system

Abstract

We provide the system. [Solution] A means of automatically generating product information, A method for analyzing product images and creating product descriptions, A method of researching market prices for similar products and proposing pricing, A means of recommending products to prospective buyers, 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, including 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] When a product is offered on an online platform, the provider needs to take a lot of trouble such as product description, price setting, photo editing, etc. Also, for potential buyers, it is difficult to find the desired product from a huge amount of product information, and there is also a problem of hesitation due to inappropriate price setting. These problems impair the convenience of users in the free market and prevent the conclusion of transactions. Therefore, a technical solution is required that enables providers to easily register products and potential buyers to easily find the desired products.

Means for Solving the Problems

[0005] This invention provides a means for automatically generating product information. Specifically, it includes means for analyzing product images and automatically creating appropriate product descriptions. Furthermore, it includes means for using AI technology to investigate market prices of similar products and suggest pricing to sellers. It also provides a function to recommend products to prospective buyers according to their conditions and means for providing price adjustment advice in related negotiations. This significantly improves convenience for both sellers and prospective buyers.

[0006] "Means for automatically generating product information" refers to technologies or processes that automatically and dynamically create detailed information related to a product without human intervention.

[0007] "A method for analyzing product images to create product descriptions" refers to a system that uses image recognition technology to extract product features and then generates text that describes the product based on those features.

[0008] "Methods for researching market prices of similar products and proposing pricing" refers to techniques that collect and analyze price data for similar products in circulation, calculate appropriate prices, and propose them to sellers.

[0009] "Methods for recommending products to potential buyers" refers to systems or algorithms that select products likely to interest buyers and propose them to them on the platform in a timely manner.

[0010] "Means of translation" refers to a process or device that has the function of automatically translating product descriptions and negotiation content between multiple languages.

[0011] "Means of providing price adjustment advice in negotiations" refers to technologies that provide users with information and strategies to support appropriate price negotiations in the negotiation setting. [Brief explanation of the drawing]

[0012] [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]

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention provides a system that simplifies transactions on a flea market platform for both sellers and buyers. This system utilizes AI technology to automate many transaction-related tasks.

[0034] The system starts when the user takes product photos using their device and uploads them to the application. The server analyzes the received image data using advanced image recognition algorithms to identify the product category and characteristics. Based on this information, the server automatically generates a product description using natural language processing technology. This product description is sent back to the user's device and used as the listing content.

[0035] Furthermore, the server crawls the market database and collects market prices for similar products based on publicly available information on the internet. Based on this data, the server calculates a fair price for the product and sends it to the terminal as a valuable suggestion. This suggestion serves as a reference for the user and helps them set an appropriate selling price.

[0036] For prospective buyers, users enter their desired product criteria into a terminal, which is then received by a server. AI is applied to search the database and select products that match the criteria. Once selected, the products are provided to the user as recommendation information via the terminal. This process supports the prospective buyer's selection and increases the likelihood of a successful transaction.

[0037] Furthermore, to facilitate transactions between different languages, the server uses an automatic translation function to translate product descriptions and negotiation details into multiple languages. This function provides an environment where transactions can be conducted smoothly even in global markets.

[0038] For example, when a user takes a photo of a jacket and lists it for sale, they can immediately register it and start selling based on the system's automatically generated description and suggested price. If a potential buyer enters their criteria, jackets that match their size and price will be recommended, allowing them to proceed with the purchase efficiently.

[0039] These features improve efficiency and satisfaction for both sellers and buyers when using the flea market app.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user takes a product photo using their device and uploads it to the application. The device then sends this image data to the server.

[0043] Step 2:

[0044] The server analyzes the received images. It uses AI image recognition algorithms to identify the product's category and characteristics.

[0045] Step 3:

[0046] The server automatically generates a product description using natural language processing technology based on the analysis results. This description is sent to the terminal, and the user is asked to confirm it.

[0047] Step 4:

[0048] The server crawls the market database, collecting and analyzing price information for similar products. Based on this, the server calculates a recommended selling price and sends it to the terminal as a suggestion.

[0049] Step 5:

[0050] The user reviews the product description and suggested price generated on their device and edits them as needed. Finally, the product information is registered on the flea market platform according to the user's instructions.

[0051] Step 6:

[0052] The prospective buyer enters product search criteria on their device. The device then sends this information to the server.

[0053] Step 7:

[0054] The server searches the database based on the specified criteria and selects suitable products. The selected product information is sent to the terminal and provided to the prospective buyer as recommendation information.

[0055] Step 8:

[0056] If the server requires multilingual support, it will automatically translate product descriptions and negotiation details into the necessary languages.

[0057] Step 9:

[0058] If the server is in a global market or if price negotiation is necessary, the system provides users with price negotiation advice based on data. Users then use this information to negotiate.

[0059] (Example 1)

[0060] 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."

[0061] Online platform transactions present challenges due to the complexity of the process, as sellers require specialized knowledge regarding product information and pricing, and communication across multiple languages ​​can be difficult. Furthermore, potential buyers struggle to find suitable products amidst a vast amount of information, hindering efficient transactions.

[0062] 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.

[0063] In this invention, the server includes means for automatically generating product information, means for analyzing product images to create product descriptions, means for researching market prices of similar products and proposing pricing, means for selecting and recommending products that meet the buyer's requirements using AI technology, and means for translating product descriptions and negotiation content between different languages. This enables both sellers and buyers to conduct transactions efficiently and smoothly.

[0064] "Means for automatically generating product information" refers to a mechanism that automatically creates detailed descriptions and features of a product without requiring user intervention.

[0065] "A method for analyzing product images to create product descriptions" refers to a system that analyzes the input image data of a product and expresses its characteristics and features as text.

[0066] "A method for researching market prices of similar products and proposing pricing" refers to a system that refers to existing market data, analyzes the prices of similar products, and shows users an appropriate selling price.

[0067] "Methods for recommending products to prospective buyers" refers to methods of presenting the most suitable products to users with purchasing intent based on their past behavior and specified conditions.

[0068] "A method of selecting products that meet the criteria using AI technology" refers to a process in which an artificial intelligence algorithm is used to narrow down the database of relevant products based on the criteria entered by the prospective buyer.

[0069] A "means of translating product descriptions between different languages" refers to a system that converts product descriptions into multiple languages ​​to facilitate smooth communication between users who speak different languages.

[0070] This invention is a system for a flea market platform that facilitates smooth and efficient transactions between sellers and prospective buyers. This system utilizes image recognition technology, natural language processing, price information analysis, and automatic translation technology to automate the tasks necessary for transactions.

[0071] The system starts when a user uses their device to take photos of the products they want to sell and uploads them to the application. The device sends this image data to the server. The server analyzes the received images using image processing software such as TENSORFLOW® or OpenCV to identify the product category and characteristics.

[0072] Based on the analysis results, the server generates a product description written in natural language using generative AI models such as GPT and BERT. This text is returned to the user's device and used as listing information.

[0073] The server then uses tools like BeautifulSoup and Scrapy to crawl market data on the internet and retrieve market prices for similar products. Based on the collected data, it calculates a fair selling price for the product and sends it to the user's device as a recommended price. This allows the user to obtain advantageous information when setting prices.

[0074] When a prospective buyer enters product specifications (e.g., size, price) into a terminal, the terminal receives this data and sends it to a server. The server uses AI technology to select products that match the specifications from its database and provides the user with the most suitable recommendation information.

[0075] Furthermore, the server uses Google Translate API and DeepL's automatic translation function to translate product descriptions and negotiation details into different languages ​​used by the user. This feature facilitates transactions between users who speak different languages.

[0076] For example, when a user takes a photo of a used jacket and uploads it to the system, the system generates a description such as "Blue denim jacket, size M" and suggests it to the user. It also suggests a fair price of "3,500 yen" based on past sales data.

[0077] An example of a prompt message might be: "I would like to take product photos, automatically identify the category and characteristics, and generate a description in natural language. I would also like you to suggest a fair market price." This allows the system to automatically provide services that meet the user's needs.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user takes product photos using their device and uploads them to the application. The input includes the image data taken by the user. The device receives this image data, performs a format conversion (e.g., to JPEG or PNG format), and sends it to the server via the internet.

[0081] Step 2:

[0082] The server analyzes image data received from the terminal. The input is product image data, which is then analyzed using an image recognition model (e.g., TensorFlow or OpenCV). Specifically, it performs feature point extraction and segmentation of the image to identify product categories and characteristics. The output generates product category information and feature data.

[0083] Step 3:

[0084] The server automatically generates product descriptions using a generative AI model (e.g., GPT, BERT) based on the information obtained from image analysis. The input consists of product category information and feature data. The server inputs this into a natural language generation model and generates a product description as output. Specifically, a description like "This product is a blue denim jacket, size M" is created.

[0085] Step 4:

[0086] The server crawls online market databases to collect price information for similar products. The input is a search query based on product category and characteristics. The server uses web scraping tools (e.g., BeautifulSoup, Scrapy) to search the database and collect historical price data. The output is the collected price information. Based on this, statistical analysis is performed to calculate a fair price.

[0087] Step 5:

[0088] The server sends the calculated fair price to the user's device. The input is fair price data. The server converts this price into a user-friendly format and sends a push notification to the device as output. The user uses this price information as a reference when listing their product.

[0089] Step 6:

[0090] The prospective buyer enters the desired product specifications into the terminal. These specifications include user-specified criteria (e.g., size M, price under 3,000 yen). The terminal then sends these specifications to the server.

[0091] Step 7:

[0092] The server searches its database based on the received conditions and uses AI technology (e.g., recommendation algorithms) to select products that meet those conditions. The input is the conditions of the prospective buyer, and the output is a list of recommended products. This list is sent to the user's terminal and displayed to the buyer.

[0093] Step 8:

[0094] The server uses an automatic translation function to translate product descriptions and negotiation details into different languages. The input is the product description written in the original language. The server uses the Google Translate API or DeepL to generate output translated into the required language. This translated information is sent to the device and displayed to the user.

[0095] (Application Example 1)

[0096] 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."

[0097] Online shopping platforms face challenges such as cumbersome procedures between sellers and buyers, difficulty in setting fair prices, and barriers to international trade due to insufficient multilingual support. Furthermore, there is a need to address the difficulty buyers face in quickly finding products that meet their requirements.

[0098] 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.

[0099] In this invention, the server includes means for automatically generating product information, means for analyzing product images to create product descriptions, means for researching market prices of similar products and suggesting pricing, means for presenting the most suitable product based on input product conditions, and means for translating product descriptions into multiple languages. This enables sellers to list products at a fair price without hassle, allows prospective buyers to quickly find products that meet their desired conditions, and facilitates smooth international transactions.

[0100] "Means for automatically generating product information" refers to a function that automatically creates product descriptions and specifications using artificial intelligence technology.

[0101] "A method for analyzing product images and creating product descriptions" refers to a technology that uses image recognition algorithms to analyze product photos and generates appropriate descriptions from the results.

[0102] "A means of researching market prices for similar products and proposing pricing" refers to a function that collects prices for similar products by referring to a market database and then presents a fair price for the product to the user based on that data.

[0103] "A method for recommending products to prospective buyers" refers to an algorithm that searches a database for products based on the conditions specified by the buyer and presents the most suitable options.

[0104] "Methods for translating product descriptions into multiple languages" refers to a function that automatically translates product descriptions to facilitate transactions between users who speak different languages.

[0105] "A means of presenting the most suitable product based on the input of product conditions" refers to a function that searches a database based on the conditions entered by the prospective buyer and presents the product that best matches those conditions.

[0106] The system for implementing this invention forms an online platform that streamlines product transactions for both sellers and prospective buyers. Specific embodiments of this system are shown below.

[0107] The server first receives product images input by the user and analyzes them using TensorFlow. Based on the product category and characteristic information obtained through image analysis, the server generates a product description using OpenAI's GPT API. This generated description is sent to the user's device and used as the listing content.

[0108] Next, the server uses Puppeteer to crawl market data and collect price information for similar products. Based on this information, it calculates a fair price and suggests it to the user.

[0109] When a prospective buyer enters product specifications into a terminal, those specifications are sent to a server. The server searches a database and selects products that match the specifications. This selected product information is then presented to the prospective buyer via the terminal to assist them in making a purchase decision.

[0110] Furthermore, the server uses the Google Cloud Translation API to translate product descriptions and negotiation details into multiple languages. This enables smooth transactions between different languages.

[0111] For example, if a user wants to list a "jacket" for sale, the server analyzes the image and generates a description such as, "This jacket is waterproof, size M, and features the latest design." It also suggests a fair price for the jacket and translates the product description into multiple languages, making it easier to appeal to international buyers.

[0112] An example of a prompt for a generative AI model would be: "This product is a jacket, it is waterproof, and the size is M. Please generate a detailed description based on this information."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The user takes a picture of the product using their device and uploads it to the system. The input in this process is the product image, and the output is the transmission of the image data to the server.

[0116] Step 2:

[0117] The server analyzes the received images using TensorFlow. The input for image analysis is a product image, and data calculations are performed to identify the product category and characteristics, which are then obtained as output.

[0118] Step 3:

[0119] The server automatically generates a product description using the OpenAI GPT API based on the analysis results. In this step, the analysis results are used as input, and the product description is output.

[0120] Step 4:

[0121] The server sends the generated product description to the user's terminal. The input is the generated product description, and the output is the description displayed on the terminal.

[0122] Step 5:

[0123] The server uses Puppeteer to crawl market data and collect price information for similar products. Here, information on similar products is taken as input, and price information is output.

[0124] Step 6:

[0125] Based on the collected price information, the server calculates the appropriate price for the product and sends it to the user as a recommended price. The input is price information for similar products, and the output is recommended price information.

[0126] Step 7:

[0127] When a user enters product criteria into their terminal, the server receives the data and performs a database search. In this step, the server searches for the most suitable product based on the entered criteria and generates a list of candidate products as output.

[0128] Step 8:

[0129] The system displays a list of recommended products on the user's device to assist in the purchase selection process. The input is the recommended products, and the output is the list of candidates displayed to the user.

[0130] Step 9:

[0131] The server utilizes the Google Cloud Translation API to translate product descriptions into multiple languages. Here, the product description is taken as input, and the translated description is output.

[0132] Step 10:

[0133] Provide users with translated product descriptions and quickly implement multilingual support. The input is the translated description, and the output is the information displayed on the user's terminal.

[0134] 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.

[0135] This invention relates to an automated transaction support system configured to facilitate transactions on a flea market platform, and in particular, to a system that takes user emotions into consideration. This system aims to improve the experience for both sellers and buyers by utilizing AI technology.

[0136] When a user takes a product photo using their device and uploads it to the application, the server first analyzes the image. This analysis uses an image recognition algorithm to automatically identify the product's category and characteristics. The server then uses natural language processing technology to generate a product description, which is presented to the user via their device.

[0137] In parallel, the server crawls the market database, collecting and analyzing information on similar products on the internet. This allows sellers to easily set reasonable prices by calculating and suggesting appropriate prices to their terminals.

[0138] Furthermore, the server receives the search criteria of potential buyers and uses an AI algorithm to select and recommend products that match those criteria. This recommendation serves to support the decision-making process for potential buyers.

[0139] In addition, this invention integrates an emotion engine. The emotion engine analyzes the user's voice, facial expressions, and input patterns to determine their current emotional state. For example, if a user expresses dissatisfaction or frustration with the negotiation situation, the server detects this. Based on this, the negotiation strategy and price offer are adjusted to improve the user experience.

[0140] For example, if a user lists an expensive item and sales are stagnating, the emotion engine will detect the user's frustration. The server will then help move negotiations forward by suggesting alternative pricing strategies or offering assistance in preparing for negotiations. Furthermore, the system supports multiple languages, enabling smooth transactions between different countries.

[0141] This invention makes flea market transactions more intuitive and effective, and allows for flexible responses that respond to users' emotions.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The user takes a product photo using their device and uploads it to the application. The device then sends this image to the server.

[0145] Step 2:

[0146] The server analyzes the received image data using an AI image recognition algorithm. It identifies product categories and characteristics, which then serve as the basis for product descriptions.

[0147] Step 3:

[0148] The server uses natural language processing technology to automatically generate a product description based on the analysis results. This description is then sent to the terminal and presented to the user.

[0149] Step 4:

[0150] The server crawls the market database, collecting and analyzing prices for similar products. Based on this information, it calculates a fair selling price and sends it to the terminal as a price suggestion.

[0151] Step 5:

[0152] Users can view product descriptions and price suggestions on their devices and edit them as needed. The edited product information is then registered on the flea market platform.

[0153] Step 6:

[0154] The prospective buyer enters product search criteria into their terminal. These criteria are then sent to the server.

[0155] Step 7:

[0156] The server uses an AI algorithm to search the database for products that match the specified criteria and sends the selected product information back to the terminal as a recommendation.

[0157] Step 8:

[0158] The server activates an emotion engine based on the voice, facial expressions, and input patterns obtained from the user to determine the user's emotional state.

[0159] Step 9:

[0160] Based on the emotions detected by the emotion engine, the server adjusts and sends transaction-related feedback and advice to the terminal.

[0161] Step 10:

[0162] The server uses its multilingual support function to automatically translate listing information and negotiation details as needed, facilitating smooth transactions between different languages.

[0163] (Example 2)

[0164] 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".

[0165] In online flea market transactions, generating product information, setting appropriate prices, and recommending items to potential buyers are often cumbersome processes. Furthermore, the need for flexible responses that consider the feelings of both sellers and buyers can sometimes lead to an inadequate user experience. Additionally, smooth transactions between users speaking different languages ​​are necessary.

[0166] 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.

[0167] In this invention, the server includes means for analyzing image data to identify product characteristics, means for creating product descriptions using natural language generation technology, means for collecting market information on the internet and calculating appropriate prices, means for recommending products based on the conditions of prospective buyers, and means for analyzing the user's emotional state and reflecting it in product recommendations. This enables automatic generation of product information, appropriate pricing, and the provision of flexible experiences based on emotions. Furthermore, it facilitates smooth transactions between multiple languages.

[0168] "Image data" refers to information that represents visual information in a digital format and can be processed by a computer.

[0169] "Product characteristics" refer to information that indicates the attributes and features of a product, and include the product's category, size, color, and brand.

[0170] "Natural language generation technology" is a technology that models human language to generate natural-sounding sentences, and is used as part of artificial intelligence.

[0171] "Market information" refers to data related to commercial transactions, such as product prices, demand trends, and inventory levels.

[0172] "Fair price" refers to a reasonable price range for a product, assessed based on market supply and demand.

[0173] "Prospective buyer" refers to an individual or group that is considering purchasing a product.

[0174] "Emotional state" refers to the user's current emotions and psychological state, and is determined by factors such as tone of voice, facial expressions, and input patterns.

[0175] "Product proposal" refers to the act of introducing a product to a user based on specific conditions.

[0176] Translation is the process of replacing expressions between different languages ​​without changing their meaning.

[0177] This invention is a system that facilitates transactions on an online flea market platform and integrates various technologies to improve the user experience. The core server of the system operates by combining image analysis, natural language generation, price calculation, recommendation systems, and sentiment analysis technologies.

[0178] Users take product photos using their devices and upload the image data to the server via the application. The server uses a common computer vision framework to analyze this image data. For example, it leverages deep learning libraries to extract image features and identify product characteristics.

[0179] The server generates a product description using natural language generation technology based on the identified product characteristics. This process utilizes a natural language processing framework known as a generative AI model to generate text data. For example, a prompt such as "Generate a product description. The product name is 'Vintage Record Player,' and the characteristics are 'Made in the 1960s, in good working order, antique finish'" might be used.

[0180] To determine a fair price for a product, the server collects market information from the internet and calculates the price. This involves using web scraping techniques to gather large amounts of market data and analyzing it through statistical models. As a result, it can propose a market price for the product to the user.

[0181] To recommend products that meet the criteria of potential buyers, the server takes into account past purchase history and preference data. An AI algorithm evaluates this data and displays products that are likely to be of interest. In addition, an emotion engine analyzes the user's emotional state and adjusts the recommendations according to the user's emotions.

[0182] The system also includes translation technology to facilitate smooth transactions between different languages. This feature streamlines communication between users and promotes international trade. As a result, using the flea market platform becomes more intuitive and effective.

[0183] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0184] Step 1:

[0185] The user takes a product photo using their device and uploads the image data to the server via the application. The input is the product image taken by the user with the camera, and the output is the image data received by the server. The server adds this data to a processing queue and prepares to perform analysis in the next step.

[0186] Step 2:

[0187] The server analyzes the image data. The input is the image data received in step 1. The server uses image recognition technology to extract features from the image and identify product characteristics. A deep learning model identifies the product and outputs category and characteristic information. For example, the image might be identified as "vintage audio equipment".

[0188] Step 3:

[0189] Based on the product characteristics identified by the server, a generative AI model is used to generate a product description using natural language generation technology. The input is the product characteristics obtained in step 2. The generative AI model is given characteristic information as a prompt and outputs a description such as, "This product is a vintage record player from the 1960s."

[0190] Step 4:

[0191] The server collects market data and calculates a fair price. The inputs are product characteristics and market information from the internet. The server uses web scraping techniques to collect price data for similar products from the internet. The collected data is analyzed using statistical methods and output price information such as "The estimated fair price is $100."

[0192] Step 5:

[0193] The server displays the generated product description and appropriate price on the terminal. The input is the information obtained in steps 3 and 4. The product description and appropriate price are displayed on the user's terminal to assist in product pricing.

[0194] Step 6:

[0195] The server receives the buyer's criteria and recommends products. The input is the buyer's search criteria data. An AI algorithm identifies products that match the search criteria and outputs a list of products that the buyer might be interested in, referencing past purchase data.

[0196] Step 7:

[0197] The server analyzes the user's emotional state and adjusts product recommendations accordingly. Input consists of user voice and facial expression data. An emotion engine analyzes this data and generates and outputs optimal product recommendations based on the user's emotions. This improves the user experience.

[0198] (Application Example 2)

[0199] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0200] Traditional flea market platforms have problems such as difficulties in smooth transactions between sellers and buyers, and challenges in properly classifying and pricing products. Furthermore, they lack the flexibility to respond to user emotions, resulting in a poor transaction experience.

[0201] 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.

[0202] In this invention, the server includes means for analyzing and classifying product images, means for evaluating image data and generating product descriptions, and means for collecting market information and estimating sales prices. This enables automatic product classification, appropriate pricing, and adjustment of sales strategies to suit user sentiment.

[0203] "Product image analysis" is a technology that uses software to process the visual data of items offered to the market, extracting and classifying their features.

[0204] "Picture data evaluation" is a technology that automatically generates descriptive text for objects based on images and related information, and clarifies the content of that text.

[0205] "Market information gathering" refers to the technique of collecting information on similar products from the internet and databases, and analyzing prices and supply and demand trends.

[0206] "Price estimation" is the process of calculating a reasonable price based on collected market information and proposing it to the seller.

[0207] "Adjusting sales strategies in response to user emotions" refers to a method of detecting the emotional state of users and dynamically changing negotiation policies and sales approaches accordingly.

[0208] To implement this invention, a system is required that combines a user's terminal, a server, and related software. First, the user takes a picture of a product using their smartphone's camera and uploads the image to an application on their terminal. This application automatically sends the image data to the server.

[0209] Upon receiving image data, the server analyzes the product images using image recognition software based on TensorFlow and determines their classification. Then, using a GPT model, it automatically generates an effective product description based on the analysis results. The generated description is sent to the user's device and displayed.

[0210] Furthermore, the server uses a Python scraping library to collect market information from the internet and analyzes the market database to estimate selling prices. This pricing information is provided to product sellers, enabling them to set appropriate prices.

[0211] After the user reviews the product description and price, the server runs an emotion analysis tool to determine the user's emotional state by analyzing their facial expressions using OpenCV and analyzing their voice. Based on the user's emotions, the server adjusts negotiation and sales strategies to optimize the user's transaction experience.

[0212] For example, if a user wants to sell a painting and takes a photo of the product, the program analyzes the image and classifies it as "painting," "art," or "landscape." The server then generates a product description such as, "Beautifully decorate your living room with this painting." An example of a prompt message would be, "Analyze the captured image, identify the main features of the product, and develop an emotionally resonant sales strategy."

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The user takes a picture of the product they want to sell using their device's camera. This image is uploaded to the application on the device. The input is the image data of the product, and the output is the data sent to the server.

[0216] Step 2:

[0217] The terminal sends the uploaded image data to the server. The server inputs the received image data into an image recognition algorithm using TensorFlow. This analyzes the product image and obtains its classification information. The output is product category data.

[0218] Step 3:

[0219] The server uses a GPT model based on image recognition results to generate a product description. The input is product category data, and the output is an automatically generated product description. The generated description is sent to the terminal and displayed to the user.

[0220] Step 4:

[0221] The server uses a Python scraping library to collect market information from the internet. The input is a search query related to a product, and the output is market data including pricing information for similar products. Based on this data, it estimates the selling price and provides the price information to the user's terminal.

[0222] Step 5:

[0223] After the user reviews the product description and price, the server uses OpenCV-based facial expression and voice analysis tools to determine the user's emotional state based on their facial expressions and voice data. The output is the user's emotional evaluation data. Based on this data, the server adjusts its sales strategy and provides the user with necessary information.

[0224] Step 6:

[0225] The server optimizes negotiation strategies based on the user's emotions and generates prompts for an AI model within the system. The input is the user's emotion rating data, and the output is a refined sales or negotiation strategy. This strategy is sent to the terminal to support the user's next action.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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".

[0242] This invention provides a system that simplifies transactions on a flea market platform for both sellers and buyers. This system utilizes AI technology to automate many transaction-related tasks.

[0243] The system starts when the user takes product photos using their device and uploads them to the application. The server analyzes the received image data using advanced image recognition algorithms to identify the product category and characteristics. Based on this information, the server automatically generates a product description using natural language processing technology. This product description is sent back to the user's device and used as the listing content.

[0244] Furthermore, the server crawls the market database and collects market prices for similar products based on publicly available information on the internet. Based on this data, the server calculates a fair price for the product and sends it to the terminal as a valuable suggestion. This suggestion serves as a reference for the user and helps them set an appropriate selling price.

[0245] For prospective buyers, users enter their desired product criteria into a terminal, which is then received by a server. AI is applied to search the database and select products that match the criteria. Once selected, the products are provided to the user as recommendation information via the terminal. This process supports the prospective buyer's selection and increases the likelihood of a successful transaction.

[0246] Furthermore, to facilitate transactions between different languages, the server uses an automatic translation function to translate product descriptions and negotiation details into multiple languages. This function provides an environment where transactions can be conducted smoothly even in global markets.

[0247] For example, when a user takes a photo of a jacket and lists it for sale, they can immediately register it and start selling based on the system's automatically generated description and suggested price. If a potential buyer enters their criteria, jackets that match their size and price will be recommended, allowing them to proceed with the purchase efficiently.

[0248] These features improve efficiency and satisfaction for both sellers and buyers when using the flea market app.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The user takes a product photo using their device and uploads it to the application. The device then sends this image data to the server.

[0252] Step 2:

[0253] The server analyzes the received images. It uses AI image recognition algorithms to identify the product's category and characteristics.

[0254] Step 3:

[0255] The server automatically generates a product description using natural language processing technology based on the analysis results. This description is sent to the terminal, and the user is asked to confirm it.

[0256] Step 4:

[0257] The server crawls the market database, collecting and analyzing price information for similar products. Based on this, the server calculates a recommended selling price and sends it to the terminal as a suggestion.

[0258] Step 5:

[0259] The user reviews the product description and suggested price generated on their device and edits them as needed. Finally, the product information is registered on the flea market platform according to the user's instructions.

[0260] Step 6:

[0261] The prospective buyer enters product search criteria on their device. The device then sends this information to the server.

[0262] Step 7:

[0263] The server searches the database based on the specified criteria and selects suitable products. The selected product information is sent to the terminal and provided to the prospective buyer as recommendation information.

[0264] Step 8:

[0265] If the server requires multilingual support, it will automatically translate product descriptions and negotiation details into the necessary languages.

[0266] Step 9:

[0267] If the server is in a global market or if price negotiation is necessary, the system provides users with price negotiation advice based on data. Users then use this information to negotiate.

[0268] (Example 1)

[0269] 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."

[0270] Online platform transactions present challenges due to the complexity of the process, as sellers require specialized knowledge regarding product information and pricing, and communication across multiple languages ​​can be difficult. Furthermore, potential buyers struggle to find suitable products amidst a vast amount of information, hindering efficient transactions.

[0271] 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.

[0272] In this invention, the server includes means for automatically generating product information, means for analyzing product images to create product descriptions, means for researching market prices of similar products and proposing pricing, means for selecting and recommending products that meet the buyer's requirements using AI technology, and means for translating product descriptions and negotiation content between different languages. This enables both sellers and buyers to conduct transactions efficiently and smoothly.

[0273] "Means for automatically generating product information" refers to a mechanism that automatically creates detailed descriptions and features of a product without requiring user intervention.

[0274] "A method for analyzing product images to create product descriptions" refers to a system that analyzes the input image data of a product and expresses its characteristics and features as text.

[0275] "A method for researching market prices of similar products and proposing pricing" refers to a system that refers to existing market data, analyzes the prices of similar products, and shows users an appropriate selling price.

[0276] "Methods for recommending products to prospective buyers" refers to methods of presenting the most suitable products to users with purchasing intent based on their past behavior and specified conditions.

[0277] "A method of selecting products that meet the criteria using AI technology" refers to a process in which an artificial intelligence algorithm is used to narrow down the database of relevant products based on the criteria entered by the prospective buyer.

[0278] A "means of translating product descriptions between different languages" refers to a system that converts product descriptions into multiple languages ​​to facilitate smooth communication between users who speak different languages.

[0279] This invention is a system for a flea market platform that facilitates smooth and efficient transactions between sellers and prospective buyers. This system utilizes image recognition technology, natural language processing, price information analysis, and automatic translation technology to automate the tasks necessary for transactions.

[0280] The system starts when a user uses their device to take photos of the products they want to sell and uploads them to the application. The device then sends this image data to the server. The server analyzes the received images using image processing software such as TensorFlow or OpenCV to identify the product category and characteristics.

[0281] Based on the analysis results, the server generates a product description written in natural language using generative AI models such as GPT and BERT. This text is returned to the user's device and used as listing information.

[0282] The server then crawls market data on the Internet using tools such as BeautifulSoup and Scrapy to obtain the market prices of similar products. Based on the collected data, it calculates the appropriate selling price of the product and sends it to the user's terminal as a recommended price. This enables the user to obtain advantageous information in price setting.

[0283] When a potential buyer inputs the conditions of a product (e.g., size, price, etc.) into the terminal, the terminal receives this data and sends it to the server. The server uses AI technology to select products that match the conditions from the database and provides the user with optimal recommendation information.

[0284] Furthermore, the server uses an automatic translation function provided by Google Translate API or DeepL to translate product descriptions and negotiation content into different languages used by the user. This function facilitates transactions between users who speak different languages.

[0285] As a specific example, when a user takes a photo of a used jacket and uploads it to the system, the system generates a description such as "blue denim jacket, size M" and proposes it to the user. Also, based on past sales data, it indicates an appropriate price of "3,500 yen".

[0286] Examples of prompt texts can include content such as "I want to take a photo of a product and automatically identify its category and characteristics to generate a description in natural language. Also, I would like to get a proposed appropriate price for the market." This enables the system to automatically provide services according to the user's requirements.

[0287] The flow of the specific process in Example 1 will be described using FIG. 11.

[0288] Step 1:

[0289] The user takes product photos using their device and uploads them to the application. The input includes the image data taken by the user. The device receives this image data, performs a format conversion (e.g., to JPEG or PNG format), and sends it to the server via the internet.

[0290] Step 2:

[0291] The server analyzes image data received from the terminal. The input is product image data, which is then analyzed using an image recognition model (e.g., TensorFlow or OpenCV). Specifically, it performs feature point extraction and segmentation of the image to identify product categories and characteristics. The output generates product category information and feature data.

[0292] Step 3:

[0293] The server automatically generates product descriptions using a generative AI model (e.g., GPT, BERT) based on the information obtained from image analysis. The input consists of product category information and feature data. The server inputs this into a natural language generation model and generates a product description as output. Specifically, a description like "This product is a blue denim jacket, size M" is created.

[0294] Step 4:

[0295] The server crawls online market databases to collect price information for similar products. The input is a search query based on product category and characteristics. The server uses web scraping tools (e.g., BeautifulSoup, Scrapy) to search the database and collect historical price data. The output is the collected price information. Based on this, statistical analysis is performed to calculate a fair price.

[0296] Step 5:

[0297] The server sends the calculated fair price to the user's device. The input is fair price data. The server converts this price into a user-friendly format and sends a push notification to the device as output. The user uses this price information as a reference when listing their product.

[0298] Step 6:

[0299] The prospective buyer enters the desired product specifications into the terminal. These specifications include user-specified criteria (e.g., size M, price under 3,000 yen). The terminal then sends these specifications to the server.

[0300] Step 7:

[0301] The server searches its database based on the received conditions and uses AI technology (e.g., recommendation algorithms) to select products that meet those conditions. The input is the conditions of the prospective buyer, and the output is a list of recommended products. This list is sent to the user's terminal and displayed to the buyer.

[0302] Step 8:

[0303] The server uses an automatic translation function to translate product descriptions and negotiation details into different languages. The input is the product description written in the original language. The server uses the Google Translate API or DeepL to generate output translated into the required language. This translated information is sent to the device and displayed to the user.

[0304] (Application Example 1)

[0305] 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."

[0306] In an online shopping platform, the procedures between sellers and buyers are complicated, and there are barriers to international transactions due to the setting of appropriate product prices and the lack of multi-language support. Furthermore, it is necessary to solve the problem that it is difficult for potential buyers to quickly find products that meet the requirements.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0308] In this invention, the server includes means for automatically generating product information, means for analyzing product images to create product descriptions, means for investigating the market prices of similar products and proposing price settings, means for presenting optimal products by inputting product conditions, and means for translating product descriptions into multiple languages. As a result, sellers can list products at appropriate prices without much effort, potential buyers can quickly find products that meet their requirements, and international transactions can be carried out smoothly.

[0309] The "means for automatically generating product information" is a function that automatically creates descriptions and specifications related to products using artificial intelligence technology.

[0310] The "means for analyzing product images to create product descriptions" is a technology that analyzes product photos using image recognition algorithms and generates appropriate descriptions from the results.

[0311] The "means for investigating the market prices of similar products and proposing price settings" is a function that collects the prices of similar products by referring to the market database and presents the appropriate price of the product to the user based on that.

[0312] The "means for recommending products to potential buyers" is an algorithm that searches for products in the database based on the conditions specified by the buyer and presents the optimal options.

[0313] "Methods for translating product descriptions into multiple languages" refers to a function that automatically translates product descriptions to facilitate transactions between users who speak different languages.

[0314] "A means of presenting the most suitable product based on the input of product conditions" refers to a function that searches a database based on the conditions entered by the prospective buyer and presents the product that best matches those conditions.

[0315] The system for implementing this invention forms an online platform that streamlines product transactions for both sellers and prospective buyers. Specific embodiments of this system are shown below.

[0316] The server first receives product images input by the user and analyzes them using TensorFlow. Based on the product category and characteristic information obtained through image analysis, the server generates a product description using OpenAI's GPT API. This generated description is sent to the user's device and used as the listing content.

[0317] Next, the server uses Puppeteer to crawl market data and collect price information for similar products. Based on this information, it calculates a fair price and suggests it to the user.

[0318] When a prospective buyer enters product specifications into a terminal, those specifications are sent to a server. The server searches a database and selects products that match the specifications. This selected product information is then presented to the prospective buyer via the terminal to assist them in making a purchase decision.

[0319] Furthermore, the server uses the Google Cloud Translation API to translate product descriptions and negotiation details into multiple languages. This enables smooth transactions between different languages.

[0320] For example, if a user wants to list a "jacket" for sale, the server analyzes the image and generates a description such as, "This jacket is waterproof, size M, and features the latest design." It also suggests a fair price for the jacket and translates the product description into multiple languages, making it easier to appeal to international buyers.

[0321] An example of a prompt for a generative AI model would be: "This product is a jacket, it is waterproof, and the size is M. Please generate a detailed description based on this information."

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The user takes a picture of the product using their device and uploads it to the system. The input in this process is the product image, and the output is the transmission of the image data to the server.

[0325] Step 2:

[0326] The server analyzes the received images using TensorFlow. The input for image analysis is a product image, and data calculations are performed to identify the product category and characteristics, which are then obtained as output.

[0327] Step 3:

[0328] The server automatically generates a product description using the OpenAI GPT API based on the analysis results. In this step, the analysis results are used as input, and the product description is output.

[0329] Step 4:

[0330] The server sends the generated product description to the user's terminal. The input is the generated product description, and the output is the description displayed on the terminal.

[0331] Step 5:

[0332] The server uses Puppeteer to crawl market data and collect price information for similar products. Here, information on similar products is taken as input, and price information is output.

[0333] Step 6:

[0334] Based on the collected price information, the server calculates the appropriate price for the product and sends it to the user as a recommended price. The input is price information for similar products, and the output is recommended price information.

[0335] Step 7:

[0336] When a user enters product criteria into their terminal, the server receives the data and performs a database search. In this step, the server searches for the most suitable product based on the entered criteria and generates a list of candidate products as output.

[0337] Step 8:

[0338] The system displays a list of recommended products on the user's device to assist in the purchase selection process. The input is the recommended products, and the output is the list of candidates displayed to the user.

[0339] Step 9:

[0340] The server utilizes the Google Cloud Translation API to translate product descriptions into multiple languages. Here, the product description is taken as input, and the translated description is output.

[0341] Step 10:

[0342] Provide users with translated product descriptions and quickly implement multilingual support. The input is the translated description, and the output is the information displayed on the user's terminal.

[0343] 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.

[0344] This invention relates to an automated transaction support system configured to facilitate transactions on a flea market platform, and in particular, to a system that takes user emotions into consideration. This system aims to improve the experience for both sellers and buyers by utilizing AI technology.

[0345] When a user takes a product photo using their device and uploads it to the application, the server first analyzes the image. This analysis uses an image recognition algorithm to automatically identify the product's category and characteristics. The server then uses natural language processing technology to generate a product description, which is presented to the user via their device.

[0346] In parallel, the server crawls the market database, collecting and analyzing information on similar products on the internet. This allows sellers to easily set reasonable prices by calculating and suggesting appropriate prices to their terminals.

[0347] Furthermore, the server receives the search criteria of potential buyers and uses an AI algorithm to select and recommend products that match those criteria. This recommendation serves to support the decision-making process for potential buyers.

[0348] In addition, this invention integrates an emotion engine. The emotion engine analyzes the user's voice, facial expressions, and input patterns to determine their current emotional state. For example, if a user expresses dissatisfaction or frustration with the negotiation situation, the server detects this. Based on this, the negotiation strategy and price offer are adjusted to improve the user experience.

[0349] For example, if a user lists an expensive item and sales are stagnating, the emotion engine will detect the user's frustration. The server will then help move negotiations forward by suggesting alternative pricing strategies or offering assistance in preparing for negotiations. Furthermore, the system supports multiple languages, enabling smooth transactions between different countries.

[0350] This invention makes flea market transactions more intuitive and effective, and allows for flexible responses that respond to users' emotions.

[0351] The following describes the processing flow.

[0352] Step 1:

[0353] The user takes a product photo using their device and uploads it to the application. The device then sends this image to the server.

[0354] Step 2:

[0355] The server analyzes the received image data using an AI image recognition algorithm. It identifies product categories and characteristics, which then serve as the basis for product descriptions.

[0356] Step 3:

[0357] The server uses natural language processing technology to automatically generate a product description based on the analysis results. This description is then sent to the terminal and presented to the user.

[0358] Step 4:

[0359] The server crawls the market database, collecting and analyzing prices for similar products. Based on this information, it calculates a fair selling price and sends it to the terminal as a price suggestion.

[0360] Step 5:

[0361] Users can view product descriptions and price suggestions on their devices and edit them as needed. The edited product information is then registered on the flea market platform.

[0362] Step 6:

[0363] The prospective buyer enters product search criteria into their terminal. These criteria are then sent to the server.

[0364] Step 7:

[0365] The server uses an AI algorithm to search the database for products that match the specified criteria and sends the selected product information back to the terminal as a recommendation.

[0366] Step 8:

[0367] The server activates an emotion engine based on the voice, facial expressions, and input patterns obtained from the user to determine the user's emotional state.

[0368] Step 9:

[0369] Based on the emotions detected by the emotion engine, the server adjusts and sends transaction-related feedback and advice to the terminal.

[0370] Step 10:

[0371] The server uses its multilingual support function to automatically translate listing information and negotiation details as needed, facilitating smooth transactions between different languages.

[0372] (Example 2)

[0373] 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".

[0374] In online flea market transactions, generating product information, setting appropriate prices, and recommending items to potential buyers are often cumbersome processes. Furthermore, the need for flexible responses that consider the feelings of both sellers and buyers can sometimes lead to an inadequate user experience. Additionally, smooth transactions between users speaking different languages ​​are necessary.

[0375] 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.

[0376] In this invention, the server includes means for analyzing image data to identify product characteristics, means for creating product descriptions using natural language generation technology, means for collecting market information on the internet and calculating appropriate prices, means for recommending products based on the conditions of prospective buyers, and means for analyzing the user's emotional state and reflecting it in product recommendations. This enables automatic generation of product information, appropriate pricing, and the provision of flexible experiences based on emotions. Furthermore, it facilitates smooth transactions between multiple languages.

[0377] "Image data" refers to information that represents visual information in a digital format and can be processed by a computer.

[0378] "Product characteristics" refer to information that indicates the attributes and features of a product, and include the product's category, size, color, and brand.

[0379] "Natural language generation technology" is a technology that models human language to generate natural-sounding sentences, and is used as part of artificial intelligence.

[0380] "Market information" refers to data related to commercial transactions, such as product prices, demand trends, and inventory levels.

[0381] "Fair price" refers to a reasonable price range for a product, assessed based on market supply and demand.

[0382] "Prospective buyer" refers to an individual or group that is considering purchasing a product.

[0383] "Emotional state" refers to the user's current emotions and psychological state, and is determined by factors such as tone of voice, facial expressions, and input patterns.

[0384] "Product proposal" refers to the act of introducing a product to a user based on specific conditions.

[0385] Translation is the process of replacing expressions between different languages ​​without changing their meaning.

[0386] This invention is a system that facilitates transactions on an online flea market platform and integrates various technologies to improve the user experience. The core server of the system operates by combining image analysis, natural language generation, price calculation, recommendation systems, and sentiment analysis technologies.

[0387] Users take product photos using their devices and upload the image data to the server via the application. The server uses a common computer vision framework to analyze this image data. For example, it leverages deep learning libraries to extract image features and identify product characteristics.

[0388] The server generates a product description using natural language generation technology based on the identified product characteristics. This process utilizes a natural language processing framework known as a generative AI model to generate text data. For example, a prompt such as "Generate a product description. The product name is 'Vintage Record Player,' and the characteristics are 'Made in the 1960s, in good working order, antique finish'" might be used.

[0389] To determine a fair price for a product, the server collects market information from the internet and calculates the price. This involves using web scraping techniques to gather large amounts of market data and analyzing it through statistical models. As a result, it can propose a market price for the product to the user.

[0390] To recommend products that meet the criteria of potential buyers, the server takes into account past purchase history and preference data. An AI algorithm evaluates this data and displays products that are likely to be of interest. In addition, an emotion engine analyzes the user's emotional state and adjusts the recommendations according to the user's emotions.

[0391] The system also includes translation technology to facilitate smooth transactions between different languages. This feature streamlines communication between users and promotes international trade. As a result, using the flea market platform becomes more intuitive and effective.

[0392] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0393] Step 1:

[0394] The user takes a product photo using their device and uploads the image data to the server via the application. The input is the product image taken by the user with the camera, and the output is the image data received by the server. The server adds this data to a processing queue and prepares to perform analysis in the next step.

[0395] Step 2:

[0396] The server analyzes the image data. The input is the image data received in step 1. The server uses image recognition technology to extract features from the image and identify product characteristics. A deep learning model identifies the product and outputs category and characteristic information. For example, the image might be identified as "vintage audio equipment".

[0397] Step 3:

[0398] Based on the product characteristics identified by the server, a generative AI model is used to generate a product description using natural language generation technology. The input is the product characteristics obtained in step 2. The generative AI model is given characteristic information as a prompt and outputs a description such as, "This product is a vintage record player from the 1960s."

[0399] Step 4:

[0400] The server collects market data and calculates a fair price. The inputs are product characteristics and market information from the internet. The server uses web scraping techniques to collect price data for similar products from the internet. The collected data is analyzed using statistical methods and output price information such as "The estimated fair price is $100."

[0401] Step 5:

[0402] The server displays the generated product description and appropriate price on the terminal. The input is the information obtained in steps 3 and 4. The product description and appropriate price are displayed on the user's terminal to assist in product pricing.

[0403] Step 6:

[0404] The server receives the buyer's criteria and recommends products. The input is the buyer's search criteria data. An AI algorithm identifies products that match the search criteria and outputs a list of products that the buyer might be interested in, referencing past purchase data.

[0405] Step 7:

[0406] The server analyzes the user's emotional state and adjusts product recommendations accordingly. Input consists of user voice and facial expression data. An emotion engine analyzes this data and generates and outputs optimal product recommendations based on the user's emotions. This improves the user experience.

[0407] (Application Example 2)

[0408] 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."

[0409] Traditional flea market platforms have problems such as difficulties in smooth transactions between sellers and buyers, and challenges in properly classifying and pricing products. Furthermore, they lack the flexibility to respond to user emotions, resulting in a poor transaction experience.

[0410] 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.

[0411] In this invention, the server includes means for analyzing and classifying product images, means for evaluating image data and generating product descriptions, and means for collecting market information and estimating sales prices. This enables automatic product classification, appropriate pricing, and adjustment of sales strategies to suit user sentiment.

[0412] "Product image analysis" is a technology that uses software to process the visual data of items offered to the market, extracting and classifying their features.

[0413] "Picture data evaluation" is a technology that automatically generates descriptive text for objects based on images and related information, and clarifies the content of that text.

[0414] "Market information gathering" refers to the technique of collecting information on similar products from the internet and databases, and analyzing prices and supply and demand trends.

[0415] "Price estimation" is the process of calculating a reasonable price based on collected market information and proposing it to the seller.

[0416] "Adjusting sales strategies in response to user emotions" refers to a method of detecting the emotional state of users and dynamically changing negotiation policies and sales approaches accordingly.

[0417] To implement this invention, a system is required that combines a user's terminal, a server, and related software. First, the user takes a picture of a product using their smartphone's camera and uploads the image to an application on their terminal. This application automatically sends the image data to the server.

[0418] Upon receiving image data, the server analyzes the product images using image recognition software based on TensorFlow and determines their classification. Then, using a GPT model, it automatically generates an effective product description based on the analysis results. The generated description is sent to the user's device and displayed.

[0419] Furthermore, the server uses a Python scraping library to collect market information from the internet and analyzes the market database to estimate selling prices. This pricing information is provided to product sellers, enabling them to set appropriate prices.

[0420] After the user reviews the product description and price, the server runs an emotion analysis tool to determine the user's emotional state by analyzing their facial expressions using OpenCV and analyzing their voice. Based on the user's emotions, the server adjusts negotiation and sales strategies to optimize the user's transaction experience.

[0421] For example, if a user wants to sell a painting and takes a photo of the product, the program analyzes the image and classifies it as "painting," "art," or "landscape." The server then generates a product description such as, "Beautifully decorate your living room with this painting." An example of a prompt message would be, "Analyze the captured image, identify the main features of the product, and develop an emotionally resonant sales strategy."

[0422] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0423] Step 1:

[0424] The user takes a picture of the product they want to sell using their device's camera. This image is uploaded to the application on the device. The input is the image data of the product, and the output is the data sent to the server.

[0425] Step 2:

[0426] The terminal sends the uploaded image data to the server. The server inputs the received image data into an image recognition algorithm using TensorFlow. This analyzes the product image and obtains its classification information. The output is product category data.

[0427] Step 3:

[0428] The server uses a GPT model based on image recognition results to generate a product description. The input is product category data, and the output is an automatically generated product description. The generated description is sent to the terminal and displayed to the user.

[0429] Step 4:

[0430] The server uses a Python scraping library to collect market information from the internet. The input is a search query related to a product, and the output is market data including pricing information for similar products. Based on this data, it estimates the selling price and provides the price information to the user's terminal.

[0431] Step 5:

[0432] After the user reviews the product description and price, the server uses OpenCV-based facial expression and voice analysis tools to determine the user's emotional state based on their facial expressions and voice data. The output is the user's emotional evaluation data. Based on this data, the server adjusts its sales strategy and provides the user with necessary information.

[0433] Step 6:

[0434] The server optimizes negotiation strategies based on the user's emotions and generates prompts for an AI model within the system. The input is the user's emotion rating data, and the output is a refined sales or negotiation strategy. This strategy is sent to the terminal to support the user's next action.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Third Embodiment]

[0439] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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".

[0451] This invention provides a system that simplifies transactions on a flea market platform for both sellers and buyers. This system utilizes AI technology to automate many transaction-related tasks.

[0452] The system starts when the user takes product photos using their device and uploads them to the application. The server analyzes the received image data using advanced image recognition algorithms to identify the product category and characteristics. Based on this information, the server automatically generates a product description using natural language processing technology. This product description is sent back to the user's device and used as the listing content.

[0453] Furthermore, the server crawls the market database and collects market prices for similar products based on publicly available information on the internet. Based on this data, the server calculates a fair price for the product and sends it to the terminal as a valuable suggestion. This suggestion serves as a reference for the user and helps them set an appropriate selling price.

[0454] For prospective buyers, users enter their desired product criteria into a terminal, which is then received by a server. AI is applied to search the database and select products that match the criteria. Once selected, the products are provided to the user as recommendation information via the terminal. This process supports the prospective buyer's selection and increases the likelihood of a successful transaction.

[0455] Furthermore, to facilitate transactions between different languages, the server uses an automatic translation function to translate product descriptions and negotiation details into multiple languages. This function provides an environment where transactions can be conducted smoothly even in global markets.

[0456] For example, when a user takes a photo of a jacket and lists it for sale, they can immediately register it and start selling based on the system's automatically generated description and suggested price. If a potential buyer enters their criteria, jackets that match their size and price will be recommended, allowing them to proceed with the purchase efficiently.

[0457] These features improve efficiency and satisfaction for both sellers and buyers when using the flea market app.

[0458] The following describes the processing flow.

[0459] Step 1:

[0460] The user takes a product photo using their device and uploads it to the application. The device then sends this image data to the server.

[0461] Step 2:

[0462] The server analyzes the received images. It uses AI image recognition algorithms to identify the product's category and characteristics.

[0463] Step 3:

[0464] The server automatically generates a product description using natural language processing technology based on the analysis results. This description is sent to the terminal, and the user is asked to confirm it.

[0465] Step 4:

[0466] The server crawls the market database, collecting and analyzing price information for similar products. Based on this, the server calculates a recommended selling price and sends it to the terminal as a suggestion.

[0467] Step 5:

[0468] The user reviews the product description and suggested price generated on their device and edits them as needed. Finally, the product information is registered on the flea market platform according to the user's instructions.

[0469] Step 6:

[0470] The prospective buyer enters product search criteria on their device. The device then sends this information to the server.

[0471] Step 7:

[0472] The server searches the database based on the specified criteria and selects suitable products. The selected product information is sent to the terminal and provided to the prospective buyer as recommendation information.

[0473] Step 8:

[0474] If the server requires multilingual support, it will automatically translate product descriptions and negotiation details into the necessary languages.

[0475] Step 9:

[0476] If the server is in a global market or if price negotiation is necessary, the system provides users with price negotiation advice based on data. Users then use this information to negotiate.

[0477] (Example 1)

[0478] 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."

[0479] Online platform transactions present challenges due to the complexity of the process, as sellers require specialized knowledge regarding product information and pricing, and communication across multiple languages ​​can be difficult. Furthermore, potential buyers struggle to find suitable products amidst a vast amount of information, hindering efficient transactions.

[0480] 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.

[0481] In this invention, the server includes means for automatically generating product information, means for analyzing product images to create product descriptions, means for researching market prices of similar products and proposing pricing, means for selecting and recommending products that meet the buyer's requirements using AI technology, and means for translating product descriptions and negotiation content between different languages. This enables both sellers and buyers to conduct transactions efficiently and smoothly.

[0482] "Means for automatically generating product information" refers to a mechanism that automatically creates detailed descriptions and features of a product without requiring user intervention.

[0483] "A method for analyzing product images to create product descriptions" refers to a system that analyzes the input image data of a product and expresses its characteristics and features as text.

[0484] "A method for researching market prices of similar products and proposing pricing" refers to a system that refers to existing market data, analyzes the prices of similar products, and shows users an appropriate selling price.

[0485] "Methods for recommending products to prospective buyers" refers to methods of presenting the most suitable products to users with purchasing intent based on their past behavior and specified conditions.

[0486] "A method of selecting products that meet the criteria using AI technology" refers to a process in which an artificial intelligence algorithm is used to narrow down the database of relevant products based on the criteria entered by the prospective buyer.

[0487] A "means of translating product descriptions between different languages" refers to a system that converts product descriptions into multiple languages ​​to facilitate smooth communication between users who speak different languages.

[0488] This invention is a system for a flea market platform that facilitates smooth and efficient transactions between sellers and prospective buyers. This system utilizes image recognition technology, natural language processing, price information analysis, and automatic translation technology to automate the tasks necessary for transactions.

[0489] The system starts when a user uses their device to take photos of the products they want to sell and uploads them to the application. The device then sends this image data to the server. The server analyzes the received images using image processing software such as TensorFlow or OpenCV to identify the product category and characteristics.

[0490] Based on the analysis results, the server generates a product description written in natural language using generative AI models such as GPT and BERT. This text is returned to the user's device and used as listing information.

[0491] The server then uses tools like BeautifulSoup and Scrapy to crawl market data on the internet and retrieve market prices for similar products. Based on the collected data, it calculates a fair selling price for the product and sends it to the user's device as a recommended price. This allows the user to obtain advantageous information when setting prices.

[0492] When a prospective buyer enters product specifications (e.g., size, price) into a terminal, the terminal receives this data and sends it to a server. The server uses AI technology to select products that match the specifications from its database and provides the user with the most suitable recommendation information.

[0493] Furthermore, the server uses the Google Translate API and DeepL's automatic translation function to translate product descriptions and negotiation details into the user's preferred language. This feature facilitates transactions between users who speak different languages.

[0494] For example, when a user takes a photo of a used jacket and uploads it to the system, the system generates a description such as "Blue denim jacket, size M" and suggests it to the user. It also suggests a fair price of "3,500 yen" based on past sales data.

[0495] An example of a prompt message might be: "I would like to take product photos, automatically identify the category and characteristics, and generate a description in natural language. I would also like you to suggest a fair market price." This allows the system to automatically provide services that meet the user's needs.

[0496] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0497] Step 1:

[0498] The user takes product photos using their device and uploads them to the application. The input includes the image data taken by the user. The device receives this image data, performs a format conversion (e.g., to JPEG or PNG format), and sends it to the server via the internet.

[0499] Step 2:

[0500] The server analyzes image data received from the terminal. The input is product image data, which is then analyzed using an image recognition model (e.g., TensorFlow or OpenCV). Specifically, it performs feature point extraction and segmentation of the image to identify product categories and characteristics. The output generates product category information and feature data.

[0501] Step 3:

[0502] The server automatically generates product descriptions using a generative AI model (e.g., GPT, BERT) based on the information obtained from image analysis. The input consists of product category information and feature data. The server inputs this into a natural language generation model and generates a product description as output. Specifically, a description like "This product is a blue denim jacket, size M" is created.

[0503] Step 4:

[0504] The server crawls online market databases to collect price information for similar products. The input is a search query based on product category and characteristics. The server uses web scraping tools (e.g., BeautifulSoup, Scrapy) to search the database and collect historical price data. The output is the collected price information. Based on this, statistical analysis is performed to calculate a fair price.

[0505] Step 5:

[0506] The server sends the calculated fair price to the user's device. The input is fair price data. The server converts this price into a user-friendly format and sends a push notification to the device as output. The user uses this price information as a reference when listing their product.

[0507] Step 6:

[0508] The prospective buyer enters the desired product specifications into the terminal. These specifications include user-specified criteria (e.g., size M, price under 3,000 yen). The terminal then sends these specifications to the server.

[0509] Step 7:

[0510] The server searches its database based on the received conditions and uses AI technology (e.g., recommendation algorithms) to select products that meet those conditions. The input is the conditions of the prospective buyer, and the output is a list of recommended products. This list is sent to the user's terminal and displayed to the buyer.

[0511] Step 8:

[0512] The server uses an automatic translation function to translate product descriptions and negotiation details into different languages. The input is the product description written in the original language. The server uses the Google Translate API or DeepL to generate output translated into the required language. This translated information is sent to the device and displayed to the user.

[0513] (Application Example 1)

[0514] 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."

[0515] Online shopping platforms face challenges such as cumbersome procedures between sellers and buyers, difficulty in setting fair prices, and barriers to international trade due to insufficient multilingual support. Furthermore, there is a need to address the difficulty buyers face in quickly finding products that meet their requirements.

[0516] 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.

[0517] In this invention, the server includes means for automatically generating product information, means for analyzing product images to create product descriptions, means for researching market prices of similar products and suggesting pricing, means for presenting the most suitable product based on input product conditions, and means for translating product descriptions into multiple languages. This enables sellers to list products at a fair price without hassle, allows prospective buyers to quickly find products that meet their desired conditions, and facilitates smooth international transactions.

[0518] "Means for automatically generating product information" refers to a function that automatically creates product descriptions and specifications using artificial intelligence technology.

[0519] "A method for analyzing product images and creating product descriptions" refers to a technology that uses image recognition algorithms to analyze product photos and generates appropriate descriptions from the results.

[0520] "A means of researching market prices for similar products and proposing pricing" refers to a function that collects prices for similar products by referring to a market database and then presents a fair price for the product to the user based on that data.

[0521] "A method for recommending products to prospective buyers" refers to an algorithm that searches a database for products based on the conditions specified by the buyer and presents the most suitable options.

[0522] "Methods for translating product descriptions into multiple languages" refers to a function that automatically translates product descriptions to facilitate transactions between users who speak different languages.

[0523] "A means of presenting the most suitable product based on the input of product conditions" refers to a function that searches a database based on the conditions entered by the prospective buyer and presents the product that best matches those conditions.

[0524] The system for implementing this invention forms an online platform that streamlines product transactions for both sellers and prospective buyers. Specific embodiments of this system are shown below.

[0525] The server first receives product images input by the user and analyzes them using TensorFlow. Based on the product category and characteristic information obtained through image analysis, the server generates a product description using OpenAI's GPT API. This generated description is sent to the user's device and used as the listing content.

[0526] Next, the server uses Puppeteer to crawl market data and collect price information for similar products. Based on this information, it calculates a fair price and suggests it to the user.

[0527] When a prospective buyer enters product specifications into a terminal, those specifications are sent to a server. The server searches a database and selects products that match the specifications. This selected product information is then presented to the prospective buyer via the terminal to assist them in making a purchase decision.

[0528] Furthermore, the server uses the Google Cloud Translation API to translate product descriptions and negotiation details into multiple languages. This enables smooth transactions between different languages.

[0529] For example, if a user wants to list a "jacket" for sale, the server analyzes the image and generates a description such as, "This jacket is waterproof, size M, and features the latest design." It also suggests a fair price for the jacket and translates the product description into multiple languages, making it easier to appeal to international buyers.

[0530] An example of a prompt for a generative AI model would be: "This product is a jacket, it is waterproof, and the size is M. Please generate a detailed description based on this information."

[0531] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0532] Step 1:

[0533] The user takes a picture of the product using their device and uploads it to the system. The input in this process is the product image, and the output is the transmission of the image data to the server.

[0534] Step 2:

[0535] The server analyzes the received images using TensorFlow. The input for image analysis is a product image, and data calculations are performed to identify the product category and characteristics, which are then obtained as output.

[0536] Step 3:

[0537] The server automatically generates a product description using the OpenAI GPT API based on the analysis results. In this step, the analysis results are used as input, and the product description is output.

[0538] Step 4:

[0539] The server sends the generated product description to the user's terminal. The input is the generated product description, and the output is the description displayed on the terminal.

[0540] Step 5:

[0541] The server uses Puppeteer to crawl market data and collect price information for similar products. Here, information on similar products is taken as input, and price information is output.

[0542] Step 6:

[0543] Based on the collected price information, the server calculates the appropriate price for the product and sends it to the user as a recommended price. The input is price information for similar products, and the output is recommended price information.

[0544] Step 7:

[0545] When a user enters product criteria into their terminal, the server receives the data and performs a database search. In this step, the server searches for the most suitable product based on the entered criteria and generates a list of candidate products as output.

[0546] Step 8:

[0547] The system displays a list of recommended products on the user's device to assist in the purchase selection process. The input is the recommended products, and the output is the list of candidates displayed to the user.

[0548] Step 9:

[0549] The server utilizes the Google Cloud Translation API to translate product descriptions into multiple languages. Here, the product description is taken as input, and the translated description is output.

[0550] Step 10:

[0551] Provide users with translated product descriptions and quickly implement multilingual support. The input is the translated description, and the output is the information displayed on the user's terminal.

[0552] 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.

[0553] This invention relates to an automated transaction support system configured to facilitate transactions on a flea market platform, and in particular, to a system that takes user emotions into consideration. This system aims to improve the experience for both sellers and buyers by utilizing AI technology.

[0554] When a user takes a product photo using their device and uploads it to the application, the server first analyzes the image. This analysis uses an image recognition algorithm to automatically identify the product's category and characteristics. The server then uses natural language processing technology to generate a product description, which is presented to the user via their device.

[0555] In parallel, the server crawls the market database, collecting and analyzing information on similar products on the internet. This allows sellers to easily set reasonable prices by calculating and suggesting appropriate prices to their terminals.

[0556] Furthermore, the server receives the search criteria of potential buyers and uses an AI algorithm to select and recommend products that match those criteria. This recommendation serves to support the decision-making process for potential buyers.

[0557] In addition, this invention integrates an emotion engine. The emotion engine analyzes the user's voice, facial expressions, and input patterns to determine their current emotional state. For example, if a user expresses dissatisfaction or frustration with the negotiation situation, the server detects this. Based on this, the negotiation strategy and price offer are adjusted to improve the user experience.

[0558] For example, if a user lists an expensive item and sales are stagnating, the emotion engine will detect the user's frustration. The server will then help move negotiations forward by suggesting alternative pricing strategies or offering assistance in preparing for negotiations. Furthermore, the system supports multiple languages, enabling smooth transactions between different countries.

[0559] This invention makes flea market transactions more intuitive and effective, and allows for flexible responses that respond to users' emotions.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] The user takes a product photo using their device and uploads it to the application. The device then sends this image to the server.

[0563] Step 2:

[0564] The server analyzes the received image data using an AI image recognition algorithm. It identifies product categories and characteristics, which then serve as the basis for product descriptions.

[0565] Step 3:

[0566] The server uses natural language processing technology to automatically generate a product description based on the analysis results. This description is then sent to the terminal and presented to the user.

[0567] Step 4:

[0568] The server crawls the market database, collecting and analyzing prices for similar products. Based on this information, it calculates a fair selling price and sends it to the terminal as a price suggestion.

[0569] Step 5:

[0570] Users can view product descriptions and price suggestions on their devices and edit them as needed. The edited product information is then registered on the flea market platform.

[0571] Step 6:

[0572] The prospective buyer enters product search criteria into their terminal. These criteria are then sent to the server.

[0573] Step 7:

[0574] The server uses an AI algorithm to search the database for products that match the specified criteria and sends the selected product information back to the terminal as a recommendation.

[0575] Step 8:

[0576] The server activates an emotion engine based on the voice, facial expressions, and input patterns obtained from the user to determine the user's emotional state.

[0577] Step 9:

[0578] Based on the emotions detected by the emotion engine, the server adjusts and sends transaction-related feedback and advice to the terminal.

[0579] Step 10:

[0580] The server uses its multilingual support function to automatically translate listing information and negotiation details as needed, facilitating smooth transactions between different languages.

[0581] (Example 2)

[0582] 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."

[0583] In online flea market transactions, generating product information, setting appropriate prices, and recommending items to potential buyers are often cumbersome processes. Furthermore, the need for flexible responses that consider the feelings of both sellers and buyers can sometimes lead to an inadequate user experience. Additionally, smooth transactions between users speaking different languages ​​are necessary.

[0584] 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.

[0585] In this invention, the server includes means for analyzing image data to identify product characteristics, means for creating product descriptions using natural language generation technology, means for collecting market information on the internet and calculating appropriate prices, means for recommending products based on the conditions of prospective buyers, and means for analyzing the user's emotional state and reflecting it in product recommendations. This enables automatic generation of product information, appropriate pricing, and the provision of flexible experiences based on emotions. Furthermore, it facilitates smooth transactions between multiple languages.

[0586] "Image data" refers to information that represents visual information in a digital format and can be processed by a computer.

[0587] "Product characteristics" refer to information that indicates the attributes and features of a product, and include the product's category, size, color, and brand.

[0588] "Natural language generation technology" is a technology that models human language to generate natural-sounding sentences, and is used as part of artificial intelligence.

[0589] "Market information" refers to data related to commercial transactions, such as product prices, demand trends, and inventory levels.

[0590] "Fair price" refers to a reasonable price range for a product, assessed based on market supply and demand.

[0591] "Prospective buyer" refers to an individual or group that is considering purchasing a product.

[0592] "Emotional state" refers to the user's current emotions and psychological state, and is determined by factors such as tone of voice, facial expressions, and input patterns.

[0593] "Product proposal" refers to the act of introducing a product to a user based on specific conditions.

[0594] Translation is the process of replacing expressions between different languages ​​without changing their meaning.

[0595] This invention is a system that facilitates transactions on an online flea market platform and integrates various technologies to improve the user experience. The core server of the system operates by combining image analysis, natural language generation, price calculation, recommendation systems, and sentiment analysis technologies.

[0596] Users take product photos using their devices and upload the image data to the server via the application. The server uses a common computer vision framework to analyze this image data. For example, it leverages deep learning libraries to extract image features and identify product characteristics.

[0597] The server generates a product description using natural language generation technology based on the identified product characteristics. This process utilizes a natural language processing framework known as a generative AI model to generate text data. For example, a prompt such as "Generate a product description. The product name is 'Vintage Record Player,' and the characteristics are 'Made in the 1960s, in good working order, antique finish'" might be used.

[0598] To determine a fair price for a product, the server collects market information from the internet and calculates the price. This involves using web scraping techniques to gather large amounts of market data and analyzing it through statistical models. As a result, it can propose a market price for the product to the user.

[0599] To recommend products that meet the criteria of potential buyers, the server takes into account past purchase history and preference data. An AI algorithm evaluates this data and displays products that are likely to be of interest. In addition, an emotion engine analyzes the user's emotional state and adjusts the recommendations according to the user's emotions.

[0600] The system also includes translation technology to facilitate smooth transactions between different languages. This feature streamlines communication between users and promotes international trade. As a result, using the flea market platform becomes more intuitive and effective.

[0601] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0602] Step 1:

[0603] The user takes a product photo using their device and uploads the image data to the server via the application. The input is the product image taken by the user with the camera, and the output is the image data received by the server. The server adds this data to a processing queue and prepares to perform analysis in the next step.

[0604] Step 2:

[0605] The server analyzes the image data. The input is the image data received in step 1. The server uses image recognition technology to extract features from the image and identify product characteristics. A deep learning model identifies the product and outputs category and characteristic information. For example, the image might be identified as "vintage audio equipment".

[0606] Step 3:

[0607] Based on the product characteristics identified by the server, a generative AI model is used to generate a product description using natural language generation technology. The input is the product characteristics obtained in step 2. The generative AI model is given characteristic information as a prompt and outputs a description such as, "This product is a vintage record player from the 1960s."

[0608] Step 4:

[0609] The server collects market data and calculates a fair price. The inputs are product characteristics and market information from the internet. The server uses web scraping techniques to collect price data for similar products from the internet. The collected data is analyzed using statistical methods and output price information such as "The estimated fair price is $100."

[0610] Step 5:

[0611] The server displays the generated product description and appropriate price on the terminal. The input is the information obtained in steps 3 and 4. The product description and appropriate price are displayed on the user's terminal to assist in product pricing.

[0612] Step 6:

[0613] The server receives the buyer's criteria and recommends products. The input is the buyer's search criteria data. An AI algorithm identifies products that match the search criteria and outputs a list of products that the buyer might be interested in, referencing past purchase data.

[0614] Step 7:

[0615] The server analyzes the user's emotional state and adjusts product recommendations accordingly. Input consists of user voice and facial expression data. An emotion engine analyzes this data and generates and outputs optimal product recommendations based on the user's emotions. This improves the user experience.

[0616] (Application Example 2)

[0617] 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."

[0618] Traditional flea market platforms have problems such as difficulties in smooth transactions between sellers and buyers, and challenges in properly classifying and pricing products. Furthermore, they lack the flexibility to respond to user emotions, resulting in a poor transaction experience.

[0619] 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.

[0620] In this invention, the server includes means for analyzing and classifying product images, means for evaluating image data and generating product descriptions, and means for collecting market information and estimating sales prices. This enables automatic product classification, appropriate pricing, and adjustment of sales strategies to suit user sentiment.

[0621] "Product image analysis" is a technology that uses software to process the visual data of items offered to the market, extracting and classifying their features.

[0622] "Picture data evaluation" is a technology that automatically generates descriptive text for objects based on images and related information, and clarifies the content of that text.

[0623] "Market information gathering" refers to the technique of collecting information on similar products from the internet and databases, and analyzing prices and supply and demand trends.

[0624] "Price estimation" is the process of calculating a reasonable price based on collected market information and proposing it to the seller.

[0625] "Adjusting sales strategies in response to user emotions" refers to a method of detecting the emotional state of users and dynamically changing negotiation policies and sales approaches accordingly.

[0626] To implement this invention, a system is required that combines a user's terminal, a server, and related software. First, the user takes a picture of a product using their smartphone's camera and uploads the image to an application on their terminal. This application automatically sends the image data to the server.

[0627] Upon receiving image data, the server analyzes the product images using image recognition software based on TensorFlow and determines their classification. Then, using a GPT model, it automatically generates an effective product description based on the analysis results. The generated description is sent to the user's device and displayed.

[0628] Furthermore, the server uses a Python scraping library to collect market information from the internet and analyzes the market database to estimate selling prices. This pricing information is provided to product sellers, enabling them to set appropriate prices.

[0629] After the user reviews the product description and price, the server runs an emotion analysis tool to determine the user's emotional state by analyzing their facial expressions using OpenCV and analyzing their voice. Based on the user's emotions, the server adjusts negotiation and sales strategies to optimize the user's transaction experience.

[0630] For example, if a user wants to sell a painting and takes a photo of the product, the program analyzes the image and classifies it as "painting," "art," or "landscape." The server then generates a product description such as, "Beautifully decorate your living room with this painting." An example of a prompt message would be, "Analyze the captured image, identify the main features of the product, and develop an emotionally resonant sales strategy."

[0631] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0632] Step 1:

[0633] The user takes a picture of the product they want to sell using their device's camera. This image is uploaded to the application on the device. The input is the image data of the product, and the output is the data sent to the server.

[0634] Step 2:

[0635] The terminal sends the uploaded image data to the server. The server inputs the received image data into an image recognition algorithm using TensorFlow. This analyzes the product image and obtains its classification information. The output is product category data.

[0636] Step 3:

[0637] The server uses a GPT model based on image recognition results to generate a product description. The input is product category data, and the output is an automatically generated product description. The generated description is sent to the terminal and displayed to the user.

[0638] Step 4:

[0639] The server uses a Python scraping library to collect market information from the internet. The input is a search query related to a product, and the output is market data including pricing information for similar products. Based on this data, it estimates the selling price and provides the price information to the user's terminal.

[0640] Step 5:

[0641] After the user reviews the product description and price, the server uses OpenCV-based facial expression and voice analysis tools to determine the user's emotional state based on their facial expressions and voice data. The output is the user's emotional evaluation data. Based on this data, the server adjusts its sales strategy and provides the user with necessary information.

[0642] Step 6:

[0643] The server optimizes negotiation strategies based on the user's emotions and generates prompts for an AI model within the system. The input is the user's emotion rating data, and the output is a refined sales or negotiation strategy. This strategy is sent to the terminal to support the user's next action.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] [Fourth Embodiment]

[0648] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0649] 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.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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).

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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".

[0661] This invention provides a system that simplifies transactions on a flea market platform for both sellers and buyers. This system utilizes AI technology to automate many transaction-related tasks.

[0662] The system starts when the user takes product photos using their device and uploads them to the application. The server analyzes the received image data using advanced image recognition algorithms to identify the product category and characteristics. Based on this information, the server automatically generates a product description using natural language processing technology. This product description is sent back to the user's device and used as the listing content.

[0663] Furthermore, the server crawls the market database and collects market prices for similar products based on publicly available information on the internet. Based on this data, the server calculates a fair price for the product and sends it to the terminal as a valuable suggestion. This suggestion serves as a reference for the user and helps them set an appropriate selling price.

[0664] For prospective buyers, users enter their desired product criteria into a terminal, which is then received by a server. AI is applied to search the database and select products that match the criteria. Once selected, the products are provided to the user as recommendation information via the terminal. This process supports the prospective buyer's selection and increases the likelihood of a successful transaction.

[0665] Furthermore, to facilitate transactions between different languages, the server uses an automatic translation function to translate product descriptions and negotiation details into multiple languages. This function provides an environment where transactions can be conducted smoothly even in global markets.

[0666] For example, when a user takes a photo of a jacket and lists it for sale, they can immediately register it and start selling based on the system's automatically generated description and suggested price. If a potential buyer enters their criteria, jackets that match their size and price will be recommended, allowing them to proceed with the purchase efficiently.

[0667] These features improve efficiency and satisfaction for both sellers and buyers when using the flea market app.

[0668] The following describes the processing flow.

[0669] Step 1:

[0670] The user takes a product photo using their device and uploads it to the application. The device then sends this image data to the server.

[0671] Step 2:

[0672] The server analyzes the received images. It uses AI image recognition algorithms to identify the product's category and characteristics.

[0673] Step 3:

[0674] The server automatically generates a product description using natural language processing technology based on the analysis results. This description is sent to the terminal, and the user is asked to confirm it.

[0675] Step 4:

[0676] The server crawls the market database, collecting and analyzing price information for similar products. Based on this, the server calculates a recommended selling price and sends it to the terminal as a suggestion.

[0677] Step 5:

[0678] The user reviews the product description and suggested price generated on their device and edits them as needed. Finally, the product information is registered on the flea market platform according to the user's instructions.

[0679] Step 6:

[0680] The prospective buyer enters product search criteria on their device. The device then sends this information to the server.

[0681] Step 7:

[0682] The server searches the database based on the specified criteria and selects suitable products. The selected product information is sent to the terminal and provided to the prospective buyer as recommendation information.

[0683] Step 8:

[0684] If the server requires multilingual support, it will automatically translate product descriptions and negotiation details into the necessary languages.

[0685] Step 9:

[0686] If the server is in a global market or if price negotiation is necessary, the system provides users with price negotiation advice based on data. Users then use this information to negotiate.

[0687] (Example 1)

[0688] 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".

[0689] Online platform transactions present challenges due to the complexity of the process, as sellers require specialized knowledge regarding product information and pricing, and communication across multiple languages ​​can be difficult. Furthermore, potential buyers struggle to find suitable products amidst a vast amount of information, hindering efficient transactions.

[0690] 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.

[0691] In this invention, the server includes means for automatically generating product information, means for analyzing product images to create product descriptions, means for researching market prices of similar products and proposing pricing, means for selecting and recommending products that meet the buyer's requirements using AI technology, and means for translating product descriptions and negotiation content between different languages. This enables both sellers and buyers to conduct transactions efficiently and smoothly.

[0692] "Means for automatically generating product information" refers to a mechanism that automatically creates detailed descriptions and features of a product without requiring user intervention.

[0693] "A method for analyzing product images to create product descriptions" refers to a system that analyzes the input image data of a product and expresses its characteristics and features as text.

[0694] "A method for researching market prices of similar products and proposing pricing" refers to a system that refers to existing market data, analyzes the prices of similar products, and shows users an appropriate selling price.

[0695] "Methods for recommending products to prospective buyers" refers to methods of presenting the most suitable products to users with purchasing intent based on their past behavior and specified conditions.

[0696] "A method of selecting products that meet the criteria using AI technology" refers to a process in which an artificial intelligence algorithm is used to narrow down the database of relevant products based on the criteria entered by the prospective buyer.

[0697] A "means of translating product descriptions between different languages" refers to a system that converts product descriptions into multiple languages ​​to facilitate smooth communication between users who speak different languages.

[0698] This invention is a system for a flea market platform that facilitates smooth and efficient transactions between sellers and prospective buyers. This system utilizes image recognition technology, natural language processing, price information analysis, and automatic translation technology to automate the tasks necessary for transactions.

[0699] The system starts when a user uses their device to take photos of the products they want to sell and uploads them to the application. The device then sends this image data to the server. The server analyzes the received images using image processing software such as TensorFlow or OpenCV to identify the product category and characteristics.

[0700] Based on the analysis results, the server generates a product description written in natural language using generative AI models such as GPT and BERT. This text is returned to the user's device and used as listing information.

[0701] The server then uses tools like BeautifulSoup and Scrapy to crawl market data on the internet and retrieve market prices for similar products. Based on the collected data, it calculates a fair selling price for the product and sends it to the user's device as a recommended price. This allows the user to obtain advantageous information when setting prices.

[0702] When a prospective buyer enters product specifications (e.g., size, price) into a terminal, the terminal receives this data and sends it to a server. The server uses AI technology to select products that match the specifications from its database and provides the user with the most suitable recommendation information.

[0703] Furthermore, the server uses the Google Translate API and DeepL's automatic translation function to translate product descriptions and negotiation details into the user's preferred language. This feature facilitates transactions between users who speak different languages.

[0704] For example, when a user takes a photo of a used jacket and uploads it to the system, the system generates a description such as "Blue denim jacket, size M" and suggests it to the user. It also suggests a fair price of "3,500 yen" based on past sales data.

[0705] An example of a prompt message might be: "I would like to take product photos, automatically identify the category and characteristics, and generate a description in natural language. I would also like you to suggest a fair market price." This allows the system to automatically provide services that meet the user's needs.

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Step 1:

[0708] The user takes product photos using their device and uploads them to the application. The input includes the image data taken by the user. The device receives this image data, performs a format conversion (e.g., to JPEG or PNG format), and sends it to the server via the internet.

[0709] Step 2:

[0710] The server analyzes image data received from the terminal. The input is product image data, which is then analyzed using an image recognition model (e.g., TensorFlow or OpenCV). Specifically, it performs feature point extraction and segmentation of the image to identify product categories and characteristics. The output generates product category information and feature data.

[0711] Step 3:

[0712] The server automatically generates product descriptions using a generative AI model (e.g., GPT, BERT) based on the information obtained from image analysis. The input consists of product category information and feature data. The server inputs this into a natural language generation model and generates a product description as output. Specifically, a description like "This product is a blue denim jacket, size M" is created.

[0713] Step 4:

[0714] The server crawls online market databases to collect price information for similar products. The input is a search query based on product category and characteristics. The server uses web scraping tools (e.g., BeautifulSoup, Scrapy) to search the database and collect historical price data. The output is the collected price information. Based on this, statistical analysis is performed to calculate a fair price.

[0715] Step 5:

[0716] The server sends the calculated fair price to the user's device. The input is fair price data. The server converts this price into a user-friendly format and sends a push notification to the device as output. The user uses this price information as a reference when listing their product.

[0717] Step 6:

[0718] The prospective buyer enters the desired product specifications into the terminal. These specifications include user-specified criteria (e.g., size M, price under 3,000 yen). The terminal then sends these specifications to the server.

[0719] Step 7:

[0720] The server searches its database based on the received conditions and uses AI technology (e.g., recommendation algorithms) to select products that meet those conditions. The input is the conditions of the prospective buyer, and the output is a list of recommended products. This list is sent to the user's terminal and displayed to the buyer.

[0721] Step 8:

[0722] The server uses an automatic translation function to translate product descriptions and negotiation details into different languages. The input is the product description written in the original language. The server uses the Google Translate API or DeepL to generate output translated into the required language. This translated information is sent to the device and displayed to the user.

[0723] (Application Example 1)

[0724] 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".

[0725] Online shopping platforms face challenges such as cumbersome procedures between sellers and buyers, difficulty in setting fair prices, and barriers to international trade due to insufficient multilingual support. Furthermore, there is a need to address the difficulty buyers face in quickly finding products that meet their requirements.

[0726] 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.

[0727] In this invention, the server includes means for automatically generating product information, means for analyzing product images to create product descriptions, means for researching market prices of similar products and suggesting pricing, means for presenting the most suitable product based on input product conditions, and means for translating product descriptions into multiple languages. This enables sellers to list products at a fair price without hassle, allows prospective buyers to quickly find products that meet their desired conditions, and facilitates smooth international transactions.

[0728] "Means for automatically generating product information" refers to a function that automatically creates product descriptions and specifications using artificial intelligence technology.

[0729] "A method for analyzing product images and creating product descriptions" refers to a technology that uses image recognition algorithms to analyze product photos and generates appropriate descriptions from the results.

[0730] "A means of researching market prices for similar products and proposing pricing" refers to a function that collects prices for similar products by referring to a market database and then presents a fair price for the product to the user based on that data.

[0731] "A method for recommending products to prospective buyers" refers to an algorithm that searches a database for products based on the conditions specified by the buyer and presents the most suitable options.

[0732] "Methods for translating product descriptions into multiple languages" refers to a function that automatically translates product descriptions to facilitate transactions between users who speak different languages.

[0733] "A means of presenting the most suitable product based on the input of product conditions" refers to a function that searches a database based on the conditions entered by the prospective buyer and presents the product that best matches those conditions.

[0734] The system for implementing this invention forms an online platform that streamlines product transactions for both sellers and prospective buyers. Specific embodiments of this system are shown below.

[0735] The server first receives product images input by the user and analyzes them using TensorFlow. Based on the product category and characteristic information obtained through image analysis, the server generates a product description using OpenAI's GPT API. This generated description is sent to the user's device and used as the listing content.

[0736] Next, the server uses Puppeteer to crawl market data and collect price information for similar products. Based on this information, it calculates a fair price and suggests it to the user.

[0737] When a prospective buyer enters product specifications into a terminal, those specifications are sent to a server. The server searches a database and selects products that match the specifications. This selected product information is then presented to the prospective buyer via the terminal to assist them in making a purchase decision.

[0738] Furthermore, the server uses the Google Cloud Translation API to translate product descriptions and negotiation details into multiple languages. This enables smooth transactions between different languages.

[0739] For example, if a user wants to list a "jacket" for sale, the server analyzes the image and generates a description such as, "This jacket is waterproof, size M, and features the latest design." It also suggests a fair price for the jacket and translates the product description into multiple languages, making it easier to appeal to international buyers.

[0740] An example of a prompt for a generative AI model would be: "This product is a jacket, it is waterproof, and the size is M. Please generate a detailed description based on this information."

[0741] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0742] Step 1:

[0743] The user takes a picture of the product using their device and uploads it to the system. The input in this process is the product image, and the output is the transmission of the image data to the server.

[0744] Step 2:

[0745] The server analyzes the received images using TensorFlow. The input for image analysis is a product image, and data calculations are performed to identify the product category and characteristics, which are then obtained as output.

[0746] Step 3:

[0747] The server automatically generates a product description using the OpenAI GPT API based on the analysis results. In this step, the analysis results are used as input, and the product description is output.

[0748] Step 4:

[0749] The server sends the generated product description to the user's terminal. The input is the generated product description, and the output is the description displayed on the terminal.

[0750] Step 5:

[0751] The server uses Puppeteer to crawl market data and collect price information for similar products. Here, information on similar products is taken as input, and price information is output.

[0752] Step 6:

[0753] Based on the collected price information, the server calculates the appropriate price for the product and sends it to the user as a recommended price. The input is price information for similar products, and the output is recommended price information.

[0754] Step 7:

[0755] When a user enters product criteria into their terminal, the server receives the data and performs a database search. In this step, the server searches for the most suitable product based on the entered criteria and generates a list of candidate products as output.

[0756] Step 8:

[0757] The system displays a list of recommended products on the user's device to assist in the purchase selection process. The input is the recommended products, and the output is the list of candidates displayed to the user.

[0758] Step 9:

[0759] The server utilizes the Google Cloud Translation API to translate product descriptions into multiple languages. Here, the product description is taken as input, and the translated description is output.

[0760] Step 10:

[0761] Provide users with translated product descriptions and quickly implement multilingual support. The input is the translated description, and the output is the information displayed on the user's terminal.

[0762] 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.

[0763] This invention relates to an automated transaction support system configured to facilitate transactions on a flea market platform, and in particular, to a system that takes user emotions into consideration. This system aims to improve the experience for both sellers and buyers by utilizing AI technology.

[0764] When a user takes a product photo using their device and uploads it to the application, the server first analyzes the image. This analysis uses an image recognition algorithm to automatically identify the product's category and characteristics. The server then uses natural language processing technology to generate a product description, which is presented to the user via their device.

[0765] In parallel, the server crawls the market database, collecting and analyzing information on similar products on the internet. This allows sellers to easily set reasonable prices by calculating and suggesting appropriate prices to their terminals.

[0766] Furthermore, the server receives the search criteria of potential buyers and uses an AI algorithm to select and recommend products that match those criteria. This recommendation serves to support the decision-making process for potential buyers.

[0767] In addition, this invention integrates an emotion engine. The emotion engine analyzes the user's voice, facial expressions, and input patterns to determine their current emotional state. For example, if a user expresses dissatisfaction or frustration with the negotiation situation, the server detects this. Based on this, the negotiation strategy and price offer are adjusted to improve the user experience.

[0768] For example, if a user lists an expensive item and sales are stagnating, the emotion engine will detect the user's frustration. The server will then help move negotiations forward by suggesting alternative pricing strategies or offering assistance in preparing for negotiations. Furthermore, the system supports multiple languages, enabling smooth transactions between different countries.

[0769] This invention makes flea market transactions more intuitive and effective, and allows for flexible responses that respond to users' emotions.

[0770] The following describes the processing flow.

[0771] Step 1:

[0772] The user takes a product photo using their device and uploads it to the application. The device then sends this image to the server.

[0773] Step 2:

[0774] The server analyzes the received image data using an AI image recognition algorithm. It identifies product categories and characteristics, which then serve as the basis for product descriptions.

[0775] Step 3:

[0776] The server uses natural language processing technology to automatically generate a product description based on the analysis results. This description is then sent to the terminal and presented to the user.

[0777] Step 4:

[0778] The server crawls the market database, collecting and analyzing prices for similar products. Based on this information, it calculates a fair selling price and sends it to the terminal as a price suggestion.

[0779] Step 5:

[0780] Users can view product descriptions and price suggestions on their devices and edit them as needed. The edited product information is then registered on the flea market platform.

[0781] Step 6:

[0782] The prospective buyer enters product search criteria into their terminal. These criteria are then sent to the server.

[0783] Step 7:

[0784] The server uses an AI algorithm to search the database for products that match the specified criteria and sends the selected product information back to the terminal as a recommendation.

[0785] Step 8:

[0786] The server activates an emotion engine based on the voice, facial expressions, and input patterns obtained from the user to determine the user's emotional state.

[0787] Step 9:

[0788] Based on the emotions detected by the emotion engine, the server adjusts and sends transaction-related feedback and advice to the terminal.

[0789] Step 10:

[0790] The server uses its multilingual support function to automatically translate listing information and negotiation details as needed, facilitating smooth transactions between different languages.

[0791] (Example 2)

[0792] 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".

[0793] In online flea market transactions, generating product information, setting appropriate prices, and recommending items to potential buyers are often cumbersome processes. Furthermore, the need for flexible responses that consider the feelings of both sellers and buyers can sometimes lead to an inadequate user experience. Additionally, smooth transactions between users speaking different languages ​​are necessary.

[0794] 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.

[0795] In this invention, the server includes means for analyzing image data to identify product characteristics, means for creating product descriptions using natural language generation technology, means for collecting market information on the internet and calculating appropriate prices, means for recommending products based on the conditions of prospective buyers, and means for analyzing the user's emotional state and reflecting it in product recommendations. This enables automatic generation of product information, appropriate pricing, and the provision of flexible experiences based on emotions. Furthermore, it facilitates smooth transactions between multiple languages.

[0796] "Image data" refers to information that represents visual information in a digital format and can be processed by a computer.

[0797] "Product characteristics" refer to information that indicates the attributes and features of a product, and include the product's category, size, color, and brand.

[0798] "Natural language generation technology" is a technology that models human language to generate natural-sounding sentences, and is used as part of artificial intelligence.

[0799] "Market information" refers to data related to commercial transactions, such as product prices, demand trends, and inventory levels.

[0800] "Fair price" refers to a reasonable price range for a product, assessed based on market supply and demand.

[0801] "Prospective buyer" refers to an individual or group that is considering purchasing a product.

[0802] "Emotional state" refers to the user's current emotions and psychological state, and is determined by factors such as tone of voice, facial expressions, and input patterns.

[0803] "Product proposal" refers to the act of introducing a product to a user based on specific conditions.

[0804] Translation is the process of replacing expressions between different languages ​​without changing their meaning.

[0805] This invention is a system that facilitates transactions on an online flea market platform and integrates various technologies to improve the user experience. The core server of the system operates by combining image analysis, natural language generation, price calculation, recommendation systems, and sentiment analysis technologies.

[0806] Users take product photos using their devices and upload the image data to the server via the application. The server uses a common computer vision framework to analyze this image data. For example, it leverages deep learning libraries to extract image features and identify product characteristics.

[0807] The server generates a product description using natural language generation technology based on the identified product characteristics. This process utilizes a natural language processing framework known as a generative AI model to generate text data. For example, a prompt such as "Generate a product description. The product name is 'Vintage Record Player,' and the characteristics are 'Made in the 1960s, in good working order, antique finish'" might be used.

[0808] To determine a fair price for a product, the server collects market information from the internet and calculates the price. This involves using web scraping techniques to gather large amounts of market data and analyzing it through statistical models. As a result, it can propose a market price for the product to the user.

[0809] To recommend products that meet the criteria of potential buyers, the server takes into account past purchase history and preference data. An AI algorithm evaluates this data and displays products that are likely to be of interest. In addition, an emotion engine analyzes the user's emotional state and adjusts the recommendations according to the user's emotions.

[0810] The system also includes translation technology to facilitate smooth transactions between different languages. This feature streamlines communication between users and promotes international trade. As a result, using the flea market platform becomes more intuitive and effective.

[0811] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0812] Step 1:

[0813] The user takes a product photo using their device and uploads the image data to the server via the application. The input is the product image taken by the user with the camera, and the output is the image data received by the server. The server adds this data to a processing queue and prepares to perform analysis in the next step.

[0814] Step 2:

[0815] The server analyzes the image data. The input is the image data received in step 1. The server uses image recognition technology to extract features from the image and identify product characteristics. A deep learning model identifies the product and outputs category and characteristic information. For example, the image might be identified as "vintage audio equipment".

[0816] Step 3:

[0817] Based on the product characteristics identified by the server, a generative AI model is used to generate a product description using natural language generation technology. The input is the product characteristics obtained in step 2. The generative AI model is given characteristic information as a prompt and outputs a description such as, "This product is a vintage record player from the 1960s."

[0818] Step 4:

[0819] The server collects market data and calculates a fair price. The inputs are product characteristics and market information from the internet. The server uses web scraping techniques to collect price data for similar products from the internet. The collected data is analyzed using statistical methods and output price information such as "The estimated fair price is $100."

[0820] Step 5:

[0821] The server displays the generated product description and appropriate price on the terminal. The input is the information obtained in steps 3 and 4. The product description and appropriate price are displayed on the user's terminal to assist in product pricing.

[0822] Step 6:

[0823] The server receives the buyer's criteria and recommends products. The input is the buyer's search criteria data. An AI algorithm identifies products that match the search criteria and outputs a list of products that the buyer might be interested in, referencing past purchase data.

[0824] Step 7:

[0825] The server analyzes the user's emotional state and adjusts product recommendations accordingly. Input consists of user voice and facial expression data. An emotion engine analyzes this data and generates and outputs optimal product recommendations based on the user's emotions. This improves the user experience.

[0826] (Application Example 2)

[0827] 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".

[0828] Traditional flea market platforms have problems such as difficulties in smooth transactions between sellers and buyers, and challenges in properly classifying and pricing products. Furthermore, they lack the flexibility to respond to user emotions, resulting in a poor transaction experience.

[0829] 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.

[0830] In this invention, the server includes means for analyzing and classifying product images, means for evaluating image data and generating product descriptions, and means for collecting market information and estimating sales prices. This enables automatic product classification, appropriate pricing, and adjustment of sales strategies to suit user sentiment.

[0831] "Product image analysis" is a technology that uses software to process the visual data of items offered to the market, extracting and classifying their features.

[0832] "Picture data evaluation" is a technology that automatically generates descriptive text for objects based on images and related information, and clarifies the content of that text.

[0833] "Market information gathering" refers to the technique of collecting information on similar products from the internet and databases, and analyzing prices and supply and demand trends.

[0834] "Price estimation" is the process of calculating a reasonable price based on collected market information and proposing it to the seller.

[0835] "Adjusting sales strategies in response to user emotions" refers to a method of detecting the emotional state of users and dynamically changing negotiation policies and sales approaches accordingly.

[0836] To implement this invention, a system is required that combines a user's terminal, a server, and related software. First, the user takes a picture of a product using their smartphone's camera and uploads the image to an application on their terminal. This application automatically sends the image data to the server.

[0837] Upon receiving image data, the server analyzes the product images using image recognition software based on TensorFlow and determines their classification. Then, using a GPT model, it automatically generates an effective product description based on the analysis results. The generated description is sent to the user's device and displayed.

[0838] Furthermore, the server uses a Python scraping library to collect market information from the internet and analyzes the market database to estimate selling prices. This pricing information is provided to product sellers, enabling them to set appropriate prices.

[0839] After the user reviews the product description and price, the server runs an emotion analysis tool to determine the user's emotional state by analyzing their facial expressions using OpenCV and analyzing their voice. Based on the user's emotions, the server adjusts negotiation and sales strategies to optimize the user's transaction experience.

[0840] For example, if a user wants to sell a painting and takes a photo of the product, the program analyzes the image and classifies it as "painting," "art," or "landscape." The server then generates a product description such as, "Beautifully decorate your living room with this painting." An example of a prompt message would be, "Analyze the captured image, identify the main features of the product, and develop an emotionally resonant sales strategy."

[0841] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0842] Step 1:

[0843] The user takes a picture of the product they want to sell using their device's camera. This image is uploaded to the application on the device. The input is the image data of the product, and the output is the data sent to the server.

[0844] Step 2:

[0845] The terminal sends the uploaded image data to the server. The server inputs the received image data into an image recognition algorithm using TensorFlow. This analyzes the product image and obtains its classification information. The output is product category data.

[0846] Step 3:

[0847] The server uses a GPT model based on image recognition results to generate a product description. The input is product category data, and the output is an automatically generated product description. The generated description is sent to the terminal and displayed to the user.

[0848] Step 4:

[0849] The server uses a Python scraping library to collect market information from the internet. The input is a search query related to a product, and the output is market data including pricing information for similar products. Based on this data, it estimates the selling price and provides the price information to the user's terminal.

[0850] Step 5:

[0851] After the user reviews the product description and price, the server uses OpenCV-based facial expression and voice analysis tools to determine the user's emotional state based on their facial expressions and voice data. The output is the user's emotional evaluation data. Based on this data, the server adjusts its sales strategy and provides the user with necessary information.

[0852] Step 6:

[0853] The server optimizes negotiation strategies based on the user's emotions and generates prompts for an AI model within the system. The input is the user's emotion rating data, and the output is a refined sales or negotiation strategy. This strategy is sent to the terminal to support the user's next action.

[0854] 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.

[0855] 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.

[0856] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0862] 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."

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0875] The following is further disclosed regarding the embodiments described above.

[0876] (Claim 1)

[0877] A means of automatically generating product information,

[0878] A method for analyzing product images and creating product descriptions,

[0879] A method of researching market prices for similar products and proposing pricing,

[0880] A means of recommending products to prospective buyers,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, further comprising means for translating product descriptions into multiple languages.

[0884] (Claim 3)

[0885] The system according to claim 1, further comprising means for providing advice on price adjustments in negotiations.

[0886] "Example 1"

[0887] (Claim 1)

[0888] A means of automatically generating product information,

[0889] A method for analyzing product images and creating product descriptions,

[0890] A method of researching market prices for similar products and proposing pricing,

[0891] A means of recommending products to prospective buyers,

[0892] A method for selecting products that meet the criteria using AI technology,

[0893] Means of translating product descriptions between different languages,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, further comprising means for automatically translating negotiation content between different languages.

[0897] (Claim 3)

[0898] The system according to claim 1, further comprising means for supporting product search based on the buyer's criteria.

[0899] "Application Example 1"

[0900] (Claim 1)

[0901] A means of automatically generating product information,

[0902] A method for analyzing product images and creating product descriptions,

[0903] A method of researching market prices for similar products and proposing pricing,

[0904] A means of recommending products to prospective buyers,

[0905] Methods for translating product descriptions into multiple languages,

[0906] A method of displaying the most suitable product by inputting product criteria,

[0907] A system that includes this.

[0908] (Claim 2)

[0909] The system according to claim 1, which facilitates international transactions through multilingual support.

[0910] (Claim 3)

[0911] The system according to claim 1, which recommends products based on the conditions of a prospective buyer.

[0912] "Example 2 of combining an emotion engine"

[0913] (Claim 1)

[0914] A means of identifying product characteristics by analyzing image data,

[0915] A means of creating product descriptions using natural language generation technology,

[0916] A means of collecting market information from the internet and calculating a fair price,

[0917] A means of recommending products based on the conditions of prospective buyers,

[0918] A means of analyzing the user's emotional state and reflecting it in product recommendations,

[0919] A system that includes this.

[0920] (Claim 2)

[0921] The system according to claim 1, further comprising means for translating information into multiple languages.

[0922] (Claim 3)

[0923] The system according to claim 1, further comprising means for providing advice on pricing strategies in negotiations.

[0924] "Application example 2 when combining with an emotional engine"

[0925] (Claim 1)

[0926] A method for analyzing and classifying product images,

[0927] A means of evaluating painting data and generating a product description,

[0928] Methods for collecting market information and estimating the selling price,

[0929] Means of presenting goods that meet the buyer's requirements,

[0930] A means of determining the emotional state of users using emotion analysis technology and adjusting sales strategies accordingly,

[0931] A system that includes this.

[0932] (Claim 2)

[0933] The system according to claim 1, further comprising means for translating product descriptions into various languages.

[0934] (Claim 3)

[0935] The system according to claim 1, further comprising means for providing guidance on adjusting the purchase price during the negotiation process. [Explanation of Symbols]

[0936] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of automatically generating product information, A method for analyzing product images and creating product descriptions, A method of researching market prices for similar products and proposing pricing, A means of recommending products to prospective buyers, A system that includes this.

2. The system according to claim 1, further comprising means for translating product descriptions into multiple languages.

3. The system according to claim 1, further comprising means for providing advice on price adjustments in negotiations.

Images