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0419] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0420] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0421] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0422] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0423] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0424] The present invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, and calculates and provides a fair market value. How the system program works is explained below with specific examples.

[0425] System Program

[0426] Data collection

[0427] server

[0428] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores, specifically price information, rating data, reviews, transaction history, etc. This allows the collection of the latest information from a variety of data sources.

[0429] Data Preprocessing

[0430] server

[0431] The server cleans the collected data, removing outliers and missing values, standardizing currency units, and removing duplicate data. It then standardizes the data to make it consistent. It also analyzes the condition of products to categorize them into categories such as "new," "like new," "good," and "used." The data is then indexed, allowing the information in the database to be quickly searched.

[0432] Value estimation using generative AI

[0433] server

[0434] The server uses a machine learning model to score each indicator of product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs).

[0435] User Interface

[0436] Terminal (user)

[0437] The user accesses the system through a terminal and inputs information about the product for which they want to know the value, such as the product name, model, and condition. The terminal then sends this information to the server in real time.

[0438] Delivering value and gathering feedback

[0439] server

[0440] Based on the information received from the user, the server calculates the fair market value of the item and sends the result back to the terminal. The terminal displays this calculation result to the user. After checking the displayed value assessment, the user can enter their thoughts on the assessment and requests for improvement. This feedback is sent back to the server and used to improve the system.

[0441] Specific examples

[0442] For example, suppose you want to know the market value of a used smartphone.

[0443] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from major online markets and flea markets.

[0444] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[0445] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of "15,000 yen" based on the price, valuation, and transaction history.

[0446] 4. The user enters the model and condition of the used smartphone from their own device.

[0447] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0448] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user. The user can use this value as a reference when considering buying or selling.

[0449] This allows users to quickly and accurately determine the fair market value based on data from a variety of sources, enabling them to make more appropriate value judgments.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it collects price information, product ratings, reviews, transaction history, etc. Since the data may be sent in different formats, a buffer area is set up to temporarily store the obtained data.

[0453] Step 2:

[0454] The server cleans the data stored in the buffer area. For example, it detects outliers (data with extremely high or low prices) and missing values ​​(data with no ratings) and deletes or corrects them. It also standardizes the currency unit of the data and converts it to Japanese yen. It also analyzes the content of text reviews and tags them as necessary.

[0455] Step 3:

[0456] The server stores the cleaned data in a database: price information in the Price table, rating data in the Rating table, reviews in the Review table, and transaction history in the Transaction table. At the same time, it runs an algorithm to classify the product condition into categories such as "new," "like new," "good," and "used."

[0457] Step 4:

[0458] The server trains a machine learning model based on the stored data. During this process, it assigns scores based on indicators such as price, ratings, reviews, and transaction history. For example, it calculates the balance of supply and demand based on the product's condition and past transaction history, and generates a score that evaluates the relative value of each product. The generating AI then combines these scores to calculate a fair market value.

[0459] Step 5:

[0460] The user inputs information about the product they want to know the value of from their device. For example, they provide information in input fields such as "product name," "model," and "condition." The information entered by the user is sent to the server in real time.

[0461] Step 6:

[0462] The server analyzes the product information received from the user and matches it with the corresponding product in its database. Once the match is complete, it recalculates the fair market value of the product based on past transaction data, reviews, and ratings. The recalculated value is converted into data that can be presented to the user in numerical and graphical formats.

[0463] Step 7:

[0464] The terminal displays the fair market value sent from the server to the user in the form of numbers, graphs, or rankings, making it easy for the user to understand.

[0465] Step 8:

[0466] Users can enter their thoughts on the provided market value and suggestions for improvement in a feedback form, including opinions on the accuracy of the displayed value assessment and requests for additional features.

[0467] Step 9:

[0468] The server receives feedback from users and stores it in a database. The collected feedback is periodically analyzed and used to improve the machine learning model and update the entire system. For example, if many users rate a particular product highly, that factor can be fed back into the machine learning model to improve the accuracy of value calculations.

[0469] Example 1

[0470] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0471] Currently, many online stores, flea markets, and auction sites often have different prices and ratings for the same product, making it difficult for consumers and businesses to determine its fair market value. Furthermore, manual data cleaning is required to address outliers and missing values, which is extremely time-consuming. Furthermore, there is a lack of a system that uniformly evaluates the condition of each product and provides it in a format that is easy for users to understand.

[0472] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0473] In this invention, the server includes a data collection means for acquiring product information from online stores, flea markets, auction sites, and brick-and-mortar stores, a data preprocessing means for cleaning and standardizing the acquired product information, and a value calculation means for scoring each indicator of the product information using a generative AI model to calculate a fair market value, enabling consumers and businesses to quickly and accurately grasp fair market value based on the latest data acquired from various information sources.

[0474] An "online store" is a website that sells products over the Internet.

[0475] A "flea market" is an online platform where individuals can buy and sell goods.

[0476] An "auction site" is an internet website that sells goods through competitive bidding.

[0477] A "brick and mortar store" is a store that sells products in a physical location.

[0478] "Product information" refers to data including product price information, evaluation data, reviews, transaction history, etc.

[0479] "Data collection means" refers to the methods and functions for obtaining product information from each source.

[0480] "Data preprocessing means" refers to methods and functions for cleaning and standardizing collected data.

[0481] A "generative AI model" refers to an artificial intelligence algorithm that learns from collected data and performs specific tasks.

[0482] "Valuation method" refers to a method or function for calculating the market value of a product using a generative AI model.

[0483] "User interface means" refers to the methods and functions by which a user accesses a system to input information and display results.

[0484] "Feedback collection means" refers to methods and functions for collecting feedback from users and using it to improve the system.

[0485] "Scoring" refers to evaluating data based on specific criteria or indicators and assigning a score.

[0486] "Fair market value" refers to the fair value of an item calculated based on data collected from various sources.

[0487] The present invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, and calculates and provides a fair market value. This system is implemented in the following steps.

[0488] First, the server is responsible for collecting data. It periodically calls APIs to obtain data from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it obtains product information such as price information, rating data, reviews, and transaction history. For example, it collects the latest price and rating data from major online markets every day.

[0489] Next, the server performs data preprocessing. It cleans the collected data and removes outliers and missing values. It also standardizes currency units and removes duplicate data. For example, it converts prices expressed in different currencies into Japanese yen and stores them in a consistent format in the database. It also categorizes the condition of products into categories such as "new," "like new," "good," and "used," and indexes them in the database, enabling quick data searches.

[0490] The server then uses the generative AI model to calculate the market value of each product. Specifically, it uses a machine learning model to score each product's indicators (price, rating, number of reviews, transaction frequency, etc.). The generative AI combines these scores to calculate the product's fair market value and converts the results into easy-to-understand formats (numbers and graphs). For example, products with high ratings and frequent transactions tend to have higher market values.

[0491] Users access the system using their own devices and enter information about the product they want to know the value of, such as "Product name: iPhone 11, Condition: Like new." The device then sends this information to the server in real time.

[0492] The server recalculates the market value of the item based on the information received from the user and returns the result to the device. The device can then display the calculation result to the user. For example, if the market value of an "iPhone 11, like new" is calculated to be "50,000 yen," the user's device will display "The fair market value is 50,000 yen." The user can use this market value as a reference when making a purchase or sale decision.

[0493] Furthermore, users can provide feedback on the displayed market value. For example, they can input their impressions such as "It sold for this price" or requests for improvement. This feedback is sent back to the server and used to improve the system.

[0494] As a result, the system of the present invention allows consumers and businesses to quickly and accurately determine fair market value based on the latest data obtained from a variety of sources, and the system can be continuously improved based on user feedback.

[0495] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0496] Step 1: Data collection

[0497] server

[0498] The server runs scheduled jobs to retrieve product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it calls APIs to retrieve price information, rating data, reviews, and transaction history. For example, it collects the latest data from Amazon and other major marketplaces at 2:00 AM every day. The input is the data request from each site, and the output is the collected product information.

[0499] Step 2: Data Preprocessing

[0500] server

[0501] The server cleans the collected data by removing outliers and missing values, standardizing currency units, and deleting duplicate data. For example, it automatically filters out abnormally high or low price data and converts prices expressed in various currencies into a single currency unit. The input is the collected raw data, and the output is cleansed, clean data. It also categorizes the condition of products into categories such as "new," "like new," "good," and "used," generating data in a consistent format.

[0502] Step 3: Standardize and index the data

[0503] server

[0504] The server standardizes the cleaned data and stores it in a database. Specifically, it converts data such as price, rating, and number of reviews into a standard format. It also indexes the data to enable quick subsequent searches and analysis. The input is the cleansed data, and the output is standardized, indexed database entries.

[0505] Step 4: Valuation

[0506] server

[0507] The server uses a generative AI model to calculate the fair market value of the product based on the collected and pre-processed data. Specifically, it uses a machine learning algorithm to score each indicator (price, rating, number of reviews, transaction frequency, etc.) and then combines them to calculate the market value. The input is standardized and indexed database data, and the output is the calculated market value (e.g., in numerical or graphical form).

[0508] Step 5: Enter user data

[0509] User

[0510] The user inputs information about the product they want to know the value of through their device. Specifically, they enter the product name, model, condition, etc. into an input form. For example, the user might enter "Product name: iPhone 11, Condition: Like new." The input is the product information the user enters into the device, and the output is the request data sent to the server.

[0511] Step 6: Sending and Receiving Data

[0512] Terminal

[0513] The terminal transmits the information input by the user to the server in real time. The server receives the input information and performs appropriate processing. The input is the product information sent by the user, and the output is a data request to the server.

[0514] Step 7: Providing market value

[0515] server

[0516] The server calculates the market value of the product based on the information received from the user and returns the result to the device. For example, if the market value of an "iPhone 11, like new" is calculated to be "50,000 yen," the result is sent to the device. The input is the product information sent by the user, and the output is the calculated market value data.

[0517] Step 8: Display Market Value

[0518] Terminal

[0519] The terminal displays the calculation results received from the server to the user. Specifically, it displays a message on the screen such as "The fair market value is 50,000 yen." The input is the market value data returned from the server, and the output is the information displayed to the user.

[0520] Step 9: Gather feedback

[0521] User

[0522] The user provides feedback on the displayed market value. Specifically, the user enters their thoughts on the evaluation and requests for improvement into an input form. For example, they provide feedback such as "It sold for this price." The input is the feedback information that the user enters into the terminal, and the output is the feedback data sent to the server.

[0523] Step 10: Use feedback

[0524] server

[0525] The server collects feedback received from users and uses it to improve the system. Specifically, it analyzes the feedback data and makes necessary adjustments to the algorithm or improves the entire system. The input is the feedback data sent by the users, and the output is the improved system function.

[0526] (Application example 1)

[0527] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0528] Currently, when users buy or sell products, it is difficult to determine whether the product has a fair market value. In addition, price and valuation information provided by different online and physical stores is inconsistent, making it difficult for users to make appropriate value judgments. Therefore, a system that allows users to quickly and accurately determine market value is needed.

[0529] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0530] In this invention, the server includes a data collection means for acquiring product information from online stores, flea markets, auction sites, and physical stores, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generative AI model to calculate the market value of the product based on the product information, a user interface means for providing the calculated market value to the user, and a feedback collection means for collecting feedback from the user and utilizing it to improve the system. This allows the user to quickly and accurately know the fair market value based on data from various information sources.

[0531] "Data collection means" refers to the means for obtaining product information from each online store, flea market, auction site, and physical store.

[0532] "Data preprocessing means" refers to means for cleansing (cleansing: removing outliers and missing values ​​in data) and standardizing (standardizing data format and units) the acquired product information.

[0533] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to calculate the market value of a product based on product information.

[0534] A "value calculation means" is a means for calculating the market value of a product based on product information using a generative AI model.

[0535] The "user interface means" is an interface for providing the calculated market value to the user, and typically refers to a smartphone application or a web page.

[0536] "Feedback collection means" refers to a means for collecting feedback from users and using it to improve the system.

[0537] "Price data" is price information for each product.

[0538] "Product evaluation" is evaluation information regarding the quality and performance of a product.

[0539] A "review" is an evaluation or comment posted by a user based on their experience using a product.

[0540] "Transaction history" is data showing the past buying and selling history and trading performance of a product.

[0541] "Scoring" is the process of calculating a product's evaluation score based on various evaluation indicators.

[0542] The following describes in detail the mode for implementing this invention. This invention is a system that organizes and analyzes product information obtained from various online stores, flea markets, auction sites, and physical stores, and calculates a fair market value using a generative AI model. The implementation method of this system is described in detail below.

[0543] Hardware and Software Configuration

[0544] 1. Server:

[0545] The server is the central function that performs all major tasks, including data collection, preprocessing, value calculation, result delivery, and feedback collection. The main technology stack used is Python, Flask, scikit-learn, Pandas, and Requests.

[0546] 2. User Device:

[0547] A smartphone or other device that acts as an interface for users to operate applications. The user interface is implemented in a browser or mobile application.

[0548] Detailed explanation of the process

[0549] 1. Data Collection:

[0550] The server periodically retrieves product information from online stores, flea markets, auction sites, and physical stores by calling public APIs. The collected data mainly includes price data, product ratings, reviews, and transaction history.

[0551] 2. Data Preprocessing:

[0552] The acquired data is cleansed and standardized on the server. Outliers and missing values ​​are removed, currency units are standardized, and duplicate data is deleted. The data is also classified according to the product's condition. The standardized data is then indexed into a database, enabling quick searches.

[0553] 3. Value estimation using generative AI models:

[0554] The server uses the collected and pre-processed data to train a generative AI model (machine learning algorithm) to calculate the fair market value of the product, which is scored based on indicators such as price, ratings, number of reviews, and transaction frequency.

[0555] 4. User Interface:

[0556] The user terminal communicates with the server via a user interface. The user inputs the product information they want to know (e.g., product name, model, condition, etc.), and the information is sent to the server in real time. The server calculates the market value and returns the result to the user terminal.

[0557] 5. Feedback Collection and System Improvement:

[0558] Users can check the displayed market value assessment and enter their thoughts and suggestions for improvement. This feedback is sent back to the server and used to improve the system.

[0559] Specific examples

[0560] For example, if a user wants to know the market value of a used smartphone, they can enter and submit the following information on their device:

[0561] Price: 15,000 yen

[0562] Rating: 4.5

[0563] Number of reviews: 50

[0564] Trading Frequency: 10

[0565] The server receives this information, calculates the market value using a generative AI model, and returns the result to the user's device: "The fair market value of this smartphone is 16,000 yen."

[0566] This allows users to quickly and accurately determine the fair market value based on data from different sources, enabling them to make appropriate value judgments.

[0567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0568] Step 1: Data collection

[0569] The server periodically retrieves product information from various online stores, flea markets, auction sites, and physical stores. Specifically, it uses APIs to access these sources and collect data such as price data, product ratings, reviews, and transaction history. For example, it calls an API endpoint and receives a JSON-formatted response. The input is the API URL, and the output is the retrieved product information.

[0570] Step 2: Data Preprocessing

[0571] The server cleanses and standardizes the collected product information. This involves removing outliers and missing values, standardizing currency units, and deleting duplicate data. It also classifies the product condition into categories such as "new," "like new," "good," and "used." Specifically, it uses the Pandas library to remove NaN values ​​and standardizes currency units through string manipulation. The input is the product information obtained in step 1, and the output is the cleansed and standardized data.

[0572] Step 3: Data Standardization

[0573] To standardize the cleansed data, the server converts each attribute (price, rating, etc.) to a certain scale. Specifically, it uses scikit-learn's StandardScaler. This allows attributes with different units to be compared on a common scale. The input is the data processed in step 2, and the output is the standardized data.

[0574] Step 4: Training the generative AI model

[0575] The server uses the standardized data to train a generative AI model. Specifically, it trains a machine learning model (e.g., a linear regression model) using features such as the product price, rating, number of reviews, and transaction frequency. The input is the standardized data obtained in step 3, and the output is the trained generative AI model.

[0576] Step 5: Receiving User Input

[0577] The user inputs information about the target product (price, rating, number of reviews, transaction frequency, etc.) from a terminal (such as a smartphone). The terminal collects this information and sends it to the server in real time. The input is the product information entered on the terminal, and the output is the data sent to the server.

[0578] Step 6: Calculate market value

[0579] The server calculates the market value of the product using a trained generative AI model based on the information received from the user. Specifically, it inputs the features entered by the user into the model and predicts the market value. The inputs are the data sent by the user and the generative AI model, and the output is the calculated market value.

[0580] Step 7: Deliver value

[0581] The server returns the calculated market value to the user's terminal. The terminal receives the market value and displays it to the user through a user interface, whose input is the market value calculated in step 6 and whose output is the market value information displayed on the user's terminal.

[0582] Step 8: Gather feedback

[0583] The user inputs their evaluation impressions and requests for improvement based on the displayed market value. The terminal sends this feedback to the server. The server collects this feedback and uses it to improve the system. The input is the user's feedback information, and the output is the collected feedback data.

[0584] Through the above steps, the present invention allows users to quickly and accurately determine the fair market value of an item.

[0585] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0586] This invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, calculates and provides a fair market value, and by combining it with an emotion engine that recognizes user emotions, achieves more accurate value provision and feedback analysis. Below, we will explain how the system program works, using specific examples.

[0587] System Program

[0588] Data collection

[0589] server

[0590] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores, specifically price information, rating data, reviews, transaction history, etc. This allows the collection of the latest information from a variety of data sources.

[0591] Data Preprocessing

[0592] server

[0593] The server cleans the collected data, removing outliers and missing values, standardizing currency units, and removing duplicate data. It then standardizes the data to make it consistent. It also analyzes the condition of products to categorize them into categories such as "new," "like new," "good," and "used." The data is then indexed, allowing the information in the database to be quickly searched.

[0594] Value estimation using generative AI

[0595] server

[0596] The server uses a machine learning model to score each indicator of product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs).

[0597] User Interface

[0598] Terminal (user)

[0599] The user accesses the system through a terminal and inputs information about the product for which they want to know the value, such as the product name, model, and condition. The terminal then sends this information to the server in real time.

[0600] Delivering value and gathering feedback

[0601] server

[0602] Based on the information received from the user, the server calculates the fair market value of the item and returns the result to the terminal. The terminal then displays this calculation result to the user. After checking the displayed value assessment, the user can enter their thoughts on the assessment and requests for improvement. This feedback is sent back to the server and used to improve the system. In addition, the emotion engine uses text analysis and voice recognition technology on the user's feedback to recognize the user's emotions.

[0603] Emotion recognition by emotion engine

[0604] server

[0605] The server recognizes the user's emotions by analyzing the text and voice data of the feedback using an emotion engine. Text analysis identifies positive, negative, and neutral emotions from the user's written feedback. It also uses speech recognition technology to understand emotional nuances from the tone, speed, and intonation of the voice.

[0606] Feedback analysis and system improvement

[0607] server

[0608] The server stores the user emotion data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotion data is reflected in improvements to the system. For example, if many users express negative emotions toward a particular product, the system may consider adjusting the evaluation algorithm for that product.

[0609] Specific examples

[0610] For example, consider the case where a user wants to know the market value of a used smartphone.

[0611] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from major online markets and flea markets.

[0612] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[0613] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of "15,000 yen" based on the price, valuation, and transaction history.

[0614] 4. The user enters the model and condition of the used smartphone from their own device.

[0615] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0616] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user.

[0617] 7. Users can enter their thoughts on the value assessment and requests for improvements in the feedback form. They can provide feedback via text and voice.

[0618] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if there are a lot of negative emotions, it adjusts the evaluation algorithm.

[0619] This allows users to quickly and accurately determine fair market value based on data from a variety of sources, and the system is continuously improved through feedback analysis based on user sentiment.

[0620] The processing flow will be explained below.

[0621] Step 1:

[0622] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it collects price information, product ratings, reviews, and transaction history. This information is temporarily stored in a buffer area.

[0623] Step 2:

[0624] The server cleans the data stored in the buffer area. This includes detecting and deleting or correcting outliers (e.g., extreme prices) and missing values ​​(e.g., data with no evaluations). At the same time, it unifies different currency units and converts them to Japanese yen.

[0625] Step 3:

[0626] The server stores the cleaned data in a database: price information in the Price table, rating data in the Rating table, reviews in the Review table, and transaction history in the Transaction table. It also runs an algorithm to classify the condition of the products into categories of "new," "like new," "good," and "used."

[0627] Step 4:

[0628] The server uses machine learning models to score each metric of the stored product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI then combines these scores to calculate the fair market value of the product, which is then converted into numerical and graphical formats.

[0629] Step 5:

[0630] The user uses the device's user interface to input information about the product for which they want to know the value. Input fields include the product name, model, and condition. The information entered by the user is sent to the server in real time.

[0631] Step 6:

[0632] The server analyzes the product information received from the user and compares it with the corresponding product data in the database. Based on the comparison results, it recalculates the fair market value. This recalculated market value is converted into data to be sent to the terminal.

[0633] Step 7:

[0634] The terminal displays the fair market value sent from the server to the user in the form of numbers, graphs, or rankings, making it easy for the user to understand.

[0635] Step 8:

[0636] Users can enter their thoughts on the displayed market value and requests for improvement in a feedback form. Feedback can be given not only by text but also by voice. Once feedback is complete, the device sends the data to the server.

[0637] Step 9:

[0638] The server receives the feedback data sent by the user and analyzes it with an emotion engine. Text analysis is used to identify positive, negative, neutral, and other emotions from the feedback text. At the same time, voice data is analyzed to understand the user's emotions from the tone, speed, and intonation of the voice.

[0639] Step 10:

[0640] The server stores the recognized emotion data in a database and periodically analyzes it. The analysis results are used to improve the machine learning model and update the system as a whole. For example, if many users express negative emotions in rating a particular product, the rating algorithm for that product will be revised.

[0641] This detailed flow enables the present invention to provide fair market value based on diverse data and continuously improve the system through feedback analysis that takes into account user sentiment.

[0642] Example 2

[0643] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0644] Conventional market value calculation systems did not adequately address inconsistencies, duplications, or missing product information obtained from a wide variety of data sources, resulting in inaccurate market values. Furthermore, user feedback was not fully utilized to improve the system, resulting in a lack of improvement in the quality of the user experience. Furthermore, there was a lack of technology to recognize user emotions and reflect them in system improvements, making it difficult to increase user satisfaction.

[0645] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0646] In this invention, the server includes a data collection means for acquiring product information from various online stores, online markets, e-commerce platforms, and physical stores, a data preprocessing means for cleaning and standardizing the acquired product information, and a value calculation means using generative AI to calculate the market value of the product based on the product information. This makes it possible to organize inconsistent data from various sources into a consistent form and calculate a fair market value using a machine learning model. Furthermore, by applying a user interface means for users to input product information and provide the calculated market value, an emotion engine for collecting user feedback and recognizing the emotion of the feedback, and a feedback collection means for improving the system based on the collected feedback, user feedback can be effectively utilized to improve the system.

[0647] An "online store" is an e-commerce platform that sells goods and services over the Internet.

[0648] An "online market" is an online commercial platform where multiple sellers come together to offer products and services.

[0649] An "e-commerce platform" is an online system for buying and selling goods and services electronically.

[0650] A "physical store" is a physical building where goods or services are sold in person.

[0651] "Data collection means" means the mechanism or technology used to obtain product information from various data sources.

[0652] "Data pre-processing means" refers to the process of cleaning and standardizing acquired data.

[0653] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0654] A "value calculation means" is a method or system for calculating the market value of a commodity based on commodity information.

[0655] The "user interface means" is an interface through which a user interacts with the system, and is a means for inputting data and displaying output.

[0656] A "feedback collection means" is a method or system for collecting user ratings and opinions.

[0657] An "emotion engine" is a technology for analyzing and recognizing emotions from user feedback data.

[0658] A "machine learning model" is an artificial intelligence algorithm that learns from training data and makes predictions or classifications based on new data.

[0659] This invention is a system that collects product information from online stores, online markets, e-commerce platforms, and physical stores, calculates and provides fair market value, and by combining it with an emotion engine that recognizes user emotions, it achieves more accurate value provision and feedback analysis.

[0660] System configuration

[0661] The system uses the following hardware and software components:

[0662] server

[0663] Data collection methods

[0664] Data preprocessing measures

[0665] Value calculation method using generative AI

[0666] Feedback collection methods

[0667] Emotion Engine

[0668] Terminal (user device)

[0669] User Interface Means

[0670] Data collection methods

[0671] The server collects product information from online stores, online markets, e-commerce platforms, and physical stores using common API endpoints. For example, to get information from Amazon, eBay, and local online markets, it calls the API endpoints of each platform. Data collection is scheduled periodically, and the latest data is retrieved regularly.

[0672] Data preprocessing measures

[0673] The server cleans and standardizes the acquired data. It removes outliers and missing values, standardizes currency units, and deletes duplicate data. Specifically, it uses the Python Pandas library to clean and standardize the data. It also analyzes the product condition to classify it into "new," "like new," "good," and "used."

[0674] Value calculation method using generative AI

[0675] The server uses a machine learning model to score product information and calculate a fair market value. This uses machine learning libraries such as TensorFlow. Variables such as price information, product ratings, number of reviews, and transaction frequency are used as inputs to generate the AI.

[0676] User Interface Means

[0677] Users access the system using their own devices (such as smartphones or computers) and enter product information. For example, they enter information such as "product name," "model," and "condition" in real time. The entered information is immediately sent to the server.

[0678] Delivering value and gathering feedback

[0679] The server analyzes the product information received from the user and calculates a fair market value. The result is sent back to the terminal, which displays it to the user. The user checks the displayed market value and enters their thoughts and requests for improvement in a feedback form. The feedback entered by the user is sent back to the server and analyzed by the emotion engine.

[0680] Emotion Engine

[0681] The server analyzes the feedback collected from users using an emotion engine. Text analysis is used to identify positive, negative, or neutral emotions from the feedback written by the user. Speech recognition technology is also used to understand emotional nuances from the tone and intonation of the voice.

[0682] Feedback analysis and system improvement

[0683] The server stores the emotional data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotional data is reflected in improvements to the system. For example, if many users express negative emotions about a particular product, the system may consider adjusting the evaluation algorithm for that product.

[0684] Specific examples

[0685] For example, consider the case where a user wants to know the market value of a used smartphone.

[0686] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from each online market.

[0687] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[0688] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of 15,000 yen based on the price, valuation, and transaction history.

[0689] 4. The user enters the model and condition of the used smartphone from their own device.

[0690] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0691] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user.

[0692] 7. Users can enter their thoughts on the value assessment and requests for improvement in the feedback form. They can provide feedback via text and voice.

[0693] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if there are a lot of negative emotions, it adjusts the evaluation algorithm.

[0694] The system allows users to quickly and accurately determine fair market value based on data from a variety of sources, and feedback analysis based on user sentiment allows for continuous improvement of the system.

[0695] Prompt Sentence Examples

[0696] The following prompt sentences are used to provide examples of how to input specific system behavior into the model:

[0697] "You are developing a program to calculate the market value of smartphones based on price information collected from online stores, flea markets, and auction sites. Using the information below, explain how you would collect, preprocess, and analyze the data to calculate a fair market value. Then, explain how you would improve the system based on user feedback."

[0698] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0699] Step 1: Data collection

[0700] The server retrieves product information from various online stores, online markets, e-commerce platforms, and physical stores. This process involves sending a request to an API endpoint, such as "GET / products?category=electronics&condition=used" to retrieve price information, rating data, reviews, transaction history, etc. The input is the API request, and the output is the response data with product information.

[0701] Specifically, the server sends a "GET / products" request to Amazon's API and stores the received data.

[0702] Step 2: Data Preprocessing

[0703] The server cleans and standardizes the acquired product information. In this step, outliers and missing values ​​are removed, currency units are standardized, and duplicate data is deleted. The Python Pandas library is used for data frame operations. The input is the product information data acquired in step 1, and the output is the cleaned and standardized product information data.

[0704] Specifically, the server uses Pandas to remove records with zero prices in the data frame and convert all currency units to USD.

[0705] Step 3: Value estimation using generative AI

[0706] The server uses a machine learning model to score product information and calculate market value. Standardized product information data obtained through data preprocessing is used as input. Generative AI (such as TensorFlow) is used to score price, rating, number of reviews, transaction frequency, etc. to calculate a fair market value. The output is the market value of each product.

[0707] Specifically, the server loads the TensorFlow model, inputs the price, rating, and number of reviews, and calculates the market value as "15,000 yen."

[0708] Step 4: Entering information in the user interface

[0709] The user inputs information about the product they wish to have appraised from their terminal. For example, they input information such as "product name," "model," and "condition," and this information is sent to the server in real time. The input is information from the user's terminal, and the output is data sent to the server.

[0710] Specifically, the user enters "iPhone 11, used, good condition" into the device's web form and clicks the submit button.

[0711] Step 5: Deliver value and gather feedback

[0712] The server calculates the market value based on the information from the user and returns the result to the terminal. The terminal displays this result to the user. The user checks the displayed market value and enters their thoughts and requests for improvement in a feedback form. The input is the market value calculation by the server and the user's feedback, and the output is the market value display and feedback transmission to the user.

[0713] Specifically, the server calculates the market value of "15,000 yen" and returns it to the terminal, which then displays it to the user. The user then enters "The accuracy is high and I'm satisfied" in the feedback form.

[0714] Step 6: Emotion Recognition with the Emotion Engine

[0715] The server analyzes the user feedback with an emotion engine to recognize emotions. The input is the user feedback data, and the output is the emotion analysis result. Text analysis and speech recognition technologies are used to identify the user's emotions.

[0716] Specifically, the server uses an NLP library to recognize positive emotions from feedback such as "I'm happy."

[0717] Step 7: Feedback analysis and system improvement

[0718] The server stores the emotion data analyzed by the emotion engine in a database and periodically analyzes it. The input is the emotion analysis results, and the output is a proposal for improving the system. Based on the analysis results, issues with the system are identified and the system is improved.

[0719] Specifically, the server analyzes the feedback emotion data every month and adjusts the algorithm when many users show negative emotions.

[0720] The above is a concrete explanation of the program processing of this system, broken down into steps.

[0721] (Application example 2)

[0722] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0723] In recent years, with the diversification of content distribution services, users are required to select what to watch from a vast amount of content. However, the lack of reliable information for users is a problem, as it is difficult to fairly grasp the ratings and market value of content. In addition, there is a lack of personalized recommendations based on viewing history and feedback, and innovations are needed to improve the user experience.

[0724] The identification processing by the identification 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 a data collection means for acquiring product information from each content distribution service, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generative AI for calculating the market value of the product based on the product information, a user interface means for providing the calculated market value to the user, a feedback collection means for collecting feedback from the user and using it to improve the system, an emotion analysis means for analyzing the user feedback and recognizing the user's emotions, and a means for improving the system based on the analyzed emotion data. This makes it easier for users to obtain reliable market value information and enables personalized content recommendations based on individual preferences.

[0725] The "data collection means" is a part that has the function of acquiring product information from each content distribution service.

[0726] The "data preprocessing means" is a part that has the function of cleansing and standardizing the acquired product information.

[0727] The "value calculation means" is the part that has the function of calculating the market value of a product based on product information using a generation AI.

[0728] The "user interface means" is a part having a function of providing the calculated market value to the user.

[0729] The "feedback collection means" is a part that has the function of collecting feedback from users and utilizing it to improve the system.

[0730] The "emotion analysis means" is a part that has the function of analyzing user feedback and recognizing the user's emotions.

[0731] The "means for improving the system" is a part that has the function of improving the system based on the analyzed emotion data.

[0732] "Product Information" refers to information related to the content, such as number of views, ratings, reviews, and viewing history.

[0733] "Generative AI" refers to artificial intelligence technology used to calculate market value based on product information.

[0734] The present invention is a system that acquires product information from a content distribution service, calculates a fair market value based on that information, provides it to users, and analyzes user feedback to improve the system. Below, we will explain how the program for this system works, using specific examples.

[0735] System Program

[0736] Data collection

[0737] server

[0738] The server periodically calls APIs to obtain product information from each content distribution service (e.g., video services, music distribution platforms, etc.). Specifically, the information being obtained includes the number of views, ratings, reviews, and viewing history. This allows the latest information to be collected from a variety of data sources.

[0739] Data Preprocessing

[0740] server

[0741] The server cleans and standardizes the collected data. This includes removing outliers and missing values, standardizing the data, normalizing view counts, standardizing rating scores, and analyzing the text of reviews. The data is then indexed, allowing for quick searches of information in the database. The software used for this is the Python libraries Pandas and NumPy.

[0742] Value estimation using generative AI

[0743] server

[0744] The server uses a machine learning model to score each indicator of product information (number of views, rating, number of reviews, viewing frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs). The software used here includes TensorFlow and Scikit-Learn.

[0745] User Interface

[0746] Terminal (user)

[0747] Users access the service through their device (smartphone, PC, smart TV, etc.) and enter information about the content they want to know the value of, such as the content name, platform, and rating. The device then sends this information to the server in real time.

[0748] Delivering value and gathering feedback

[0749] server

[0750] Based on the information received from the user, the server calculates the fair market value of the content and sends the result back to the terminal. The terminal displays this calculation result to the user. The user can check the displayed value assessment and then enter their thoughts on the assessment or requests for improvement. This feedback is sent back to the server and used to improve the system.

[0751] Emotion recognition by emotion engine

[0752] server

[0753] The server recognizes the user's emotions by analyzing the text and voice data of the feedback with an emotion engine. It uses the Natural Language Toolkit (NLTK) for text analysis and Google Cloud Speech-to-Text for voice recognition. This allows it to identify positive, negative, or neutral emotions from the user's description.

[0754] Feedback analysis and system improvement

[0755] server

[0756] The server stores the user's emotional data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotional data is reflected in improvements to the system. For example, if many users have a positive reaction to a particular piece of content, the server may consider increasing the frequency with which that content is recommended.

[0757] Specific examples

[0758] For example, suppose a user wants to know the market value of a movie.

[0759] 1. The server collects movie view counts, ratings, reviews, and viewing history from major content distribution services.

[0760] 2. The server cleans and standardizes the collected data, normalizing view counts and standardizing rating scores.

[0761] 3. The server uses a machine learning model to score the metrics of each piece of content. The AI ​​generator calculates a fair market value of 8.5 / 10 based on the number of views, ratings, and reviews.

[0762] 4. The user enters the movie title and platform on their device.

[0763] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0764] 6. The terminal displays the fair market value received from the server, "8.5 / 10", to the user.

[0765] 7. Users can enter their thoughts on the value assessment and requests for improvements in the feedback form. They can provide feedback via text and voice.

[0766] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if many users express positive emotions, the system adjusts its recommendation algorithm based on that information.

[0767] Prompt Sentence Examples

[0768] Title: Inception

[0769] Platform: Streaming Service

[0770] Rating: 9.5

[0771] User Reviews: Positive

[0772] User Comments: "Amazing plot and visual effects!"

[0773] Calculate fair market value and provide summary score.

[0774] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0775] Step 1: Data collection

[0776] The server periodically collects product information from each content distribution service (video service, music distribution platform, etc.) via API. Specifically, it obtains information such as the number of views, ratings, reviews, and viewing history. The input is the response data from the API, and the output is the collected raw data.

[0777] Step 2: Data Preprocessing

[0778] The server cleans and standardizes the data collected in step 1. Data cleaning involves removing outliers and missing values. Next, it normalizes the number of views and rating scores, and performs text analysis on the reviews to categorize them. The input is raw data, and the output is cleansed and standardized data.

[0779] Step 3: Index the data

[0780] The server indexes the preprocessed data, allowing for quick searches of information in the database. The software used is MySQL or MongoDB. The input is the preprocessed data, and the output is the indexed data.

[0781] Step 4: Valuation

[0782] The server uses a machine learning model to score each indicator of product information (number of views, rating, number of reviews, viewing frequency, etc.). A generative AI model combines these scores to calculate a fair market value. The software used is TensorFlow and Scikit-Learn. The input is the indexed data, and the output is the calculated market value.

[0783] Step 5: Provide a user interface

[0784] The terminal provides an interface for users to input information about the content they want to know the value of. The user inputs information such as the "content name," "platform," and "rating," and the terminal sends this information to the server. The input is the information entered by the user, and the output is the data to be sent to the server.

[0785] Step 6: Delivering valuation results

[0786] The server calculates the market value based on the information received from the user and returns the result to the terminal. The terminal displays the calculation result to the user. The input is the user information and the calculation result, and the output is the market value displayed to the user.

[0787] Step 7: Gather feedback

[0788] The terminal allows the user to input their thoughts and requests for improvement about the displayed market value into a feedback form. The user provides feedback by text or voice, and the terminal sends this information to the server. The input is the user's feedback, and the output is data to be sent to the server.

[0789] Step 8: Sentiment Analysis

[0790] The server analyzes the feedback text and audio data using an emotion engine. It uses the Natural Language Toolkit (NLTK) and Google Cloud Speech-to-Text to identify the user's emotions. The input is the feedback data, and the output is the analysis result.

[0791] Step 9: System Improvement

[0792] The server stores the analyzed emotional data in a database and periodically analyzes it. This information is used to improve the system. For example, it adjusts the algorithm to prioritize recommending content with a high number of positive reactions. The input is emotional data, and the output is improved system parameters.

[0793] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0794] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0795] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0796] [Third embodiment]

[0797] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0798] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0799] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0800] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0801] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0802] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0803] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0804] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0805] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0806] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0807] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0808] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0809] The present invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, and calculates and provides a fair market value. How the system program works is explained below with specific examples.

[0810] System Program

[0811] Data collection

[0812] server

[0813] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores, specifically price information, rating data, reviews, transaction history, etc. This allows the collection of the latest information from a variety of data sources.

[0814] Data Preprocessing

[0815] server

[0816] The server cleans the collected data, removing outliers and missing values, standardizing currency units, and removing duplicate data. It then standardizes the data to make it consistent. It also analyzes the condition of products to categorize them into categories such as "new," "like new," "good," and "used." The data is then indexed, allowing the information in the database to be quickly searched.

[0817] Value estimation using generative AI

[0818] server

[0819] The server uses a machine learning model to score each indicator of product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs).

[0820] User Interface

[0821] Terminal (user)

[0822] The user accesses the system through a terminal and inputs information about the product for which they want to know the value, such as the product name, model, and condition. The terminal then sends this information to the server in real time.

[0823] Delivering value and gathering feedback

[0824] server

[0825] Based on the information received from the user, the server calculates the fair market value of the item and sends the result back to the terminal. The terminal displays this calculation result to the user. After checking the displayed value assessment, the user can enter their thoughts on the assessment and requests for improvement. This feedback is sent back to the server and used to improve the system.

[0826] Specific examples

[0827] For example, suppose you want to know the market value of a used smartphone.

[0828] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from major online markets and flea markets.

[0829] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[0830] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of "15,000 yen" based on the price, valuation, and transaction history.

[0831] 4. The user enters the model and condition of the used smartphone from their own device.

[0832] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[0833] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user. The user can use this value as a reference when considering buying or selling.

[0834] This allows users to quickly and accurately determine the fair market value based on data from a variety of sources, enabling them to make more appropriate value judgments.

[0835] The processing flow will be explained below.

[0836] Step 1:

[0837] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it collects price information, product ratings, reviews, transaction history, etc. Since the data may be sent in different formats, a buffer area is set up to temporarily store the obtained data.

[0838] Step 2:

[0839] The server cleans the data stored in the buffer area. For example, it detects outliers (data with extremely high or low prices) and missing values ​​(data with no ratings) and deletes or corrects them. It also standardizes the currency unit of the data and converts it to Japanese yen. It also analyzes the content of text reviews and tags them as necessary.

[0840] Step 3:

[0841] The server stores the cleaned data in a database: price information in the Price table, rating data in the Rating table, reviews in the Review table, and transaction history in the Transaction table. At the same time, it runs an algorithm to classify the product condition into categories such as "new," "like new," "good," and "used."

[0842] Step 4:

[0843] The server trains a machine learning model based on the stored data. During this process, it assigns scores based on indicators such as price, ratings, reviews, and transaction history. For example, it calculates the balance of supply and demand based on the product's condition and past transaction history, and generates a score that evaluates the relative value of each product. The generating AI then combines these scores to calculate a fair market value.

[0844] Step 5:

[0845] The user inputs information about the product they want to know the value of from their device. For example, they provide information in input fields such as "product name," "model," and "condition." The information entered by the user is sent to the server in real time.

[0846] Step 6:

[0847] The server analyzes the product information received from the user and matches it with the corresponding product in its database. Once the match is complete, it recalculates the fair market value of the product based on past transaction data, reviews, and ratings. The recalculated value is converted into data that can be presented to the user in numerical and graphical formats.

[0848] Step 7:

[0849] The terminal displays the fair market value sent from the server to the user in the form of numbers, graphs, or rankings, making it easy for the user to understand.

[0850] Step 8:

[0851] Users can enter their thoughts on the provided market value and suggestions for improvement in a feedback form, including opinions on the accuracy of the displayed value assessment and requests for additional features.

[0852] Step 9:

[0853] The server receives feedback from users and stores it in a database. The collected feedback is periodically analyzed and used to improve the machine learning model and update the entire system. For example, if many users rate a particular product highly, that factor can be fed back into the machine learning model to improve the accuracy of value calculations.

[0854] Example 1

[0855] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0856] Currently, many online stores, flea markets, and auction sites often have different prices and ratings for the same product, making it difficult for consumers and businesses to determine its fair market value. Furthermore, manual data cleaning is required to address outliers and missing values, which is extremely time-consuming. Furthermore, there is a lack of a system that uniformly evaluates the condition of each product and provides it in a format that is easy for users to understand.

[0857] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0858] In this invention, the server includes a data collection means for acquiring product information from online stores, flea markets, auction sites, and brick-and-mortar stores, a data preprocessing means for cleaning and standardizing the acquired product information, and a value calculation means for scoring each indicator of the product information using a generative AI model to calculate a fair market value, enabling consumers and businesses to quickly and accurately grasp fair market value based on the latest data acquired from various information sources.

[0859] An "online store" is a website that sells products over the Internet.

[0860] A "flea market" is an online platform where individuals can buy and sell goods.

[0861] An "auction site" is an internet website that sells goods through competitive bidding.

[0862] A "brick and mortar store" is a store that sells products in a physical location.

[0863] "Product information" refers to data including product price information, evaluation data, reviews, transaction history, etc.

[0864] "Data collection means" refers to the methods and functions for obtaining product information from each source.

[0865] "Data preprocessing means" refers to methods and functions for cleaning and standardizing collected data.

[0866] A "generative AI model" refers to an artificial intelligence algorithm that learns from collected data and performs specific tasks.

[0867] "Valuation method" refers to a method or function for calculating the market value of a product using a generative AI model.

[0868] "User interface means" refers to the methods and functions by which a user accesses a system to input information and display results.

[0869] "Feedback collection means" refers to methods and functions for collecting feedback from users and using it to improve the system.

[0870] "Scoring" refers to evaluating data based on specific criteria or indicators and assigning a score.

[0871] "Fair market value" refers to the fair value of an item calculated based on data collected from various sources.

[0872] The present invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, and calculates and provides a fair market value. This system is implemented in the following steps.

[0873] First, the server is responsible for collecting data. It periodically calls APIs to obtain data from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it obtains product information such as price information, rating data, reviews, and transaction history. For example, it collects the latest price and rating data from major online markets every day.

[0874] Next, the server performs data preprocessing. It cleans the collected data and removes outliers and missing values. It also standardizes currency units and removes duplicate data. For example, it converts prices expressed in different currencies into Japanese yen and stores them in a consistent format in the database. It also categorizes the condition of products into categories such as "new," "like new," "good," and "used," and indexes them in the database, enabling quick data searches.

[0875] The server then uses the generative AI model to calculate the market value of each product. Specifically, it uses a machine learning model to score each product's indicators (price, rating, number of reviews, transaction frequency, etc.). The generative AI combines these scores to calculate the product's fair market value and converts the results into easy-to-understand formats (numbers and graphs). For example, products with high ratings and frequent transactions tend to have higher market values.

[0876] Users access the system using their own devices and enter information about the product they want to know the value of, such as "Product name: iPhone 11, Condition: Like new." The device then sends this information to the server in real time.

[0877] The server recalculates the market value of the item based on the information received from the user and returns the result to the device. The device can then display the calculation result to the user. For example, if the market value of an "iPhone 11, like new" is calculated to be "50,000 yen," the user's device will display "The fair market value is 50,000 yen." The user can use this market value as a reference when making a purchase or sale decision.

[0878] Furthermore, users can provide feedback on the displayed market value. For example, they can input their impressions such as "It sold for this price" or requests for improvement. This feedback is sent back to the server and used to improve the system.

[0879] As a result, the system of the present invention allows consumers and businesses to quickly and accurately determine fair market value based on the latest data obtained from a variety of sources, and the system can be continuously improved based on user feedback.

[0880] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0881] Step 1: Data collection

[0882] server

[0883] The server runs scheduled jobs to retrieve product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it calls APIs to retrieve price information, rating data, reviews, and transaction history. For example, it collects the latest data from Amazon and other major marketplaces at 2:00 AM every day. The input is the data request from each site, and the output is the collected product information.

[0884] Step 2: Data Preprocessing

[0885] server

[0886] The server cleans the collected data by removing outliers and missing values, standardizing currency units, and deleting duplicate data. For example, it automatically filters out abnormally high or low price data and converts prices expressed in various currencies into a single currency unit. The input is the collected raw data, and the output is cleansed, clean data. It also categorizes the condition of products into categories such as "new," "like new," "good," and "used," generating data in a consistent format.

[0887] Step 3: Standardize and index the data

[0888] server

[0889] The server standardizes the cleaned data and stores it in a database. Specifically, it converts data such as price, rating, and number of reviews into a standard format. It also indexes the data to enable quick subsequent searches and analysis. The input is the cleansed data, and the output is standardized, indexed database entries.

[0890] Step 4: Valuation

[0891] server

[0892] The server uses a generative AI model to calculate the fair market value of the product based on the collected and pre-processed data. Specifically, it uses a machine learning algorithm to score each indicator (price, rating, number of reviews, transaction frequency, etc.) and then combines them to calculate the market value. The input is standardized and indexed database data, and the output is the calculated market value (e.g., in numerical or graphical form).

[0893] Step 5: Enter user data

[0894] User

[0895] The user inputs information about the product they want to know the value of through their device. Specifically, they enter the product name, model, condition, etc. into an input form. For example, the user might enter "Product name: iPhone 11, Condition: Like new." The input is the product information the user enters into the device, and the output is the request data sent to the server.

[0896] Step 6: Sending and Receiving Data

[0897] Terminal

[0898] The terminal transmits the information input by the user to the server in real time. The server receives the input information and performs appropriate processing. The input is the product information sent by the user, and the output is a data request to the server.

[0899] Step 7: Providing market value

[0900] server

[0901] The server calculates the market value of the product based on the information received from the user and returns the result to the device. For example, if the market value of an "iPhone 11, like new" is calculated to be "50,000 yen," the result is sent to the device. The input is the product information sent by the user, and the output is the calculated market value data.

[0902] Step 8: Display Market Value

[0903] Terminal

[0904] The terminal displays the calculation results received from the server to the user. Specifically, it displays a message on the screen such as "The fair market value is 50,000 yen." The input is the market value data returned from the server, and the output is the information displayed to the user.

[0905] Step 9: Gather feedback

[0906] User

[0907] The user provides feedback on the displayed market value. Specifically, the user enters their thoughts on the evaluation and requests for improvement into an input form. For example, they provide feedback such as "It sold for this price." The input is the feedback information that the user enters into the terminal, and the output is the feedback data sent to the server.

[0908] Step 10: Use feedback

[0909] server

[0910] The server collects feedback received from users and uses it to improve the system. Specifically, it analyzes the feedback data and makes necessary adjustments to the algorithm or improves the entire system. The input is the feedback data sent by the users, and the output is the improved system function.

[0911] (Application example 1)

[0912] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0913] Currently, when users buy or sell products, it is difficult to determine whether the product has a fair market value. In addition, price and valuation information provided by different online and physical stores is inconsistent, making it difficult for users to make appropriate value judgments. Therefore, a system that allows users to quickly and accurately determine market value is needed.

[0914] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0915] In this invention, the server includes a data collection means for acquiring product information from online stores, flea markets, auction sites, and physical stores, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generative AI model to calculate the market value of the product based on the product information, a user interface means for providing the calculated market value to the user, and a feedback collection means for collecting feedback from the user and utilizing it to improve the system. This allows the user to quickly and accurately know the fair market value based on data from various information sources.

[0916] "Data collection means" refers to the means for obtaining product information from each online store, flea market, auction site, and physical store.

[0917] "Data preprocessing means" refers to means for cleansing (cleansing: removing outliers and missing values ​​in data) and standardizing (standardizing data format and units) the acquired product information.

[0918] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to calculate the market value of a product based on product information.

[0919] A "value calculation means" is a means for calculating the market value of a product based on product information using a generative AI model.

[0920] The "user interface means" is an interface for providing the calculated market value to the user, and typically refers to a smartphone application or a web page.

[0921] "Feedback collection means" refers to a means for collecting feedback from users and using it to improve the system.

[0922] "Price data" is price information for each product.

[0923] "Product evaluation" is evaluation information regarding the quality and performance of a product.

[0924] A "review" is an evaluation or comment posted by a user based on their experience using a product.

[0925] "Transaction history" is data showing the past buying and selling history and trading performance of a product.

[0926] "Scoring" is the process of calculating a product's evaluation score based on various evaluation indicators.

[0927] The following describes in detail the mode for implementing this invention. This invention is a system that organizes and analyzes product information obtained from various online stores, flea markets, auction sites, and physical stores, and calculates a fair market value using a generative AI model. The implementation method of this system is described in detail below.

[0928] Hardware and Software Configuration

[0929] 1. Server:

[0930] The server is the central function that performs all major tasks, including data collection, preprocessing, value calculation, result delivery, and feedback collection. The main technology stack used is Python, Flask, scikit-learn, Pandas, and Requests.

[0931] 2. User Device:

[0932] A smartphone or other device that acts as an interface for users to operate applications. The user interface is implemented in a browser or mobile application.

[0933] Detailed explanation of the process

[0934] 1. Data Collection:

[0935] The server periodically retrieves product information from online stores, flea markets, auction sites, and physical stores by calling public APIs. The collected data mainly includes price data, product ratings, reviews, and transaction history.

[0936] 2. Data Preprocessing:

[0937] The acquired data is cleansed and standardized on the server. Outliers and missing values ​​are removed, currency units are standardized, and duplicate data is deleted. The data is also classified according to the product's condition. The standardized data is then indexed into a database, enabling quick searches.

[0938] 3. Value estimation using generative AI models:

[0939] The server uses the collected and pre-processed data to train a generative AI model (machine learning algorithm) to calculate the fair market value of the product, which is scored based on indicators such as price, ratings, number of reviews, and transaction frequency.

[0940] 4. User Interface:

[0941] The user terminal communicates with the server via a user interface. The user inputs the product information they want to know (e.g., product name, model, condition, etc.), and the information is sent to the server in real time. The server calculates the market value and returns the result to the user terminal.

[0942] 5. Feedback Collection and System Improvement:

[0943] Users can check the displayed market value assessment and enter their thoughts and suggestions for improvement. This feedback is sent back to the server and used to improve the system.

[0944] Specific examples

[0945] For example, if a user wants to know the market value of a used smartphone, they can enter and submit the following information on their device:

[0946] Price: 15,000 yen

[0947] Rating: 4.5

[0948] Number of reviews: 50

[0949] Trading Frequency: 10

[0950] The server receives this information, calculates the market value using a generative AI model, and returns the result to the user's device: "The fair market value of this smartphone is 16,000 yen."

[0951] This allows users to quickly and accurately determine the fair market value based on data from different sources, enabling them to make appropriate value judgments.

[0952] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0953] Step 1: Data collection

[0954] The server periodically retrieves product information from various online stores, flea markets, auction sites, and physical stores. Specifically, it uses APIs to access these sources and collect data such as price data, product ratings, reviews, and transaction history. For example, it calls an API endpoint and receives a JSON-formatted response. The input is the API URL, and the output is the retrieved product information.

[0955] Step 2: Data Preprocessing

[0956] The server cleanses and standardizes the collected product information. This involves removing outliers and missing values, standardizing currency units, and deleting duplicate data. It also classifies the product condition into categories such as "new," "like new," "good," and "used." Specifically, it uses the Pandas library to remove NaN values ​​and standardizes currency units through string manipulation. The input is the product information obtained in step 1, and the output is the cleansed and standardized data.

[0957] Step 3: Data Standardization

[0958] To standardize the cleansed data, the server converts each attribute (price, rating, etc.) to a certain scale. Specifically, it uses scikit-learn's StandardScaler. This allows attributes with different units to be compared on a common scale. The input is the data processed in step 2, and the output is the standardized data.

[0959] Step 4: Training the generative AI model

[0960] The server uses the standardized data to train a generative AI model. Specifically, it trains a machine learning model (e.g., a linear regression model) using features such as the product price, rating, number of reviews, and transaction frequency. The input is the standardized data obtained in step 3, and the output is the trained generative AI model.

[0961] Step 5: Receiving User Input

[0962] The user inputs information about the target product (price, rating, number of reviews, transaction frequency, etc.) from a terminal (such as a smartphone). The terminal collects this information and sends it to the server in real time. The input is the product information entered on the terminal, and the output is the data sent to the server.

[0963] Step 6: Calculate market value

[0964] The server calculates the market value of the product using a trained generative AI model based on the information received from the user. Specifically, it inputs the features entered by the user into the model and predicts the market value. The inputs are the data sent by the user and the generative AI model, and the output is the calculated market value.

[0965] Step 7: Deliver value

[0966] The server returns the calculated market value to the user's terminal. The terminal receives the market value and displays it to the user through a user interface, whose input is the market value calculated in step 6 and whose output is the market value information displayed on the user's terminal.

[0967] Step 8: Gather feedback

[0968] The user inputs their evaluation impressions and requests for improvement based on the displayed market value. The terminal sends this feedback to the server. The server collects this feedback and uses it to improve the system. The input is the user's feedback information, and the output is the collected feedback data.

[0969] Through the above steps, the present invention allows users to quickly and accurately determine the fair market value of an item.

[0970] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0971] This invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, calculates and provides a fair market value, and by combining it with an emotion engine that recognizes user emotions, achieves more accurate value provision and feedback analysis. Below, we will explain how the system program works, using specific examples.

[0972] System Program

[0973] Data collection

[0974] server

[0975] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores, specifically price information, rating data, reviews, transaction history, etc. This allows the collection of the latest information from a variety of data sources.

[0976] Data Preprocessing

[0977] server

[0978] The server cleans the collected data, removing outliers and missing values, standardizing currency units, and removing duplicate data. It then standardizes the data to make it consistent. It also analyzes the condition of products to categorize them into categories such as "new," "like new," "good," and "used." The data is then indexed, allowing the information in the database to be quickly searched.

[0979] Value estimation using generative AI

[0980] server

[0981] The server uses a machine learning model to score each indicator of product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs).

[0982] User Interface

[0983] Terminal (user)

[0984] The user accesses the system through a terminal and inputs information about the product for which they want to know the value, such as the product name, model, and condition. The terminal then sends this information to the server in real time.

[0985] Delivering value and gathering feedback

[0986] server

[0987] Based on the information received from the user, the server calculates the fair market value of the item and returns the result to the terminal. The terminal then displays this calculation result to the user. After checking the displayed value assessment, the user can enter their thoughts on the assessment and requests for improvement. This feedback is sent back to the server and used to improve the system. In addition, the emotion engine uses text analysis and voice recognition technology on the user's feedback to recognize the user's emotions.

[0988] Emotion recognition by emotion engine

[0989] server

[0990] The server recognizes the user's emotions by analyzing the text and voice data of the feedback using an emotion engine. Text analysis identifies positive, negative, and neutral emotions from the user's written feedback. It also uses speech recognition technology to understand emotional nuances from the tone, speed, and intonation of the voice.

[0991] Feedback analysis and system improvement

[0992] server

[0993] The server stores the user emotion data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotion data is reflected in improvements to the system. For example, if many users express negative emotions toward a particular product, the system may consider adjusting the evaluation algorithm for that product.

[0994] Specific examples

[0995] For example, consider the case where a user wants to know the market value of a used smartphone.

[0996] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from major online markets and flea markets.

[0997] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[0998] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of "15,000 yen" based on the price, valuation, and transaction history.

[0999] 4. The user enters the model and condition of the used smartphone from their own device.

[1000] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[1001] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user.

[1002] 7. Users can enter their thoughts on the value assessment and requests for improvements in the feedback form. They can provide feedback via text and voice.

[1003] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if there are a lot of negative emotions, it adjusts the evaluation algorithm.

[1004] This allows users to quickly and accurately determine fair market value based on data from a variety of sources, and the system is continuously improved through feedback analysis based on user sentiment.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it collects price information, product ratings, reviews, and transaction history. This information is temporarily stored in a buffer area.

[1008] Step 2:

[1009] The server cleans the data stored in the buffer area. This includes detecting and deleting or correcting outliers (e.g., extreme prices) and missing values ​​(e.g., data with no evaluations). At the same time, it unifies different currency units and converts them to Japanese yen.

[1010] Step 3:

[1011] The server stores the cleaned data in a database: price information in the Price table, rating data in the Rating table, reviews in the Review table, and transaction history in the Transaction table. It also runs an algorithm to classify the condition of the products into categories of "new," "like new," "good," and "used."

[1012] Step 4:

[1013] The server uses machine learning models to score each metric of the stored product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI then combines these scores to calculate the fair market value of the product, which is then converted into numerical and graphical formats.

[1014] Step 5:

[1015] The user uses the device's user interface to input information about the product for which they want to know the value. Input fields include the product name, model, and condition. The information entered by the user is sent to the server in real time.

[1016] Step 6:

[1017] The server analyzes the product information received from the user and compares it with the corresponding product data in the database. Based on the comparison results, it recalculates the fair market value. This recalculated market value is converted into data to be sent to the terminal.

[1018] Step 7:

[1019] The terminal displays the fair market value sent from the server to the user in the form of numbers, graphs, or rankings, making it easy for the user to understand.

[1020] Step 8:

[1021] Users can enter their thoughts on the displayed market value and requests for improvement in a feedback form. Feedback can be given not only by text but also by voice. Once feedback is complete, the device sends the data to the server.

[1022] Step 9:

[1023] The server receives the feedback data sent by the user and analyzes it with an emotion engine. Text analysis is used to identify positive, negative, neutral, and other emotions from the feedback text. At the same time, voice data is analyzed to understand the user's emotions from the tone, speed, and intonation of the voice.

[1024] Step 10:

[1025] The server stores the recognized emotion data in a database and periodically analyzes it. The analysis results are used to improve the machine learning model and update the system as a whole. For example, if many users express negative emotions in rating a particular product, the rating algorithm for that product will be revised.

[1026] This detailed flow enables the present invention to provide fair market value based on diverse data and continuously improve the system through feedback analysis that takes into account user sentiment.

[1027] Example 2

[1028] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1029] Conventional market value calculation systems did not adequately address inconsistencies, duplications, or missing product information obtained from a wide variety of data sources, resulting in inaccurate market values. Furthermore, user feedback was not fully utilized to improve the system, resulting in a lack of improvement in the quality of the user experience. Furthermore, there was a lack of technology to recognize user emotions and reflect them in system improvements, making it difficult to increase user satisfaction.

[1030] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1031] In this invention, the server includes a data collection means for acquiring product information from various online stores, online markets, e-commerce platforms, and physical stores, a data preprocessing means for cleaning and standardizing the acquired product information, and a value calculation means using generative AI to calculate the market value of the product based on the product information. This makes it possible to organize inconsistent data from various sources into a consistent form and calculate a fair market value using a machine learning model. Furthermore, by applying a user interface means for users to input product information and provide the calculated market value, an emotion engine for collecting user feedback and recognizing the emotion of the feedback, and a feedback collection means for improving the system based on the collected feedback, user feedback can be effectively utilized to improve the system.

[1032] An "online store" is an e-commerce platform that sells goods and services over the Internet.

[1033] An "online market" is an online commercial platform where multiple sellers come together to offer products and services.

[1034] An "e-commerce platform" is an online system for buying and selling goods and services electronically.

[1035] A "physical store" is a physical building where goods or services are sold in person.

[1036] "Data collection means" means the mechanism or technology used to obtain product information from various data sources.

[1037] "Data pre-processing means" refers to the process of cleaning and standardizing acquired data.

[1038] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[1039] A "value calculation means" is a method or system for calculating the market value of a commodity based on commodity information.

[1040] The "user interface means" is an interface through which a user interacts with the system, and is a means for inputting data and displaying output.

[1041] A "feedback collection means" is a method or system for collecting user ratings and opinions.

[1042] An "emotion engine" is a technology for analyzing and recognizing emotions from user feedback data.

[1043] A "machine learning model" is an artificial intelligence algorithm that learns from training data and makes predictions or classifications based on new data.

[1044] This invention is a system that collects product information from online stores, online markets, e-commerce platforms, and physical stores, calculates and provides fair market value, and by combining it with an emotion engine that recognizes user emotions, it achieves more accurate value provision and feedback analysis.

[1045] System configuration

[1046] The system uses the following hardware and software components:

[1047] server

[1048] Data collection methods

[1049] Data preprocessing measures

[1050] Value calculation method using generative AI

[1051] Feedback collection methods

[1052] Emotion Engine

[1053] Terminal (user device)

[1054] User Interface Means

[1055] Data collection methods

[1056] The server collects product information from online stores, online markets, e-commerce platforms, and physical stores using common API endpoints. For example, to get information from Amazon, eBay, and local online markets, it calls the API endpoints of each platform. Data collection is scheduled periodically, and the latest data is retrieved regularly.

[1057] Data preprocessing measures

[1058] The server cleans and standardizes the acquired data. It removes outliers and missing values, standardizes currency units, and deletes duplicate data. Specifically, it uses the Python Pandas library to clean and standardize the data. It also analyzes the product condition to classify it into "new," "like new," "good," and "used."

[1059] Value calculation method using generative AI

[1060] The server uses a machine learning model to score product information and calculate a fair market value. This uses machine learning libraries such as TensorFlow. Variables such as price information, product ratings, number of reviews, and transaction frequency are used as inputs to generate the AI.

[1061] User Interface Means

[1062] Users access the system using their own devices (such as smartphones or computers) and enter product information. For example, they enter information such as "product name," "model," and "condition" in real time. The entered information is immediately sent to the server.

[1063] Delivering value and gathering feedback

[1064] The server analyzes the product information received from the user and calculates a fair market value. The result is sent back to the terminal, which displays it to the user. The user checks the displayed market value and enters their thoughts and requests for improvement in a feedback form. The feedback entered by the user is sent back to the server and analyzed by the emotion engine.

[1065] Emotion Engine

[1066] The server analyzes the feedback collected from users using an emotion engine. Text analysis is used to identify positive, negative, or neutral emotions from the feedback written by the user. Speech recognition technology is also used to understand emotional nuances from the tone and intonation of the voice.

[1067] Feedback analysis and system improvement

[1068] The server stores the emotional data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotional data is reflected in improvements to the system. For example, if many users express negative emotions about a particular product, the system may consider adjusting the evaluation algorithm for that product.

[1069] Specific examples

[1070] For example, consider the case where a user wants to know the market value of a used smartphone.

[1071] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from each online market.

[1072] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[1073] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of 15,000 yen based on the price, valuation, and transaction history.

[1074] 4. The user enters the model and condition of the used smartphone from their own device.

[1075] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[1076] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user.

[1077] 7. Users can enter their thoughts on the value assessment and requests for improvement in the feedback form. They can provide feedback via text and voice.

[1078] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if there are a lot of negative emotions, it adjusts the evaluation algorithm.

[1079] The system allows users to quickly and accurately determine fair market value based on data from a variety of sources, and feedback analysis based on user sentiment allows for continuous improvement of the system.

[1080] Prompt Sentence Examples

[1081] The following prompt sentences are used to provide examples of how to input specific system behavior into the model:

[1082] "You are developing a program to calculate the market value of smartphones based on price information collected from online stores, flea markets, and auction sites. Using the information below, explain how you would collect, preprocess, and analyze the data to calculate a fair market value. Then, explain how you would improve the system based on user feedback."

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

[1084] Step 1: Data collection

[1085] The server retrieves product information from various online stores, online markets, e-commerce platforms, and physical stores. This process involves sending a request to an API endpoint, such as "GET / products?category=electronics&condition=used" to retrieve price information, rating data, reviews, transaction history, etc. The input is the API request, and the output is the response data with product information.

[1086] Specifically, the server sends a "GET / products" request to Amazon's API and stores the received data.

[1087] Step 2: Data Preprocessing

[1088] The server cleans and standardizes the acquired product information. In this step, outliers and missing values ​​are removed, currency units are standardized, and duplicate data is deleted. The Python Pandas library is used for data frame operations. The input is the product information data acquired in step 1, and the output is the cleaned and standardized product information data.

[1089] Specifically, the server uses Pandas to remove records with zero prices in the data frame and convert all currency units to USD.

[1090] Step 3: Value estimation using generative AI

[1091] The server uses a machine learning model to score product information and calculate market value. Standardized product information data obtained through data preprocessing is used as input. Generative AI (such as TensorFlow) is used to score price, rating, number of reviews, transaction frequency, etc. to calculate a fair market value. The output is the market value of each product.

[1092] Specifically, the server loads the TensorFlow model, inputs the price, rating, and number of reviews, and calculates the market value as "15,000 yen."

[1093] Step 4: Entering information in the user interface

[1094] The user inputs information about the product they wish to have appraised from their terminal. For example, they input information such as "product name," "model," and "condition," and this information is sent to the server in real time. The input is information from the user's terminal, and the output is data sent to the server.

[1095] Specifically, the user enters "iPhone 11, used, good condition" into the device's web form and clicks the submit button.

[1096] Step 5: Deliver value and gather feedback

[1097] The server calculates the market value based on the information from the user and returns the result to the terminal. The terminal displays this result to the user. The user checks the displayed market value and enters their thoughts and requests for improvement in a feedback form. The input is the market value calculation by the server and the user's feedback, and the output is the market value display and feedback transmission to the user.

[1098] Specifically, the server calculates the market value of "15,000 yen" and returns it to the terminal, which then displays it to the user. The user then enters "The accuracy is high and I'm satisfied" in the feedback form.

[1099] Step 6: Emotion Recognition with the Emotion Engine

[1100] The server analyzes the user feedback with an emotion engine to recognize emotions. The input is the user feedback data, and the output is the emotion analysis result. Text analysis and speech recognition technologies are used to identify the user's emotions.

[1101] Specifically, the server uses an NLP library to recognize positive emotions from feedback such as "I'm happy."

[1102] Step 7: Feedback analysis and system improvement

[1103] The server stores the emotion data analyzed by the emotion engine in a database and periodically analyzes it. The input is the emotion analysis results, and the output is a proposal for improving the system. Based on the analysis results, issues with the system are identified and the system is improved.

[1104] Specifically, the server analyzes the feedback emotion data every month and adjusts the algorithm when many users show negative emotions.

[1105] The above is a concrete explanation of the program processing of this system, broken down into steps.

[1106] (Application example 2)

[1107] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1108] In recent years, with the diversification of content distribution services, users are required to select what to watch from a vast amount of content. However, the lack of reliable information for users is a problem, as it is difficult to fairly grasp the ratings and market value of content. In addition, there is a lack of personalized recommendations based on viewing history and feedback, and innovations are needed to improve the user experience.

[1109] The identification processing by the identification 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 a data collection means for acquiring product information from each content distribution service, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generative AI for calculating the market value of the product based on the product information, a user interface means for providing the calculated market value to the user, a feedback collection means for collecting feedback from the user and using it to improve the system, an emotion analysis means for analyzing the user feedback and recognizing the user's emotions, and a means for improving the system based on the analyzed emotion data. This makes it easier for users to obtain reliable market value information and enables personalized content recommendations based on individual preferences.

[1110] The "data collection means" is a part that has the function of acquiring product information from each content distribution service.

[1111] The "data preprocessing means" is a part that has the function of cleansing and standardizing the acquired product information.

[1112] The "value calculation means" is the part that has the function of calculating the market value of a product based on product information using a generation AI.

[1113] The "user interface means" is a part having a function of providing the calculated market value to the user.

[1114] The "feedback collection means" is a part that has the function of collecting feedback from users and utilizing it to improve the system.

[1115] The "emotion analysis means" is a part that has the function of analyzing user feedback and recognizing the user's emotions.

[1116] The "means for improving the system" is a part that has the function of improving the system based on the analyzed emotion data.

[1117] "Product Information" refers to information related to the content, such as number of views, ratings, reviews, and viewing history.

[1118] "Generative AI" refers to artificial intelligence technology used to calculate market value based on product information.

[1119] The present invention is a system that acquires product information from a content distribution service, calculates a fair market value based on that information, provides it to users, and analyzes user feedback to improve the system. Below, we will explain how the program for this system works, using specific examples.

[1120] System Program

[1121] Data collection

[1122] server

[1123] The server periodically calls APIs to obtain product information from each content distribution service (e.g., video services, music distribution platforms, etc.). Specifically, the information being obtained includes the number of views, ratings, reviews, and viewing history. This allows the latest information to be collected from a variety of data sources.

[1124] Data Preprocessing

[1125] server

[1126] The server cleans and standardizes the collected data. This includes removing outliers and missing values, standardizing the data, normalizing view counts, standardizing rating scores, and analyzing the text of reviews. The data is then indexed, allowing for quick searches of information in the database. The software used for this is the Python libraries Pandas and NumPy.

[1127] Value estimation using generative AI

[1128] server

[1129] The server uses a machine learning model to score each indicator of product information (number of views, rating, number of reviews, viewing frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs). The software used here includes TensorFlow and Scikit-Learn.

[1130] User Interface

[1131] Terminal (user)

[1132] Users access the service through their device (smartphone, PC, smart TV, etc.) and enter information about the content they want to know the value of, such as the content name, platform, and rating. The device then sends this information to the server in real time.

[1133] Delivering value and gathering feedback

[1134] server

[1135] Based on the information received from the user, the server calculates the fair market value of the content and sends the result back to the terminal. The terminal displays this calculation result to the user. The user can check the displayed value assessment and then enter their thoughts on the assessment or requests for improvement. This feedback is sent back to the server and used to improve the system.

[1136] Emotion recognition by emotion engine

[1137] server

[1138] The server recognizes the user's emotions by analyzing the text and voice data of the feedback with an emotion engine. It uses the Natural Language Toolkit (NLTK) for text analysis and Google Cloud Speech-to-Text for voice recognition. This allows it to identify positive, negative, or neutral emotions from the user's description.

[1139] Feedback analysis and system improvement

[1140] server

[1141] The server stores the user's emotional data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotional data is reflected in improvements to the system. For example, if many users have a positive reaction to a particular piece of content, the server may consider increasing the frequency with which that content is recommended.

[1142] Specific examples

[1143] For example, suppose a user wants to know the market value of a movie.

[1144] 1. The server collects movie view counts, ratings, reviews, and viewing history from major content distribution services.

[1145] 2. The server cleans and standardizes the collected data, normalizing view counts and standardizing rating scores.

[1146] 3. The server uses a machine learning model to score the metrics of each piece of content. The AI ​​generator calculates a fair market value of 8.5 / 10 based on the number of views, ratings, and reviews.

[1147] 4. The user enters the movie title and platform on their device.

[1148] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[1149] 6. The terminal displays the fair market value received from the server, "8.5 / 10", to the user.

[1150] 7. Users can enter their thoughts on the value assessment and requests for improvements in the feedback form. They can provide feedback via text and voice.

[1151] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if many users express positive emotions, the system adjusts its recommendation algorithm based on that information.

[1152] Prompt Sentence Examples

[1153] Title: Inception

[1154] Platform: Streaming Service

[1155] Rating: 9.5

[1156] User Reviews: Positive

[1157] User Comments: "Amazing plot and visual effects!"

[1158] Calculate fair market value and provide summary score.

[1159] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1160] Step 1: Data collection

[1161] The server periodically collects product information from each content distribution service (video service, music distribution platform, etc.) via API. Specifically, it obtains information such as the number of views, ratings, reviews, and viewing history. The input is the response data from the API, and the output is the collected raw data.

[1162] Step 2: Data Preprocessing

[1163] The server cleans and standardizes the data collected in step 1. Data cleaning involves removing outliers and missing values. Next, it normalizes the number of views and rating scores, and performs text analysis on the reviews to categorize them. The input is raw data, and the output is cleansed and standardized data.

[1164] Step 3: Index the data

[1165] The server indexes the preprocessed data, allowing for quick searches of information in the database. The software used is MySQL or MongoDB. The input is the preprocessed data, and the output is the indexed data.

[1166] Step 4: Valuation

[1167] The server uses a machine learning model to score each indicator of product information (number of views, rating, number of reviews, viewing frequency, etc.). A generative AI model combines these scores to calculate a fair market value. The software used is TensorFlow and Scikit-Learn. The input is the indexed data, and the output is the calculated market value.

[1168] Step 5: Provide a user interface

[1169] The terminal provides an interface for users to input information about the content they want to know the value of. The user inputs information such as the "content name," "platform," and "rating," and the terminal sends this information to the server. The input is the information entered by the user, and the output is the data to be sent to the server.

[1170] Step 6: Delivering valuation results

[1171] The server calculates the market value based on the information received from the user and returns the result to the terminal. The terminal displays the calculation result to the user. The input is the user information and the calculation result, and the output is the market value displayed to the user.

[1172] Step 7: Gather feedback

[1173] The terminal allows the user to input their thoughts and requests for improvement about the displayed market value into a feedback form. The user provides feedback by text or voice, and the terminal sends this information to the server. The input is the user's feedback, and the output is data to be sent to the server.

[1174] Step 8: Sentiment Analysis

[1175] The server analyzes the feedback text and audio data using an emotion engine. It uses the Natural Language Toolkit (NLTK) and Google Cloud Speech-to-Text to identify the user's emotions. The input is the feedback data, and the output is the analysis result.

[1176] Step 9: System Improvement

[1177] The server stores the analyzed emotional data in a database and periodically analyzes it. This information is used to improve the system. For example, it adjusts the algorithm to prioritize recommending content with a high number of positive reactions. The input is emotional data, and the output is improved system parameters.

[1178] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1179] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1180] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1181] [Fourth embodiment]

[1182] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1183] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1184] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1185] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1186] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1187] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1188] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1189] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1190] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1191] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1192] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1193] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1194] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1195] The present invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, and calculates and provides a fair market value. How the system program works is explained below with specific examples.

[1196] System Program

[1197] Data collection

[1198] server

[1199] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores, specifically price information, rating data, reviews, transaction history, etc. This allows the collection of the latest information from a variety of data sources.

[1200] Data Preprocessing

[1201] server

[1202] The server cleans the collected data, removing outliers and missing values, standardizing currency units, and removing duplicate data. It then standardizes the data to make it consistent. It also analyzes the condition of products to categorize them into categories such as "new," "like new," "good," and "used." The data is then indexed, allowing the information in the database to be quickly searched.

[1203] Value estimation using generative AI

[1204] server

[1205] The server uses a machine learning model to score each indicator of product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs).

[1206] User Interface

[1207] Terminal (user)

[1208] The user accesses the system through a terminal and inputs information about the product for which they want to know the value, such as the product name, model, and condition. The terminal then sends this information to the server in real time.

[1209] Delivering value and gathering feedback

[1210] server

[1211] Based on the information received from the user, the server calculates the fair market value of the item and sends the result back to the terminal. The terminal displays this calculation result to the user. After checking the displayed value assessment, the user can enter their thoughts on the assessment and requests for improvement. This feedback is sent back to the server and used to improve the system.

[1212] Specific examples

[1213] For example, suppose you want to know the market value of a used smartphone.

[1214] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from major online markets and flea markets.

[1215] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[1216] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of "15,000 yen" based on the price, valuation, and transaction history.

[1217] 4. The user enters the model and condition of the used smartphone from their own device.

[1218] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[1219] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user. The user can use this value as a reference when considering buying or selling.

[1220] This allows users to quickly and accurately determine the fair market value based on data from a variety of sources, enabling them to make more appropriate value judgments.

[1221] The processing flow will be explained below.

[1222] Step 1:

[1223] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it collects price information, product ratings, reviews, transaction history, etc. Since the data may be sent in different formats, a buffer area is set up to temporarily store the obtained data.

[1224] Step 2:

[1225] The server cleans the data stored in the buffer area. For example, it detects outliers (data with extremely high or low prices) and missing values ​​(data with no ratings) and deletes or corrects them. It also standardizes the currency unit of the data and converts it to Japanese yen. It also analyzes the content of text reviews and tags them as necessary.

[1226] Step 3:

[1227] The server stores the cleaned data in a database: price information in the Price table, rating data in the Rating table, reviews in the Review table, and transaction history in the Transaction table. At the same time, it runs an algorithm to classify the product condition into categories such as "new," "like new," "good," and "used."

[1228] Step 4:

[1229] The server trains a machine learning model based on the stored data. During this process, it assigns scores based on indicators such as price, ratings, reviews, and transaction history. For example, it calculates the balance of supply and demand based on the product's condition and past transaction history, and generates a score that evaluates the relative value of each product. The generating AI then combines these scores to calculate a fair market value.

[1230] Step 5:

[1231] The user inputs information about the product they want to know the value of from their device. For example, they provide information in input fields such as "product name," "model," and "condition." The information entered by the user is sent to the server in real time.

[1232] Step 6:

[1233] The server analyzes the product information received from the user and matches it with the corresponding product in its database. Once the match is complete, it recalculates the fair market value of the product based on past transaction data, reviews, and ratings. The recalculated value is converted into data that can be presented to the user in numerical and graphical formats.

[1234] Step 7:

[1235] The terminal displays the fair market value sent from the server to the user in the form of numbers, graphs, or rankings, making it easy for the user to understand.

[1236] Step 8:

[1237] Users can enter their thoughts on the provided market value and suggestions for improvement in a feedback form, including opinions on the accuracy of the displayed value assessment and requests for additional features.

[1238] Step 9:

[1239] The server receives feedback from users and stores it in a database. The collected feedback is periodically analyzed and used to improve the machine learning model and update the entire system. For example, if many users rate a particular product highly, that factor can be fed back into the machine learning model to improve the accuracy of value calculations.

[1240] Example 1

[1241] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1242] Currently, many online stores, flea markets, and auction sites often have different prices and ratings for the same product, making it difficult for consumers and businesses to determine its fair market value. Furthermore, manual data cleaning is required to address outliers and missing values, which is extremely time-consuming. Furthermore, there is a lack of a system that uniformly evaluates the condition of each product and provides it in a format that is easy for users to understand.

[1243] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1244] In this invention, the server includes a data collection means for acquiring product information from online stores, flea markets, auction sites, and brick-and-mortar stores, a data preprocessing means for cleaning and standardizing the acquired product information, and a value calculation means for scoring each indicator of the product information using a generative AI model to calculate a fair market value, enabling consumers and businesses to quickly and accurately grasp fair market value based on the latest data acquired from various information sources.

[1245] An "online store" is a website that sells products over the Internet.

[1246] A "flea market" is an online platform where individuals can buy and sell goods.

[1247] An "auction site" is an internet website that sells goods through competitive bidding.

[1248] A "brick and mortar store" is a store that sells products in a physical location.

[1249] "Product information" refers to data including product price information, evaluation data, reviews, transaction history, etc.

[1250] "Data collection means" refers to the methods and functions for obtaining product information from each source.

[1251] "Data preprocessing means" refers to methods and functions for cleaning and standardizing collected data.

[1252] A "generative AI model" refers to an artificial intelligence algorithm that learns from collected data and performs specific tasks.

[1253] "Valuation method" refers to a method or function for calculating the market value of a product using a generative AI model.

[1254] "User interface means" refers to the methods and functions by which a user accesses a system to input information and display results.

[1255] "Feedback collection means" refers to methods and functions for collecting feedback from users and using it to improve the system.

[1256] "Scoring" refers to evaluating data based on specific criteria or indicators and assigning a score.

[1257] "Fair market value" refers to the fair value of an item calculated based on data collected from various sources.

[1258] The present invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, and calculates and provides a fair market value. This system is implemented in the following steps.

[1259] First, the server is responsible for collecting data. It periodically calls APIs to obtain data from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it obtains product information such as price information, rating data, reviews, and transaction history. For example, it collects the latest price and rating data from major online markets every day.

[1260] Next, the server performs data preprocessing. It cleans the collected data and removes outliers and missing values. It also standardizes currency units and removes duplicate data. For example, it converts prices expressed in different currencies into Japanese yen and stores them in a consistent format in the database. It also categorizes the condition of products into categories such as "new," "like new," "good," and "used," and indexes them in the database, enabling quick data searches.

[1261] The server then uses the generative AI model to calculate the market value of each product. Specifically, it uses a machine learning model to score each product's indicators (price, rating, number of reviews, transaction frequency, etc.). The generative AI combines these scores to calculate the product's fair market value and converts the results into easy-to-understand formats (numbers and graphs). For example, products with high ratings and frequent transactions tend to have higher market values.

[1262] Users access the system using their own devices and enter information about the product they want to know the value of, such as "Product name: iPhone 11, Condition: Like new." The device then sends this information to the server in real time.

[1263] The server recalculates the market value of the item based on the information received from the user and returns the result to the device. The device can then display the calculation result to the user. For example, if the market value of an "iPhone 11, like new" is calculated to be "50,000 yen," the user's device will display "The fair market value is 50,000 yen." The user can use this market value as a reference when making a purchase or sale decision.

[1264] Furthermore, users can provide feedback on the displayed market value. For example, they can input their impressions such as "It sold for this price" or requests for improvement. This feedback is sent back to the server and used to improve the system.

[1265] As a result, the system of the present invention allows consumers and businesses to quickly and accurately determine fair market value based on the latest data obtained from a variety of sources, and the system can be continuously improved based on user feedback.

[1266] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1267] Step 1: Data collection

[1268] server

[1269] The server runs scheduled jobs to retrieve product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it calls APIs to retrieve price information, rating data, reviews, and transaction history. For example, it collects the latest data from Amazon and other major marketplaces at 2:00 AM every day. The input is the data request from each site, and the output is the collected product information.

[1270] Step 2: Data Preprocessing

[1271] server

[1272] The server cleans the collected data by removing outliers and missing values, standardizing currency units, and deleting duplicate data. For example, it automatically filters out abnormally high or low price data and converts prices expressed in various currencies into a single currency unit. The input is the collected raw data, and the output is cleansed, clean data. It also categorizes the condition of products into categories such as "new," "like new," "good," and "used," generating data in a consistent format.

[1273] Step 3: Standardize and index the data

[1274] server

[1275] The server standardizes the cleaned data and stores it in a database. Specifically, it converts data such as price, rating, and number of reviews into a standard format. It also indexes the data to enable quick subsequent searches and analysis. The input is the cleansed data, and the output is standardized, indexed database entries.

[1276] Step 4: Valuation

[1277] server

[1278] The server uses a generative AI model to calculate the fair market value of the product based on the collected and pre-processed data. Specifically, it uses a machine learning algorithm to score each indicator (price, rating, number of reviews, transaction frequency, etc.) and then combines them to calculate the market value. The input is standardized and indexed database data, and the output is the calculated market value (e.g., in numerical or graphical form).

[1279] Step 5: Enter user data

[1280] User

[1281] The user inputs information about the product they want to know the value of through their device. Specifically, they enter the product name, model, condition, etc. into an input form. For example, the user might enter "Product name: iPhone 11, Condition: Like new." The input is the product information the user enters into the device, and the output is the request data sent to the server.

[1282] Step 6: Sending and Receiving Data

[1283] Terminal

[1284] The terminal transmits the information input by the user to the server in real time. The server receives the input information and performs appropriate processing. The input is the product information sent by the user, and the output is a data request to the server.

[1285] Step 7: Providing market value

[1286] server

[1287] The server calculates the market value of the product based on the information received from the user and returns the result to the device. For example, if the market value of an "iPhone 11, like new" is calculated to be "50,000 yen," the result is sent to the device. The input is the product information sent by the user, and the output is the calculated market value data.

[1288] Step 8: Display Market Value

[1289] Terminal

[1290] The terminal displays the calculation results received from the server to the user. Specifically, it displays a message on the screen such as "The fair market value is 50,000 yen." The input is the market value data returned from the server, and the output is the information displayed to the user.

[1291] Step 9: Gather feedback

[1292] User

[1293] The user provides feedback on the displayed market value. Specifically, the user enters their thoughts on the evaluation and requests for improvement into an input form. For example, they provide feedback such as "It sold for this price." The input is the feedback information that the user enters into the terminal, and the output is the feedback data sent to the server.

[1294] Step 10: Use feedback

[1295] server

[1296] The server collects feedback received from users and uses it to improve the system. Specifically, it analyzes the feedback data and makes necessary adjustments to the algorithm or improves the entire system. The input is the feedback data sent by the users, and the output is the improved system function.

[1297] (Application example 1)

[1298] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1299] Currently, when users buy or sell products, it is difficult to determine whether the product has a fair market value. In addition, price and valuation information provided by different online and physical stores is inconsistent, making it difficult for users to make appropriate value judgments. Therefore, a system that allows users to quickly and accurately determine market value is needed.

[1300] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1301] In this invention, the server includes a data collection means for acquiring product information from online stores, flea markets, auction sites, and physical stores, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generative AI model to calculate the market value of the product based on the product information, a user interface means for providing the calculated market value to the user, and a feedback collection means for collecting feedback from the user and utilizing it to improve the system. This allows the user to quickly and accurately know the fair market value based on data from various information sources.

[1302] "Data collection means" refers to the means for obtaining product information from each online store, flea market, auction site, and physical store.

[1303] "Data preprocessing means" refers to means for cleansing (cleansing: removing outliers and missing values ​​in data) and standardizing (standardizing data format and units) the acquired product information.

[1304] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to calculate the market value of a product based on product information.

[1305] A "value calculation means" is a means for calculating the market value of a product based on product information using a generative AI model.

[1306] The "user interface means" is an interface for providing the calculated market value to the user, and typically refers to a smartphone application or a web page.

[1307] "Feedback collection means" refers to a means for collecting feedback from users and using it to improve the system.

[1308] "Price data" is price information for each product.

[1309] "Product evaluation" is evaluation information regarding the quality and performance of a product.

[1310] A "review" is an evaluation or comment posted by a user based on their experience using a product.

[1311] "Transaction history" is data showing the past buying and selling history and trading performance of a product.

[1312] "Scoring" is the process of calculating a product's evaluation score based on various evaluation indicators.

[1313] The following describes in detail the mode for implementing this invention. This invention is a system that organizes and analyzes product information obtained from various online stores, flea markets, auction sites, and physical stores, and calculates a fair market value using a generative AI model. The implementation method of this system is described in detail below.

[1314] Hardware and Software Configuration

[1315] 1. Server:

[1316] The server is the central function that performs all major tasks, including data collection, preprocessing, value calculation, result delivery, and feedback collection. The main technology stack used is Python, Flask, scikit-learn, Pandas, and Requests.

[1317] 2. User Device:

[1318] A smartphone or other device that acts as an interface for users to operate applications. The user interface is implemented in a browser or mobile application.

[1319] Detailed explanation of the process

[1320] 1. Data Collection:

[1321] The server periodically retrieves product information from online stores, flea markets, auction sites, and physical stores by calling public APIs. The collected data mainly includes price data, product ratings, reviews, and transaction history.

[1322] 2. Data Preprocessing:

[1323] The acquired data is cleansed and standardized on the server. Outliers and missing values ​​are removed, currency units are standardized, and duplicate data is deleted. The data is also classified according to the product's condition. The standardized data is then indexed into a database, enabling quick searches.

[1324] 3. Value estimation using generative AI models:

[1325] The server uses the collected and pre-processed data to train a generative AI model (machine learning algorithm) to calculate the fair market value of the product, which is scored based on indicators such as price, ratings, number of reviews, and transaction frequency.

[1326] 4. User Interface:

[1327] The user terminal communicates with the server via a user interface. The user inputs the product information they want to know (e.g., product name, model, condition, etc.), and the information is sent to the server in real time. The server calculates the market value and returns the result to the user terminal.

[1328] 5. Feedback Collection and System Improvement:

[1329] Users can check the displayed market value assessment and enter their thoughts and suggestions for improvement. This feedback is sent back to the server and used to improve the system.

[1330] Specific examples

[1331] For example, if a user wants to know the market value of a used smartphone, they can enter and submit the following information on their device:

[1332] Price: 15,000 yen

[1333] Rating: 4.5

[1334] Number of reviews: 50

[1335] Trading Frequency: 10

[1336] The server receives this information, calculates the market value using a generative AI model, and returns the result to the user's device: "The fair market value of this smartphone is 16,000 yen."

[1337] This allows users to quickly and accurately determine the fair market value based on data from different sources, enabling them to make appropriate value judgments.

[1338] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1339] Step 1: Data collection

[1340] The server periodically retrieves product information from various online stores, flea markets, auction sites, and physical stores. Specifically, it uses APIs to access these sources and collect data such as price data, product ratings, reviews, and transaction history. For example, it calls an API endpoint and receives a JSON-formatted response. The input is the API URL, and the output is the retrieved product information.

[1341] Step 2: Data Preprocessing

[1342] The server cleanses and standardizes the collected product information. This involves removing outliers and missing values, standardizing currency units, and deleting duplicate data. It also classifies the product condition into categories such as "new," "like new," "good," and "used." Specifically, it uses the Pandas library to remove NaN values ​​and standardizes currency units through string manipulation. The input is the product information obtained in step 1, and the output is the cleansed and standardized data.

[1343] Step 3: Data Standardization

[1344] To standardize the cleansed data, the server converts each attribute (price, rating, etc.) to a certain scale. Specifically, it uses scikit-learn's StandardScaler. This allows attributes with different units to be compared on a common scale. The input is the data processed in step 2, and the output is the standardized data.

[1345] Step 4: Training the generative AI model

[1346] The server uses the standardized data to train a generative AI model. Specifically, it trains a machine learning model (e.g., a linear regression model) using features such as the product price, rating, number of reviews, and transaction frequency. The input is the standardized data obtained in step 3, and the output is the trained generative AI model.

[1347] Step 5: Receiving User Input

[1348] The user inputs information about the target product (price, rating, number of reviews, transaction frequency, etc.) from a terminal (such as a smartphone). The terminal collects this information and sends it to the server in real time. The input is the product information entered on the terminal, and the output is the data sent to the server.

[1349] Step 6: Calculate market value

[1350] The server calculates the market value of the product using a trained generative AI model based on the information received from the user. Specifically, it inputs the features entered by the user into the model and predicts the market value. The inputs are the data sent by the user and the generative AI model, and the output is the calculated market value.

[1351] Step 7: Deliver value

[1352] The server returns the calculated market value to the user's terminal. The terminal receives the market value and displays it to the user through a user interface, whose input is the market value calculated in step 6 and whose output is the market value information displayed on the user's terminal.

[1353] Step 8: Gather feedback

[1354] The user inputs their evaluation impressions and requests for improvement based on the displayed market value. The terminal sends this feedback to the server. The server collects this feedback and uses it to improve the system. The input is the user's feedback information, and the output is the collected feedback data.

[1355] Through the above steps, the present invention allows users to quickly and accurately determine the fair market value of an item.

[1356] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1357] This invention relates to a system that collects product information from online stores, flea markets, auction sites, and brick-and-mortar stores, calculates and provides a fair market value, and by combining it with an emotion engine that recognizes user emotions, achieves more accurate value provision and feedback analysis. Below, we will explain how the system program works, using specific examples.

[1358] System Program

[1359] Data collection

[1360] server

[1361] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores, specifically price information, rating data, reviews, transaction history, etc. This allows the collection of the latest information from a variety of data sources.

[1362] Data Preprocessing

[1363] server

[1364] The server cleans the collected data, removing outliers and missing values, standardizing currency units, and removing duplicate data. It then standardizes the data to make it consistent. It also analyzes the condition of products to categorize them into categories such as "new," "like new," "good," and "used." The data is then indexed, allowing the information in the database to be quickly searched.

[1365] Value estimation using generative AI

[1366] server

[1367] The server uses a machine learning model to score each indicator of product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs).

[1368] User Interface

[1369] Terminal (user)

[1370] The user accesses the system through a terminal and inputs information about the product for which they want to know the value, such as the product name, model, and condition. The terminal then sends this information to the server in real time.

[1371] Delivering value and gathering feedback

[1372] server

[1373] Based on the information received from the user, the server calculates the fair market value of the item and returns the result to the terminal. The terminal then displays this calculation result to the user. After checking the displayed value assessment, the user can enter their thoughts on the assessment and requests for improvement. This feedback is sent back to the server and used to improve the system. In addition, the emotion engine uses text analysis and voice recognition technology on the user's feedback to recognize the user's emotions.

[1374] Emotion recognition by emotion engine

[1375] server

[1376] The server recognizes the user's emotions by analyzing the text and voice data of the feedback using an emotion engine. Text analysis identifies positive, negative, and neutral emotions from the user's written feedback. It also uses speech recognition technology to understand emotional nuances from the tone, speed, and intonation of the voice.

[1377] Feedback analysis and system improvement

[1378] server

[1379] The server stores the user emotion data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotion data is reflected in improvements to the system. For example, if many users express negative emotions toward a particular product, the system may consider adjusting the evaluation algorithm for that product.

[1380] Specific examples

[1381] For example, consider the case where a user wants to know the market value of a used smartphone.

[1382] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from major online markets and flea markets.

[1383] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[1384] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of "15,000 yen" based on the price, valuation, and transaction history.

[1385] 4. The user enters the model and condition of the used smartphone from their own device.

[1386] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[1387] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user.

[1388] 7. Users can enter their thoughts on the value assessment and requests for improvements in the feedback form. They can provide feedback via text and voice.

[1389] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if there are a lot of negative emotions, it adjusts the evaluation algorithm.

[1390] This allows users to quickly and accurately determine fair market value based on data from a variety of sources, and the system is continuously improved through feedback analysis based on user sentiment.

[1391] The processing flow will be explained below.

[1392] Step 1:

[1393] The server periodically calls APIs to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. Specifically, it collects price information, product ratings, reviews, and transaction history. This information is temporarily stored in a buffer area.

[1394] Step 2:

[1395] The server cleans the data stored in the buffer area. This includes detecting and deleting or correcting outliers (e.g., extreme prices) and missing values ​​(e.g., data with no evaluations). At the same time, it unifies different currency units and converts them to Japanese yen.

[1396] Step 3:

[1397] The server stores the cleaned data in a database: price information in the Price table, rating data in the Rating table, reviews in the Review table, and transaction history in the Transaction table. It also runs an algorithm to classify the condition of the products into categories of "new," "like new," "good," and "used."

[1398] Step 4:

[1399] The server uses machine learning models to score each metric of the stored product information (price, rating, number of reviews, transaction frequency, etc.). The generation AI then combines these scores to calculate the fair market value of the product, which is then converted into numerical and graphical formats.

[1400] Step 5:

[1401] The user uses the device's user interface to input information about the product for which they want to know the value. Input fields include the product name, model, and condition. The information entered by the user is sent to the server in real time.

[1402] Step 6:

[1403] The server analyzes the product information received from the user and compares it with the corresponding product data in the database. Based on the comparison results, it recalculates the fair market value. This recalculated market value is converted into data to be sent to the terminal.

[1404] Step 7:

[1405] The terminal displays the fair market value sent from the server to the user in the form of numbers, graphs, or rankings, making it easy for the user to understand.

[1406] Step 8:

[1407] Users can enter their thoughts on the displayed market value and requests for improvement in a feedback form. Feedback can be given not only by text but also by voice. Once feedback is complete, the device sends the data to the server.

[1408] Step 9:

[1409] The server receives the feedback data sent by the user and analyzes it with an emotion engine. Text analysis is used to identify positive, negative, neutral, and other emotions from the feedback text. At the same time, voice data is analyzed to understand the user's emotions from the tone, speed, and intonation of the voice.

[1410] Step 10:

[1411] The server stores the recognized emotion data in a database and periodically analyzes it. The analysis results are used to improve the machine learning model and update the system as a whole. For example, if many users express negative emotions in rating a particular product, the rating algorithm for that product will be revised.

[1412] This detailed flow enables the present invention to provide fair market value based on diverse data and continuously improve the system through feedback analysis that takes into account user sentiment.

[1413] Example 2

[1414] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1415] Conventional market value calculation systems did not adequately address inconsistencies, duplications, or missing product information obtained from a wide variety of data sources, resulting in inaccurate market values. Furthermore, user feedback was not fully utilized to improve the system, resulting in a lack of improvement in the quality of the user experience. Furthermore, there was a lack of technology to recognize user emotions and reflect them in system improvements, making it difficult to increase user satisfaction.

[1416] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1417] In this invention, the server includes a data collection means for acquiring product information from various online stores, online markets, e-commerce platforms, and physical stores, a data preprocessing means for cleaning and standardizing the acquired product information, and a value calculation means using generative AI to calculate the market value of the product based on the product information. This makes it possible to organize inconsistent data from various sources into a consistent form and calculate a fair market value using a machine learning model. Furthermore, by applying a user interface means for users to input product information and provide the calculated market value, an emotion engine for collecting user feedback and recognizing the emotion of the feedback, and a feedback collection means for improving the system based on the collected feedback, user feedback can be effectively utilized to improve the system.

[1418] An "online store" is an e-commerce platform that sells goods and services over the Internet.

[1419] An "online market" is an online commercial platform where multiple sellers come together to offer products and services.

[1420] An "e-commerce platform" is an online system for buying and selling goods and services electronically.

[1421] A "physical store" is a physical building where goods or services are sold in person.

[1422] "Data collection means" means the mechanism or technology used to obtain product information from various data sources.

[1423] "Data pre-processing means" refers to the process of cleaning and standardizing acquired data.

[1424] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[1425] A "value calculation means" is a method or system for calculating the market value of a commodity based on commodity information.

[1426] The "user interface means" is an interface through which a user interacts with the system, and is a means for inputting data and displaying output.

[1427] A "feedback collection means" is a method or system for collecting user ratings and opinions.

[1428] An "emotion engine" is a technology for analyzing and recognizing emotions from user feedback data.

[1429] A "machine learning model" is an artificial intelligence algorithm that learns from training data and makes predictions or classifications based on new data.

[1430] This invention is a system that collects product information from online stores, online markets, e-commerce platforms, and physical stores, calculates and provides fair market value, and by combining it with an emotion engine that recognizes user emotions, it achieves more accurate value provision and feedback analysis.

[1431] System configuration

[1432] The system uses the following hardware and software components:

[1433] server

[1434] Data collection methods

[1435] Data preprocessing measures

[1436] Value calculation method using generative AI

[1437] Feedback collection methods

[1438] Emotion Engine

[1439] Terminal (user device)

[1440] User Interface Means

[1441] Data collection methods

[1442] The server collects product information from online stores, online markets, e-commerce platforms, and physical stores using common API endpoints. For example, to get information from Amazon, eBay, and local online markets, it calls the API endpoints of each platform. Data collection is scheduled periodically, and the latest data is retrieved regularly.

[1443] Data preprocessing measures

[1444] The server cleans and standardizes the acquired data. It removes outliers and missing values, standardizes currency units, and deletes duplicate data. Specifically, it uses the Python Pandas library to clean and standardize the data. It also analyzes the product condition to classify it into "new," "like new," "good," and "used."

[1445] Value calculation method using generative AI

[1446] The server uses a machine learning model to score product information and calculate a fair market value. This uses machine learning libraries such as TensorFlow. Variables such as price information, product ratings, number of reviews, and transaction frequency are used as inputs to generate the AI.

[1447] User Interface Means

[1448] Users access the system using their own devices (such as smartphones or computers) and enter product information. For example, they enter information such as "product name," "model," and "condition" in real time. The entered information is immediately sent to the server.

[1449] Delivering value and gathering feedback

[1450] The server analyzes the product information received from the user and calculates a fair market value. The result is sent back to the terminal, which displays it to the user. The user checks the displayed market value and enters their thoughts and requests for improvement in a feedback form. The feedback entered by the user is sent back to the server and analyzed by the emotion engine.

[1451] Emotion Engine

[1452] The server analyzes the feedback collected from users using an emotion engine. Text analysis is used to identify positive, negative, or neutral emotions from the feedback written by the user. Speech recognition technology is also used to understand emotional nuances from the tone and intonation of the voice.

[1453] Feedback analysis and system improvement

[1454] The server stores the emotional data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotional data is reflected in improvements to the system. For example, if many users express negative emotions about a particular product, the system may consider adjusting the evaluation algorithm for that product.

[1455] Specific examples

[1456] For example, consider the case where a user wants to know the market value of a used smartphone.

[1457] 1. The server collects price information, rating data, reviews, and transaction history of used smartphones from each online market.

[1458] 2. The server cleans the collected data, standardizes the currency unit, and classifies the condition of the product as "like new," "good," or "used."

[1459] 3. The server uses a machine learning model to score the indicators of each product. The generative AI calculates a fair market value of 15,000 yen based on the price, valuation, and transaction history.

[1460] 4. The user enters the model and condition of the used smartphone from their own device.

[1461] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[1462] 6. The terminal displays the fair market value of "15,000 yen" received from the server to the user.

[1463] 7. Users can enter their thoughts on the value assessment and requests for improvement in the feedback form. They can provide feedback via text and voice.

[1464] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if there are a lot of negative emotions, it adjusts the evaluation algorithm.

[1465] The system allows users to quickly and accurately determine fair market value based on data from a variety of sources, and feedback analysis based on user sentiment allows for continuous improvement of the system.

[1466] Prompt Sentence Examples

[1467] The following prompt sentences are used to provide examples of how to input specific system behavior into the model:

[1468] "You are developing a program to calculate the market value of smartphones based on price information collected from online stores, flea markets, and auction sites. Using the information below, explain how you would collect, preprocess, and analyze the data to calculate a fair market value. Then, explain how you would improve the system based on user feedback."

[1469] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1470] Step 1: Data collection

[1471] The server retrieves product information from various online stores, online markets, e-commerce platforms, and physical stores. This process involves sending a request to an API endpoint, such as "GET / products?category=electronics&condition=used" to retrieve price information, rating data, reviews, transaction history, etc. The input is the API request, and the output is the response data with product information.

[1472] Specifically, the server sends a "GET / products" request to Amazon's API and stores the received data.

[1473] Step 2: Data Preprocessing

[1474] The server cleans and standardizes the acquired product information. In this step, outliers and missing values ​​are removed, currency units are standardized, and duplicate data is deleted. The Python Pandas library is used for data frame operations. The input is the product information data acquired in step 1, and the output is the cleaned and standardized product information data.

[1475] Specifically, the server uses Pandas to remove records with zero prices in the data frame and convert all currency units to USD.

[1476] Step 3: Value estimation using generative AI

[1477] The server uses a machine learning model to score product information and calculate market value. Standardized product information data obtained through data preprocessing is used as input. Generative AI (such as TensorFlow) is used to score price, rating, number of reviews, transaction frequency, etc. to calculate a fair market value. The output is the market value of each product.

[1478] Specifically, the server loads the TensorFlow model, inputs the price, rating, and number of reviews, and calculates the market value as "15,000 yen."

[1479] Step 4: Entering information in the user interface

[1480] The user inputs information about the product they wish to have appraised from their terminal. For example, they input information such as "product name," "model," and "condition," and this information is sent to the server in real time. The input is information from the user's terminal, and the output is data sent to the server.

[1481] Specifically, the user enters "iPhone 11, used, good condition" into the device's web form and clicks the submit button.

[1482] Step 5: Deliver value and gather feedback

[1483] The server calculates the market value based on the information from the user and returns the result to the terminal. The terminal displays this result to the user. The user checks the displayed market value and enters their thoughts and requests for improvement in a feedback form. The input is the market value calculation by the server and the user's feedback, and the output is the market value display and feedback transmission to the user.

[1484] Specifically, the server calculates the market value of "15,000 yen" and returns it to the terminal, which then displays it to the user. The user then enters "The accuracy is high and I'm satisfied" in the feedback form.

[1485] Step 6: Emotion Recognition with the Emotion Engine

[1486] The server analyzes the user feedback with an emotion engine to recognize emotions. The input is the user feedback data, and the output is the emotion analysis result. Text analysis and speech recognition technologies are used to identify the user's emotions.

[1487] Specifically, the server uses an NLP library to recognize positive emotions from feedback such as "I'm happy."

[1488] Step 7: Feedback analysis and system improvement

[1489] The server stores the emotion data analyzed by the emotion engine in a database and periodically analyzes it. The input is the emotion analysis results, and the output is a proposal for improving the system. Based on the analysis results, issues with the system are identified and the system is improved.

[1490] Specifically, the server analyzes the feedback emotion data every month and adjusts the algorithm when many users show negative emotions.

[1491] The above is a concrete explanation of the program processing of this system, broken down into steps.

[1492] (Application example 2)

[1493] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1494] In recent years, with the diversification of content distribution services, users are required to select what to watch from a vast amount of content. However, the lack of reliable information for users is a problem, as it is difficult to fairly grasp the ratings and market value of content. In addition, there is a lack of personalized recommendations based on viewing history and feedback, and innovations are needed to improve the user experience.

[1495] The identification processing by the identification 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 a data collection means for acquiring product information from each content distribution service, a data preprocessing means for cleansing and standardizing the acquired product information, a value calculation means using a generative AI for calculating the market value of the product based on the product information, a user interface means for providing the calculated market value to the user, a feedback collection means for collecting feedback from the user and using it to improve the system, an emotion analysis means for analyzing the user feedback and recognizing the user's emotions, and a means for improving the system based on the analyzed emotion data. This makes it easier for users to obtain reliable market value information and enables personalized content recommendations based on individual preferences.

[1496] The "data collection means" is a part that has the function of acquiring product information from each content distribution service.

[1497] The "data preprocessing means" is a part that has the function of cleansing and standardizing the acquired product information.

[1498] The "value calculation means" is the part that has the function of calculating the market value of a product based on product information using a generation AI.

[1499] The "user interface means" is a part having a function of providing the calculated market value to the user.

[1500] The "feedback collection means" is a part that has the function of collecting feedback from users and utilizing it to improve the system.

[1501] The "emotion analysis means" is a part that has the function of analyzing user feedback and recognizing the user's emotions.

[1502] The "means for improving the system" is a part that has the function of improving the system based on the analyzed emotion data.

[1503] "Product Information" refers to information related to the content, such as number of views, ratings, reviews, and viewing history.

[1504] "Generative AI" refers to artificial intelligence technology used to calculate market value based on product information.

[1505] The present invention is a system that acquires product information from a content distribution service, calculates a fair market value based on that information, provides it to users, and analyzes user feedback to improve the system. Below, we will explain how the program for this system works, using specific examples.

[1506] System Program

[1507] Data collection

[1508] server

[1509] The server periodically calls APIs to obtain product information from each content distribution service (e.g., video services, music distribution platforms, etc.). Specifically, the information being obtained includes the number of views, ratings, reviews, and viewing history. This allows the latest information to be collected from a variety of data sources.

[1510] Data Preprocessing

[1511] server

[1512] The server cleans and standardizes the collected data. This includes removing outliers and missing values, standardizing the data, normalizing view counts, standardizing rating scores, and analyzing the text of reviews. The data is then indexed, allowing for quick searches of information in the database. The software used for this is the Python libraries Pandas and NumPy.

[1513] Value estimation using generative AI

[1514] server

[1515] The server uses a machine learning model to score each indicator of product information (number of views, rating, number of reviews, viewing frequency, etc.). The generation AI combines these scores to calculate the fair market value of the product. The results are converted into a user-friendly format (numbers and graphs). The software used here includes TensorFlow and Scikit-Learn.

[1516] User Interface

[1517] Terminal (user)

[1518] Users access the service through their device (smartphone, PC, smart TV, etc.) and enter information about the content they want to know the value of, such as the content name, platform, and rating. The device then sends this information to the server in real time.

[1519] Delivering value and gathering feedback

[1520] server

[1521] Based on the information received from the user, the server calculates the fair market value of the content and sends the result back to the terminal. The terminal displays this calculation result to the user. The user can check the displayed value assessment and then enter their thoughts on the assessment or requests for improvement. This feedback is sent back to the server and used to improve the system.

[1522] Emotion recognition by emotion engine

[1523] server

[1524] The server recognizes the user's emotions by analyzing the text and voice data of the feedback with an emotion engine. It uses the Natural Language Toolkit (NLTK) for text analysis and Google Cloud Speech-to-Text for voice recognition. This allows it to identify positive, negative, or neutral emotions from the user's description.

[1525] Feedback analysis and system improvement

[1526] server

[1527] The server stores the user's emotional data analyzed by the emotion engine in a database and periodically analyzes it. The analyzed emotional data is reflected in improvements to the system. For example, if many users have a positive reaction to a particular piece of content, the server may consider increasing the frequency with which that content is recommended.

[1528] Specific examples

[1529] For example, suppose a user wants to know the market value of a movie.

[1530] 1. The server collects movie view counts, ratings, reviews, and viewing history from major content distribution services.

[1531] 2. The server cleans and standardizes the collected data, normalizing view counts and standardizing rating scores.

[1532] 3. The server uses a machine learning model to score the metrics of each piece of content. The AI ​​generator calculates a fair market value of 8.5 / 10 based on the number of views, ratings, and reviews.

[1533] 4. The user enters the movie title and platform on their device.

[1534] 5. The terminal sends the input information to the server, and the server returns the calculation results to the terminal.

[1535] 6. The terminal displays the fair market value received from the server, "8.5 / 10", to the user.

[1536] 7. Users can enter their thoughts on the value assessment and requests for improvements in the feedback form. They can provide feedback via text and voice.

[1537] 8. The server analyzes the feedback using an emotion engine to recognize the user's emotions. For example, if many users express positive emotions, the system adjusts its recommendation algorithm based on that information.

[1538] Prompt Sentence Examples

[1539] Title: Inception

[1540] Platform: Streaming Service

[1541] Rating: 9.5

[1542] User Reviews: Positive

[1543] User Comments: "Amazing plot and visual effects!"

[1544] Calculate fair market value and provide summary score.

[1545] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1546] Step 1: Data collection

[1547] The server periodically collects product information from each content distribution service (video service, music distribution platform, etc.) via API. Specifically, it obtains information such as the number of views, ratings, reviews, and viewing history. The input is the response data from the API, and the output is the collected raw data.

[1548] Step 2: Data Preprocessing

[1549] The server cleans and standardizes the data collected in step 1. Data cleaning involves removing outliers and missing values. Next, it normalizes the number of views and rating scores, and performs text analysis on the reviews to categorize them. The input is raw data, and the output is cleansed and standardized data.

[1550] Step 3: Index the data

[1551] The server indexes the preprocessed data, allowing for quick searches of information in the database. The software used is MySQL or MongoDB. The input is the preprocessed data, and the output is the indexed data.

[1552] Step 4: Valuation

[1553] The server uses a machine learning model to score each indicator of product information (number of views, rating, number of reviews, viewing frequency, etc.). A generative AI model combines these scores to calculate a fair market value. The software used is TensorFlow and Scikit-Learn. The input is the indexed data, and the output is the calculated market value.

[1554] Step 5: Provide a user interface

[1555] The terminal provides an interface for users to input information about the content they want to know the value of. The user inputs information such as the "content name," "platform," and "rating," and the terminal sends this information to the server. The input is the information entered by the user, and the output is the data to be sent to the server.

[1556] Step 6: Delivering valuation results

[1557] The server calculates the market value based on the information received from the user and returns the result to the terminal. The terminal displays the calculation result to the user. The input is the user information and the calculation result, and the output is the market value displayed to the user.

[1558] Step 7: Gather feedback

[1559] The terminal allows the user to input their thoughts and requests for improvement about the displayed market value into a feedback form. The user provides feedback by text or voice, and the terminal sends this information to the server. The input is the user's feedback, and the output is data to be sent to the server.

[1560] Step 8: Sentiment Analysis

[1561] The server analyzes the feedback text and audio data using an emotion engine. It uses the Natural Language Toolkit (NLTK) and Google Cloud Speech-to-Text to identify the user's emotions. The input is the feedback data, and the output is the analysis result.

[1562] Step 9: System Improvement

[1563] The server stores the analyzed emotional data in a database and periodically analyzes it. This information is used to improve the system. For example, it adjusts the algorithm to prioritize recommending content with a high number of positive reactions. The input is emotional data, and the output is improved system parameters.

[1564] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1565] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1566] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1567] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1568] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1569] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1570] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1571] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1572] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1573] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1574] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1575] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1576] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1577] 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.

[1578] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1579] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1580] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1581] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1582] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1583] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1584] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1585] The following is further disclosed regarding the above embodiment.

[1586] (Claim 1)

[1587] A data collection method to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores.

[1588] a data preprocessing means for cleansing and standardizing the acquired product information;

[1589] A value calculation means using a generation AI that calculates the market value of a product based on product information;

[1590] a user interface means for providing the calculated market value to a user;

[1591] A feedback collection means for collecting feedback from users and utilizing it to improve the system;

[1592] A system including:

[1593] (Claim 2)

[1594] 10. The system of claim 1, wherein the product information includes price information, product ratings, reviews, and transaction history.

[1595] (Claim 3)

[1596] The system of claim 1, wherein the generating AI uses a machine learning model to score product information and calculate a fair market value.

[1597] "Example 1"

[1598] (Claim 1)

[1599] A data collection method for acquiring product information from online stores, flea markets, auction sites, and brick-and-mortar stores;

[1600] a data preprocessing means for cleaning and standardizing the acquired product information;

[1601] a value calculation means for calculating a fair market value by scoring each indicator of the product information using a generative AI model;

[1602] a user interface means for allowing a user to input product information through a terminal and for providing a calculated market value;

[1603] A feedback collection means for collecting feedback from users and utilizing it to improve the system;

[1604] A system including:

[1605] (Claim 2)

[1606] 10. The system of claim 1, wherein the product information includes price information, product ratings, reviews, and transaction history.

[1607] (Claim 3)

[1608] 2. The system of claim 1, wherein the generative AI model uses a machine learning algorithm to score product information and calculate a fair market value.

[1609] "Application Example 1"

[1610] (Claim 1)

[1611] A data collection method for obtaining product information from online stores, flea markets, auction sites, and physical stores;

[1612] a data preprocessing means for cleansing and standardizing the acquired product information;

[1613] a value calculation means using a generative AI model that calculates the market value of a product based on product information;

[1614] a user interface means for providing the calculated market value to a user;

[1615] A feedback collection means for collecting feedback from users and utilizing it to improve the system;

[1616] A system including:

[1617] (Claim 2)

[1618] 10. The system of claim 1, wherein the product information includes price data, product ratings, reviews, and transaction history.

[1619] (Claim 3)

[1620] 2. The system of claim 1, wherein the generative AI model uses a machine learning algorithm to score product information and calculate a fair market value.

[1621] "Example 2: Combining Emotion Engines"

[1622] (Claim 1)

[1623] A data collection means for obtaining product information from each online store, online marketplace, e-commerce platform, and physical store;

[1624] a data preprocessing means for cleaning and standardizing the acquired product information;

[1625] A value calculation means using a generation AI that calculates the market value of a product based on product information;

[1626] a user interface means for allowing a user to input product information and providing the calculated market value to the user;

[1627] an emotion engine that collects feedback from users and recognizes the emotion of the feedback;

[1628] a feedback collection means for improving the system based on the collected feedback;

[1629] A system including:

[1630] (Claim 2)

[1631] 10. The system of claim 1, wherein the product information includes price information, product ratings, reviews, and transaction history.

[1632] (Claim 3)

[1633] The system of claim 1, wherein the generating AI uses a machine learning model to score product information and calculate a fair market value.

[1634] "Application example 2 when combining emotion engines"

[1635] (Claim 1)

[1636] a data collection means for acquiring product information from each content distribution service;

[1637] a data preprocessing means for cleansing and standardizing the acquired product information;

[1638] A value calculation means using a generation AI that calculates the market value of a product based on product information;

[1639] a user interface means for providing the calculated market value to a user;

[1640] A feedback collection means for collecting feedback from users and utilizing it to improve the system;

[1641] emotion analysis means for analyzing user feedback and recognizing user emotions;

[1642] A means for improving the system based on the analyzed emotion data; and

[1643] A system including:

[1644] (Claim 2)

[1645] The system of claim 1, wherein the product information includes view counts, ratings, reviews, and viewing history.

[1646] (Claim 3)

[1647] The system of claim 1, wherein the generating AI uses a machine learning model to score product information and calculate a fair market value. [Explanation of symbols]

[1648] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method to obtain product information from online stores, flea markets, auction sites, and brick-and-mortar stores. a data preprocessing means for cleansing and standardizing the acquired product information; A value calculation means using a generation AI that calculates the market value of a product based on product information; a user interface means for providing the calculated market value to a user; A feedback collection means for collecting feedback from users and utilizing it to improve the system; A system including:

2. The system of claim 1 , wherein the product information includes price information, product ratings, reviews, and transaction history.

3. The system of claim 1, wherein the generating AI uses a machine learning model to score product information and calculate a fair market value.

Images