system

Abstract

We provide the system. [Solution] A means for inputting product video data, A means for storing the aforementioned product video data, A means of referring to a database of past listing videos, A means for comparing the aforementioned product video data with video data in the aforementioned past listing video database to determine the condition of the product, A means for setting a fair price for a product based on the aforementioned product condition, A means for generating a product description based on the aforementioned product condition and the aforementioned appropriate price, A means for presenting the aforementioned product condition, the aforementioned appropriate price, and the aforementioned product description to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional free market apps, when a user offers a product, there are problems such as the need for a lot of labor, such as taking pictures of the product, creating a description text, and setting an appropriate price. Due to this labor, there are many cases where many users give up offering products. Also, it is difficult to set an appropriate price, and there is a possibility of unsold items or losses. The present invention aims to solve these problems and enable users to offer products more easily and efficiently.

Means for Solving the Problems

[0005] The system of the present invention includes the following means:

[0006] 1. Means for inputting product video data

[0007] It provides a means for users to film product footage and input it into the system.

[0008] 2. Means for storing the aforementioned product video data

[0009] This system provides a means for saving input product video data, facilitating data retention and subsequent processing.

[0010] 3. Means of referring to a database of past listing videos

[0011] This system provides a means to obtain comparison targets by referring to a database of videos of products previously listed for sale.

[0012] 4. Means for comparing the product video data with the video data in the past listing video database to determine the product condition.

[0013] This system provides a method for automatically determining the condition of a product by comparing and analyzing input product video data with video data from a database of past listing videos.

[0014] 5. Means for setting an appropriate price for a product based on the aforementioned product condition.

[0015] This system provides a means to automatically set an appropriate selling price by referring to past data based on the determined condition of the product.

[0016] 6. Means for generating a product description based on the product condition and the appropriate price.

[0017] This system provides a means for automatically generating product descriptions based on the product's condition and appropriate price.

[0018] 7. Means for presenting the product condition, the appropriate price, and the product description to the user.

[0019] Provide means for displaying to the user the determined product condition, the set appropriate price, and the generated product description text.

[0020] Furthermore, the system of the present invention includes means for enabling the user to edit the generated product description text and appropriate price, and means for analyzing product video data using an image recognition algorithm, thereby providing more accurate listing information and significantly reducing the user's effort.

[0021] "Product video data" is data in the form of a video obtained by shooting the product that the user offers for sale.

[0022] "Means for inputting" is an interface or process used by the user to upload product video data to the system.

[0023] "Means for storing" is a technology or system for holding the uploaded product video data in a server or storage device.

[0024] "Database of past listing video data" is a database that accumulates video data and related information of products that were previously listed.

[0025] "Means for referring" is a process for searching and obtaining necessary video data from the database of past listing video data.

[0026] "Means for comparing and determining the product condition" is an algorithm or system that compares the input product video data with the past listing video data and determines the condition of the product.

[0027] [[ID=-31]] "Means for setting the appropriate price of the product" is an algorithm or system that calculates an appropriate selling price while referring to past data based on the determined product condition.

[0028] "Methods for generating product descriptions" refer to technologies and systems for automatically creating product descriptions.

[0029] "Means of presentation to the user" refers to the interface or process by which the system displays the judgment result, appropriate price, and product description on the user's device. [Brief explanation of the drawing]

[0030] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0031] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0032] First, let's explain the terminology used in the following explanation.

[0033] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0034] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0035] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0036] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0037] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0038] [First Embodiment]

[0039] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0040] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0041] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0042] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0043] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0044] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0045] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0046] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0047] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0048] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0049] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0050] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0051] Embodiments of the present invention will be described in detail below.

[0052] This invention provides a system that supports listing products by automatically generating product condition, appropriate price, and description simply by having the user film product images and upload them to a flea market application. This significantly reduces the effort required from the user and enables efficient listing.

[0053] The system consists of a server and user terminals. First, the user takes a video of the item they want to sell using their terminal. This video must include detailed information about the item. Next, the user uploads the video to the server through the flea market app.

[0054] The server receives and stores the uploaded product video data. The stored product video data is then compared with the video database on the server. This video database contains video data of previously listed products, their condition, and their selling prices.

[0055] The server uses an image recognition algorithm to compare uploaded product video data with past listing video data in the database. Based on this comparison, the server automatically determines the product's condition. The condition is categorized into several categories, such as "new / unused," "almost new," "good," and "used."

[0056] Next, the server sets an appropriate selling price based on the determined condition of the product, referencing data from similar products in the past. This appropriate price is calculated based on the prices at which similar products in the same category were traded in the past.

[0057] Furthermore, the server automatically generates a product description based on the product's condition and appropriate price. This description is generated from the original template and includes detailed information about the product, such as its condition and selling price.

[0058] Finally, the server displays the generated product description, the determined condition, and the set appropriate price to the user's device. The user can review this information and edit it as needed. Once editing is complete, the user can finally list the product for sale.

[0059] Specific example:

[0060] User A wants to sell a used smartphone and takes detailed video footage of the smartphone. Next, User A uploads this video to a server through a flea market application. The server receives and saves the video and compares it with video data of similar smartphones from the past.

[0061] Based on the video comparison, the server determines that User A's smartphone is in "almost new" condition. It also sets the appropriate price at 35,000 yen based on past data. Next, the server automatically generates a product description like the following:

[0062] "I'm selling a smartphone that's barely been used. It's in excellent condition, practically brand new. The price is 35,000 yen."

[0063] This information is displayed to User A's device, and User A reviews the content and edits the description and price as needed. After editing is complete, User A can proceed with the listing process and list their smartphone for sale on the flea market.

[0064] The above describes the embodiment of the present invention. This embodiment enables users to list products efficiently without any hassle.

[0065] The following describes the processing flow.

[0066] Step 1:

[0067] Users film product footage and upload it to the system using their devices.

[0068] Users use devices such as smartphones or tablets to take detailed videos of the items they want to list for sale.

[0069] After filming is complete, the video files are uploaded to the server via a flea market app.

[0070] Step 2:

[0071] The server receives and saves the uploaded product video data.

[0072] The server receives the video file sent by the user.

[0073] The received video data is saved to a temporary storage directory, and the metadata of that file (e.g., upload date and time, user ID, etc.) is also recorded.

[0074] Step 3:

[0075] The server searches for similar products by referring to a database of past listing videos.

[0076] The server retrieves video data of previously listed products from the database.

[0077] Video data is filtered based on metadata such as product category, manufacturer, and model number to select appropriate comparison targets.

[0078] Step 4:

[0079] The server uses video comparison technology to analyze and compare product video data.

[0080] The server analyzes product video data frame by frame using image recognition algorithms (such as CNN or SIFT).

[0081] Based on the analyzed data, we compare it with video data of similar products to extract features related to the condition of the product.

[0082] Step 5:

[0083] The server determines the condition of the product based on the video comparison results.

[0084] The server determines the condition category to which the product belongs based on the extracted features.

[0085] The condition category can be selected from options such as "New / Unused," "Like New," "Good," and "Used."

[0086] Step 6:

[0087] The server sets an appropriate selling price based on data on the condition and selling price of similar products from the past.

[0088] The server uses past data of similar products as a reference to determine the price based on the determined condition category.

[0089] The optimal selling price is calculated by utilizing statistical data such as the average price, median price, and latest transaction price.

[0090] Step 7:

[0091] The server automatically generates a product description based on the product's condition and pricing.

[0092] The server generates product descriptions based on a template.

[0093] The generated description will include a detailed description of the product's condition and its selling price.

[0094] Step 8:

[0095] The server displays the generated description, the determined condition, and the set selling price to the user.

[0096] The server displays the generated description and pricing information on the user's device.

[0097] Users can review the presented content and make corrections as needed.

[0098] Step 9:

[0099] The user reviews and edits the product information, and finally completes the listing process.

[0100] The user edits the provided product information, and if they are satisfied with the content, they press the "List Item" button to complete the listing process.

[0101] The final listing information is sent to the server and posted on the flea market app.

[0102] Through the above processing steps, users can easily list products and save a lot of time and effort.

[0103] (Example 1)

[0104] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0105] Current flea market applications present a problem: users must create detailed descriptions for each item they list and set appropriate prices, a process that is extremely time-consuming and laborious. Furthermore, accurately assessing the condition of an item requires specialized knowledge, making it difficult for the average user. As a result, users have to expend a great deal of effort when listing items, making efficient listing difficult.

[0106] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0107] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a database of past listing videos, means for comparing the product video data with video data in the database of past listing videos to determine the condition of the product, means for setting an appropriate price for the product based on the condition of the product, means for using a generation AI to generate a product description, means for generating a product description based on the condition of the product and the appropriate price, and means for presenting the condition of the product, the appropriate price, and the product description to the user. As a result, users can simply upload product videos, and the system will automatically determine the condition of the product, set an appropriate price, and generate a product description, enabling efficient listing.

[0108] "Product video data" refers to video information about products listed by users, and is data that visually records the detailed condition and characteristics of the product.

[0109] "Means of storage" refers to a system for storing and managing received product video data in a database or storage device.

[0110] "Means of reference" refers to a system that allows users to view past listing video data and use it for comparison and analysis.

[0111] "Means for comparing and determining the condition of a product" refers to algorithms or software that compare product video data with video data from a database of past listing videos and automatically classify and evaluate the condition of the product.

[0112] "Methods for setting appropriate prices" refer to systems for calculating the optimal selling price of a product based on its condition and past transaction data.

[0113] "Methods of using generative AI" refer to systems that use artificial intelligence technology to automatically create and generate text and data.

[0114] "Methods for generating product descriptions" refers to a function that automatically generates user-oriented descriptions based on elements such as product details, condition, and price.

[0115] "Means of presentation to the user" refers to an interface that provides the user with the generated product description, the determined product condition, and the set appropriate price, allowing the user to review and edit them.

[0116] This invention supports listing products by allowing users to simply film product images and upload them to a flea market application. The system automatically generates product condition, appropriate price, and description, significantly reducing user effort and enabling efficient listing. The details are described below.

[0117] The system consists of a server and user terminals. First, the user takes a video of the item they want to sell using their terminal. This video must include detailed information about the item. Next, the user uploads the video to the server through a flea market application.

[0118] The server receives uploaded product video data and has a database for storing it. The stored product video data is compared with the video database on the server, which includes video data of previously listed products, their condition, and sales price.

[0119] Image data analysis utilizes image recognition algorithms such as TENSORFLOW® and PyTorch. The server uses these algorithms to compare uploaded product video data with past listing video data, automatically determining the product's condition. The condition is categorized into several categories, including "new / unused," "almost new," "good," and "used."

[0120] Next, the server uses a generative AI model (e.g., GPT-3®) to generate a product description. The description is generated from a template based on the product's condition and appropriate price. For example, a description such as, "I am selling a smartphone that has hardly been used. It is in excellent condition, almost like new. The price is 35,000 yen," might be created.

[0121] Finally, the server displays the generated product description, the determined condition, and the set appropriate price to the user's device. The user can review this information and edit the description and price as needed. Once editing is complete, the user can finally list the product for sale.

[0122] Specific example

[0123] User A wants to sell a used smartphone and takes detailed video footage of the smartphone. Next, User A uploads this video to a server through a flea market application. The server receives and saves the video and compares it with video data of similar smartphones from the past.

[0124] Based on the video comparison, the server determines that User A's smartphone is in "almost new" condition. It also sets the appropriate price at 35,000 yen based on past data. Next, the server automatically generates a product description like the following:

[0125] "I'm selling a smartphone that's barely been used. It's in excellent condition, practically brand new. The price is 35,000 yen."

[0126] This information is displayed to User A's device, and User A reviews the content and edits the description and price as needed. After editing is complete, User A can proceed with the listing process and list their smartphone for sale on the flea market.

[0127] Example of a prompt

[0128] "Please record video data of your used smartphone and upload it to the server via the flea market application. The server will receive and analyze the video data, automatically determine the product's condition and appropriate price, and generate a description. Once you have reviewed and edited this information, please list your product for sale."

[0129] The above describes the embodiments for carrying out the present invention. This embodiment allows users to list products efficiently without any hassle.

[0130] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0131] Step 1:

[0132] Input: Video data of the product the user wants to list for sale.

[0133] Process: Users use their own devices to film detailed videos of the products they wish to sell. The videos must include the overall image and specific distinctive features. For example, in the case of a smartphone, videos should be taken from various angles, including the front, back, sides, and screen.

[0134] Output: Recorded video data

[0135] Step 2:

[0136] Input: Recorded video data

[0137] Processing: The user's device uploads the captured video data to the server via the flea market application. During this process, the application compresses and formats the video data, converting it into a format optimized for transfer. For example, it compresses the video data into JPEG or PNG format before sending it.

[0138] Output: Compressed video data transferred to the server

[0139] Step 3:

[0140] Input: Compressed video data transferred to the server

[0141] Processing: The server saves the received video data to a database. Each product is assigned a unique identifier in this database, and the data is managed based on that identifier. The saved video data is used for subsequent analysis.

[0142] Output: Video data stored in the database

[0143] Step 4:

[0144] Input: Video data stored in the database

[0145] Processing: The server analyzes the video data using an image recognition algorithm (e.g., TensorFlow or PyTorch). The algorithm automatically identifies the condition and characteristics of the product. Specifically, it detects scratches, color variations, button wear, etc.

[0146] Output: Product feature information based on video data

[0147] Step 5:

[0148] Input: Product feature information based on video data

[0149] Processing: The server determines the condition of the product based on its characteristic information, comparing it with past listing data. For example, it classifies items into categories such as "new / unused," "almost new," "good," and "used." This comparison uses a database of previously accumulated listing data.

[0150] Output: Condition of the determined product

[0151] Step 6:

[0152] Input: Condition of the item being assessed

[0153] Processing: The server sets an appropriate selling price based on the product's condition and by referring to past transaction data. For example, it calculates the price based on the prices at which similar products in the same category and condition have been sold in the past.

[0154] Output: Set appropriate selling price

[0155] Step 7:

[0156] Input: Condition of the assessed product and fair selling price

[0157] Processing: The server uses a generative AI model (e.g., GPT-3) to generate product descriptions. It inserts the product's condition and price into a description template to create a specific description. For example: "I am selling a smartphone in almost unused condition. It is in excellent condition, practically brand new. The price is 35,000 yen."

[0158] Output: Generated product description

[0159] Step 8:

[0160] Input: Generated product description, determined product condition, and appropriate selling price.

[0161] Processing: The server sends this information to the user's terminal. A dedicated interface is designed to make it easy for the user to review the content on their terminal. The user can also edit this information.

[0162] Output: Product description, product condition, and fair selling price displayed on the user's device.

[0163] Step 9:

[0164] Input: User-verified and edited introductory text and price

[0165] Processing: Users review the presented information and edit the product description and appropriate selling price as needed. For example, they can add additional information to the description, such as "Original box and accessories are included," or make minor adjustments to the price.

[0166] Output: Edited product description and selling price

[0167] Step 10:

[0168] Input: Edited product description and selling price

[0169] Processing: The user completes the final listing procedure. They press the "List Item" button in the application to list the item on the flea market. This action automatically completes the listing process on the system side, and the item is listed on the flea market.

[0170] Output: Items listed on the flea market

[0171] (Application Example 1)

[0172] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0173] Current flea market and online shopping sites require users to go through many steps when listing items. Specifically, it involves taking photos of the product, assessing its condition, setting an appropriate price, and writing a product description. This can cause users to hesitate to list items, and sales may suffer due to inappropriate pricing or poor product descriptions. Therefore, there is a need to streamline the listing process and reduce the burden on users.

[0174] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0175] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a database of past listing videos, means for comparing product video data with video data in the database of past listing videos to determine the condition of the product, means for setting an appropriate price for the product based on the condition of the product, means for generating a product description based on the condition of the product and the appropriate price, means for presenting the condition of the product, the appropriate price, and the product description to the user, means for sending the condition of the product and the appropriate price to a cloud server and analyzing it using an image recognition algorithm, and means for generating a product description using a generation AI model. This makes it possible for users to list products quickly and efficiently without any hassle.

[0176] "Product video data" refers to video and image data of products that users plan to list for sale.

[0177] "Means of storage" refers to the part that has the function of storing the input product video data in a storage device.

[0178] The "Listing Video Database" is a database that stores video data and information about products that have been listed for sale in the past.

[0179] The "means of comparison and judgment" refers to the function that automatically evaluates the condition of a product by comparing product video data with data from a database of past listing videos.

[0180] "Means of setting" refers to the part that has the function of determining an appropriate selling price for a product based on the determined product condition.

[0181] "Generating means" refers to the part that has the function of automatically creating a product description based on the product condition and appropriate price.

[0182] "Means of presentation" refers to the part that has the function of displaying information such as the generated product description, the determined condition, and the set appropriate price to the user.

[0183] "Means of transmission" refers to the part that has the function of transferring data such as product condition and appropriate price to a cloud server.

[0184] An "image recognition algorithm" refers to a computational method or program used to analyze video data and identify the condition of a product.

[0185] A "generative AI model" is an artificial intelligence model that automatically creates product descriptions using natural language generation technology.

[0186] The embodiments for carrying out the present invention are described in detail below. The present invention significantly reduces the burden on the user by allowing the user to take product video data and upload it to an application for a flea market or e-commerce site, and the system automatically generates the product's condition, appropriate price, and description.

[0187] First, the user takes a picture of the item they want to list using their smartphone's camera function. The captured video data is uploaded to a cloud server via the application. The cloud server receives the video data and stores it in a database. This database contains video data of previously listed items, along with their corresponding condition and selling price.

[0188] The server uses an image recognition algorithm (e.g., Amazon Rekognition) to analyze uploaded product video data and compare it to video data in a database of past listing videos. This automatically determines the product's condition. Condition categories are classified into multiple levels, such as "new / unused," "like new," "good," and "used."

[0189] Next, the server refers to data on similar past products to determine a fair price based on the condition of the determined product. The fair price is automatically calculated based on the prices at which similar products in the same category have been traded.

[0190] Furthermore, the server automatically generates product descriptions using a generation AI model (e.g., OpenAI® GPT-4®). The product descriptions are generated based on a template that includes detailed information about the product, along with the determined condition and the set appropriate price. This product description, containing this information, is sent to the user's terminal, where the user can review it.

[0191] Users can review the generated product description and appropriate price, and edit them as needed. They can then proceed to the final listing process within the application, allowing them to list their products on flea markets and e-commerce sites.

[0192] Hardware and software to be used

[0193] 1. Hardware:

[0194] Smartphone (for taking photos and using applications)

[0195] Cloud server (data storage and analysis)

[0196] 2. Software:

[0197] Smartphone application (for shooting and uploading product video data)

[0198] Amazon Rekognition (image analysis)

[0199] MySQL (registered trademark) (database of past video listings)

[0200] OpenAI GPT-4 (product description generation)

[0201] Specific example

[0202] User B decides to sell a guitar they no longer need and takes a picture of it with their smartphone camera. They then upload the video to a cloud server via an application. The server receives the video data and uses Amazon Rekognition to perform video analysis. It detects scratches and signs of wear on the guitar and compares them with a past database, resulting in a determination that the guitar "shows signs of wear." Based on past price data, a fair price of 20,000 yen is calculated.

[0203] Using OpenAI GPT-4, the following product description is generated and sent to user B's terminal:

[0204] "It shows some signs of use, but it's still a perfectly playable guitar. The price is 20,000 yen."

[0205] User B reviews this information, edits it as needed, and finally proceeds with the listing process.

[0206] Example of a prompt

[0207] Please generate an appropriate product description based on the product information provided.

[0208] Product name: Electric guitar

[0209] Condition: Shows signs of use.

[0210] Fair price: 20,000 yen

[0211] Example output:

[0212] "It shows some signs of use, but it's still a perfectly playable guitar. The price is 20,000 yen."

[0213] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0214] Step 1:

[0215] Users use their smartphone cameras to capture video data of the products they wish to list for sale. The video data must clearly show the product's appearance and details. The input is the video data of the product captured by the user. The output is the video data uploaded to the application.

[0216] Step 2:

[0217] The device uploads the captured product video data to a cloud server via an application. The video data is transmitted over the internet and stored in cloud storage (e.g., Amazon S3). The input is the video data captured by the user, and the output is the URL of the cloud storage where the data is saved.

[0218] Step 3:

[0219] The server retrieves product video data stored in cloud storage and performs analysis using an image recognition algorithm (e.g., Amazon Rekognition). The server analyzes the product video data, extracts features from the video data, and compares them with a database of past listing videos. The input is the URL of the video data, and the output is the analysis results (product features and condition information).

[0220] Step 4:

[0221] The server uses the results of an image recognition algorithm to determine the condition of a product by referencing a database of past listing images (e.g., MySQL). Simultaneously, it calculates a fair price by referencing past sales data for products in the same category. The input is the analyzed product characteristics, and the output is the product condition and fair price.

[0222] Step 5:

[0223] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate a product description based on the determined product condition and fair price. The generative AI model is supplied with predefined templates and prompts. The inputs are the product condition, fair price, and template, and the output is the automatically generated product description.

[0224] Step 6:

[0225] The server sends the generated product description, determined condition, and set appropriate price to the user's terminal. The user can review this information and edit it as needed. The input is the automatically generated product description and price information, and the output is the information provided to the user in a visual interface.

[0226] Step 7:

[0227] The user reviews the edited information on the application and then clicks the "List for Sale" button to finally list the product on the flea market or e-commerce site. The server receives this and completes the final product listing process. The input is the user's final confirmation information, and the output is the product list that will be published on the flea market or e-commerce site.

[0228] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0229] The following describes in detail embodiments of the present invention that combine an emotion engine.

[0230] This invention combines a system that automatically generates product condition, appropriate price, and description to assist users in listing items simply by having them shoot product video data and upload it to a flea market application, with an emotion engine that recognizes the user's emotions. This provides an even more personalized listing experience.

[0231] The system consists of a server, an emotion engine, and a user terminal. The program's processing is described below in natural language.

[0232] 1. Input and save of product video data

[0233] First, the user takes a video of the item they want to sell using their device. The video must include detailed information about the item. The user uploads this video data to the server via the flea market app. The server receives the video data and stores it.

[0234] 2. Analysis and comparison of video data

[0235] The server references a database of past listing videos and uses an image recognition algorithm to compare uploaded product video data with similar products. This comparison automatically determines the condition of the product.

[0236] 3. Setting appropriate prices and generating introductory texts.

[0237] Based on the determined product condition, the server sets an appropriate selling price by referring to data on similar products from the past. It also automatically generates a product description based on the product condition and appropriate price. This description includes a detailed explanation of the product and the appropriate price for the user.

[0238] 4. Recognition of user emotions by an emotion engine

[0239] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions in real time. For example, if a user expresses dissatisfaction or confusion regarding a product description or price, the emotion engine will detect this.

[0240] 5. Emotion-based presentation and adjustment

[0241] Based on user sentiment, the server adjusts product descriptions and suggestions. For example, if a user expresses dissatisfaction, it readjusts the price and description based on data from other similar products. It can also provide product recommendations and advice based on sentiment recognition results.

[0242] 6. Presentation to the user and editing

[0243] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. Users can review this information and edit the description and price as needed. Because adjustments based on the sentiment engine are also incorporated, users can create more satisfying listings.

[0244] Specific example

[0245] For example, user B wants to sell a used digital camera and takes a video of it. They upload this video to the server via a flea market app. The server saves the video data, compares it to past digital camera listings, and determines that the camera is in "good" condition. It also sets a fair price of 28,000 yen based on past data and generates a product description like the following:

[0246] "I'm selling a digital camera in good condition. It shows some signs of use, but there are no problems with its performance. The price is 28,000 yen."

[0247] The generated information is presented to User B, and the emotion engine detects that User B appears slightly dissatisfied. Therefore, the server suggests readjusting the price and revising the description. User B then reviews and edits the description and price before completing the listing.

[0248] The above describes an embodiment of the present invention that combines an emotion engine. This embodiment allows users to enjoy a personalized listing experience and make the listing process more effective and satisfying.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] Users film product footage and upload it to the system using their devices.

[0252] Users use devices such as smartphones or tablets to take detailed videos of the items they want to list for sale.

[0253] After filming is complete, the video files are uploaded to the server via a flea market app.

[0254] Step 2:

[0255] The server receives and saves the uploaded product video data.

[0256] The server receives the video file sent by the user.

[0257] The received video data is saved to a temporary storage directory, and the metadata of that file (e.g., upload date and time, user ID, etc.) is also recorded.

[0258] Step 3:

[0259] The server searches for similar products by referring to a database of past listing videos.

[0260] The server retrieves video data of previously listed products from the database.

[0261] Video data is filtered based on metadata such as product category, manufacturer, and model number to select appropriate comparison targets.

[0262] Step 4:

[0263] The server uses video comparison technology to analyze and compare product video data.

[0264] The server analyzes product video data frame by frame using image recognition algorithms (such as CNN or SIFT).

[0265] Based on the analyzed data, we compare it with video data of similar products to extract features related to the condition of the product.

[0266] Step 5:

[0267] The server determines the condition of the product based on the video comparison results.

[0268] The server determines the condition category to which the product belongs based on the extracted features.

[0269] The condition category can be selected from options such as "New / Unused," "Like New," "Good," and "Used."

[0270] Step 6:

[0271] The server sets an appropriate selling price based on data on the condition and selling price of similar products from the past.

[0272] The server uses past data of similar products as a reference to determine the price based on the determined condition category.

[0273] The optimal selling price is calculated by utilizing statistical data such as the average price, median price, and latest transaction price.

[0274] Step 7:

[0275] The server automatically generates a product description based on the product's condition and pricing.

[0276] The server generates product descriptions based on a template.

[0277] The generated description will include a detailed description of the product's condition and its selling price.

[0278] Step 8:

[0279] The emotion engine recognizes the user's emotions.

[0280] The emotion engine analyzes the user's expressions and voice in real time when the user interacts with the system.

[0281] The emotion engine recognizes the user's emotional state (e.g., satisfaction, dissatisfaction, confusion, etc.).

[0282] Step 9:

[0283] Based on the emotion recognition result, the server adjusts the product introduction text and the way of presenting the price.

[0284] Receiving the result of the emotion engine, the server adjusts the product introduction text and the set price.

[0285] For example, if the user shows dissatisfaction, the price is reviewed or changed to complement the explanation.

[0286] Step 10:

[0287] The server presents the generated introduction text, the determined conditions, and the set selling price to the user.

[0288] The server displays this information on the user's terminal.

[0289] The user can check the presented content and edit the introduction text and price as needed.

[0290] Step 11:

[0291] The user checks and edits the product information and finally completes the listing.

[0292] The user edits the presented product information and, if satisfied with the content, presses the listing button to complete the listing procedure.

[0293] The final listing information is sent to the server and posted on the free market app.

[0294] Through the above processing steps, the present invention provides users with a personalized listing experience, enabling more effective and satisfying listings.

[0295] (Example 2)

[0296] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0297] Traditional flea market applications had problems such as requiring users to spend a lot of time and effort determining the condition of their items, setting appropriate prices, and writing product descriptions when listing items. Furthermore, they lacked features that provided a personalized listing experience that took user emotions into consideration. As a result, it was difficult for users to list items in a way that they found satisfying.

[0298] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0299] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referencing past listing video data, means for comparing the product video data with data in the past listing video data to determine the product condition, means for setting an appropriate price for the product based on the product condition, means for generating a product description based on the product condition and the appropriate price, means for recognizing the user's emotions, means for adjusting the product description and appropriate price based on the user's emotions, and means for presenting the product condition, appropriate price, and product description to the user. As a result, users can easily determine the product condition, set an appropriate price, generate a personalized product description, and make adjustments that take into account the user's emotions, making it possible to list products that will satisfy users.

[0300] "Product video data" refers to video data of products that users wish to list for sale, captured with a camera, and includes information that shows the product's appearance and characteristics.

[0301] The "means for storage" refers to the function for storing and managing the video data received by the server in a storage device such as a database.

[0302] The "past product-listing video data" refers to the video data of products previously listed by users through a free-market application, and is used as reference data for determining the product condition and price.

[0303] The "means for comparison" refers to the function of collating the uploaded product video data with the past product-listing video data using an image recognition algorithm to determine the condition of the product.

[0304] The "product condition" refers to an evaluation indicating the usage status and presence or absence of damage of a product, and refers to the condition of the product to be listed.

[0305] The "appropriate price" refers to the reasonable selling price of the product to be listed, set based on past listing data and sales records of similar products.

[0306] The "product description text" is a text that describes the features, condition, and selling price of the product to be listed, and includes information for appealing the product to potential buyers.

[0307] The "means for recognizing user's emotion" refers to the function of collecting the user's facial expression and voice data using a camera and a microphone, and analyzing it to identify the user's emotional state (e.g., satisfaction, dissatisfaction, confusion).

[0308] The "means for presentation" refers to the function of the server to display the finally generated product description text, the determined condition, and the set appropriate price on the user's terminal, enabling the user to confirm and edit the information.

[0309] The following describes in detail an embodiment of the present invention that incorporates an emotion engine. The present invention combines an emotion engine that recognizes the user's emotions with a system that automatically generates product condition, appropriate price, and description to support listing a product simply by the user taking product video data and uploading it to a flea market application. This provides an even more personalized listing experience.

[0310] The system consists of a server, terminals, and an emotion engine. Specifically, it is implemented using the following hardware and software:

[0311] Hardware and software to be used

[0312] 1. Server:

[0313] Databases for data storage and processing (e.g., MySQL, PostgreSQL)

[0314] Image recognition algorithms (e.g., TensorFlow, OpenCV)

[0315] Statistical analysis and machine learning algorithms (e.g., Scikit-learn)

[0316] Emotion engine (e.g., Affectiva, Microsoft® Azure® Cognitive Services)

[0317] Generative AI models (e.g., GPT-4)

[0318] 2. Terminal:

[0319] Smartphones and tablets used by users

[0320] Camera and microphone functions

[0321] 3. Network:

[0322] Internet connection for connecting terminals and servers

[0323] Example of operation

[0324] The following provides specific examples of how to operate the system.

[0325] Product video data input

[0326] Users use their device's camera to capture video data of the items they want to list for sale. For example, when photographing a used digital camera, they should ensure that the camera body and its main components are clearly visible.

[0327] Uploading product video data

[0328] Users upload the recorded video data to the server via a flea market app on their device. This is done by selecting the "List Item" button in the app, specifying the video data, and sending it.

[0329] Analysis and comparison of video data

[0330] The server imports the stored product video data into an analysis program and determines the product's condition while referring to a database of past listing videos. This process utilizes image recognition algorithms such as TensorFlow and OpenCV.

[0331] Setting appropriate prices and generating introductory texts.

[0332] Based on the determined product condition, the server sets an appropriate selling price by referring to data on similar products from the past. This uses machine learning algorithms such as Scikit-learn. In addition, product descriptions are automatically generated using an AI model (e.g., GPT-4) that generates information on the appropriate price and product condition.

[0333] Recognition of user emotions by an emotion engine

[0334] While the user is reviewing product descriptions and prices displayed on their device, the device's camera and microphone record the user's facial expressions and voice. This data is sent to a server, where an emotion engine analyzes the user's emotional state.

[0335] Final presentation to the user

[0336] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. The user can review this information and edit the description and price as needed. Because the sentiment engine's adjustments are reflected, users can create more satisfying listings.

[0337] Examples of prompts to input into a generative AI model

[0338] "I have uploaded images of a used digital camera. Please assess the camera's condition and generate an appropriate selling price and description. Also, please consider user sentiment and adjust the description and price accordingly to present the final listing."

[0339] The above describes an embodiment of the present invention that combines an emotion engine. This embodiment allows users to enjoy a personalized listing experience and make the listing process more effective and satisfying.

[0340] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0341] Step 1: Input and save product video data.

[0342] 1.1 Filming product video data

[0343] The user takes photos of the item they want to list using their device. These input videos must capture the item's main features and condition in detail. Specifically, the user launches their smartphone's camera app and takes photos of the item from several angles.

[0344] 1.2 Uploading video data

[0345] Users upload recorded video data to the server via a flea market app. Input is done by the user selecting video data from their device and tapping the "List Item" button in the app. Output is the video data being sent to the server.

[0346] 1.3 Data storage on the server

[0347] The server verifies the received video data and saves it to the database. In this step, a unique ID is assigned to the video data so that it can be referenced in subsequent processing. The input is the uploaded video data, and the output is the unique ID of the saved data.

[0348] Step 2: Analysis and comparison of video data

[0349] 2.1 Importing video data

[0350] The server takes the stored video data into the analysis program. The input is the stored video data, and the output is video data in a format suitable for analysis. Specifically, preprocessing is performed to extract image and text information.

[0351] 2.2 Searching for similar products

[0352] The server references a database of past listing videos and uses an image recognition algorithm to compare uploaded product video data with similar products. The input is the captured video data and past listing data, and the output is the matching result with similar products. Specifically, image analysis is performed using TensorFlow and OpenCV.

[0353] 2.3 Determining the condition of the product

[0354] The server automatically determines the condition of the product in the analyzed video data based on data of similar products. The input is the matching results for similar products, and the output is the product condition evaluation. The evaluation algorithm determines the product condition (e.g., "Good," "Like New") based on evaluation criteria.

[0355] Step 3: Setting an appropriate price and generating a promotional text.

[0356] 3.1 Setting a fair price

[0357] The server sets an appropriate selling price based on the determined product condition, referencing data from similar products in the past. The input is the product condition evaluation and data from similar products in the past, and the output is the appropriate price. Specifically, it uses statistical analysis algorithms such as Scikit-learn and machine learning algorithms.

[0358] 3.2 Generating Product Descriptions

[0359] The server automatically generates product descriptions using a generative AI model based on information about the appropriate price and product condition. The input is information about the appropriate price and product condition, and the output is the product description. Specifically, a generative AI model (e.g., GPT-4) is used to create text that attractively expresses the features and benefits of the product.

[0360] Step 4: Recognition of user emotions by the emotion engine

[0361] 4.1 Collecting User Feedback

[0362] While the user is reviewing the product description and price, the device's camera and microphone are used to record the user's facial expressions and voice. The input consists of the displayed product description and price, as well as the user's reaction data (facial expressions, voice), and the output is this reaction data.

[0363] 4.2 Analysis of User Sentiment

[0364] Data collected by the device is sent to the server in real time. The server uses an emotion engine to analyze the user's emotions. The input is the user's reaction data, and the output is an evaluation of the emotional state. Specifically, it uses emotion analysis engines such as Affectiva or Microsoft Azure Cognitive Services.

[0365] 4.3 Feedback on emotional data

[0366] The analysis results from the emotion engine are returned to the server, and data on the user's emotional state (e.g., satisfied, dissatisfied, confused) is fed back. The input is the evaluation result of the emotional state, and the output is the feedback data.

[0367] Step 5: Emotion-based presentation and adjustment

[0368] 5.1 Data Recalibration

[0369] The server readjusts product descriptions and prices based on the results of sentiment analysis. Input is feedback data and existing description and price information, while output is the readjusted description and price. If the user expresses dissatisfaction or confusion, the server attempts to regenerate the price and description using a different dataset or new parameters.

[0370] 5.2 Providing recommendations and advice

[0371] If necessary, the server provides recommendations for other similar products and advice to help users be satisfied. The input is re-tuned data and user sentiment analysis results, and the output is advice information and recommendation lists.

[0372] Step 6: Presentation to the user and editing

[0373] 6.1 Final presentation

[0374] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. The input is the re-adjusted data, and the output is the final information displayed on the user's device. The user can review this information and edit the description and price as needed.

[0375] 6.2 Editing Users

[0376] Users can review the presented information and edit the description and price as needed. The input is the final information presented, and the output is the edited information. Text and numbers can be changed using the editing function within the app.

[0377] 6.3 Completion of listing

[0378] After the user confirms the listing details they are finally satisfied with, they can press the "Complete Listing" button to officially list the product. The input is the final information edited by the user, and the output is the final listing data.

[0379] (Application Example 2)

[0380] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0381] Traditional e-commerce sites display product descriptions and reviews uniformly, making it difficult to address the individual emotions and needs of each consumer. In particular, the lack of real-time solutions to consumer frustrations and questions while browsing product pages poses a risk of diminishing their purchase intent. Therefore, a system is needed that dynamically adjusts product descriptions, prices, and recommendations based on consumer emotions, providing information optimized for each individual consumer.

[0382] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a past listing video database, means for comparing the product video data with video data in the past listing video database to determine the product condition, means for setting an appropriate price for the product based on the product condition, means for generating a product description based on the product condition and the appropriate price, means for analyzing input video and audio data to analyze the user's emotions, means for adjusting the product description and the appropriate price based on the user's emotions, and means for presenting the product condition, the appropriate price, and the product description to the user. This makes it possible to provide personalized information based on the consumer's emotions in real time.

[0383] "Product video data" refers to digital data of videos of products that a user wishes to list or purchase.

[0384] The "Past Listing Video Database" is a database that stores videos and related data of items previously listed on flea markets and online shopping sites.

[0385] "Product condition" refers to information about the product's condition, such as its age (new or old) and whether or not it has any damage.

[0386] A "fair price" is a fair and realistic selling price calculated based on the condition of the product and the supply and demand in the market.

[0387] A "product description" is a descriptive text that details the product's features, condition, price, and other relevant information.

[0388] "Emotion analysis means" refers to technical means for analyzing a user's video and audio data to recognize their emotions.

[0389] "Presentation method" refers to a means of displaying the generated product condition, appropriate price, and product description to the user.

[0390] "Editing methods" refer to means that enable users to modify and edit product descriptions and appropriate pricing.

[0391] An "image recognition algorithm" is an algorithm that analyzes input video data to identify and determine the content of an image.

[0392] This invention relates to a system that automatically generates product condition, appropriate price, and product description based on product video data, and adjusts them based on the user's emotions. This system inputs product video data, stores it, analyzes it, and performs a series of processes to present it to the user. Furthermore, it can analyze the user's emotions and personalize the content accordingly.

[0393] First, the user takes product video data using a device such as a smartphone or smart glasses and inputs it into the system. The input product video data is sent to a server and stored there.

[0394] Next, the server analyzes the stored product video data. Image recognition algorithms are used for this analysis. The server refers to a database of past listing videos and compares them with the current video data to determine the condition of the product. For example, it determines whether the product is used or new, and how much wear and tear it has.

[0395] Subsequently, the server sets an appropriate price based on the determined product condition. Past data on similar products is used as a reference when setting the appropriate price. Furthermore, a product description is automatically generated based on the determined product condition and appropriate price. This product description includes details such as the product's features, condition, and price.

[0396] Next, emotion analysis tools are used to analyze the user's emotions in real time. These tools analyze the user's facial expressions and voice to recognize their emotions. This analysis utilizes the camera and microphone of a smartphone or smart glasses.

[0397] Based on the sentiment analysis results, the server adjusts product descriptions and appropriate pricing. For example, if a user displays a dissatisfied expression, the detailed product description and price will be reconsidered. Recommended products and advice based on sentiment analysis are also provided.

[0398] Finally, the adjusted product condition, appropriate price, and product description are presented to the user. The user can review this and edit it as needed.

[0399] Specific example

[0400] For example, a user takes a picture of a used digital camera using their smartphone and uploads the image data to the system. Based on this data, the server determines the product's condition as "good" and sets a fair price of 28,000 yen. A generated product description is then presented to the user.

[0401] If a user expresses dissatisfaction with the offered price, sentiment analysis tools will recognize this, and the server will readjust the price and description. Ultimately, the user can list their product in a way that satisfies them.

[0402] Examples of prompts for generative AI models

[0403] Create specific code for an e-commerce application that recognizes user emotions in real time from facial expressions and voice, and provides personalized product information based on those emotions. Include a process for collecting user data using the camera and microphone of a smartphone or smart glasses, and optimizing product information after emotion analysis. The generated code should specifically indicate the use of emotion and recommendation engines.

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] Users use their smartphones or smart glasses to capture video data of the items they want to list for sale. This video data includes detailed information about the products.

[0407] Input: Product video data

[0408] Output: Video data stored on the device

[0409] Specific operation: The user takes a picture of the product using the camera function of their smartphone or smart glasses, and the image data is saved on the device.

[0410] Step 2:

[0411] The device uploads the captured product video data to the server via the flea market application.

[0412] Input: Video data stored on the device

[0413] Output: Video data sent to the server

[0414] Specific operation: The user presses the "Upload" button within the application, and the video data is sent to the server via the internet.

[0415] Step 3:

[0416] The server receives the uploaded product video data and saves it to the database.

[0417] Input: Video data sent to the server

[0418] Output: Video data stored in the database

[0419] Specific operation: The server receives an HTTP request and saves the video data to dedicated storage.

[0420] Step 4:

[0421] The server analyzes the stored product video data. This analysis uses an image recognition algorithm.

[0422] Input: Video data stored in the database

[0423] Output: Analyzed product condition data

[0424] Specific operation: The server executes an image recognition algorithm and analyzes the video data to determine the condition of the product. For example, information such as the age of the product and whether or not there are any scratches is extracted.

[0425] Step 5:

[0426] The server refers to a database of past listing videos and compares them with current video data to determine the product's condition in more detail.

[0427] Input: Analyzed product condition data, past listing video database

[0428] Output: Detailed product condition data

[0429] Specific operation: The server searches for similar images in its past database, compares them with the current data, and determines the product condition more accurately.

[0430] Step 6:

[0431] The server sets an appropriate price based on the determined product condition. This setting is based on data from similar products in the past.

[0432] Input: Detailed product condition data, historical data on similar products.

[0433] Output: Fair price data

[0434] Specific operation: The server uses an algorithm to combine product condition and market data to calculate a fair price.

[0435] Step 7:

[0436] The server automatically generates a product description based on the determined product condition and appropriate price.

[0437] Input: Detailed product condition data, appropriate price data

[0438] Output: Product description data

[0439] Specific operation: The server uses a text generation algorithm to generate a product description. This description includes the product's features, condition, price, etc.

[0440] Step 8:

[0441] The server analyzes video and audio data received from the terminal in real time to analyze the user's emotions.

[0442] Input: Video and audio data received from the device.

[0443] Output: User's emotional data

[0444] Specific operation: Using data collected from the device's camera and microphone, the server runs an emotion analysis engine to recognize the user's emotions.

[0445] Step 9:

[0446] The server adjusts product descriptions and appropriate pricing based on user sentiment data.

[0447] Input: User sentiment data, product description data, appropriate price data

[0448] Output: Adjusted product description data, adjusted fair price data

[0449] Specific operation: The server uses user sentiment data to review the generated product description and appropriate price, and makes corrections as needed.

[0450] Step 10:

[0451] The server then presents the user with the final adjusted product condition, appropriate price, and product description, which the user can review and edit as needed.

[0452] Input: Adjusted product description data, adjusted fair price data

[0453] Output: Final data presented to the user

[0454] Specific operation: The server sends the adjusted information to the user's terminal, the user reviews the displayed data, edits it as needed, and then performs a final confirmation.

[0455] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0456] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0457] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0458] [Second Embodiment]

[0459] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0460] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0461] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0462] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0463] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0464] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0465] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0466] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0467] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0468] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0469] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0470] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0471] Embodiments of the present invention will be described in detail below.

[0472] This invention provides a system that supports listing products by automatically generating product condition, appropriate price, and description simply by having the user film product images and upload them to a flea market application. This significantly reduces the effort required from the user and enables efficient listing.

[0473] The system consists of a server and user terminals. First, the user takes a video of the item they want to sell using their terminal. This video must include detailed information about the item. Next, the user uploads the video to the server through the flea market app.

[0474] The server receives and stores the uploaded product video data. The stored product video data is then compared with the video database on the server. This video database contains video data of previously listed products, their condition, and their selling prices.

[0475] The server uses an image recognition algorithm to compare uploaded product video data with past listing video data in the database. Based on this comparison, the server automatically determines the product's condition. The condition is categorized into several categories, such as "new / unused," "almost new," "good," and "used."

[0476] Next, the server sets an appropriate selling price based on the determined condition of the product, referencing data from similar products in the past. This appropriate price is calculated based on the prices at which similar products in the same category were traded in the past.

[0477] Furthermore, the server automatically generates a product description based on the product's condition and appropriate price. This description is generated from the original template and includes detailed information about the product, such as its condition and selling price.

[0478] Finally, the server displays the generated product description, the determined condition, and the set appropriate price to the user's device. The user can review this information and edit it as needed. Once editing is complete, the user can finally list the product for sale.

[0479] Specific example:

[0480] User A wants to sell a used smartphone and takes detailed video footage of the smartphone. Next, User A uploads this video to a server through a flea market application. The server receives and saves the video and compares it with video data of similar smartphones from the past.

[0481] Based on the video comparison, the server determines that User A's smartphone is in "almost new" condition. It also sets the appropriate price at 35,000 yen based on past data. Next, the server automatically generates a product description like the following:

[0482] "I'm selling a smartphone that's barely been used. It's in excellent condition, practically brand new. The price is 35,000 yen."

[0483] This information is displayed to User A's device, and User A reviews the content and edits the description and price as needed. After editing is complete, User A can proceed with the listing process and list their smartphone for sale on the flea market.

[0484] The above describes the embodiment of the present invention. This embodiment enables users to list products efficiently without any hassle.

[0485] The following describes the processing flow.

[0486] Step 1:

[0487] Users film product footage and upload it to the system using their devices.

[0488] Users use devices such as smartphones or tablets to take detailed videos of the items they want to list for sale.

[0489] After filming is complete, the video files are uploaded to the server via a flea market app.

[0490] Step 2:

[0491] The server receives and saves the uploaded product video data.

[0492] The server receives the video file sent by the user.

[0493] The received video data is saved to a temporary storage directory, and the metadata of that file (e.g., upload date and time, user ID, etc.) is also recorded.

[0494] Step 3:

[0495] The server searches for similar products by referring to a database of past listing videos.

[0496] The server retrieves video data of previously listed products from the database.

[0497] Video data is filtered based on metadata such as product category, manufacturer, and model number to select appropriate comparison targets.

[0498] Step 4:

[0499] The server uses video comparison technology to analyze and compare product video data.

[0500] The server analyzes product video data frame by frame using image recognition algorithms (such as CNN or SIFT).

[0501] Based on the analyzed data, we compare it with video data of similar products to extract features related to the condition of the product.

[0502] Step 5:

[0503] The server determines the condition of the product based on the video comparison results.

[0504] The server determines the condition category to which the product belongs based on the extracted features.

[0505] The condition category can be selected from options such as "New / Unused," "Like New," "Good," and "Used."

[0506] Step 6:

[0507] The server sets an appropriate selling price based on data on the condition and selling price of similar products from the past.

[0508] The server uses past data of similar products as a reference to determine the price based on the determined condition category.

[0509] The optimal selling price is calculated by utilizing statistical data such as the average price, median price, and latest transaction price.

[0510] Step 7:

[0511] The server automatically generates a product description based on the product's condition and pricing.

[0512] The server generates product descriptions based on a template.

[0513] The generated description will include a detailed description of the product's condition and its selling price.

[0514] Step 8:

[0515] The server displays the generated description, the determined condition, and the set selling price to the user.

[0516] The server displays the generated description and pricing information on the user's device.

[0517] Users can review the presented content and make corrections as needed.

[0518] Step 9:

[0519] The user reviews and edits the product information, and finally completes the listing process.

[0520] The user edits the provided product information, and if they are satisfied with the content, they press the "List Item" button to complete the listing process.

[0521] The final listing information is sent to the server and posted on the flea market app.

[0522] Through the above processing steps, users can easily list products and save a lot of time and effort.

[0523] (Example 1)

[0524] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0525] Current flea market applications present a problem: users must create detailed descriptions for each item they list and set appropriate prices, a process that is extremely time-consuming and laborious. Furthermore, accurately assessing the condition of an item requires specialized knowledge, making it difficult for the average user. As a result, users have to expend a great deal of effort when listing items, making efficient listing difficult.

[0526] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0527] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a database of past listing videos, means for comparing the product video data with video data in the database of past listing videos to determine the condition of the product, means for setting an appropriate price for the product based on the condition of the product, means for using a generation AI to generate a product description, means for generating a product description based on the condition of the product and the appropriate price, and means for presenting the condition of the product, the appropriate price, and the product description to the user. As a result, users can simply upload product videos, and the system will automatically determine the condition of the product, set an appropriate price, and generate a product description, enabling efficient listing.

[0528] "Product video data" refers to video information about products listed by users, and is data that visually records the detailed condition and characteristics of the product.

[0529] "Means of storage" refers to a system for storing and managing received product video data in a database or storage device.

[0530] "Means of reference" refers to a system that allows users to view past listing video data and use it for comparison and analysis.

[0531] "Means for comparing and determining the condition of a product" refers to algorithms or software that compare product video data with video data from a database of past listing videos and automatically classify and evaluate the condition of the product.

[0532] "Methods for setting appropriate prices" refer to systems for calculating the optimal selling price of a product based on its condition and past transaction data.

[0533] "Methods of using generative AI" refer to systems that use artificial intelligence technology to automatically create and generate text and data.

[0534] "Methods for generating product descriptions" refers to a function that automatically generates user-oriented descriptions based on elements such as product details, condition, and price.

[0535] "Means of presentation to the user" refers to an interface that provides the user with the generated product description, the determined product condition, and the set appropriate price, allowing the user to review and edit them.

[0536] This invention supports listing products by allowing users to simply film product images and upload them to a flea market application. The system automatically generates product condition, appropriate price, and description, significantly reducing user effort and enabling efficient listing. The details are described below.

[0537] The system consists of a server and user terminals. First, the user takes a video of the item they want to sell using their terminal. This video must include detailed information about the item. Next, the user uploads the video to the server through a flea market application.

[0538] The server receives uploaded product video data and has a database for storing it. The stored product video data is compared with the video database on the server, which includes video data of previously listed products, their condition, and sales price.

[0539] Image data analysis uses image recognition algorithms such as TensorFlow and PyTorch. The server uses these algorithms to compare uploaded product video data with past listing video data and automatically determine the product's condition. The condition is classified into several categories, such as "new / unused," "almost new," "good," and "used."

[0540] Next, the server uses a generative AI model (e.g., GPT-3) to generate a product description. The description is generated from a template based on the product's condition and appropriate price. For example, a description such as, "I am selling a smartphone that has hardly been used. It is in excellent condition, almost like new. The price is 35,000 yen," might be created.

[0541] Finally, the server displays the generated product description, the determined condition, and the set appropriate price to the user's device. The user can review this information and edit the description and price as needed. Once editing is complete, the user can finally list the product for sale.

[0542] Specific example

[0543] User A wants to sell a used smartphone and takes detailed video footage of the smartphone. Next, User A uploads this video to a server through a flea market application. The server receives and saves the video and compares it with video data of similar smartphones from the past.

[0544] Based on the video comparison, the server determines that User A's smartphone is in "almost new" condition. It also sets the appropriate price at 35,000 yen based on past data. Next, the server automatically generates a product description like the following:

[0545] "I'm selling a smartphone that's barely been used. It's in excellent condition, practically brand new. The price is 35,000 yen."

[0546] This information is displayed to User A's device, and User A reviews the content and edits the description and price as needed. After editing is complete, User A can proceed with the listing process and list their smartphone for sale on the flea market.

[0547] Example of a prompt

[0548] "Please record video data of your used smartphone and upload it to the server via the flea market application. The server will receive and analyze the video data, automatically determine the product's condition and appropriate price, and generate a description. Once you have reviewed and edited this information, please list your product for sale."

[0549] The above describes the embodiments for carrying out the present invention. This embodiment allows users to list products efficiently without any hassle.

[0550] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0551] Step 1:

[0552] Input: Video data of the product the user wants to list for sale.

[0553] Process: Users use their own devices to film detailed videos of the products they wish to sell. The videos must include the overall image and specific distinctive features. For example, in the case of a smartphone, videos should be taken from various angles, including the front, back, sides, and screen.

[0554] Output: Recorded video data

[0555] Step 2:

[0556] Input: Recorded video data

[0557] Processing: The user's device uploads the captured video data to the server via the flea market application. During this process, the application compresses and formats the video data, converting it into a format optimized for transfer. For example, it compresses the video data into JPEG or PNG format before sending it.

[0558] Output: Compressed video data transferred to the server

[0559] Step 3:

[0560] Input: Compressed video data transferred to the server

[0561] Processing: The server saves the received video data to a database. Each product is assigned a unique identifier in this database, and the data is managed based on that identifier. The saved video data is used for subsequent analysis.

[0562] Output: Video data stored in the database

[0563] Step 4:

[0564] Input: Video data stored in the database

[0565] Processing: The server analyzes the video data using an image recognition algorithm (e.g., TensorFlow or PyTorch). The algorithm automatically identifies the condition and characteristics of the product. Specifically, it detects scratches, color variations, button wear, etc.

[0566] Output: Product feature information based on video data

[0567] Step 5:

[0568] Input: Product feature information based on video data

[0569] Processing: The server determines the condition of the product based on its characteristic information, comparing it with past listing data. For example, it classifies items into categories such as "new / unused," "almost new," "good," and "used." This comparison uses a database of previously accumulated listing data.

[0570] Output: Condition of the determined product

[0571] Step 6:

[0572] Input: Condition of the item being assessed

[0573] Processing: The server sets an appropriate selling price based on the product's condition and by referring to past transaction data. For example, it calculates the price based on the prices at which similar products in the same category and condition have been sold in the past.

[0574] Output: Set appropriate selling price

[0575] Step 7:

[0576] Input: Condition of the assessed product and fair selling price

[0577] Processing: The server uses a generative AI model (e.g., GPT-3) to generate product descriptions. It inserts the product's condition and price into a description template to create a specific description. For example: "I am selling a smartphone in almost unused condition. It is in excellent condition, practically brand new. The price is 35,000 yen."

[0578] Output: Generated product description

[0579] Step 8:

[0580] Input: Generated product description, determined product condition, and appropriate selling price.

[0581] Processing: The server sends this information to the user's terminal. A dedicated interface is designed to make it easy for the user to review the content on their terminal. The user can also edit this information.

[0582] Output: Product description, product condition, and fair selling price displayed on the user's device.

[0583] Step 9:

[0584] Input: User-verified and edited introductory text and price

[0585] Processing: Users review the presented information and edit the product description and appropriate selling price as needed. For example, they can add additional information to the description, such as "Original box and accessories are included," or make minor adjustments to the price.

[0586] Output: Edited product description and selling price

[0587] Step 10:

[0588] Input: Edited product description and selling price

[0589] Processing: The user completes the final listing procedure. They press the "List Item" button in the application to list the item on the flea market. This action automatically completes the listing process on the system side, and the item is listed on the flea market.

[0590] Output: Items listed on the flea market

[0591] (Application Example 1)

[0592] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0593] Current flea market and online shopping sites require users to go through many steps when listing items. Specifically, it involves taking photos of the product, assessing its condition, setting an appropriate price, and writing a product description. This can cause users to hesitate to list items, and sales may suffer due to inappropriate pricing or poor product descriptions. Therefore, there is a need to streamline the listing process and reduce the burden on users.

[0594] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0595] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a database of past listing videos, means for comparing product video data with video data in the database of past listing videos to determine the condition of the product, means for setting an appropriate price for the product based on the condition of the product, means for generating a product description based on the condition of the product and the appropriate price, means for presenting the condition of the product, the appropriate price, and the product description to the user, means for sending the condition of the product and the appropriate price to a cloud server and analyzing it using an image recognition algorithm, and means for generating a product description using a generation AI model. This makes it possible for users to list products quickly and efficiently without any hassle.

[0596] "Product video data" refers to video and image data of products that users plan to list for sale.

[0597] "Means of storage" refers to the part that has the function of storing the input product video data in a storage device.

[0598] The "Listing Video Database" is a database that stores video data and information about products that have been listed for sale in the past.

[0599] The "means of comparison and judgment" refers to the function that automatically evaluates the condition of a product by comparing product video data with data from a database of past listing videos.

[0600] "Means of setting" refers to the part that has the function of determining an appropriate selling price for a product based on the determined product condition.

[0601] "Generating means" refers to the part that has the function of automatically creating a product description based on the product condition and appropriate price.

[0602] "Means of presentation" refers to the part that has the function of displaying information such as the generated product description, the determined condition, and the set appropriate price to the user.

[0603] "Means of transmission" refers to the part that has the function of transferring data such as product condition and appropriate price to a cloud server.

[0604] An "image recognition algorithm" refers to a computational method or program used to analyze video data and identify the condition of a product.

[0605] A "generative AI model" is an artificial intelligence model that automatically creates product descriptions using natural language generation technology.

[0606] The embodiments for carrying out the present invention are described in detail below. The present invention significantly reduces the burden on the user by allowing the user to take product video data and upload it to an application for a flea market or e-commerce site, and the system automatically generates the product's condition, appropriate price, and description.

[0607] First, the user takes a picture of the item they want to list using their smartphone's camera function. The captured video data is uploaded to a cloud server via the application. The cloud server receives the video data and stores it in a database. This database contains video data of previously listed items, along with their corresponding condition and selling price.

[0608] The server uses an image recognition algorithm (e.g., Amazon Rekognition) to analyze uploaded product video data and compare it to video data in a database of past listing videos. This automatically determines the product's condition. Condition categories are classified into multiple levels, such as "new / unused," "like new," "good," and "used."

[0609] Next, the server refers to data on similar past products to determine a fair price based on the condition of the determined product. The fair price is automatically calculated based on the prices at which similar products in the same category have been traded.

[0610] Furthermore, the server automatically generates product descriptions using a generative AI model (e.g., OpenAI GPT-4). The product descriptions are generated based on a template that includes detailed product information, the determined condition, and the set appropriate price. This product description, containing this information, is sent to the user's device, where the user can review it.

[0611] Users can review the generated product description and appropriate price, and edit them as needed. They can then proceed to the final listing process within the application, allowing them to list their products on flea markets and e-commerce sites.

[0612] Hardware and software to be used

[0613] 1. Hardware:

[0614] Smartphone (for taking photos and using applications)

[0615] Cloud server (data storage and analysis)

[0616] 2. Software:

[0617] Smartphone application (for shooting and uploading product video data)

[0618] Amazon Rekognition (image analysis)

[0619] MySQL (database of past listing videos)

[0620] OpenAI GPT-4 (product description generation)

[0621] Specific example

[0622] User B decides to sell a guitar they no longer need and takes a picture of it with their smartphone camera. They then upload the video to a cloud server via an application. The server receives the video data and uses Amazon Rekognition to perform video analysis. It detects scratches and signs of wear on the guitar and compares them with a past database, resulting in a determination that the guitar "shows signs of wear." Based on past price data, a fair price of 20,000 yen is calculated.

[0623] Using OpenAI GPT-4, the following product description is generated and sent to user B's terminal:

[0624] "It shows some signs of use, but it's still a perfectly playable guitar. The price is 20,000 yen."

[0625] User B reviews this information, edits it as needed, and finally proceeds with the listing process.

[0626] Example of a prompt

[0627] Please generate an appropriate product description based on the product information provided.

[0628] Product name: Electric guitar

[0629] Condition: Shows signs of use.

[0630] Fair price: 20,000 yen

[0631] Example output:

[0632] "It shows some signs of use, but it's still a perfectly playable guitar. The price is 20,000 yen."

[0633] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0634] Step 1:

[0635] Users use their smartphone cameras to capture video data of the products they wish to list for sale. The video data must clearly show the product's appearance and details. The input is the video data of the product captured by the user. The output is the video data uploaded to the application.

[0636] Step 2:

[0637] The device uploads the captured product video data to a cloud server via an application. The video data is transmitted over the internet and stored in cloud storage (e.g., Amazon S3). The input is the video data captured by the user, and the output is the URL of the cloud storage where the data is saved.

[0638] Step 3:

[0639] The server retrieves product video data stored in cloud storage and performs analysis using an image recognition algorithm (e.g., Amazon Rekognition). The server analyzes the product video data, extracts features from the video data, and compares them with a database of past listing videos. The input is the URL of the video data, and the output is the analysis results (product features and condition information).

[0640] Step 4:

[0641] The server uses the results of an image recognition algorithm to determine the condition of a product by referencing a database of past listing images (e.g., MySQL). Simultaneously, it calculates a fair price by referencing past sales data for products in the same category. The input is the analyzed product characteristics, and the output is the product condition and fair price.

[0642] Step 5:

[0643] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate a product description based on the determined product condition and fair price. The generative AI model is supplied with predefined templates and prompts. The inputs are the product condition, fair price, and template, and the output is the automatically generated product description.

[0644] Step 6:

[0645] The server sends the generated product description, determined condition, and set appropriate price to the user's terminal. The user can review this information and edit it as needed. The input is the automatically generated product description and price information, and the output is the information provided to the user in a visual interface.

[0646] Step 7:

[0647] The user reviews the edited information on the application and then clicks the "List for Sale" button to finally list the product on the flea market or e-commerce site. The server receives this and completes the final product listing process. The input is the user's final confirmation information, and the output is the product list that will be published on the flea market or e-commerce site.

[0648] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0649] The following describes in detail embodiments of the present invention that combine an emotion engine.

[0650] This invention combines a system that automatically generates product condition, appropriate price, and description to assist users in listing items simply by having them shoot product video data and upload it to a flea market application, with an emotion engine that recognizes the user's emotions. This provides an even more personalized listing experience.

[0651] The system consists of a server, an emotion engine, and a user terminal. The program's processing is described below in natural language.

[0652] 1. Input and save of product video data

[0653] First, the user takes a video of the item they want to sell using their device. The video must include detailed information about the item. The user uploads this video data to the server via the flea market app. The server receives the video data and stores it.

[0654] 2. Analysis and comparison of video data

[0655] The server references a database of past listing videos and uses an image recognition algorithm to compare uploaded product video data with similar products. This comparison automatically determines the condition of the product.

[0656] 3. Setting appropriate prices and generating introductory texts.

[0657] Based on the determined product condition, the server sets an appropriate selling price by referring to data on similar products from the past. It also automatically generates a product description based on the product condition and appropriate price. This description includes a detailed explanation of the product and the appropriate price for the user.

[0658] 4. Recognition of user emotions by an emotion engine

[0659] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions in real time. For example, if a user expresses dissatisfaction or confusion regarding a product description or price, the emotion engine will detect this.

[0660] 5. Emotion-based presentation and adjustment

[0661] Based on user sentiment, the server adjusts product descriptions and suggestions. For example, if a user expresses dissatisfaction, it readjusts the price and description based on data from other similar products. It can also provide product recommendations and advice based on sentiment recognition results.

[0662] 6. Presentation to the user and editing

[0663] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. Users can review this information and edit the description and price as needed. Because adjustments based on the sentiment engine are also incorporated, users can create more satisfying listings.

[0664] Specific example

[0665] For example, user B wants to sell a used digital camera and takes a video of it. They upload this video to the server via a flea market app. The server saves the video data, compares it to past digital camera listings, and determines that the camera is in "good" condition. It also sets a fair price of 28,000 yen based on past data and generates a product description like the following:

[0666] "I'm selling a digital camera in good condition. It shows some signs of use, but there are no problems with its performance. The price is 28,000 yen."

[0667] The generated information is presented to User B, and the emotion engine detects that User B appears slightly dissatisfied. Therefore, the server suggests readjusting the price and revising the description. User B then reviews and edits the description and price before completing the listing.

[0668] The above describes an embodiment of the present invention that combines an emotion engine. This embodiment allows users to enjoy a personalized listing experience and make the listing process more effective and satisfying.

[0669] The following describes the processing flow.

[0670] Step 1:

[0671] Users film product footage and upload it to the system using their devices.

[0672] Users use devices such as smartphones or tablets to take detailed videos of the items they want to list for sale.

[0673] After filming is complete, the video files are uploaded to the server via a flea market app.

[0674] Step 2:

[0675] The server receives and saves the uploaded product video data.

[0676] The server receives the video file sent by the user.

[0677] The received video data is saved to a temporary storage directory, and the metadata of that file (e.g., upload date and time, user ID, etc.) is also recorded.

[0678] Step 3:

[0679] The server searches for similar products by referring to a database of past listing videos.

[0680] The server retrieves video data of previously listed products from the database.

[0681] Video data is filtered based on metadata such as product category, manufacturer, and model number to select appropriate comparison targets.

[0682] Step 4:

[0683] The server uses video comparison technology to analyze and compare product video data.

[0684] The server analyzes product video data frame by frame using image recognition algorithms (such as CNN or SIFT).

[0685] Based on the analyzed data, we compare it with video data of similar products to extract features related to the condition of the product.

[0686] Step 5:

[0687] The server determines the condition of the product based on the video comparison results.

[0688] The server determines the condition category to which the product belongs based on the extracted features.

[0689] The condition category can be selected from options such as "New / Unused," "Like New," "Good," and "Used."

[0690] Step 6:

[0691] The server sets an appropriate selling price based on data on the condition and selling price of similar products from the past.

[0692] The server uses past data of similar products as a reference to determine the price based on the determined condition category.

[0693] The optimal selling price is calculated by utilizing statistical data such as the average price, median price, and latest transaction price.

[0694] Step 7:

[0695] The server automatically generates a product description based on the product's condition and pricing.

[0696] The server generates product descriptions based on a template.

[0697] The generated description will include a detailed description of the product's condition and its selling price.

[0698] Step 8:

[0699] The emotion engine recognizes the user's emotions.

[0700] The emotion engine analyzes the user's facial expressions and voice in real time as they interact with the system.

[0701] The emotion engine recognizes the user's emotional state (e.g., satisfaction, dissatisfaction, confusion, etc.).

[0702] Step 9:

[0703] The server adjusts the product description and pricing based on the emotion recognition results.

[0704] Based on the results from the emotion engine, the server adjusts the product description and the set price.

[0705] For example, if a user expresses dissatisfaction, we might revise the pricing or make changes to supplement the explanation.

[0706] Step 10:

[0707] The server displays the generated description, the determined condition, and the set selling price to the user.

[0708] The server displays this information on the user's device.

[0709] Users can review the presented information and edit the description and price as needed.

[0710] Step 11:

[0711] The user reviews and edits the product information, and finally completes the listing process.

[0712] The user edits the provided product information, and if they are satisfied with the content, they press the "List Item" button to complete the listing process.

[0713] The final listing information is sent to the server and posted on the flea market app.

[0714] Through the above processing steps, the present invention provides users with a personalized listing experience, enabling more effective and satisfying listings.

[0715] (Example 2)

[0716] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0717] Traditional flea market applications had problems such as requiring users to spend a lot of time and effort determining the condition of their items, setting appropriate prices, and writing product descriptions when listing items. Furthermore, they lacked features that provided a personalized listing experience that took user emotions into consideration. As a result, it was difficult for users to list items in a way that they found satisfying.

[0718] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0719] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referencing past listing video data, means for comparing the product video data with data in the past listing video data to determine the product condition, means for setting an appropriate price for the product based on the product condition, means for generating a product description based on the product condition and the appropriate price, means for recognizing the user's emotions, means for adjusting the product description and appropriate price based on the user's emotions, and means for presenting the product condition, appropriate price, and product description to the user. As a result, users can easily determine the product condition, set an appropriate price, generate a personalized product description, and make adjustments that take into account the user's emotions, making it possible to list products that will satisfy users.

[0720] "Product video data" refers to video data of products that users wish to list for sale, captured with a camera, and includes information that shows the product's appearance and characteristics.

[0721] "Means of storage" refers to the function of storing and managing video data received by the server in a storage device such as a database.

[0722] "Past listing video data" refers to video data of items that users have previously listed through the flea market application, and is used as reference data to determine the condition and price of the items.

[0723] "Method of comparison" refers to a function that uses an image recognition algorithm to compare uploaded product video data with past listing video data to determine the condition of the product.

[0724] "Product condition" refers to an assessment of the product's usage history, presence or absence of damage, and describes the condition of the item being offered for sale.

[0725] "Fair price" refers to a reasonable selling price for a listed product, determined based on past listing data and sales performance of similar products.

[0726] A "product description" is a text that explains the features, condition, and selling price of the listed product, and includes information to make the product appealing to potential buyers.

[0727] "Means of recognizing user emotions" refers to a function that uses cameras and microphones to collect user facial expressions and voice data, analyzes it, and identifies the user's emotional state (e.g., satisfaction, dissatisfaction, confusion).

[0728] "Means of presentation" refers to the function by which the server displays the final generated product description, determined condition, and set appropriate price on the user's device, allowing the user to review and edit the information.

[0729] The following describes in detail an embodiment of the present invention that incorporates an emotion engine. The present invention combines an emotion engine that recognizes the user's emotions with a system that automatically generates product condition, appropriate price, and description to support listing a product simply by the user taking product video data and uploading it to a flea market application. This provides an even more personalized listing experience.

[0730] The system consists of a server, terminals, and an emotion engine. Specifically, it is implemented using the following hardware and software:

[0731] Hardware and software to be used

[0732] 1. Server:

[0733] Databases for data storage and processing (e.g., MySQL, PostgreSQL)

[0734] Image recognition algorithms (e.g., TensorFlow, OpenCV)

[0735] Statistical analysis and machine learning algorithms (e.g., Scikit-learn)

[0736] Emotion engine (e.g., Affectiva, Microsoft Azure Cognitive Services)

[0737] Generative AI models (e.g., GPT-4)

[0738] 2. Terminal:

[0739] Smartphones and tablets used by users

[0740] Camera and microphone functions

[0741] 3. Network:

[0742] Internet connection for connecting terminals and servers

[0743] Example of operation

[0744] The following provides specific examples of how to operate the system.

[0745] Product video data input

[0746] Users use their device's camera to capture video data of the items they want to list for sale. For example, when photographing a used digital camera, they should ensure that the camera body and its main components are clearly visible.

[0747] Uploading product video data

[0748] Users upload the recorded video data to the server via a flea market app on their device. This is done by selecting the "List Item" button in the app, specifying the video data, and sending it.

[0749] Analysis and comparison of video data

[0750] The server imports the stored product video data into an analysis program and determines the product's condition while referring to a database of past listing videos. This process utilizes image recognition algorithms such as TensorFlow and OpenCV.

[0751] Setting appropriate prices and generating introductory texts.

[0752] Based on the determined product condition, the server sets an appropriate selling price by referring to data on similar products from the past. This uses machine learning algorithms such as Scikit-learn. In addition, product descriptions are automatically generated using an AI model (e.g., GPT-4) that generates information on the appropriate price and product condition.

[0753] Recognition of user emotions by an emotion engine

[0754] While the user is reviewing product descriptions and prices displayed on their device, the device's camera and microphone record the user's facial expressions and voice. This data is sent to a server, where an emotion engine analyzes the user's emotional state.

[0755] Final presentation to the user

[0756] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. The user can review this information and edit the description and price as needed. Because the sentiment engine's adjustments are reflected, users can create more satisfying listings.

[0757] Examples of prompts to input into a generative AI model

[0758] "I have uploaded images of a used digital camera. Please assess the camera's condition and generate an appropriate selling price and description. Also, please consider user sentiment and adjust the description and price accordingly to present the final listing."

[0759] The above describes an embodiment of the present invention that combines an emotion engine. This embodiment allows users to enjoy a personalized listing experience and make the listing process more effective and satisfying.

[0760] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0761] Step 1: Input and save product video data.

[0762] 1.1 Filming product video data

[0763] The user takes photos of the item they want to list using their device. These input videos must capture the item's main features and condition in detail. Specifically, the user launches their smartphone's camera app and takes photos of the item from several angles.

[0764] 1.2 Uploading video data

[0765] Users upload recorded video data to the server via a flea market app. Input is done by the user selecting video data from their device and tapping the "List Item" button in the app. Output is the video data being sent to the server.

[0766] 1.3 Data storage on the server

[0767] The server verifies the received video data and saves it to the database. In this step, a unique ID is assigned to the video data so that it can be referenced in subsequent processing. The input is the uploaded video data, and the output is the unique ID of the saved data.

[0768] Step 2: Analysis and comparison of video data

[0769] 2.1 Importing video data

[0770] The server takes the stored video data into the analysis program. The input is the stored video data, and the output is video data in a format suitable for analysis. Specifically, preprocessing is performed to extract image and text information.

[0771] 2.2 Searching for similar products

[0772] The server references a database of past listing videos and uses an image recognition algorithm to compare uploaded product video data with similar products. The input is the captured video data and past listing data, and the output is the matching result with similar products. Specifically, image analysis is performed using TensorFlow and OpenCV.

[0773] 2.3 Determining the condition of the product

[0774] The server automatically determines the condition of the product in the analyzed video data based on data of similar products. The input is the matching results for similar products, and the output is the product condition evaluation. The evaluation algorithm determines the product condition (e.g., "Good," "Like New") based on evaluation criteria.

[0775] Step 3: Setting an appropriate price and generating a promotional text.

[0776] 3.1 Setting a fair price

[0777] The server sets an appropriate selling price based on the determined product condition, referencing data from similar products in the past. The input is the product condition evaluation and data from similar products in the past, and the output is the appropriate price. Specifically, it uses statistical analysis algorithms such as Scikit-learn and machine learning algorithms.

[0778] 3.2 Generating Product Descriptions

[0779] The server automatically generates product descriptions using a generative AI model based on information about the appropriate price and product condition. The input is information about the appropriate price and product condition, and the output is the product description. Specifically, a generative AI model (e.g., GPT-4) is used to create text that attractively expresses the features and benefits of the product.

[0780] Step 4: Recognition of user emotions by the emotion engine

[0781] 4.1 Collecting User Feedback

[0782] While the user is reviewing the product description and price, the device's camera and microphone are used to record the user's facial expressions and voice. The input consists of the displayed product description and price, as well as the user's reaction data (facial expressions, voice), and the output is this reaction data.

[0783] 4.2 Analysis of User Sentiment

[0784] Data collected by the device is sent to the server in real time. The server uses an emotion engine to analyze the user's emotions. The input is the user's reaction data, and the output is an evaluation of the emotional state. Specifically, it uses emotion analysis engines such as Affectiva or Microsoft Azure Cognitive Services.

[0785] 4.3 Feedback on emotional data

[0786] The analysis results from the emotion engine are returned to the server, and data on the user's emotional state (e.g., satisfied, dissatisfied, confused) is fed back. The input is the evaluation result of the emotional state, and the output is the feedback data.

[0787] Step 5: Emotion-based presentation and adjustment

[0788] 5.1 Data Recalibration

[0789] The server readjusts product descriptions and prices based on the results of sentiment analysis. Input is feedback data and existing description and price information, while output is the readjusted description and price. If the user expresses dissatisfaction or confusion, the server attempts to regenerate the price and description using a different dataset or new parameters.

[0790] 5.2 Providing recommendations and advice

[0791] If necessary, the server provides recommendations for other similar products and advice to help users be satisfied. The input is re-tuned data and user sentiment analysis results, and the output is advice information and recommendation lists.

[0792] Step 6: Presentation to the user and editing

[0793] 6.1 Final presentation

[0794] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. The input is the re-adjusted data, and the output is the final information displayed on the user's device. The user can review this information and edit the description and price as needed.

[0795] 6.2 Editing Users

[0796] Users can review the presented information and edit the description and price as needed. The input is the final information presented, and the output is the edited information. Text and numbers can be changed using the editing function within the app.

[0797] 6.3 Completion of listing

[0798] After the user confirms the listing details they are finally satisfied with, they can press the "Complete Listing" button to officially list the product. The input is the final information edited by the user, and the output is the final listing data.

[0799] (Application Example 2)

[0800] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0801] Traditional e-commerce sites display product descriptions and reviews uniformly, making it difficult to address the individual emotions and needs of each consumer. In particular, the lack of real-time solutions to consumer frustrations and questions while browsing product pages poses a risk of diminishing their purchase intent. Therefore, a system is needed that dynamically adjusts product descriptions, prices, and recommendations based on consumer emotions, providing information optimized for each individual consumer.

[0802] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a past listing video database, means for comparing the product video data with video data in the past listing video database to determine the product condition, means for setting an appropriate price for the product based on the product condition, means for generating a product description based on the product condition and the appropriate price, means for analyzing input video and audio data to analyze the user's emotions, means for adjusting the product description and the appropriate price based on the user's emotions, and means for presenting the product condition, the appropriate price, and the product description to the user. This makes it possible to provide personalized information based on the consumer's emotions in real time.

[0803] "Product video data" refers to digital data of videos taken by users of products they wish to list or purchase.

[0804] The "Past Listing Video Database" is a database that stores videos and related data of items previously listed on flea markets and online shopping sites.

[0805] "Product condition" refers to information about the product's condition, such as its age (new or old) and whether or not it has any damage.

[0806] A "fair price" is a fair and realistic selling price calculated based on the condition of the product and the supply and demand in the market.

[0807] A "product description" is a descriptive text that details the product's features, condition, price, and other relevant information.

[0808] "Emotion analysis means" refers to technical means for analyzing a user's video and audio data to recognize their emotions.

[0809] "Presentation method" refers to a means of displaying the generated product condition, appropriate price, and product description to the user.

[0810] "Editing methods" refer to means that enable users to modify and edit product descriptions and appropriate pricing.

[0811] An "image recognition algorithm" is an algorithm that analyzes input video data to identify and determine the content of an image.

[0812] This invention relates to a system that automatically generates product condition, appropriate price, and product description based on product video data, and adjusts them based on the user's emotions. This system inputs product video data, stores it, analyzes it, and performs a series of processes to present it to the user. Furthermore, it can analyze the user's emotions and personalize the content accordingly.

[0813] First, the user takes product video data using a device such as a smartphone or smart glasses and inputs it into the system. The input product video data is sent to a server and stored there.

[0814] Next, the server analyzes the stored product video data. Image recognition algorithms are used for this analysis. The server refers to a database of past listing videos and compares them with the current video data to determine the condition of the product. For example, it determines whether the product is used or new, and how much wear and tear it has.

[0815] Subsequently, the server sets an appropriate price based on the determined product condition. Past data on similar products is used as a reference when setting the appropriate price. Furthermore, a product description is automatically generated based on the determined product condition and appropriate price. This product description includes details such as the product's features, condition, and price.

[0816] Next, emotion analysis tools are used to analyze the user's emotions in real time. These tools analyze the user's facial expressions and voice to recognize their emotions. This analysis utilizes the camera and microphone of a smartphone or smart glasses.

[0817] Based on the sentiment analysis results, the server adjusts product descriptions and appropriate pricing. For example, if a user displays a dissatisfied expression, the detailed product description and price will be reconsidered. Recommended products and advice based on sentiment analysis are also provided.

[0818] Finally, the adjusted product condition, appropriate price, and product description are presented to the user. The user can review this and edit it as needed.

[0819] Specific example

[0820] For example, a user takes a picture of a used digital camera using their smartphone and uploads the image data to the system. Based on this data, the server determines the product's condition as "good" and sets a fair price of 28,000 yen. A generated product description is then presented to the user.

[0821] If a user expresses dissatisfaction with the offered price, sentiment analysis tools will recognize this, and the server will readjust the price and description. Ultimately, the user can list their product in a way that satisfies them.

[0822] Examples of prompts for generative AI models

[0823] Create specific code for an e-commerce application that recognizes user emotions in real time from facial expressions and voice, and provides personalized product information based on those emotions. Include a process for collecting user data using the camera and microphone of a smartphone or smart glasses, and optimizing product information after emotion analysis. The generated code should specifically indicate the use of emotion and recommendation engines.

[0824] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0825] Step 1:

[0826] Users use their smartphones or smart glasses to capture video data of the items they want to list for sale. This video data includes detailed information about the products.

[0827] Input: Product video data

[0828] Output: Video data stored on the device

[0829] Specific operation: The user takes a picture of the product using the camera function of their smartphone or smart glasses, and the image data is saved on the device.

[0830] Step 2:

[0831] The device uploads the captured product video data to the server via the flea market application.

[0832] Input: Video data stored on the device

[0833] Output: Video data sent to the server

[0834] Specific operation: The user presses the "Upload" button within the application, and the video data is sent to the server via the internet.

[0835] Step 3:

[0836] The server receives the uploaded product video data and saves it to the database.

[0837] Input: Video data sent to the server

[0838] Output: Video data stored in the database

[0839] Specific operation: The server receives an HTTP request and saves the video data to dedicated storage.

[0840] Step 4:

[0841] The server analyzes the stored product video data. This analysis uses an image recognition algorithm.

[0842] Input: Video data stored in the database

[0843] Output: Analyzed product condition data

[0844] Specific operation: The server executes an image recognition algorithm and analyzes the video data to determine the condition of the product. For example, information such as the age of the product and whether or not there are any scratches is extracted.

[0845] Step 5:

[0846] The server refers to a database of past listing videos and compares them with current video data to determine the product's condition in more detail.

[0847] Input: Analyzed product condition data, past listing video database

[0848] Output: Detailed product condition data

[0849] Specific operation: The server searches for similar images in its past database, compares them with the current data, and determines the product condition more accurately.

[0850] Step 6:

[0851] The server sets an appropriate price based on the determined product condition. This setting is based on data from similar products in the past.

[0852] Input: Detailed product condition data, data on similar products from the past.

[0853] Output: Fair price data

[0854] Specific operation: The server uses an algorithm to combine product condition and market data to calculate a fair price.

[0855] Step 7:

[0856] The server automatically generates a product description based on the determined product condition and appropriate price.

[0857] Input: Detailed product condition data, appropriate price data

[0858] Output: Product description data

[0859] Specific operation: The server uses a text generation algorithm to generate a product description. This description includes the product's features, condition, price, etc.

[0860] Step 8:

[0861] The server analyzes video and audio data received from the terminal in real time to analyze the user's emotions.

[0862] Input: Video and audio data received from the device.

[0863] Output: User's emotional data

[0864] Specific operation: Using data collected from the device's camera and microphone, the server runs an emotion analysis engine to recognize the user's emotions.

[0865] Step 9:

[0866] The server adjusts product descriptions and appropriate pricing based on user sentiment data.

[0867] Input: User sentiment data, product description data, appropriate price data

[0868] Output: Adjusted product description data, adjusted fair price data

[0869] Specific operation: The server uses user sentiment data to review the generated product description and appropriate price, and makes corrections as needed.

[0870] Step 10:

[0871] The server then presents the user with the final adjusted product condition, appropriate price, and product description, which the user can review and edit as needed.

[0872] Input: Adjusted product description data, adjusted fair price data

[0873] Output: Final data presented to the user

[0874] Specific operation: The server sends the adjusted information to the user's terminal, the user reviews the displayed data, edits it as needed, and then performs a final confirmation.

[0875] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0876] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0877] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0878] [Third Embodiment]

[0879] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0880] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0881] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0882] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0883] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0884] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0885] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0886] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0887] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0888] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0889] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0890] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0891] Embodiments of the present invention will be described in detail below.

[0892] This invention provides a system that supports listing products by automatically generating product condition, appropriate price, and description simply by having the user film product images and upload them to a flea market application. This significantly reduces the effort required from the user and enables efficient listing.

[0893] The system consists of a server and user terminals. First, the user takes a video of the item they want to sell using their terminal. This video must include detailed information about the item. Next, the user uploads the video to the server through the flea market app.

[0894] The server receives and stores the uploaded product video data. The stored product video data is then compared with the video database on the server. This video database contains video data of previously listed products, their condition, and their selling prices.

[0895] The server uses an image recognition algorithm to compare uploaded product video data with past listing video data in the database. Based on this comparison, the server automatically determines the product's condition. The condition is categorized into several categories, such as "new / unused," "almost new," "good," and "used."

[0896] Next, the server sets an appropriate selling price based on the determined condition of the product, referencing data from similar products in the past. This appropriate price is calculated based on the prices at which similar products in the same category were traded in the past.

[0897] Furthermore, the server automatically generates a product description based on the product's condition and appropriate price. This description is generated from the original template and includes detailed information about the product, such as its condition and selling price.

[0898] Finally, the server displays the generated product description, the determined condition, and the set appropriate price to the user's device. The user can review this information and edit it as needed. Once editing is complete, the user can finally list the product for sale.

[0899] Specific example:

[0900] User A wants to sell a used smartphone and takes detailed video footage of the smartphone. Next, User A uploads this video to a server through a flea market application. The server receives and saves the video and compares it with video data of similar smartphones from the past.

[0901] Based on the video comparison, the server determines that User A's smartphone is in "almost new" condition. It also sets the appropriate price at 35,000 yen based on past data. Next, the server automatically generates a product description like the following:

[0902] "I'm selling a smartphone that's barely been used. It's in excellent condition, practically brand new. The price is 35,000 yen."

[0903] This information is displayed to User A's device, and User A reviews the content and edits the description and price as needed. After editing is complete, User A can proceed with the listing process and list their smartphone for sale on the flea market.

[0904] The above describes the embodiment of the present invention. This embodiment enables users to list products efficiently without any hassle.

[0905] The following describes the processing flow.

[0906] Step 1:

[0907] Users film product footage and upload it to the system using their devices.

[0908] Users use devices such as smartphones or tablets to take detailed videos of the items they want to list for sale.

[0909] After filming is complete, the video files are uploaded to the server via a flea market app.

[0910] Step 2:

[0911] The server receives and saves the uploaded product video data.

[0912] The server receives the video file sent by the user.

[0913] The received video data is saved to a temporary storage directory, and the metadata of that file (e.g., upload date and time, user ID, etc.) is also recorded.

[0914] Step 3:

[0915] The server searches for similar products by referring to a database of past listing videos.

[0916] The server retrieves video data of previously listed products from the database.

[0917] Video data is filtered based on metadata such as product category, manufacturer, and model number to select appropriate comparison targets.

[0918] Step 4:

[0919] The server uses video comparison technology to analyze and compare product video data.

[0920] The server analyzes product video data frame by frame using image recognition algorithms (such as CNN or SIFT).

[0921] Based on the analyzed data, we compare it with video data of similar products to extract features related to the condition of the product.

[0922] Step 5:

[0923] The server determines the condition of the product based on the video comparison results.

[0924] The server determines the condition category to which the product belongs based on the extracted features.

[0925] The condition category can be selected from options such as "New / Unused," "Like New," "Good," and "Used."

[0926] Step 6:

[0927] The server sets an appropriate selling price based on data on the condition and selling price of similar products from the past.

[0928] The server uses past data of similar products as a reference to determine the price based on the determined condition category.

[0929] The optimal selling price is calculated by utilizing statistical data such as the average price, median price, and latest transaction price.

[0930] Step 7:

[0931] The server automatically generates a product description based on the product's condition and pricing.

[0932] The server generates product descriptions based on a template.

[0933] The generated description will include a detailed description of the product's condition and its selling price.

[0934] Step 8:

[0935] The server displays the generated description, the determined condition, and the set selling price to the user.

[0936] The server displays the generated description and pricing information on the user's device.

[0937] Users can review the presented content and make corrections as needed.

[0938] Step 9:

[0939] The user reviews and edits the product information, and finally completes the listing process.

[0940] The user edits the provided product information, and if they are satisfied with the content, they press the "List Item" button to complete the listing process.

[0941] The final listing information is sent to the server and posted on the flea market app.

[0942] Through the above processing steps, users can easily list products and save a lot of time and effort.

[0943] (Example 1)

[0944] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0945] Current flea market applications present a problem: users must create detailed descriptions for each item they list and set appropriate prices, a process that is extremely time-consuming and laborious. Furthermore, accurately assessing the condition of an item requires specialized knowledge, making it difficult for the average user. As a result, users have to expend a great deal of effort when listing items, making efficient listing difficult.

[0946] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0947] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a database of past listing videos, means for comparing the product video data with video data in the database of past listing videos to determine the condition of the product, means for setting an appropriate price for the product based on the condition of the product, means for using a generation AI to generate a product description, means for generating a product description based on the condition of the product and the appropriate price, and means for presenting the condition of the product, the appropriate price, and the product description to the user. As a result, users can simply upload product videos, and the system will automatically determine the condition of the product, set an appropriate price, and generate a product description, enabling efficient listing.

[0948] "Product video data" refers to video information about products listed by users, and is data that visually records the detailed condition and characteristics of the product.

[0949] "Means of storage" refers to a system for storing and managing received product video data in a database or storage device.

[0950] "Means of reference" refers to a system that allows users to view past listing video data and use it for comparison and analysis.

[0951] "Means for comparing and determining the condition of a product" refers to algorithms or software that compare product video data with video data from a database of past listing videos and automatically classify and evaluate the condition of the product.

[0952] "Methods for setting appropriate prices" refer to systems for calculating the optimal selling price of a product based on its condition and past transaction data.

[0953] "Methods of using generative AI" refer to systems that use artificial intelligence technology to automatically create and generate text and data.

[0954] "Methods for generating product descriptions" refers to a function that automatically generates user-oriented descriptions based on elements such as product details, condition, and price.

[0955] "Means of presentation to the user" refers to an interface that provides the user with the generated product description, the determined product condition, and the set appropriate price, allowing the user to review and edit them.

[0956] This invention supports listing products by allowing users to simply film product images and upload them to a flea market application. The system automatically generates product condition, appropriate price, and description, significantly reducing user effort and enabling efficient listing. The details are described below.

[0957] The system consists of a server and user terminals. First, the user takes a video of the item they want to sell using their terminal. This video must include detailed information about the item. Next, the user uploads the video to the server through a flea market application.

[0958] The server receives uploaded product video data and has a database for storing it. The stored product video data is compared with the video database on the server, which includes video data of previously listed products, their condition, and sales price.

[0959] Image data analysis uses image recognition algorithms such as TensorFlow and PyTorch. The server uses these algorithms to compare uploaded product video data with past listing video data and automatically determine the product's condition. The condition is classified into several categories, such as "new / unused," "almost new," "good," and "used."

[0960] Next, the server uses a generative AI model (e.g., GPT-3) to generate a product description. The description is generated from a template based on the product's condition and appropriate price. For example, a description such as, "I am selling a smartphone that has hardly been used. It is in excellent condition, almost like new. The price is 35,000 yen," might be created.

[0961] Finally, the server displays the generated product description, the determined condition, and the set appropriate price to the user's device. The user can review this information and edit the description and price as needed. Once editing is complete, the user can finally list the product for sale.

[0962] Specific example

[0963] User A wants to sell a used smartphone and takes detailed video footage of the smartphone. Next, User A uploads this video to a server through a flea market application. The server receives and saves the video and compares it with video data of similar smartphones from the past.

[0964] Based on the video comparison, the server determines that User A's smartphone is in "almost new" condition. It also sets the appropriate price at 35,000 yen based on past data. Next, the server automatically generates a product description like the following:

[0965] "I'm selling a smartphone that's barely been used. It's in excellent condition, practically brand new. The price is 35,000 yen."

[0966] This information is displayed to User A's device, and User A reviews the content and edits the description and price as needed. After editing is complete, User A can proceed with the listing process and list their smartphone for sale on the flea market.

[0967] Example of a prompt

[0968] "Please record video data of your used smartphone and upload it to the server via the flea market application. The server will receive and analyze the video data, automatically determine the product's condition and appropriate price, and generate a description. Once you have reviewed and edited this information, please list your product for sale."

[0969] The above describes the embodiments for carrying out the present invention. This embodiment allows users to list products efficiently without any hassle.

[0970] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0971] Step 1:

[0972] Input: Video data of the product the user wants to list for sale.

[0973] Process: Users use their own devices to film detailed videos of the products they wish to sell. The videos must include the overall image and specific distinctive features. For example, in the case of a smartphone, videos should be taken from various angles, including the front, back, sides, and screen.

[0974] Output: Recorded video data

[0975] Step 2:

[0976] Input: Recorded video data

[0977] Processing: The user's device uploads the captured video data to the server via the flea market application. During this process, the application compresses and formats the video data, converting it into a format optimized for transfer. For example, it compresses the video data into JPEG or PNG format before sending it.

[0978] Output: Compressed video data transferred to the server

[0979] Step 3:

[0980] Input: Compressed video data transferred to the server

[0981] Processing: The server saves the received video data to a database. Each product is assigned a unique identifier in this database, and the data is managed based on that identifier. The saved video data is used for subsequent analysis.

[0982] Output: Video data stored in the database

[0983] Step 4:

[0984] Input: Video data stored in the database

[0985] Processing: The server analyzes the video data using an image recognition algorithm (e.g., TensorFlow or PyTorch). The algorithm automatically identifies the condition and characteristics of the product. Specifically, it detects scratches, color variations, button wear, etc.

[0986] Output: Product feature information based on video data

[0987] Step 5:

[0988] Input: Product feature information based on video data

[0989] Processing: The server determines the condition of the product based on its characteristic information, comparing it with past listing data. For example, it classifies items into categories such as "new / unused," "almost new," "good," and "used." This comparison uses a database of previously accumulated listing data.

[0990] Output: Condition of the determined product

[0991] Step 6:

[0992] Input: Condition of the item being assessed

[0993] Processing: The server sets an appropriate selling price based on the product's condition and by referring to past transaction data. For example, it calculates the price based on the prices at which similar products in the same category and condition have been sold in the past.

[0994] Output: Set appropriate selling price

[0995] Step 7:

[0996] Input: Condition of the assessed product and fair selling price

[0997] Processing: The server uses a generative AI model (e.g., GPT-3) to generate product descriptions. It inserts the product's condition and price into a description template to create a specific description. For example: "I am selling a smartphone in almost unused condition. It is in excellent condition, practically brand new. The price is 35,000 yen."

[0998] Output: Generated product description

[0999] Step 8:

[1000] Input: Generated product description, determined product condition, and appropriate selling price.

[1001] Processing: The server sends this information to the user's terminal. A dedicated interface is designed to make it easy for the user to review the content on their terminal. The user can also edit this information.

[1002] Output: Product description, product condition, and fair selling price displayed on the user's device.

[1003] Step 9:

[1004] Input: User-verified and edited introductory text and price

[1005] Processing: Users review the presented information and edit the product description and appropriate selling price as needed. For example, they can add additional information to the description, such as "Original box and accessories are included," or make minor adjustments to the price.

[1006] Output: Edited product description and selling price

[1007] Step 10:

[1008] Input: Edited product description and selling price

[1009] Processing: The user completes the final listing procedure. They press the "List Item" button in the application to list the item on the flea market. This action automatically completes the listing process on the system side, and the item is listed on the flea market.

[1010] Output: Items listed on the flea market

[1011] (Application Example 1)

[1012] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1013] Current flea market and online shopping sites require users to go through many steps when listing items. Specifically, it involves taking photos of the product, assessing its condition, setting an appropriate price, and writing a product description. This can cause users to hesitate to list items, and sales may suffer due to inappropriate pricing or poor product descriptions. Therefore, there is a need to streamline the listing process and reduce the burden on users.

[1014] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1015] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a database of past listing videos, means for comparing product video data with video data in the database of past listing videos to determine the condition of the product, means for setting an appropriate price for the product based on the condition of the product, means for generating a product description based on the condition of the product and the appropriate price, means for presenting the condition of the product, the appropriate price, and the product description to the user, means for sending the condition of the product and the appropriate price to a cloud server and analyzing it using an image recognition algorithm, and means for generating a product description using a generation AI model. This makes it possible for users to list products quickly and efficiently without any hassle.

[1016] "Product video data" refers to video and image data of products that users plan to list for sale.

[1017] "Means of storage" refers to the part that has the function of storing the input product video data in a storage device.

[1018] The "Listing Video Database" is a database that stores video data and information about products that have been listed for sale in the past.

[1019] The "means of comparison and judgment" refers to the function that automatically evaluates the condition of a product by comparing product video data with data from a database of past listing videos.

[1020] "Means of setting" refers to the part that has the function of determining an appropriate selling price for a product based on the determined product condition.

[1021] "Generating means" refers to the part that has the function of automatically creating a product description based on the product condition and appropriate price.

[1022] "Means of presentation" refers to the part that has the function of displaying information such as the generated product description, the determined condition, and the set appropriate price to the user.

[1023] "Means of transmission" refers to the part that has the function of transferring data such as product condition and appropriate price to a cloud server.

[1024] An "image recognition algorithm" refers to a computational method or program used to analyze video data and identify the condition of a product.

[1025] A "generative AI model" is an artificial intelligence model that automatically creates product descriptions using natural language generation technology.

[1026] The embodiments for carrying out the present invention are described in detail below. The present invention significantly reduces the burden on the user by allowing the user to take product video data and upload it to an application for a flea market or e-commerce site, and the system automatically generates the product's condition, appropriate price, and description.

[1027] First, the user takes a picture of the item they want to list using their smartphone's camera function. The captured video data is uploaded to a cloud server via the application. The cloud server receives the video data and stores it in a database. This database contains video data of previously listed items, along with their corresponding condition and selling price.

[1028] The server uses an image recognition algorithm (e.g., Amazon Rekognition) to analyze uploaded product video data and compare it to video data in a database of past listing videos. This automatically determines the product's condition. Condition categories are classified into multiple levels, such as "new / unused," "like new," "good," and "used."

[1029] Next, the server refers to data on similar past products to determine a fair price based on the condition of the determined product. The fair price is automatically calculated based on the prices at which similar products in the same category have been traded.

[1030] Furthermore, the server automatically generates product descriptions using a generative AI model (e.g., OpenAI GPT-4). The product descriptions are generated based on a template that includes detailed product information, the determined condition, and the set appropriate price. This product description, containing this information, is sent to the user's device, where the user can review it.

[1031] Users can review the generated product description and appropriate price, and edit them as needed. They can then proceed to the final listing process within the application, allowing them to list their products on flea markets and e-commerce sites.

[1032] Hardware and software to be used

[1033] 1. Hardware:

[1034] Smartphone (for taking photos and using applications)

[1035] Cloud server (data storage and analysis)

[1036] 2. Software:

[1037] Smartphone application (for shooting and uploading product video data)

[1038] Amazon Rekognition (image analysis)

[1039] MySQL (database of past listing videos)

[1040] OpenAI GPT-4 (product description generation)

[1041] Specific example

[1042] User B decides to sell a guitar they no longer need and takes a picture of it with their smartphone camera. They then upload the video to a cloud server via an application. The server receives the video data and uses Amazon Rekognition to perform video analysis. It detects scratches and signs of wear on the guitar and compares them with a past database, resulting in a determination that the guitar "shows signs of wear." Based on past price data, a fair price of 20,000 yen is calculated.

[1043] Using OpenAI GPT-4, the following product description is generated and sent to user B's terminal:

[1044] "It shows some signs of use, but it's still a perfectly playable guitar. The price is 20,000 yen."

[1045] User B reviews this information, edits it as needed, and finally proceeds with the listing process.

[1046] Example of a prompt

[1047] Please generate an appropriate product description based on the product information provided.

[1048] Product name: Electric guitar

[1049] Condition: Shows signs of use.

[1050] Fair price: 20,000 yen

[1051] Example output:

[1052] "It shows some signs of use, but it's still a perfectly playable guitar. The price is 20,000 yen."

[1053] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1054] Step 1:

[1055] Users use their smartphone cameras to capture video data of the products they wish to list for sale. The video data must clearly show the product's appearance and details. The input is the video data of the product captured by the user. The output is the video data uploaded to the application.

[1056] Step 2:

[1057] The device uploads the captured product video data to a cloud server via an application. The video data is transmitted over the internet and stored in cloud storage (e.g., Amazon S3). The input is the video data captured by the user, and the output is the URL of the cloud storage where the data is saved.

[1058] Step 3:

[1059] The server retrieves product video data stored in cloud storage and performs analysis using an image recognition algorithm (e.g., Amazon Rekognition). The server analyzes the product video data, extracts features from the video data, and compares them with a database of past listing videos. The input is the URL of the video data, and the output is the analysis results (product features and condition information).

[1060] Step 4:

[1061] The server uses the results of an image recognition algorithm to determine the condition of a product by referencing a database of past listing images (e.g., MySQL). Simultaneously, it calculates a fair price by referencing past sales data for products in the same category. The input is the analyzed product characteristics, and the output is the product condition and fair price.

[1062] Step 5:

[1063] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate a product description based on the determined product condition and fair price. The generative AI model is supplied with predefined templates and prompts. The inputs are the product condition, fair price, and template, and the output is the automatically generated product description.

[1064] Step 6:

[1065] The server sends the generated product description, determined condition, and set appropriate price to the user's terminal. The user can review this information and edit it as needed. The input is the automatically generated product description and price information, and the output is the information provided to the user in a visual interface.

[1066] Step 7:

[1067] The user reviews the edited information on the application and then clicks the "List for Sale" button to finally list the product on the flea market or e-commerce site. The server receives this and completes the final product listing process. The input is the user's final confirmation information, and the output is the product list that will be published on the flea market or e-commerce site.

[1068] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1069] The following describes in detail embodiments of the present invention that combine an emotion engine.

[1070] This invention combines a system that automatically generates product condition, appropriate price, and description to assist users in listing items simply by having them shoot product video data and upload it to a flea market application, with an emotion engine that recognizes the user's emotions. This provides an even more personalized listing experience.

[1071] The system consists of a server, an emotion engine, and a user terminal. The program's processing is described below in natural language.

[1072] 1. Input and save of product video data

[1073] First, the user takes a video of the item they want to sell using their device. The video must include detailed information about the item. The user uploads this video data to the server via the flea market app. The server receives the video data and stores it.

[1074] 2. Analysis and comparison of video data

[1075] The server references a database of past listing videos and uses an image recognition algorithm to compare uploaded product video data with similar products. This comparison automatically determines the condition of the product.

[1076] 3. Setting appropriate prices and generating introductory texts.

[1077] Based on the determined product condition, the server sets an appropriate selling price by referring to data on similar products from the past. It also automatically generates a product description based on the product condition and appropriate price. This description includes a detailed explanation of the product and the appropriate price for the user.

[1078] 4. Recognition of user emotions by an emotion engine

[1079] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions in real time. For example, if a user expresses dissatisfaction or confusion regarding a product description or price, the emotion engine will detect this.

[1080] 5. Emotion-based presentation and adjustment

[1081] Based on user sentiment, the server adjusts product descriptions and suggestions. For example, if a user expresses dissatisfaction, it readjusts the price and description based on data from other similar products. It can also provide product recommendations and advice based on sentiment recognition results.

[1082] 6. Presentation to the user and editing

[1083] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. Users can review this information and edit the description and price as needed. Because adjustments based on the sentiment engine are also incorporated, users can create more satisfying listings.

[1084] Specific example

[1085] For example, user B wants to sell a used digital camera and takes a video of it. They upload this video to the server via a flea market app. The server saves the video data, compares it to past digital camera listings, and determines that the camera is in "good" condition. It also sets a fair price of 28,000 yen based on past data and generates a product description like the following:

[1086] "I'm selling a digital camera in good condition. It shows some signs of use, but there are no problems with its performance. The price is 28,000 yen."

[1087] The generated information is presented to User B, and the emotion engine detects that User B appears slightly dissatisfied. Therefore, the server suggests readjusting the price and revising the description. User B then reviews and edits the description and price before completing the listing.

[1088] The above describes an embodiment of the present invention that combines an emotion engine. This embodiment allows users to enjoy a personalized listing experience and make the listing process more effective and satisfying.

[1089] The following describes the processing flow.

[1090] Step 1:

[1091] Users film product footage and upload it to the system using their devices.

[1092] Users use devices such as smartphones or tablets to take detailed videos of the items they want to list for sale.

[1093] After filming is complete, the video files are uploaded to the server via a flea market app.

[1094] Step 2:

[1095] The server receives and saves the uploaded product video data.

[1096] The server receives the video file sent by the user.

[1097] The received video data is saved to a temporary storage directory, and the metadata of that file (e.g., upload date and time, user ID, etc.) is also recorded.

[1098] Step 3:

[1099] The server searches for similar products by referring to a database of past listing videos.

[1100] The server retrieves video data of previously listed products from the database.

[1101] Video data is filtered based on metadata such as product category, manufacturer, and model number to select appropriate comparison targets.

[1102] Step 4:

[1103] The server uses video comparison technology to analyze and compare product video data.

[1104] The server analyzes product video data frame by frame using image recognition algorithms (such as CNN or SIFT).

[1105] Based on the analyzed data, we compare it with video data of similar products to extract features related to the condition of the product.

[1106] Step 5:

[1107] The server determines the condition of the product based on the video comparison results.

[1108] The server determines the condition category to which the product belongs based on the extracted features.

[1109] The condition category can be selected from options such as "New / Unused," "Like New," "Good," and "Used."

[1110] Step 6:

[1111] The server sets an appropriate selling price based on data on the condition and selling price of similar products from the past.

[1112] The server uses past data of similar products as a reference to determine the price based on the determined condition category.

[1113] The optimal selling price is calculated by utilizing statistical data such as the average price, median price, and latest transaction price.

[1114] Step 7:

[1115] The server automatically generates a product description based on the product's condition and pricing.

[1116] The server generates product descriptions based on a template.

[1117] The generated description will include a detailed description of the product's condition and its selling price.

[1118] Step 8:

[1119] The emotion engine recognizes the user's emotions.

[1120] The emotion engine analyzes the user's facial expressions and voice in real time as they interact with the system.

[1121] The emotion engine recognizes the user's emotional state (e.g., satisfaction, dissatisfaction, confusion, etc.).

[1122] Step 9:

[1123] The server adjusts the product description and pricing based on the emotion recognition results.

[1124] Based on the results from the emotion engine, the server adjusts the product description and the set price.

[1125] For example, if a user expresses dissatisfaction, we might revise the pricing or make changes to supplement the explanation.

[1126] Step 10:

[1127] The server displays the generated description, the determined condition, and the set selling price to the user.

[1128] The server displays this information on the user's device.

[1129] Users can review the presented information and edit the description and price as needed.

[1130] Step 11:

[1131] The user reviews and edits the product information, and finally completes the listing process.

[1132] The user edits the provided product information, and if they are satisfied with the content, they press the "List Item" button to complete the listing process.

[1133] The final listing information is sent to the server and posted on the flea market app.

[1134] Through the above processing steps, the present invention provides users with a personalized listing experience, enabling more effective and satisfying listings.

[1135] (Example 2)

[1136] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1137] Traditional flea market applications had problems such as requiring users to spend a lot of time and effort determining the condition of their items, setting appropriate prices, and writing product descriptions when listing items. Furthermore, they lacked features that provided a personalized listing experience that took user emotions into consideration. As a result, it was difficult for users to list items in a way that they found satisfying.

[1138] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1139] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referencing past listing video data, means for comparing the product video data with data in the past listing video data to determine the product condition, means for setting an appropriate price for the product based on the product condition, means for generating a product description based on the product condition and the appropriate price, means for recognizing the user's emotions, means for adjusting the product description and appropriate price based on the user's emotions, and means for presenting the product condition, appropriate price, and product description to the user. As a result, users can easily determine the product condition, set an appropriate price, generate a personalized product description, and make adjustments that take into account the user's emotions, making it possible to list products that will satisfy users.

[1140] "Product video data" refers to video data of products that users wish to list for sale, captured with a camera, and includes information that shows the product's appearance and characteristics.

[1141] "Means of storage" refers to the function of storing and managing video data received by the server in a storage device such as a database.

[1142] "Past listing video data" refers to video data of items that users have previously listed through the flea market application, and is used as reference data to determine the condition and price of the items.

[1143] "Method of comparison" refers to a function that uses an image recognition algorithm to compare uploaded product video data with past listing video data to determine the condition of the product.

[1144] "Product condition" refers to an assessment of the product's usage history, presence or absence of damage, and describes the condition of the item being offered for sale.

[1145] "Fair price" refers to a reasonable selling price for a listed product, determined based on past listing data and sales performance of similar products.

[1146] A "product description" is a text that explains the features, condition, and selling price of the listed product, and includes information to make the product appealing to potential buyers.

[1147] "Means of recognizing user emotions" refers to a function that uses cameras and microphones to collect user facial expressions and voice data, analyzes it, and identifies the user's emotional state (e.g., satisfaction, dissatisfaction, confusion).

[1148] "Means of presentation" refers to the function by which the server displays the final generated product description, determined condition, and set appropriate price on the user's device, allowing the user to review and edit the information.

[1149] The following describes in detail an embodiment of the present invention that incorporates an emotion engine. The present invention combines an emotion engine that recognizes the user's emotions with a system that automatically generates product condition, appropriate price, and description to support listing a product simply by the user taking product video data and uploading it to a flea market application. This provides an even more personalized listing experience.

[1150] The system consists of a server, terminals, and an emotion engine. Specifically, it is implemented using the following hardware and software:

[1151] Hardware and software to be used

[1152] 1. Server:

[1153] Databases for data storage and processing (e.g., MySQL, PostgreSQL)

[1154] Image recognition algorithms (e.g., TensorFlow, OpenCV)

[1155] Statistical analysis and machine learning algorithms (e.g., Scikit-learn)

[1156] Emotion engine (e.g., Affectiva, Microsoft Azure Cognitive Services)

[1157] Generative AI models (e.g., GPT-4)

[1158] 2. Terminal:

[1159] Smartphones and tablets used by users

[1160] Camera and microphone functions

[1161] 3. Network:

[1162] Internet connection for connecting terminals and servers

[1163] Example of operation

[1164] The following provides specific examples of how to operate the system.

[1165] Product video data input

[1166] Users use their device's camera to capture video data of the items they want to list for sale. For example, when photographing a used digital camera, they should ensure that the camera body and its main components are clearly visible.

[1167] Uploading product video data

[1168] Users upload the recorded video data to the server via a flea market app on their device. This is done by selecting the "List Item" button in the app, specifying the video data, and sending it.

[1169] Analysis and comparison of video data

[1170] The server imports the stored product video data into an analysis program and determines the product's condition while referring to a database of past listing videos. This process utilizes image recognition algorithms such as TensorFlow and OpenCV.

[1171] Setting appropriate prices and generating introductory texts.

[1172] Based on the determined product condition, the server sets an appropriate selling price by referring to data on similar products from the past. This uses machine learning algorithms such as Scikit-learn. In addition, product descriptions are automatically generated using an AI model (e.g., GPT-4) that generates information on the appropriate price and product condition.

[1173] Recognition of user emotions by an emotion engine

[1174] While the user is reviewing product descriptions and prices displayed on their device, the device's camera and microphone record the user's facial expressions and voice. This data is sent to a server, where an emotion engine analyzes the user's emotional state.

[1175] Final presentation to the user

[1176] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. The user can review this information and edit the description and price as needed. Because the sentiment engine's adjustments are reflected, users can create more satisfying listings.

[1177] Examples of prompts to input into a generative AI model

[1178] "I have uploaded images of a used digital camera. Please assess the camera's condition and generate an appropriate selling price and description. Also, please consider user sentiment and adjust the description and price accordingly to present the final listing."

[1179] The above describes an embodiment of the present invention that combines an emotion engine. This embodiment allows users to enjoy a personalized listing experience and make the listing process more effective and satisfying.

[1180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1181] Step 1: Input and save product video data.

[1182] 1.1 Filming product video data

[1183] The user takes photos of the item they want to list using their device. These input videos must capture the item's main features and condition in detail. Specifically, the user launches their smartphone's camera app and takes photos of the item from several angles.

[1184] 1.2 Uploading video data

[1185] Users upload recorded video data to the server via a flea market app. Input is done by the user selecting video data from their device and tapping the "List Item" button in the app. Output is the video data being sent to the server.

[1186] 1.3 Data storage on the server

[1187] The server verifies the received video data and saves it to the database. In this step, a unique ID is assigned to the video data so that it can be referenced in subsequent processing. The input is the uploaded video data, and the output is the unique ID of the saved data.

[1188] Step 2: Analysis and comparison of video data

[1189] 2.1 Importing video data

[1190] The server takes the stored video data into the analysis program. The input is the stored video data, and the output is video data in a format suitable for analysis. Specifically, preprocessing is performed to extract image and text information.

[1191] 2.2 Searching for similar products

[1192] The server references a database of past listing videos and uses an image recognition algorithm to compare uploaded product video data with similar products. The input is the captured video data and past listing data, and the output is the matching result with similar products. Specifically, image analysis is performed using TensorFlow and OpenCV.

[1193] 2.3 Determining the condition of the product

[1194] The server automatically determines the condition of the product in the analyzed video data based on data of similar products. The input is the matching results for similar products, and the output is the product condition evaluation. The evaluation algorithm determines the product condition (e.g., "Good," "Like New") based on evaluation criteria.

[1195] Step 3: Setting an appropriate price and generating a promotional text.

[1196] 3.1 Setting a fair price

[1197] The server sets an appropriate selling price based on the determined product condition, referencing data from similar products in the past. The input is the product condition evaluation and data from similar products in the past, and the output is the appropriate price. Specifically, it uses statistical analysis algorithms such as Scikit-learn and machine learning algorithms.

[1198] 3.2 Generating Product Descriptions

[1199] The server automatically generates product descriptions using a generative AI model based on information about the appropriate price and product condition. The input is information about the appropriate price and product condition, and the output is the product description. Specifically, a generative AI model (e.g., GPT-4) is used to create text that attractively expresses the features and benefits of the product.

[1200] Step 4: Recognition of user emotions by the emotion engine

[1201] 4.1 Collecting User Feedback

[1202] While the user is reviewing the product description and price, the device's camera and microphone are used to record the user's facial expressions and voice. The input consists of the displayed product description and price, as well as the user's reaction data (facial expressions, voice), and the output is this reaction data.

[1203] 4.2 Analysis of User Sentiment

[1204] Data collected by the device is sent to the server in real time. The server uses an emotion engine to analyze the user's emotions. The input is the user's reaction data, and the output is an evaluation of the emotional state. Specifically, it uses emotion analysis engines such as Affectiva or Microsoft Azure Cognitive Services.

[1205] 4.3 Feedback on emotional data

[1206] The analysis results from the emotion engine are returned to the server, and data on the user's emotional state (e.g., satisfied, dissatisfied, confused) is fed back. The input is the evaluation result of the emotional state, and the output is the feedback data.

[1207] Step 5: Emotion-based presentation and adjustment

[1208] 5.1 Data Recalibration

[1209] The server readjusts product descriptions and prices based on the results of sentiment analysis. Input is feedback data and existing description and price information, while output is the readjusted description and price. If the user expresses dissatisfaction or confusion, the server attempts to regenerate the price and description using a different dataset or new parameters.

[1210] 5.2 Providing recommendations and advice

[1211] If necessary, the server provides recommendations for other similar products and advice to help users be satisfied. The input is re-tuned data and user sentiment analysis results, and the output is advice information and recommendation lists.

[1212] Step 6: Presentation to the user and editing

[1213] 6.1 Final presentation

[1214] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. The input is the re-adjusted data, and the output is the final information displayed on the user's device. The user can review this information and edit the description and price as needed.

[1215] 6.2 Editing Users

[1216] Users can review the presented information and edit the description and price as needed. The input is the final information presented, and the output is the edited information. Text and numbers can be changed using the editing function within the app.

[1217] 6.3 Completion of listing

[1218] After the user confirms the listing details they are finally satisfied with, they can press the "Complete Listing" button to officially list the product. The input is the final information edited by the user, and the output is the final listing data.

[1219] (Application Example 2)

[1220] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1221] Traditional e-commerce sites display product descriptions and reviews uniformly, making it difficult to address the individual emotions and needs of each consumer. In particular, the lack of real-time solutions to consumer frustrations and questions while browsing product pages poses a risk of diminishing their purchase intent. Therefore, a system is needed that dynamically adjusts product descriptions, prices, and recommendations based on consumer emotions, providing information optimized for each individual consumer.

[1222] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a past listing video database, means for comparing the product video data with video data in the past listing video database to determine the product condition, means for setting an appropriate price for the product based on the product condition, means for generating a product description based on the product condition and the appropriate price, means for analyzing input video and audio data to analyze the user's emotions, means for adjusting the product description and the appropriate price based on the user's emotions, and means for presenting the product condition, the appropriate price, and the product description to the user. This makes it possible to provide personalized information based on the consumer's emotions in real time.

[1223] "Product video data" refers to digital data of videos of products that a user wishes to list or purchase.

[1224] The "Past Listing Video Database" is a database that stores videos and related data of items previously listed on flea markets and online shopping sites.

[1225] "Product condition" refers to information about the product's condition, such as its age (new or old) and whether or not it has any damage.

[1226] A "fair price" is a fair and realistic selling price calculated based on the condition of the product and the supply and demand in the market.

[1227] A "product description" is a descriptive text that details the product's features, condition, price, and other relevant information.

[1228] "Emotion analysis means" refers to technical means for analyzing a user's video and audio data to recognize their emotions.

[1229] "Presentation method" refers to a means of displaying the generated product condition, appropriate price, and product description to the user.

[1230] "Editing methods" refer to means that enable users to modify and edit product descriptions and appropriate pricing.

[1231] An "image recognition algorithm" is an algorithm that analyzes input video data to identify and determine the content of an image.

[1232] This invention relates to a system that automatically generates product condition, appropriate price, and product description based on product video data, and adjusts them based on the user's emotions. This system inputs product video data, stores it, analyzes it, and performs a series of processes to present it to the user. Furthermore, it can analyze the user's emotions and personalize the content accordingly.

[1233] First, the user takes product video data using a device such as a smartphone or smart glasses and inputs it into the system. The input product video data is sent to a server and stored there.

[1234] Next, the server analyzes the stored product video data. Image recognition algorithms are used for this analysis. The server refers to a database of past listing videos and compares them with the current video data to determine the condition of the product. For example, it determines whether the product is used or new, and how much wear and tear it has.

[1235] Subsequently, the server sets an appropriate price based on the determined product condition. Past data on similar products is used as a reference when setting the appropriate price. Furthermore, a product description is automatically generated based on the determined product condition and appropriate price. This product description includes details such as the product's features, condition, and price.

[1236] Next, emotion analysis tools are used to analyze the user's emotions in real time. These tools analyze the user's facial expressions and voice to recognize their emotions. This analysis utilizes the camera and microphone of a smartphone or smart glasses.

[1237] Based on the sentiment analysis results, the server adjusts product descriptions and appropriate pricing. For example, if a user displays a dissatisfied expression, the detailed product description and price will be reconsidered. Recommended products and advice based on sentiment analysis are also provided.

[1238] Finally, the adjusted product condition, appropriate price, and product description are presented to the user. The user can review this and edit it as needed.

[1239] Specific example

[1240] For example, a user takes a picture of a used digital camera using their smartphone and uploads the image data to the system. Based on this data, the server determines the product's condition as "good" and sets a fair price of 28,000 yen. A generated product description is then presented to the user.

[1241] If a user expresses dissatisfaction with the offered price, sentiment analysis tools will recognize this, and the server will readjust the price and description. Ultimately, the user can list their product in a way that satisfies them.

[1242] Examples of prompts for generative AI models

[1243] Create specific code for an e-commerce application that recognizes user emotions in real time from facial expressions and voice, and provides personalized product information based on those emotions. Include a process for collecting user data using the camera and microphone of a smartphone or smart glasses, and optimizing product information after emotion analysis. The generated code should specifically indicate the use of emotion and recommendation engines.

[1244] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1245] Step 1:

[1246] Users use their smartphones or smart glasses to capture video data of the items they want to list for sale. This video data includes detailed information about the products.

[1247] Input: Product video data

[1248] Output: Video data stored on the device

[1249] Specific operation: The user takes a picture of the product using the camera function of their smartphone or smart glasses, and the image data is saved on the device.

[1250] Step 2:

[1251] The device uploads the captured product video data to the server via the flea market application.

[1252] Input: Video data stored on the device

[1253] Output: Video data sent to the server

[1254] Specific operation: The user presses the "Upload" button within the application, and the video data is sent to the server via the internet.

[1255] Step 3:

[1256] The server receives the uploaded product video data and saves it to the database.

[1257] Input: Video data sent to the server

[1258] Output: Video data stored in the database

[1259] Specific operation: The server receives an HTTP request and saves the video data to dedicated storage.

[1260] Step 4:

[1261] The server analyzes the stored product video data. This analysis uses an image recognition algorithm.

[1262] Input: Video data stored in the database

[1263] Output: Analyzed product condition data

[1264] Specific operation: The server executes an image recognition algorithm and analyzes the video data to determine the condition of the product. For example, information such as the age of the product and whether or not there are any scratches is extracted.

[1265] Step 5:

[1266] The server refers to a database of past listing videos and compares them with current video data to determine the product's condition in more detail.

[1267] Input: Analyzed product condition data, past listing video database

[1268] Output: Detailed product condition data

[1269] Specific operation: The server searches for similar images in its past database, compares them with the current data, and determines the product condition more accurately.

[1270] Step 6:

[1271] The server sets an appropriate price based on the determined product condition. This setting is based on data from similar products in the past.

[1272] Input: Detailed product condition data, historical data on similar products.

[1273] Output: Fair price data

[1274] Specific operation: The server uses an algorithm to combine product condition and market data to calculate a fair price.

[1275] Step 7:

[1276] The server automatically generates a product description based on the determined product condition and appropriate price.

[1277] Input: Detailed product condition data, appropriate price data

[1278] Output: Product description data

[1279] Specific operation: The server uses a text generation algorithm to generate a product description. This description includes the product's features, condition, price, etc.

[1280] Step 8:

[1281] The server analyzes video and audio data received from the terminal in real time to analyze the user's emotions.

[1282] Input: Video and audio data received from the device.

[1283] Output: User's emotional data

[1284] Specific operation: Using data collected from the device's camera and microphone, the server runs an emotion analysis engine to recognize the user's emotions.

[1285] Step 9:

[1286] The server adjusts product descriptions and appropriate pricing based on user sentiment data.

[1287] Input: User sentiment data, product description data, appropriate price data

[1288] Output: Adjusted product description data, adjusted fair price data

[1289] Specific operation: The server uses user sentiment data to review the generated product description and appropriate price, and makes corrections as needed.

[1290] Step 10:

[1291] The server then presents the user with the final adjusted product condition, appropriate price, and product description, which the user can review and edit as needed.

[1292] Input: Adjusted product description data, adjusted fair price data

[1293] Output: Final data presented to the user

[1294] Specific operation: The server sends the adjusted information to the user's terminal, the user reviews the displayed data, edits it as needed, and then performs a final confirmation.

[1295] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1296] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1297] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1298] [Fourth Embodiment]

[1299] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1300] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1301] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1302] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1303] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1304] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1305] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1306] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1307] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1308] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1309] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1310] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1311] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1312] Embodiments of the present invention will be described in detail below.

[1313] This invention provides a system that supports listing products by automatically generating product condition, appropriate price, and description simply by having the user film product images and upload them to a flea market application. This significantly reduces the effort required from the user and enables efficient listing.

[1314] The system consists of a server and user terminals. First, the user takes a video of the item they want to sell using their terminal. This video must include detailed information about the item. Next, the user uploads the video to the server through the flea market app.

[1315] The server receives and stores the uploaded product video data. The stored product video data is then compared with the video database on the server. This video database contains video data of previously listed products, their condition, and their selling prices.

[1316] The server uses an image recognition algorithm to compare uploaded product video data with past listing video data in the database. Based on this comparison, the server automatically determines the product's condition. The condition is categorized into several categories, such as "new / unused," "almost new," "good," and "used."

[1317] Next, the server sets an appropriate selling price based on the determined condition of the product, referencing data from similar products in the past. This appropriate price is calculated based on the prices at which similar products in the same category were traded in the past.

[1318] Furthermore, the server automatically generates a product description based on the product's condition and appropriate price. This description is generated from the original template and includes detailed information about the product, such as its condition and selling price.

[1319] Finally, the server displays the generated product description, the determined condition, and the set appropriate price to the user's device. The user can review this information and edit it as needed. Once editing is complete, the user can finally list the product for sale.

[1320] Specific example:

[1321] User A wants to sell a used smartphone and takes detailed video footage of the smartphone. Next, User A uploads this video to a server through a flea market application. The server receives and saves the video and compares it with video data of similar smartphones from the past.

[1322] Based on the video comparison, the server determines that User A's smartphone is in "almost new" condition. It also sets the appropriate price at 35,000 yen based on past data. Next, the server automatically generates a product description like the following:

[1323] "I'm selling a smartphone that's barely been used. It's in excellent condition, practically brand new. The price is 35,000 yen."

[1324] This information is displayed to User A's device, and User A reviews the content and edits the description and price as needed. After editing is complete, User A can proceed with the listing process and list their smartphone for sale on the flea market.

[1325] The above describes the embodiment of the present invention. This embodiment enables users to list products efficiently without any hassle.

[1326] The following describes the processing flow.

[1327] Step 1:

[1328] Users film product footage and upload it to the system using their devices.

[1329] Users use devices such as smartphones or tablets to take detailed videos of the items they want to list for sale.

[1330] After filming is complete, the video files are uploaded to the server via a flea market app.

[1331] Step 2:

[1332] The server receives and saves the uploaded product video data.

[1333] The server receives the video file sent by the user.

[1334] The received video data is saved to a temporary storage directory, and the metadata of that file (e.g., upload date and time, user ID, etc.) is also recorded.

[1335] Step 3:

[1336] The server searches for similar products by referring to a database of past listing videos.

[1337] The server retrieves video data of previously listed products from the database.

[1338] Video data is filtered based on metadata such as product category, manufacturer, and model number to select appropriate comparison targets.

[1339] Step 4:

[1340] The server uses video comparison technology to analyze and compare product video data.

[1341] The server analyzes product video data frame by frame using image recognition algorithms (such as CNN or SIFT).

[1342] Based on the analyzed data, we compare it with video data of similar products to extract features related to the condition of the product.

[1343] Step 5:

[1344] The server determines the condition of the product based on the video comparison results.

[1345] The server determines the condition category to which the product belongs based on the extracted features.

[1346] The condition category can be selected from options such as "New / Unused," "Like New," "Good," and "Used."

[1347] Step 6:

[1348] The server sets an appropriate selling price based on data on the condition and selling price of similar products from the past.

[1349] The server uses past data of similar products as a reference to determine the price based on the determined condition category.

[1350] The optimal selling price is calculated by utilizing statistical data such as the average price, median price, and latest transaction price.

[1351] Step 7:

[1352] The server automatically generates a product description based on the product's condition and pricing.

[1353] The server generates product descriptions based on a template.

[1354] The generated description will include a detailed description of the product's condition and its selling price.

[1355] Step 8:

[1356] The server displays the generated description, the determined condition, and the set selling price to the user.

[1357] The server displays the generated description and pricing information on the user's device.

[1358] Users can review the presented content and make corrections as needed.

[1359] Step 9:

[1360] The user reviews and edits the product information, and finally completes the listing process.

[1361] The user edits the provided product information, and if they are satisfied with the content, they press the "List Item" button to complete the listing process.

[1362] The final listing information is sent to the server and posted on the flea market app.

[1363] Through the above processing steps, users can easily list products and save a lot of time and effort.

[1364] (Example 1)

[1365] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1366] Current flea market applications present a problem: users must create detailed descriptions for each item they list and set appropriate prices, a process that is extremely time-consuming and laborious. Furthermore, accurately assessing the condition of an item requires specialized knowledge, making it difficult for the average user. As a result, users have to expend a great deal of effort when listing items, making efficient listing difficult.

[1367] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1368] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a database of past listing videos, means for comparing the product video data with video data in the database of past listing videos to determine the condition of the product, means for setting an appropriate price for the product based on the condition of the product, means for using a generation AI to generate a product description, means for generating a product description based on the condition of the product and the appropriate price, and means for presenting the condition of the product, the appropriate price, and the product description to the user. As a result, users can simply upload product videos, and the system will automatically determine the condition of the product, set an appropriate price, and generate a product description, enabling efficient listing.

[1369] "Product video data" refers to video information about products listed by users, and is data that visually records the detailed condition and characteristics of the product.

[1370] "Means of storage" refers to a system for storing and managing received product video data in a database or storage device.

[1371] "Means of reference" refers to a system that allows users to view past listing video data and use it for comparison and analysis.

[1372] "Means for comparing and determining the condition of a product" refers to algorithms or software that compare product video data with video data from a database of past listing videos and automatically classify and evaluate the condition of the product.

[1373] "Methods for setting appropriate prices" refer to systems for calculating the optimal selling price of a product based on its condition and past transaction data.

[1374] "Methods of using generative AI" refer to systems that use artificial intelligence technology to automatically create and generate text and data.

[1375] "Methods for generating product descriptions" refers to a function that automatically generates user-oriented descriptions based on elements such as product details, condition, and price.

[1376] "Means of presentation to the user" refers to an interface that provides the user with the generated product description, the determined product condition, and the set appropriate price, allowing the user to review and edit them.

[1377] This invention supports listing products by allowing users to simply film product images and upload them to a flea market application. The system automatically generates product condition, appropriate price, and description, significantly reducing user effort and enabling efficient listing. The details are described below.

[1378] The system consists of a server and user terminals. First, the user takes a video of the item they want to sell using their terminal. This video must include detailed information about the item. Next, the user uploads the video to the server through a flea market application.

[1379] The server receives uploaded product video data and has a database for storing it. The stored product video data is compared with the video database on the server, which includes video data of previously listed products, their condition, and sales price.

[1380] Image data analysis uses image recognition algorithms such as TensorFlow and PyTorch. The server uses these algorithms to compare uploaded product video data with past listing video data and automatically determine the product's condition. The condition is classified into several categories, such as "new / unused," "almost new," "good," and "used."

[1381] Next, the server uses a generative AI model (e.g., GPT-3) to generate a product description. The description is generated from a template based on the product's condition and appropriate price. For example, a description such as, "I am selling a smartphone that has hardly been used. It is in excellent condition, almost like new. The price is 35,000 yen," might be created.

[1382] Finally, the server displays the generated product description, the determined condition, and the set appropriate price to the user's device. The user can review this information and edit the description and price as needed. Once editing is complete, the user can finally list the product for sale.

[1383] Specific example

[1384] User A wants to sell a used smartphone and takes detailed video footage of the smartphone. Next, User A uploads this video to a server through a flea market application. The server receives and saves the video and compares it with video data of similar smartphones from the past.

[1385] Based on the video comparison, the server determines that User A's smartphone is in "almost new" condition. It also sets the appropriate price at 35,000 yen based on past data. Next, the server automatically generates a product description like the following:

[1386] "I'm selling a smartphone that's barely been used. It's in excellent condition, practically brand new. The price is 35,000 yen."

[1387] This information is displayed to User A's device, and User A reviews the content and edits the description and price as needed. After editing is complete, User A can proceed with the listing process and list their smartphone for sale on the flea market.

[1388] Example of a prompt

[1389] "Please record video data of your used smartphone and upload it to the server via the flea market application. The server will receive and analyze the video data, automatically determine the product's condition and appropriate price, and generate a description. Once you have reviewed and edited this information, please list your product for sale."

[1390] The above describes the embodiments for carrying out the present invention. This embodiment allows users to list products efficiently without any hassle.

[1391] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1392] Step 1:

[1393] Input: Video data of the product the user wants to list for sale.

[1394] Process: Users use their own devices to film detailed videos of the products they wish to sell. The videos must include the overall image and specific distinctive features. For example, in the case of a smartphone, videos should be taken from various angles, including the front, back, sides, and screen.

[1395] Output: Recorded video data

[1396] Step 2:

[1397] Input: Recorded video data

[1398] Processing: The user's device uploads the captured video data to the server via the flea market application. During this process, the application compresses and formats the video data, converting it into a format optimized for transfer. For example, it compresses the video data into JPEG or PNG format before sending it.

[1399] Output: Compressed video data transferred to the server

[1400] Step 3:

[1401] Input: Compressed video data transferred to the server

[1402] Processing: The server saves the received video data to a database. Each product is assigned a unique identifier in this database, and the data is managed based on that identifier. The saved video data is used for subsequent analysis.

[1403] Output: Video data stored in the database

[1404] Step 4:

[1405] Input: Video data stored in the database

[1406] Processing: The server analyzes the video data using an image recognition algorithm (e.g., TensorFlow or PyTorch). The algorithm automatically identifies the condition and characteristics of the product. Specifically, it detects scratches, color variations, button wear, etc.

[1407] Output: Product feature information based on video data

[1408] Step 5:

[1409] Input: Product feature information based on video data

[1410] Processing: The server determines the condition of the product based on its characteristic information, comparing it with past listing data. For example, it classifies items into categories such as "new / unused," "almost new," "good," and "used." This comparison uses a database of previously accumulated listing data.

[1411] Output: Condition of the determined product

[1412] Step 6:

[1413] Input: Condition of the item being assessed

[1414] Processing: The server sets an appropriate selling price based on the product's condition and by referring to past transaction data. For example, it calculates the price based on the prices at which similar products in the same category and condition have been sold in the past.

[1415] Output: Set appropriate selling price

[1416] Step 7:

[1417] Input: Condition of the assessed product and fair selling price

[1418] Processing: The server uses a generative AI model (e.g., GPT-3) to generate product descriptions. It inserts the product's condition and price into a description template to create a specific description. For example: "I am selling a smartphone in almost unused condition. It is in excellent condition, practically brand new. The price is 35,000 yen."

[1419] Output: Generated product description

[1420] Step 8:

[1421] Input: Generated product description, determined product condition, and appropriate selling price.

[1422] Processing: The server sends this information to the user's terminal. A dedicated interface is designed to make it easy for the user to review the content on their terminal. The user can also edit this information.

[1423] Output: Product description, product condition, and fair selling price displayed on the user's device.

[1424] Step 9:

[1425] Input: User-verified and edited introductory text and price

[1426] Processing: Users review the presented information and edit the product description and appropriate selling price as needed. For example, they can add additional information to the description, such as "Original box and accessories are included," or make minor adjustments to the price.

[1427] Output: Edited product description and selling price

[1428] Step 10:

[1429] Input: Edited product description and selling price

[1430] Processing: The user completes the final listing procedure. They press the "List Item" button in the application to list the item on the flea market. This action automatically completes the listing process on the system side, and the item is listed on the flea market.

[1431] Output: Items listed on the flea market

[1432] (Application Example 1)

[1433] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1434] Current flea market and online shopping sites require users to go through many steps when listing items. Specifically, it involves taking photos of the product, assessing its condition, setting an appropriate price, and writing a product description. This can cause users to hesitate to list items, and sales may suffer due to inappropriate pricing or poor product descriptions. Therefore, there is a need to streamline the listing process and reduce the burden on users.

[1435] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1436] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a database of past listing videos, means for comparing product video data with video data in the database of past listing videos to determine the condition of the product, means for setting an appropriate price for the product based on the condition of the product, means for generating a product description based on the condition of the product and the appropriate price, means for presenting the condition of the product, the appropriate price, and the product description to the user, means for sending the condition of the product and the appropriate price to a cloud server and analyzing it using an image recognition algorithm, and means for generating a product description using a generation AI model. This makes it possible for users to list products quickly and efficiently without any hassle.

[1437] "Product video data" refers to video and image data of products that users plan to list for sale.

[1438] "Means of storage" refers to the part that has the function of storing the input product video data in a storage device.

[1439] The "Listing Video Database" is a database that stores video data and information about products that have been listed for sale in the past.

[1440] The "means of comparison and judgment" refers to the function that automatically evaluates the condition of a product by comparing product video data with data from a database of past listing videos.

[1441] "Means of setting" refers to the part that has the function of determining an appropriate selling price for a product based on the determined product condition.

[1442] "Generating means" refers to the part that has the function of automatically creating a product description based on the product condition and appropriate price.

[1443] "Means of presentation" refers to the part that has the function of displaying information such as the generated product description, the determined condition, and the set appropriate price to the user.

[1444] "Means of transmission" refers to the part that has the function of transferring data such as product condition and appropriate price to a cloud server.

[1445] An "image recognition algorithm" refers to a computational method or program used to analyze video data and identify the condition of a product.

[1446] A "generative AI model" is an artificial intelligence model that automatically creates product descriptions using natural language generation technology.

[1447] The embodiments for carrying out the present invention are described in detail below. The present invention significantly reduces the burden on the user by allowing the user to take product video data and upload it to an application for a flea market or e-commerce site, and the system automatically generates the product's condition, appropriate price, and description.

[1448] First, the user takes a picture of the item they want to list using their smartphone's camera function. The captured video data is uploaded to a cloud server via the application. The cloud server receives the video data and stores it in a database. This database contains video data of previously listed items, along with their corresponding condition and selling price.

[1449] The server uses an image recognition algorithm (e.g., Amazon Rekognition) to analyze uploaded product video data and compare it to video data in a database of past listing videos. This automatically determines the product's condition. Condition categories are classified into multiple levels, such as "new / unused," "like new," "good," and "used."

[1450] Next, the server refers to data on similar past products to determine a fair price based on the condition of the determined product. The fair price is automatically calculated based on the prices at which similar products in the same category have been traded.

[1451] Furthermore, the server automatically generates product descriptions using a generative AI model (e.g., OpenAI GPT-4). The product descriptions are generated based on a template that includes detailed product information, the determined condition, and the set appropriate price. This product description, containing this information, is sent to the user's device, where the user can review it.

[1452] Users can review the generated product description and appropriate price, and edit them as needed. They can then proceed to the final listing process within the application, allowing them to list their products on flea markets and e-commerce sites.

[1453] Hardware and software to be used

[1454] 1. Hardware:

[1455] Smartphone (for taking photos and using applications)

[1456] Cloud server (data storage and analysis)

[1457] 2. Software:

[1458] Smartphone application (for shooting and uploading product video data)

[1459] Amazon Rekognition (image analysis)

[1460] MySQL (database of past listing videos)

[1461] OpenAI GPT-4 (product description generation)

[1462] Specific example

[1463] User B decides to sell a guitar they no longer need and takes a picture of it with their smartphone camera. They then upload the video to a cloud server via an application. The server receives the video data and uses Amazon Rekognition to perform video analysis. It detects scratches and signs of wear on the guitar and compares them with a past database, resulting in a determination that the guitar "shows signs of wear." Based on past price data, a fair price of 20,000 yen is calculated.

[1464] Using OpenAI GPT-4, the following product description is generated and sent to user B's terminal:

[1465] "It shows some signs of use, but it's still a perfectly playable guitar. The price is 20,000 yen."

[1466] User B reviews this information, edits it as needed, and finally proceeds with the listing process.

[1467] Example of a prompt

[1468] Please generate an appropriate product description based on the product information provided.

[1469] Product name: Electric guitar

[1470] Condition: Shows signs of use.

[1471] Fair price: 20,000 yen

[1472] Example output:

[1473] "It shows some signs of use, but it's still a perfectly playable guitar. The price is 20,000 yen."

[1474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1475] Step 1:

[1476] Users use their smartphone cameras to capture video data of the products they wish to list for sale. The video data must clearly show the product's appearance and details. The input is the video data of the product captured by the user. The output is the video data uploaded to the application.

[1477] Step 2:

[1478] The device uploads the captured product video data to a cloud server via an application. The video data is transmitted over the internet and stored in cloud storage (e.g., Amazon S3). The input is the video data captured by the user, and the output is the URL of the cloud storage where the data is saved.

[1479] Step 3:

[1480] The server retrieves product video data stored in cloud storage and performs analysis using an image recognition algorithm (e.g., Amazon Rekognition). The server analyzes the product video data, extracts features from the video data, and compares them with a database of past listing videos. The input is the URL of the video data, and the output is the analysis results (product features and condition information).

[1481] Step 4:

[1482] The server uses the results of an image recognition algorithm to determine the condition of a product by referencing a database of past listing images (e.g., MySQL). Simultaneously, it calculates a fair price by referencing past sales data for products in the same category. The input is the analyzed product characteristics, and the output is the product condition and fair price.

[1483] Step 5:

[1484] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate a product description based on the determined product condition and fair price. The generative AI model is supplied with predefined templates and prompts. The inputs are the product condition, fair price, and template, and the output is the automatically generated product description.

[1485] Step 6:

[1486] The server sends the generated product description, determined condition, and set appropriate price to the user's terminal. The user can review this information and edit it as needed. The input is the automatically generated product description and price information, and the output is the information provided to the user in a visual interface.

[1487] Step 7:

[1488] The user reviews the edited information on the application and then clicks the "List for Sale" button to finally list the product on the flea market or e-commerce site. The server receives this and completes the final product listing process. The input is the user's final confirmation information, and the output is the product list that will be published on the flea market or e-commerce site.

[1489] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1490] The following describes in detail embodiments of the present invention that combine an emotion engine.

[1491] This invention combines a system that automatically generates product condition, appropriate price, and description to assist users in listing items simply by having them shoot product video data and upload it to a flea market application, with an emotion engine that recognizes the user's emotions. This provides an even more personalized listing experience.

[1492] The system consists of a server, an emotion engine, and a user terminal. The program's processing is described below in natural language.

[1493] 1. Input and save of product video data

[1494] First, the user takes a video of the item they want to sell using their device. The video must include detailed information about the item. The user uploads this video data to the server via the flea market app. The server receives the video data and stores it.

[1495] 2. Analysis and comparison of video data

[1496] The server references a database of past listing videos and uses an image recognition algorithm to compare uploaded product video data with similar products. This comparison automatically determines the condition of the product.

[1497] 3. Setting appropriate prices and generating introductory texts.

[1498] Based on the determined product condition, the server sets an appropriate selling price by referring to data on similar products from the past. It also automatically generates a product description based on the product condition and appropriate price. This description includes a detailed explanation of the product and the appropriate price for the user.

[1499] 4. Recognition of user emotions by an emotion engine

[1500] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions in real time. For example, if a user expresses dissatisfaction or confusion regarding a product description or price, the emotion engine will detect this.

[1501] 5. Emotion-based presentation and adjustment

[1502] Based on user sentiment, the server adjusts product descriptions and suggestions. For example, if a user expresses dissatisfaction, it readjusts the price and description based on data from other similar products. It can also provide product recommendations and advice based on sentiment recognition results.

[1503] 6. Presentation to the user and editing

[1504] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. Users can review this information and edit the description and price as needed. Because adjustments based on the sentiment engine are also incorporated, users can create more satisfying listings.

[1505] Specific example

[1506] For example, user B wants to sell a used digital camera and takes a video of it. They upload this video to the server via a flea market app. The server saves the video data, compares it to past digital camera listings, and determines that the camera is in "good" condition. It also sets a fair price of 28,000 yen based on past data and generates a product description like the following:

[1507] "I'm selling a digital camera in good condition. It shows some signs of use, but there are no problems with its performance. The price is 28,000 yen."

[1508] The generated information is presented to User B, and the emotion engine detects that User B appears slightly dissatisfied. Therefore, the server suggests readjusting the price and revising the description. User B then reviews and edits the description and price before completing the listing.

[1509] The above describes an embodiment of the present invention that combines an emotion engine. This embodiment allows users to enjoy a personalized listing experience and make the listing process more effective and satisfying.

[1510] The following describes the processing flow.

[1511] Step 1:

[1512] Users film product footage and upload it to the system using their devices.

[1513] Users use devices such as smartphones or tablets to take detailed videos of the items they want to list for sale.

[1514] After filming is complete, the video files are uploaded to the server via a flea market app.

[1515] Step 2:

[1516] The server receives and saves the uploaded product video data.

[1517] The server receives the video file sent by the user.

[1518] The received video data is saved to a temporary storage directory, and the metadata of that file (e.g., upload date and time, user ID, etc.) is also recorded.

[1519] Step 3:

[1520] The server searches for similar products by referring to a database of past listing videos.

[1521] The server retrieves video data of previously listed products from the database.

[1522] Video data is filtered based on metadata such as product category, manufacturer, and model number to select appropriate comparison targets.

[1523] Step 4:

[1524] The server uses video comparison technology to analyze and compare product video data.

[1525] The server analyzes product video data frame by frame using image recognition algorithms (such as CNN or SIFT).

[1526] Based on the analyzed data, we compare it with video data of similar products to extract features related to the condition of the product.

[1527] Step 5:

[1528] The server determines the condition of the product based on the video comparison results.

[1529] The server determines the condition category to which the product belongs based on the extracted features.

[1530] The condition category can be selected from options such as "New / Unused," "Like New," "Good," and "Used."

[1531] Step 6:

[1532] The server sets an appropriate selling price based on data on the condition and selling price of similar products from the past.

[1533] The server uses past data of similar products as a reference to determine the price based on the determined condition category.

[1534] The optimal selling price is calculated by utilizing statistical data such as the average price, median price, and latest transaction price.

[1535] Step 7:

[1536] The server automatically generates a product description based on the product's condition and pricing.

[1537] The server generates product descriptions based on a template.

[1538] The generated description will include a detailed description of the product's condition and its selling price.

[1539] Step 8:

[1540] The emotion engine recognizes the user's emotions.

[1541] The emotion engine analyzes the user's facial expressions and voice in real time as they interact with the system.

[1542] The emotion engine recognizes the user's emotional state (e.g., satisfaction, dissatisfaction, confusion, etc.).

[1543] Step 9:

[1544] The server adjusts the product description and pricing based on the emotion recognition results.

[1545] Based on the results from the emotion engine, the server adjusts the product description and the set price.

[1546] For example, if a user expresses dissatisfaction, we might revise the pricing or make changes to supplement the explanation.

[1547] Step 10:

[1548] The server displays the generated description, the determined condition, and the set selling price to the user.

[1549] The server displays this information on the user's device.

[1550] Users can review the presented information and edit the description and price as needed.

[1551] Step 11:

[1552] The user reviews and edits the product information, and finally completes the listing process.

[1553] The user edits the provided product information, and if they are satisfied with the content, they press the "List Item" button to complete the listing process.

[1554] The final listing information is sent to the server and posted on the flea market app.

[1555] Through the above processing steps, the present invention provides users with a personalized listing experience, enabling more effective and satisfying listings.

[1556] (Example 2)

[1557] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1558] Traditional flea market applications had problems such as requiring users to spend a lot of time and effort determining the condition of their items, setting appropriate prices, and writing product descriptions when listing items. Furthermore, they lacked features that provided a personalized listing experience that took user emotions into consideration. As a result, it was difficult for users to list items in a way that they found satisfying.

[1559] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1560] In this invention, the server includes means for inputting product video data, means for storing product video data, means for referencing past listing video data, means for comparing the product video data with data in the past listing video data to determine the product condition, means for setting an appropriate price for the product based on the product condition, means for generating a product description based on the product condition and the appropriate price, means for recognizing the user's emotions, means for adjusting the product description and appropriate price based on the user's emotions, and means for presenting the product condition, appropriate price, and product description to the user. As a result, users can easily determine the product condition, set an appropriate price, generate a personalized product description, and make adjustments that take into account the user's emotions, making it possible to list products that will satisfy users.

[1561] "Product video data" refers to video data of products that users wish to list for sale, captured with a camera, and includes information that shows the product's appearance and characteristics.

[1562] "Means of storage" refers to the function of storing and managing video data received by the server in a storage device such as a database.

[1563] "Past listing video data" refers to video data of items that users have previously listed through the flea market application, and is used as reference data to determine the condition and price of the items.

[1564] "Method of comparison" refers to a function that uses an image recognition algorithm to compare uploaded product video data with past listing video data to determine the condition of the product.

[1565] "Product condition" refers to an assessment of the product's usage history, presence or absence of damage, and describes the condition of the item being offered for sale.

[1566] "Fair price" refers to a reasonable selling price for a listed product, determined based on past listing data and sales performance of similar products.

[1567] A "product description" is a text that explains the features, condition, and selling price of the listed product, and includes information to make the product appealing to potential buyers.

[1568] "Means of recognizing user emotions" refers to a function that uses cameras and microphones to collect user facial expressions and voice data, analyzes it, and identifies the user's emotional state (e.g., satisfaction, dissatisfaction, confusion).

[1569] "Means of presentation" refers to the function by which the server displays the final generated product description, determined condition, and set appropriate price on the user's device, allowing the user to review and edit the information.

[1570] The following describes in detail an embodiment of the present invention that incorporates an emotion engine. The present invention combines an emotion engine that recognizes the user's emotions with a system that automatically generates product condition, appropriate price, and description to support listing a product simply by the user taking product video data and uploading it to a flea market application. This provides an even more personalized listing experience.

[1571] The system consists of a server, terminals, and an emotion engine. Specifically, it is implemented using the following hardware and software:

[1572] Hardware and software to be used

[1573] 1. Server:

[1574] Databases for data storage and processing (e.g., MySQL, PostgreSQL)

[1575] Image recognition algorithms (e.g., TensorFlow, OpenCV)

[1576] Statistical analysis and machine learning algorithms (e.g., Scikit-learn)

[1577] Emotion engine (e.g., Affectiva, Microsoft Azure Cognitive Services)

[1578] Generative AI models (e.g., GPT-4)

[1579] 2. Terminal:

[1580] Smartphones and tablets used by users

[1581] Camera and microphone functions

[1582] 3. Network:

[1583] Internet connection for connecting terminals and servers

[1584] Example of operation

[1585] The following provides specific examples of how to operate the system.

[1586] Product video data input

[1587] Users use their device's camera to capture video data of the items they want to list for sale. For example, when photographing a used digital camera, they should ensure that the camera body and its main components are clearly visible.

[1588] Uploading product video data

[1589] Users upload the recorded video data to the server via a flea market app on their device. This is done by selecting the "List Item" button in the app, specifying the video data, and sending it.

[1590] Analysis and comparison of video data

[1591] The server imports the stored product video data into an analysis program and determines the product's condition while referring to a database of past listing videos. This process utilizes image recognition algorithms such as TensorFlow and OpenCV.

[1592] Setting appropriate prices and generating introductory texts.

[1593] Based on the determined product condition, the server sets an appropriate selling price by referring to data on similar products from the past. This uses machine learning algorithms such as Scikit-learn. In addition, product descriptions are automatically generated using an AI model (e.g., GPT-4) that generates information on the appropriate price and product condition.

[1594] Recognition of user emotions by an emotion engine

[1595] While the user is reviewing product descriptions and prices displayed on their device, the device's camera and microphone record the user's facial expressions and voice. This data is sent to a server, where an emotion engine analyzes the user's emotional state.

[1596] Final presentation to the user

[1597] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. The user can review this information and edit the description and price as needed. Because the sentiment engine's adjustments are reflected, users can create more satisfying listings.

[1598] Examples of prompts to input into a generative AI model

[1599] "I have uploaded images of a used digital camera. Please assess the camera's condition and generate an appropriate selling price and description. Also, please consider user sentiment and adjust the description and price accordingly to present the final listing."

[1600] The above describes an embodiment of the present invention that combines an emotion engine. This embodiment allows users to enjoy a personalized listing experience and make the listing process more effective and satisfying.

[1601] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1602] Step 1: Input and save product video data.

[1603] 1.1 Filming product video data

[1604] The user takes photos of the item they want to list using their device. These input videos must capture the item's main features and condition in detail. Specifically, the user launches their smartphone's camera app and takes photos of the item from several angles.

[1605] 1.2 Uploading video data

[1606] Users upload recorded video data to the server via a flea market app. Input is done by the user selecting video data from their device and tapping the "List Item" button in the app. Output is the video data being sent to the server.

[1607] 1.3 Data storage on the server

[1608] The server verifies the received video data and saves it to the database. In this step, a unique ID is assigned to the video data so that it can be referenced in subsequent processing. The input is the uploaded video data, and the output is the unique ID of the saved data.

[1609] Step 2: Analysis and comparison of video data

[1610] 2.1 Importing video data

[1611] The server takes the stored video data into the analysis program. The input is the stored video data, and the output is video data in a format suitable for analysis. Specifically, preprocessing is performed to extract image and text information.

[1612] 2.2 Searching for similar products

[1613] The server references a database of past listing videos and uses an image recognition algorithm to compare uploaded product video data with similar products. The input is the captured video data and past listing data, and the output is the matching result with similar products. Specifically, image analysis is performed using TensorFlow and OpenCV.

[1614] 2.3 Determining the condition of the product

[1615] The server automatically determines the condition of the product in the analyzed video data based on data of similar products. The input is the matching results for similar products, and the output is the product condition evaluation. The evaluation algorithm determines the product condition (e.g., "Good," "Like New") based on evaluation criteria.

[1616] Step 3: Setting an appropriate price and generating a promotional text.

[1617] 3.1 Setting a fair price

[1618] The server sets an appropriate selling price based on the determined product condition, referencing data from similar products in the past. The input is the product condition evaluation and data from similar products in the past, and the output is the appropriate price. Specifically, it uses statistical analysis algorithms such as Scikit-learn and machine learning algorithms.

[1619] 3.2 Generating Product Descriptions

[1620] The server automatically generates product descriptions using a generative AI model based on information about the appropriate price and product condition. The input is information about the appropriate price and product condition, and the output is the product description. Specifically, a generative AI model (e.g., GPT-4) is used to create text that attractively expresses the features and benefits of the product.

[1621] Step 4: Recognition of user emotions by the emotion engine

[1622] 4.1 Collecting User Feedback

[1623] While the user is reviewing the product description and price, the device's camera and microphone are used to record the user's facial expressions and voice. The input consists of the displayed product description and price, as well as the user's reaction data (facial expressions, voice), and the output is this reaction data.

[1624] 4.2 Analysis of User Sentiment

[1625] Data collected by the device is sent to the server in real time. The server uses an emotion engine to analyze the user's emotions. The input is the user's reaction data, and the output is an evaluation of the emotional state. Specifically, it uses emotion analysis engines such as Affectiva or Microsoft Azure Cognitive Services.

[1626] 4.3 Feedback on emotional data

[1627] The analysis results from the emotion engine are returned to the server, and data on the user's emotional state (e.g., satisfied, dissatisfied, confused) is fed back. The input is the evaluation result of the emotional state, and the output is the feedback data.

[1628] Step 5: Emotion-based presentation and adjustment

[1629] 5.1 Data Recalibration

[1630] The server readjusts product descriptions and prices based on the results of sentiment analysis. Input is feedback data and existing description and price information, while output is the readjusted description and price. If the user expresses dissatisfaction or confusion, the server attempts to regenerate the price and description using a different dataset or new parameters.

[1631] 5.2 Providing recommendations and advice

[1632] If necessary, the server provides recommendations for other similar products and advice to help users be satisfied. The input is re-tuned data and user sentiment analysis results, and the output is advice information and recommendation lists.

[1633] Step 6: Presentation to the user and editing

[1634] 6.1 Final presentation

[1635] The server then presents the user with the final generated product description, the determined condition, and the set appropriate price. The input is the re-adjusted data, and the output is the final information displayed on the user's device. The user can review this information and edit the description and price as needed.

[1636] 6.2 Editing Users

[1637] Users can review the presented information and edit the description and price as needed. The input is the final information presented, and the output is the edited information. Text and numbers can be changed using the editing function within the app.

[1638] 6.3 Completion of listing

[1639] After the user confirms the listing details they are finally satisfied with, they can press the "Complete Listing" button to officially list the product. The input is the final information edited by the user, and the output is the final listing data.

[1640] (Application Example 2)

[1641] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1642] Traditional e-commerce sites display product descriptions and reviews uniformly, making it difficult to address the individual emotions and needs of each consumer. In particular, the lack of real-time solutions to consumer frustrations and questions while browsing product pages poses a risk of diminishing their purchase intent. Therefore, a system is needed that dynamically adjusts product descriptions, prices, and recommendations based on consumer emotions, providing information optimized for each individual consumer.

[1643] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting product video data, means for storing product video data, means for referring to a past listing video database, means for comparing the product video data with video data in the past listing video database to determine the product condition, means for setting an appropriate price for the product based on the product condition, means for generating a product description based on the product condition and the appropriate price, means for analyzing input video and audio data to analyze the user's emotions, means for adjusting the product description and the appropriate price based on the user's emotions, and means for presenting the product condition, the appropriate price, and the product description to the user. This makes it possible to provide personalized information based on the consumer's emotions in real time.

[1644] "Product video data" refers to digital data of videos of products that a user wishes to list or purchase.

[1645] The "Past Listing Video Database" is a database that stores videos and related data of items previously listed on flea markets and online shopping sites.

[1646] "Product condition" refers to information about the product's condition, such as its age (new or old) and whether or not it has any damage.

[1647] A "fair price" is a fair and realistic selling price calculated based on the condition of the product and the supply and demand in the market.

[1648] A "product description" is a descriptive text that details the product's features, condition, price, and other relevant information.

[1649] "Emotion analysis means" refers to technical means for analyzing a user's video and audio data to recognize their emotions.

[1650] "Presentation method" refers to a means of displaying the generated product condition, appropriate price, and product description to the user.

[1651] "Editing methods" refer to means that enable users to modify and edit product descriptions and appropriate pricing.

[1652] An "image recognition algorithm" is an algorithm that analyzes input video data to identify and determine the content of an image.

[1653] This invention relates to a system that automatically generates product condition, appropriate price, and product description based on product video data, and adjusts them based on the user's emotions. This system inputs product video data, stores it, analyzes it, and performs a series of processes to present it to the user. Furthermore, it can analyze the user's emotions and personalize the content accordingly.

[1654] First, the user takes product video data using a device such as a smartphone or smart glasses and inputs it into the system. The input product video data is sent to a server and stored there.

[1655] Next, the server analyzes the stored product video data. Image recognition algorithms are used for this analysis. The server refers to a database of past listing videos and compares them with the current video data to determine the condition of the product. For example, it determines whether the product is used or new, and how much wear and tear it has.

[1656] Subsequently, the server sets an appropriate price based on the determined product condition. Past data on similar products is used as a reference when setting the appropriate price. Furthermore, a product description is automatically generated based on the determined product condition and appropriate price. This product description includes details such as the product's features, condition, and price.

[1657] Next, emotion analysis tools are used to analyze the user's emotions in real time. These tools analyze the user's facial expressions and voice to recognize their emotions. This analysis utilizes the camera and microphone of a smartphone or smart glasses.

[1658] Based on the sentiment analysis results, the server adjusts product descriptions and appropriate pricing. For example, if a user displays a dissatisfied expression, the detailed product description and price will be reconsidered. Recommended products and advice based on sentiment analysis are also provided.

[1659] Finally, the adjusted product condition, appropriate price, and product description are presented to the user. The user can review this and edit it as needed.

[1660] Specific example

[1661] For example, a user takes a picture of a used digital camera using their smartphone and uploads the image data to the system. Based on this data, the server determines the product's condition as "good" and sets a fair price of 28,000 yen. A generated product description is then presented to the user.

[1662] If a user expresses dissatisfaction with the offered price, sentiment analysis tools will recognize this, and the server will readjust the price and description. Ultimately, the user can list their product in a way that satisfies them.

[1663] Examples of prompts for generative AI models

[1664] Create specific code for an e-commerce application that recognizes user emotions in real time from facial expressions and voice, and provides personalized product information based on those emotions. Include a process for collecting user data using the camera and microphone of a smartphone or smart glasses, and optimizing product information after emotion analysis. The generated code should specifically indicate the use of emotion and recommendation engines.

[1665] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1666] Step 1:

[1667] Users use their smartphones or smart glasses to capture video data of the items they want to list for sale. This video data includes detailed information about the products.

[1668] Input: Product video data

[1669] Output: Video data stored on the device

[1670] Specific operation: The user takes a picture of the product using the camera function of their smartphone or smart glasses, and the image data is saved on the device.

[1671] Step 2:

[1672] The device uploads the captured product video data to the server via the flea market application.

[1673] Input: Video data stored on the device

[1674] Output: Video data sent to the server

[1675] Specific operation: The user presses the "Upload" button within the application, and the video data is sent to the server via the internet.

[1676] Step 3:

[1677] The server receives the uploaded product video data and saves it to the database.

[1678] Input: Video data sent to the server

[1679] Output: Video data stored in the database

[1680] Specific operation: The server receives an HTTP request and saves the video data to dedicated storage.

[1681] Step 4:

[1682] The server analyzes the stored product video data. This analysis uses an image recognition algorithm.

[1683] Input: Video data stored in the database

[1684] Output: Analyzed product condition data

[1685] Specific operation: The server executes an image recognition algorithm and analyzes the video data to determine the condition of the product. For example, information such as the age of the product and whether or not there are any scratches is extracted.

[1686] Step 5:

[1687] The server refers to a database of past listing videos and compares them with current video data to determine the product's condition in more detail.

[1688] Input: Analyzed product condition data, past listing video database

[1689] Output: Detailed product condition data

[1690] Specific operation: The server searches for similar images in its past database, compares them with the current data, and determines the product condition more accurately.

[1691] Step 6:

[1692] The server sets an appropriate price based on the determined product condition. This setting is based on data from similar products in the past.

[1693] Input: Detailed product condition data, historical data on similar products.

[1694] Output: Fair price data

[1695] Specific operation: The server uses an algorithm to combine product condition and market data to calculate a fair price.

[1696] Step 7:

[1697] The server automatically generates a product description based on the determined product condition and appropriate price.

[1698] Input: Detailed product condition data, appropriate price data

[1699] Output: Product description data

[1700] Specific operation: The server uses a text generation algorithm to generate a product description. This description includes the product's features, condition, price, etc.

[1701] Step 8:

[1702] The server analyzes video and audio data received from the terminal in real time to analyze the user's emotions.

[1703] Input: Video and audio data received from the device.

[1704] Output: User's emotional data

[1705] Specific operation: Using data collected from the device's camera and microphone, the server runs an emotion analysis engine to recognize the user's emotions.

[1706] Step 9:

[1707] The server adjusts product descriptions and appropriate pricing based on user sentiment data.

[1708] Input: User sentiment data, product description data, appropriate price data

[1709] Output: Adjusted product description data, adjusted fair price data

[1710] Specific operation: The server uses user sentiment data to review the generated product description and appropriate price, and makes corrections as needed.

[1711] Step 10:

[1712] The server then presents the user with the final adjusted product condition, appropriate price, and product description, which the user can review and edit as needed.

[1713] Input: Adjusted product description data, adjusted fair price data

[1714] Output: Final data presented to the user

[1715] Specific operation: The server sends the adjusted information to the user's terminal, the user reviews the displayed data, edits it as needed, and then performs a final confirmation.

[1716] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1717] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1718] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1719] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1720] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1721] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1722] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1723] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1724] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1725] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1726] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1727] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1728] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1729] 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.

[1730] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1731] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1732] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1733] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1734] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1735] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1736] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1737] The following is further disclosed regarding the embodiments described above.

[1738] (Claim 1)

[1739] A means of inputting product video data,

[1740] A means for storing the aforementioned product video data,

[1741] A means of referring to a database of past listing videos,

[1742] A means for comparing the aforementioned product video data with video data in the aforementioned past listing video database to determine the condition of the product,

[1743] A means for setting a fair price for a product based on the aforementioned product condition,

[1744] A means for generating a product description based on the aforementioned product condition and the aforementioned appropriate price,

[1745] A means for presenting the aforementioned product condition, the aforementioned appropriate price, and the aforementioned product description to the user,

[1746] A system that includes this.

[1747] (Claim 2)

[1748] The system according to claim 1, further comprising means for allowing the user to edit the product description and the appropriate price.

[1749] (Claim 3)

[1750] The system according to claim 1, further comprising means for using an image recognition algorithm to analyze the aforementioned product video data.

[1751] "Example 1"

[1752] (Claim 1)

[1753] A means of inputting product video data,

[1754] A means for storing the aforementioned product video data,

[1755] A means of referring to a database of past listing videos,

[1756] A means for comparing the aforementioned product video data with video data in the aforementioned past listing video database to determine the condition of the product,

[1757] A means for setting a fair price for a product based on the aforementioned product condition,

[1758] A method of using a generation AI to generate product descriptions,

[1759] A means for generating a product description based on the aforementioned product condition and the aforementioned appropriate price,

[1760] A means for presenting the aforementioned product condition, the aforementioned appropriate price, and the aforementioned product description to the user,

[1761] A system that includes this.

[1762] (Claim 2)

[1763] The system according to claim 1, comprising an interface for allowing the user to edit the product description and the appropriate price.

[1764] (Claim 3)

[1765] The system according to claim 1, further comprising means for using an image recognition algorithm to analyze the aforementioned product video data.

[1766] "Application Example 1"

[1767] (Claim 1)

[1768] A means of inputting product video data,

[1769] A means for storing the aforementioned product video data,

[1770] A means of referring to a database of past listing videos,

[1771] A means for comparing the aforementioned product video data with video data in the aforementioned past listing video database to determine the condition of the product,

[1772] A means for setting a fair price for a product based on the aforementioned product condition,

[1773] A means for generating a product description based on the aforementioned product condition and the aforementioned appropriate price,

[1774] A means for presenting the aforementioned product condition, the aforementioned appropriate price, and the aforementioned product description to the user,

[1775] A means for transmitting the aforementioned product condition and the aforementioned appropriate price to a cloud server and analyzing them using an image recognition algorithm,

[1776] A means of generating product descriptions using a generative AI model,

[1777] A system that includes this.

[1778] (Claim 2)

[1779] The system according to claim 1, further comprising means for allowing the user to edit the product description and the appropriate price.

[1780] (Claim 3)

[1781] The system according to claim 1, further comprising means for using an image recognition algorithm to analyze the aforementioned product video data.

[1782] "Example 2 of combining an emotion engine"

[1783] (Claim 1)

[1784] A means of inputting product video data,

[1785] A means for storing the aforementioned product video data,

[1786] A means of referring to past listing video data,

[1787] A means for comparing the aforementioned product video data with data in the aforementioned past listing video data to determine the product condition,

[1788] A means for setting a fair price for a product based on the aforementioned product condition,

[1789] A means for generating a product description based on the aforementioned product condition and the aforementioned appropriate price,

[1790] Means of recognizing user emotions,

[1791] A means for adjusting the product descripti...

Claims

1. A means of inputting product video data, A means for storing the aforementioned product video data, A means of referring to a database of past listing videos, A means for comparing the aforementioned product video data with video data in the aforementioned past listing video database to determine the condition of the product, A means for setting a fair price for a product based on the aforementioned product condition, A means for generating a product description based on the aforementioned product condition and the aforementioned appropriate price, A means for presenting the aforementioned product condition, the aforementioned appropriate price, and the aforementioned product description to the user, A system that includes this.

2. The system according to claim 1, further comprising means for allowing the user to edit the product description and the appropriate price.

3. The system according to claim 1, further comprising means for using an image recognition algorithm to analyze the aforementioned product video data.

Images