System

Abstract

A system is provided.SOLUTION: A system for providing advice for improving the quality of a product description to a seller of a bar auction or an electronic marketplace, comprising: means for receiving product information input from the seller; analyzing means for analyzing the received product information and identifying information deficiencies; advice generating means for generating advice of a specific product description to the seller based on the analysis; and means for presenting the generated advice to the seller.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In online auctions and electronic markets, sellers often provide insufficient product descriptions, which reduces buyers' willingness to purchase. For example, in the case of clothing jackets, they often only provide general size descriptions such as "medium" or "size 9," without providing specific measurements (shoulder width, chest width, sleeve length, etc.). This requires time and effort from buyers to ask questions of the seller, which reduces buyers' willingness to purchase. A system that solves this problem and improves the matching rate between buyers and sellers is needed. [Means for solving the problem]

[0005] This system includes a means for receiving product information entered by a seller, analyzing the received product information to identify information deficiencies, generating specific product description advice for the seller based on the analysis, and presenting the generated advice to the seller. The system also includes an additional means for collecting and learning from past purchase data, and conducting surveys of buyers and learning from the results to improve the quality of the product description advice generation means. This allows sellers to provide specific product descriptions that encourage purchases, thereby improving the matching rate between buyers and sellers.

[0006] A "seller" is an individual or corporation that lists their own products for sale on an online auction or electronic marketplace.

[0007] "Product information" refers to data that describes the details of the product that a seller is selling, and may include information such as specific dimensions, color, and condition.

[0008] "Advice" refers to guidance or suggestions provided to make product information more specific and attractive to buyers.

[0009] An "online auction" is an online platform for buying and selling goods over the Internet, where buyers make bids.

[0010] An "electronic marketplace" is an online platform that uses the Internet to buy and sell goods, including those sold at fixed prices.

[0011] "Analysis means" refers to a technical means for analyzing product information from the input format and identifying missing information and areas for improvement.

[0012] The "advice generation means" is a function for generating specific and useful advice to the seller based on the information obtained from the analysis means.

[0013] "Presentation means" refers to a technical means for notifying or displaying the generated advice to the seller.

[0014] "Purchase data" refers to all data that indicates the purchase intent for the listed product, such as past purchase history and buyer behavior data.

[0015] A "survey" is a questionnaire-based survey conducted to gather buyers' opinions and satisfaction levels.

[0016] "Learning means" refers to the technical means for analyzing and learning from collected data to improve the accuracy of advice generation. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This invention includes a system for providing high-quality product descriptions to sellers of online auctions and electronic markets, allowing sellers to create specific product descriptions that encourage purchases.

[0039] System Overview

[0040] This system has the following main functions:

[0041] 1. How to receive product information from sellers

[0042] 2. Analysis means for analyzing received product information and identifying missing information

[0043] 3. Advice generation method that generates specific product description advice based on the analysis results

[0044] 4. A method for presenting the generated advice to the seller

[0045] 5. Learning tools to collect and learn from past purchase data to improve the quality of advice

[0046] 6. Surveying customers and learning from the results

[0047] Program processing explanation

[0048] 1. User Input

[0049] The user inputs product information from the terminal. For example, the user might input product category ("jacket"), size ("M"), color ("blue"), and product condition ("almost new").

[0050] 2. Data Reception and Analysis

[0051] The server receives the product information sent from the device. The AI ​​on the server analyzes this information and identifies any missing information or areas for improvement. For example, if only "Size: M" is listed in the "Jacket" category, it will determine that specific measurements (shoulder width, chest width, sleeve length, etc.) are missing.

[0052] 3. Advice Generation

[0053] The server's AI generates specific advice based on the analysis results. For example, it might generate advice like, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. For example: Shoulder width XX cm, chest width XX cm, sleeve length XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[0054] 4. Learning from purchasing data

[0055] The server collects and organizes past purchase data, and the AI ​​learns from it to improve the accuracy of advice it can give to sellers. For example, it can learn that the more specific the size information, the higher the purchase rate.

[0056] 5. Presentation to the User

[0057] The server sends the generated advice to the terminal and displays it to the user, who can then modify or resubmit the product description according to the advice.

[0058] 6. Survey and learning

[0059] The server sends a questionnaire to the customer about their satisfaction with the purchased product and the usefulness of the product description. The received results are analyzed, and the AI ​​learns from the data, allowing it to generate more precise advice.

[0060] Specific examples

[0061] Example 1:

[0062] The user enters "Jacket", "Size: M", "Color: Blue", and "Condition: Like New".

[0063] The server determined that specific measurements were insufficient and generated the advice, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag."

[0064] Users measure, take photos, and edit product descriptions.

[0065] Example 2:

[0066] In a customer survey, we received feedback that "specific dimensions were listed, so I was able to make the purchase with confidence."

[0067] The server learns from this and reflects it in future advice generation.

[0068] This will increase the matching rate between buyers and sellers and make transactions smoother.

[0069] The processing flow will be explained below.

[0070] Step 1: User Input

[0071] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[0072] The terminal checks the input product information and prepares to send it to the server.

[0073] Step 2: Receiving data

[0074] The server receives the product information sent from the terminal.

[0075] The server stores the received data in a database as a preprocessing step for analysis.

[0076] Step 3: Data analysis

[0077] The server's AI confirms that the product category is "jacket."

[0078] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[0079] The server's AI also checks the color and state information to make sure there are no problems with these.

[0080] Step 4: Advice Generation

[0081] The server's AI generates specific product description advice based on the missing information. For example, it might generate advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width xx cm, chest width xx cm, sleeve length xx cm)."

[0082] You will also be asked to take a photo of the whole thing and a photo of the tag.

[0083] Step 5: Learn the purchasing data

[0084] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[0085] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[0086] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[0087] Step 6: Present to the user

[0088] The server transmits the generated advice to the user's terminal.

[0089] The device displays the received advice to the user, who then modifies the product description in accordance with the advice.

[0090] Step 7: User corrections and resubmission

[0091] Based on advice from the server, the user measures specific dimensions and takes photos of the overall object and the tag.

[0092] The user retransmits the corrected information from the terminal to the server.

[0093] Step 8: Survey

[0094] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0095] Step 9: Collect and learn from survey results

[0096] The server collects the survey results and stores them in a database.

[0097] The server's AI learns from the survey results and reflects them in generating future advice.

[0098] This allows sellers to provide specific product descriptions that increase purchasing motivation, and improves the matching rate between buyers and sellers.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] In online auctions and electronic markets, sellers need to create attractive and specific product descriptions, but in many cases, the information is insufficient or vague, preventing them from motivating buyers. Furthermore, sellers may not receive appropriate advice, leading to sluggish sales. Furthermore, there is also the issue of past purchase data and feedback from buyers not being fully utilized, preventing the quality of advice from improving.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes means for receiving product information input by a seller, analysis means for analyzing the received product information and identifying insufficient information, advice generation means for generating specific product description advice for the seller based on the analysis, means for presenting the generated advice to the seller, means for transmitting the generated product description advice to a terminal and displaying it to the seller, means for collecting past purchase data and improving the quality of the product description advice based on the data, and means for conducting a survey of buyers and improving the quality of the product description advice based on the results. This enables the seller to create specific product descriptions that encourage purchases, and also increases buyer satisfaction.

[0104] A "seller" is an individual or company that lists an item for sale on an online auction or electronic marketplace.

[0105] "Product information" refers to information about the product being offered for sale by the seller, including, for example, category, size, color, condition, etc.

[0106] A "server" is a computer system that receives, processes, and transmits data over a network.

[0107] A "terminal" is a device through which sellers input product information and receive generated advice, etc., and specifically refers to a PC or smartphone.

[0108] The "analysis means" is software or hardware that has the function of analyzing the received product information and identifying missing information or areas for improvement.

[0109] The "advice generation means" is software or hardware having a function for automatically generating specific product description advice to the seller based on the analysis results.

[0110] The "presentation means" refers to software or hardware having a function for presenting the generated advice to the seller visually or in some other way.

[0111] "Past purchasing data" refers to information about past transactions on online auctions and electronic markets, and specifically includes sales data, buyer feedback, and the like.

[0112] "Survey" refers to a questionnaire used to collect feedback provided by buyers after purchase, including satisfaction levels and product ratings.

[0113] The "AI analysis module" is software that uses artificial intelligence technology to analyze product information and identify missing information and areas for improvement.

[0114] The "AI advice generation module" is software that uses artificial intelligence technology to generate specific advice based on analysis results.

[0115] The "AI learning module" is software that trains artificial intelligence based on past purchasing data and survey results to improve the quality of advice.

[0116] A "buyer" is an individual or company that purchases goods through an online auction or electronic marketplace.

[0117] The present invention provides a system that allows sellers in online auctions and electronic markets to create specific product descriptions that encourage purchases. This system allows sellers to input appropriate product information and receive optimal product descriptions based on that information.

[0118] First, the user enters product information using their own device (PC, smartphone, etc.), including specific information such as product category (e.g., jacket), size (e.g., M), color (e.g., blue), and product condition (e.g., almost new).

[0119] The terminal sends the input product information to a server, which is equipped with an AI analysis module that analyzes the received product information.

[0120] When the server receives product information, it first stores it in a database. Next, an AI analysis module reads the product information and identifies missing information and areas for improvement. Based on this analysis, the AI ​​generates specific advice. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Example: Shoulder width XX cm, chest width XX cm, sleeve length XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[0121] The generated advice is sent to the terminal by the server and displayed to the user, who can then follow the advice to modify the product description and send it again.

[0122] Furthermore, the server collects past purchase data and uses it to improve the quality of advice. The server is equipped with an AI learning module that learns from past transaction data and customer feedback to improve the accuracy of the advice it generates. For example, it learns the trend that "the more specific the size information, the higher the purchase rate" and generates advice based on this.

[0123] The server also conducts surveys on customers and collects the results, which the AI ​​learning module uses to generate even higher quality advice.

[0124] Specific examples of how this system works include the following scenarios:

[0125] Specific examples

[0126] The user enters "Jacket," "Size: M," "Color: Blue," and "Condition: Like New." The device sends this input information to the server. The server receives the product information and, after analysis, determines that specific measurements are missing. The server's AI analysis module generates advice saying, "Please enter the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag." The device displays this advice on the user interface. The user measures the measurements, takes photos, and corrects the product description.

[0127] An example prompt might be, "When I list a new item, I'd like some advice on how to include specific dimensions and detailed photos. Also, suggestions based on past purchasing data would be helpful."

[0128] This system allows sellers to create detailed product descriptions that encourage purchases, improving buyer satisfaction and helping to ensure smooth transactions.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1:

[0131] The user inputs product information from their own device (PC, smartphone, etc.) This product information includes product category (e.g., jacket), size (e.g., M), color (e.g., blue), and product condition (e.g., almost new).

[0132] Input: Product information (category, size, color, condition)

[0133] Output: Product information data sent by the device to the server

[0134] Specific behavior:

[0135] The user opens a web form and enters product information into each field.

[0136] The user checks the input contents and clicks the send button.

[0137] The terminal transmits the input information to the server.

[0138] Step 2:

[0139] The server receives the product information sent from the device, stores it in a database, and an AI analysis module identifies any missing information or areas that need improvement.

[0140] Input: Product information data received from the terminal

[0141] Output: A list of missing information and improvements analyzed by the AI ​​analysis module

[0142] Specific behavior:

[0143] The server stores the received product information in a database.

[0144] The server's AI analysis module reads the product information and identifies any missing parts.

[0145] The server will list any identified gaps or areas for improvement.

[0146] Step 3:

[0147] The server's AI generates specific advice based on the analysis results. For example, it might say, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. For example, shoulder width: XX cm, chest width: XX cm, sleeve length: XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[0148] Input: Analysis results (list of missing information and improvements)

[0149] Output: Specific advice generated

[0150] Specific behavior:

[0151] The server's AI advice generation module automatically generates advice based on the analysis results.

[0152] The server compiles the generated advice into a list.

[0153] Step 4:

[0154] The server sends the generated advice to the terminal and displays it to the user, who can then follow the advice to modify the product description and resubmit it.

[0155] Input: Generated specific advice

[0156] Output: Advice displayed on the terminal

[0157] Specific behavior:

[0158] The server sends the generated advice to the terminal in JSON format.

[0159] The terminal displays the received advice on the user interface.

[0160] The user checks the displayed advice and modifies the product description.

[0161] Step 5:

[0162] The server collects past purchase data and uses it to improve the quality of advice. An AI learning module learns from this data to improve the accuracy of advice.

[0163] Input: Past purchase data

[0164] Output: Improved advice accuracy due to the trained model

[0165] Specific behavior:

[0166] The server extracts past purchase data from a database.

[0167] The server's AI learning module uses the extracted purchasing data to learn.

[0168] The server stores the learning results in a database and reflects them in future advice generation.

[0169] Step 6:

[0170] The server conducts surveys of customers and collects the results. The AI ​​learning module also learns from these survey results and generates even higher quality advice.

[0171] Input: Survey results from buyers

[0172] Output: Further improved advice accuracy due to the trained model

[0173] Specific behavior:

[0174] The server automatically sends a questionnaire to the purchaser.

[0175] The purchaser answers the questionnaire and submits it.

[0176] The server stores the received survey results in a database and provides them to the AI ​​learning module.

[0177] The AI ​​learning module learns from this and generates even more accurate advice.

[0178] (Application example 1)

[0179] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0180] In online auctions and electronic markets, if sellers do not effectively explain their products, it can discourage buyers and prevent transactions from proceeding smoothly. This requires sellers to provide detailed product information, which takes time and effort. Furthermore, it is often difficult to identify the missing information, resulting in a decline in the quality of product descriptions. Therefore, a system is needed that can continuously improve the quality of advice by utilizing past purchase data and buyer feedback.

[0181] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0182] In this invention, the server includes a means for inputting product information, an analysis means for analyzing the input product information and identifying missing information, an advice generation means for generating specific product description advice based on the analysis, a means for presenting the generated advice, and a means for learning past purchase data using a generative AI model to improve the quality of the advice. This enables sellers to quickly create effective and detailed product descriptions, increasing buyer trust and facilitating transactions.

[0183] "Product information" refers to detailed information about a product entered by a seller in an online auction or online marketplace. This information includes attribute information such as the product name, category, size, color, and condition.

[0184] "Analysis means" refers to the technology or method for analyzing input product information and identifying missing information or areas requiring improvement.

[0185] "Advice generation means" refers to a technique or method for instructing sellers on specific improvements to product descriptions and methods for providing additional information based on the analysis results.

[0186] "Presentation means" refers to the technology or method for presenting the generated advice to the seller in an easy-to-view manner and encouraging necessary improvements.

[0187] A "generative AI model" refers to an artificial intelligence model that learns from past purchasing data and customer feedback to constantly improve the quality of advice.

[0188] "Past purchase data" is historical information about past purchases, and includes data such as product category, number of purchases, and buyer ratings.

[0189] A "customer survey" is a questionnaire-based survey sent to buyers to assess the usefulness of product descriptions and their satisfaction with the purchased product.

[0190] The system of the present invention is configured to provide sellers with specific advice to improve the quality of their product descriptions. The main components of the system and their roles will be described below.

[0191] System configuration:

[0192] This system is realized mainly using the following hardware and software.

[0193] Hardware: The smartphone or computer used by the seller

[0194] Software: Server, SpaCy, scikit-learn, generative AI model

[0195] 1. Product information input method:

[0196] The user (seller) enters product information via a smartphone or computer, such as "Jacket, Size M, Color: Blue, Condition: Almost New."

[0197] 2. Analysis method:

[0198] The server uses SpaCy to analyze the input product information. Specifically, it extracts important tags (nouns and adjectives) from the information and identifies any missing information.

[0199] 3. Advice Generation Methods:

[0200] The server uses scikit-learn functions to generate specific advice about missing information or information that needs improvement. For example, specific advice might be generated such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag."

[0201] 4. Means of presentation:

[0202] The generated advice is displayed on the user's smartphone or computer, and the seller can revise the product description accordingly.

[0203] 5. Learning tools:

[0204] The generative AI model on the server learns from past purchase data and customer survey results. Based on this data, it continuously improves the quality of advice. For example, it learns trends such as "products with specific dimensional information have a higher purchase rate."

[0205] Examples:

[0206] User Input: Seller enters "Jacket, Size M, Color: Blue, Condition: Like New."

[0207] Analysis result: The server analyzes the input information using Spacy and determines that the information for "shoulder width," "chest width," and "sleeve length" is missing.

[0208] Generated advice: Using scikit-learn, the server generates the advice, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag." and presents it to the seller.

[0209] Example prompt sentence:

[0210] Product information: Blue jacket, size M, condition almost new

[0211] From the analysis results, we identified the missing information as "shoulder width," "chest width," and "sleeve length." Please create a product description that includes specific examples like the ones below.

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1:

[0214] User enters product information

[0215] Users input product information using a smartphone or computer. This input includes detailed information such as product category, size, color, and condition. Specific input is possible, such as "Jacket, Size M, Color: Blue, Condition: Almost New."

[0216] Step 2:

[0217] Server receives product information

[0218] The server receives the product information entered by the user and stores it in a database for use in subsequent analysis.

[0219] Step 3:

[0220] The server analyzes the input information

[0221] The server uses SpaCy to analyze the received product information. Specifically, it extracts important tags (nouns and adjectives) and identifies missing information. For example, it determines that the shoulder width, chest width, and sleeve length are missing for a jacket.

[0222] Input: Product information entered by the user (e.g., "Jacket, Size M, Color: Blue, Condition: Like New")

[0223] Output: Extracted important tags (e.g., "shoulder width," "chest width," and "sleeve length" are determined to be missing)

[0224] Step 4:

[0225] Server generates advice

[0226] The server uses scikit-learn to generate specific advice based on the missing information. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and the tag."

[0227] Input: Missing information (e.g. "shoulder width", "chest width", "sleeve length")

[0228] Output: Generated specific advice (e.g., "Please provide the specific measurements for shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and a photo of the tag.")

[0229] Step 5:

[0230] The server provides advice to the user

[0231] The server sends the generated advice to the user's smartphone or PC, allowing the user to refer to the advice and revise the product description.

[0232] Input: Generated advice (e.g., "Please provide the specific measurements for shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and a photo of the tag.")

[0233] Output: Advice displayed on the user's terminal

[0234] Step 6:

[0235] The server learns the purchasing data

[0236] The generative AI model on the server collects past purchase data and learns from it. For example, it can extract trends such as "products with specific dimensional information have a higher purchase rate." The results of this learning are reflected in future advice generation.

[0237] Input: Past purchase data

[0238] Output: Learning results (e.g., "Products with specific dimensions have a higher purchase rate.")

[0239] Step 7:

[0240] The server learns the survey results

[0241] The server conducts surveys of shoppers and collects and learns from the results. This provides information on the usefulness of product descriptions and satisfaction with purchased products. The generative AI model uses this information to further improve the quality of advice.

[0242] Input: Customer survey results

[0243] Output: Learning results (e.g., feedback such as "The specific dimensions were listed, so I was able to make the purchase with confidence.")

[0244] Through the above steps, sellers can create high-quality product descriptions, which increases buyers' trust and facilitates smooth transactions.

[0245] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0246] This invention includes a system that provides high-quality product descriptions to sellers of online auctions and electronic marketplaces. This system allows sellers to create specific product descriptions that encourage purchases. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, the system can provide more personalized advice.

[0247] System Overview

[0248] This system has the following main functions:

[0249] 1. How to receive product information from sellers

[0250] 2. Analysis means for analyzing received product information and identifying missing information

[0251] 3. Advice generation method that generates specific product description advice based on the analysis results

[0252] 4. A method for presenting the generated advice to the seller

[0253] 5. Learning tools to collect and learn from past purchase data to improve the quality of advice

[0254] 6. A means of surveying buyers and learning from their results

[0255] 7. An emotion engine that recognizes user emotions and uses that information to generate advice.

[0256] Program processing explanation

[0257] 1. User Input

[0258] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[0259] The terminal checks the input product information and prepares to send it to the server.

[0260] 2. Data Reception and Analysis

[0261] The server receives the product information sent from the terminal.

[0262] The server stores the received data in a database as a preprocessing step for analysis.

[0263] The server's AI confirms that the product category is "jacket."

[0264] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[0265] 3. Emotion Recognition by Emotion Engine

[0266] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine.

[0267] The server's emotion engine analyzes this and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.).

[0268] The server stores the emotion information obtained from the emotion engine as the analysis result.

[0269] 4. Advice Generation

[0270] The server's AI generates specific product description advice based on the missing information. For example, it generates specific advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width xx cm, chest width xx cm, sleeve length xx cm)."

[0271] The information from the emotion engine is reflected and the content and tone of the advice is adjusted, such as "brief instructions if the user is anxious" or "detailed instructions if the user is relieved."

[0272] 5. Learning from purchasing data

[0273] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[0274] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[0275] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[0276] 6. Presentation to the User

[0277] The server transmits the generated advice to the user's terminal.

[0278] The device displays the received advice to the user, who then modifies the product description in accordance with the advice.

[0279] 7. User Modifications and Resubmissions

[0280] Based on advice from the server, the user measures specific dimensions and takes photos of the overall object and the tag.

[0281] The user retransmits the corrected information from the terminal to the server.

[0282] 8. Survey implementation

[0283] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0284] 9. Collecting and Learning from Survey Results

[0285] The server collects the survey results and stores them in a database.

[0286] The server's AI learns from the survey results and reflects them in generating future advice.

[0287] Specific examples

[0288] Example 1:

[0289] The user inputs "Jacket", "Size: M", "Color: Blue", and "Condition: Like New". The emotion engine detects the emotion "Impatience".

[0290] The server generates specific and concise advice: "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Sample sentences for concise descriptions are shown below: Shoulder width XX cm, chest width XX cm, sleeve length XX cm."

[0291] The user measures the dimensions and briefly edits the product description.

[0292] Example 2:

[0293] In a customer survey, we received feedback that "specific dimensions were listed, so I was able to make the purchase with confidence."

[0294] The server learns from this and reflects it in future advice generation.

[0295] In this way, by providing specific advice that takes into account the user's emotions, it is possible to improve the quality of product descriptions and further increase the matching rate between buyers and sellers.

[0296] The processing flow will be explained below.

[0297] Step 1: User Input

[0298] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[0299] The terminal checks the input product information and prepares to send it to the server.

[0300] Step 2: Receiving data

[0301] The server receives the product information sent from the terminal.

[0302] The server stores the received data in a database as a preprocessing step for analysis.

[0303] Step 3: Emotion recognition by the emotion engine

[0304] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine.

[0305] The server's emotion engine analyzes this and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.).

[0306] The server stores the emotion information obtained from the emotion engine as analysis data.

[0307] Step 4: Data analysis

[0308] The server's AI analyzes the received product information.

[0309] The server's AI confirms that the product category is "jacket."

[0310] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[0311] The server's AI also checks color and state information, and also refers to emotion information.

[0312] Step 5: Advice Generation

[0313] The server's AI generates specific product description advice for sellers based on the data analysis results and emotional information.

[0314] For example, if the emotional information is "impatience," the system generates concise advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width XX cm, chest width XX cm, sleeve length XX cm). Also, please take photos of the entire product and the tag."

[0315] If the emotional information is "peace of mind," detailed advice is provided: "Please describe the product's features in detail and include specific measurements such as shoulder width, chest width, and sleeve length. Photos should include an overall view of the product, tags, and details."

[0316] Step 6: Present to the user

[0317] The server transmits the generated advice to the user's terminal.

[0318] The terminal displays the received advice to the user.

[0319] Step 7: User corrections and resubmission

[0320] The user makes the necessary corrections based on the provided advice, such as taking specific measurements and taking photos of the overall product and the tag.

[0321] The user retransmits the corrected information from the terminal to the server.

[0322] Step 8: Learn your purchasing data

[0323] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[0324] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[0325] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[0326] Step 9: Survey

[0327] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0328] Step 10: Collect and learn from survey results

[0329] The server collects the survey results and stores them in a database.

[0330] The server's AI learns from the survey results and reflects them in generating future advice.

[0331] In this way, sellers can create specific and inspiring product descriptions by providing specific advice that takes users' emotions into account, further increasing the chances of matching buyers and sellers.

[0332] Example 2

[0333] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0334] In online auctions and electronic markets, if sellers provide insufficient product descriptions, buyers have difficulty understanding the product details, which reduces their willingness to purchase. Furthermore, some users are easily influenced by their emotions, and the quality and content of product descriptions can directly affect their willingness to purchase. Therefore, there is a need for support for sellers to provide high-quality, specific product descriptions that take emotions into consideration.

[0335] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving product information input by a seller, a means for analyzing the received product information to identify insufficient information, a means for acquiring and analyzing the user's emotional state based on the input product information, a means for generating specific product description advice to the seller based on the analysis, and a means for presenting the generated advice to the seller. This enables the seller to supplement the insufficient information and provide a high-quality product description that takes the user's emotions into consideration.

[0336] A "seller" is an individual or organization that sells goods on an online auction or electronic marketplace.

[0337] "Product information" refers to detailed information about the product being sold by the seller, including, specifically, the category, size, color, condition, and the like.

[0338] The "emotional state" refers to the psychological state of the user when inputting product information, and examples include feelings such as impatience, anxiety, and relief.

[0339] The "receiving means" is a function that receives product information sent from the terminal at the server and performs processing to store the information in the database.

[0340] The "analysis means" is a function for analyzing received product information and identifying missing information.

[0341] The "emotion recognition means" is a function for analyzing the user's facial expressions and voice and identifying their emotional state.

[0342] The "advice generation means" is a function for dynamically generating specific advice on product descriptions based on the results of the analysis means and emotion recognition means.

[0343] The "presentation means" is a function for displaying the generated advice to the seller in an easy-to-understand manner.

[0344] "Purchase data" refers to data including product categories, detailed product descriptions, purchaser behavior data, and the like from past transactions.

[0345] A "survey" is a survey conducted to collect feedback from buyers about their satisfaction with the purchased product and the usefulness of the product description.

[0346] "Collection means" refers to a function for effectively collecting purchasing data and survey results.

[0347] The "learning means" is a function that uses collected data to learn, through a machine learning algorithm, what kind of product descriptions will increase purchasing desire, and reflects this in the advice generation algorithm.

[0348] This invention is a system that provides high-quality product descriptions to sellers of online auctions and electronic markets. This system allows sellers to create specific product descriptions that encourage purchases. In addition, by incorporating an emotion engine that recognizes the user's emotions, the system can provide more personalized advice.

[0349] Hardware and software used

[0350] This system uses servers and terminals as its main hardware. The server requires a high-performance processor, a large amount of memory, and a database (e.g., MySQL, PostgreSQL) to store large amounts of data. It also incorporates an AI engine (e.g., TensorFlow, PyTorch) for emotion recognition and data analysis. The terminals are devices equipped with cameras and microphones (e.g., smartphones, tablets).

[0351] Explanation of program processing

[0352] The program of this system performs processing roughly according to the following steps.

[0353] User Input

[0354] The user inputs product information into the terminal. For example, "Category: Jacket," "Size: M," "Color: Blue," "Condition: Almost New," etc. The terminal confirms the user's input and prepares to send it to the server.

[0355] Data reception and analysis

[0356] The server receives the product information sent from the device. It then stores the data in a database and begins analyzing the received data. The server's AI confirms that the product category is "jacket" and identifies that the size information sent is "M," but that specific measurements for shoulder width, chest width, and sleeve length are missing.

[0357] Emotion recognition by emotion engine

[0358] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine. The server's emotion engine analyzes these and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.). The acquired emotional information is recorded in a database as an analysis result.

[0359] Advice Generation

[0360] The server's AI generates specific product description advice based on the missing information and the acquired emotional information. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width XX cm, chest width XX cm, sleeve length XX cm)." The content and tone of the advice are adjusted to reflect the information from the emotional engine, such as "concise instructions if the customer is in a hurry" or "detailed instructions if the customer is relieved."

[0361] Learning from purchasing data

[0362] The server periodically collects past purchase data, including product categories, product description details, and buyer behavior data. The server's AI uses this data to learn what product descriptions increase purchase motivation and update its advice generation algorithm.

[0363] Presenting to the user

[0364] The server sends the generated advice to the user's terminal, which displays the received advice to the user, who then modifies the product description in accordance with the advice.

[0365] User correction and resubmission

[0366] Based on the advice from the server, the user measures the specific dimensions, takes photos of the whole area and the tag, and then resends the corrected information from the device to the server.

[0367] Survey

[0368] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0369] Collecting and learning from survey results

[0370] The server collects the survey results and stores them in a database. The server's AI learns from the survey results and uses them to generate future advice.

[0371] Specific examples

[0372] 1. A user enters "Jacket", "Size: M", "Color: Blue", "Condition: Like New". The emotion engine detects the emotion "Impatient".

[0373] 2. The server generates specific and concise advice: "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Sample sentences for concise descriptions are shown below: Shoulder width XX cm, chest width XX cm, sleeve length XX cm." The user measures the measurements and briefly amends the product description.

[0374] Prompt Sentence Examples

[0375] "If the jacket is a size medium, please provide detailed measurements such as shoulder width, chest width, and sleeve length. Also, adjust the instructions to be brief or detailed depending on the user's emotional state."

[0376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0377] Step 1:

[0378] The user inputs product information into the terminal. The user inputs information such as "Category: Jacket," "Size: M," "Color: Blue," and "Condition: Almost new" into the input form on the terminal. The terminal checks the input product information, formats it, and prepares to send it to the server. Input: User-entered data, Output: Formatted product information data

[0379] Step 2:

[0380] The server receives the product information sent from the terminal. The server parses the received data in JSON format and checks whether the required fields are filled in. The server stores the received data in a database. Input: Formatted product information data, Output: Records stored in the database

[0381] Step 3:

[0382] The server's AI confirms that the product category is "jacket" and identifies that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing. The server identifies the missing information and lists it. Input: Records stored in the database, Output: List of missing information

[0383] Step 4:

[0384] The device collects facial expressions and voice data when the user enters product information, and sends this data to the emotion engine in real time. The emotion engine uses facial expression recognition and voice analysis technology to detect the user's emotional state (e.g., impatience, anxiety, relief). Input: User's facial and voice data, Output: User's emotional state

[0385] Step 5:

[0386] The emotion engine on the server records the detected emotional state in a database as an analysis result. Input: User's emotional state, Output: Analysis result stored in the database

[0387] Step 6:

[0388] The server's AI generates specific product description advice based on the missing information and emotional information. For example, it generates advice such as "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g. shoulder width XX cm, chest width XX cm, sleeve length XX cm)." It reflects the information from the emotional engine and adjusts the content and tone of the advice in the form of "concise instructions if the user is in a hurry" or "detailed instructions if the user is relieved." Input: Missing information list, user's emotional state, Output: Generated advice

[0389] Step 7:

[0390] The server sends the generated advice to the user's terminal. The terminal displays the received advice to the user, who then modifies the product description according to the advice. Input: Generated advice, Output: Advice displayed on the user's terminal

[0391] Step 8:

[0392] Based on the advice from the server, the user measures the specific dimensions and takes photos of the overall product and the tag. The user then resends the corrected information from their device to the server. Input: Dimensional information and photo data, Output: Re-sent product information data

[0393] Step 9:

[0394] The server sends a survey to the customer, asking about their satisfaction with the purchased product and the usefulness of the product description. Input: Customer data, Output: Sent survey link

[0395] Step 10:

[0396] The server collects the survey results and stores them in a database. The server's AI learns from the survey results and uses them to generate future advice. Input: Survey result data, Output: Feedback data stored in the database

[0397] (Application example 2)

[0398] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0399] While many sellers want to improve the quality of product descriptions in online auctions and electronic markets, they often don't know how to create specific and compelling product descriptions. Furthermore, it can be difficult to create consistent, high-quality descriptions due to emotional states. Furthermore, they are unable to effectively utilize buyer feedback and past purchase data, which hinders progress in improving product descriptions.

[0400] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving product information input by the seller, analysis means for analyzing the received product information and identifying information deficiencies, advice generation means for generating specific product description advice for the seller based on the analysis, means for presenting the generated advice to the seller, emotion recognition means for recognizing the seller's emotions in real time and adjusting the content of the advice, and advice adjustment means for adapting the tone and content of the advice based on user emotion information. This makes it possible to create effective and attractive product descriptions while taking into account the emotional state faced by the seller, and to increase purchasing desire.

[0401] "Seller" refers to an individual or corporation that enters and publishes product information in order to sell products on online auctions or electronic markets.

[0402] "Product Information" refers to detailed information necessary for sales, such as product category, size, color, condition, price, and description.

[0403] "Means for receiving" refers to the hardware or software used to receive product information provided by sellers.

[0404] "Analysis means" refers to algorithms or software for analyzing received product information and identifying missing information.

[0405] "Advice generation means" refers to a system that provides sellers with specific improvements and suggestions for product descriptions based on the analysis results.

[0406] "Means for presentation" refers to an interface for displaying or communicating the generated advice to the seller in an easy-to-view format.

[0407] "Emotion recognition means" refers to sensors and analytical algorithms that recognize the seller's emotional state in real time.

[0408] "Advice adjustment means" refers to a system for adjusting the tone and content of advice to suit the seller's current emotional state based on information from the emotion recognition means.

[0409] "Purchase data" refers to a series of data related to product sales, such as past purchase history, buyer feedback, and product description details.

[0410] A "survey" is a survey conducted among buyers to collect feedback on the usefulness of product descriptions and satisfaction with products.

[0411] This invention is a system for improving the quality of product descriptions in online auctions and electronic marketplaces. It involves a process in which a seller inputs product information, analyzes it to identify missing information, and generates and presents specific advice. It also has a function to recognize the seller's emotional state in real time using emotion recognition means and adjust the content and tone of the advice accordingly. The main components of this system and their operation are described in detail below.

[0412] System Components and Operation

[0413] 1. Receiving product information (user input)

[0414] A user uses a smartphone application to input product information, such as "smartphone case," "size: 6 inches," "color: black," and "condition: new." This data is sent from the user's device to a server. During this process, the smartphone's camera and microphone are also used to collect emotional information.

[0415] 2. Data reception and analysis (server processing)

[0416] The server receives product information sent from the user's device. The received data is stored in a database, and the product information is analyzed using analytical means. For example, it may confirm that the product category is a "smartphone case," but identify that specific dimensional information is missing. Here, a database management system (e.g., PostgreSQL) and an AI analysis engine (e.g., TensorFlow) are used.

[0417] 3. Emotion Recognition and Data Processing (Server Processing)

[0418] Facial expression and voice data collected when the user enters product information is sent to the emotion recognition means. The emotion recognition engine on the server analyzes this data and recognizes the user's emotional state (e.g., anxiety, relief, etc.). This recognition result is also stored in the database. Emotion recognition uses an emotion recognition library (e.g., OpenCV or Microsoft Emotion API).

[0419] 4. Generating and Presenting Advice (Server and Terminal Processing)

[0420] The server's AI model (e.g., GPT-3) generates specific product description advice based on the analysis results and emotional information. For example, the advice might be, "Please add specific details such as color, material, and case thickness. It would also be a good idea to add a statement guaranteeing the quality of the product so that buyers can make a purchase with confidence." The generated advice is sent to the user's device and displayed in a smartphone application.

[0421] 5. Learning purchasing data (server processing)

[0422] The server periodically collects past purchase data to learn which product descriptions encourage purchases. This data includes product categories, product details, and buyer behavior data. This allows the advice generation algorithm to be continuously improved.

[0423] 6. Survey implementation and learning (server processing)

[0424] The server sends a questionnaire to the customer, asking about their satisfaction with the purchased product and the usefulness of the product description. The collected survey results are also used as learning data and reflected in future advice generation.

[0425] Specific examples

[0426] For example, if a user enters "smartphone case," "size: 6 inches," "color: black," and "condition: new" into a smartphone app and the emotion engine detects the emotion of "anxiety," the server will generate and display specific advice such as, "Please add specific descriptions such as the color, material, and thickness of the case. It would also be a good idea to add a statement guaranteeing the quality of the product so that buyers can make their purchase with confidence."

[0427] Prompt Sentence Examples

[0428] "A user is trying to list a smartphone case. Please generate specific product description advice based on the following information: Product information: 'Size: 6 inches, Color: Black, Condition: New'. User sentiment: 'Anxious'. Please add specific dimensions and ask for advice."

[0429] This makes it possible to create effective and attractive product descriptions while taking into account the emotional state that the seller faces, thereby increasing purchasing motivation.

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] User Input

[0433] The user uses an application on their device (smartphone) to input product information (for example, "smartphone case," "size: 6 inches," "color: black," and "condition: new"). The input product information is temporarily stored on the device, and at the same time, the device's camera and microphone are used to collect the user's facial expressions and voice in real time. This allows emotional data to be collected as well. The input data is in the form of text and metadata.

[0434] Step 2:

[0435] Receiving and storing data

[0436] The device sends product information and emotion data to the server, which receives it and stores it in a database (e.g., PostgreSQL). Product information is stored as text data, and emotion data is stored as metadata. This lays the foundation for subsequent analysis and advice generation.

[0437] Step 3:

[0438] Data analysis

[0439] The server's analysis means (AI analysis engine, e.g., TensorFlow) analyzes the received product information and identifies missing information. For example, it confirms that the product category is "smartphone case," but identifies that specific dimensional information is missing. This analysis result is saved back into the database. In this step, text analysis is performed, and data calculations are performed to identify missing information.

[0440] Step 4:

[0441] emotion recognition

[0442] Facial expression and voice data collected when the user enters product information is sent to the server's emotion recognition engine (e.g., OpenCV or Microsoft Emotion API). The server analyzes this data and recognizes the user's emotional state (e.g., "anxiety," "relief," etc.). The recognition results are stored in a database as analysis results and are used to generate subsequent advice. Analysis of emotion data includes image analysis and voice analysis.

[0443] Step 5:

[0444] Advice Generation

[0445] The server's AI model (e.g., GPT-3) generates specific product description advice based on the analysis results and emotional information. For example, the advice might be, "Please add specific details such as color, material, and case thickness." The tone and content are also adjusted based on the emotional data. This generated advice is then stored back in the database. The generative AI model performs text generation and data calculations based on the prompt.

[0446] Step 6:

[0447] Providing advice

[0448] The server sends the generated advice to the user's terminal. On the user's terminal, the received advice is displayed to the user through an application. In this step, data is sent from the server to the terminal and displayed to the user. The advice is displayed in text format.

[0449] Step 7:

[0450] Collecting and learning from purchasing data

[0451] The server periodically collects past purchase data and stores it in a database. The collected data includes product categories, product descriptions, and buyer behavior data. The server's AI analysis engine analyzes this data and improves the advice generation algorithm. This step uses data collection and machine learning algorithms.

[0452] Step 8:

[0453] Conducting a survey

[0454] The server sends a questionnaire to the buyer, asking about the usefulness of the product description and their satisfaction with the product. Feedback from the buyer is collected by the server and stored in a database. The results of this questionnaire are used to generate future advice. Data is transmitted between the server and the buyer.

[0455] Step 9:

[0456] Studying survey results

[0457] The server's AI analysis engine analyzes the survey results and uses feedback on product satisfaction and the usefulness of product descriptions as learning data. This improves the accuracy of future advice generation. This step involves data analysis and machine learning.

[0458] Through these steps, sellers can receive specific advice based on real-time emotion recognition and purchasing data, enabling them to create high-quality product descriptions.

[0459] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0460] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0461] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0462] [Second embodiment]

[0463] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0464] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0465] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0466] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0467] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0468] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0469] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0470] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0471] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0472] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0473] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0474] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0475] This invention includes a system for providing high-quality product descriptions to sellers of online auctions and electronic markets, allowing sellers to create specific product descriptions that encourage purchases.

[0476] System Overview

[0477] This system has the following main functions:

[0478] 1. How to receive product information from sellers

[0479] 2. Analysis means for analyzing received product information and identifying missing information

[0480] 3. Advice generation method that generates specific product description advice based on the analysis results

[0481] 4. A method for presenting the generated advice to the seller

[0482] 5. Learning tools to collect and learn from past purchase data to improve the quality of advice

[0483] 6. Surveying customers and learning from the results

[0484] Program processing explanation

[0485] 1. User Input

[0486] The user inputs product information from the terminal. For example, the user might input product category ("jacket"), size ("M"), color ("blue"), and product condition ("almost new").

[0487] 2. Data Reception and Analysis

[0488] The server receives the product information sent from the device. The AI ​​on the server analyzes this information and identifies any missing information or areas for improvement. For example, if only "Size: M" is listed in the "Jacket" category, it will determine that specific measurements (shoulder width, chest width, sleeve length, etc.) are missing.

[0489] 3. Advice Generation

[0490] The server's AI generates specific advice based on the analysis results. For example, it might generate advice like, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. For example: Shoulder width XX cm, chest width XX cm, sleeve length XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[0491] 4. Learning from purchasing data

[0492] The server collects and organizes past purchase data, and the AI ​​learns from it to improve the accuracy of advice it can give to sellers. For example, it can learn that the more specific the size information, the higher the purchase rate.

[0493] 5. Presentation to the User

[0494] The server sends the generated advice to the terminal and displays it to the user, who can then modify or resubmit the product description according to the advice.

[0495] 6. Survey and learning

[0496] The server sends a questionnaire to the customer about their satisfaction with the purchased product and the usefulness of the product description. The received results are analyzed, and the AI ​​learns from the data, allowing it to generate more precise advice.

[0497] Specific examples

[0498] Example 1:

[0499] The user enters "Jacket", "Size: M", "Color: Blue", and "Condition: Like New".

[0500] The server determined that specific measurements were insufficient and generated the advice, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag."

[0501] Users measure, take photos, and edit product descriptions.

[0502] Example 2:

[0503] In a customer survey, we received feedback that "specific dimensions were listed, so I was able to make the purchase with confidence."

[0504] The server learns from this and reflects it in future advice generation.

[0505] This will increase the matching rate between buyers and sellers and make transactions smoother.

[0506] The processing flow will be explained below.

[0507] Step 1: User Input

[0508] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[0509] The terminal checks the input product information and prepares to send it to the server.

[0510] Step 2: Receiving data

[0511] The server receives the product information sent from the terminal.

[0512] The server stores the received data in a database as a preprocessing step for analysis.

[0513] Step 3: Data analysis

[0514] The server's AI confirms that the product category is "jacket."

[0515] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[0516] The server's AI also checks the color and state information to make sure there are no problems with these.

[0517] Step 4: Advice Generation

[0518] The server's AI generates specific product description advice based on the missing information. For example, it might generate advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width xx cm, chest width xx cm, sleeve length xx cm)."

[0519] You will also be asked to take a photo of the whole thing and a photo of the tag.

[0520] Step 5: Learn the purchasing data

[0521] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[0522] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[0523] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[0524] Step 6: Present to the user

[0525] The server transmits the generated advice to the user's terminal.

[0526] The device displays the received advice to the user, who then modifies the product description in accordance with the advice.

[0527] Step 7: User corrections and resubmission

[0528] Based on advice from the server, the user measures specific dimensions and takes photos of the overall object and the tag.

[0529] The user retransmits the corrected information from the terminal to the server.

[0530] Step 8: Survey

[0531] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0532] Step 9: Collect and learn from survey results

[0533] The server collects the survey results and stores them in a database.

[0534] The server's AI learns from the survey results and reflects them in generating future advice.

[0535] This allows sellers to provide specific product descriptions that increase purchasing motivation, and improves the matching rate between buyers and sellers.

[0536] Example 1

[0537] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0538] In online auctions and electronic markets, sellers need to create attractive and specific product descriptions, but in many cases, the information is insufficient or vague, preventing them from motivating buyers. Furthermore, sellers may not receive appropriate advice, leading to sluggish sales. Furthermore, there is also the issue of past purchase data and feedback from buyers not being fully utilized, preventing the quality of advice from improving.

[0539] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0540] In this invention, the server includes means for receiving product information input by a seller, analysis means for analyzing the received product information and identifying insufficient information, advice generation means for generating specific product description advice for the seller based on the analysis, means for presenting the generated advice to the seller, means for transmitting the generated product description advice to a terminal and displaying it to the seller, means for collecting past purchase data and improving the quality of the product description advice based on the data, and means for conducting a survey of buyers and improving the quality of the product description advice based on the results. This enables the seller to create specific product descriptions that encourage purchases, and also increases buyer satisfaction.

[0541] A "seller" is an individual or company that lists an item for sale on an online auction or electronic marketplace.

[0542] "Product information" refers to information about the product being offered for sale by the seller, including, for example, category, size, color, condition, etc.

[0543] A "server" is a computer system that receives, processes, and transmits data over a network.

[0544] A "terminal" is a device through which sellers input product information and receive generated advice, etc., and specifically refers to a PC or smartphone.

[0545] The "analysis means" is software or hardware that has the function of analyzing the received product information and identifying missing information or areas for improvement.

[0546] The "advice generation means" is software or hardware having a function for automatically generating specific product description advice to the seller based on the analysis results.

[0547] The "presentation means" refers to software or hardware having a function for presenting the generated advice to the seller visually or in some other way.

[0548] "Past purchasing data" refers to information about past transactions on online auctions and electronic markets, and specifically includes sales data, buyer feedback, and the like.

[0549] "Survey" refers to a questionnaire used to collect feedback provided by buyers after purchase, including satisfaction levels and product ratings.

[0550] The "AI analysis module" is software that uses artificial intelligence technology to analyze product information and identify missing information and areas for improvement.

[0551] The "AI advice generation module" is software that uses artificial intelligence technology to generate specific advice based on analysis results.

[0552] The "AI learning module" is software that trains artificial intelligence based on past purchasing data and survey results to improve the quality of advice.

[0553] A "buyer" is an individual or company that purchases goods through an online auction or electronic marketplace.

[0554] The present invention provides a system that allows sellers in online auctions and electronic markets to create specific product descriptions that encourage purchases. This system allows sellers to input appropriate product information and receive optimal product descriptions based on that information.

[0555] First, the user enters product information using their own device (PC, smartphone, etc.), including specific information such as product category (e.g., jacket), size (e.g., M), color (e.g., blue), and product condition (e.g., almost new).

[0556] The terminal sends the input product information to a server, which is equipped with an AI analysis module that analyzes the received product information.

[0557] When the server receives product information, it first stores it in a database. Next, an AI analysis module reads the product information and identifies missing information and areas for improvement. Based on this analysis, the AI ​​generates specific advice. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Example: Shoulder width XX cm, chest width XX cm, sleeve length XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[0558] The generated advice is sent to the terminal by the server and displayed to the user, who can then follow the advice to modify the product description and send it again.

[0559] Furthermore, the server collects past purchase data and uses it to improve the quality of advice. The server is equipped with an AI learning module that learns from past transaction data and customer feedback to improve the accuracy of the advice it generates. For example, it learns the trend that "the more specific the size information, the higher the purchase rate" and generates advice based on this.

[0560] The server also conducts surveys on customers and collects the results, which the AI ​​learning module uses to generate even higher quality advice.

[0561] Specific examples of how this system works include the following scenarios:

[0562] Specific examples

[0563] The user enters "Jacket," "Size: M," "Color: Blue," and "Condition: Like New." The device sends this input information to the server. The server receives the product information and, after analysis, determines that specific measurements are missing. The server's AI analysis module generates advice saying, "Please enter the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag." The device displays this advice on the user interface. The user measures the measurements, takes photos, and corrects the product description.

[0564] An example prompt might be, "When I list a new item, I'd like some advice on how to include specific dimensions and detailed photos. Also, suggestions based on past purchasing data would be helpful."

[0565] This system allows sellers to create detailed product descriptions that encourage purchases, improving buyer satisfaction and helping to ensure smooth transactions.

[0566] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0567] Step 1:

[0568] The user inputs product information from their own device (PC, smartphone, etc.) This product information includes product category (e.g., jacket), size (e.g., M), color (e.g., blue), and product condition (e.g., almost new).

[0569] Input: Product information (category, size, color, condition)

[0570] Output: Product information data sent by the device to the server

[0571] Specific behavior:

[0572] The user opens a web form and enters product information into each field.

[0573] The user checks the input contents and clicks the send button.

[0574] The terminal transmits the input information to the server.

[0575] Step 2:

[0576] The server receives the product information sent from the device, stores it in a database, and an AI analysis module identifies any missing information or areas that need improvement.

[0577] Input: Product information data received from the terminal

[0578] Output: A list of missing information and improvements analyzed by the AI ​​analysis module

[0579] Specific behavior:

[0580] The server stores the received product information in a database.

[0581] The server's AI analysis module reads the product information and identifies any missing parts.

[0582] The server will list any identified gaps or areas for improvement.

[0583] Step 3:

[0584] The server's AI generates specific advice based on the analysis results. For example, it might say, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. For example, shoulder width: XX cm, chest width: XX cm, sleeve length: XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[0585] Input: Analysis results (list of missing information and improvements)

[0586] Output: Specific advice generated

[0587] Specific behavior:

[0588] The server's AI advice generation module automatically generates advice based on the analysis results.

[0589] The server compiles the generated advice into a list.

[0590] Step 4:

[0591] The server sends the generated advice to the terminal and displays it to the user, who can then follow the advice to modify the product description and resubmit it.

[0592] Input: Generated specific advice

[0593] Output: Advice displayed on the terminal

[0594] Specific behavior:

[0595] The server sends the generated advice to the terminal in JSON format.

[0596] The terminal displays the received advice on the user interface.

[0597] The user checks the displayed advice and modifies the product description.

[0598] Step 5:

[0599] The server collects past purchase data and uses it to improve the quality of advice. An AI learning module learns from this data to improve the accuracy of advice.

[0600] Input: Past purchase data

[0601] Output: Improved advice accuracy due to the trained model

[0602] Specific behavior:

[0603] The server extracts past purchase data from a database.

[0604] The server's AI learning module uses the extracted purchasing data to learn.

[0605] The server stores the learning results in a database and reflects them in future advice generation.

[0606] Step 6:

[0607] The server conducts surveys of customers and collects the results. The AI ​​learning module also learns from these survey results and generates even higher quality advice.

[0608] Input: Survey results from buyers

[0609] Output: Further improved advice accuracy due to the trained model

[0610] Specific behavior:

[0611] The server automatically sends a questionnaire to the purchaser.

[0612] The purchaser answers the questionnaire and submits it.

[0613] The server stores the received survey results in a database and provides them to the AI ​​learning module.

[0614] The AI ​​learning module learns from this and generates even more accurate advice.

[0615] (Application example 1)

[0616] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0617] In online auctions and electronic markets, if sellers do not effectively explain their products, it can discourage buyers and prevent transactions from proceeding smoothly. This requires sellers to provide detailed product information, which takes time and effort. Furthermore, it is often difficult to identify the missing information, resulting in a decline in the quality of product descriptions. Therefore, a system is needed that can continuously improve the quality of advice by utilizing past purchase data and buyer feedback.

[0618] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0619] In this invention, the server includes a means for inputting product information, an analysis means for analyzing the input product information and identifying missing information, an advice generation means for generating specific product description advice based on the analysis, a means for presenting the generated advice, and a means for learning past purchase data using a generative AI model to improve the quality of the advice. This enables sellers to quickly create effective and detailed product descriptions, increasing buyer trust and facilitating transactions.

[0620] "Product information" refers to detailed information about a product entered by a seller in an online auction or online marketplace. This information includes attribute information such as the product name, category, size, color, and condition.

[0621] "Analysis means" refers to the technology or method for analyzing input product information and identifying missing information or areas requiring improvement.

[0622] "Advice generation means" refers to a technique or method for instructing sellers on specific improvements to product descriptions and methods for providing additional information based on the analysis results.

[0623] "Presentation means" refers to the technology or method for presenting the generated advice to the seller in an easy-to-view manner and encouraging necessary improvements.

[0624] A "generative AI model" refers to an artificial intelligence model that learns from past purchasing data and customer feedback to constantly improve the quality of advice.

[0625] "Past purchase data" is historical information about past purchases, and includes data such as product category, number of purchases, and buyer ratings.

[0626] A "customer survey" is a questionnaire-based survey sent to buyers to assess the usefulness of product descriptions and their satisfaction with the purchased product.

[0627] The system of the present invention is configured to provide sellers with specific advice to improve the quality of their product descriptions. The main components of the system and their roles will be described below.

[0628] System configuration:

[0629] This system is realized mainly using the following hardware and software.

[0630] Hardware: The smartphone or computer used by the seller

[0631] Software: Server, SpaCy, scikit-learn, generative AI model

[0632] 1. Product information input method:

[0633] The user (seller) enters product information via a smartphone or computer, such as "Jacket, Size M, Color: Blue, Condition: Almost New."

[0634] 2. Analysis method:

[0635] The server uses SpaCy to analyze the input product information. Specifically, it extracts important tags (nouns and adjectives) from the information and identifies any missing information.

[0636] 3. Advice Generation Methods:

[0637] The server uses scikit-learn functions to generate specific advice about missing information or information that needs improvement. For example, specific advice might be generated such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag."

[0638] 4. Means of presentation:

[0639] The generated advice is displayed on the user's smartphone or computer, and the seller can revise the product description accordingly.

[0640] 5. Learning tools:

[0641] The generative AI model on the server learns from past purchase data and customer survey results. Based on this data, it continuously improves the quality of advice. For example, it learns trends such as "products with specific dimensional information have a higher purchase rate."

[0642] Examples:

[0643] User Input: Seller enters "Jacket, Size M, Color: Blue, Condition: Like New."

[0644] Analysis result: The server analyzes the input information using Spacy and determines that the information for "shoulder width," "chest width," and "sleeve length" is missing.

[0645] Generated advice: Using scikit-learn, the server generates the advice, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag." and presents it to the seller.

[0646] Example prompt sentence:

[0647] Product information: Blue jacket, size M, condition almost new

[0648] From the analysis results, we identified the missing information as "shoulder width," "chest width," and "sleeve length." Please create a product description that includes specific examples like the ones below.

[0649] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0650] Step 1:

[0651] User enters product information

[0652] Users input product information using a smartphone or computer. This input includes detailed information such as product category, size, color, and condition. Specific input is possible, such as "Jacket, Size M, Color: Blue, Condition: Almost New."

[0653] Step 2:

[0654] Server receives product information

[0655] The server receives the product information entered by the user and stores it in a database for use in subsequent analysis.

[0656] Step 3:

[0657] The server analyzes the input information

[0658] The server uses SpaCy to analyze the received product information. Specifically, it extracts important tags (nouns and adjectives) and identifies missing information. For example, it determines that the shoulder width, chest width, and sleeve length are missing for a jacket.

[0659] Input: Product information entered by the user (e.g., "Jacket, Size M, Color: Blue, Condition: Like New")

[0660] Output: Extracted important tags (e.g., "shoulder width," "chest width," and "sleeve length" are determined to be missing)

[0661] Step 4:

[0662] Server generates advice

[0663] The server uses scikit-learn to generate specific advice based on the missing information. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and the tag."

[0664] Input: Missing information (e.g. "shoulder width", "chest width", "sleeve length")

[0665] Output: Generated specific advice (e.g., "Please provide the specific measurements for shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and a photo of the tag.")

[0666] Step 5:

[0667] The server provides advice to the user

[0668] The server sends the generated advice to the user's smartphone or PC, allowing the user to refer to the advice and revise the product description.

[0669] Input: Generated advice (e.g., "Please provide the specific measurements for shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and a photo of the tag.")

[0670] Output: Advice displayed on the user's terminal

[0671] Step 6:

[0672] The server learns the purchasing data

[0673] The generative AI model on the server collects past purchase data and learns from it. For example, it can extract trends such as "products with specific dimensional information have a higher purchase rate." The results of this learning are reflected in future advice generation.

[0674] Input: Past purchase data

[0675] Output: Learning results (e.g., "Products with specific dimensions have a higher purchase rate.")

[0676] Step 7:

[0677] The server learns the survey results

[0678] The server conducts surveys of shoppers and collects and learns from the results. This provides information on the usefulness of product descriptions and satisfaction with purchased products. The generative AI model uses this information to further improve the quality of advice.

[0679] Input: Customer survey results

[0680] Output: Learning results (e.g., feedback such as "The specific dimensions were listed, so I was able to make the purchase with confidence.")

[0681] Through the above steps, sellers can create high-quality product descriptions, which increases buyers' trust and facilitates smooth transactions.

[0682] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0683] This invention includes a system that provides high-quality product descriptions to sellers of online auctions and electronic marketplaces. This system allows sellers to create specific product descriptions that encourage purchases. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, the system can provide more personalized advice.

[0684] System Overview

[0685] This system has the following main functions:

[0686] 1. How to receive product information from sellers

[0687] 2. Analysis means for analyzing received product information and identifying missing information

[0688] 3. Advice generation method that generates specific product description advice based on the analysis results

[0689] 4. A method for presenting the generated advice to the seller

[0690] 5. Learning tools to collect and learn from past purchase data to improve the quality of advice

[0691] 6. A means of surveying buyers and learning from their results

[0692] 7. An emotion engine that recognizes user emotions and uses that information to generate advice.

[0693] Program processing explanation

[0694] 1. User Input

[0695] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[0696] The terminal checks the input product information and prepares to send it to the server.

[0697] 2. Data Reception and Analysis

[0698] The server receives the product information sent from the terminal.

[0699] The server stores the received data in a database as a preprocessing step for analysis.

[0700] The server's AI confirms that the product category is "jacket."

[0701] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[0702] 3. Emotion Recognition by Emotion Engine

[0703] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine.

[0704] The server's emotion engine analyzes this and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.).

[0705] The server stores the emotion information obtained from the emotion engine as the analysis result.

[0706] 4. Advice Generation

[0707] The server's AI generates specific product description advice based on the missing information. For example, it generates specific advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width xx cm, chest width xx cm, sleeve length xx cm)."

[0708] The information from the emotion engine is reflected and the content and tone of the advice is adjusted, such as "brief instructions if the user is anxious" or "detailed instructions if the user is relieved."

[0709] 5. Learning from purchasing data

[0710] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[0711] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[0712] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[0713] 6. Presentation to the User

[0714] The server transmits the generated advice to the user's terminal.

[0715] The device displays the received advice to the user, who then modifies the product description in accordance with the advice.

[0716] 7. User Modifications and Resubmissions

[0717] Based on advice from the server, the user measures specific dimensions and takes photos of the overall object and the tag.

[0718] The user retransmits the corrected information from the terminal to the server.

[0719] 8. Survey implementation

[0720] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0721] 9. Collecting and Learning from Survey Results

[0722] The server collects the survey results and stores them in a database.

[0723] The server's AI learns from the survey results and reflects them in generating future advice.

[0724] Specific examples

[0725] Example 1:

[0726] The user inputs "Jacket", "Size: M", "Color: Blue", and "Condition: Like New". The emotion engine detects the emotion "Impatience".

[0727] The server generates specific and concise advice: "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Sample sentences for concise descriptions are shown below: Shoulder width XX cm, chest width XX cm, sleeve length XX cm."

[0728] The user measures the dimensions and briefly edits the product description.

[0729] Example 2:

[0730] In a customer survey, we received feedback that "specific dimensions were listed, so I was able to make the purchase with confidence."

[0731] The server learns from this and reflects it in future advice generation.

[0732] In this way, by providing specific advice that takes into account the user's emotions, it is possible to improve the quality of product descriptions and further increase the matching rate between buyers and sellers.

[0733] The processing flow will be explained below.

[0734] Step 1: User Input

[0735] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[0736] The terminal checks the input product information and prepares to send it to the server.

[0737] Step 2: Receiving data

[0738] The server receives the product information sent from the terminal.

[0739] The server stores the received data in a database as a preprocessing step for analysis.

[0740] Step 3: Emotion recognition by the emotion engine

[0741] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine.

[0742] The server's emotion engine analyzes this and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.).

[0743] The server stores the emotion information obtained from the emotion engine as analysis data.

[0744] Step 4: Data analysis

[0745] The server's AI analyzes the received product information.

[0746] The server's AI confirms that the product category is "jacket."

[0747] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[0748] The server's AI also checks color and state information, and also refers to emotion information.

[0749] Step 5: Advice Generation

[0750] The server's AI generates specific product description advice for sellers based on the data analysis results and emotional information.

[0751] For example, if the emotional information is "impatience," the system generates concise advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width XX cm, chest width XX cm, sleeve length XX cm). Also, please take photos of the entire product and the tag."

[0752] If the emotional information is "peace of mind," detailed advice is provided: "Please describe the product's features in detail and include specific measurements such as shoulder width, chest width, and sleeve length. Photos should include an overall view of the product, tags, and details."

[0753] Step 6: Present to the user

[0754] The server transmits the generated advice to the user's terminal.

[0755] The terminal displays the received advice to the user.

[0756] Step 7: User corrections and resubmission

[0757] The user makes the necessary corrections based on the provided advice, such as taking specific measurements and taking photos of the overall product and the tag.

[0758] The user retransmits the corrected information from the terminal to the server.

[0759] Step 8: Learn your purchasing data

[0760] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[0761] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[0762] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[0763] Step 9: Survey

[0764] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0765] Step 10: Collect and learn from survey results

[0766] The server collects the survey results and stores them in a database.

[0767] The server's AI learns from the survey results and reflects them in generating future advice.

[0768] In this way, sellers can create specific and inspiring product descriptions by providing specific advice that takes users' emotions into account, further increasing the chances of matching buyers and sellers.

[0769] Example 2

[0770] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0771] In online auctions and electronic markets, if sellers provide insufficient product descriptions, buyers have difficulty understanding the product details, which reduces their willingness to purchase. Furthermore, some users are easily influenced by their emotions, and the quality and content of product descriptions can directly affect their willingness to purchase. Therefore, there is a need for support for sellers to provide high-quality, specific product descriptions that take emotions into consideration.

[0772] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving product information input by a seller, a means for analyzing the received product information to identify insufficient information, a means for acquiring and analyzing the user's emotional state based on the input product information, a means for generating specific product description advice to the seller based on the analysis, and a means for presenting the generated advice to the seller. This enables the seller to supplement the insufficient information and provide a high-quality product description that takes the user's emotions into consideration.

[0773] A "seller" is an individual or organization that sells goods on an online auction or electronic marketplace.

[0774] "Product information" refers to detailed information about the product being sold by the seller, including, specifically, the category, size, color, condition, and the like.

[0775] The "emotional state" refers to the psychological state of the user when inputting product information, and examples include feelings such as impatience, anxiety, and relief.

[0776] The "receiving means" is a function that receives product information sent from the terminal at the server and performs processing to store the information in the database.

[0777] The "analysis means" is a function for analyzing received product information and identifying missing information.

[0778] The "emotion recognition means" is a function for analyzing the user's facial expressions and voice and identifying their emotional state.

[0779] The "advice generation means" is a function for dynamically generating specific advice on product descriptions based on the results of the analysis means and emotion recognition means.

[0780] The "presentation means" is a function for displaying the generated advice to the seller in an easy-to-understand manner.

[0781] "Purchase data" refers to data including product categories, detailed product descriptions, purchaser behavior data, and the like from past transactions.

[0782] A "survey" is a survey conducted to collect feedback from buyers about their satisfaction with the purchased product and the usefulness of the product description.

[0783] "Collection means" refers to a function for effectively collecting purchasing data and survey results.

[0784] The "learning means" is a function that uses collected data to learn, through a machine learning algorithm, what kind of product descriptions will increase purchasing desire, and reflects this in the advice generation algorithm.

[0785] This invention is a system that provides high-quality product descriptions to sellers of online auctions and electronic markets. This system allows sellers to create specific product descriptions that encourage purchases. In addition, by incorporating an emotion engine that recognizes the user's emotions, the system can provide more personalized advice.

[0786] Hardware and software used

[0787] This system uses servers and terminals as its main hardware. The server requires a high-performance processor, a large amount of memory, and a database (e.g., MySQL, PostgreSQL) to store large amounts of data. It also incorporates an AI engine (e.g., TensorFlow, PyTorch) for emotion recognition and data analysis. The terminals are devices equipped with cameras and microphones (e.g., smartphones, tablets).

[0788] Explanation of program processing

[0789] The program of this system performs processing roughly according to the following steps.

[0790] User Input

[0791] The user inputs product information into the terminal. For example, "Category: Jacket," "Size: M," "Color: Blue," "Condition: Almost New," etc. The terminal confirms the user's input and prepares to send it to the server.

[0792] Data reception and analysis

[0793] The server receives the product information sent from the device. It then stores the data in a database and begins analyzing the received data. The server's AI confirms that the product category is "jacket" and identifies that the size information sent is "M," but that specific measurements for shoulder width, chest width, and sleeve length are missing.

[0794] Emotion recognition by emotion engine

[0795] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine. The server's emotion engine analyzes these and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.). The acquired emotional information is recorded in a database as an analysis result.

[0796] Advice Generation

[0797] The server's AI generates specific product description advice based on the missing information and the acquired emotional information. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width XX cm, chest width XX cm, sleeve length XX cm)." The content and tone of the advice are adjusted to reflect the information from the emotional engine, such as "concise instructions if the customer is in a hurry" or "detailed instructions if the customer is relieved."

[0798] Learning from purchasing data

[0799] The server periodically collects past purchase data, including product categories, product description details, and buyer behavior data. The server's AI uses this data to learn what product descriptions increase purchase motivation and update its advice generation algorithm.

[0800] Presenting to the user

[0801] The server sends the generated advice to the user's terminal, which displays the received advice to the user, who then modifies the product description in accordance with the advice.

[0802] User correction and resubmission

[0803] Based on the advice from the server, the user measures the specific dimensions, takes photos of the whole area and the tag, and then resends the corrected information from the device to the server.

[0804] Survey

[0805] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0806] Collecting and learning from survey results

[0807] The server collects the survey results and stores them in a database. The server's AI learns from the survey results and uses them to generate future advice.

[0808] Specific examples

[0809] 1. A user enters "Jacket", "Size: M", "Color: Blue", "Condition: Like New". The emotion engine detects the emotion "Impatient".

[0810] 2. The server generates specific and concise advice: "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Sample sentences for concise descriptions are shown below: Shoulder width XX cm, chest width XX cm, sleeve length XX cm." The user measures the measurements and briefly amends the product description.

[0811] Prompt Sentence Examples

[0812] "If the jacket is a size medium, please provide detailed measurements such as shoulder width, chest width, and sleeve length. Also, adjust the instructions to be brief or detailed depending on the user's emotional state."

[0813] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0814] Step 1:

[0815] The user inputs product information into the terminal. The user inputs information such as "Category: Jacket," "Size: M," "Color: Blue," and "Condition: Almost new" into the input form on the terminal. The terminal checks the input product information, formats it, and prepares to send it to the server. Input: User-entered data, Output: Formatted product information data

[0816] Step 2:

[0817] The server receives the product information sent from the terminal. The server parses the received data in JSON format and checks whether the required fields are filled in. The server stores the received data in a database. Input: Formatted product information data, Output: Records stored in the database

[0818] Step 3:

[0819] The server's AI confirms that the product category is "jacket" and identifies that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing. The server identifies the missing information and lists it. Input: Records stored in the database, Output: List of missing information

[0820] Step 4:

[0821] The device collects facial expressions and voice data when the user enters product information, and sends this data to the emotion engine in real time. The emotion engine uses facial expression recognition and voice analysis technology to detect the user's emotional state (e.g., impatience, anxiety, relief). Input: User's facial and voice data, Output: User's emotional state

[0822] Step 5:

[0823] The emotion engine on the server records the detected emotional state in a database as an analysis result. Input: User's emotional state, Output: Analysis result stored in the database

[0824] Step 6:

[0825] The server's AI generates specific product description advice based on the missing information and emotional information. For example, it generates advice such as "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g. shoulder width XX cm, chest width XX cm, sleeve length XX cm)." It reflects the information from the emotional engine and adjusts the content and tone of the advice in the form of "concise instructions if the user is in a hurry" or "detailed instructions if the user is relieved." Input: Missing information list, user's emotional state, Output: Generated advice

[0826] Step 7:

[0827] The server sends the generated advice to the user's terminal. The terminal displays the received advice to the user, who then modifies the product description according to the advice. Input: Generated advice, Output: Advice displayed on the user's terminal

[0828] Step 8:

[0829] Based on the advice from the server, the user measures the specific dimensions and takes photos of the overall product and the tag. The user then resends the corrected information from their device to the server. Input: Dimensional information and photo data, Output: Re-sent product information data

[0830] Step 9:

[0831] The server sends a survey to the customer, asking about their satisfaction with the purchased product and the usefulness of the product description. Input: Customer data, Output: Sent survey link

[0832] Step 10:

[0833] The server collects the survey results and stores them in a database. The server's AI learns from the survey results and uses them to generate future advice. Input: Survey result data, Output: Feedback data stored in the database

[0834] (Application example 2)

[0835] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0836] While many sellers want to improve the quality of product descriptions in online auctions and electronic markets, they often don't know how to create specific and compelling product descriptions. Furthermore, it can be difficult to create consistent, high-quality descriptions due to emotional states. Furthermore, they are unable to effectively utilize buyer feedback and past purchase data, which hinders progress in improving product descriptions.

[0837] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving product information input by the seller, analysis means for analyzing the received product information and identifying information deficiencies, advice generation means for generating specific product description advice for the seller based on the analysis, means for presenting the generated advice to the seller, emotion recognition means for recognizing the seller's emotions in real time and adjusting the content of the advice, and advice adjustment means for adapting the tone and content of the advice based on user emotion information. This makes it possible to create effective and attractive product descriptions while taking into account the emotional state faced by the seller, and to increase purchasing desire.

[0838] "Seller" refers to an individual or corporation that enters and publishes product information in order to sell products on online auctions or electronic markets.

[0839] "Product Information" refers to detailed information necessary for sales, such as product category, size, color, condition, price, and description.

[0840] "Means for receiving" refers to the hardware or software used to receive product information provided by sellers.

[0841] "Analysis means" refers to algorithms or software for analyzing received product information and identifying missing information.

[0842] "Advice generation means" refers to a system that provides sellers with specific improvements and suggestions for product descriptions based on the analysis results.

[0843] "Means for presentation" refers to an interface for displaying or communicating the generated advice to the seller in an easy-to-view format.

[0844] "Emotion recognition means" refers to sensors and analytical algorithms that recognize the seller's emotional state in real time.

[0845] "Advice adjustment means" refers to a system for adjusting the tone and content of advice to suit the seller's current emotional state based on information from the emotion recognition means.

[0846] "Purchase data" refers to a series of data related to product sales, such as past purchase history, buyer feedback, and product description details.

[0847] A "survey" is a survey conducted among buyers to collect feedback on the usefulness of product descriptions and satisfaction with products.

[0848] This invention is a system for improving the quality of product descriptions in online auctions and electronic marketplaces. It involves a process in which a seller inputs product information, analyzes it to identify missing information, and generates and presents specific advice. It also has a function to recognize the seller's emotional state in real time using emotion recognition means and adjust the content and tone of the advice accordingly. The main components of this system and their operation are described in detail below.

[0849] System Components and Operation

[0850] 1. Receiving product information (user input)

[0851] A user uses a smartphone application to input product information, such as "smartphone case," "size: 6 inches," "color: black," and "condition: new." This data is sent from the user's device to a server. During this process, the smartphone's camera and microphone are also used to collect emotional information.

[0852] 2. Data reception and analysis (server processing)

[0853] The server receives product information sent from the user's device. The received data is stored in a database, and the product information is analyzed using analytical means. For example, it may confirm that the product category is a "smartphone case," but identify that specific dimensional information is missing. Here, a database management system (e.g., PostgreSQL) and an AI analysis engine (e.g., TensorFlow) are used.

[0854] 3. Emotion Recognition and Data Processing (Server Processing)

[0855] Facial expression and voice data collected when the user enters product information is sent to the emotion recognition means. The emotion recognition engine on the server analyzes this data and recognizes the user's emotional state (e.g., anxiety, relief, etc.). This recognition result is also stored in the database. Emotion recognition uses an emotion recognition library (e.g., OpenCV or Microsoft Emotion API).

[0856] 4. Generating and Presenting Advice (Server and Terminal Processing)

[0857] The server's AI model (e.g., GPT-3) generates specific product description advice based on the analysis results and emotional information. For example, the advice might be, "Please add specific details such as color, material, and case thickness. It would also be a good idea to add a statement guaranteeing the quality of the product so that buyers can make a purchase with confidence." The generated advice is sent to the user's device and displayed in a smartphone application.

[0858] 5. Learning purchasing data (server processing)

[0859] The server periodically collects past purchase data to learn which product descriptions encourage purchases. This data includes product categories, product details, and buyer behavior data. This allows the advice generation algorithm to be continuously improved.

[0860] 6. Survey implementation and learning (server processing)

[0861] The server sends a questionnaire to the customer, asking about their satisfaction with the purchased product and the usefulness of the product description. The collected survey results are also used as learning data and reflected in future advice generation.

[0862] Specific examples

[0863] For example, if a user enters "smartphone case," "size: 6 inches," "color: black," and "condition: new" into a smartphone app and the emotion engine detects the emotion of "anxiety," the server will generate and display specific advice such as, "Please add specific descriptions such as the color, material, and thickness of the case. It would also be a good idea to add a statement guaranteeing the quality of the product so that buyers can make their purchase with confidence."

[0864] Prompt Sentence Examples

[0865] "A user is trying to list a smartphone case. Please generate specific product description advice based on the following information: Product information: 'Size: 6 inches, Color: Black, Condition: New'. User sentiment: 'Anxious'. Please add specific dimensions and ask for advice."

[0866] This makes it possible to create effective and attractive product descriptions while taking into account the emotional state that the seller faces, thereby increasing purchasing motivation.

[0867] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0868] Step 1:

[0869] User Input

[0870] The user uses an application on their device (smartphone) to input product information (for example, "smartphone case," "size: 6 inches," "color: black," and "condition: new"). The input product information is temporarily stored on the device, and at the same time, the device's camera and microphone are used to collect the user's facial expressions and voice in real time. This allows emotional data to be collected as well. The input data is in the form of text and metadata.

[0871] Step 2:

[0872] Receiving and storing data

[0873] The device sends product information and emotion data to the server, which receives it and stores it in a database (e.g., PostgreSQL). Product information is stored as text data, and emotion data is stored as metadata. This lays the foundation for subsequent analysis and advice generation.

[0874] Step 3:

[0875] Data analysis

[0876] The server's analysis means (AI analysis engine, e.g., TensorFlow) analyzes the received product information and identifies missing information. For example, it confirms that the product category is "smartphone case," but identifies that specific dimensional information is missing. This analysis result is saved back into the database. In this step, text analysis is performed, and data calculations are performed to identify missing information.

[0877] Step 4:

[0878] emotion recognition

[0879] Facial expression and voice data collected when the user enters product information is sent to the server's emotion recognition engine (e.g., OpenCV or Microsoft Emotion API). The server analyzes this data and recognizes the user's emotional state (e.g., "anxiety," "relief," etc.). The recognition results are stored in a database as analysis results and are used to generate subsequent advice. Analysis of emotion data includes image analysis and voice analysis.

[0880] Step 5:

[0881] Advice Generation

[0882] The server's AI model (e.g., GPT-3) generates specific product description advice based on the analysis results and emotional information. For example, the advice might be, "Please add specific details such as color, material, and case thickness." The tone and content are also adjusted based on the emotional data. This generated advice is then stored back in the database. The generative AI model performs text generation and data calculations based on the prompt.

[0883] Step 6:

[0884] Providing advice

[0885] The server sends the generated advice to the user's terminal. On the user's terminal, the received advice is displayed to the user through an application. In this step, data is sent from the server to the terminal and displayed to the user. The advice is displayed in text format.

[0886] Step 7:

[0887] Collecting and learning from purchasing data

[0888] The server periodically collects past purchase data and stores it in a database. The collected data includes product categories, product descriptions, and buyer behavior data. The server's AI analysis engine analyzes this data and improves the advice generation algorithm. This step uses data collection and machine learning algorithms.

[0889] Step 8:

[0890] Conducting a survey

[0891] The server sends a questionnaire to the buyer, asking about the usefulness of the product description and their satisfaction with the product. Feedback from the buyer is collected by the server and stored in a database. The results of this questionnaire are used to generate future advice. Data is transmitted between the server and the buyer.

[0892] Step 9:

[0893] Studying survey results

[0894] The server's AI analysis engine analyzes the survey results and uses feedback on product satisfaction and the usefulness of product descriptions as learning data. This improves the accuracy of future advice generation. This step involves data analysis and machine learning.

[0895] Through these steps, sellers can receive specific advice based on real-time emotion recognition and purchasing data, enabling them to create high-quality product descriptions.

[0896] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0897] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0898] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0899] [Third embodiment]

[0900] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0901] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0902] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0903] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0904] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0905] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0906] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0907] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0908] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0909] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0910] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0911] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0912] This invention includes a system for providing high-quality product descriptions to sellers of online auctions and electronic markets, allowing sellers to create specific product descriptions that encourage purchases.

[0913] System Overview

[0914] This system has the following main functions:

[0915] 1. How to receive product information from sellers

[0916] 2. Analysis means for analyzing received product information and identifying missing information

[0917] 3. Advice generation method that generates specific product description advice based on the analysis results

[0918] 4. A method for presenting the generated advice to the seller

[0919] 5. Learning tools to collect and learn from past purchase data to improve the quality of advice

[0920] 6. Surveying customers and learning from the results

[0921] Program processing explanation

[0922] 1. User Input

[0923] The user inputs product information from the terminal. For example, the user might input product category ("jacket"), size ("M"), color ("blue"), and product condition ("almost new").

[0924] 2. Data Reception and Analysis

[0925] The server receives the product information sent from the device. The AI ​​on the server analyzes this information and identifies any missing information or areas for improvement. For example, if only "Size: M" is listed in the "Jacket" category, it will determine that specific measurements (shoulder width, chest width, sleeve length, etc.) are missing.

[0926] 3. Advice Generation

[0927] The server's AI generates specific advice based on the analysis results. For example, it might generate advice like, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. For example: Shoulder width XX cm, chest width XX cm, sleeve length XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[0928] 4. Learning from purchasing data

[0929] The server collects and organizes past purchase data, and the AI ​​learns from it to improve the accuracy of advice it can give to sellers. For example, it can learn that the more specific the size information, the higher the purchase rate.

[0930] 5. Presentation to the User

[0931] The server sends the generated advice to the terminal and displays it to the user, who can then modify or resubmit the product description according to the advice.

[0932] 6. Survey and learning

[0933] The server sends a questionnaire to the customer about their satisfaction with the purchased product and the usefulness of the product description. The received results are analyzed, and the AI ​​learns from the data, allowing it to generate more precise advice.

[0934] Specific examples

[0935] Example 1:

[0936] The user enters "Jacket", "Size: M", "Color: Blue", and "Condition: Like New".

[0937] The server determined that specific measurements were insufficient and generated the advice, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag."

[0938] Users measure, take photos, and edit product descriptions.

[0939] Example 2:

[0940] In a customer survey, we received feedback that "specific dimensions were listed, so I was able to make the purchase with confidence."

[0941] The server learns from this and reflects it in future advice generation.

[0942] This will increase the matching rate between buyers and sellers and make transactions smoother.

[0943] The processing flow will be explained below.

[0944] Step 1: User Input

[0945] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[0946] The terminal checks the input product information and prepares to send it to the server.

[0947] Step 2: Receiving data

[0948] The server receives the product information sent from the terminal.

[0949] The server stores the received data in a database as a preprocessing step for analysis.

[0950] Step 3: Data analysis

[0951] The server's AI confirms that the product category is "jacket."

[0952] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[0953] The server's AI also checks the color and state information to make sure there are no problems with these.

[0954] Step 4: Advice Generation

[0955] The server's AI generates specific product description advice based on the missing information. For example, it might generate advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width xx cm, chest width xx cm, sleeve length xx cm)."

[0956] You will also be asked to take a photo of the whole thing and a photo of the tag.

[0957] Step 5: Learn the purchasing data

[0958] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[0959] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[0960] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[0961] Step 6: Present to the user

[0962] The server transmits the generated advice to the user's terminal.

[0963] The device displays the received advice to the user, who then modifies the product description in accordance with the advice.

[0964] Step 7: User corrections and resubmission

[0965] Based on advice from the server, the user measures specific dimensions and takes photos of the overall object and the tag.

[0966] The user retransmits the corrected information from the terminal to the server.

[0967] Step 8: Survey

[0968] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[0969] Step 9: Collect and learn from survey results

[0970] The server collects the survey results and stores them in a database.

[0971] The server's AI learns from the survey results and reflects them in generating future advice.

[0972] This allows sellers to provide specific product descriptions that increase purchasing motivation, and improves the matching rate between buyers and sellers.

[0973] Example 1

[0974] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0975] In online auctions and electronic markets, sellers need to create attractive and specific product descriptions, but in many cases, the information is insufficient or vague, preventing them from motivating buyers. Furthermore, sellers may not receive appropriate advice, leading to sluggish sales. Furthermore, there is also the issue of past purchase data and feedback from buyers not being fully utilized, preventing the quality of advice from improving.

[0976] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0977] In this invention, the server includes means for receiving product information input by a seller, analysis means for analyzing the received product information and identifying insufficient information, advice generation means for generating specific product description advice for the seller based on the analysis, means for presenting the generated advice to the seller, means for transmitting the generated product description advice to a terminal and displaying it to the seller, means for collecting past purchase data and improving the quality of the product description advice based on the data, and means for conducting a survey of buyers and improving the quality of the product description advice based on the results. This enables the seller to create specific product descriptions that encourage purchases, and also increases buyer satisfaction.

[0978] A "seller" is an individual or company that lists an item for sale on an online auction or electronic marketplace.

[0979] "Product information" refers to information about the product being offered for sale by the seller, including, for example, category, size, color, condition, etc.

[0980] A "server" is a computer system that receives, processes, and transmits data over a network.

[0981] A "terminal" is a device through which sellers input product information and receive generated advice, etc., and specifically refers to a PC or smartphone.

[0982] The "analysis means" is software or hardware that has the function of analyzing the received product information and identifying missing information or areas for improvement.

[0983] The "advice generation means" is software or hardware having a function for automatically generating specific product description advice to the seller based on the analysis results.

[0984] The "presentation means" refers to software or hardware having a function for presenting the generated advice to the seller visually or in some other way.

[0985] "Past purchasing data" refers to information about past transactions on online auctions and electronic markets, and specifically includes sales data, buyer feedback, and the like.

[0986] "Survey" refers to a questionnaire used to collect feedback provided by buyers after purchase, including satisfaction levels and product ratings.

[0987] The "AI analysis module" is software that uses artificial intelligence technology to analyze product information and identify missing information and areas for improvement.

[0988] The "AI advice generation module" is software that uses artificial intelligence technology to generate specific advice based on analysis results.

[0989] The "AI learning module" is software that trains artificial intelligence based on past purchasing data and survey results to improve the quality of advice.

[0990] A "buyer" is an individual or company that purchases goods through an online auction or electronic marketplace.

[0991] The present invention provides a system that allows sellers in online auctions and electronic markets to create specific product descriptions that encourage purchases. This system allows sellers to input appropriate product information and receive optimal product descriptions based on that information.

[0992] First, the user enters product information using their own device (PC, smartphone, etc.), including specific information such as product category (e.g., jacket), size (e.g., M), color (e.g., blue), and product condition (e.g., almost new).

[0993] The terminal sends the input product information to a server, which is equipped with an AI analysis module that analyzes the received product information.

[0994] When the server receives product information, it first stores it in a database. Next, an AI analysis module reads the product information and identifies missing information and areas for improvement. Based on this analysis, the AI ​​generates specific advice. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Example: Shoulder width XX cm, chest width XX cm, sleeve length XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[0995] The generated advice is sent to the terminal by the server and displayed to the user, who can then follow the advice to modify the product description and send it again.

[0996] Furthermore, the server collects past purchase data and uses it to improve the quality of advice. The server is equipped with an AI learning module that learns from past transaction data and customer feedback to improve the accuracy of the advice it generates. For example, it learns the trend that "the more specific the size information, the higher the purchase rate" and generates advice based on this.

[0997] The server also conducts surveys on customers and collects the results, which the AI ​​learning module uses to generate even higher quality advice.

[0998] Specific examples of how this system works include the following scenarios:

[0999] Specific examples

[1000] The user enters "Jacket," "Size: M," "Color: Blue," and "Condition: Like New." The device sends this input information to the server. The server receives the product information and, after analysis, determines that specific measurements are missing. The server's AI analysis module generates advice saying, "Please enter the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag." The device displays this advice on the user interface. The user measures the measurements, takes photos, and corrects the product description.

[1001] An example prompt might be, "When I list a new item, I'd like some advice on how to include specific dimensions and detailed photos. Also, suggestions based on past purchasing data would be helpful."

[1002] This system allows sellers to create detailed product descriptions that encourage purchases, improving buyer satisfaction and helping to ensure smooth transactions.

[1003] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1004] Step 1:

[1005] The user inputs product information from their own device (PC, smartphone, etc.) This product information includes product category (e.g., jacket), size (e.g., M), color (e.g., blue), and product condition (e.g., almost new).

[1006] Input: Product information (category, size, color, condition)

[1007] Output: Product information data sent by the device to the server

[1008] Specific behavior:

[1009] The user opens a web form and enters product information into each field.

[1010] The user checks the input contents and clicks the send button.

[1011] The terminal transmits the input information to the server.

[1012] Step 2:

[1013] The server receives the product information sent from the device, stores it in a database, and an AI analysis module identifies any missing information or areas that need improvement.

[1014] Input: Product information data received from the terminal

[1015] Output: A list of missing information and improvements analyzed by the AI ​​analysis module

[1016] Specific behavior:

[1017] The server stores the received product information in a database.

[1018] The server's AI analysis module reads the product information and identifies any missing parts.

[1019] The server will list any identified gaps or areas for improvement.

[1020] Step 3:

[1021] The server's AI generates specific advice based on the analysis results. For example, it might say, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. For example, shoulder width: XX cm, chest width: XX cm, sleeve length: XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[1022] Input: Analysis results (list of missing information and improvements)

[1023] Output: Specific advice generated

[1024] Specific behavior:

[1025] The server's AI advice generation module automatically generates advice based on the analysis results.

[1026] The server compiles the generated advice into a list.

[1027] Step 4:

[1028] The server sends the generated advice to the terminal and displays it to the user, who can then follow the advice to modify the product description and resubmit it.

[1029] Input: Generated specific advice

[1030] Output: Advice displayed on the terminal

[1031] Specific behavior:

[1032] The server sends the generated advice to the terminal in JSON format.

[1033] The terminal displays the received advice on the user interface.

[1034] The user checks the displayed advice and modifies the product description.

[1035] Step 5:

[1036] The server collects past purchase data and uses it to improve the quality of advice. An AI learning module learns from this data to improve the accuracy of advice.

[1037] Input: Past purchase data

[1038] Output: Improved advice accuracy due to the trained model

[1039] Specific behavior:

[1040] The server extracts past purchase data from a database.

[1041] The server's AI learning module uses the extracted purchasing data to learn.

[1042] The server stores the learning results in a database and reflects them in future advice generation.

[1043] Step 6:

[1044] The server conducts surveys of customers and collects the results. The AI ​​learning module also learns from these survey results and generates even higher quality advice.

[1045] Input: Survey results from buyers

[1046] Output: Further improved advice accuracy due to the trained model

[1047] Specific behavior:

[1048] The server automatically sends a questionnaire to the purchaser.

[1049] The purchaser answers the questionnaire and submits it.

[1050] The server stores the received survey results in a database and provides them to the AI ​​learning module.

[1051] The AI ​​learning module learns from this and generates even more accurate advice.

[1052] (Application example 1)

[1053] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1054] In online auctions and electronic markets, if sellers do not effectively explain their products, it can discourage buyers and prevent transactions from proceeding smoothly. This requires sellers to provide detailed product information, which takes time and effort. Furthermore, it is often difficult to identify the missing information, resulting in a decline in the quality of product descriptions. Therefore, a system is needed that can continuously improve the quality of advice by utilizing past purchase data and buyer feedback.

[1055] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1056] In this invention, the server includes a means for inputting product information, an analysis means for analyzing the input product information and identifying missing information, an advice generation means for generating specific product description advice based on the analysis, a means for presenting the generated advice, and a means for learning past purchase data using a generative AI model to improve the quality of the advice. This enables sellers to quickly create effective and detailed product descriptions, increasing buyer trust and facilitating transactions.

[1057] "Product information" refers to detailed information about a product entered by a seller in an online auction or online marketplace. This information includes attribute information such as the product name, category, size, color, and condition.

[1058] "Analysis means" refers to the technology or method for analyzing input product information and identifying missing information or areas requiring improvement.

[1059] "Advice generation means" refers to a technique or method for instructing sellers on specific improvements to product descriptions and methods for providing additional information based on the analysis results.

[1060] "Presentation means" refers to the technology or method for presenting the generated advice to the seller in an easy-to-view manner and encouraging necessary improvements.

[1061] A "generative AI model" refers to an artificial intelligence model that learns from past purchasing data and customer feedback to constantly improve the quality of advice.

[1062] "Past purchase data" is historical information about past purchases, and includes data such as product category, number of purchases, and buyer ratings.

[1063] A "customer survey" is a questionnaire-based survey sent to buyers to assess the usefulness of product descriptions and their satisfaction with the purchased product.

[1064] The system of the present invention is configured to provide sellers with specific advice to improve the quality of their product descriptions. The main components of the system and their roles will be described below.

[1065] System configuration:

[1066] This system is realized mainly using the following hardware and software.

[1067] Hardware: The smartphone or computer used by the seller

[1068] Software: Server, SpaCy, scikit-learn, generative AI model

[1069] 1. Product information input method:

[1070] The user (seller) enters product information via a smartphone or computer, such as "Jacket, Size M, Color: Blue, Condition: Almost New."

[1071] 2. Analysis method:

[1072] The server uses SpaCy to analyze the input product information. Specifically, it extracts important tags (nouns and adjectives) from the information and identifies any missing information.

[1073] 3. Advice Generation Methods:

[1074] The server uses scikit-learn functions to generate specific advice about missing information or information that needs improvement. For example, specific advice might be generated such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag."

[1075] 4. Means of presentation:

[1076] The generated advice is displayed on the user's smartphone or computer, and the seller can revise the product description accordingly.

[1077] 5. Learning tools:

[1078] The generative AI model on the server learns from past purchase data and customer survey results. Based on this data, it continuously improves the quality of advice. For example, it learns trends such as "products with specific dimensional information have a higher purchase rate."

[1079] Examples:

[1080] User Input: Seller enters "Jacket, Size M, Color: Blue, Condition: Like New."

[1081] Analysis result: The server analyzes the input information using Spacy and determines that the information for "shoulder width," "chest width," and "sleeve length" is missing.

[1082] Generated advice: Using scikit-learn, the server generates the advice, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag." and presents it to the seller.

[1083] Example prompt sentence:

[1084] Product information: Blue jacket, size M, condition almost new

[1085] From the analysis results, we identified the missing information as "shoulder width," "chest width," and "sleeve length." Please create a product description that includes specific examples like the ones below.

[1086] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1087] Step 1:

[1088] User enters product information

[1089] Users input product information using a smartphone or computer. This input includes detailed information such as product category, size, color, and condition. Specific input is possible, such as "Jacket, Size M, Color: Blue, Condition: Almost New."

[1090] Step 2:

[1091] Server receives product information

[1092] The server receives the product information entered by the user and stores it in a database for use in subsequent analysis.

[1093] Step 3:

[1094] The server analyzes the input information

[1095] The server uses SpaCy to analyze the received product information. Specifically, it extracts important tags (nouns and adjectives) and identifies missing information. For example, it determines that the shoulder width, chest width, and sleeve length are missing for a jacket.

[1096] Input: Product information entered by the user (e.g., "Jacket, Size M, Color: Blue, Condition: Like New")

[1097] Output: Extracted important tags (e.g., "shoulder width," "chest width," and "sleeve length" are determined to be missing)

[1098] Step 4:

[1099] Server generates advice

[1100] The server uses scikit-learn to generate specific advice based on the missing information. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and the tag."

[1101] Input: Missing information (e.g. "shoulder width", "chest width", "sleeve length")

[1102] Output: Generated specific advice (e.g., "Please provide the specific measurements for shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and a photo of the tag.")

[1103] Step 5:

[1104] The server provides advice to the user

[1105] The server sends the generated advice to the user's smartphone or PC, allowing the user to refer to the advice and revise the product description.

[1106] Input: Generated advice (e.g., "Please provide the specific measurements for shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and a photo of the tag.")

[1107] Output: Advice displayed on the user's terminal

[1108] Step 6:

[1109] The server learns the purchasing data

[1110] The generative AI model on the server collects past purchase data and learns from it. For example, it can extract trends such as "products with specific dimensional information have a higher purchase rate." The results of this learning are reflected in future advice generation.

[1111] Input: Past purchase data

[1112] Output: Learning results (e.g., "Products with specific dimensions have a higher purchase rate.")

[1113] Step 7:

[1114] The server learns the survey results

[1115] The server conducts surveys of shoppers and collects and learns from the results. This provides information on the usefulness of product descriptions and satisfaction with purchased products. The generative AI model uses this information to further improve the quality of advice.

[1116] Input: Customer survey results

[1117] Output: Learning results (e.g., feedback such as "The specific dimensions were listed, so I was able to make the purchase with confidence.")

[1118] Through the above steps, sellers can create high-quality product descriptions, which increases buyers' trust and facilitates smooth transactions.

[1119] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1120] This invention includes a system that provides high-quality product descriptions to sellers of online auctions and electronic marketplaces. This system allows sellers to create specific product descriptions that encourage purchases. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, the system can provide more personalized advice.

[1121] System Overview

[1122] This system has the following main functions:

[1123] 1. How to receive product information from sellers

[1124] 2. Analysis means for analyzing received product information and identifying missing information

[1125] 3. Advice generation method that generates specific product description advice based on the analysis results

[1126] 4. A method for presenting the generated advice to the seller

[1127] 5. Learning tools to collect and learn from past purchase data to improve the quality of advice

[1128] 6. A means of surveying buyers and learning from their results

[1129] 7. An emotion engine that recognizes user emotions and uses that information to generate advice.

[1130] Program processing explanation

[1131] 1. User Input

[1132] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[1133] The terminal checks the input product information and prepares to send it to the server.

[1134] 2. Data Reception and Analysis

[1135] The server receives the product information sent from the terminal.

[1136] The server stores the received data in a database as a preprocessing step for analysis.

[1137] The server's AI confirms that the product category is "jacket."

[1138] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[1139] 3. Emotion Recognition by Emotion Engine

[1140] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine.

[1141] The server's emotion engine analyzes this and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.).

[1142] The server stores the emotion information obtained from the emotion engine as the analysis result.

[1143] 4. Advice Generation

[1144] The server's AI generates specific product description advice based on the missing information. For example, it generates specific advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width xx cm, chest width xx cm, sleeve length xx cm)."

[1145] The information from the emotion engine is reflected and the content and tone of the advice is adjusted, such as "brief instructions if the user is anxious" or "detailed instructions if the user is relieved."

[1146] 5. Learning from purchasing data

[1147] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[1148] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[1149] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[1150] 6. Presentation to the User

[1151] The server transmits the generated advice to the user's terminal.

[1152] The device displays the received advice to the user, who then modifies the product description in accordance with the advice.

[1153] 7. User Modifications and Resubmissions

[1154] Based on advice from the server, the user measures specific dimensions and takes photos of the overall object and the tag.

[1155] The user retransmits the corrected information from the terminal to the server.

[1156] 8. Survey implementation

[1157] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[1158] 9. Collecting and Learning from Survey Results

[1159] The server collects the survey results and stores them in a database.

[1160] The server's AI learns from the survey results and reflects them in generating future advice.

[1161] Specific examples

[1162] Example 1:

[1163] The user inputs "Jacket", "Size: M", "Color: Blue", and "Condition: Like New". The emotion engine detects the emotion "Impatience".

[1164] The server generates specific and concise advice: "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Sample sentences for concise descriptions are shown below: Shoulder width XX cm, chest width XX cm, sleeve length XX cm."

[1165] The user measures the dimensions and briefly edits the product description.

[1166] Example 2:

[1167] In a customer survey, we received feedback that "specific dimensions were listed, so I was able to make the purchase with confidence."

[1168] The server learns from this and reflects it in future advice generation.

[1169] In this way, by providing specific advice that takes into account the user's emotions, it is possible to improve the quality of product descriptions and further increase the matching rate between buyers and sellers.

[1170] The processing flow will be explained below.

[1171] Step 1: User Input

[1172] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[1173] The terminal checks the input product information and prepares to send it to the server.

[1174] Step 2: Receiving data

[1175] The server receives the product information sent from the terminal.

[1176] The server stores the received data in a database as a preprocessing step for analysis.

[1177] Step 3: Emotion recognition by the emotion engine

[1178] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine.

[1179] The server's emotion engine analyzes this and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.).

[1180] The server stores the emotion information obtained from the emotion engine as analysis data.

[1181] Step 4: Data analysis

[1182] The server's AI analyzes the received product information.

[1183] The server's AI confirms that the product category is "jacket."

[1184] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[1185] The server's AI also checks color and state information, and also refers to emotion information.

[1186] Step 5: Advice Generation

[1187] The server's AI generates specific product description advice for sellers based on the data analysis results and emotional information.

[1188] For example, if the emotional information is "impatience," the system generates concise advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width XX cm, chest width XX cm, sleeve length XX cm). Also, please take photos of the entire product and the tag."

[1189] If the emotional information is "peace of mind," detailed advice is provided: "Please describe the product's features in detail and include specific measurements such as shoulder width, chest width, and sleeve length. Photos should include an overall view of the product, tags, and details."

[1190] Step 6: Present to the user

[1191] The server transmits the generated advice to the user's terminal.

[1192] The terminal displays the received advice to the user.

[1193] Step 7: User corrections and resubmission

[1194] The user makes the necessary corrections based on the provided advice, such as taking specific measurements and taking photos of the overall product and the tag.

[1195] The user retransmits the corrected information from the terminal to the server.

[1196] Step 8: Learn your purchasing data

[1197] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[1198] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[1199] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[1200] Step 9: Survey

[1201] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[1202] Step 10: Collect and learn from survey results

[1203] The server collects the survey results and stores them in a database.

[1204] The server's AI learns from the survey results and reflects them in generating future advice.

[1205] In this way, sellers can create specific and inspiring product descriptions by providing specific advice that takes users' emotions into account, further increasing the chances of matching buyers and sellers.

[1206] Example 2

[1207] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1208] In online auctions and electronic markets, if sellers provide insufficient product descriptions, buyers have difficulty understanding the product details, which reduces their willingness to purchase. Furthermore, some users are easily influenced by their emotions, and the quality and content of product descriptions can directly affect their willingness to purchase. Therefore, there is a need for support for sellers to provide high-quality, specific product descriptions that take emotions into consideration.

[1209] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving product information input by a seller, a means for analyzing the received product information to identify insufficient information, a means for acquiring and analyzing the user's emotional state based on the input product information, a means for generating specific product description advice to the seller based on the analysis, and a means for presenting the generated advice to the seller. This enables the seller to supplement the insufficient information and provide a high-quality product description that takes the user's emotions into consideration.

[1210] A "seller" is an individual or organization that sells goods on an online auction or electronic marketplace.

[1211] "Product information" refers to detailed information about the product being sold by the seller, including, specifically, the category, size, color, condition, and the like.

[1212] The "emotional state" refers to the psychological state of the user when inputting product information, and examples include feelings such as impatience, anxiety, and relief.

[1213] The "receiving means" is a function that receives product information sent from the terminal at the server and performs processing to store the information in the database.

[1214] The "analysis means" is a function for analyzing received product information and identifying missing information.

[1215] The "emotion recognition means" is a function for analyzing the user's facial expressions and voice and identifying their emotional state.

[1216] The "advice generation means" is a function for dynamically generating specific advice on product descriptions based on the results of the analysis means and emotion recognition means.

[1217] The "presentation means" is a function for displaying the generated advice to the seller in an easy-to-understand manner.

[1218] "Purchase data" refers to data including product categories, detailed product descriptions, purchaser behavior data, and the like from past transactions.

[1219] A "survey" is a survey conducted to collect feedback from buyers about their satisfaction with the purchased product and the usefulness of the product description.

[1220] "Collection means" refers to a function for effectively collecting purchasing data and survey results.

[1221] The "learning means" is a function that uses collected data to learn, through a machine learning algorithm, what kind of product descriptions will increase purchasing desire, and reflects this in the advice generation algorithm.

[1222] This invention is a system that provides high-quality product descriptions to sellers of online auctions and electronic markets. This system allows sellers to create specific product descriptions that encourage purchases. In addition, by incorporating an emotion engine that recognizes the user's emotions, the system can provide more personalized advice.

[1223] Hardware and software used

[1224] This system uses servers and terminals as its main hardware. The server requires a high-performance processor, a large amount of memory, and a database (e.g., MySQL, PostgreSQL) to store large amounts of data. It also incorporates an AI engine (e.g., TensorFlow, PyTorch) for emotion recognition and data analysis. The terminals are devices equipped with cameras and microphones (e.g., smartphones, tablets).

[1225] Explanation of program processing

[1226] The program of this system performs processing roughly according to the following steps.

[1227] User Input

[1228] The user inputs product information into the terminal. For example, "Category: Jacket," "Size: M," "Color: Blue," "Condition: Almost New," etc. The terminal confirms the user's input and prepares to send it to the server.

[1229] Data reception and analysis

[1230] The server receives the product information sent from the device. It then stores the data in a database and begins analyzing the received data. The server's AI confirms that the product category is "jacket" and identifies that the size information sent is "M," but that specific measurements for shoulder width, chest width, and sleeve length are missing.

[1231] Emotion recognition by emotion engine

[1232] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine. The server's emotion engine analyzes these and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.). The acquired emotional information is recorded in a database as an analysis result.

[1233] Advice Generation

[1234] The server's AI generates specific product description advice based on the missing information and the acquired emotional information. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width XX cm, chest width XX cm, sleeve length XX cm)." The content and tone of the advice are adjusted to reflect the information from the emotional engine, such as "concise instructions if the customer is in a hurry" or "detailed instructions if the customer is relieved."

[1235] Learning from purchasing data

[1236] The server periodically collects past purchase data, including product categories, product description details, and buyer behavior data. The server's AI uses this data to learn what product descriptions increase purchase motivation and update its advice generation algorithm.

[1237] Presenting to the user

[1238] The server sends the generated advice to the user's terminal, which displays the received advice to the user, who then modifies the product description in accordance with the advice.

[1239] User correction and resubmission

[1240] Based on the advice from the server, the user measures the specific dimensions, takes photos of the whole area and the tag, and then resends the corrected information from the device to the server.

[1241] Survey

[1242] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[1243] Collecting and learning from survey results

[1244] The server collects the survey results and stores them in a database. The server's AI learns from the survey results and uses them to generate future advice.

[1245] Specific examples

[1246] 1. A user enters "Jacket", "Size: M", "Color: Blue", "Condition: Like New". The emotion engine detects the emotion "Impatient".

[1247] 2. The server generates specific and concise advice: "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Sample sentences for concise descriptions are shown below: Shoulder width XX cm, chest width XX cm, sleeve length XX cm." The user measures the measurements and briefly amends the product description.

[1248] Prompt Sentence Examples

[1249] "If the jacket is a size medium, please provide detailed measurements such as shoulder width, chest width, and sleeve length. Also, adjust the instructions to be brief or detailed depending on the user's emotional state."

[1250] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1251] Step 1:

[1252] The user inputs product information into the terminal. The user inputs information such as "Category: Jacket," "Size: M," "Color: Blue," and "Condition: Almost new" into the input form on the terminal. The terminal checks the input product information, formats it, and prepares to send it to the server. Input: User-entered data, Output: Formatted product information data

[1253] Step 2:

[1254] The server receives the product information sent from the terminal. The server parses the received data in JSON format and checks whether the required fields are filled in. The server stores the received data in a database. Input: Formatted product information data, Output: Records stored in the database

[1255] Step 3:

[1256] The server's AI confirms that the product category is "jacket" and identifies that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing. The server identifies the missing information and lists it. Input: Records stored in the database, Output: List of missing information

[1257] Step 4:

[1258] The device collects facial expressions and voice data when the user enters product information, and sends this data to the emotion engine in real time. The emotion engine uses facial expression recognition and voice analysis technology to detect the user's emotional state (e.g., impatience, anxiety, relief). Input: User's facial and voice data, Output: User's emotional state

[1259] Step 5:

[1260] The emotion engine on the server records the detected emotional state in a database as an analysis result. Input: User's emotional state, Output: Analysis result stored in the database

[1261] Step 6:

[1262] The server's AI generates specific product description advice based on the missing information and emotional information. For example, it generates advice such as "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g. shoulder width XX cm, chest width XX cm, sleeve length XX cm)." It reflects the information from the emotional engine and adjusts the content and tone of the advice in the form of "concise instructions if the user is in a hurry" or "detailed instructions if the user is relieved." Input: Missing information list, user's emotional state, Output: Generated advice

[1263] Step 7:

[1264] The server sends the generated advice to the user's terminal. The terminal displays the received advice to the user, who then modifies the product description according to the advice. Input: Generated advice, Output: Advice displayed on the user's terminal

[1265] Step 8:

[1266] Based on the advice from the server, the user measures the specific dimensions and takes photos of the overall product and the tag. The user then resends the corrected information from their device to the server. Input: Dimensional information and photo data, Output: Re-sent product information data

[1267] Step 9:

[1268] The server sends a survey to the customer, asking about their satisfaction with the purchased product and the usefulness of the product description. Input: Customer data, Output: Sent survey link

[1269] Step 10:

[1270] The server collects the survey results and stores them in a database. The server's AI learns from the survey results and uses them to generate future advice. Input: Survey result data, Output: Feedback data stored in the database

[1271] (Application example 2)

[1272] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1273] While many sellers want to improve the quality of product descriptions in online auctions and electronic markets, they often don't know how to create specific and compelling product descriptions. Furthermore, it can be difficult to create consistent, high-quality descriptions due to emotional states. Furthermore, they are unable to effectively utilize buyer feedback and past purchase data, which hinders progress in improving product descriptions.

[1274] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving product information input by the seller, analysis means for analyzing the received product information and identifying information deficiencies, advice generation means for generating specific product description advice for the seller based on the analysis, means for presenting the generated advice to the seller, emotion recognition means for recognizing the seller's emotions in real time and adjusting the content of the advice, and advice adjustment means for adapting the tone and content of the advice based on user emotion information. This makes it possible to create effective and attractive product descriptions while taking into account the emotional state faced by the seller, and to increase purchasing desire.

[1275] "Seller" refers to an individual or corporation that enters and publishes product information in order to sell products on online auctions or electronic markets.

[1276] "Product Information" refers to detailed information necessary for sales, such as product category, size, color, condition, price, and description.

[1277] "Means for receiving" refers to the hardware or software used to receive product information provided by sellers.

[1278] "Analysis means" refers to algorithms or software for analyzing received product information and identifying missing information.

[1279] "Advice generation means" refers to a system that provides sellers with specific improvements and suggestions for product descriptions based on the analysis results.

[1280] "Means for presentation" refers to an interface for displaying or communicating the generated advice to the seller in an easy-to-view format.

[1281] "Emotion recognition means" refers to sensors and analytical algorithms that recognize the seller's emotional state in real time.

[1282] "Advice adjustment means" refers to a system for adjusting the tone and content of advice to suit the seller's current emotional state based on information from the emotion recognition means.

[1283] "Purchase data" refers to a series of data related to product sales, such as past purchase history, buyer feedback, and product description details.

[1284] A "survey" is a survey conducted among buyers to collect feedback on the usefulness of product descriptions and satisfaction with products.

[1285] This invention is a system for improving the quality of product descriptions in online auctions and electronic marketplaces. It involves a process in which a seller inputs product information, analyzes it to identify missing information, and generates and presents specific advice. It also has a function to recognize the seller's emotional state in real time using emotion recognition means and adjust the content and tone of the advice accordingly. The main components of this system and their operation are described in detail below.

[1286] System Components and Operation

[1287] 1. Receiving product information (user input)

[1288] A user uses a smartphone application to input product information, such as "smartphone case," "size: 6 inches," "color: black," and "condition: new." This data is sent from the user's device to a server. During this process, the smartphone's camera and microphone are also used to collect emotional information.

[1289] 2. Data reception and analysis (server processing)

[1290] The server receives product information sent from the user's device. The received data is stored in a database, and the product information is analyzed using analytical means. For example, it may confirm that the product category is a "smartphone case," but identify that specific dimensional information is missing. Here, a database management system (e.g., PostgreSQL) and an AI analysis engine (e.g., TensorFlow) are used.

[1291] 3. Emotion Recognition and Data Processing (Server Processing)

[1292] Facial expression and voice data collected when the user enters product information is sent to the emotion recognition means. The emotion recognition engine on the server analyzes this data and recognizes the user's emotional state (e.g., anxiety, relief, etc.). This recognition result is also stored in the database. Emotion recognition uses an emotion recognition library (e.g., OpenCV or Microsoft Emotion API).

[1293] 4. Generating and Presenting Advice (Server and Terminal Processing)

[1294] The server's AI model (e.g., GPT-3) generates specific product description advice based on the analysis results and emotional information. For example, the advice might be, "Please add specific details such as color, material, and case thickness. It would also be a good idea to add a statement guaranteeing the quality of the product so that buyers can make a purchase with confidence." The generated advice is sent to the user's device and displayed in a smartphone application.

[1295] 5. Learning purchasing data (server processing)

[1296] The server periodically collects past purchase data to learn which product descriptions encourage purchases. This data includes product categories, product details, and buyer behavior data. This allows the advice generation algorithm to be continuously improved.

[1297] 6. Survey implementation and learning (server processing)

[1298] The server sends a questionnaire to the customer, asking about their satisfaction with the purchased product and the usefulness of the product description. The collected survey results are also used as learning data and reflected in future advice generation.

[1299] Specific examples

[1300] For example, if a user enters "smartphone case," "size: 6 inches," "color: black," and "condition: new" into a smartphone app and the emotion engine detects the emotion of "anxiety," the server will generate and display specific advice such as, "Please add specific descriptions such as the color, material, and thickness of the case. It would also be a good idea to add a statement guaranteeing the quality of the product so that buyers can make their purchase with confidence."

[1301] Prompt Sentence Examples

[1302] "A user is trying to list a smartphone case. Please generate specific product description advice based on the following information: Product information: 'Size: 6 inches, Color: Black, Condition: New'. User sentiment: 'Anxious'. Please add specific dimensions and ask for advice."

[1303] This makes it possible to create effective and attractive product descriptions while taking into account the emotional state that the seller faces, thereby increasing purchasing motivation.

[1304] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1305] Step 1:

[1306] User Input

[1307] The user uses an application on their device (smartphone) to input product information (for example, "smartphone case," "size: 6 inches," "color: black," and "condition: new"). The input product information is temporarily stored on the device, and at the same time, the device's camera and microphone are used to collect the user's facial expressions and voice in real time. This allows emotional data to be collected as well. The input data is in the form of text and metadata.

[1308] Step 2:

[1309] Receiving and storing data

[1310] The device sends product information and emotion data to the server, which receives it and stores it in a database (e.g., PostgreSQL). Product information is stored as text data, and emotion data is stored as metadata. This lays the foundation for subsequent analysis and advice generation.

[1311] Step 3:

[1312] Data analysis

[1313] The server's analysis means (AI analysis engine, e.g., TensorFlow) analyzes the received product information and identifies missing information. For example, it confirms that the product category is "smartphone case," but identifies that specific dimensional information is missing. This analysis result is saved back into the database. In this step, text analysis is performed, and data calculations are performed to identify missing information.

[1314] Step 4:

[1315] emotion recognition

[1316] Facial expression and voice data collected when the user enters product information is sent to the server's emotion recognition engine (e.g., OpenCV or Microsoft Emotion API). The server analyzes this data and recognizes the user's emotional state (e.g., "anxiety," "relief," etc.). The recognition results are stored in a database as analysis results and are used to generate subsequent advice. Analysis of emotion data includes image analysis and voice analysis.

[1317] Step 5:

[1318] Advice Generation

[1319] The server's AI model (e.g., GPT-3) generates specific product description advice based on the analysis results and emotional information. For example, the advice might be, "Please add specific details such as color, material, and case thickness." The tone and content are also adjusted based on the emotional data. This generated advice is then stored back in the database. The generative AI model performs text generation and data calculations based on the prompt.

[1320] Step 6:

[1321] Providing advice

[1322] The server sends the generated advice to the user's terminal. On the user's terminal, the received advice is displayed to the user through an application. In this step, data is sent from the server to the terminal and displayed to the user. The advice is displayed in text format.

[1323] Step 7:

[1324] Collecting and learning from purchasing data

[1325] The server periodically collects past purchase data and stores it in a database. The collected data includes product categories, product descriptions, and buyer behavior data. The server's AI analysis engine analyzes this data and improves the advice generation algorithm. This step uses data collection and machine learning algorithms.

[1326] Step 8:

[1327] Conducting a survey

[1328] The server sends a questionnaire to the buyer, asking about the usefulness of the product description and their satisfaction with the product. Feedback from the buyer is collected by the server and stored in a database. The results of this questionnaire are used to generate future advice. Data is transmitted between the server and the buyer.

[1329] Step 9:

[1330] Studying survey results

[1331] The server's AI analysis engine analyzes the survey results and uses feedback on product satisfaction and the usefulness of product descriptions as learning data. This improves the accuracy of future advice generation. This step involves data analysis and machine learning.

[1332] Through these steps, sellers can receive specific advice based on real-time emotion recognition and purchasing data, enabling them to create high-quality product descriptions.

[1333] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1334] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1335] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1336] [Fourth embodiment]

[1337] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1338] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1339] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1340] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1341] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1342] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1343] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1344] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1345] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1346] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1347] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1348] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1349] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1350] This invention includes a system for providing high-quality product descriptions to sellers of online auctions and electronic markets, allowing sellers to create specific product descriptions that encourage purchases.

[1351] System Overview

[1352] This system has the following main functions:

[1353] 1. How to receive product information from sellers

[1354] 2. Analysis means for analyzing received product information and identifying missing information

[1355] 3. Advice generation method that generates specific product description advice based on the analysis results

[1356] 4. A method for presenting the generated advice to the seller

[1357] 5. Learning tools to collect and learn from past purchase data to improve the quality of advice

[1358] 6. Surveying customers and learning from the results

[1359] Program processing explanation

[1360] 1. User Input

[1361] The user inputs product information from the terminal. For example, the user might input product category ("jacket"), size ("M"), color ("blue"), and product condition ("almost new").

[1362] 2. Data Reception and Analysis

[1363] The server receives the product information sent from the device. The AI ​​on the server analyzes this information and identifies any missing information or areas for improvement. For example, if only "Size: M" is listed in the "Jacket" category, it will determine that specific measurements (shoulder width, chest width, sleeve length, etc.) are missing.

[1364] 3. Advice Generation

[1365] The server's AI generates specific advice based on the analysis results. For example, it might generate advice like, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. For example: Shoulder width XX cm, chest width XX cm, sleeve length XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[1366] 4. Learning from purchasing data

[1367] The server collects and organizes past purchase data, and the AI ​​learns from it to improve the accuracy of advice it can give to sellers. For example, it can learn that the more specific the size information, the higher the purchase rate.

[1368] 5. Presentation to the User

[1369] The server sends the generated advice to the terminal and displays it to the user, who can then modify or resubmit the product description according to the advice.

[1370] 6. Survey and learning

[1371] The server sends a questionnaire to the customer about their satisfaction with the purchased product and the usefulness of the product description. The received results are analyzed, and the AI ​​learns from the data, allowing it to generate more precise advice.

[1372] Specific examples

[1373] Example 1:

[1374] The user enters "Jacket", "Size: M", "Color: Blue", and "Condition: Like New".

[1375] The server determined that specific measurements were insufficient and generated the advice, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag."

[1376] Users measure, take photos, and edit product descriptions.

[1377] Example 2:

[1378] In a customer survey, we received feedback that "specific dimensions were listed, so I was able to make the purchase with confidence."

[1379] The server learns from this and reflects it in future advice generation.

[1380] This will increase the matching rate between buyers and sellers and make transactions smoother.

[1381] The processing flow will be explained below.

[1382] Step 1: User Input

[1383] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[1384] The terminal checks the input product information and prepares to send it to the server.

[1385] Step 2: Receiving data

[1386] The server receives the product information sent from the terminal.

[1387] The server stores the received data in a database as a preprocessing step for analysis.

[1388] Step 3: Data analysis

[1389] The server's AI confirms that the product category is "jacket."

[1390] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[1391] The server's AI also checks the color and state information to make sure there are no problems with these.

[1392] Step 4: Advice Generation

[1393] The server's AI generates specific product description advice based on the missing information. For example, it might generate advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width xx cm, chest width xx cm, sleeve length xx cm)."

[1394] You will also be asked to take a photo of the whole thing and a photo of the tag.

[1395] Step 5: Learn the purchasing data

[1396] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[1397] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[1398] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[1399] Step 6: Present to the user

[1400] The server transmits the generated advice to the user's terminal.

[1401] The device displays the received advice to the user, who then modifies the product description in accordance with the advice.

[1402] Step 7: User corrections and resubmission

[1403] Based on advice from the server, the user measures specific dimensions and takes photos of the overall object and the tag.

[1404] The user retransmits the corrected information from the terminal to the server.

[1405] Step 8: Survey

[1406] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[1407] Step 9: Collect and learn from survey results

[1408] The server collects the survey results and stores them in a database.

[1409] The server's AI learns from the survey results and reflects them in generating future advice.

[1410] This allows sellers to provide specific product descriptions that increase purchasing motivation, and improves the matching rate between buyers and sellers.

[1411] Example 1

[1412] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1413] In online auctions and electronic markets, sellers need to create attractive and specific product descriptions, but in many cases, the information is insufficient or vague, preventing them from motivating buyers. Furthermore, sellers may not receive appropriate advice, leading to sluggish sales. Furthermore, there is also the issue of past purchase data and feedback from buyers not being fully utilized, preventing the quality of advice from improving.

[1414] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1415] In this invention, the server includes means for receiving product information input by a seller, analysis means for analyzing the received product information and identifying insufficient information, advice generation means for generating specific product description advice for the seller based on the analysis, means for presenting the generated advice to the seller, means for transmitting the generated product description advice to a terminal and displaying it to the seller, means for collecting past purchase data and improving the quality of the product description advice based on the data, and means for conducting a survey of buyers and improving the quality of the product description advice based on the results. This enables the seller to create specific product descriptions that encourage purchases, and also increases buyer satisfaction.

[1416] A "seller" is an individual or company that lists an item for sale on an online auction or electronic marketplace.

[1417] "Product information" refers to information about the product being offered for sale by the seller, including, for example, category, size, color, condition, etc.

[1418] A "server" is a computer system that receives, processes, and transmits data over a network.

[1419] A "terminal" is a device through which sellers input product information and receive generated advice, etc., and specifically refers to a PC or smartphone.

[1420] The "analysis means" is software or hardware that has the function of analyzing the received product information and identifying missing information or areas for improvement.

[1421] The "advice generation means" is software or hardware having a function for automatically generating specific product description advice to the seller based on the analysis results.

[1422] The "presentation means" refers to software or hardware having a function for presenting the generated advice to the seller visually or in some other way.

[1423] "Past purchasing data" refers to information about past transactions on online auctions and electronic markets, and specifically includes sales data, buyer feedback, and the like.

[1424] "Survey" refers to a questionnaire used to collect feedback provided by buyers after purchase, including satisfaction levels and product ratings.

[1425] The "AI analysis module" is software that uses artificial intelligence technology to analyze product information and identify missing information and areas for improvement.

[1426] The "AI advice generation module" is software that uses artificial intelligence technology to generate specific advice based on analysis results.

[1427] The "AI learning module" is software that trains artificial intelligence based on past purchasing data and survey results to improve the quality of advice.

[1428] A "buyer" is an individual or company that purchases goods through an online auction or electronic marketplace.

[1429] The present invention provides a system that allows sellers in online auctions and electronic markets to create specific product descriptions that encourage purchases. This system allows sellers to input appropriate product information and receive optimal product descriptions based on that information.

[1430] First, the user enters product information using their own device (PC, smartphone, etc.), including specific information such as product category (e.g., jacket), size (e.g., M), color (e.g., blue), and product condition (e.g., almost new).

[1431] The terminal sends the input product information to a server, which is equipped with an AI analysis module that analyzes the received product information.

[1432] When the server receives product information, it first stores it in a database. Next, an AI analysis module reads the product information and identifies missing information and areas for improvement. Based on this analysis, the AI ​​generates specific advice. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Example: Shoulder width XX cm, chest width XX cm, sleeve length XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[1433] The generated advice is sent to the terminal by the server and displayed to the user, who can then follow the advice to modify the product description and send it again.

[1434] Furthermore, the server collects past purchase data and uses it to improve the quality of advice. The server is equipped with an AI learning module that learns from past transaction data and customer feedback to improve the accuracy of the advice it generates. For example, it learns the trend that "the more specific the size information, the higher the purchase rate" and generates advice based on this.

[1435] The server also conducts surveys on customers and collects the results, which the AI ​​learning module uses to generate even higher quality advice.

[1436] Specific examples of how this system works include the following scenarios:

[1437] Specific examples

[1438] The user enters "Jacket," "Size: M," "Color: Blue," and "Condition: Like New." The device sends this input information to the server. The server receives the product information and, after analysis, determines that specific measurements are missing. The server's AI analysis module generates advice saying, "Please enter the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag." The device displays this advice on the user interface. The user measures the measurements, takes photos, and corrects the product description.

[1439] An example prompt might be, "When I list a new item, I'd like some advice on how to include specific dimensions and detailed photos. Also, suggestions based on past purchasing data would be helpful."

[1440] This system allows sellers to create detailed product descriptions that encourage purchases, improving buyer satisfaction and helping to ensure smooth transactions.

[1441] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1442] Step 1:

[1443] The user inputs product information from their own device (PC, smartphone, etc.) This product information includes product category (e.g., jacket), size (e.g., M), color (e.g., blue), and product condition (e.g., almost new).

[1444] Input: Product information (category, size, color, condition)

[1445] Output: Product information data sent by the device to the server

[1446] Specific behavior:

[1447] The user opens a web form and enters product information into each field.

[1448] The user checks the input contents and clicks the send button.

[1449] The terminal transmits the input information to the server.

[1450] Step 2:

[1451] The server receives the product information sent from the device, stores it in a database, and an AI analysis module identifies any missing information or areas that need improvement.

[1452] Input: Product information data received from the terminal

[1453] Output: A list of missing information and improvements analyzed by the AI ​​analysis module

[1454] Specific behavior:

[1455] The server stores the received product information in a database.

[1456] The server's AI analysis module reads the product information and identifies any missing parts.

[1457] The server will list any identified gaps or areas for improvement.

[1458] Step 3:

[1459] The server's AI generates specific advice based on the analysis results. For example, it might say, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. For example, shoulder width: XX cm, chest width: XX cm, sleeve length: XX cm. Also, please take a photo of the tag in addition to a photo of the entire product."

[1460] Input: Analysis results (list of missing information and improvements)

[1461] Output: Specific advice generated

[1462] Specific behavior:

[1463] The server's AI advice generation module automatically generates advice based on the analysis results.

[1464] The server compiles the generated advice into a list.

[1465] Step 4:

[1466] The server sends the generated advice to the terminal and displays it to the user, who can then follow the advice to modify the product description and resubmit it.

[1467] Input: Generated specific advice

[1468] Output: Advice displayed on the terminal

[1469] Specific behavior:

[1470] The server sends the generated advice to the terminal in JSON format.

[1471] The terminal displays the received advice on the user interface.

[1472] The user checks the displayed advice and modifies the product description.

[1473] Step 5:

[1474] The server collects past purchase data and uses it to improve the quality of advice. An AI learning module learns from this data to improve the accuracy of advice.

[1475] Input: Past purchase data

[1476] Output: Improved advice accuracy due to the trained model

[1477] Specific behavior:

[1478] The server extracts past purchase data from a database.

[1479] The server's AI learning module uses the extracted purchasing data to learn.

[1480] The server stores the learning results in a database and reflects them in future advice generation.

[1481] Step 6:

[1482] The server conducts surveys of customers and collects the results. The AI ​​learning module also learns from these survey results and generates even higher quality advice.

[1483] Input: Survey results from buyers

[1484] Output: Further improved advice accuracy due to the trained model

[1485] Specific behavior:

[1486] The server automatically sends a questionnaire to the purchaser.

[1487] The purchaser answers the questionnaire and submits it.

[1488] The server stores the received survey results in a database and provides them to the AI ​​learning module.

[1489] The AI ​​learning module learns from this and generates even more accurate advice.

[1490] (Application example 1)

[1491] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1492] In online auctions and electronic markets, if sellers do not effectively explain their products, it can discourage buyers and prevent transactions from proceeding smoothly. This requires sellers to provide detailed product information, which takes time and effort. Furthermore, it is often difficult to identify the missing information, resulting in a decline in the quality of product descriptions. Therefore, a system is needed that can continuously improve the quality of advice by utilizing past purchase data and buyer feedback.

[1493] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1494] In this invention, the server includes a means for inputting product information, an analysis means for analyzing the input product information and identifying missing information, an advice generation means for generating specific product description advice based on the analysis, a means for presenting the generated advice, and a means for learning past purchase data using a generative AI model to improve the quality of the advice. This enables sellers to quickly create effective and detailed product descriptions, increasing buyer trust and facilitating transactions.

[1495] "Product information" refers to detailed information about a product entered by a seller in an online auction or online marketplace. This information includes attribute information such as the product name, category, size, color, and condition.

[1496] "Analysis means" refers to the technology or method for analyzing input product information and identifying missing information or areas requiring improvement.

[1497] "Advice generation means" refers to a technique or method for instructing sellers on specific improvements to product descriptions and methods for providing additional information based on the analysis results.

[1498] "Presentation means" refers to the technology or method for presenting the generated advice to the seller in an easy-to-view manner and encouraging necessary improvements.

[1499] A "generative AI model" refers to an artificial intelligence model that learns from past purchasing data and customer feedback to constantly improve the quality of advice.

[1500] "Past purchase data" is historical information about past purchases, and includes data such as product category, number of purchases, and buyer ratings.

[1501] A "customer survey" is a questionnaire-based survey sent to buyers to assess the usefulness of product descriptions and their satisfaction with the purchased product.

[1502] The system of the present invention is configured to provide sellers with specific advice to improve the quality of their product descriptions. The main components of the system and their roles will be described below.

[1503] System configuration:

[1504] This system is realized mainly using the following hardware and software.

[1505] Hardware: The smartphone or computer used by the seller

[1506] Software: Server, SpaCy, scikit-learn, generative AI model

[1507] 1. Product information input method:

[1508] The user (seller) enters product information via a smartphone or computer, such as "Jacket, Size M, Color: Blue, Condition: Almost New."

[1509] 2. Analysis method:

[1510] The server uses SpaCy to analyze the input product information. Specifically, it extracts important tags (nouns and adjectives) from the information and identifies any missing information.

[1511] 3. Advice Generation Methods:

[1512] The server uses scikit-learn functions to generate specific advice about missing information or information that needs improvement. For example, specific advice might be generated such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag."

[1513] 4. Means of presentation:

[1514] The generated advice is displayed on the user's smartphone or computer, and the seller can revise the product description accordingly.

[1515] 5. Learning tools:

[1516] The generative AI model on the server learns from past purchase data and customer survey results. Based on this data, it continuously improves the quality of advice. For example, it learns trends such as "products with specific dimensional information have a higher purchase rate."

[1517] Examples:

[1518] User Input: Seller enters "Jacket, Size M, Color: Blue, Condition: Like New."

[1519] Analysis result: The server analyzes the input information using Spacy and determines that the information for "shoulder width," "chest width," and "sleeve length" is missing.

[1520] Generated advice: Using scikit-learn, the server generates the advice, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take photos of the entire product and the tag." and presents it to the seller.

[1521] Example prompt sentence:

[1522] Product information: Blue jacket, size M, condition almost new

[1523] From the analysis results, we identified the missing information as "shoulder width," "chest width," and "sleeve length." Please create a product description that includes specific examples like the ones below.

[1524] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1525] Step 1:

[1526] User enters product information

[1527] Users input product information using a smartphone or computer. This input includes detailed information such as product category, size, color, and condition. Specific input is possible, such as "Jacket, Size M, Color: Blue, Condition: Almost New."

[1528] Step 2:

[1529] Server receives product information

[1530] The server receives the product information entered by the user and stores it in a database for use in subsequent analysis.

[1531] Step 3:

[1532] The server analyzes the input information

[1533] The server uses SpaCy to analyze the received product information. Specifically, it extracts important tags (nouns and adjectives) and identifies missing information. For example, it determines that the shoulder width, chest width, and sleeve length are missing for a jacket.

[1534] Input: Product information entered by the user (e.g., "Jacket, Size M, Color: Blue, Condition: Like New")

[1535] Output: Extracted important tags (e.g., "shoulder width," "chest width," and "sleeve length" are determined to be missing)

[1536] Step 4:

[1537] Server generates advice

[1538] The server uses scikit-learn to generate specific advice based on the missing information. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and the tag."

[1539] Input: Missing information (e.g. "shoulder width", "chest width", "sleeve length")

[1540] Output: Generated specific advice (e.g., "Please provide the specific measurements for shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and a photo of the tag.")

[1541] Step 5:

[1542] The server provides advice to the user

[1543] The server sends the generated advice to the user's smartphone or PC, allowing the user to refer to the advice and revise the product description.

[1544] Input: Generated advice (e.g., "Please provide the specific measurements for shoulder width, chest width, and sleeve length. Also, please take a photo of the entire product and a photo of the tag.")

[1545] Output: Advice displayed on the user's terminal

[1546] Step 6:

[1547] The server learns the purchasing data

[1548] The generative AI model on the server collects past purchase data and learns from it. For example, it can extract trends such as "products with specific dimensional information have a higher purchase rate." The results of this learning are reflected in future advice generation.

[1549] Input: Past purchase data

[1550] Output: Learning results (e.g., "Products with specific dimensions have a higher purchase rate.")

[1551] Step 7:

[1552] The server learns the survey results

[1553] The server conducts surveys of shoppers and collects and learns from the results. This provides information on the usefulness of product descriptions and satisfaction with purchased products. The generative AI model uses this information to further improve the quality of advice.

[1554] Input: Customer survey results

[1555] Output: Learning results (e.g., feedback such as "The specific dimensions were listed, so I was able to make the purchase with confidence.")

[1556] Through the above steps, sellers can create high-quality product descriptions, which increases buyers' trust and facilitates smooth transactions.

[1557] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1558] This invention includes a system that provides high-quality product descriptions to sellers of online auctions and electronic marketplaces. This system allows sellers to create specific product descriptions that encourage purchases. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, the system can provide more personalized advice.

[1559] System Overview

[1560] This system has the following main functions:

[1561] 1. How to receive product information from sellers

[1562] 2. Analysis means for analyzing received product information and identifying missing information

[1563] 3. Advice generation method that generates specific product description advice based on the analysis results

[1564] 4. A method for presenting the generated advice to the seller

[1565] 5. Learning tools to collect and learn from past purchase data to improve the quality of advice

[1566] 6. A means of surveying buyers and learning from their results

[1567] 7. An emotion engine that recognizes user emotions and uses that information to generate advice.

[1568] Program processing explanation

[1569] 1. User Input

[1570] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[1571] The terminal checks the input product information and prepares to send it to the server.

[1572] 2. Data Reception and Analysis

[1573] The server receives the product information sent from the terminal.

[1574] The server stores the received data in a database as a preprocessing step for analysis.

[1575] The server's AI confirms that the product category is "jacket."

[1576] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[1577] 3. Emotion Recognition by Emotion Engine

[1578] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine.

[1579] The server's emotion engine analyzes this and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.).

[1580] The server stores the emotion information obtained from the emotion engine as the analysis result.

[1581] 4. Advice Generation

[1582] The server's AI generates specific product description advice based on the missing information. For example, it generates specific advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width xx cm, chest width xx cm, sleeve length xx cm)."

[1583] The information from the emotion engine is reflected and the content and tone of the advice is adjusted, such as "brief instructions if the user is anxious" or "detailed instructions if the user is relieved."

[1584] 5. Learning from purchasing data

[1585] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[1586] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[1587] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[1588] 6. Presentation to the User

[1589] The server transmits the generated advice to the user's terminal.

[1590] The device displays the received advice to the user, who then modifies the product description in accordance with the advice.

[1591] 7. User Modifications and Resubmissions

[1592] Based on advice from the server, the user measures specific dimensions and takes photos of the overall object and the tag.

[1593] The user retransmits the corrected information from the terminal to the server.

[1594] 8. Survey implementation

[1595] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[1596] 9. Collecting and Learning from Survey Results

[1597] The server collects the survey results and stores them in a database.

[1598] The server's AI learns from the survey results and reflects them in generating future advice.

[1599] Specific examples

[1600] Example 1:

[1601] The user inputs "Jacket", "Size: M", "Color: Blue", and "Condition: Like New". The emotion engine detects the emotion "Impatience".

[1602] The server generates specific and concise advice: "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Sample sentences for concise descriptions are shown below: Shoulder width XX cm, chest width XX cm, sleeve length XX cm."

[1603] The user measures the dimensions and briefly edits the product description.

[1604] Example 2:

[1605] In a customer survey, we received feedback that "specific dimensions were listed, so I was able to make the purchase with confidence."

[1606] The server learns from this and reflects it in future advice generation.

[1607] In this way, by providing specific advice that takes into account the user's emotions, it is possible to improve the quality of product descriptions and further increase the matching rate between buyers and sellers.

[1608] The processing flow will be explained below.

[1609] Step 1: User Input

[1610] The user inputs product information into the terminal, such as category ("jacket"), size ("M"), color ("blue"), and condition ("almost new").

[1611] The terminal checks the input product information and prepares to send it to the server.

[1612] Step 2: Receiving data

[1613] The server receives the product information sent from the terminal.

[1614] The server stores the received data in a database as a preprocessing step for analysis.

[1615] Step 3: Emotion recognition by the emotion engine

[1616] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine.

[1617] The server's emotion engine analyzes this and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.).

[1618] The server stores the emotion information obtained from the emotion engine as analysis data.

[1619] Step 4: Data analysis

[1620] The server's AI analyzes the received product information.

[1621] The server's AI confirms that the product category is "jacket."

[1622] The server's AI determines that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing.

[1623] The server's AI also checks color and state information, and also refers to emotion information.

[1624] Step 5: Advice Generation

[1625] The server's AI generates specific product description advice for sellers based on the data analysis results and emotional information.

[1626] For example, if the emotional information is "impatience," the system generates concise advice such as, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width XX cm, chest width XX cm, sleeve length XX cm). Also, please take photos of the entire product and the tag."

[1627] If the emotional information is "peace of mind," detailed advice is provided: "Please describe the product's features in detail and include specific measurements such as shoulder width, chest width, and sleeve length. Photos should include an overall view of the product, tags, and details."

[1628] Step 6: Present to the user

[1629] The server transmits the generated advice to the user's terminal.

[1630] The terminal displays the received advice to the user.

[1631] Step 7: User corrections and resubmission

[1632] The user makes the necessary corrections based on the provided advice, such as taking specific measurements and taking photos of the overall product and the tag.

[1633] The user retransmits the corrected information from the terminal to the server.

[1634] Step 8: Learn your purchasing data

[1635] The server periodically collects past purchase data, including product categories, product details, and buyer behavior data.

[1636] Based on the collected purchasing data, the server's AI learns what kind of product descriptions will increase purchasing desire.

[1637] Based on the learning results, the advice generation algorithm is updated to improve accuracy.

[1638] Step 9: Survey

[1639] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[1640] Step 10: Collect and learn from survey results

[1641] The server collects the survey results and stores them in a database.

[1642] The server's AI learns from the survey results and reflects them in generating future advice.

[1643] In this way, sellers can create specific and inspiring product descriptions by providing specific advice that takes users' emotions into account, further increasing the chances of matching buyers and sellers.

[1644] Example 2

[1645] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1646] In online auctions and electronic markets, if sellers provide insufficient product descriptions, buyers have difficulty understanding the product details, which reduces their willingness to purchase. Furthermore, some users are easily influenced by their emotions, and the quality and content of product descriptions can directly affect their willingness to purchase. Therefore, there is a need for support for sellers to provide high-quality, specific product descriptions that take emotions into consideration.

[1647] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving product information input by a seller, a means for analyzing the received product information to identify insufficient information, a means for acquiring and analyzing the user's emotional state based on the input product information, a means for generating specific product description advice to the seller based on the analysis, and a means for presenting the generated advice to the seller. This enables the seller to supplement the insufficient information and provide a high-quality product description that takes the user's emotions into consideration.

[1648] A "seller" is an individual or organization that sells goods on an online auction or electronic marketplace.

[1649] "Product information" refers to detailed information about the product being sold by the seller, including, specifically, the category, size, color, condition, and the like.

[1650] The "emotional state" refers to the psychological state of the user when inputting product information, and examples include feelings such as impatience, anxiety, and relief.

[1651] The "receiving means" is a function that receives product information sent from the terminal at the server and performs processing to store the information in the database.

[1652] The "analysis means" is a function for analyzing received product information and identifying missing information.

[1653] The "emotion recognition means" is a function for analyzing the user's facial expressions and voice and identifying their emotional state.

[1654] The "advice generation means" is a function for dynamically generating specific advice on product descriptions based on the results of the analysis means and emotion recognition means.

[1655] The "presentation means" is a function for displaying the generated advice to the seller in an easy-to-understand manner.

[1656] "Purchase data" refers to data including product categories, detailed product descriptions, purchaser behavior data, and the like from past transactions.

[1657] A "survey" is a survey conducted to collect feedback from buyers about their satisfaction with the purchased product and the usefulness of the product description.

[1658] "Collection means" refers to a function for effectively collecting purchasing data and survey results.

[1659] The "learning means" is a function that uses collected data to learn, through a machine learning algorithm, what kind of product descriptions will increase purchasing desire, and reflects this in the advice generation algorithm.

[1660] This invention is a system that provides high-quality product descriptions to sellers of online auctions and electronic markets. This system allows sellers to create specific product descriptions that encourage purchases. In addition, by incorporating an emotion engine that recognizes the user's emotions, the system can provide more personalized advice.

[1661] Hardware and software used

[1662] This system uses servers and terminals as its main hardware. The server requires a high-performance processor, a large amount of memory, and a database (e.g., MySQL, PostgreSQL) to store large amounts of data. It also incorporates an AI engine (e.g., TensorFlow, PyTorch) for emotion recognition and data analysis. The terminals are devices equipped with cameras and microphones (e.g., smartphones, tablets).

[1663] Explanation of program processing

[1664] The program of this system performs processing roughly according to the following steps.

[1665] User Input

[1666] The user inputs product information into the terminal. For example, "Category: Jacket," "Size: M," "Color: Blue," "Condition: Almost New," etc. The terminal confirms the user's input and prepares to send it to the server.

[1667] Data reception and analysis

[1668] The server receives the product information sent from the device. It then stores the data in a database and begins analyzing the received data. The server's AI confirms that the product category is "jacket" and identifies that the size information sent is "M," but that specific measurements for shoulder width, chest width, and sleeve length are missing.

[1669] Emotion recognition by emotion engine

[1670] The device collects facial expressions and voices as the user enters product information and sends them to the emotion engine. The server's emotion engine analyzes these and recognizes the user's emotional state (e.g., impatience, anxiety, relief, etc.). The acquired emotional information is recorded in a database as an analysis result.

[1671] Advice Generation

[1672] The server's AI generates specific product description advice based on the missing information and the acquired emotional information. For example, the advice generated might be, "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g., shoulder width XX cm, chest width XX cm, sleeve length XX cm)." The content and tone of the advice are adjusted to reflect the information from the emotional engine, such as "concise instructions if the customer is in a hurry" or "detailed instructions if the customer is relieved."

[1673] Learning from purchasing data

[1674] The server periodically collects past purchase data, including product categories, product description details, and buyer behavior data. The server's AI uses this data to learn what product descriptions increase purchase motivation and update its advice generation algorithm.

[1675] Presenting to the user

[1676] The server sends the generated advice to the user's terminal, which displays the received advice to the user, who then modifies the product description in accordance with the advice.

[1677] User correction and resubmission

[1678] Based on the advice from the server, the user measures the specific dimensions, takes photos of the whole area and the tag, and then resends the corrected information from the device to the server.

[1679] Survey

[1680] The server sends a questionnaire to the purchaser, asking about the satisfaction with the purchased product and the usefulness of the product description.

[1681] Collecting and learning from survey results

[1682] The server collects the survey results and stores them in a database. The server's AI learns from the survey results and uses them to generate future advice.

[1683] Specific examples

[1684] 1. A user enters "Jacket", "Size: M", "Color: Blue", "Condition: Like New". The emotion engine detects the emotion "Impatient".

[1685] 2. The server generates specific and concise advice: "Please provide the specific measurements of shoulder width, chest width, and sleeve length. Sample sentences for concise descriptions are shown below: Shoulder width XX cm, chest width XX cm, sleeve length XX cm." The user measures the measurements and briefly amends the product description.

[1686] Prompt Sentence Examples

[1687] "If the jacket is a size medium, please provide detailed measurements such as shoulder width, chest width, and sleeve length. Also, adjust the instructions to be brief or detailed depending on the user's emotional state."

[1688] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1689] Step 1:

[1690] The user inputs product information into the terminal. The user inputs information such as "Category: Jacket," "Size: M," "Color: Blue," and "Condition: Almost new" into the input form on the terminal. The terminal checks the input product information, formats it, and prepares to send it to the server. Input: User-entered data, Output: Formatted product information data

[1691] Step 2:

[1692] The server receives the product information sent from the terminal. The server parses the received data in JSON format and checks whether the required fields are filled in. The server stores the received data in a database. Input: Formatted product information data, Output: Records stored in the database

[1693] Step 3:

[1694] The server's AI confirms that the product category is "jacket" and identifies that the size information is "M" and that specific dimensional information (shoulder width, chest width, sleeve length, etc.) is missing. The server identifies the missing information and lists it. Input: Records stored in the database, Output: List of missing information

[1695] Step 4:

[1696] The device collects facial expressions and voice data when the user enters product information, and sends this data to the emotion engine in real time. The emotion engine uses facial expression recognition and voice analysis technology to detect the user's emotional state (e.g., impatience, anxiety, relief). Input: User's facial and voice data, Output: User's emotional state

[1697] Step 5:

[1698] The emotion engine on the server records the detected emotional state in a database as an analysis result. Input: User's emotional state, Output: Analysis result stored in the database

[1699] Step 6:

[1700] The server's AI generates specific product description advice based on the missing information and emotional information. For example, it generates advice such as "Please provide the specific measurements of shoulder width, chest width, and sleeve length (e.g. shoulder width XX cm, chest width XX cm, sleeve length XX cm)." It reflects the information from the emotional engine and adjusts the content and tone of the advice in the form of "concise instructions if the user is in a hurry" or "detailed instructions if the user is relieved." Input: Missing information list, user's emotional state, Output: Generated advice

[1701] Step 7:

[1702] The server sends the generated advice to the user's terminal. The terminal displays the received advice to the user, who then modifies the product description according to the advice. Input: Generated advice, Output: Advice displayed on the user's terminal

[1703] Step 8:

[1704] Based on the advice from the server, the user measures the specific dimensions and takes photos of the overall product and the tag. The user then resends the corrected information from their device to the server. Input: Dimensional information and photo data, Output: Re-sent product information data

[1705] Step 9:

[1706] The server sends a survey to the customer, asking about their satisfaction with the purchased product and the usefulness of the product description. Input: Customer data, Output: Sent survey link

[1707] Step 10:

[1708] The server collects the survey results and stores them in a database. The server's AI learns from the survey results and uses them to generate future advice. Input: Survey result data, Output: Feedback data stored in the database

[1709] (Application example 2)

[1710] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1711] While many sellers want to improve the quality of product descriptions in online auctions and electronic markets, they often don't know how to create specific and compelling product descriptions. Furthermore, it can be difficult to create consistent, high-quality descriptions due to emotional states. Furthermore, they are unable to effectively utilize buyer feedback and past purchase data, which hinders progress in improving product descriptions.

[1712] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving product information input by the seller, analysis means for analyzing the received product information and identifying information deficiencies, advice generation means for generating specific product description advice for the seller based on the analysis, means for presenting the generated advice to the seller, emotion recognition means for recognizing the seller's emotions in real time and adjusting the content of the advice, and advice adjustment means for adapting the tone and content of the advice based on user emotion information. This makes it possible to create effective and attractive product descriptions while taking into account the emotional state faced by the seller, and to increase purchasing desire.

[1713] "Seller" refers to an individual or corporation that enters and publishes product information in order to sell products on online auctions or electronic markets.

[1714] "Product Information" refers to detailed information necessary for sales, such as product category, size, color, condition, price, and description.

[1715] "Means for receiving" refers to the hardware or software used to receive product information provided by sellers.

[1716] "Analysis means" refers to algorithms or software for analyzing received product information and identifying missing information.

[1717] "Advice generation means" refers to a system that provides sellers with specific improvements and suggestions for product descriptions based on the analysis results.

[1718] "Means for presentation" refers to an interface for displaying or communicating the generated advice to the seller in an easy-to-view format.

[1719] "Emotion recognition means" refers to sensors and analytical algorithms that recognize the seller's emotional state in real time.

[1720] "Advice adjustment means" refers to a system for adjusting the tone and content of advice to suit the seller's current emotional state based on information from the emotion recognition means.

[1721] "Purchase data" refers to a series of data related to product sales, such as past purchase history, buyer feedback, and product description details.

[1722] A "survey" is a survey conducted among buyers to collect feedback on the usefulness of product descriptions and satisfaction with products.

[1723] This invention is a system for improving the quality of product descriptions in online auctions and electronic marketplaces. It involves a process in which a seller inputs product information, analyzes it to identify missing information, and generates and presents specific advice. It also has a function to recognize the seller's emotional state in real time using emotion recognition means and adjust the content and tone of the advice accordingly. The main components of this system and their operation are described in detail below.

[1724] System Components and Operation

[1725] 1. Receiving product information (user input)

[1726] A user uses a smartphone application to input product information, such as "smartphone case," "size: 6 inches," "color: black," and "condition: new." This data is sent from the user's device to a server. During this process, the smartphone's camera and microphone are also used to collect emotional information.

[1727] 2. Data reception and analysis (server processing)

[1728] The server receives product information sent from the user's device. The received data is stored in a database, and the product information is analyzed using analytical means. For example, it may confirm that the product category is a "smartphone case," but identify that specific dimensional information is missing. Here, a database management system (e.g., PostgreSQL) and an AI analysis engine (e.g., TensorFlow) are used.

[1729] 3. Emotion Recognition and Data Processing (Server Processing)

[1730] Facial expression and voice data collected when the user enters product information is sent to the emotion recognition means. The emotion recognition engine on the server analyzes this data and recognizes the user's emotional state (e.g., anxiety, relief, etc.). This recognition result is also stored in the database. Emotion recognition uses an emotion recognition library (e.g., OpenCV or Microsoft Emotion API).

[1731] 4. Generating and Presenting Advice (Server and Terminal Processing)

[1732] The server's AI model (e.g., GPT-3) generates specific product description advice based on the analysis results and emotional information. For example, the advice might be, "Please add specific details such as color, material, and case thickness. It would also be a good idea to add a statement guaranteeing the quality of the product so that buyers can make a purchase with confidence." The generated advice is sent to the user's device and displayed in a smartphone application.

[1733] 5. Learning purchasing data (server processing)

[1734] The server periodically collects past purchase data to learn which product descriptions encourage purchases. This data includes product categories, product details, and buyer behavior data. This allows the advice generation algorithm to be continuously improved.

[1735] 6. Survey implementation and learning (server processing)

[1736] The server sends a questionnaire to the customer, asking about their satisfaction with the purchased product and the usefulness of the product description. The collected survey results are also used as learning data and reflected in future advice generation.

[1737] Specific examples

[1738] For example, if a user enters "smartphone case," "size: 6 inches," "color: black," and "condition: new" into a smartphone app and the emotion engine detects the emotion of "anxiety," the server will generate and display specific advice such as, "Please add specific descriptions such as the color, material, and thickness of the case. It would also be a good idea to add a statement guaranteeing the quality of the product so that buyers can make their purchase with confidence."

[1739] Prompt Sentence Examples

[1740] "A user is trying to list a smartphone case. Please generate specific product description advice based on the following information: Product information: 'Size: 6 inches, Color: Black, Condition: New'. User sentiment: 'Anxious'. Please add specific dimensions and ask for advice."

[1741] This makes it possible to create effective and attractive product descriptions while taking into account the emotional state that the seller faces, thereby increasing purchasing motivation.

[1742] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1743] Step 1:

[1744] User Input

[1745] The user uses an application on their device (smartphone) to input product information (for example, "smartphone case," "size: 6 inches," "color: black," and "condition: new"). The input product information is temporarily stored on the device, and at the same time, the device's camera and microphone are used to collect the user's facial expressions and voice in real time. This allows emotional data to be collected as well. The input data is in the form of text and metadata.

[1746] Step 2:

[1747] Receiving and storing data

[1748] The device sends product information and emotion data to the server, which receives it and stores it in a database (e.g., PostgreSQL). Product information is stored as text data, and emotion data is stored as metadata. This lays the foundation for subsequent analysis and advice generation.

[1749] Step 3:

[1750] Data analysis

[1751] The server's analysis means (AI analysis engine, e.g., TensorFlow) analyzes the received product information and identifies missing information. For example, it confirms that the product category is "smartphone case," but identifies that specific dimensional information is missing. This analysis result is saved back into the database. In this step, text analysis is performed, and data calculations are performed to identify missing information.

[1752] Step 4:

[1753] emotion recognition

[1754] Facial expression and voice data collected when the user enters product information is sent to the server's emotion recognition engine (e.g., OpenCV or Microsoft Emotion API). The server analyzes this data and recognizes the user's emotional state (e.g., "anxiety," "relief," etc.). The recognition results are stored in a database as analysis results and are used to generate subsequent advice. Analysis of emotion data includes image analysis and voice analysis.

[1755] Step 5:

[1756] Advice Generation

[1757] The server's AI model (e.g., GPT-3) generates specific product description advice based on the analysis results and emotional information. For example, the advice might be, "Please add specific details such as color, material, and case thickness." The tone and content are also adjusted based on the emotional data. This generated advice is then stored back in the database. The generative AI model performs text generation and data calculations based on the prompt.

[1758] Step 6:

[1759] Providing advice

[1760] The server sends the generated advice to the user's terminal. On the user's terminal, the received advice is displayed to the user through an application. In this step, data is sent from the server to the terminal and displayed to the user. The advice is displayed in text format.

[1761] Step 7:

[1762] Collecting and learning from purchasing data

[1763] The server periodically collects past purchase data and stores it in a database. The collected data includes product categories, product descriptions, and buyer behavior data. The server's AI analysis engine analyzes this data and improves the advice generation algorithm. This step uses data collection and machine learning algorithms.

[1764] Step 8:

[1765] Conducting a survey

[1766] The server sends a questionnaire to the buyer, asking about the usefulness of the product description and their satisfaction with the product. Feedback from the buyer is collected by the server and stored in a database. The results of this questionnaire are used to generate future advice. Data is transmitted between the server and the buyer.

[1767] Step 9:

[1768] Studying survey results

[1769] The server's AI analysis engine analyzes the survey results and uses feedback on product satisfaction and the usefulness of product descriptions as learning data. This improves the accuracy of future advice generation. This step involves data analysis and machine learning.

[1770] Through these steps, sellers can receive specific advice based on real-time emotion recognition and purchasing data, enabling them to create high-quality product descriptions.

[1771] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1772] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1773] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1774] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1775] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1776] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1777] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1778] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1779] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1780] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1781] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1782] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1783] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1784] 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.

[1785] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1786] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1787] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1788] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1789] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1790] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1791] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1792] The following is further disclosed regarding the above embodiment.

[1793] (Claim 1)

[1794] A system for providing advice to sellers of online auctions or electronic markets to improve the quality of product descriptions,

[1795] A means for receiving product information input by a seller;

[1796] an analysis means for analyzing the received product information and identifying information deficiencies;

[1797] an advice generating means for generating specific product description advice for the seller based on the analysis;

[1798] a means for presenting the generated advice to the seller;

[1799] A system including:

[1800] (Claim 2)

[1801] 10. The system of claim 1, further comprising means for collecting and learning from past purchase data to improve the quality of the product description advice generator.

[1802] (Claim 3)

[1803] 2. The system according to claim 1, further comprising means for conducting a survey of purchasers and collecting and learning the results to improve the quality of the means for generating advice on product descriptions.

[1804] "Example 1"

[1805] (Claim 1)

[1806] A means for receiving product information input by a seller;

[1807] an analysis means for analyzing the received product information and identifying information deficiencies;

[1808] an advice generating means for generating specific product description advice for the seller based on the analysis;

[1809] a means for presenting the generated advice to the seller;

[1810] A means for transmitting the generated product description advice to a terminal and displaying it to a seller;

[1811] A means to collect past purchase data and use it to improve the quality of product explanation advice,

[1812] Conducting surveys of buyers and using the results to improve the quality of product explanation advice,

[1813] A system including:

[1814] (Claim 2)

[1815] 10. The system of claim 1, wherein past purchase data is collected and learned to improve the quality of the product description advice generator.

[1816] (Claim 3)

[1817] 2. The system according to claim 1, wherein the system improves the quality of the means for generating advice on product descriptions by conducting a survey of purchasers and collecting and learning from the results.

[1818] "Application Example 1"

[1819] (Claim 1)

[1820] A system for providing advice to improve the quality of product descriptions, comprising: a means for inputting product information;

[1821] an analysis means for analyzing the input product information and identifying missing information;

[1822] advice generation means for generating specific product description advice based on the analysis;

[1823] a means for presenting the generated advice;

[1824] A generative AI model that learns from past purchase data to improve the quality of advice.

[1825] A system including:

[1826] (Claim 2)

[1827] 10. The system of claim 1, further comprising means for automatically analyzing specific missing information related to the product category entered by the seller and providing advice regarding detailed attributes such as specific dimensions and photos.

[1828] (Claim 3)

[1829] 2. The system according to claim 1, further comprising means for conducting a survey of purchasers regarding their satisfaction with the purchased product and the usefulness of the product description, and learning from the results of the survey to improve the quality of the advice generating means.

[1830] "Example 2: Combining Emotion Engines"

[1831] (Claim 1)

[1832] A means for receiving product information input by a seller;

[1833] means for analyzing the received product information to identify missing information;

[1834] A means for acquiring and analyzing the emotional state of a user based on input product information;

[1835] means for generating specific product description advice to the seller based on the analysis;

[1836] a means for presenting the generated advice to the seller;

[1837] A system including:

[1838] (Claim 2)

[1839] 10. The system of claim 1, further comprising means for collecting and learning from past purchase data to improve the quality of the product description advice generator.

[1840] (Claim 3)

[1841] 2. The system according to claim 1, further comprising means for conducting a survey of purchasers and collecting and learning the results to improve the quality of the means for generating advice on product descriptions.

[1842] "Application example 2 when combining emotion engines"

[1843] (Claim 1)

[1844] A system for providing advice to sellers of online auctions or electronic markets to improve the quality of product descriptions,

[1845] A means for receiving product information input by a seller;

[1846] an analysis means for analyzing the received product information and identifying information deficiencies;

[1847] an advice generating means for generating specific product description advice for the seller based on the analysis;

[1848] a means for presenting the generated advice to the seller;

[1849] An emotion recognition means for recognizing the emotions of sellers in real time and adjusting the advice content;

[1850] an advice adjusting means for adapting the tone and content of the advice based on the user emotion information;

[1851] A system including:

[1852] (Claim 2)

[1853] 10. The system of claim 1, further comprising means for collecting and learning from past purchase data to improve the quality of the product description advice generator.

[1854] (Claim 3)

[1855] 2. The system according to claim 1, further comprising means for conducting a survey of purchasers and collecting and learning the results to improve the quality of the means for generating advice on product descriptions. [Explanation of symbols]

[1856] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system for providing advice to sellers of online auctions or electronic markets to improve the quality of product descriptions, A means for receiving product information input by a seller; an analysis means for analyzing the received product information and identifying information deficiencies; an advice generating means for generating specific product description advice for the seller based on the analysis; a means for presenting the generated advice to the seller; A system including:

2. 10. The system of claim 1, further comprising means for collecting and learning from past purchase data to improve the quality of the product description advice generator.

3. 2. The system according to claim 1, further comprising means for conducting a survey of purchasers and collecting and learning from the results to improve the quality of the means for generating advice on product descriptions.

Images