System

Abstract

To provide a system for achieving efficient and effective use of a reuse market.SOLUTION: A means for collecting and analyzing a search history, a browsing history, and a purchase history of a user, a means for analyzing a price of an exhibited product based on price data of other similar products and calculating an appropriate price, a means for collecting feedback from a user and updating a matching algorithm based on the feedback, a means for analyzing past behavior data and market trend data of the user and predicting latent needs of the user, and a means for generating a product list based on the predicted needs; The system includes a means for notifying a user of the list, a means for receiving a negotiation request from a purchase applicant and generating an appropriate negotiation proposal based on past negotiation data and market prices, and a means for supporting negotiation based on a request and a proposal transmitted by the user.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 today's reuse markets, users face the challenge of finding the right product for them. Sellers also struggle to set fair prices for their products, making it difficult to secure a suitable transaction. Furthermore, users face fewer opportunities to discover products they are potentially interested in, and the negotiation process is complicated, resulting in transactions that do not proceed smoothly. The present invention aims to solve these problems and enable users to use reuse markets efficiently and effectively. [Means for solving the problem]

[0005] The present invention provides a means for collecting and analyzing users' search history, browsing history, and purchase history, making it easier to understand users' interests and purchasing trends. It also includes a means for analyzing the prices of listed items based on price data for other similar items to calculate appropriate prices. It also includes a means for collecting user feedback and updating the matching algorithm based on that feedback, thereby improving matching accuracy over time. It also provides a means for analyzing users' past behavioral data and market trend data to predict users' potential needs. It generates a product list based on this data and notifies the user of the list. Furthermore, the system includes a means for receiving negotiation requests from potential buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, and a means for supporting negotiations based on requests and proposals submitted by users, thereby enabling efficient and effective use of the reuse market.

[0006] "Search history" is a record of keywords and phrases a user has previously entered into the search bar.

[0007] "Browse history" refers to the history of products and pages that a user has viewed in the past and found interesting.

[0008] "Purchase history" refers to records of products that a user has actually purchased in the past.

[0009] "Analytics" is the processing and analysis of collected data to find patterns and trends.

[0010] A "fair price" is the price at which a product is judged to have fair value in the market, and is calculated based on price data for other similar products.

[0011] "Feedback" refers to the evaluations and opinions users provide regarding the services and prices offered by the system.

[0012] "Matching algorithm" refers to a computational method or program used to effectively match users with products.

[0013] "Latent needs" are wants and desires that users may be interested in but are not currently explicitly aware of.

[0014] A "negotiation request" is a request regarding price and transaction terms that a potential buyer presents to a seller.

[0015] A "negotiation proposal" is a proposal that the system generates based on a negotiation request, showing the best conditions for both parties.

[0016] "Market trend data" refers to data on market trends, popular products, and price fluctuations. [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] The system of the present invention has functions for collecting users' search history, browsing history, and purchase history, for analyzing the prices of listed products and calculating appropriate prices, for collecting feedback from users and updating the matching algorithm, for predicting users' potential needs and recommending products, and for generating negotiation proposals based on negotiation requests and supporting negotiations.

[0039] User data collection and analysis

[0040] The server collects and analyzes data such as user search terms, browsing history, and past purchase history, which is used to understand user preferences, purchasing trends, and price sensitivity.

[0041] When a user searches, the device sends the search terms to the server in real time, allowing the server to analyze the latest data. For example, if a user searches for "vintage watches," their search history is sent to the server, and related products are displayed based on the analysis results.

[0042] Smart Pricing

[0043] The server analyzes the price data of similar products on the market based on the photos and description of the listed product and calculates an appropriate price. For example, if a seller wants to list an "iPhone (registered trademark) 12," the server analyzes the market price data of other similar products, calculates a recommended price of "70,000 yen," and displays it on the seller's device. The seller can use this price as a reference to set the listing price.

[0044] Improved matching accuracy

[0045] The server collects feedback from users and updates the matching algorithm based on that feedback, improving the accuracy of matching over time. For example, when a user provides feedback such as "This price is reasonable" or "I think it's cheaper," that data is stored on the server and used to suggest prices and improve matching accuracy the next time.

[0046] Predicting potential needs and recommending products

[0047] The server predicts users' potential needs based on their past behavioral data and market trend data. It then generates and notifies users of a list of products that best suit their needs. For example, if a user frequently searches for and browses "cameras," the server will recommend related camera accessories and new camera models.

[0048] The user's device will notify and display this list of recommended products, making it easier for the user to find products that meet their potential needs.

[0049] Negotiation support function

[0050] The server receives a negotiation request from a potential buyer and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a potential buyer requests a slight price reduction, the server calculates the appropriate price reduction amount based on past data and notifies the potential buyer and seller of the price reduction proposal.

[0051] The buyer and seller's devices can display negotiation proposals in real time and proceed with the negotiations based on them, which results in a smoother transaction and makes it easier to reach terms that satisfy both users.

[0052] The above is a specific embodiment of the system based on the present invention. By using this system, users can efficiently search for, purchase, and negotiate products, which is expected to revitalize the entire reuse market.

[0053] The processing flow will be explained below.

[0054] User data collection and analysis

[0055] Step 1:

[0056] A user opens the Reuse Market app on their device, types "vintage watches" into the search bar, and presses the search button.

[0057] Step 2:

[0058] The terminal sends the entered search words to the server.

[0059] Step 3:

[0060] The server stores the received search terms in a database and compares them with past search and purchase history.

[0061] Step 4:

[0062] The server analyzes the user's interests and purchasing trends based on the stored data, and generates appropriate information based on the results.

[0063] Smart Pricing

[0064] Step 1:

[0065] To list an iPhone 12, a seller enters product photos and descriptions from their device and presses the list button.

[0066] Step 2:

[0067] The terminal transmits the product information to the server.

[0068] Step 3:

[0069] The server analyzes the market price data of similar products based on the transmitted product information.

[0070] Step 4:

[0071] The server calculates the optimal price as a result of the analysis and generates a recommended price.

[0072] Step 5:

[0073] The server sends the recommended price to the seller's terminal, which displays the price to the seller.

[0074] Improved matching accuracy

[0075] Step 1:

[0076] The user provides feedback such as "This price is good" or "It could be a little cheaper."

[0077] Step 2:

[0078] The device sends the user's feedback to the server.

[0079] Step 3:

[0080] The server stores the received feedback and adds it to a database to be analyzed.

[0081] Step 4:

[0082] The server updates its matching algorithm based on the new feedback, improving accuracy.

[0083] Predicting potential needs and recommending products

[0084] Step 1:

[0085] The server compares the user's past behavioral data (search history, browsing history, purchase history) with market trend data to predict the user's potential needs.

[0086] Step 2:

[0087] The server generates a list of products that best suit the user based on their predicted needs.

[0088] Step 3:

[0089] The server transmits the generated recommended product list to the user's terminal, and the terminal notifies the user of the recommended products.

[0090] Negotiation support function

[0091] Step 1:

[0092] A prospective purchaser sends a price reduction request for the product.

[0093] Step 2:

[0094] The terminal sends this request to the server.

[0095] Step 3:

[0096] The server analyzes the request and generates an appropriate negotiation proposal based on past negotiation data and market prices.

[0097] Step 4:

[0098] The server sends the generated negotiation proposal to the prospective buyer and the seller.

[0099] Step 5:

[0100] The buyer and seller's terminals display negotiation proposals in real time and confirm them with each other.

[0101] Step 6:

[0102] The user (seller) sets a new price based on the proposal, and the transaction is completed when the potential buyer agrees to it.

[0103] Example 1

[0104] 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."

[0105] In current online marketplaces, many systems that effectively utilize users' search and purchase histories to suggest products face challenges in terms of matching accuracy and price accuracy. Furthermore, they lack the ability to accurately predict users' potential needs and support functions to smoothly advance the negotiation process. These challenges must be addressed to increase user satisfaction.

[0106] 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.

[0107] In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history, means for transmitting search terms from the user's terminal in real time, means for analyzing price data of similar products in the market based on information about the listed product and calculating an appropriate price, means for collecting feedback from the user and updating a matching algorithm based on the feedback, means for analyzing past user behavior data and market trend data and predicting the user's potential needs, means for generating a product list based on the predicted needs and notifying the user of the list, means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, and means for supporting negotiations based on requests and proposals transmitted by the user. This enables users to efficiently search for, purchase, and negotiate on products.

[0108] "User" refers to a person who uses the System to search for, view, purchase, or list products.

[0109] "Device" refers to electronic devices such as computers, smartphones, and tablets used by users.

[0110] "Server" refers to a computer system that receives, analyzes, stores, and processes data submitted by users.

[0111] "Search History" refers to a record of keywords and phrases that a User has previously searched for on the System.

[0112] "Browse history" refers to the record of product pages that a user has viewed on the System.

[0113] "Purchase History" refers to the record of products that a User has previously purchased through this System.

[0114] "Feedback" refers to data such as opinions, ratings, and impressions provided by users.

[0115] A "matching algorithm" refers to a calculation method that analyzes user data and product data to suggest the most suitable product to the user.

[0116] "Fair price" refers to the price that is considered appropriate for the product, calculated by the server by analyzing market data.

[0117] "Latent needs" refer to the desires and needs that users may have that are not explicitly stated by users but that can be inferred from past behavioral data and market trend data.

[0118] "Product list" refers to a list of multiple products that the server generates based on the user's potential needs and notifies the user.

[0119] A "negotiation request" refers to a request from a prospective buyer to a seller to change the price or terms of the transaction.

[0120] "Negotiation proposal" refers to the negotiation conditions that the server generates based on past negotiation data and market price data and notifies the prospective buyer and seller.

[0121] The system of the present invention uses multiple hardware and software components to provide functions for collecting and analyzing users' search history, browsing history, and purchase history, analyzing the prices of listed items to calculate appropriate prices, collecting feedback from users to update matching algorithms, predicting users' potential needs and recommending items, and generating negotiation proposals based on negotiation requests to support negotiations.

[0122] Hardware used

[0123] 1. Device: The computer, smartphone, tablet, etc. used by the user.

[0124] 2. Server: A high-performance computer system that collects, analyzes, stores, and processes data.

[0125] Software used

[0126] 1. Data collection program: Software that runs on the device and transmits user operations to a server in real time.

[0127] 2. Data analysis program: An algorithm that runs on the server and analyzes the collected data.

[0128] 3. Feedback collection program: Software that receives and analyzes feedback from users.

[0129] 4. Price analysis program: An algorithm that runs on the server and calculates the fair price based on market data.

[0130] 5. Matching algorithm: A calculation method for suggesting optimal products based on user data.

[0131] 6. Product recommendation generator: Software that predicts users' potential needs and generates product lists.

[0132] 7. Negotiation Support Program: Software that receives negotiation requests, generates appropriate negotiation proposals, and sends them to the user.

[0133] Example of operation

[0134] When a user searches for "vintage watches," the user's device sends the search term to the server in real time. The server collects data including the user's search history, past browsing history, and purchase history, and performs analysis related to the search term "vintage watches." As a result, the server generates a list of related products and displays it on the user's device.

[0135] When a seller tries to list an iPhone 12, the product information entered on the seller's device is sent to the server. The server analyzes the product's photos and description and retrieves pricing data for similar products from other online marketplaces. It then calculates the optimal price of 70,000 yen and provides it to the seller's device. The seller can use this price as a reference to set the selling price of their own product.

[0136] When a user provides feedback, such as "this price is reasonable" or "it should be cheaper," that feedback is sent from the user's device to the server and stored. The server then incorporates this feedback into the next price suggestion and matching accuracy improvement, thereby improving accuracy.

[0137] If a user frequently searches and browses for "camera," the server will use that data to recommend camera-related accessories and new camera models, and these recommendations will be displayed on the user's device and the user will be notified.

[0138] When a prospective buyer sends a negotiation request saying, "I would like to ask for a further price reduction," the server generates an appropriate price reduction proposal based on past negotiation data and market price data, and sends it to the terminals of the prospective buyer and the seller for presentation.

[0139] Prompt Sentence Examples

[0140] "Based on the user's past search history and market trends, predict his potential needs and generate a list of relevant products."

[0141] "Please calculate a fair price based on the description of the listed item and market price data."

[0142] "Update your matching algorithm based on user feedback data."

[0143] As a result, the system of the present invention provides users with optimal product search, purchasing, and negotiation, and is expected to revitalize the entire reuse market.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1: Collect user data

[0146] 1.1. Submitting search terms

[0147] A user enters a search term into the device's search bar.

[0148] The device sends the entered search term (e.g., "vintage watch") to the server in real time.

[0149] Input: User's search term.

[0150] Data processing: Formalizing and structuring search terms.

[0151] Output: Search word data sent to the server.

[0152] 1.2. Collection of browsing and purchase history

[0153] The server collects data on the product pages the user has previously viewed and the products they have purchased.

[0154] Input: User's browsing history, purchase history.

[0155] Data processing: Organizing data based on time series.

[0156] Output: Structured browsing and purchase history data.

[0157] Step 2: Analyze the data

[0158] 2.1. Analysis of user trends

[0159] The server analyzes the collected search terms, browsing history, and purchase history to identify the user's preferences and purchasing trends.

[0160] Input: Search terms, browsing history, and purchase history data.

[0161] Data processing: Data analysis and pattern recognition.

[0162] Output: Analysis of user preferences and purchasing trends.

[0163] 2.2. Display of related products

[0164] The server generates a list of related products based on the analysis results and notifies the user's device.

[0165] Input: Analysis of user preferences and purchasing trends.

[0166] Data processing: Generate a list of related products.

[0167] Output: Related product list displayed on the device.

[0168] Step 3: Smart Pricing

[0169] 3.1. Product data collection

[0170] The user (seller) enters product information (photo and description) into the terminal and sends it to the server.

[0171] Input: Product information (photo, description).

[0172] Data Processing: Receiving product information and converting it into data for analysis.

[0173] Output: Structured product data.

[0174] 3.2. Market price data collection

[0175] The server collects price data for other similar products in the market.

[0176] Input: Product information, matching market data.

[0177] Data processing: market data collection and matching.

[0178] Output: Price data for similar products.

[0179] 3.3. Calculating the fair price

[0180] The server calculates the fair price of the auction item based on the market price data.

[0181] Input: Price data for similar products.

[0182] Data processing: Calculating fair prices.

[0183] Output: Reasonably priced and affordable.

[0184] 3.4. Recommended Price

[0185] The server notifies the seller's terminal of the calculated fair price.

[0186] Enter: Fair Price.

[0187] Data processing: Formalization of pricing data.

[0188] Output: The suggested price displayed on the seller's device.

[0189] Step 4: Gather feedback and update the algorithm

[0190] 4.1. Sending Feedback

[0191] Users enter feedback about prices and product ratings into the device.

[0192] Input: Feedback content.

[0193] Data processing: Formalization of feedback data.

[0194] Output: Feedback data sent to the server.

[0195] 4.2. Gathering Feedback for Algorithm Updates

[0196] The server accumulates and stores the collected feedback data.

[0197] Input: Feedback data.

[0198] Data processing: Accumulation and analysis of feedback data.

[0199] Output: The updated matching algorithm.

[0200] Step 5: Anticipating potential needs and recommending products

[0201] 5.1. Analysis of behavioral data

[0202] The server analyzes users' past behavioral data and market trend data.

[0203] Inputs: Behavioral data, market trend data.

[0204] Data processing: Data analysis and pattern recognition.

[0205] Output: Prediction of potential user needs.

[0206] 5.2. Creating a Product List

[0207] The server generates a list of related products based on the predicted user needs and notifies the user's terminal.

[0208] Input: Predicted potential needs.

[0209] Data processing: Product list generation.

[0210] Output: A list of recommended products displayed on the device.

[0211] Step 6: Negotiation support

[0212] 6.1. Sending a Negotiation Request

[0213] The prospective buyer sends a negotiation request from the terminal.

[0214] Input: Negotiation request.

[0215] Data processing: Request formatting and storage.

[0216] Output: The negotiation request sent to the server.

[0217] 6.2. Generating Negotiation Proposals

[0218] The server generates appropriate negotiation proposals based on past negotiation data and market data.

[0219] Inputs: Negotiation request, historical negotiation data, market data.

[0220] Data processing: Generating negotiation proposals.

[0221] Output: Negotiation proposal sent to the buyer's and seller's devices.

[0222] This will enable each function of the system to be realized, enabling users to efficiently search for, purchase, and negotiate products.

[0223] (Application example 1)

[0224] 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."

[0225] Traditional online shopping sites typically recommend products based on users' search and purchase histories, but this method is often inaccurate. In particular, it is difficult to accurately predict and recommend products that users will be interested in, which can result in poor user experience. Furthermore, there is a lack of functionality to automatically generate appropriate negotiation proposals based on negotiation requests and facilitate smooth negotiations between users. This creates the challenge of finding transaction terms that satisfy users.

[0226] 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.

[0227] In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history, means for analyzing the price of a listed item based on price data of other similar items and calculating an appropriate price, means for collecting user feedback and updating a matching algorithm based on the feedback, means for analyzing the user's past behavioral data and market trend data and predicting the user's potential needs, means for generating a product list based on the predicted needs and notifying the user of the list, means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, means for supporting negotiations based on requests and proposals submitted by the user, means for providing optimal prices and product recommendations based on the user's behavioral data, and means for generating prompt messages using a generative AI model that has learned the user's purchasing tendencies. This enables efficient product recommendations, calculation of appropriate prices, and negotiation support based on the user's behavioral data, thereby significantly improving the user experience.

[0228] "Search history" is a record of a user's past search queries within websites and applications.

[0229] "Browsing history" is a record of data about web pages and product pages that a user has viewed in the past.

[0230] "Purchase history" is a record of data on products purchased by a user in the past.

[0231] "Analysis" is the process of extracting meaning from collected data using statistical or machine learning algorithms.

[0232] "Price data for similar products" refers to price information for products of the same type or with similar characteristics that exist in the market.

[0233] A "fair price" is a product price that is determined statistically or algorithmically to be fair and appropriate to the market.

[0234] "Feedback" refers to opinions and evaluation data provided by users.

[0235] A "matching algorithm" is a calculation procedure that recommends optimal products and services based on user data.

[0236] "Past behavioral data" refers to the user's accumulated behavioral records, such as search history, browsing history, and purchase history.

[0237] "Market trend data" is data that includes information on current market trends and popular products.

[0238] "Latent needs" are needs that are inferred from users' behavior and past data, even if they are not explicitly stated.

[0239] A "negotiation request" is a request sent by a potential purchaser to change the product price or adjust the terms.

[0240] A "negotiation proposal" is a proposal for negotiation that is generated based on past data and market prices.

[0241] A "generative AI model" is a model trained by artificial intelligence that performs generative tasks based on user behavior and tendencies.

[0242] A "prompt" is a sentence output by a generative AI model that suggests the next action or suggestion to the user.

[0243] The present invention relates to a system that collects user behavior data on an online shopping site, calculates product prices based on the collected data, recommends optimal products, and supports negotiations. Specific embodiments of the system are described below.

[0244] System Configuration

[0245] Hardware

[0246] The system of the present invention comprises the following hardware:

[0247] Smartphone: A device where users can enter data and receive product recommendations and negotiation offers.

[0248] Server: Hardware for collecting data, analyzing it, running generative AI models, and generating prompts to notify the user.

[0249] software

[0250] The system of the present invention uses the following software:

[0251] Python: A programming language for data collection, analysis, prediction, and proposals.

[0252] Keras: A framework that uses neural networks to learn from user data and build generative AI models.

[0253] Scikit-learn: A library for data preprocessing such as clustering and standardization.

[0254] Data collection and analysis

[0255] The server collects the user's search history, browsing history, and purchase history, and analyzes the user's behavior based on this. Specifically, when a user searches, the search terms are sent from the device in real time, and the data is analyzed by the server. For example, if a user searches for "vintage watches," the server saves the search history and displays related products.

[0256] Smart Pricing

[0257] The server calculates the appropriate price based on the description of the listed product and price data for similar products in the market. For example, if an iPhone 12 is listed, the server analyzes market price data, calculates a recommended price of 70,000 yen, and displays this on the seller's device.

[0258] Improved matching accuracy

[0259] The server collects user feedback and updates the matching algorithm based on it, improving the accuracy of matching over time. For example, when a user provides feedback such as "This price is reasonable" or "I think it's cheaper," that data is stored on the server and used for the next price suggestion and product recommendation.

[0260] Predicting potential needs and recommending products

[0261] The server predicts the user's potential needs based on past user behavior data and market trend data, and generates optimal product listings. For example, if a user frequently searches and browses for "cameras," it will recommend related camera accessories and new camera models.

[0262] Negotiation support function

[0263] The server receives negotiation requests from potential buyers and generates appropriate negotiation proposals based on past negotiation data and market price data. For example, if a potential buyer requests a slight price reduction, the server calculates the amount of price reduction based on past data and notifies the potential buyer and seller.

[0264] Generate prompt statement

[0265] The generative AI model learns user behavior data and generates prompts. For example, if a user frequently searches for cameras, it generates a prompt such as, "If you're looking for a new camera, how about this model?" Specific examples of prompts that can be provided include:

[0266] plain

[0267] If you're looking for a new camera, how about this model?

[0268] Recommended Products: [Product List]

[0269] As a result, recommendations, price calculations, and negotiation support can be efficiently performed based on user behavior data, improving the user experience.

[0270] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0271] Step 1:

[0272] When a user searches for a product, the device sends a search query to the server. The input is the user's search term (e.g., "vintage watch"). The server receives this search query and stores it in a database. This updates the user's recent search history.

[0273] Step 2:

[0274] The server collects and analyzes the user's search history, browsing history, and purchase history. The input is the user's behavioral data saved from previous visits. The server analyzes this data to extract the user's preferences and behavioral patterns. The analysis results reveal the user's tastes and purchasing tendencies.

[0275] Step 3:

[0276] The price of the listed item is analyzed and a fair price is calculated. Inputs include the product description, photos, and market price data for similar items. The server analyzes the market price data, calculates a fair price, and displays it on the seller's device. For example, for an iPhone 12 listing, a suggested price of 70,000 yen is calculated.

[0277] Step 4:

[0278] Collecting user feedback. The input is the feedback provided by the user (e.g., "This price is reasonable"). The server receives this feedback and stores it in a database. This feedback is then used for the next algorithm update.

[0279] Step 5:

[0280] The server updates the matching algorithm based on the feedback data. The input is the collected feedback data. The server uses this data to adjust the parameters of the algorithm and improve the matching accuracy.

[0281] Step 6:

[0282] The server analyzes the user's past behavioral data and market trend data to predict the user's potential needs. The inputs include the user's search history, browsing history, purchase history, and market trend data. The server analyzes this data and generates the optimal product list for the user.

[0283] Step 7:

[0284] The server generates a product list based on the predicted needs and notifies the user. The input is the result of predicting potential needs. The server generates a product list based on this result and notifies the device. For example, if cameras are frequently searched for, related camera accessories will be recommended.

[0285] Step 8:

[0286] Receives a negotiation request from a potential buyer. The input is the buyer's request (e.g., "I would like a lower price"). The server receives this request and stores it in a database.

[0287] Step 9:

[0288] The server generates an appropriate negotiation proposal based on past negotiation data and market price data. The inputs are a negotiation request, past negotiation data, and current market price data. The server calculates an appropriate price reduction amount based on this data and generates a proposal.

[0289] Step 10:

[0290] The server notifies the buyer and seller of the generated negotiation proposal. The input is the generated negotiation proposal. The server notifies the terminal of this proposal and progresses the negotiation. This allows the transaction to proceed smoothly and improves user satisfaction.

[0291] The above are the specific processing steps in the system of the present invention. These steps enable efficient product recommendations, price calculations, and negotiation support based on user behavior data.

[0292] 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.

[0293] The system of the present invention has functions for collecting and analyzing users' search history, browsing history, and purchase history, analyzing the prices of listed items to calculate appropriate prices, collecting user feedback to update the matching algorithm, predicting users' potential needs and recommending items, and generating negotiation proposals based on negotiation requests to support negotiations.In addition, the system is equipped with an emotion engine that recognizes users' emotions and uses the emotion data to further personalize the user experience.

[0294] User data collection and analysis

[0295] The server collects and analyzes data such as the user's search terms, browsing history, and past purchase history, as well as emotional data. This data is used to understand not only the user's preferences, purchasing trends, and price perception, but also changes in their emotions.

[0296] When a user searches, the device sends emotional data along with the search terms to the server in real time. For example, when a user searches for "vintage watches," the emotion engine recognizes "interest" from facial expressions and voice at the time and sends this information to the server. Based on this data, the server generates and displays more accurate product information.

[0297] Smart Pricing

[0298] The server analyzes the price data of similar products on the market based on the photos and descriptions of the listed items, as well as emotional data, to calculate an appropriate price. For example, if a seller is listing an iPhone 12, the server analyzes the market price data of other similar products and the seller's emotional state, and suggests a price of 70,000 yen. If the seller is having difficulty setting a price, the emotion engine will recognize their anxiety, and the server can send them price advice or a message of support.

[0299] Improved matching accuracy

[0300] The server collects user feedback and emotional data and updates the matching algorithm based on that information. For example, when a user provides feedback such as "This price is appropriate" or "I think it could be cheaper," the emotional engine recognizes their satisfaction or dissatisfaction at that time and sends that data to the server. The server then uses this data to improve the accuracy of the next price suggestion and matching.

[0301] Predicting potential needs and recommending products

[0302] The server predicts the user's potential needs based on the user's past behavioral data, emotional data, and market trend data. It then generates and notifies the user of a list of optimal products. For example, if a user frequently searches for "camera" and the emotion engine recognizes the user's heightened emotions, the server will recommend related camera accessories and new camera models.

[0303] The user's device will notify and display this recommended product list, allowing the user to find products that match their potential needs based on their emotions.

[0304] Negotiation support function

[0305] The server receives emotion data along with a negotiation request from a prospective buyer, analyzes it, and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a prospective buyer requests a slight price reduction and the emotion is recognized as a strong desire, the server generates a corresponding negotiation proposal and notifies the prospective buyer and the seller.

[0306] The devices of the buyer and seller display negotiation proposals in real time, allowing each party to negotiate based on their emotions according to the situation. As a result, the transaction proceeds smoothly and it becomes easier to reach terms that satisfy the user emotionally.

[0307] By integrating these functions, the system of this invention can provide personalized product suggestions and pricing according to the user's needs, and support negotiations and transactions with consideration for emotions, which is expected to revitalize the entire reuse market.

[0308] The processing flow will be explained below.

[0309] User data collection and analysis

[0310] Step 1:

[0311] A user opens the Reuse Market app on their device, types "vintage watches" into the search bar, and presses the search button.

[0312] Step 2:

[0313] The device sends the entered search words and "interest" emotion data analyzed by the emotion engine from the user's facial expressions and voice to the server.

[0314] Step 3:

[0315] The server stores the received search terms and emotion data in a database and compares them with past search history, purchase history, and browsing history.

[0316] Step 4:

[0317] The server analyzes the user's interests, purchasing trends, and emotional changes based on the stored data, and generates and displays appropriate product information.

[0318] Smart Pricing

[0319] Step 1:

[0320] To list an iPhone 12, a seller enters product photos and descriptions from their device and presses the list button.

[0321] Step 2:

[0322] The device sends product information and "anxiety" emotion data analyzed by an emotion engine from the seller's facial expressions and voice to the server.

[0323] Step 3:

[0324] The server analyzes market price data for similar products based on the transmitted product information and emotion data.

[0325] Step 4:

[0326] The server calculates the optimal price as a result of the analysis and generates price advice and supportive messages according to the seller's emotional state.

[0327] Step 5:

[0328] The server transmits the recommended price and a support message to the seller's terminal, and the terminal displays the price and message to the seller.

[0329] Improved matching accuracy

[0330] Step 1:

[0331] The user provides feedback such as "This price is appropriate" or "It could be cheaper," and the emotion engine simultaneously analyzes the user's emotions, such as "satisfaction" or "dissatisfaction."

[0332] Step 2:

[0333] The device sends user feedback and emotion data to the server.

[0334] Step 3:

[0335] The server stores the received feedback and emotion data and adds it to a database to be analyzed.

[0336] Step 4:

[0337] The server uses this new data to update its matching algorithm and improve the accuracy of its next price suggestions and recommended products.

[0338] Predicting potential needs and recommending products

[0339] Step 1:

[0340] The server analyzes the user's past behavioral data, stored emotion data, and market trend data to predict the user's potential needs.

[0341] Step 2:

[0342] The server generates a list of products that are best suited to the user based on predicted needs and sentiment data.

[0343] Step 3:

[0344] The server transmits the generated recommended product list to the user's terminal, and the terminal notifies the user of an emotion-inducing message related to the recommended products.

[0345] Negotiation support function

[0346] Step 1:

[0347] A prospective purchaser sends a price reduction request for the product.

[0348] Step 2:

[0349] The device sends this request along with "strong desire" emotion data analyzed by the emotion engine from the prospective buyer's facial expressions and tone of voice to the server.

[0350] Step 3:

[0351] The server analyzes the request and sentiment data and generates appropriate negotiation proposals based on past negotiation data and market price data.

[0352] Step 4:

[0353] The server sends the generated negotiation proposal and a message according to the emotion to the prospective buyer and the seller.

[0354] Step 5:

[0355] The devices of the prospective buyer and seller display negotiation proposals and messages in real time, and each party proceeds with the negotiations with emotions appropriate to the situation.

[0356] Step 6:

[0357] The user (seller) sets a new price based on the proposal, and the transaction is completed when the potential buyer agrees to it.

[0358] These steps allow the system of the present invention to optimize the user's searching, listing, and negotiating experience based on emotions.

[0359] Example 2

[0360] 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."

[0361] Conventional e-commerce systems use users' search and purchase histories to suggest products and set prices, but this often does not adequately address users' emotions and needs. Furthermore, pricing and negotiation support sometimes ignore the emotions of sellers and potential buyers, resulting in lower user satisfaction. To address these issues, a more personalized system that incorporates user emotional data is needed, offering higher levels of satisfaction.

[0362] 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 means for collecting and analyzing the user's search history, browsing history, and purchase history, means for analyzing the price of the listed product based on the price data of other similar products to calculate the appropriate price, and means for collecting and analyzing the user's emotional data. This allows the user's emotional data to be analyzed together with their past behavioral data, enabling more accurate product proposals, pricing, and negotiation support.

[0363] "User search history" is a record of the user's search behavior within the system.

[0364] "Browse history" is a record of the products a user has viewed within the system.

[0365] "Purchase history" is a record of products a user has previously purchased within the system.

[0366] A "fair price" is a fair and reasonable price calculated based on market data and price data for similar products.

[0367] "Emotional data" refers to emotional information analyzed from the user's facial expressions, voice, etc.

[0368] "Feedback" refers to users' evaluations and opinions of the products and services they provide.

[0369] A "matching algorithm" is a calculation method for selecting products and services that match a user's requirements and preferences.

[0370] "Latent needs" are needs or desires that are not explicitly expressed by the user but can be predicted from their behavioral and emotional data.

[0371] "Product List" means a list of products selected for offering to users.

[0372] A "negotiation request" is a request by a prospective purchaser to change the product price.

[0373] A "negotiation proposal" is a proposal for price and terms of trade generated by the server in response to a negotiation request.

[0374] The system according to the present invention is an advanced system that collects user search history, browsing history, purchase history, and emotional data, and uses this data to propose products, set prices, and assist in negotiations. The following describes how to specifically implement this system.

[0375] First, to generate the program for this system, the following main hardware and software are required: Hardware includes a server and user devices (PCs, smartphones, tablets, etc.), while software includes an emotion recognition engine (e.g., Microsoft® Emotion API, Google® Cloud Speech-to-Text API), a database (e.g., MongoDB, PostgreSQL), a machine learning algorithm (e.g., TENSORFLOW®, PyTorch), and natural language processing technology (e.g., SpaCy).

[0376] The server integrates and analyzes the user's search history, browsing history, and purchase history, as well as emotional data collected from facial expressions and voice. This allows the system to understand not only the user's preferences and purchasing trends, but also changes in their emotions. For example, if a user searches for "vintage watches" and their facial expression indicates "interest," the server receives and analyzes this data in real time.

[0377] Based on the analysis results, the server searches the product database, generates a list of products that are best suited to the user, and notifies the device. This allows users to quickly find the products they are interested in. For example, products related to "vintage watches" are displayed preferentially, and information such as price, quality rating, and seller rating is provided.

[0378] The server analyzes the price of a listed item based on the price data of other similar items and the seller's emotional data to calculate an appropriate price. For example, when a seller tries to list an iPhone 12, the server analyzes the market price data of other similar items and suggests a recommended price of 70,000 yen. If the seller is feeling anxious, the emotion recognition engine will recognize this and the server can send an encouraging message.

[0379] The server collects user feedback and emotional data and updates the matching algorithm based on this. For example, if a user provides feedback such as "This price is reasonable" or "I think it could be cheaper," and the user's emotional response is satisfied, the server will improve the algorithm for the next price and product suggestion.

[0380] Furthermore, the server can analyze the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. For example, if the user frequently searches for "camera" and shows high emotional responses, the server can recommend camera accessories and new camera models based on that information. These recommended product lists are then sent to the user's device.

[0381] Finally, the server analyzes the buyer's negotiation request and emotional data, and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a buyer requests a slight price reduction and the emotion is recognized as a strong desire, the server generates a corresponding negotiation proposal and notifies the buyer and seller. Displaying the negotiation proposal in real time makes it easier to reach a deal that satisfies both parties.

[0382] As a concrete example, the generative AI model can be used with the following prompt sentence:

[0383] Example prompt:

[0384] "If a user searches for vintage watches and the emotion engine recognizes their current interest, how would the server generate and display product information?"

[0385] As a result, the system of the present invention can make product proposals and set prices personalized to the user's needs, and further support negotiations by taking emotions into consideration, thereby achieving more satisfying transactions.

[0386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0387] Step 1:

[0388] A user enters a search term, such as "vintage watches," into the device. The input includes the search term (e.g., "vintage watches") and facial and vocal emotion data collected using the device's camera and microphone. The device's software uses an emotion recognition engine (e.g., Microsoft Emotion API, Google Cloud Speech-to-Text API) to convert the facial and vocal data into emotion data such as "interest." The output is a combination of the search term and the emotion data.

[0389] Step 2:

[0390] The terminal transmits the user's search words and collected emotion data to the server in real time using SSL / TLS encryption protocol. The input is the search words and emotion data, and the output after transmission is the data safely reaching the server.

[0391] Step 3:

[0392] The server searches a database based on the received search term and emotion data. The input is a search term (e.g., "vintage watch") and emotion data (e.g., "interest"). The server searches a large product database (e.g., MongoDB) to obtain information on related products. Specifically, it uses machine learning algorithms (e.g., TensorFlow, PyTorch) to search for and prioritize related products. The output is a list of optimal products.

[0393] Step 4:

[0394] The server notifies the terminal of the generated product list. The input is the optimal product list, and the output is to display it on the target user's terminal. Specifically, the server encodes the product list in JSON format and sends it to the terminal.

[0395] Step 5:

[0396] The user browses the presented product list and clicks on a product page. The input is the ID of the individual product selected from the product list. The terminal requests detailed information about the selected product from the server and displays the product detail page to the user as output. Specifically, the terminal captures the user's click event and sends a detailed information request to the server.

[0397] Step 6:

[0398] When a seller attempts to list a new item, the server calculates the appropriate price based on product information and emotional data. The input is product information (e.g., "iPhone 12") and the seller's emotional data (e.g., "anxiety"). The server analyzes market data and price data for similar products to calculate the appropriate price that will give the seller peace of mind. The output is a recommended price (e.g., "70,000 yen"). Specific operations involve using a machine learning model that takes into account emotional data along with statistical analysis.

[0399] Step 7:

[0400] The user provides feedback on the price and product evaluation. The input is the user's feedback (e.g., "This price is appropriate") and facial expression data at that time (e.g., "Satisfied"). The device transmits the feedback and emotional data to the server in real time, and the output is the data received by the server. Specifically, the device uses a feedback form and an emotion-recognition camera.

[0401] Step 8:

[0402] The server updates the matching algorithm based on the received feedback and emotion data. The input is the feedback and emotion data. Using a data analysis engine, the algorithm for the next price or product suggestion is adjusted, and the output is the updated algorithm. Specifically, the feedback data is fed into a machine learning model to optimize the algorithm parameters.

[0403] Step 9:

[0404] The server analyzes the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. The input is past behavioral data and emotional data. A machine learning algorithm is used to predict the user's purchasing intentions, and the output is a product list based on the predicted needs. Specific operations include time series analysis and clustering techniques.

[0405] Step 10:

[0406] The server generates an appropriate negotiation proposal based on the negotiation request and emotional data from the prospective buyer. The input is the prospective buyer's request (e.g., "I would like to ask for a smaller price reduction") and emotional data (e.g., "I strongly desire it"). The server analyzes past negotiation data and market price data, generates an appropriate negotiation proposal, and notifies the prospective buyer and seller as output. In concrete terms, the server integrates and uses an emotion recognition algorithm and a negotiation support algorithm.

[0407] (Application example 2)

[0408] 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."

[0409] Modern online shopping sites are required to make more personalized product recommendations and set fair prices by effectively utilizing not only users' search and purchase histories but also their emotional data. Generating negotiation proposals based on users' emotional state and improving the success rate of negotiations is also an important challenge. However, conventional systems have had difficulty fully integrating and effectively utilizing these functions.

[0410] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history; means for analyzing the price of a listed product based on price data of other similar products to calculate an appropriate price; means for collecting user feedback and updating a matching algorithm based on the feedback; means for analyzing the user's past behavioral data and market trend data to predict the user's potential needs; means for generating a product list based on the predicted needs and notifying the user of the list; means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices; means for supporting negotiations based on requests and proposals submitted by the user; means for analyzing the user's emotional data and making personalized product proposals and pricing based on the analyzed data; and means for making appropriate negotiation proposals when providing negotiation support based on the user's current emotional state. This enables personalized product proposals, pricing, and negotiation support that take the user's emotions into consideration.

[0411] "User search history" is a record of keywords and phrases that a user has searched for on the Internet.

[0412] "Browsing history" is a record of the pages a user has visited on a website or application.

[0413] "Purchase history" is a record of the products and services a user has actually purchased.

[0414] "Price data of similar products" refers to price information of the same or similar products traded in the market.

[0415] "Feedback" refers to opinions and ratings provided by users, which is information used to improve and adjust the system.

[0416] A "matching algorithm" is a calculation method for suggesting optimal products and services based on a user's preferences and needs.

[0417] "Past behavioral data" refers to historical information about searches, browsing, purchases, etc. that a user has conducted.

[0418] "Market trend data" refers to information about overall market trends and user behavior trends.

[0419] "Latent needs" are requests for products or services that users are not yet clearly aware of but may need in the future.

[0420] A "product list" is a list of multiple products or services that the system suggests to the user.

[0421] A "negotiation request" is a request for negotiations sent by a prospective buyer to a seller regarding price and conditions.

[0422] A "negotiation proposal" is a proposal regarding price and other terms generated in response to a negotiation request.

[0423] "Emotion data" is information about the user's emotional state that can be inferred from facial expressions, voice, etc.

[0424] "Personalization" refers to providing customized suggestions and settings based on individual user preferences and behavior.

[0425] The present invention provides a system that collects users' search history, browsing history, purchase history, and emotional data, and uses this data to make personalized product proposals and set prices, as well as provide negotiation support.

[0426] User data collection and analysis

[0427] The server collects information on the keywords the user has searched for, the pages they have viewed, and the products they have purchased in the past. In addition, the emotion engine analyzes emotional data from the user's facial expressions and voice, and collects this data as well. The device sends data to the server in real time when the user performs a search. For example, if a user searches for "vintage watches," the emotion engine recognizes "interests" from their facial expressions and voice at the time and sends this data to the server. The server uses this data to analyze the user's preferences and purchasing trends, and generates appropriate product information to display to the user.

[0428] Smart Pricing

[0429] The server analyzes the price data of similar products on the market based on the photos and descriptions of the listed items, as well as emotional data, and calculates an appropriate price. For example, if a seller is listing a smartphone, the server analyzes the market price data of other similar products and the seller's emotional state, and suggests a price of 50,000 yen. If the seller is having difficulty setting a price, the emotion engine will recognize their anxiety, and the server can send them price advice or a message of support.

[0430] Improved matching accuracy

[0431] The server collects user feedback and emotional data and updates the matching algorithm based on that information. For example, while a user provides feedback such as "This price is reasonable" or "I think it could be cheaper," the emotional engine recognizes their satisfaction or dissatisfaction at that time. Based on this data, the server uses it to improve the accuracy of the next price suggestion and matching.

[0432] Predicting potential needs and recommending products

[0433] The server predicts a user's potential needs based on the user's past behavioral data, emotional data, and market trend data. For example, if a user frequently searches for "camera" and the emotion engine recognizes the user's heightened emotions, the server will recommend related camera accessories and new camera models. The user's device will notify and display a list of these recommended products, allowing the user to easily find products that meet their potential needs.

[0434] Negotiation support function

[0435] The server receives and analyzes emotional data along with a negotiation request from a potential buyer. For example, if a potential buyer requests a slight price reduction, and the server recognizes this emotion as a strong desire, it generates a corresponding negotiation proposal and notifies the potential buyer and seller in real time. The seller's device displays a negotiation proposal that takes into account the potential buyer's emotional state, allowing negotiations to proceed based on emotions appropriate to each situation. This allows for smoother transactions and makes it easier to reach transaction terms that satisfy the user emotionally.

[0436] By integrating the above functions, the system of the present invention can provide personalized product suggestions and pricing based on user needs, and emotionally support negotiations and transactions, which is expected to revitalize the entire online market.

[0437] Prompt Sentence Examples

[0438] Based on the user's search history, use the search term "vintage watches" and its sentiment data to perform the following tasks:

[0439] Calculating fair prices from market data

[0440] Recommend related products

[0441] Generate negotiation support proposals

[0442] Also, optimize your matching algorithm based on feedback.

[0443] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0444] Step 1:

[0445] When a user searches, the device sends search terms along with emotional data captured from facial expressions and voice to the server in real time. The search terms and emotional data are used as inputs, and the data is then processed to track the user's interests. As an output, the server stores the information in a database for analyzing the user's preferences and interests.

[0446] Step 2:

[0447] The server collects and analyzes users' search, browsing, and purchase histories along with emotional data. Using this history and emotional data as input, data calculations are performed to identify specific purchasing trends and patterns. As output, personalized product information is generated based on the user's purchasing trends and preferences.

[0448] Step 3:

[0449] When setting the price of a newly listed item, the server analyzes the price data of similar items on the market and the seller's sentiment data. Using the product details, market data, and sentiment data as input, the server performs data calculations to calculate an appropriate price. As an output, a suggested selling price is displayed on the product page and notified to the seller.

[0450] Step 4:

[0451] The server collects user feedback and sentiment data and uses it to update the matching algorithm. Using the feedback and sentiment data as input, it performs data calculations to adjust and improve the algorithm. The output is an improved matching algorithm, which is reflected in future searches and recommendations.

[0452] Step 5:

[0453] The server analyzes the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. Using the behavioral data, emotional data, and trend data as input, data calculations are performed to identify potential needs. As output, a product list based on the predicted potential needs is generated and notified to the user.

[0454] Step 6:

[0455] When a negotiation request is received from a potential buyer, the server analyzes the emotion data and generates an appropriate negotiation proposal based on past negotiation data and market price data. Using the negotiation request, emotion data, past negotiation data, and price data as input, data calculations are performed to propose optimal negotiation terms. As an output, the generated negotiation proposal is notified to the potential buyer and seller in real time.

[0456] Step 7:

[0457] The user's device displays the personalized product list and negotiation proposals sent from the server to the user, allowing the user to proceed with the purchase or negotiation based on the presented information. Using the data sent from the server as input, the data is processed to display appropriately to the user. As output, an interface is generated for the user to view or operate.

[0458] 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.

[0459] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0460] 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.

[0461] [Second embodiment]

[0462] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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."

[0474] The system of the present invention has functions for collecting users' search history, browsing history, and purchase history, for analyzing the prices of listed products and calculating appropriate prices, for collecting feedback from users and updating the matching algorithm, for predicting users' potential needs and recommending products, and for generating negotiation proposals based on negotiation requests and supporting negotiations.

[0475] User data collection and analysis

[0476] The server collects and analyzes data such as user search terms, browsing history, and past purchase history, which is used to understand user preferences, purchasing trends, and price sensitivity.

[0477] When a user searches, the device sends the search terms to the server in real time, allowing the server to analyze the latest data. For example, if a user searches for "vintage watches," their search history is sent to the server, and related products are displayed based on the analysis results.

[0478] Smart Pricing

[0479] The server analyzes the price data of similar products on the market based on the photos and description of the listed product and calculates an appropriate price. For example, if a seller wants to list an iPhone 12, the server analyzes the market price data of other similar products, calculates a recommended price of 70,000 yen, and displays it on the seller's device. The seller can use this price as a reference to set their listing price.

[0480] Improved matching accuracy

[0481] The server collects feedback from users and updates the matching algorithm based on that feedback, improving the accuracy of matching over time. For example, when a user provides feedback such as "This price is reasonable" or "I think it's cheaper," that data is stored on the server and used to suggest prices and improve matching accuracy the next time.

[0482] Predicting potential needs and recommending products

[0483] The server predicts users' potential needs based on their past behavioral data and market trend data. It then generates and notifies users of a list of products that best suit their needs. For example, if a user frequently searches for and browses "cameras," the server will recommend related camera accessories and new camera models.

[0484] The user's device will notify and display this list of recommended products, making it easier for the user to find products that meet their potential needs.

[0485] Negotiation support function

[0486] The server receives a negotiation request from a potential buyer and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a potential buyer requests a slight price reduction, the server calculates the appropriate price reduction amount based on past data and notifies the potential buyer and seller of the price reduction proposal.

[0487] The buyer and seller's devices can display negotiation proposals in real time and proceed with the negotiations based on them, which results in a smoother transaction and makes it easier to reach terms that satisfy both users.

[0488] The above is a specific embodiment of the system based on the present invention. By using this system, users can efficiently search for, purchase, and negotiate products, which is expected to revitalize the entire reuse market.

[0489] The processing flow will be explained below.

[0490] User data collection and analysis

[0491] Step 1:

[0492] A user opens the Reuse Market app on their device, types "vintage watches" into the search bar, and presses the search button.

[0493] Step 2:

[0494] The terminal sends the entered search words to the server.

[0495] Step 3:

[0496] The server stores the received search terms in a database and compares them with past search and purchase history.

[0497] Step 4:

[0498] The server analyzes the user's interests and purchasing trends based on the stored data, and generates appropriate information based on the results.

[0499] Smart Pricing

[0500] Step 1:

[0501] To list an iPhone 12, a seller enters product photos and descriptions from their device and presses the list button.

[0502] Step 2:

[0503] The terminal transmits the product information to the server.

[0504] Step 3:

[0505] The server analyzes the market price data of similar products based on the transmitted product information.

[0506] Step 4:

[0507] The server calculates the optimal price as a result of the analysis and generates a recommended price.

[0508] Step 5:

[0509] The server sends the recommended price to the seller's terminal, which displays the price to the seller.

[0510] Improved matching accuracy

[0511] Step 1:

[0512] The user provides feedback such as "This price is good" or "It could be a little cheaper."

[0513] Step 2:

[0514] The device sends the user's feedback to the server.

[0515] Step 3:

[0516] The server stores the received feedback and adds it to a database to be analyzed.

[0517] Step 4:

[0518] The server updates its matching algorithm based on the new feedback, improving accuracy.

[0519] Predicting potential needs and recommending products

[0520] Step 1:

[0521] The server compares the user's past behavioral data (search history, browsing history, purchase history) with market trend data to predict the user's potential needs.

[0522] Step 2:

[0523] The server generates a list of products that best suit the user based on their predicted needs.

[0524] Step 3:

[0525] The server transmits the generated recommended product list to the user's terminal, and the terminal notifies the user of the recommended products.

[0526] Negotiation support function

[0527] Step 1:

[0528] A prospective purchaser sends a price reduction request for the product.

[0529] Step 2:

[0530] The terminal sends this request to the server.

[0531] Step 3:

[0532] The server analyzes the request and generates an appropriate negotiation proposal based on past negotiation data and market prices.

[0533] Step 4:

[0534] The server sends the generated negotiation proposal to the prospective buyer and the seller.

[0535] Step 5:

[0536] The buyer and seller's terminals display negotiation proposals in real time and confirm them with each other.

[0537] Step 6:

[0538] The user (seller) sets a new price based on the proposal, and the transaction is completed when the potential buyer agrees to it.

[0539] Example 1

[0540] 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."

[0541] In current online marketplaces, many systems that effectively utilize users' search and purchase histories to suggest products face challenges in terms of matching accuracy and price accuracy. Furthermore, they lack the ability to accurately predict users' potential needs and support functions to smoothly advance the negotiation process. These challenges must be addressed to increase user satisfaction.

[0542] 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.

[0543] In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history, means for transmitting search terms from the user's terminal in real time, means for analyzing price data of similar products in the market based on information about the listed product and calculating an appropriate price, means for collecting feedback from the user and updating a matching algorithm based on the feedback, means for analyzing past user behavior data and market trend data and predicting the user's potential needs, means for generating a product list based on the predicted needs and notifying the user of the list, means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, and means for supporting negotiations based on requests and proposals transmitted by the user. This enables users to efficiently search for, purchase, and negotiate on products.

[0544] "User" refers to a person who uses the System to search for, view, purchase, or list products.

[0545] "Device" refers to electronic devices such as computers, smartphones, and tablets used by users.

[0546] "Server" refers to a computer system that receives, analyzes, stores, and processes data submitted by users.

[0547] "Search History" refers to a record of keywords and phrases that a User has previously searched for on the System.

[0548] "Browse history" refers to the record of product pages that a user has viewed on the System.

[0549] "Purchase History" refers to the record of products that a User has previously purchased through this System.

[0550] "Feedback" refers to data such as opinions, ratings, and impressions provided by users.

[0551] A "matching algorithm" refers to a calculation method that analyzes user data and product data to suggest the most suitable product to the user.

[0552] "Fair price" refers to the price that is considered appropriate for the product, calculated by the server by analyzing market data.

[0553] "Latent needs" refer to the desires and needs that users may have that are not explicitly stated by users but that can be inferred from past behavioral data and market trend data.

[0554] "Product list" refers to a list of multiple products that the server generates based on the user's potential needs and notifies the user.

[0555] A "negotiation request" refers to a request from a prospective buyer to a seller to change the price or terms of the transaction.

[0556] "Negotiation proposal" refers to the negotiation conditions that the server generates based on past negotiation data and market price data and notifies the prospective buyer and seller.

[0557] The system of the present invention uses multiple hardware and software components to provide functions for collecting and analyzing users' search history, browsing history, and purchase history, analyzing the prices of listed items to calculate appropriate prices, collecting feedback from users to update matching algorithms, predicting users' potential needs and recommending items, and generating negotiation proposals based on negotiation requests to support negotiations.

[0558] Hardware used

[0559] 1. Device: The computer, smartphone, tablet, etc. used by the user.

[0560] 2. Server: A high-performance computer system that collects, analyzes, stores, and processes data.

[0561] Software used

[0562] 1. Data collection program: Software that runs on the device and transmits user operations to a server in real time.

[0563] 2. Data analysis program: An algorithm that runs on the server and analyzes the collected data.

[0564] 3. Feedback collection program: Software that receives and analyzes feedback from users.

[0565] 4. Price analysis program: An algorithm that runs on the server and calculates the fair price based on market data.

[0566] 5. Matching algorithm: A calculation method for suggesting optimal products based on user data.

[0567] 6. Product recommendation generator: Software that predicts users' potential needs and generates product lists.

[0568] 7. Negotiation Support Program: Software that receives negotiation requests, generates appropriate negotiation proposals, and sends them to the user.

[0569] Example of operation

[0570] When a user searches for "vintage watches," the user's device sends the search term to the server in real time. The server collects data including the user's search history, past browsing history, and purchase history, and performs analysis related to the search term "vintage watches." As a result, the server generates a list of related products and displays it on the user's device.

[0571] When a seller tries to list an iPhone 12, the product information entered on the seller's device is sent to the server. The server analyzes the product's photos and description and retrieves pricing data for similar products from other online marketplaces. It then calculates the optimal price of 70,000 yen and provides it to the seller's device. The seller can use this price as a reference to set the selling price of their own product.

[0572] When a user provides feedback, such as "this price is reasonable" or "it should be cheaper," that feedback is sent from the user's device to the server and stored. The server then incorporates this feedback into the next price suggestion and matching accuracy improvement, thereby improving accuracy.

[0573] If a user frequently searches and browses for "camera," the server will use that data to recommend camera-related accessories and new camera models, and these recommendations will be displayed on the user's device and the user will be notified.

[0574] When a prospective buyer sends a negotiation request saying, "I would like to ask for a further price reduction," the server generates an appropriate price reduction proposal based on past negotiation data and market price data, and sends it to the terminals of the prospective buyer and the seller for presentation.

[0575] Prompt Sentence Examples

[0576] "Based on the user's past search history and market trends, predict his potential needs and generate a list of relevant products."

[0577] "Please calculate a fair price based on the description of the listed item and market price data."

[0578] "Update your matching algorithm based on user feedback data."

[0579] As a result, the system of the present invention provides users with optimal product search, purchasing, and negotiation, and is expected to revitalize the entire reuse market.

[0580] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0581] Step 1: Collect user data

[0582] 1.1. Submitting search terms

[0583] A user enters a search term into the device's search bar.

[0584] The device sends the entered search term (e.g., "vintage watch") to the server in real time.

[0585] Input: User's search term.

[0586] Data processing: Formalizing and structuring search terms.

[0587] Output: Search word data sent to the server.

[0588] 1.2. Collection of browsing and purchase history

[0589] The server collects data on the product pages the user has previously viewed and the products they have purchased.

[0590] Input: User's browsing history, purchase history.

[0591] Data processing: Organizing data based on time series.

[0592] Output: Structured browsing and purchase history data.

[0593] Step 2: Analyze the data

[0594] 2.1. Analysis of user trends

[0595] The server analyzes the collected search terms, browsing history, and purchase history to identify the user's preferences and purchasing trends.

[0596] Input: Search terms, browsing history, and purchase history data.

[0597] Data processing: Data analysis and pattern recognition.

[0598] Output: Analysis of user preferences and purchasing trends.

[0599] 2.2. Display of related products

[0600] The server generates a list of related products based on the analysis results and notifies the user's device.

[0601] Input: Analysis of user preferences and purchasing trends.

[0602] Data processing: Generate a list of related products.

[0603] Output: Related product list displayed on the device.

[0604] Step 3: Smart Pricing

[0605] 3.1. Product data collection

[0606] The user (seller) enters product information (photo and description) into the terminal and sends it to the server.

[0607] Input: Product information (photo, description).

[0608] Data Processing: Receiving product information and converting it into data for analysis.

[0609] Output: Structured product data.

[0610] 3.2. Market price data collection

[0611] The server collects price data for other similar products in the market.

[0612] Input: Product information, matching market data.

[0613] Data processing: market data collection and matching.

[0614] Output: Price data for similar products.

[0615] 3.3. Calculating the fair price

[0616] The server calculates the fair price of the auction item based on the market price data.

[0617] Input: Price data for similar products.

[0618] Data processing: Calculating fair prices.

[0619] Output: Reasonably priced and affordable.

[0620] 3.4. Recommended Price

[0621] The server notifies the seller's terminal of the calculated fair price.

[0622] Enter: Fair Price.

[0623] Data processing: Formalization of pricing data.

[0624] Output: The suggested price displayed on the seller's device.

[0625] Step 4: Gather feedback and update the algorithm

[0626] 4.1. Sending Feedback

[0627] Users enter feedback about prices and product ratings into the device.

[0628] Input: Feedback content.

[0629] Data processing: Formalization of feedback data.

[0630] Output: Feedback data sent to the server.

[0631] 4.2. Gathering Feedback for Algorithm Updates

[0632] The server accumulates and stores the collected feedback data.

[0633] Input: Feedback data.

[0634] Data processing: Accumulation and analysis of feedback data.

[0635] Output: The updated matching algorithm.

[0636] Step 5: Anticipating potential needs and recommending products

[0637] 5.1. Analysis of behavioral data

[0638] The server analyzes users' past behavioral data and market trend data.

[0639] Inputs: Behavioral data, market trend data.

[0640] Data processing: Data analysis and pattern recognition.

[0641] Output: Prediction of potential user needs.

[0642] 5.2. Creating a Product List

[0643] The server generates a list of related products based on the predicted user needs and notifies the user's terminal.

[0644] Input: Predicted potential needs.

[0645] Data processing: Product list generation.

[0646] Output: A list of recommended products displayed on the device.

[0647] Step 6: Negotiation support

[0648] 6.1. Sending a Negotiation Request

[0649] The prospective buyer sends a negotiation request from the terminal.

[0650] Input: Negotiation request.

[0651] Data processing: Request formatting and storage.

[0652] Output: The negotiation request sent to the server.

[0653] 6.2. Generating Negotiation Proposals

[0654] The server generates appropriate negotiation proposals based on past negotiation data and market data.

[0655] Inputs: Negotiation request, historical negotiation data, market data.

[0656] Data processing: Generating negotiation proposals.

[0657] Output: Negotiation proposal sent to the buyer's and seller's devices.

[0658] This will enable each function of the system to be realized, enabling users to efficiently search for, purchase, and negotiate products.

[0659] (Application example 1)

[0660] 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."

[0661] Traditional online shopping sites typically recommend products based on users' search and purchase histories, but this method is often inaccurate. In particular, it is difficult to accurately predict and recommend products that users will be interested in, which can result in poor user experience. Furthermore, there is a lack of functionality to automatically generate appropriate negotiation proposals based on negotiation requests and facilitate smooth negotiations between users. This creates the challenge of finding transaction terms that satisfy users.

[0662] 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.

[0663] In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history, means for analyzing the price of a listed item based on price data of other similar items and calculating an appropriate price, means for collecting user feedback and updating a matching algorithm based on the feedback, means for analyzing the user's past behavioral data and market trend data and predicting the user's potential needs, means for generating a product list based on the predicted needs and notifying the user of the list, means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, means for supporting negotiations based on requests and proposals submitted by the user, means for providing optimal prices and product recommendations based on the user's behavioral data, and means for generating prompt messages using a generative AI model that has learned the user's purchasing tendencies. This enables efficient product recommendations, calculation of appropriate prices, and negotiation support based on the user's behavioral data, thereby significantly improving the user experience.

[0664] "Search history" is a record of a user's past search queries within websites and applications.

[0665] "Browsing history" is a record of data about web pages and product pages that a user has viewed in the past.

[0666] "Purchase history" is a record of data on products purchased by a user in the past.

[0667] "Analysis" is the process of extracting meaning from collected data using statistical or machine learning algorithms.

[0668] "Price data for similar products" refers to price information for products of the same type or with similar characteristics that exist in the market.

[0669] A "fair price" is a product price that is determined statistically or algorithmically to be fair and appropriate to the market.

[0670] "Feedback" refers to opinions and evaluation data provided by users.

[0671] A "matching algorithm" is a calculation procedure that recommends optimal products and services based on user data.

[0672] "Past behavioral data" refers to the user's accumulated behavioral records, such as search history, browsing history, and purchase history.

[0673] "Market trend data" is data that includes information on current market trends and popular products.

[0674] "Latent needs" are needs that are inferred from users' behavior and past data, even if they are not explicitly stated.

[0675] A "negotiation request" is a request sent by a potential purchaser to change the product price or adjust the terms.

[0676] A "negotiation proposal" is a proposal for negotiation that is generated based on past data and market prices.

[0677] A "generative AI model" is a model trained by artificial intelligence that performs generative tasks based on user behavior and tendencies.

[0678] A "prompt" is a sentence output by a generative AI model that suggests the next action or suggestion to the user.

[0679] The present invention relates to a system that collects user behavior data on an online shopping site, calculates product prices based on the collected data, recommends optimal products, and supports negotiations. Specific embodiments of the system are described below.

[0680] System Configuration

[0681] Hardware

[0682] The system of the present invention comprises the following hardware:

[0683] Smartphone: A device where users can enter data and receive product recommendations and negotiation offers.

[0684] Server: Hardware for collecting data, analyzing it, running generative AI models, and generating prompts to notify the user.

[0685] software

[0686] The system of the present invention uses the following software:

[0687] Python: A programming language for data collection, analysis, prediction, and proposals.

[0688] Keras: A framework that uses neural networks to learn from user data and build generative AI models.

[0689] Scikit-learn: A library for data preprocessing such as clustering and standardization.

[0690] Data collection and analysis

[0691] The server collects the user's search history, browsing history, and purchase history, and analyzes the user's behavior based on this. Specifically, when a user searches, the search terms are sent from the device in real time, and the data is analyzed by the server. For example, if a user searches for "vintage watches," the server saves the search history and displays related products.

[0692] Smart Pricing

[0693] The server calculates the appropriate price based on the description of the listed product and price data for similar products in the market. For example, if an iPhone 12 is listed, the server analyzes market price data, calculates a recommended price of 70,000 yen, and displays this on the seller's device.

[0694] Improved matching accuracy

[0695] The server collects user feedback and updates the matching algorithm based on it, improving the accuracy of matching over time. For example, when a user provides feedback such as "This price is reasonable" or "I think it's cheaper," that data is stored on the server and used for the next price suggestion and product recommendation.

[0696] Predicting potential needs and recommending products

[0697] The server predicts the user's potential needs based on past user behavior data and market trend data, and generates optimal product listings. For example, if a user frequently searches and browses for "cameras," it will recommend related camera accessories and new camera models.

[0698] Negotiation support function

[0699] The server receives negotiation requests from potential buyers and generates appropriate negotiation proposals based on past negotiation data and market price data. For example, if a potential buyer requests a slight price reduction, the server calculates the amount of price reduction based on past data and notifies the potential buyer and seller.

[0700] Generate prompt statement

[0701] The generative AI model learns user behavior data and generates prompts. For example, if a user frequently searches for cameras, it generates a prompt such as, "If you're looking for a new camera, how about this model?" Specific examples of prompts that can be provided include:

[0702] plain

[0703] If you're looking for a new camera, how about this model?

[0704] Recommended Products: [Product List]

[0705] As a result, recommendations, price calculations, and negotiation support can be efficiently performed based on user behavior data, improving the user experience.

[0706] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0707] Step 1:

[0708] When a user searches for a product, the device sends a search query to the server. The input is the user's search term (e.g., "vintage watch"). The server receives this search query and stores it in a database. This updates the user's recent search history.

[0709] Step 2:

[0710] The server collects and analyzes the user's search history, browsing history, and purchase history. The input is the user's behavioral data saved from previous visits. The server analyzes this data to extract the user's preferences and behavioral patterns. The analysis results reveal the user's tastes and purchasing tendencies.

[0711] Step 3:

[0712] The price of the listed item is analyzed and a fair price is calculated. Inputs include the product description, photos, and market price data for similar items. The server analyzes the market price data, calculates a fair price, and displays it on the seller's device. For example, for an iPhone 12 listing, a suggested price of 70,000 yen is calculated.

[0713] Step 4:

[0714] Collecting user feedback. The input is the feedback provided by the user (e.g., "This price is reasonable"). The server receives this feedback and stores it in a database. This feedback is then used for the next algorithm update.

[0715] Step 5:

[0716] The server updates the matching algorithm based on the feedback data. The input is the collected feedback data. The server uses this data to adjust the parameters of the algorithm and improve the matching accuracy.

[0717] Step 6:

[0718] The server analyzes the user's past behavioral data and market trend data to predict the user's potential needs. The inputs include the user's search history, browsing history, purchase history, and market trend data. The server analyzes this data and generates the optimal product list for the user.

[0719] Step 7:

[0720] The server generates a product list based on the predicted needs and notifies the user. The input is the result of predicting potential needs. The server generates a product list based on this result and notifies the device. For example, if cameras are frequently searched for, related camera accessories will be recommended.

[0721] Step 8:

[0722] Receives a negotiation request from a potential buyer. The input is the buyer's request (e.g., "I would like a lower price"). The server receives this request and stores it in a database.

[0723] Step 9:

[0724] The server generates an appropriate negotiation proposal based on past negotiation data and market price data. The inputs are a negotiation request, past negotiation data, and current market price data. The server calculates an appropriate price reduction amount based on this data and generates a proposal.

[0725] Step 10:

[0726] The server notifies the buyer and seller of the generated negotiation proposal. The input is the generated negotiation proposal. The server notifies the terminal of this proposal and progresses the negotiation. This allows the transaction to proceed smoothly and improves user satisfaction.

[0727] The above are the specific processing steps in the system of the present invention. These steps enable efficient product recommendations, price calculations, and negotiation support based on user behavior data.

[0728] 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.

[0729] The system of the present invention has functions for collecting and analyzing users' search history, browsing history, and purchase history, analyzing the prices of listed items to calculate appropriate prices, collecting user feedback to update the matching algorithm, predicting users' potential needs and recommending items, and generating negotiation proposals based on negotiation requests to support negotiations.In addition, the system is equipped with an emotion engine that recognizes users' emotions and uses the emotion data to further personalize the user experience.

[0730] User data collection and analysis

[0731] The server collects and analyzes data such as the user's search terms, browsing history, and past purchase history, as well as emotional data. This data is used to understand not only the user's preferences, purchasing trends, and price perception, but also changes in their emotions.

[0732] When a user searches, the device sends emotional data along with the search terms to the server in real time. For example, when a user searches for "vintage watches," the emotion engine recognizes "interest" from facial expressions and voice at the time and sends this information to the server. Based on this data, the server generates and displays more accurate product information.

[0733] Smart Pricing

[0734] The server analyzes the price data of similar products on the market based on the photos and descriptions of the listed items, as well as emotional data, to calculate an appropriate price. For example, if a seller is listing an iPhone 12, the server analyzes the market price data of other similar products and the seller's emotional state, and suggests a price of 70,000 yen. If the seller is having difficulty setting a price, the emotion engine will recognize their anxiety, and the server can send them price advice or a message of support.

[0735] Improved matching accuracy

[0736] The server collects user feedback and emotional data and updates the matching algorithm based on that information. For example, when a user provides feedback such as "This price is appropriate" or "I think it could be cheaper," the emotional engine recognizes their satisfaction or dissatisfaction at that time and sends that data to the server. The server then uses this data to improve the accuracy of the next price suggestion and matching.

[0737] Predicting potential needs and recommending products

[0738] The server predicts the user's potential needs based on the user's past behavioral data, emotional data, and market trend data. It then generates and notifies the user of a list of optimal products. For example, if a user frequently searches for "camera" and the emotion engine recognizes the user's heightened emotions, the server will recommend related camera accessories and new camera models.

[0739] The user's device will notify and display this recommended product list, allowing the user to find products that match their potential needs based on their emotions.

[0740] Negotiation support function

[0741] The server receives emotion data along with a negotiation request from a prospective buyer, analyzes it, and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a prospective buyer requests a slight price reduction and the emotion is recognized as a strong desire, the server generates a corresponding negotiation proposal and notifies the prospective buyer and the seller.

[0742] The devices of the buyer and seller display negotiation proposals in real time, allowing each party to negotiate based on their emotions according to the situation. As a result, the transaction proceeds smoothly and it becomes easier to reach terms that satisfy the user emotionally.

[0743] By integrating these functions, the system of this invention can provide personalized product suggestions and pricing according to the user's needs, and support negotiations and transactions with consideration for emotions, which is expected to revitalize the entire reuse market.

[0744] The processing flow will be explained below.

[0745] User data collection and analysis

[0746] Step 1:

[0747] A user opens the Reuse Market app on their device, types "vintage watches" into the search bar, and presses the search button.

[0748] Step 2:

[0749] The device sends the entered search words and "interest" emotion data analyzed by the emotion engine from the user's facial expressions and voice to the server.

[0750] Step 3:

[0751] The server stores the received search terms and emotion data in a database and compares them with past search history, purchase history, and browsing history.

[0752] Step 4:

[0753] The server analyzes the user's interests, purchasing trends, and emotional changes based on the stored data, and generates and displays appropriate product information.

[0754] Smart Pricing

[0755] Step 1:

[0756] To list an iPhone 12, a seller enters product photos and descriptions from their device and presses the list button.

[0757] Step 2:

[0758] The device sends product information and "anxiety" emotion data analyzed by an emotion engine from the seller's facial expressions and voice to the server.

[0759] Step 3:

[0760] The server analyzes market price data for similar products based on the transmitted product information and emotion data.

[0761] Step 4:

[0762] The server calculates the optimal price as a result of the analysis and generates price advice and supportive messages according to the seller's emotional state.

[0763] Step 5:

[0764] The server transmits the recommended price and a support message to the seller's terminal, and the terminal displays the price and message to the seller.

[0765] Improved matching accuracy

[0766] Step 1:

[0767] The user provides feedback such as "This price is appropriate" or "It could be cheaper," and the emotion engine simultaneously analyzes the user's emotions, such as "satisfaction" or "dissatisfaction."

[0768] Step 2:

[0769] The device sends user feedback and emotion data to the server.

[0770] Step 3:

[0771] The server stores the received feedback and emotion data and adds it to a database to be analyzed.

[0772] Step 4:

[0773] The server uses this new data to update its matching algorithm and improve the accuracy of its next price suggestions and recommended products.

[0774] Predicting potential needs and recommending products

[0775] Step 1:

[0776] The server analyzes the user's past behavioral data, stored emotion data, and market trend data to predict the user's potential needs.

[0777] Step 2:

[0778] The server generates a list of products that are best suited to the user based on predicted needs and sentiment data.

[0779] Step 3:

[0780] The server transmits the generated recommended product list to the user's terminal, and the terminal notifies the user of an emotion-inducing message related to the recommended products.

[0781] Negotiation support function

[0782] Step 1:

[0783] A prospective purchaser sends a price reduction request for the product.

[0784] Step 2:

[0785] The device sends this request along with "strong desire" emotion data analyzed by the emotion engine from the prospective buyer's facial expressions and tone of voice to the server.

[0786] Step 3:

[0787] The server analyzes the request and sentiment data and generates appropriate negotiation proposals based on past negotiation data and market price data.

[0788] Step 4:

[0789] The server sends the generated negotiation proposal and a message according to the emotion to the prospective buyer and the seller.

[0790] Step 5:

[0791] The devices of the prospective buyer and seller display negotiation proposals and messages in real time, and each party proceeds with the negotiations with emotions appropriate to the situation.

[0792] Step 6:

[0793] The user (seller) sets a new price based on the proposal, and the transaction is completed when the potential buyer agrees to it.

[0794] These steps allow the system of the present invention to optimize the user's searching, listing, and negotiating experience based on emotions.

[0795] Example 2

[0796] 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."

[0797] Conventional e-commerce systems use users' search and purchase histories to suggest products and set prices, but this often does not adequately address users' emotions and needs. Furthermore, pricing and negotiation support sometimes ignore the emotions of sellers and potential buyers, resulting in lower user satisfaction. To address these issues, a more personalized system that incorporates user emotional data is needed, offering higher levels of satisfaction.

[0798] 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 means for collecting and analyzing the user's search history, browsing history, and purchase history, means for analyzing the price of the listed product based on the price data of other similar products to calculate the appropriate price, and means for collecting and analyzing the user's emotional data. This allows the user's emotional data to be analyzed together with their past behavioral data, enabling more accurate product proposals, pricing, and negotiation support.

[0799] "User search history" is a record of the user's search behavior within the system.

[0800] "Browse history" is a record of the products a user has viewed within the system.

[0801] "Purchase history" is a record of products a user has previously purchased within the system.

[0802] A "fair price" is a fair and reasonable price calculated based on market data and price data for similar products.

[0803] "Emotional data" refers to emotional information analyzed from the user's facial expressions, voice, etc.

[0804] "Feedback" refers to users' evaluations and opinions of the products and services they provide.

[0805] A "matching algorithm" is a calculation method for selecting products and services that match a user's requirements and preferences.

[0806] "Latent needs" are needs or desires that are not explicitly expressed by the user but can be predicted from their behavioral and emotional data.

[0807] "Product List" means a list of products selected for offering to users.

[0808] A "negotiation request" is a request by a prospective purchaser to change the product price.

[0809] A "negotiation proposal" is a proposal for price and terms of trade generated by the server in response to a negotiation request.

[0810] The system according to the present invention is an advanced system that collects user search history, browsing history, purchase history, and emotional data, and uses this data to propose products, set prices, and assist in negotiations. The following describes how to specifically implement this system.

[0811] First, to generate the program for this system, the following main hardware and software are required: Hardware includes a server and user devices (PCs, smartphones, tablets, etc.), while software includes an emotion recognition engine (e.g., Microsoft Emotion API, Google Cloud Speech-to-Text API), a database (e.g., MongoDB, PostgreSQL), machine learning algorithms (e.g., TensorFlow, PyTorch), and natural language processing technology (e.g., SpaCy).

[0812] The server integrates and analyzes the user's search history, browsing history, and purchase history, as well as emotional data collected from facial expressions and voice. This allows the system to understand not only the user's preferences and purchasing trends, but also changes in their emotions. For example, if a user searches for "vintage watches" and their facial expression indicates "interest," the server receives and analyzes this data in real time.

[0813] Based on the analysis results, the server searches the product database, generates a list of products that are best suited to the user, and notifies the device. This allows users to quickly find the products they are interested in. For example, products related to "vintage watches" are displayed preferentially, and information such as price, quality rating, and seller rating is provided.

[0814] The server analyzes the price of a listed item based on the price data of other similar items and the seller's emotional data to calculate an appropriate price. For example, when a seller tries to list an iPhone 12, the server analyzes the market price data of other similar items and suggests a recommended price of 70,000 yen. If the seller is feeling anxious, the emotion recognition engine will recognize this and the server can send an encouraging message.

[0815] The server collects user feedback and emotional data and updates the matching algorithm based on this. For example, if a user provides feedback such as "This price is reasonable" or "I think it could be cheaper," and the user's emotional response is satisfied, the server will improve the algorithm for the next price and product suggestion.

[0816] Furthermore, the server can analyze the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. For example, if the user frequently searches for "camera" and shows high emotional responses, the server can recommend camera accessories and new camera models based on that information. These recommended product lists are then sent to the user's device.

[0817] Finally, the server analyzes the buyer's negotiation request and emotional data, and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a buyer requests a slight price reduction and the emotion is recognized as a strong desire, the server generates a corresponding negotiation proposal and notifies the buyer and seller. Displaying the negotiation proposal in real time makes it easier to reach a deal that satisfies both parties.

[0818] As a concrete example, the generative AI model can be used with the following prompt sentence:

[0819] Example prompt:

[0820] "If a user searches for vintage watches and the emotion engine recognizes their current interest, how would the server generate and display product information?"

[0821] As a result, the system of the present invention can make product proposals and set prices personalized to the user's needs, and further support negotiations by taking emotions into consideration, thereby achieving more satisfying transactions.

[0822] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0823] Step 1:

[0824] A user enters a search term, such as "vintage watches," into the device. The input includes the search term (e.g., "vintage watches") and facial and vocal emotion data collected using the device's camera and microphone. The device's software uses an emotion recognition engine (e.g., Microsoft Emotion API, Google Cloud Speech-to-Text API) to convert the facial and vocal data into emotion data such as "interest." The output is a combination of the search term and the emotion data.

[0825] Step 2:

[0826] The terminal transmits the user's search words and collected emotion data to the server in real time using SSL / TLS encryption protocol. The input is the search words and emotion data, and the output after transmission is the data safely reaching the server.

[0827] Step 3:

[0828] The server searches a database based on the received search term and emotion data. The input is a search term (e.g., "vintage watch") and emotion data (e.g., "interest"). The server searches a large product database (e.g., MongoDB) to obtain information on related products. Specifically, it uses machine learning algorithms (e.g., TensorFlow, PyTorch) to search for and prioritize related products. The output is a list of optimal products.

[0829] Step 4:

[0830] The server notifies the terminal of the generated product list. The input is the optimal product list, and the output is to display it on the target user's terminal. Specifically, the server encodes the product list in JSON format and sends it to the terminal.

[0831] Step 5:

[0832] The user browses the presented product list and clicks on a product page. The input is the ID of the individual product selected from the product list. The terminal requests detailed information about the selected product from the server and displays the product detail page to the user as output. Specifically, the terminal captures the user's click event and sends a detailed information request to the server.

[0833] Step 6:

[0834] When a seller attempts to list a new item, the server calculates the appropriate price based on product information and emotional data. The input is product information (e.g., "iPhone 12") and the seller's emotional data (e.g., "anxiety"). The server analyzes market data and price data for similar products to calculate the appropriate price that will give the seller peace of mind. The output is a recommended price (e.g., "70,000 yen"). Specific operations involve using a machine learning model that takes into account emotional data along with statistical analysis.

[0835] Step 7:

[0836] The user provides feedback on the price and product evaluation. The input is the user's feedback (e.g., "This price is appropriate") and facial expression data at that time (e.g., "Satisfied"). The device transmits the feedback and emotional data to the server in real time, and the output is the data received by the server. Specifically, the device uses a feedback form and an emotion-recognition camera.

[0837] Step 8:

[0838] The server updates the matching algorithm based on the received feedback and emotion data. The input is the feedback and emotion data. Using a data analysis engine, the algorithm for the next price or product suggestion is adjusted, and the output is the updated algorithm. Specifically, the feedback data is fed into a machine learning model to optimize the algorithm parameters.

[0839] Step 9:

[0840] The server analyzes the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. The input is past behavioral data and emotional data. A machine learning algorithm is used to predict the user's purchasing intentions, and the output is a product list based on the predicted needs. Specific operations include time series analysis and clustering techniques.

[0841] Step 10:

[0842] The server generates an appropriate negotiation proposal based on the negotiation request and emotional data from the prospective buyer. The input is the prospective buyer's request (e.g., "I would like to ask for a smaller price reduction") and emotional data (e.g., "I strongly desire it"). The server analyzes past negotiation data and market price data, generates an appropriate negotiation proposal, and notifies the prospective buyer and seller as output. In concrete terms, the server integrates and uses an emotion recognition algorithm and a negotiation support algorithm.

[0843] (Application example 2)

[0844] 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."

[0845] Modern online shopping sites are required to make more personalized product recommendations and set fair prices by effectively utilizing not only users' search and purchase histories but also their emotional data. Generating negotiation proposals based on users' emotional state and improving the success rate of negotiations is also an important challenge. However, conventional systems have had difficulty fully integrating and effectively utilizing these functions.

[0846] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history; means for analyzing the price of a listed product based on price data of other similar products to calculate an appropriate price; means for collecting user feedback and updating a matching algorithm based on the feedback; means for analyzing the user's past behavioral data and market trend data to predict the user's potential needs; means for generating a product list based on the predicted needs and notifying the user of the list; means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices; means for supporting negotiations based on requests and proposals submitted by the user; means for analyzing the user's emotional data and making personalized product proposals and pricing based on the analyzed data; and means for making appropriate negotiation proposals when providing negotiation support based on the user's current emotional state. This enables personalized product proposals, pricing, and negotiation support that take the user's emotions into consideration.

[0847] "User search history" is a record of keywords and phrases that a user has searched for on the Internet.

[0848] "Browsing history" is a record of the pages a user has visited on a website or application.

[0849] "Purchase history" is a record of the products and services a user has actually purchased.

[0850] "Price data of similar products" refers to price information of the same or similar products traded in the market.

[0851] "Feedback" refers to opinions and ratings provided by users, which is information used to improve and adjust the system.

[0852] A "matching algorithm" is a calculation method for suggesting optimal products and services based on a user's preferences and needs.

[0853] "Past behavioral data" refers to historical information about searches, browsing, purchases, etc. that a user has conducted.

[0854] "Market trend data" refers to information about overall market trends and user behavior trends.

[0855] "Latent needs" are requests for products or services that users are not yet clearly aware of but may need in the future.

[0856] A "product list" is a list of multiple products or services that the system suggests to the user.

[0857] A "negotiation request" is a request for negotiations sent by a prospective buyer to a seller regarding price and conditions.

[0858] A "negotiation proposal" is a proposal regarding price and other terms generated in response to a negotiation request.

[0859] "Emotion data" is information about the user's emotional state that can be inferred from facial expressions, voice, etc.

[0860] "Personalization" refers to providing customized suggestions and settings based on individual user preferences and behavior.

[0861] The present invention provides a system that collects users' search history, browsing history, purchase history, and emotional data, and uses this data to make personalized product proposals and set prices, as well as provide negotiation support.

[0862] User data collection and analysis

[0863] The server collects information on the keywords the user has searched for, the pages they have viewed, and the products they have purchased in the past. In addition, the emotion engine analyzes emotional data from the user's facial expressions and voice, and collects this data as well. The device sends data to the server in real time when the user performs a search. For example, if a user searches for "vintage watches," the emotion engine recognizes "interests" from their facial expressions and voice at the time and sends this data to the server. The server uses this data to analyze the user's preferences and purchasing trends, and generates appropriate product information to display to the user.

[0864] Smart Pricing

[0865] The server analyzes the price data of similar products on the market based on the photos and descriptions of the listed items, as well as emotional data, and calculates an appropriate price. For example, if a seller is listing a smartphone, the server analyzes the market price data of other similar products and the seller's emotional state, and suggests a price of 50,000 yen. If the seller is having difficulty setting a price, the emotion engine will recognize their anxiety, and the server can send them price advice or a message of support.

[0866] Improved matching accuracy

[0867] The server collects user feedback and emotional data and updates the matching algorithm based on that information. For example, while a user provides feedback such as "This price is reasonable" or "I think it could be cheaper," the emotional engine recognizes their satisfaction or dissatisfaction at that time. Based on this data, the server uses it to improve the accuracy of the next price suggestion and matching.

[0868] Predicting potential needs and recommending products

[0869] The server predicts a user's potential needs based on the user's past behavioral data, emotional data, and market trend data. For example, if a user frequently searches for "camera" and the emotion engine recognizes the user's heightened emotions, the server will recommend related camera accessories and new camera models. The user's device will notify and display a list of these recommended products, allowing the user to easily find products that meet their potential needs.

[0870] Negotiation support function

[0871] The server receives and analyzes emotional data along with a negotiation request from a potential buyer. For example, if a potential buyer requests a slight price reduction, and the server recognizes this emotion as a strong desire, it generates a corresponding negotiation proposal and notifies the potential buyer and seller in real time. The seller's device displays a negotiation proposal that takes into account the potential buyer's emotional state, allowing negotiations to proceed based on emotions appropriate to each situation. This allows for smoother transactions and makes it easier to reach transaction terms that satisfy the user emotionally.

[0872] By integrating the above functions, the system of the present invention can provide personalized product suggestions and pricing based on user needs, and emotionally support negotiations and transactions, which is expected to revitalize the entire online market.

[0873] Prompt Sentence Examples

[0874] Based on the user's search history, use the search term "vintage watches" and its sentiment data to perform the following tasks:

[0875] Calculating fair prices from market data

[0876] Recommend related products

[0877] Generate negotiation support proposals

[0878] Also, optimize your matching algorithm based on feedback.

[0879] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0880] Step 1:

[0881] When a user searches, the device sends search terms along with emotional data captured from facial expressions and voice to the server in real time. The search terms and emotional data are used as inputs, and the data is then processed to track the user's interests. As an output, the server stores the information in a database for analyzing the user's preferences and interests.

[0882] Step 2:

[0883] The server collects and analyzes users' search, browsing, and purchase histories along with emotional data. Using this history and emotional data as input, data calculations are performed to identify specific purchasing trends and patterns. As output, personalized product information is generated based on the user's purchasing trends and preferences.

[0884] Step 3:

[0885] When setting the price of a newly listed item, the server analyzes the price data of similar items on the market and the seller's sentiment data. Using the product details, market data, and sentiment data as input, the server performs data calculations to calculate an appropriate price. As an output, a suggested selling price is displayed on the product page and notified to the seller.

[0886] Step 4:

[0887] The server collects user feedback and sentiment data and uses it to update the matching algorithm. Using the feedback and sentiment data as input, it performs data calculations to adjust and improve the algorithm. The output is an improved matching algorithm, which is reflected in future searches and recommendations.

[0888] Step 5:

[0889] The server analyzes the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. Using the behavioral data, emotional data, and trend data as input, data calculations are performed to identify potential needs. As output, a product list based on the predicted potential needs is generated and notified to the user.

[0890] Step 6:

[0891] When a negotiation request is received from a potential buyer, the server analyzes the emotion data and generates an appropriate negotiation proposal based on past negotiation data and market price data. Using the negotiation request, emotion data, past negotiation data, and price data as input, data calculations are performed to propose optimal negotiation terms. As an output, the generated negotiation proposal is notified to the potential buyer and seller in real time.

[0892] Step 7:

[0893] The user's device displays the personalized product list and negotiation proposals sent from the server to the user, allowing the user to proceed with the purchase or negotiation based on the presented information. Using the data sent from the server as input, the data is processed to display appropriately to the user. As output, an interface is generated for the user to view or operate.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] [Third embodiment]

[0898] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0899] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0900] 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).

[0901] 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.

[0902] 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.

[0903] 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).

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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."

[0910] The system of the present invention has functions for collecting users' search history, browsing history, and purchase history, for analyzing the prices of listed products and calculating appropriate prices, for collecting feedback from users and updating the matching algorithm, for predicting users' potential needs and recommending products, and for generating negotiation proposals based on negotiation requests and supporting negotiations.

[0911] User data collection and analysis

[0912] The server collects and analyzes data such as user search terms, browsing history, and past purchase history, which is used to understand user preferences, purchasing trends, and price sensitivity.

[0913] When a user searches, the device sends the search terms to the server in real time, allowing the server to analyze the latest data. For example, if a user searches for "vintage watches," their search history is sent to the server, and related products are displayed based on the analysis results.

[0914] Smart Pricing

[0915] The server analyzes the price data of similar products on the market based on the photos and description of the listed product and calculates an appropriate price. For example, if a seller wants to list an iPhone 12, the server analyzes the market price data of other similar products, calculates a recommended price of 70,000 yen, and displays it on the seller's device. The seller can use this price as a reference to set their listing price.

[0916] Improved matching accuracy

[0917] The server collects feedback from users and updates the matching algorithm based on that feedback, improving the accuracy of matching over time. For example, when a user provides feedback such as "This price is reasonable" or "I think it's cheaper," that data is stored on the server and used to suggest prices and improve matching accuracy the next time.

[0918] Predicting potential needs and recommending products

[0919] The server predicts users' potential needs based on their past behavioral data and market trend data. It then generates and notifies users of a list of products that best suit their needs. For example, if a user frequently searches for and browses "cameras," the server will recommend related camera accessories and new camera models.

[0920] The user's device will notify and display this list of recommended products, making it easier for the user to find products that meet their potential needs.

[0921] Negotiation support function

[0922] The server receives a negotiation request from a potential buyer and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a potential buyer requests a slight price reduction, the server calculates the appropriate price reduction amount based on past data and notifies the potential buyer and seller of the price reduction proposal.

[0923] The buyer and seller's devices can display negotiation proposals in real time and proceed with the negotiations based on them, which results in a smoother transaction and makes it easier to reach terms that satisfy both users.

[0924] The above is a specific embodiment of the system based on the present invention. By using this system, users can efficiently search for, purchase, and negotiate products, which is expected to revitalize the entire reuse market.

[0925] The processing flow will be explained below.

[0926] User data collection and analysis

[0927] Step 1:

[0928] A user opens the Reuse Market app on their device, types "vintage watches" into the search bar, and presses the search button.

[0929] Step 2:

[0930] The terminal sends the entered search words to the server.

[0931] Step 3:

[0932] The server stores the received search terms in a database and compares them with past search and purchase history.

[0933] Step 4:

[0934] The server analyzes the user's interests and purchasing trends based on the stored data, and generates appropriate information based on the results.

[0935] Smart Pricing

[0936] Step 1:

[0937] To list an iPhone 12, a seller enters product photos and descriptions from their device and presses the list button.

[0938] Step 2:

[0939] The terminal transmits the product information to the server.

[0940] Step 3:

[0941] The server analyzes the market price data of similar products based on the transmitted product information.

[0942] Step 4:

[0943] The server calculates the optimal price as a result of the analysis and generates a recommended price.

[0944] Step 5:

[0945] The server sends the recommended price to the seller's terminal, which displays the price to the seller.

[0946] Improved matching accuracy

[0947] Step 1:

[0948] The user provides feedback such as "This price is good" or "It could be a little cheaper."

[0949] Step 2:

[0950] The device sends the user's feedback to the server.

[0951] Step 3:

[0952] The server stores the received feedback and adds it to a database to be analyzed.

[0953] Step 4:

[0954] The server updates its matching algorithm based on the new feedback, improving accuracy.

[0955] Predicting potential needs and recommending products

[0956] Step 1:

[0957] The server compares the user's past behavioral data (search history, browsing history, purchase history) with market trend data to predict the user's potential needs.

[0958] Step 2:

[0959] The server generates a list of products that best suit the user based on their predicted needs.

[0960] Step 3:

[0961] The server transmits the generated recommended product list to the user's terminal, and the terminal notifies the user of the recommended products.

[0962] Negotiation support function

[0963] Step 1:

[0964] A prospective purchaser sends a price reduction request for the product.

[0965] Step 2:

[0966] The terminal sends this request to the server.

[0967] Step 3:

[0968] The server analyzes the request and generates an appropriate negotiation proposal based on past negotiation data and market prices.

[0969] Step 4:

[0970] The server sends the generated negotiation proposal to the prospective buyer and the seller.

[0971] Step 5:

[0972] The buyer and seller's terminals display negotiation proposals in real time and confirm them with each other.

[0973] Step 6:

[0974] The user (seller) sets a new price based on the proposal, and the transaction is completed when the potential buyer agrees to it.

[0975] Example 1

[0976] 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."

[0977] In current online marketplaces, many systems that effectively utilize users' search and purchase histories to suggest products face challenges in terms of matching accuracy and price accuracy. Furthermore, they lack the ability to accurately predict users' potential needs and support functions to smoothly advance the negotiation process. These challenges must be addressed to increase user satisfaction.

[0978] 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.

[0979] In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history, means for transmitting search terms from the user's terminal in real time, means for analyzing price data of similar products in the market based on information about the listed product and calculating an appropriate price, means for collecting feedback from the user and updating a matching algorithm based on the feedback, means for analyzing past user behavior data and market trend data and predicting the user's potential needs, means for generating a product list based on the predicted needs and notifying the user of the list, means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, and means for supporting negotiations based on requests and proposals transmitted by the user. This enables users to efficiently search for, purchase, and negotiate on products.

[0980] "User" refers to a person who uses the System to search for, view, purchase, or list products.

[0981] "Device" refers to electronic devices such as computers, smartphones, and tablets used by users.

[0982] "Server" refers to a computer system that receives, analyzes, stores, and processes data submitted by users.

[0983] "Search History" refers to a record of keywords and phrases that a User has previously searched for on the System.

[0984] "Browse history" refers to the record of product pages that a user has viewed on the System.

[0985] "Purchase History" refers to the record of products that a User has previously purchased through this System.

[0986] "Feedback" refers to data such as opinions, ratings, and impressions provided by users.

[0987] A "matching algorithm" refers to a calculation method that analyzes user data and product data to suggest the most suitable product to the user.

[0988] "Fair price" refers to the price that is considered appropriate for the product, calculated by the server by analyzing market data.

[0989] "Latent needs" refer to the desires and needs that users may have that are not explicitly stated by users but that can be inferred from past behavioral data and market trend data.

[0990] "Product list" refers to a list of multiple products that the server generates based on the user's potential needs and notifies the user.

[0991] A "negotiation request" refers to a request from a prospective buyer to a seller to change the price or terms of the transaction.

[0992] "Negotiation proposal" refers to the negotiation conditions that the server generates based on past negotiation data and market price data and notifies the prospective buyer and seller.

[0993] The system of the present invention uses multiple hardware and software components to provide functions for collecting and analyzing users' search history, browsing history, and purchase history, analyzing the prices of listed items to calculate appropriate prices, collecting feedback from users to update matching algorithms, predicting users' potential needs and recommending items, and generating negotiation proposals based on negotiation requests to support negotiations.

[0994] Hardware used

[0995] 1. Device: The computer, smartphone, tablet, etc. used by the user.

[0996] 2. Server: A high-performance computer system that collects, analyzes, stores, and processes data.

[0997] Software used

[0998] 1. Data collection program: Software that runs on the device and transmits user operations to a server in real time.

[0999] 2. Data analysis program: An algorithm that runs on the server and analyzes the collected data.

[1000] 3. Feedback collection program: Software that receives and analyzes feedback from users.

[1001] 4. Price analysis program: An algorithm that runs on the server and calculates the fair price based on market data.

[1002] 5. Matching algorithm: A calculation method for suggesting optimal products based on user data.

[1003] 6. Product recommendation generator: Software that predicts users' potential needs and generates product lists.

[1004] 7. Negotiation Support Program: Software that receives negotiation requests, generates appropriate negotiation proposals, and sends them to the user.

[1005] Example of operation

[1006] When a user searches for "vintage watches," the user's device sends the search term to the server in real time. The server collects data including the user's search history, past browsing history, and purchase history, and performs analysis related to the search term "vintage watches." As a result, the server generates a list of related products and displays it on the user's device.

[1007] When a seller tries to list an iPhone 12, the product information entered on the seller's device is sent to the server. The server analyzes the product's photos and description and retrieves pricing data for similar products from other online marketplaces. It then calculates the optimal price of 70,000 yen and provides it to the seller's device. The seller can use this price as a reference to set the selling price of their own product.

[1008] When a user provides feedback, such as "this price is reasonable" or "it should be cheaper," that feedback is sent from the user's device to the server and stored. The server then incorporates this feedback into the next price suggestion and matching accuracy improvement, thereby improving accuracy.

[1009] If a user frequently searches and browses for "camera," the server will use that data to recommend camera-related accessories and new camera models, and these recommendations will be displayed on the user's device and the user will be notified.

[1010] When a prospective buyer sends a negotiation request saying, "I would like to ask for a further price reduction," the server generates an appropriate price reduction proposal based on past negotiation data and market price data, and sends it to the terminals of the prospective buyer and the seller for presentation.

[1011] Prompt Sentence Examples

[1012] "Based on the user's past search history and market trends, predict his potential needs and generate a list of relevant products."

[1013] "Please calculate a fair price based on the description of the listed item and market price data."

[1014] "Update your matching algorithm based on user feedback data."

[1015] As a result, the system of the present invention provides users with optimal product search, purchasing, and negotiation, and is expected to revitalize the entire reuse market.

[1016] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1017] Step 1: Collect user data

[1018] 1.1. Submitting search terms

[1019] A user enters a search term into the device's search bar.

[1020] The device sends the entered search term (e.g., "vintage watch") to the server in real time.

[1021] Input: User's search term.

[1022] Data processing: Formalizing and structuring search terms.

[1023] Output: Search word data sent to the server.

[1024] 1.2. Collection of browsing and purchase history

[1025] The server collects data on the product pages the user has previously viewed and the products they have purchased.

[1026] Input: User's browsing history, purchase history.

[1027] Data processing: Organizing data based on time series.

[1028] Output: Structured browsing and purchase history data.

[1029] Step 2: Analyze the data

[1030] 2.1. Analysis of user trends

[1031] The server analyzes the collected search terms, browsing history, and purchase history to identify the user's preferences and purchasing trends.

[1032] Input: Search terms, browsing history, and purchase history data.

[1033] Data processing: Data analysis and pattern recognition.

[1034] Output: Analysis of user preferences and purchasing trends.

[1035] 2.2. Display of related products

[1036] The server generates a list of related products based on the analysis results and notifies the user's device.

[1037] Input: Analysis of user preferences and purchasing trends.

[1038] Data processing: Generate a list of related products.

[1039] Output: Related product list displayed on the device.

[1040] Step 3: Smart Pricing

[1041] 3.1. Product data collection

[1042] The user (seller) enters product information (photo and description) into the terminal and sends it to the server.

[1043] Input: Product information (photo, description).

[1044] Data Processing: Receiving product information and converting it into data for analysis.

[1045] Output: Structured product data.

[1046] 3.2. Market price data collection

[1047] The server collects price data for other similar products in the market.

[1048] Input: Product information, matching market data.

[1049] Data processing: market data collection and matching.

[1050] Output: Price data for similar products.

[1051] 3.3. Calculating the fair price

[1052] The server calculates the fair price of the auction item based on the market price data.

[1053] Input: Price data for similar products.

[1054] Data processing: Calculating fair prices.

[1055] Output: Reasonably priced and affordable.

[1056] 3.4. Recommended Price

[1057] The server notifies the seller's terminal of the calculated fair price.

[1058] Enter: Fair Price.

[1059] Data processing: Formalization of pricing data.

[1060] Output: The suggested price displayed on the seller's device.

[1061] Step 4: Gather feedback and update the algorithm

[1062] 4.1. Sending Feedback

[1063] Users enter feedback about prices and product ratings into the device.

[1064] Input: Feedback content.

[1065] Data processing: Formalization of feedback data.

[1066] Output: Feedback data sent to the server.

[1067] 4.2. Gathering Feedback for Algorithm Updates

[1068] The server accumulates and stores the collected feedback data.

[1069] Input: Feedback data.

[1070] Data processing: Accumulation and analysis of feedback data.

[1071] Output: The updated matching algorithm.

[1072] Step 5: Anticipating potential needs and recommending products

[1073] 5.1. Analysis of behavioral data

[1074] The server analyzes users' past behavioral data and market trend data.

[1075] Inputs: Behavioral data, market trend data.

[1076] Data processing: Data analysis and pattern recognition.

[1077] Output: Prediction of potential user needs.

[1078] 5.2. Creating a Product List

[1079] The server generates a list of related products based on the predicted user needs and notifies the user's terminal.

[1080] Input: Predicted potential needs.

[1081] Data processing: Product list generation.

[1082] Output: A list of recommended products displayed on the device.

[1083] Step 6: Negotiation support

[1084] 6.1. Sending a Negotiation Request

[1085] The prospective buyer sends a negotiation request from the terminal.

[1086] Input: Negotiation request.

[1087] Data processing: Request formatting and storage.

[1088] Output: The negotiation request sent to the server.

[1089] 6.2. Generating Negotiation Proposals

[1090] The server generates appropriate negotiation proposals based on past negotiation data and market data.

[1091] Inputs: Negotiation request, historical negotiation data, market data.

[1092] Data processing: Generating negotiation proposals.

[1093] Output: Negotiation proposal sent to the buyer's and seller's devices.

[1094] This will enable each function of the system to be realized, enabling users to efficiently search for, purchase, and negotiate products.

[1095] (Application example 1)

[1096] 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."

[1097] Traditional online shopping sites typically recommend products based on users' search and purchase histories, but this method is often inaccurate. In particular, it is difficult to accurately predict and recommend products that users will be interested in, which can result in poor user experience. Furthermore, there is a lack of functionality to automatically generate appropriate negotiation proposals based on negotiation requests and facilitate smooth negotiations between users. This creates the challenge of finding transaction terms that satisfy users.

[1098] 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.

[1099] In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history, means for analyzing the price of a listed item based on price data of other similar items and calculating an appropriate price, means for collecting user feedback and updating a matching algorithm based on the feedback, means for analyzing the user's past behavioral data and market trend data and predicting the user's potential needs, means for generating a product list based on the predicted needs and notifying the user of the list, means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, means for supporting negotiations based on requests and proposals submitted by the user, means for providing optimal prices and product recommendations based on the user's behavioral data, and means for generating prompt messages using a generative AI model that has learned the user's purchasing tendencies. This enables efficient product recommendations, calculation of appropriate prices, and negotiation support based on the user's behavioral data, thereby significantly improving the user experience.

[1100] "Search history" is a record of a user's past search queries within websites and applications.

[1101] "Browsing history" is a record of data about web pages and product pages that a user has viewed in the past.

[1102] "Purchase history" is a record of data on products purchased by a user in the past.

[1103] "Analysis" is the process of extracting meaning from collected data using statistical or machine learning algorithms.

[1104] "Price data for similar products" refers to price information for products of the same type or with similar characteristics that exist in the market.

[1105] A "fair price" is a product price that is determined statistically or algorithmically to be fair and appropriate to the market.

[1106] "Feedback" refers to opinions and evaluation data provided by users.

[1107] A "matching algorithm" is a calculation procedure that recommends optimal products and services based on user data.

[1108] "Past behavioral data" refers to the user's accumulated behavioral records, such as search history, browsing history, and purchase history.

[1109] "Market trend data" is data that includes information on current market trends and popular products.

[1110] "Latent needs" are needs that are inferred from users' behavior and past data, even if they are not explicitly stated.

[1111] A "negotiation request" is a request sent by a potential purchaser to change the product price or adjust the terms.

[1112] A "negotiation proposal" is a proposal for negotiation that is generated based on past data and market prices.

[1113] A "generative AI model" is a model trained by artificial intelligence that performs generative tasks based on user behavior and tendencies.

[1114] A "prompt" is a sentence output by a generative AI model that suggests the next action or suggestion to the user.

[1115] The present invention relates to a system that collects user behavior data on an online shopping site, calculates product prices based on the collected data, recommends optimal products, and supports negotiations. Specific embodiments of the system are described below.

[1116] System Configuration

[1117] Hardware

[1118] The system of the present invention comprises the following hardware:

[1119] Smartphone: A device where users can enter data and receive product recommendations and negotiation offers.

[1120] Server: Hardware for collecting data, analyzing it, running generative AI models, and generating prompts to notify the user.

[1121] software

[1122] The system of the present invention uses the following software:

[1123] Python: A programming language for data collection, analysis, prediction, and proposals.

[1124] Keras: A framework that uses neural networks to learn from user data and build generative AI models.

[1125] Scikit-learn: A library for data preprocessing such as clustering and standardization.

[1126] Data collection and analysis

[1127] The server collects the user's search history, browsing history, and purchase history, and analyzes the user's behavior based on this. Specifically, when a user searches, the search terms are sent from the device in real time, and the data is analyzed by the server. For example, if a user searches for "vintage watches," the server saves the search history and displays related products.

[1128] Smart Pricing

[1129] The server calculates the appropriate price based on the description of the listed product and price data for similar products in the market. For example, if an iPhone 12 is listed, the server analyzes market price data, calculates a recommended price of 70,000 yen, and displays this on the seller's device.

[1130] Improved matching accuracy

[1131] The server collects user feedback and updates the matching algorithm based on it, improving the accuracy of matching over time. For example, when a user provides feedback such as "This price is reasonable" or "I think it's cheaper," that data is stored on the server and used for the next price suggestion and product recommendation.

[1132] Predicting potential needs and recommending products

[1133] The server predicts the user's potential needs based on past user behavior data and market trend data, and generates optimal product listings. For example, if a user frequently searches and browses for "cameras," it will recommend related camera accessories and new camera models.

[1134] Negotiation support function

[1135] The server receives negotiation requests from potential buyers and generates appropriate negotiation proposals based on past negotiation data and market price data. For example, if a potential buyer requests a slight price reduction, the server calculates the amount of price reduction based on past data and notifies the potential buyer and seller.

[1136] Generate prompt statement

[1137] The generative AI model learns user behavior data and generates prompts. For example, if a user frequently searches for cameras, it generates a prompt such as, "If you're looking for a new camera, how about this model?" Specific examples of prompts that can be provided include:

[1138] plain

[1139] If you're looking for a new camera, how about this model?

[1140] Recommended Products: [Product List]

[1141] As a result, recommendations, price calculations, and negotiation support can be efficiently performed based on user behavior data, improving the user experience.

[1142] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1143] Step 1:

[1144] When a user searches for a product, the device sends a search query to the server. The input is the user's search term (e.g., "vintage watch"). The server receives this search query and stores it in a database. This updates the user's recent search history.

[1145] Step 2:

[1146] The server collects and analyzes the user's search history, browsing history, and purchase history. The input is the user's behavioral data saved from previous visits. The server analyzes this data to extract the user's preferences and behavioral patterns. The analysis results reveal the user's tastes and purchasing tendencies.

[1147] Step 3:

[1148] The price of the listed item is analyzed and a fair price is calculated. Inputs include the product description, photos, and market price data for similar items. The server analyzes the market price data, calculates a fair price, and displays it on the seller's device. For example, for an iPhone 12 listing, a suggested price of 70,000 yen is calculated.

[1149] Step 4:

[1150] Collecting user feedback. The input is the feedback provided by the user (e.g., "This price is reasonable"). The server receives this feedback and stores it in a database. This feedback is then used for the next algorithm update.

[1151] Step 5:

[1152] The server updates the matching algorithm based on the feedback data. The input is the collected feedback data. The server uses this data to adjust the parameters of the algorithm and improve the matching accuracy.

[1153] Step 6:

[1154] The server analyzes the user's past behavioral data and market trend data to predict the user's potential needs. The inputs include the user's search history, browsing history, purchase history, and market trend data. The server analyzes this data and generates the optimal product list for the user.

[1155] Step 7:

[1156] The server generates a product list based on the predicted needs and notifies the user. The input is the result of predicting potential needs. The server generates a product list based on this result and notifies the device. For example, if cameras are frequently searched for, related camera accessories will be recommended.

[1157] Step 8:

[1158] Receives a negotiation request from a potential buyer. The input is the buyer's request (e.g., "I would like a lower price"). The server receives this request and stores it in a database.

[1159] Step 9:

[1160] The server generates an appropriate negotiation proposal based on past negotiation data and market price data. The inputs are a negotiation request, past negotiation data, and current market price data. The server calculates an appropriate price reduction amount based on this data and generates a proposal.

[1161] Step 10:

[1162] The server notifies the buyer and seller of the generated negotiation proposal. The input is the generated negotiation proposal. The server notifies the terminal of this proposal and progresses the negotiation. This allows the transaction to proceed smoothly and improves user satisfaction.

[1163] The above are the specific processing steps in the system of the present invention. These steps enable efficient product recommendations, price calculations, and negotiation support based on user behavior data.

[1164] 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.

[1165] The system of the present invention has functions for collecting and analyzing users' search history, browsing history, and purchase history, analyzing the prices of listed items to calculate appropriate prices, collecting user feedback to update the matching algorithm, predicting users' potential needs and recommending items, and generating negotiation proposals based on negotiation requests to support negotiations.In addition, the system is equipped with an emotion engine that recognizes users' emotions and uses the emotion data to further personalize the user experience.

[1166] User data collection and analysis

[1167] The server collects and analyzes data such as the user's search terms, browsing history, and past purchase history, as well as emotional data. This data is used to understand not only the user's preferences, purchasing trends, and price perception, but also changes in their emotions.

[1168] When a user searches, the device sends emotional data along with the search terms to the server in real time. For example, when a user searches for "vintage watches," the emotion engine recognizes "interest" from facial expressions and voice at the time and sends this information to the server. Based on this data, the server generates and displays more accurate product information.

[1169] Smart Pricing

[1170] The server analyzes the price data of similar products on the market based on the photos and descriptions of the listed items, as well as emotional data, to calculate an appropriate price. For example, if a seller is listing an iPhone 12, the server analyzes the market price data of other similar products and the seller's emotional state, and suggests a price of 70,000 yen. If the seller is having difficulty setting a price, the emotion engine will recognize their anxiety, and the server can send them price advice or a message of support.

[1171] Improved matching accuracy

[1172] The server collects user feedback and emotional data and updates the matching algorithm based on that information. For example, when a user provides feedback such as "This price is appropriate" or "I think it could be cheaper," the emotional engine recognizes their satisfaction or dissatisfaction at that time and sends that data to the server. The server then uses this data to improve the accuracy of the next price suggestion and matching.

[1173] Predicting potential needs and recommending products

[1174] The server predicts the user's potential needs based on the user's past behavioral data, emotional data, and market trend data. It then generates and notifies the user of a list of optimal products. For example, if a user frequently searches for "camera" and the emotion engine recognizes the user's heightened emotions, the server will recommend related camera accessories and new camera models.

[1175] The user's device will notify and display this recommended product list, allowing the user to find products that match their potential needs based on their emotions.

[1176] Negotiation support function

[1177] The server receives emotion data along with a negotiation request from a prospective buyer, analyzes it, and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a prospective buyer requests a slight price reduction and the emotion is recognized as a strong desire, the server generates a corresponding negotiation proposal and notifies the prospective buyer and the seller.

[1178] The devices of the buyer and seller display negotiation proposals in real time, allowing each party to negotiate based on their emotions according to the situation. As a result, the transaction proceeds smoothly and it becomes easier to reach terms that satisfy the user emotionally.

[1179] By integrating these functions, the system of this invention can provide personalized product suggestions and pricing according to the user's needs, and support negotiations and transactions with consideration for emotions, which is expected to revitalize the entire reuse market.

[1180] The processing flow will be explained below.

[1181] User data collection and analysis

[1182] Step 1:

[1183] A user opens the Reuse Market app on their device, types "vintage watches" into the search bar, and presses the search button.

[1184] Step 2:

[1185] The device sends the entered search words and "interest" emotion data analyzed by the emotion engine from the user's facial expressions and voice to the server.

[1186] Step 3:

[1187] The server stores the received search terms and emotion data in a database and compares them with past search history, purchase history, and browsing history.

[1188] Step 4:

[1189] The server analyzes the user's interests, purchasing trends, and emotional changes based on the stored data, and generates and displays appropriate product information.

[1190] Smart Pricing

[1191] Step 1:

[1192] To list an iPhone 12, a seller enters product photos and descriptions from their device and presses the list button.

[1193] Step 2:

[1194] The device sends product information and "anxiety" emotion data analyzed by an emotion engine from the seller's facial expressions and voice to the server.

[1195] Step 3:

[1196] The server analyzes market price data for similar products based on the transmitted product information and emotion data.

[1197] Step 4:

[1198] The server calculates the optimal price as a result of the analysis and generates price advice and supportive messages according to the seller's emotional state.

[1199] Step 5:

[1200] The server transmits the recommended price and a support message to the seller's terminal, and the terminal displays the price and message to the seller.

[1201] Improved matching accuracy

[1202] Step 1:

[1203] The user provides feedback such as "This price is appropriate" or "It could be cheaper," and the emotion engine simultaneously analyzes the user's emotions, such as "satisfaction" or "dissatisfaction."

[1204] Step 2:

[1205] The device sends user feedback and emotion data to the server.

[1206] Step 3:

[1207] The server stores the received feedback and emotion data and adds it to a database to be analyzed.

[1208] Step 4:

[1209] The server uses this new data to update its matching algorithm and improve the accuracy of its next price suggestions and recommended products.

[1210] Predicting potential needs and recommending products

[1211] Step 1:

[1212] The server analyzes the user's past behavioral data, stored emotion data, and market trend data to predict the user's potential needs.

[1213] Step 2:

[1214] The server generates a list of products that are best suited to the user based on predicted needs and sentiment data.

[1215] Step 3:

[1216] The server transmits the generated recommended product list to the user's terminal, and the terminal notifies the user of an emotion-inducing message related to the recommended products.

[1217] Negotiation support function

[1218] Step 1:

[1219] A prospective purchaser sends a price reduction request for the product.

[1220] Step 2:

[1221] The device sends this request along with "strong desire" emotion data analyzed by the emotion engine from the prospective buyer's facial expressions and tone of voice to the server.

[1222] Step 3:

[1223] The server analyzes the request and sentiment data and generates appropriate negotiation proposals based on past negotiation data and market price data.

[1224] Step 4:

[1225] The server sends the generated negotiation proposal and a message according to the emotion to the prospective buyer and the seller.

[1226] Step 5:

[1227] The devices of the prospective buyer and seller display negotiation proposals and messages in real time, and each party proceeds with the negotiations with emotions appropriate to the situation.

[1228] Step 6:

[1229] The user (seller) sets a new price based on the proposal, and the transaction is completed when the potential buyer agrees to it.

[1230] These steps allow the system of the present invention to optimize the user's searching, listing, and negotiating experience based on emotions.

[1231] Example 2

[1232] 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."

[1233] Conventional e-commerce systems use users' search and purchase histories to suggest products and set prices, but this often does not adequately address users' emotions and needs. Furthermore, pricing and negotiation support sometimes ignore the emotions of sellers and potential buyers, resulting in lower user satisfaction. To address these issues, a more personalized system that incorporates user emotional data is needed, offering higher levels of satisfaction.

[1234] 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 means for collecting and analyzing the user's search history, browsing history, and purchase history, means for analyzing the price of the listed product based on the price data of other similar products to calculate the appropriate price, and means for collecting and analyzing the user's emotional data. This allows the user's emotional data to be analyzed together with their past behavioral data, enabling more accurate product proposals, pricing, and negotiation support.

[1235] "User search history" is a record of the user's search behavior within the system.

[1236] "Browse history" is a record of the products a user has viewed within the system.

[1237] "Purchase history" is a record of products a user has previously purchased within the system.

[1238] A "fair price" is a fair and reasonable price calculated based on market data and price data for similar products.

[1239] "Emotional data" refers to emotional information analyzed from the user's facial expressions, voice, etc.

[1240] "Feedback" refers to users' evaluations and opinions of the products and services they provide.

[1241] A "matching algorithm" is a calculation method for selecting products and services that match a user's requirements and preferences.

[1242] "Latent needs" are needs or desires that are not explicitly expressed by the user but can be predicted from their behavioral and emotional data.

[1243] "Product List" means a list of products selected for offering to users.

[1244] A "negotiation request" is a request by a prospective purchaser to change the product price.

[1245] A "negotiation proposal" is a proposal for price and terms of trade generated by the server in response to a negotiation request.

[1246] The system according to the present invention is an advanced system that collects user search history, browsing history, purchase history, and emotional data, and uses this data to propose products, set prices, and assist in negotiations. The following describes how to specifically implement this system.

[1247] First, to generate the program for this system, the following main hardware and software are required: Hardware includes a server and user devices (PCs, smartphones, tablets, etc.), while software includes an emotion recognition engine (e.g., Microsoft Emotion API, Google Cloud Speech-to-Text API), a database (e.g., MongoDB, PostgreSQL), machine learning algorithms (e.g., TensorFlow, PyTorch), and natural language processing technology (e.g., SpaCy).

[1248] The server integrates and analyzes the user's search history, browsing history, and purchase history, as well as emotional data collected from facial expressions and voice. This allows the system to understand not only the user's preferences and purchasing trends, but also changes in their emotions. For example, if a user searches for "vintage watches" and their facial expression indicates "interest," the server receives and analyzes this data in real time.

[1249] Based on the analysis results, the server searches the product database, generates a list of products that are best suited to the user, and notifies the device. This allows users to quickly find the products they are interested in. For example, products related to "vintage watches" are displayed preferentially, and information such as price, quality rating, and seller rating is provided.

[1250] The server analyzes the price of a listed item based on the price data of other similar items and the seller's emotional data to calculate an appropriate price. For example, when a seller tries to list an iPhone 12, the server analyzes the market price data of other similar items and suggests a recommended price of 70,000 yen. If the seller is feeling anxious, the emotion recognition engine will recognize this and the server can send an encouraging message.

[1251] The server collects user feedback and emotional data and updates the matching algorithm based on this. For example, if a user provides feedback such as "This price is reasonable" or "I think it could be cheaper," and the user's emotional response is satisfied, the server will improve the algorithm for the next price and product suggestion.

[1252] Furthermore, the server can analyze the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. For example, if the user frequently searches for "camera" and shows high emotional responses, the server can recommend camera accessories and new camera models based on that information. These recommended product lists are then sent to the user's device.

[1253] Finally, the server analyzes the buyer's negotiation request and emotional data, and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a buyer requests a slight price reduction and the emotion is recognized as a strong desire, the server generates a corresponding negotiation proposal and notifies the buyer and seller. Displaying the negotiation proposal in real time makes it easier to reach a deal that satisfies both parties.

[1254] As a concrete example, the generative AI model can be used with the following prompt sentence:

[1255] Example prompt:

[1256] "If a user searches for vintage watches and the emotion engine recognizes their current interest, how would the server generate and display product information?"

[1257] As a result, the system of the present invention can make product proposals and set prices personalized to the user's needs, and further support negotiations by taking emotions into consideration, thereby achieving more satisfying transactions.

[1258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1259] Step 1:

[1260] A user enters a search term, such as "vintage watches," into the device. The input includes the search term (e.g., "vintage watches") and facial and vocal emotion data collected using the device's camera and microphone. The device's software uses an emotion recognition engine (e.g., Microsoft Emotion API, Google Cloud Speech-to-Text API) to convert the facial and vocal data into emotion data such as "interest." The output is a combination of the search term and the emotion data.

[1261] Step 2:

[1262] The terminal transmits the user's search words and collected emotion data to the server in real time using SSL / TLS encryption protocol. The input is the search words and emotion data, and the output after transmission is the data safely reaching the server.

[1263] Step 3:

[1264] The server searches a database based on the received search term and emotion data. The input is a search term (e.g., "vintage watch") and emotion data (e.g., "interest"). The server searches a large product database (e.g., MongoDB) to obtain information on related products. Specifically, it uses machine learning algorithms (e.g., TensorFlow, PyTorch) to search for and prioritize related products. The output is a list of optimal products.

[1265] Step 4:

[1266] The server notifies the terminal of the generated product list. The input is the optimal product list, and the output is to display it on the target user's terminal. Specifically, the server encodes the product list in JSON format and sends it to the terminal.

[1267] Step 5:

[1268] The user browses the presented product list and clicks on a product page. The input is the ID of the individual product selected from the product list. The terminal requests detailed information about the selected product from the server and displays the product detail page to the user as output. Specifically, the terminal captures the user's click event and sends a detailed information request to the server.

[1269] Step 6:

[1270] When a seller attempts to list a new item, the server calculates the appropriate price based on product information and emotional data. The input is product information (e.g., "iPhone 12") and the seller's emotional data (e.g., "anxiety"). The server analyzes market data and price data for similar products to calculate the appropriate price that will give the seller peace of mind. The output is a recommended price (e.g., "70,000 yen"). Specific operations involve using a machine learning model that takes into account emotional data along with statistical analysis.

[1271] Step 7:

[1272] The user provides feedback on the price and product evaluation. The input is the user's feedback (e.g., "This price is appropriate") and facial expression data at that time (e.g., "Satisfied"). The device transmits the feedback and emotional data to the server in real time, and the output is the data received by the server. Specifically, the device uses a feedback form and an emotion-recognition camera.

[1273] Step 8:

[1274] The server updates the matching algorithm based on the received feedback and emotion data. The input is the feedback and emotion data. Using a data analysis engine, the algorithm for the next price or product suggestion is adjusted, and the output is the updated algorithm. Specifically, the feedback data is fed into a machine learning model to optimize the algorithm parameters.

[1275] Step 9:

[1276] The server analyzes the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. The input is past behavioral data and emotional data. A machine learning algorithm is used to predict the user's purchasing intentions, and the output is a product list based on the predicted needs. Specific operations include time series analysis and clustering techniques.

[1277] Step 10:

[1278] The server generates an appropriate negotiation proposal based on the negotiation request and emotional data from the prospective buyer. The input is the prospective buyer's request (e.g., "I would like to ask for a smaller price reduction") and emotional data (e.g., "I strongly desire it"). The server analyzes past negotiation data and market price data, generates an appropriate negotiation proposal, and notifies the prospective buyer and seller as output. In concrete terms, the server integrates and uses an emotion recognition algorithm and a negotiation support algorithm.

[1279] (Application example 2)

[1280] 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."

[1281] Modern online shopping sites are required to make more personalized product recommendations and set fair prices by effectively utilizing not only users' search and purchase histories but also their emotional data. Generating negotiation proposals based on users' emotional state and improving the success rate of negotiations is also an important challenge. However, conventional systems have had difficulty fully integrating and effectively utilizing these functions.

[1282] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history; means for analyzing the price of a listed product based on price data of other similar products to calculate an appropriate price; means for collecting user feedback and updating a matching algorithm based on the feedback; means for analyzing the user's past behavioral data and market trend data to predict the user's potential needs; means for generating a product list based on the predicted needs and notifying the user of the list; means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices; means for supporting negotiations based on requests and proposals submitted by the user; means for analyzing the user's emotional data and making personalized product proposals and pricing based on the analyzed data; and means for making appropriate negotiation proposals when providing negotiation support based on the user's current emotional state. This enables personalized product proposals, pricing, and negotiation support that take the user's emotions into consideration.

[1283] "User search history" is a record of keywords and phrases that a user has searched for on the Internet.

[1284] "Browsing history" is a record of the pages a user has visited on a website or application.

[1285] "Purchase history" is a record of the products and services a user has actually purchased.

[1286] "Price data of similar products" refers to price information of the same or similar products traded in the market.

[1287] "Feedback" refers to opinions and ratings provided by users, which is information used to improve and adjust the system.

[1288] A "matching algorithm" is a calculation method for suggesting optimal products and services based on a user's preferences and needs.

[1289] "Past behavioral data" refers to historical information about searches, browsing, purchases, etc. that a user has conducted.

[1290] "Market trend data" refers to information about overall market trends and user behavior trends.

[1291] "Latent needs" are requests for products or services that users are not yet clearly aware of but may need in the future.

[1292] A "product list" is a list of multiple products or services that the system suggests to the user.

[1293] A "negotiation request" is a request for negotiations sent by a prospective buyer to a seller regarding price and conditions.

[1294] A "negotiation proposal" is a proposal regarding price and other terms generated in response to a negotiation request.

[1295] "Emotion data" is information about the user's emotional state that can be inferred from facial expressions, voice, etc.

[1296] "Personalization" refers to providing customized suggestions and settings based on individual user preferences and behavior.

[1297] The present invention provides a system that collects users' search history, browsing history, purchase history, and emotional data, and uses this data to make personalized product proposals and set prices, as well as provide negotiation support.

[1298] User data collection and analysis

[1299] The server collects information on the keywords the user has searched for, the pages they have viewed, and the products they have purchased in the past. In addition, the emotion engine analyzes emotional data from the user's facial expressions and voice, and collects this data as well. The device sends data to the server in real time when the user performs a search. For example, if a user searches for "vintage watches," the emotion engine recognizes "interests" from their facial expressions and voice at the time and sends this data to the server. The server uses this data to analyze the user's preferences and purchasing trends, and generates appropriate product information to display to the user.

[1300] Smart Pricing

[1301] The server analyzes the price data of similar products on the market based on the photos and descriptions of the listed items, as well as emotional data, and calculates an appropriate price. For example, if a seller is listing a smartphone, the server analyzes the market price data of other similar products and the seller's emotional state, and suggests a price of 50,000 yen. If the seller is having difficulty setting a price, the emotion engine will recognize their anxiety, and the server can send them price advice or a message of support.

[1302] Improved matching accuracy

[1303] The server collects user feedback and emotional data and updates the matching algorithm based on that information. For example, while a user provides feedback such as "This price is reasonable" or "I think it could be cheaper," the emotional engine recognizes their satisfaction or dissatisfaction at that time. Based on this data, the server uses it to improve the accuracy of the next price suggestion and matching.

[1304] Predicting potential needs and recommending products

[1305] The server predicts a user's potential needs based on the user's past behavioral data, emotional data, and market trend data. For example, if a user frequently searches for "camera" and the emotion engine recognizes the user's heightened emotions, the server will recommend related camera accessories and new camera models. The user's device will notify and display a list of these recommended products, allowing the user to easily find products that meet their potential needs.

[1306] Negotiation support function

[1307] The server receives and analyzes emotional data along with a negotiation request from a potential buyer. For example, if a potential buyer requests a slight price reduction, and the server recognizes this emotion as a strong desire, it generates a corresponding negotiation proposal and notifies the potential buyer and seller in real time. The seller's device displays a negotiation proposal that takes into account the potential buyer's emotional state, allowing negotiations to proceed based on emotions appropriate to each situation. This allows for smoother transactions and makes it easier to reach transaction terms that satisfy the user emotionally.

[1308] By integrating the above functions, the system of the present invention can provide personalized product suggestions and pricing based on user needs, and emotionally support negotiations and transactions, which is expected to revitalize the entire online market.

[1309] Prompt Sentence Examples

[1310] Based on the user's search history, use the search term "vintage watches" and its sentiment data to perform the following tasks:

[1311] Calculating fair prices from market data

[1312] Recommend related products

[1313] Generate negotiation support proposals

[1314] Also, optimize your matching algorithm based on feedback.

[1315] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1316] Step 1:

[1317] When a user searches, the device sends search terms along with emotional data captured from facial expressions and voice to the server in real time. The search terms and emotional data are used as inputs, and the data is then processed to track the user's interests. As an output, the server stores the information in a database for analyzing the user's preferences and interests.

[1318] Step 2:

[1319] The server collects and analyzes users' search, browsing, and purchase histories along with emotional data. Using this history and emotional data as input, data calculations are performed to identify specific purchasing trends and patterns. As output, personalized product information is generated based on the user's purchasing trends and preferences.

[1320] Step 3:

[1321] When setting the price of a newly listed item, the server analyzes the price data of similar items on the market and the seller's sentiment data. Using the product details, market data, and sentiment data as input, the server performs data calculations to calculate an appropriate price. As an output, a suggested selling price is displayed on the product page and notified to the seller.

[1322] Step 4:

[1323] The server collects user feedback and sentiment data and uses it to update the matching algorithm. Using the feedback and sentiment data as input, it performs data calculations to adjust and improve the algorithm. The output is an improved matching algorithm, which is reflected in future searches and recommendations.

[1324] Step 5:

[1325] The server analyzes the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. Using the behavioral data, emotional data, and trend data as input, data calculations are performed to identify potential needs. As output, a product list based on the predicted potential needs is generated and notified to the user.

[1326] Step 6:

[1327] When a negotiation request is received from a potential buyer, the server analyzes the emotion data and generates an appropriate negotiation proposal based on past negotiation data and market price data. Using the negotiation request, emotion data, past negotiation data, and price data as input, data calculations are performed to propose optimal negotiation terms. As an output, the generated negotiation proposal is notified to the potential buyer and seller in real time.

[1328] Step 7:

[1329] The user's device displays the personalized product list and negotiation proposals sent from the server to the user, allowing the user to proceed with the purchase or negotiation based on the presented information. Using the data sent from the server as input, the data is processed to display appropriately to the user. As output, an interface is generated for the user to view or operate.

[1330] 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.

[1331] 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.

[1332] 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.

[1333] [Fourth embodiment]

[1334] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1335] 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.

[1336] 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).

[1337] 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.

[1338] 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.

[1339] 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).

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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."

[1347] The system of the present invention has functions for collecting users' search history, browsing history, and purchase history, for analyzing the prices of listed products and calculating appropriate prices, for collecting feedback from users and updating the matching algorithm, for predicting users' potential needs and recommending products, and for generating negotiation proposals based on negotiation requests and supporting negotiations.

[1348] User data collection and analysis

[1349] The server collects and analyzes data such as user search terms, browsing history, and past purchase history, which is used to understand user preferences, purchasing trends, and price sensitivity.

[1350] When a user searches, the device sends the search terms to the server in real time, allowing the server to analyze the latest data. For example, if a user searches for "vintage watches," their search history is sent to the server, and related products are displayed based on the analysis results.

[1351] Smart Pricing

[1352] The server analyzes the price data of similar products on the market based on the photos and description of the listed product and calculates an appropriate price. For example, if a seller wants to list an iPhone 12, the server analyzes the market price data of other similar products, calculates a recommended price of 70,000 yen, and displays it on the seller's device. The seller can use this price as a reference to set their listing price.

[1353] Improved matching accuracy

[1354] The server collects feedback from users and updates the matching algorithm based on that feedback, improving the accuracy of matching over time. For example, when a user provides feedback such as "This price is reasonable" or "I think it's cheaper," that data is stored on the server and used to suggest prices and improve matching accuracy the next time.

[1355] Predicting potential needs and recommending products

[1356] The server predicts users' potential needs based on their past behavioral data and market trend data. It then generates and notifies users of a list of products that best suit their needs. For example, if a user frequently searches for and browses "cameras," the server will recommend related camera accessories and new camera models.

[1357] The user's device will notify and display this list of recommended products, making it easier for the user to find products that meet their potential needs.

[1358] Negotiation support function

[1359] The server receives a negotiation request from a potential buyer and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a potential buyer requests a slight price reduction, the server calculates the appropriate price reduction amount based on past data and notifies the potential buyer and seller of the price reduction proposal.

[1360] The buyer and seller's devices can display negotiation proposals in real time and proceed with the negotiations based on them, which results in a smoother transaction and makes it easier to reach terms that satisfy both users.

[1361] The above is a specific embodiment of the system based on the present invention. By using this system, users can efficiently search for, purchase, and negotiate products, which is expected to revitalize the entire reuse market.

[1362] The processing flow will be explained below.

[1363] User data collection and analysis

[1364] Step 1:

[1365] A user opens the Reuse Market app on their device, types "vintage watches" into the search bar, and presses the search button.

[1366] Step 2:

[1367] The terminal sends the entered search words to the server.

[1368] Step 3:

[1369] The server stores the received search terms in a database and compares them with past search and purchase history.

[1370] Step 4:

[1371] The server analyzes the user's interests and purchasing trends based on the stored data, and generates appropriate information based on the results.

[1372] Smart Pricing

[1373] Step 1:

[1374] To list an iPhone 12, a seller enters product photos and descriptions from their device and presses the list button.

[1375] Step 2:

[1376] The terminal transmits the product information to the server.

[1377] Step 3:

[1378] The server analyzes the market price data of similar products based on the transmitted product information.

[1379] Step 4:

[1380] The server calculates the optimal price as a result of the analysis and generates a recommended price.

[1381] Step 5:

[1382] The server sends the recommended price to the seller's terminal, which displays the price to the seller.

[1383] Improved matching accuracy

[1384] Step 1:

[1385] The user provides feedback such as "This price is good" or "It could be a little cheaper."

[1386] Step 2:

[1387] The device sends the user's feedback to the server.

[1388] Step 3:

[1389] The server stores the received feedback and adds it to a database to be analyzed.

[1390] Step 4:

[1391] The server updates its matching algorithm based on the new feedback, improving accuracy.

[1392] Predicting potential needs and recommending products

[1393] Step 1:

[1394] The server compares the user's past behavioral data (search history, browsing history, purchase history) with market trend data to predict the user's potential needs.

[1395] Step 2:

[1396] The server generates a list of products that best suit the user based on their predicted needs.

[1397] Step 3:

[1398] The server transmits the generated recommended product list to the user's terminal, and the terminal notifies the user of the recommended products.

[1399] Negotiation support function

[1400] Step 1:

[1401] A prospective purchaser sends a price reduction request for the product.

[1402] Step 2:

[1403] The terminal sends this request to the server.

[1404] Step 3:

[1405] The server analyzes the request and generates an appropriate negotiation proposal based on past negotiation data and market prices.

[1406] Step 4:

[1407] The server sends the generated negotiation proposal to the prospective buyer and the seller.

[1408] Step 5:

[1409] The buyer and seller's terminals display negotiation proposals in real time and confirm them with each other.

[1410] Step 6:

[1411] The user (seller) sets a new price based on the proposal, and the transaction is completed when the potential buyer agrees to it.

[1412] Example 1

[1413] 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."

[1414] In current online marketplaces, many systems that effectively utilize users' search and purchase histories to suggest products face challenges in terms of matching accuracy and price accuracy. Furthermore, they lack the ability to accurately predict users' potential needs and support functions to smoothly advance the negotiation process. These challenges must be addressed to increase user satisfaction.

[1415] 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.

[1416] In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history, means for transmitting search terms from the user's terminal in real time, means for analyzing price data of similar products in the market based on information about the listed product and calculating an appropriate price, means for collecting feedback from the user and updating a matching algorithm based on the feedback, means for analyzing past user behavior data and market trend data and predicting the user's potential needs, means for generating a product list based on the predicted needs and notifying the user of the list, means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, and means for supporting negotiations based on requests and proposals transmitted by the user. This enables users to efficiently search for, purchase, and negotiate on products.

[1417] "User" refers to a person who uses the System to search for, view, purchase, or list products.

[1418] "Device" refers to electronic devices such as computers, smartphones, and tablets used by users.

[1419] "Server" refers to a computer system that receives, analyzes, stores, and processes data submitted by users.

[1420] "Search History" refers to a record of keywords and phrases that a User has previously searched for on the System.

[1421] "Browse history" refers to the record of product pages that a user has viewed on the System.

[1422] "Purchase History" refers to the record of products that a User has previously purchased through this System.

[1423] "Feedback" refers to data such as opinions, ratings, and impressions provided by users.

[1424] A "matching algorithm" refers to a calculation method that analyzes user data and product data to suggest the most suitable product to the user.

[1425] "Fair price" refers to the price that is considered appropriate for the product, calculated by the server by analyzing market data.

[1426] "Latent needs" refer to the desires and needs that users may have that are not explicitly stated by users but that can be inferred from past behavioral data and market trend data.

[1427] "Product list" refers to a list of multiple products that the server generates based on the user's potential needs and notifies the user.

[1428] A "negotiation request" refers to a request from a prospective buyer to a seller to change the price or terms of the transaction.

[1429] "Negotiation proposal" refers to the negotiation conditions that the server generates based on past negotiation data and market price data and notifies the prospective buyer and seller.

[1430] The system of the present invention uses multiple hardware and software components to provide functions for collecting and analyzing users' search history, browsing history, and purchase history, analyzing the prices of listed items to calculate appropriate prices, collecting feedback from users to update matching algorithms, predicting users' potential needs and recommending items, and generating negotiation proposals based on negotiation requests to support negotiations.

[1431] Hardware used

[1432] 1. Device: The computer, smartphone, tablet, etc. used by the user.

[1433] 2. Server: A high-performance computer system that collects, analyzes, stores, and processes data.

[1434] Software used

[1435] 1. Data collection program: Software that runs on the device and transmits user operations to a server in real time.

[1436] 2. Data analysis program: An algorithm that runs on the server and analyzes the collected data.

[1437] 3. Feedback collection program: Software that receives and analyzes feedback from users.

[1438] 4. Price analysis program: An algorithm that runs on the server and calculates the fair price based on market data.

[1439] 5. Matching algorithm: A calculation method for suggesting optimal products based on user data.

[1440] 6. Product recommendation generator: Software that predicts users' potential needs and generates product lists.

[1441] 7. Negotiation Support Program: Software that receives negotiation requests, generates appropriate negotiation proposals, and sends them to the user.

[1442] Example of operation

[1443] When a user searches for "vintage watches," the user's device sends the search term to the server in real time. The server collects data including the user's search history, past browsing history, and purchase history, and performs analysis related to the search term "vintage watches." As a result, the server generates a list of related products and displays it on the user's device.

[1444] When a seller tries to list an iPhone 12, the product information entered on the seller's device is sent to the server. The server analyzes the product's photos and description and retrieves pricing data for similar products from other online marketplaces. It then calculates the optimal price of 70,000 yen and provides it to the seller's device. The seller can use this price as a reference to set the selling price of their own product.

[1445] When a user provides feedback, such as "this price is reasonable" or "it should be cheaper," that feedback is sent from the user's device to the server and stored. The server then incorporates this feedback into the next price suggestion and matching accuracy improvement, thereby improving accuracy.

[1446] If a user frequently searches and browses for "camera," the server will use that data to recommend camera-related accessories and new camera models, and these recommendations will be displayed on the user's device and the user will be notified.

[1447] When a prospective buyer sends a negotiation request saying, "I would like to ask for a further price reduction," the server generates an appropriate price reduction proposal based on past negotiation data and market price data, and sends it to the terminals of the prospective buyer and the seller for presentation.

[1448] Prompt Sentence Examples

[1449] "Based on the user's past search history and market trends, predict his potential needs and generate a list of relevant products."

[1450] "Please calculate a fair price based on the description of the listed item and market price data."

[1451] "Update your matching algorithm based on user feedback data."

[1452] As a result, the system of the present invention provides users with optimal product search, purchasing, and negotiation, and is expected to revitalize the entire reuse market.

[1453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1454] Step 1: Collect user data

[1455] 1.1. Submitting search terms

[1456] A user enters a search term into the device's search bar.

[1457] The device sends the entered search term (e.g., "vintage watch") to the server in real time.

[1458] Input: User's search term.

[1459] Data processing: Formalizing and structuring search terms.

[1460] Output: Search word data sent to the server.

[1461] 1.2. Collection of browsing and purchase history

[1462] The server collects data on the product pages the user has previously viewed and the products they have purchased.

[1463] Input: User's browsing history, purchase history.

[1464] Data processing: Organizing data based on time series.

[1465] Output: Structured browsing and purchase history data.

[1466] Step 2: Analyze the data

[1467] 2.1. Analysis of user trends

[1468] The server analyzes the collected search terms, browsing history, and purchase history to identify the user's preferences and purchasing trends.

[1469] Input: Search terms, browsing history, and purchase history data.

[1470] Data processing: Data analysis and pattern recognition.

[1471] Output: Analysis of user preferences and purchasing trends.

[1472] 2.2. Display of related products

[1473] The server generates a list of related products based on the analysis results and notifies the user's device.

[1474] Input: Analysis of user preferences and purchasing trends.

[1475] Data processing: Generate a list of related products.

[1476] Output: Related product list displayed on the device.

[1477] Step 3: Smart Pricing

[1478] 3.1. Product data collection

[1479] The user (seller) enters product information (photo and description) into the terminal and sends it to the server.

[1480] Input: Product information (photo, description).

[1481] Data Processing: Receiving product information and converting it into data for analysis.

[1482] Output: Structured product data.

[1483] 3.2. Market price data collection

[1484] The server collects price data for other similar products in the market.

[1485] Input: Product information, matching market data.

[1486] Data processing: market data collection and matching.

[1487] Output: Price data for similar products.

[1488] 3.3. Calculating the fair price

[1489] The server calculates the fair price of the auction item based on the market price data.

[1490] Input: Price data for similar products.

[1491] Data processing: Calculating fair prices.

[1492] Output: Reasonably priced and affordable.

[1493] 3.4. Recommended Price

[1494] The server notifies the seller's terminal of the calculated fair price.

[1495] Enter: Fair Price.

[1496] Data processing: Formalization of pricing data.

[1497] Output: The suggested price displayed on the seller's device.

[1498] Step 4: Gather feedback and update the algorithm

[1499] 4.1. Sending Feedback

[1500] Users enter feedback about prices and product ratings into the device.

[1501] Input: Feedback content.

[1502] Data processing: Formalization of feedback data.

[1503] Output: Feedback data sent to the server.

[1504] 4.2. Gathering Feedback for Algorithm Updates

[1505] The server accumulates and stores the collected feedback data.

[1506] Input: Feedback data.

[1507] Data processing: Accumulation and analysis of feedback data.

[1508] Output: The updated matching algorithm.

[1509] Step 5: Anticipating potential needs and recommending products

[1510] 5.1. Analysis of behavioral data

[1511] The server analyzes users' past behavioral data and market trend data.

[1512] Inputs: Behavioral data, market trend data.

[1513] Data processing: Data analysis and pattern recognition.

[1514] Output: Prediction of potential user needs.

[1515] 5.2. Creating a Product List

[1516] The server generates a list of related products based on the predicted user needs and notifies the user's terminal.

[1517] Input: Predicted potential needs.

[1518] Data processing: Product list generation.

[1519] Output: A list of recommended products displayed on the device.

[1520] Step 6: Negotiation support

[1521] 6.1. Sending a Negotiation Request

[1522] The prospective buyer sends a negotiation request from the terminal.

[1523] Input: Negotiation request.

[1524] Data processing: Request formatting and storage.

[1525] Output: The negotiation request sent to the server.

[1526] 6.2. Generating Negotiation Proposals

[1527] The server generates appropriate negotiation proposals based on past negotiation data and market data.

[1528] Inputs: Negotiation request, historical negotiation data, market data.

[1529] Data processing: Generating negotiation proposals.

[1530] Output: Negotiation proposal sent to the buyer's and seller's devices.

[1531] This will enable each function of the system to be realized, enabling users to efficiently search for, purchase, and negotiate products.

[1532] (Application example 1)

[1533] 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."

[1534] Traditional online shopping sites typically recommend products based on users' search and purchase histories, but this method is often inaccurate. In particular, it is difficult to accurately predict and recommend products that users will be interested in, which can result in poor user experience. Furthermore, there is a lack of functionality to automatically generate appropriate negotiation proposals based on negotiation requests and facilitate smooth negotiations between users. This creates the challenge of finding transaction terms that satisfy users.

[1535] 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.

[1536] In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history, means for analyzing the price of a listed item based on price data of other similar items and calculating an appropriate price, means for collecting user feedback and updating a matching algorithm based on the feedback, means for analyzing the user's past behavioral data and market trend data and predicting the user's potential needs, means for generating a product list based on the predicted needs and notifying the user of the list, means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices, means for supporting negotiations based on requests and proposals submitted by the user, means for providing optimal prices and product recommendations based on the user's behavioral data, and means for generating prompt messages using a generative AI model that has learned the user's purchasing tendencies. This enables efficient product recommendations, calculation of appropriate prices, and negotiation support based on the user's behavioral data, thereby significantly improving the user experience.

[1537] "Search history" is a record of a user's past search queries within websites and applications.

[1538] "Browsing history" is a record of data about web pages and product pages that a user has viewed in the past.

[1539] "Purchase history" is a record of data on products purchased by a user in the past.

[1540] "Analysis" is the process of extracting meaning from collected data using statistical or machine learning algorithms.

[1541] "Price data for similar products" refers to price information for products of the same type or with similar characteristics that exist in the market.

[1542] A "fair price" is a product price that is determined statistically or algorithmically to be fair and appropriate to the market.

[1543] "Feedback" refers to opinions and evaluation data provided by users.

[1544] A "matching algorithm" is a calculation procedure that recommends optimal products and services based on user data.

[1545] "Past behavioral data" refers to the user's accumulated behavioral records, such as search history, browsing history, and purchase history.

[1546] "Market trend data" is data that includes information on current market trends and popular products.

[1547] "Latent needs" are needs that are inferred from users' behavior and past data, even if they are not explicitly stated.

[1548] A "negotiation request" is a request sent by a potential purchaser to change the product price or adjust the terms.

[1549] A "negotiation proposal" is a proposal for negotiation that is generated based on past data and market prices.

[1550] A "generative AI model" is a model trained by artificial intelligence that performs generative tasks based on user behavior and tendencies.

[1551] A "prompt" is a sentence output by a generative AI model that suggests the next action or suggestion to the user.

[1552] The present invention relates to a system that collects user behavior data on an online shopping site, calculates product prices based on the collected data, recommends optimal products, and supports negotiations. Specific embodiments of the system are described below.

[1553] System Configuration

[1554] Hardware

[1555] The system of the present invention comprises the following hardware:

[1556] Smartphone: A device where users can enter data and receive product recommendations and negotiation offers.

[1557] Server: Hardware for collecting data, analyzing it, running generative AI models, and generating prompts to notify the user.

[1558] software

[1559] The system of the present invention uses the following software:

[1560] Python: A programming language for data collection, analysis, prediction, and proposals.

[1561] Keras: A framework that uses neural networks to learn from user data and build generative AI models.

[1562] Scikit-learn: A library for data preprocessing such as clustering and standardization.

[1563] Data collection and analysis

[1564] The server collects the user's search history, browsing history, and purchase history, and analyzes the user's behavior based on this. Specifically, when a user searches, the search terms are sent from the device in real time, and the data is analyzed by the server. For example, if a user searches for "vintage watches," the server saves the search history and displays related products.

[1565] Smart Pricing

[1566] The server calculates the appropriate price based on the description of the listed product and price data for similar products in the market. For example, if an iPhone 12 is listed, the server analyzes market price data, calculates a recommended price of 70,000 yen, and displays this on the seller's device.

[1567] Improved matching accuracy

[1568] The server collects user feedback and updates the matching algorithm based on it, improving the accuracy of matching over time. For example, when a user provides feedback such as "This price is reasonable" or "I think it's cheaper," that data is stored on the server and used for the next price suggestion and product recommendation.

[1569] Predicting potential needs and recommending products

[1570] The server predicts the user's potential needs based on past user behavior data and market trend data, and generates optimal product listings. For example, if a user frequently searches and browses for "cameras," it will recommend related camera accessories and new camera models.

[1571] Negotiation support function

[1572] The server receives negotiation requests from potential buyers and generates appropriate negotiation proposals based on past negotiation data and market price data. For example, if a potential buyer requests a slight price reduction, the server calculates the amount of price reduction based on past data and notifies the potential buyer and seller.

[1573] Generate prompt statement

[1574] The generative AI model learns user behavior data and generates prompts. For example, if a user frequently searches for cameras, it generates a prompt such as, "If you're looking for a new camera, how about this model?" Specific examples of prompts that can be provided include:

[1575] plain

[1576] If you're looking for a new camera, how about this model?

[1577] Recommended Products: [Product List]

[1578] As a result, recommendations, price calculations, and negotiation support can be efficiently performed based on user behavior data, improving the user experience.

[1579] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1580] Step 1:

[1581] When a user searches for a product, the device sends a search query to the server. The input is the user's search term (e.g., "vintage watch"). The server receives this search query and stores it in a database. This updates the user's recent search history.

[1582] Step 2:

[1583] The server collects and analyzes the user's search history, browsing history, and purchase history. The input is the user's behavioral data saved from previous visits. The server analyzes this data to extract the user's preferences and behavioral patterns. The analysis results reveal the user's tastes and purchasing tendencies.

[1584] Step 3:

[1585] The price of the listed item is analyzed and a fair price is calculated. Inputs include the product description, photos, and market price data for similar items. The server analyzes the market price data, calculates a fair price, and displays it on the seller's device. For example, for an iPhone 12 listing, a suggested price of 70,000 yen is calculated.

[1586] Step 4:

[1587] Collecting user feedback. The input is the feedback provided by the user (e.g., "This price is reasonable"). The server receives this feedback and stores it in a database. This feedback is then used for the next algorithm update.

[1588] Step 5:

[1589] The server updates the matching algorithm based on the feedback data. The input is the collected feedback data. The server uses this data to adjust the parameters of the algorithm and improve the matching accuracy.

[1590] Step 6:

[1591] The server analyzes the user's past behavioral data and market trend data to predict the user's potential needs. The inputs include the user's search history, browsing history, purchase history, and market trend data. The server analyzes this data and generates the optimal product list for the user.

[1592] Step 7:

[1593] The server generates a product list based on the predicted needs and notifies the user. The input is the result of predicting potential needs. The server generates a product list based on this result and notifies the device. For example, if cameras are frequently searched for, related camera accessories will be recommended.

[1594] Step 8:

[1595] Receives a negotiation request from a potential buyer. The input is the buyer's request (e.g., "I would like a lower price"). The server receives this request and stores it in a database.

[1596] Step 9:

[1597] The server generates an appropriate negotiation proposal based on past negotiation data and market price data. The inputs are a negotiation request, past negotiation data, and current market price data. The server calculates an appropriate price reduction amount based on this data and generates a proposal.

[1598] Step 10:

[1599] The server notifies the buyer and seller of the generated negotiation proposal. The input is the generated negotiation proposal. The server notifies the terminal of this proposal and progresses the negotiation. This allows the transaction to proceed smoothly and improves user satisfaction.

[1600] The above are the specific processing steps in the system of the present invention. These steps enable efficient product recommendations, price calculations, and negotiation support based on user behavior data.

[1601] 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.

[1602] The system of the present invention has functions for collecting and analyzing users' search history, browsing history, and purchase history, analyzing the prices of listed items to calculate appropriate prices, collecting user feedback to update the matching algorithm, predicting users' potential needs and recommending items, and generating negotiation proposals based on negotiation requests to support negotiations.In addition, the system is equipped with an emotion engine that recognizes users' emotions and uses the emotion data to further personalize the user experience.

[1603] User data collection and analysis

[1604] The server collects and analyzes data such as the user's search terms, browsing history, and past purchase history, as well as emotional data. This data is used to understand not only the user's preferences, purchasing trends, and price perception, but also changes in their emotions.

[1605] When a user searches, the device sends emotional data along with the search terms to the server in real time. For example, when a user searches for "vintage watches," the emotion engine recognizes "interest" from facial expressions and voice at the time and sends this information to the server. Based on this data, the server generates and displays more accurate product information.

[1606] Smart Pricing

[1607] The server analyzes the price data of similar products on the market based on the photos and descriptions of the listed items, as well as emotional data, to calculate an appropriate price. For example, if a seller is listing an iPhone 12, the server analyzes the market price data of other similar products and the seller's emotional state, and suggests a price of 70,000 yen. If the seller is having difficulty setting a price, the emotion engine will recognize their anxiety, and the server can send them price advice or a message of support.

[1608] Improved matching accuracy

[1609] The server collects user feedback and emotional data and updates the matching algorithm based on that information. For example, when a user provides feedback such as "This price is appropriate" or "I think it could be cheaper," the emotional engine recognizes their satisfaction or dissatisfaction at that time and sends that data to the server. The server then uses this data to improve the accuracy of the next price suggestion and matching.

[1610] Predicting potential needs and recommending products

[1611] The server predicts the user's potential needs based on the user's past behavioral data, emotional data, and market trend data. It then generates and notifies the user of a list of optimal products. For example, if a user frequently searches for "camera" and the emotion engine recognizes the user's heightened emotions, the server will recommend related camera accessories and new camera models.

[1612] The user's device will notify and display this recommended product list, allowing the user to find products that match their potential needs based on their emotions.

[1613] Negotiation support function

[1614] The server receives emotion data along with a negotiation request from a prospective buyer, analyzes it, and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a prospective buyer requests a slight price reduction and the emotion is recognized as a strong desire, the server generates a corresponding negotiation proposal and notifies the prospective buyer and the seller.

[1615] The devices of the buyer and seller display negotiation proposals in real time, allowing each party to negotiate based on their emotions according to the situation. As a result, the transaction proceeds smoothly and it becomes easier to reach terms that satisfy the user emotionally.

[1616] By integrating these functions, the system of this invention can provide personalized product suggestions and pricing according to the user's needs, and support negotiations and transactions with consideration for emotions, which is expected to revitalize the entire reuse market.

[1617] The processing flow will be explained below.

[1618] User data collection and analysis

[1619] Step 1:

[1620] A user opens the Reuse Market app on their device, types "vintage watches" into the search bar, and presses the search button.

[1621] Step 2:

[1622] The device sends the entered search words and "interest" emotion data analyzed by the emotion engine from the user's facial expressions and voice to the server.

[1623] Step 3:

[1624] The server stores the received search terms and emotion data in a database and compares them with past search history, purchase history, and browsing history.

[1625] Step 4:

[1626] The server analyzes the user's interests, purchasing trends, and emotional changes based on the stored data, and generates and displays appropriate product information.

[1627] Smart Pricing

[1628] Step 1:

[1629] To list an iPhone 12, a seller enters product photos and descriptions from their device and presses the list button.

[1630] Step 2:

[1631] The device sends product information and "anxiety" emotion data analyzed by an emotion engine from the seller's facial expressions and voice to the server.

[1632] Step 3:

[1633] The server analyzes market price data for similar products based on the transmitted product information and emotion data.

[1634] Step 4:

[1635] The server calculates the optimal price as a result of the analysis and generates price advice and supportive messages according to the seller's emotional state.

[1636] Step 5:

[1637] The server transmits the recommended price and a support message to the seller's terminal, and the terminal displays the price and message to the seller.

[1638] Improved matching accuracy

[1639] Step 1:

[1640] The user provides feedback such as "This price is appropriate" or "It could be cheaper," and the emotion engine simultaneously analyzes the user's emotions, such as "satisfaction" or "dissatisfaction."

[1641] Step 2:

[1642] The device sends user feedback and emotion data to the server.

[1643] Step 3:

[1644] The server stores the received feedback and emotion data and adds it to a database to be analyzed.

[1645] Step 4:

[1646] The server uses this new data to update its matching algorithm and improve the accuracy of its next price suggestions and recommended products.

[1647] Predicting potential needs and recommending products

[1648] Step 1:

[1649] The server analyzes the user's past behavioral data, stored emotion data, and market trend data to predict the user's potential needs.

[1650] Step 2:

[1651] The server generates a list of products that are best suited to the user based on predicted needs and sentiment data.

[1652] Step 3:

[1653] The server transmits the generated recommended product list to the user's terminal, and the terminal notifies the user of an emotion-inducing message related to the recommended products.

[1654] Negotiation support function

[1655] Step 1:

[1656] A prospective purchaser sends a price reduction request for the product.

[1657] Step 2:

[1658] The device sends this request along with "strong desire" emotion data analyzed by the emotion engine from the prospective buyer's facial expressions and tone of voice to the server.

[1659] Step 3:

[1660] The server analyzes the request and sentiment data and generates appropriate negotiation proposals based on past negotiation data and market price data.

[1661] Step 4:

[1662] The server sends the generated negotiation proposal and a message according to the emotion to the prospective buyer and the seller.

[1663] Step 5:

[1664] The devices of the prospective buyer and seller display negotiation proposals and messages in real time, and each party proceeds with the negotiations with emotions appropriate to the situation.

[1665] Step 6:

[1666] The user (seller) sets a new price based on the proposal, and the transaction is completed when the potential buyer agrees to it.

[1667] These steps allow the system of the present invention to optimize the user's searching, listing, and negotiating experience based on emotions.

[1668] Example 2

[1669] 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."

[1670] Conventional e-commerce systems use users' search and purchase histories to suggest products and set prices, but this often does not adequately address users' emotions and needs. Furthermore, pricing and negotiation support sometimes ignore the emotions of sellers and potential buyers, resulting in lower user satisfaction. To address these issues, a more personalized system that incorporates user emotional data is needed, offering higher levels of satisfaction.

[1671] 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 means for collecting and analyzing the user's search history, browsing history, and purchase history, means for analyzing the price of the listed product based on the price data of other similar products to calculate the appropriate price, and means for collecting and analyzing the user's emotional data. This allows the user's emotional data to be analyzed together with their past behavioral data, enabling more accurate product proposals, pricing, and negotiation support.

[1672] "User search history" is a record of the user's search behavior within the system.

[1673] "Browse history" is a record of the products a user has viewed within the system.

[1674] "Purchase history" is a record of products a user has previously purchased within the system.

[1675] A "fair price" is a fair and reasonable price calculated based on market data and price data for similar products.

[1676] "Emotional data" refers to emotional information analyzed from the user's facial expressions, voice, etc.

[1677] "Feedback" refers to users' evaluations and opinions of the products and services they provide.

[1678] A "matching algorithm" is a calculation method for selecting products and services that match a user's requirements and preferences.

[1679] "Latent needs" are needs or desires that are not explicitly expressed by the user but can be predicted from their behavioral and emotional data.

[1680] "Product List" means a list of products selected for offering to users.

[1681] A "negotiation request" is a request by a prospective purchaser to change the product price.

[1682] A "negotiation proposal" is a proposal for price and terms of trade generated by the server in response to a negotiation request.

[1683] The system according to the present invention is an advanced system that collects user search history, browsing history, purchase history, and emotional data, and uses this data to propose products, set prices, and assist in negotiations. The following describes how to specifically implement this system.

[1684] First, to generate the program for this system, the following main hardware and software are required: Hardware includes a server and user devices (PCs, smartphones, tablets, etc.), while software includes an emotion recognition engine (e.g., Microsoft Emotion API, Google Cloud Speech-to-Text API), a database (e.g., MongoDB, PostgreSQL), machine learning algorithms (e.g., TensorFlow, PyTorch), and natural language processing technology (e.g., SpaCy).

[1685] The server integrates and analyzes the user's search history, browsing history, and purchase history, as well as emotional data collected from facial expressions and voice. This allows the system to understand not only the user's preferences and purchasing trends, but also changes in their emotions. For example, if a user searches for "vintage watches" and their facial expression indicates "interest," the server receives and analyzes this data in real time.

[1686] Based on the analysis results, the server searches the product database, generates a list of products that are best suited to the user, and notifies the device. This allows users to quickly find the products they are interested in. For example, products related to "vintage watches" are displayed preferentially, and information such as price, quality rating, and seller rating is provided.

[1687] The server analyzes the price of a listed item based on the price data of other similar items and the seller's emotional data to calculate an appropriate price. For example, when a seller tries to list an iPhone 12, the server analyzes the market price data of other similar items and suggests a recommended price of 70,000 yen. If the seller is feeling anxious, the emotion recognition engine will recognize this and the server can send an encouraging message.

[1688] The server collects user feedback and emotional data and updates the matching algorithm based on this. For example, if a user provides feedback such as "This price is reasonable" or "I think it could be cheaper," and the user's emotional response is satisfied, the server will improve the algorithm for the next price and product suggestion.

[1689] Furthermore, the server can analyze the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. For example, if the user frequently searches for "camera" and shows high emotional responses, the server can recommend camera accessories and new camera models based on that information. These recommended product lists are then sent to the user's device.

[1690] Finally, the server analyzes the buyer's negotiation request and emotional data, and generates an appropriate negotiation proposal based on past negotiation data and market price data. For example, if a buyer requests a slight price reduction and the emotion is recognized as a strong desire, the server generates a corresponding negotiation proposal and notifies the buyer and seller. Displaying the negotiation proposal in real time makes it easier to reach a deal that satisfies both parties.

[1691] As a concrete example, the generative AI model can be used with the following prompt sentence:

[1692] Example prompt:

[1693] "If a user searches for vintage watches and the emotion engine recognizes their current interest, how would the server generate and display product information?"

[1694] As a result, the system of the present invention can make product proposals and set prices personalized to the user's needs, and further support negotiations by taking emotions into consideration, thereby achieving more satisfying transactions.

[1695] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1696] Step 1:

[1697] A user enters a search term, such as "vintage watches," into the device. The input includes the search term (e.g., "vintage watches") and facial and vocal emotion data collected using the device's camera and microphone. The device's software uses an emotion recognition engine (e.g., Microsoft Emotion API, Google Cloud Speech-to-Text API) to convert the facial and vocal data into emotion data such as "interest." The output is a combination of the search term and the emotion data.

[1698] Step 2:

[1699] The terminal transmits the user's search words and collected emotion data to the server in real time using SSL / TLS encryption protocol. The input is the search words and emotion data, and the output after transmission is the data safely reaching the server.

[1700] Step 3:

[1701] The server searches a database based on the received search term and emotion data. The input is a search term (e.g., "vintage watch") and emotion data (e.g., "interest"). The server searches a large product database (e.g., MongoDB) to obtain information on related products. Specifically, it uses machine learning algorithms (e.g., TensorFlow, PyTorch) to search for and prioritize related products. The output is a list of optimal products.

[1702] Step 4:

[1703] The server notifies the terminal of the generated product list. The input is the optimal product list, and the output is to display it on the target user's terminal. Specifically, the server encodes the product list in JSON format and sends it to the terminal.

[1704] Step 5:

[1705] The user browses the presented product list and clicks on a product page. The input is the ID of the individual product selected from the product list. The terminal requests detailed information about the selected product from the server and displays the product detail page to the user as output. Specifically, the terminal captures the user's click event and sends a detailed information request to the server.

[1706] Step 6:

[1707] When a seller attempts to list a new item, the server calculates the appropriate price based on product information and emotional data. The input is product information (e.g., "iPhone 12") and the seller's emotional data (e.g., "anxiety"). The server analyzes market data and price data for similar products to calculate the appropriate price that will give the seller peace of mind. The output is a recommended price (e.g., "70,000 yen"). Specific operations involve using a machine learning model that takes into account emotional data along with statistical analysis.

[1708] Step 7:

[1709] The user provides feedback on the price and product evaluation. The input is the user's feedback (e.g., "This price is appropriate") and facial expression data at that time (e.g., "Satisfied"). The device transmits the feedback and emotional data to the server in real time, and the output is the data received by the server. Specifically, the device uses a feedback form and an emotion-recognition camera.

[1710] Step 8:

[1711] The server updates the matching algorithm based on the received feedback and emotion data. The input is the feedback and emotion data. Using a data analysis engine, the algorithm for the next price or product suggestion is adjusted, and the output is the updated algorithm. Specifically, the feedback data is fed into a machine learning model to optimize the algorithm parameters.

[1712] Step 9:

[1713] The server analyzes the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. The input is past behavioral data and emotional data. A machine learning algorithm is used to predict the user's purchasing intentions, and the output is a product list based on the predicted needs. Specific operations include time series analysis and clustering techniques.

[1714] Step 10:

[1715] The server generates an appropriate negotiation proposal based on the negotiation request and emotional data from the prospective buyer. The input is the prospective buyer's request (e.g., "I would like to ask for a smaller price reduction") and emotional data (e.g., "I strongly desire it"). The server analyzes past negotiation data and market price data, generates an appropriate negotiation proposal, and notifies the prospective buyer and seller as output. In concrete terms, the server integrates and uses an emotion recognition algorithm and a negotiation support algorithm.

[1716] (Application example 2)

[1717] 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."

[1718] Modern online shopping sites are required to make more personalized product recommendations and set fair prices by effectively utilizing not only users' search and purchase histories but also their emotional data. Generating negotiation proposals based on users' emotional state and improving the success rate of negotiations is also an important challenge. However, conventional systems have had difficulty fully integrating and effectively utilizing these functions.

[1719] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing a user's search history, browsing history, and purchase history; means for analyzing the price of a listed product based on price data of other similar products to calculate an appropriate price; means for collecting user feedback and updating a matching algorithm based on the feedback; means for analyzing the user's past behavioral data and market trend data to predict the user's potential needs; means for generating a product list based on the predicted needs and notifying the user of the list; means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices; means for supporting negotiations based on requests and proposals submitted by the user; means for analyzing the user's emotional data and making personalized product proposals and pricing based on the analyzed data; and means for making appropriate negotiation proposals when providing negotiation support based on the user's current emotional state. This enables personalized product proposals, pricing, and negotiation support that take the user's emotions into consideration.

[1720] "User search history" is a record of keywords and phrases that a user has searched for on the Internet.

[1721] "Browsing history" is a record of the pages a user has visited on a website or application.

[1722] "Purchase history" is a record of the products and services a user has actually purchased.

[1723] "Price data of similar products" refers to price information of the same or similar products traded in the market.

[1724] "Feedback" refers to opinions and ratings provided by users, which is information used to improve and adjust the system.

[1725] A "matching algorithm" is a calculation method for suggesting optimal products and services based on a user's preferences and needs.

[1726] "Past behavioral data" refers to historical information about searches, browsing, purchases, etc. that a user has conducted.

[1727] "Market trend data" refers to information about overall market trends and user behavior trends.

[1728] "Latent needs" are requests for products or services that users are not yet clearly aware of but may need in the future.

[1729] A "product list" is a list of multiple products or services that the system suggests to the user.

[1730] A "negotiation request" is a request for negotiations sent by a prospective buyer to a seller regarding price and conditions.

[1731] A "negotiation proposal" is a proposal regarding price and other terms generated in response to a negotiation request.

[1732] "Emotion data" is information about the user's emotional state that can be inferred from facial expressions, voice, etc.

[1733] "Personalization" refers to providing customized suggestions and settings based on individual user preferences and behavior.

[1734] The present invention provides a system that collects users' search history, browsing history, purchase history, and emotional data, and uses this data to make personalized product proposals and set prices, as well as provide negotiation support.

[1735] User data collection and analysis

[1736] The server collects information on the keywords the user has searched for, the pages they have viewed, and the products they have purchased in the past. In addition, the emotion engine analyzes emotional data from the user's facial expressions and voice, and collects this data as well. The device sends data to the server in real time when the user performs a search. For example, if a user searches for "vintage watches," the emotion engine recognizes "interests" from their facial expressions and voice at the time and sends this data to the server. The server uses this data to analyze the user's preferences and purchasing trends, and generates appropriate product information to display to the user.

[1737] Smart Pricing

[1738] The server analyzes the price data of similar products on the market based on the photos and descriptions of the listed items, as well as emotional data, and calculates an appropriate price. For example, if a seller is listing a smartphone, the server analyzes the market price data of other similar products and the seller's emotional state, and suggests a price of 50,000 yen. If the seller is having difficulty setting a price, the emotion engine will recognize their anxiety, and the server can send them price advice or a message of support.

[1739] Improved matching accuracy

[1740] The server collects user feedback and emotional data and updates the matching algorithm based on that information. For example, while a user provides feedback such as "This price is reasonable" or "I think it could be cheaper," the emotional engine recognizes their satisfaction or dissatisfaction at that time. Based on this data, the server uses it to improve the accuracy of the next price suggestion and matching.

[1741] Predicting potential needs and recommending products

[1742] The server predicts a user's potential needs based on the user's past behavioral data, emotional data, and market trend data. For example, if a user frequently searches for "camera" and the emotion engine recognizes the user's heightened emotions, the server will recommend related camera accessories and new camera models. The user's device will notify and display a list of these recommended products, allowing the user to easily find products that meet their potential needs.

[1743] Negotiation support function

[1744] The server receives and analyzes emotional data along with a negotiation request from a potential buyer. For example, if a potential buyer requests a slight price reduction, and the server recognizes this emotion as a strong desire, it generates a corresponding negotiation proposal and notifies the potential buyer and seller in real time. The seller's device displays a negotiation proposal that takes into account the potential buyer's emotional state, allowing negotiations to proceed based on emotions appropriate to each situation. This allows for smoother transactions and makes it easier to reach transaction terms that satisfy the user emotionally.

[1745] By integrating the above functions, the system of the present invention can provide personalized product suggestions and pricing based on user needs, and emotionally support negotiations and transactions, which is expected to revitalize the entire online market.

[1746] Prompt Sentence Examples

[1747] Based on the user's search history, use the search term "vintage watches" and its sentiment data to perform the following tasks:

[1748] Calculating fair prices from market data

[1749] Recommend related products

[1750] Generate negotiation support proposals

[1751] Also, optimize your matching algorithm based on feedback.

[1752] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1753] Step 1:

[1754] When a user searches, the device sends search terms along with emotional data captured from facial expressions and voice to the server in real time. The search terms and emotional data are used as inputs, and the data is then processed to track the user's interests. As an output, the server stores the information in a database for analyzing the user's preferences and interests.

[1755] Step 2:

[1756] The server collects and analyzes users' search, browsing, and purchase histories along with emotional data. Using this history and emotional data as input, data calculations are performed to identify specific purchasing trends and patterns. As output, personalized product information is generated based on the user's purchasing trends and preferences.

[1757] Step 3:

[1758] When setting the price of a newly listed item, the server analyzes the price data of similar items on the market and the seller's sentiment data. Using the product details, market data, and sentiment data as input, the server performs data calculations to calculate an appropriate price. As an output, a suggested selling price is displayed on the product page and notified to the seller.

[1759] Step 4:

[1760] The server collects user feedback and sentiment data and uses it to update the matching algorithm. Using the feedback and sentiment data as input, it performs data calculations to adjust and improve the algorithm. The output is an improved matching algorithm, which is reflected in future searches and recommendations.

[1761] Step 5:

[1762] The server analyzes the user's past behavioral data, emotional data, and market trend data to predict the user's potential needs. Using the behavioral data, emotional data, and trend data as input, data calculations are performed to identify potential needs. As output, a product list based on the predicted potential needs is generated and notified to the user.

[1763] Step 6:

[1764] When a negotiation request is received from a potential buyer, the server analyzes the emotion data and generates an appropriate negotiation proposal based on past negotiation data and market price data. Using the negotiation request, emotion data, past negotiation data, and price data as input, data calculations are performed to propose optimal negotiation terms. As an output, the generated negotiation proposal is notified to the potential buyer and seller in real time.

[1765] Step 7:

[1766] The user's device displays the personalized product list and negotiation proposals sent from the server to the user, allowing the user to proceed with the purchase or negotiation based on the presented information. Using the data sent from the server as input, the data is processed to display appropriately to the user. As output, an interface is generated for the user to view or operate.

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] 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.

[1773] 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).

[1774] 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.

[1775] 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."

[1776] 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.

[1777] 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).

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] The following is further disclosed regarding the above embodiment.

[1789] (Claim 1)

[1790] A means for collecting and analyzing users' search history, browsing history, and purchase history;

[1791] A means for analyzing the price of the listed product based on price data of other similar products and calculating a fair price;

[1792] A means of collecting user feedback and updating the matching algorithm based on that feedback; and

[1793] A means of analyzing users' past behavioral data and market trend data to predict users' potential needs;

[1794] means for generating a product list based on the predicted needs and notifying the user of the list;

[1795] a means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices;

[1796] means for supporting negotiations based on requests and proposals submitted by users;

[1797] A system including:

[1798] (Claim 2)

[1799] 10. The system of claim 1, wherein the system collects feedback and updates the matching algorithm based on the feedback.

[1800] (Claim 3)

[1801] 2. The system of claim 1, wherein the system predicts a user's potential needs and generates a product list based on the prediction.

[1802] "Example 1"

[1803] (Claim 1)

[1804] A means for collecting and analyzing users' search history, browsing history, and purchase history;

[1805] A means of sending search terms in real time from the user's device;

[1806] A means for analyzing price data of similar products in the market based on the information of the listed product and calculating the appropriate price;

[1807] A means of collecting user feedback and updating the matching algorithm based on that feedback; and

[1808] A means of analyzing users' past behavioral data and market trend data to predict users' potential needs;

[1809] means for generating a product list based on the predicted needs and notifying the user of the list;

[1810] a means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices;

[1811] means for supporting negotiations based on requests and proposals submitted by users;

[1812] A system including:

[1813] (Claim 2)

[1814] 10. The system of claim 1, wherein the system collects feedback and updates the matching algorithm based on the feedback.

[1815] (Claim 3)

[1816] 2. The system according to claim 1, which predicts the user's potential needs and generates and notifies the user of a product list based on the prediction.

[1817] "Application Example 1"

[1818] (Claim 1)

[1819] A means for collecting and analyzing users' search history, browsing history, and purchase history;

[1820] A means for analyzing the price of the listed product based on price data of other similar products and calculating a fair price;

[1821] A means of collecting user feedback and updating the matching algorithm based on that feedback; and

[1822] A means of analyzing users' past behavioral data and market trend data to predict users' potential needs;

[1823] means for generating a product list based on the predicted needs and notifying the user of the list;

[1824] a means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices;

[1825] means for supporting negotiations based on requests and proposals submitted by users;

[1826] A means to provide optimal prices and product recommendations based on user behavior data,

[1827] A means for generating prompt sentences using a generative AI model that has learned the user's purchasing habits;

[1828] A system including:

[1829] (Claim 2)

[1830] 10. The system of claim 1, wherein the system collects feedback and updates the matching algorithm based on the feedback.

[1831] (Claim 3)

[1832] 2. The system of claim 1, wherein the system predicts a user's potential needs and generates a product list based on the prediction.

[1833] "Example 2: Combining Emotion Engines"

[1834] (Claim 1)

[1835] A means for collecting and analyzing users' search history, browsing history, and purchase history;

[1836] A means for analyzing the price of the listed product based on price data of other similar products and calculating a fair price;

[1837] A means for collecting and analyzing user emotional data;

[1838] a means of collecting user feedback and sentiment data and updating the matching algorithm based on that data;

[1839] A means for analyzing users' past behavioral data, emotional data, and market trend data to predict users' potential needs;

[1840] means for generating a product list based on the predicted needs and notifying the user of the list;

[1841] a means for receiving negotiation requests and emotion data from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices;

[1842] A means for supporting negotiation based on requests, proposals and emotion data sent by a user;

[1843] A system including:

[1844] (Claim 2)

[1845] 10. The system of claim 1, wherein the system collects feedback and sentiment data and updates the matching algorithm based on the collected feedback and sentiment data.

[1846] (Claim 3)

[1847] 2. The system of claim 1, wherein the system predicts a user's potential needs and generates a product list based on the prediction.

[1848] "Application example 2 when combining emotion engines"

[1849] (Claim 1)

[1850] A means for collec...

Claims

1. A means for collecting and analyzing users' search history, browsing history, and purchase history; A means for analyzing the price of the listed product based on price data of other similar products and calculating a fair price; A means of collecting user feedback and updating the matching algorithm based on that feedback; and A means of analyzing users' past behavioral data and market trend data to predict users' potential needs; means for generating a product list based on the predicted needs and notifying the user of the list; a means for receiving negotiation requests from prospective buyers and generating appropriate negotiation proposals based on past negotiation data and market prices; means for supporting negotiations based on requests and proposals submitted by users; A system including:

2. 10. The system of claim 1, further comprising: collecting feedback and updating a matching algorithm based on the feedback.

3. The system according to claim 1, wherein the system predicts a user's potential needs and generates a product list based on the prediction.

Images