system

Abstract

We provide the system. [Solution] Means of collecting information from ticket trading platforms, A means of detecting transactions where the selling price exceeds the benchmark price from the collected information, A means of sending a notification to adjust the selling price of detected transactions to the base price, A means to re-register transactions adjusted to the benchmark price, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the ticket resale market, there is a problem that high-price reselling not only disadvantages customers but also damages the credibility of event organizers. Such problems hinder ticket sales at appropriate prices and are factors that damage the trust relationship between consumers and organizers.

Means for Solving the Problems

[0005] This invention provides a system for detecting tickets being fraudulently resold at inflated prices on a ticket trading platform, adjusting the price to a standard price, and reselling them. Specifically, it includes a means for collecting information from the ticket trading platform, sending price adjustment information to the seller using a notification means if the selling price exceeds the standard price, and re-registering the adjusted transaction. This system enables the sale of tickets at a fair price and helps maintain trust between consumers and event organizers.

[0006] A "ticket trading platform" is a digital platform that facilitates the online sale and purchase of tickets.

[0007] The "standard price" is the fair price at which the ticket should rightfully be sold, and is set by the organizer or official ticket vendor.

[0008] A "generating inference model" refers to a model that uses artificial intelligence techniques to predict or infer specific results based on data analysis.

[0009] A "notification means" is a means equipped with communication functions for transmitting specific information to a user or system.

[0010] "Means of collection" refers to a function or mechanism for obtaining necessary information from a specific data source.

[0011] "Price adjustment" refers to the operation or procedure of adjusting the selling price of a ticket to match a benchmark price.

[0012] "Re-registration" refers to the process of re-registering a transaction or information on the platform with adjusted details. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The present invention provides a method for detecting fraudulent price gouging on ticket trading platforms and enabling resale at fairer prices. This system is primarily managed by a server and is designed to automatically monitor and adjust ticket pricing.

[0035] First, the server periodically retrieves the latest ticket information from the ticket trading platform. This involves collecting ticket IDs, event names, listing prices, and reference prices through scraping techniques and publicly available APIs.

[0036] Next, the server analyzes the collected data and uses a generated inference model to identify transactions where the listing price exceeds a set benchmark price. This model enables price anomaly detection based on historical data and market trends.

[0037] The server sends a warning message via a communication interface to ticket sellers whose prices exceed the benchmark price. This message is implemented using a messaging service such as the LINE API, allowing sellers to immediately know that their listings will be adjusted based on the benchmark price.

[0038] The server then adjusts the price of any tickets exceeding the standard price on the platform and re-registers them on the platform. This process ensures that potential buyers can obtain tickets at a fair price.

[0039] As a concrete example, consider a case where tickets for a music event are being sold at a base price of 5,000 yen. If the server detects that a ticket is being offered for 7,000 yen on a resale platform, the price of that listing will be adjusted. The server will notify the seller and ask them to revise the listing to 5,000 yen and re-register it. In this way, event organizers can more easily manage the distribution of tickets at fair prices, and consumers can be provided with a market where they can trade with peace of mind.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server accesses the ticket trading platform as a regularly scheduled task and begins collecting data. Specifically, it uses APIs or web scraping techniques to retrieve all ticket listing information and saves it to a local database.

[0043] Step 2:

[0044] The server analyzes the ticket information stored in the local database. Here, it uses a generated inference model to determine if the listing price of each ticket exceeds the benchmark price. The benchmark price is the official selling price set by the organizer and is automatically referenced according to the list.

[0045] Step 3:

[0046] The server lists tickets that are being offered at a price exceeding the benchmark price. It also cross-references the excess price and seller information to create a detailed list.

[0047] Step 4:

[0048] The server sends a notification to the seller using a messaging service such as the LINE API for tickets with prices exceeding the limit. This notification includes the message, "The listing price has exceeded the standard price. An adjustment will be made."

[0049] Step 5:

[0050] The server automatically adjusts any listing price exceeding the limit to the base price. This process is performed remotely using the resale site's API, and the price is corrected immediately.

[0051] Step 6:

[0052] The server then relists the tickets for which price adjustments have been completed. The listing information on the platform is re-registered at the base price, making it possible to purchase them at the appropriate price.

[0053] Step 7:

[0054] The server logs the completion of a series of processes and prepares for the next scheduled task. This includes detailed information such as the time taken for the actions performed and the number of adjustments made.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In the current ticket market, fraudulent price gouging is depriving prospective buyers of the opportunity to purchase tickets at a fair price. This problem is particularly pronounced for popular events and undermines the health of the market. Therefore, there is a need for a method that automatically detects and adjusts listings with unfair pricing while maintaining a benchmark ticket price.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for an information processing device to collect data from a ticket trading medium, means for the information processing device to identify data exceeding a benchmark price using a data analysis function, and means for the information processing device to transmit a notification using an information transmission device in order to adjust the price of the identified data. This makes it possible to create a fair trading market by automatically detecting and adjusting unfair prices.

[0060] An "information processing device" is a device that has the functions of collecting, analyzing, and managing data, and is primarily used as a server to process information in ticket transactions.

[0061] A "ticket trading platform" refers to any platform that facilitates the buying and selling of tickets online or offline, and the platform that manages the ticket information circulating within it.

[0062] "Data analysis functionality" refers to technologies used to detect specific patterns or anomalies based on collected data, and involves the use of specific algorithms or generative AI models.

[0063] The "benchmark price" refers to a standard selling price that is recognized as fair in ticket transactions, and is a basic benchmark price set by the platform.

[0064] An "information transmission device" is a device used to send notifications and information to sellers and prospective buyers, and it uses messaging services via a communication interface.

[0065] A "generated intelligent reasoning model" is an algorithm created based on past data and market trends, and is a data analysis model aimed at price setting and detecting anomalies in transactions.

[0066] "Digital media" refers to a medium for transmitting data and information online, and is a broad concept that includes internet services and applications.

[0067] A "data provider" refers to an individual or legal entity that registers sales information with a ticket trading platform, and is a user who acts as a seller.

[0068] One embodiment of the present invention is a method in which the information processing device is used as a server. The server connects to a ticket trading medium via the internet and periodically collects ticket sales information. This mainly utilizes web scraping technology and publicly available APIs.

[0069] The server stores the collected data in its internal database and performs data analysis using a generated intelligent inference model. This inference model learns from past transaction data and existing market trends, making it capable of detecting abnormal pricing that exceeds the benchmark price.

[0070] If an anomaly is detected, the server uses an information transmission device to send a notification to the data provider on the ticket trading platform, prompting them to adjust the price. Since the notification is sent in real time using digital media, sellers can quickly understand the situation and take action.

[0071] As a concrete example, consider a scenario where the benchmark price for tickets to a certain music event is set at 5,000 yen. When the server collects data from ticket trading platforms and identifies a listing at 7,000 yen, a notification is sent to the seller, and the price is adjusted to the benchmark price. This ensures fair trading.

[0072] A concrete example of a prompt message is, "Check the current ticket price and what adjustments should be made to maintain a fair price?" This prompt is the driving force behind the data analysis and price adjustment process, which utilizes a generative AI model.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server connects to ticket trading platforms and uses web scraping techniques and APIs to collect data such as ticket IDs, event names, listing prices, and reference prices from those platforms. It accepts URLs of trading platforms or API endpoints as input and constructs the acquired dataset as output. Specifically, the server sends HTTP requests, parses the returned JSON data, and extracts the necessary information.

[0076] Step 2:

[0077] The server stores the collected data in an internal database. Using the dataset collected in step 1 as input, it generates information stored in the database as output. Specifically, it inserts the analyzed data into the appropriate table in the database and saves it in a searchable and updateable format.

[0078] Step 3:

[0079] The server analyzes the stored data using the generated intelligent reasoning model. The input includes ticket information retrieved from the database, and the output identifies listings that exceed the base price. In this step, the AI ​​model analyzes the input data and detects abnormal pricing. Specifically, the AI ​​model compares each price to the base price and sets an outlier flag based on the result.

[0080] Step 4:

[0081] The server uses a data transmission device to send notifications to sellers regarding listings whose prices exceed a certain threshold. It receives data with an abnormal flag as input and generates a notification message as output. Specifically, it sends a notification to the seller's registered device via the LINE API or other messaging services stating, "Your listing exceeds the price limit. Please adjust the price."

[0082] Step 5:

[0083] The server automatically adjusts the prices of identified anomaly tickets. Input includes listing information and a base price, and output generates adjusted price information. Specifically, it updates the relevant entries in the database and corrects the ticket prices to match the base price.

[0084] Step 6:

[0085] The server re-registers the adjusted data with the platform. The updated ticket data is used as input, and the normalized price information is delivered as output. Specifically, the server calls the platform's update API, re-edits the ticket with the corrected price, and publishes it.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] On e-commerce platforms, product prices can be unfairly set, resulting in consumers being at risk of purchasing goods at unreasonably high prices. There is a need to detect such unfair pricing and provide consumers with goods at fair prices.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for collecting information from an e-commerce platform, means for detecting transactions where the product price exceeds a benchmark price from the collected information, and means for sending notifications to adjust the product price of the detected transactions to the benchmark price. This makes it possible to create an environment in which consumers can purchase goods at a fair price.

[0091] An "e-commerce platform" is an online platform used for buying and selling goods and services over the internet.

[0092] "Means for collecting information" refers to devices or technologies that have the function of automatically acquiring the prices and transaction information of products on the platform.

[0093] "Means for detecting transactions where the commodity price exceeds the benchmark price" refers to a device or technology that has the function of determining whether the commodity price exceeds a predetermined benchmark price based on collected information.

[0094] "Means for sending notifications" refers to a device or technology equipped with communication functions for transmitting information about detected transactions to sellers and related parties.

[0095] A "standard price" is a price standard that is set in advance as reasonable and fair for the selling price of goods or services.

[0096] In order to implement this invention, it is necessary to build a system that involves the cooperation of a server, a terminal, and a user.

[0097] The server collects product information from e-commerce platforms. This is done using APIs or scraping techniques. The collected data is analyzed based on a trained model generated using the Scikit-learn library developed in Python. This analysis detects transactions where the product price exceeds a set benchmark price.

[0098] If a transaction exceeding the benchmark price is detected, the server sends a notification to the seller via a communication method. A messaging API is used for this purpose. The notification immediately informs the seller that the product price will be adjusted based on the benchmark price.

[0099] After the price adjustment is made, the transaction is re-registered on the platform, allowing users to purchase the product at a fair price. Users with devices can check the fair price of the product and obtain information through the application.

[0100] As a concrete example, suppose a newly released clothing item has a base price of 1000 yen. If the server detects that the item is being sold for 1200 yen on an e-commerce platform, a notification is sent to the seller, and the price of the item is adjusted to 1000 yen. In this way, a more transparent market environment can be provided to consumers.

[0101] Examples of prompts to input to a generative AI model include: "Generative AI model, tell me how to monitor for fraudulent pricing on e-commerce sites and display accurate prices."

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The server collects product information from e-commerce platforms. It uses the platform's API or scraping techniques as input to obtain product names, prices, product IDs, etc. The output is formally organized product information stored in a database.

[0105] Step 2:

[0106] The server uses a generative AI model to detect price anomalies based on the collected product information. The input is a dataset of product information, and data processing such as price standardization and filtering is performed. The output is a list of anomaly prices that exceed the baseline price.

[0107] Step 3:

[0108] The server, upon detecting an abnormal price, sends a notification to the seller via a communication method. The input is a list of abnormal prices and the seller's contact information, and the output is the notification message sent via the messaging API. The seller is informed that the product price will be adjusted based on the benchmark price.

[0109] Step 4:

[0110] The server re-registers product transactions adjusted to the benchmark price. The input is the correct adjusted product price, and the output is the transaction information re-registered on the platform. This provides an environment where consumers can purchase goods at a fair price.

[0111] Step 5:

[0112] Users can check the fair price of products through an application on their device. The input is the latest product information obtained from the platform, and the output is the fair price information displayed on the device screen. Based on this information, users can make purchasing decisions.

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] This invention provides a system that monitors sales pricing on a ticket trading platform to prevent fraudulent price gouging, and also enables effective notifications that take user sentiment into consideration. This system operates server-centric and integrates multiple functions.

[0115] First, the server periodically accesses the ticket trading platform to retrieve the latest ticket listing information. This data includes ticket IDs, event names, listing prices, and reference prices. This data is stored in a local database and used in the next analysis step.

[0116] Next, the server analyzes the collected data using the generated inference model. This model determines whether the listing price of each ticket exceeds the threshold price. For listings that exceed the threshold price, the sentiment engine prepares to analyze the user's emotional state.

[0117] The emotion engine estimates the emotions a particular user might be currently experiencing based on past interaction data with that user. For example, if emotions such as dissatisfaction or surprise are detected, the server takes this into account and adjusts the content and tone of notification messages accordingly.

[0118] Subsequently, the server sends a appropriately tailored notification message to the seller via a communication interface such as the LINE API. In this step, the seller is notified in a way that is sensitive to their feelings that their listing will be adjusted to match the benchmark price.

[0119] As a specific example, consider a case where a server adjusts a seller's ticket price from 7,000 yen to a base price of 5,000 yen. If the seller might resist the price change, the emotion engine anticipates their feelings and adjusts the notification message to be polite and easy to understand. For example, a message such as, "Based on current market analysis, we have made an appropriate price adjustment. We appreciate your understanding," might be sent.

[0120] Thus, this system, which incorporates an emotion engine, not only adjusts ticket prices but also contributes to creating a smoother transaction environment by providing notifications that appeal to the seller's emotions.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The server accesses the ticket trading platform according to a pre-configured schedule and collects information on tickets being offered for sale. This includes data such as ticket ID, event name, listing price, and reference price, and is obtained using APIs or scraping techniques.

[0124] Step 2:

[0125] The server stores the collected ticket information in a local database, then uses a generated inference model to analyze the data and detect transactions where the listing price exceeds the benchmark price. Based on this analysis, a list of these excess transactions is created along with seller information.

[0126] Step 3:

[0127] The emotion engine receives a list of detected listings exceeding the listed price and analyzes the user's past interaction data to estimate their current emotional state. Emotions such as dissatisfaction, resistance, and understanding are considered.

[0128] Step 4:

[0129] Based on the analysis results of the emotion engine, the server creates a customized notification message tailored to the user's emotions. This message aims to reduce the psychological burden on sellers by carefully explaining why a price revision is necessary.

[0130] Step 5:

[0131] The server sends a notification message to the seller, which has been adjusted using a communication interface such as the LINE API. Here, the server confirms that the seller has received the notification, and their response can be used for future analysis.

[0132] Step 6:

[0133] The server automatically adjusts the listing price that exceeds the limit to the base price and re-registers it with the resale site. It verifies whether the re-registration was successful and saves the result as a log in the database.

[0134] Step 7:

[0135] The server logs the completion of a series of processes and prepares for the next scheduled process. This information will be used to optimize and improve future transactions.

[0136] (Example 2)

[0137] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0138] In current ticket trading, the problem of reselling tickets at prices significantly exceeding the standard price is a major issue. Furthermore, it is difficult to properly notify sellers when adjusting the selling price, hindering smooth transactions. In this situation, there is a need for a method that can effectively notify sellers while taking their feelings into consideration.

[0139] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0140] In this invention, the server includes means for collecting data from an information processing device, means for detecting transactions where the sales amount exceeds a standard amount from the collected data, and means for sending notifications adjusted based on sentiment analysis for the detected transactions. This enables smooth transactions by providing notifications regarding adjustments to the sales amount in a manner that takes into account the seller's sentiment.

[0141] An "information processing device" is a computer system used to collect and analyze data, and it is responsible for connecting to databases and networks to acquire various types of information.

[0142] "Data" is a general term for information related to ticket transactions, and includes information such as ticket ID, event name, sales price, and base price.

[0143] "Selling price" refers to the price set by the seller when selling tickets on the ticket trading platform.

[0144] The "standard price" refers to a benchmark value set as the appropriate selling price for tickets, and is an indicator used to determine whether the selling price exceeds this value.

[0145] "Transaction" refers to a sales contract and related activities conducted on a ticket trading platform.

[0146] "Sentiment analysis" refers to the analytical process performed to estimate a user's emotional state based on their past behavior and transaction history.

[0147] "Notification" refers to the activity of sending appropriate information or messages to the seller based on detected transactions.

[0148] "Communication means" is a general term for the lines and protocols used to transmit data and messages between an information processing device and an exhibitor, and includes network interfaces and APIs.

[0149] This invention relates to a system for preventing fraudulent resale at inflated prices in ticket transactions and for providing effective notifications that take into account the user's psychological state. The system is composed of multiple functions, mainly integrating an information processing device, a generative AI model, and an emotion analysis engine.

[0150] First, the server periodically retrieves the latest data through the ticket trading platform's API. This data includes ticket IDs, event names, sales amounts, and base amounts, and is stored in a local database in a structured format.

[0151] Next, the server uses a generative AI model to analyze the collected data. The AI ​​model has learned from past price trends and market information, and determines whether the sales amount exceeds a certain threshold. Data suspected of being fraudulent transactions is extracted separately.

[0152] The sentiment analysis engine is activated by the server and estimates the potential emotions a seller might be experiencing based on past interaction data with the user. This allows for measures to be taken to minimize the psychological impact that price adjustment notifications have on sellers.

[0153] Subsequently, the server generates a notification message based on the sentiment analysis results and sends it to the seller via the network interface, which is the means of communication. This procedure ensures that the seller receives a message with appropriate content, facilitating a smooth transaction.

[0154] For example, if a ticket listed for 7,000 yen has a baseline price of 5,000 yen, the AI ​​model will determine this price difference to be abnormal. The sentiment analysis engine considers the seller's past transaction history and, if it determines that the seller may be dissatisfied, the notification message will be designed to encourage understanding.

[0155] This invention makes it possible to send price adjustment notifications in a way that takes into account the seller's feelings, thereby greatly contributing to the smooth operation of the transaction environment. An example of a prompt message to the generating AI model would be, "In setting the price for ticket transactions, how should we analyze each user's feelings and adjust the notification content based on that?"

[0156] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0157] Step 1:

[0158] The server accesses the ticket trading platform's API to retrieve the latest listing data.

[0159] Input: API endpoint of the ticket trading platform.

[0160] Specific operation: Send an API request to retrieve listing information including ticket ID, event name, selling price, and base price.

[0161] Output: The retrieved listing data is saved in a structured format to the server's local database.

[0162] Step 2:

[0163] The server collects data, which is then input into an AI model for analysis.

[0164] Input: Listing data stored on the server.

[0165] Specific operation: Data is fed into the AI ​​model to determine whether the sales price of each listing exceeds a certain threshold.

[0166] Output: A list of transactions that were determined to exceed the threshold amount is created.

[0167] Step 3:

[0168] The server uses an emotion analysis engine to estimate the seller's emotional state.

[0169] Input: Transaction data exceeding a certain threshold and past user interaction data.

[0170] Specific operation: The emotion analysis engine estimates the emotions the seller might be experiencing (e.g., dissatisfaction or surprise).

[0171] Output: Estimated results are generated based on the emotional state.

[0172] Step 4:

[0173] The server generates a notification message based on the sentiment analysis results and sends it to the seller.

[0174] Input: Sentiment analysis results and transaction data exceeding a threshold amount.

[0175] Specific actions: Generate a notification message with emotionally sensitive content and tone, and send it to the seller via communication means.

[0176] Output: The adjusted notification message received by the seller.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] In recent years, fraudulent high-priced transactions and resales have become a social problem on ticket trading platforms and electronic payment networks. However, current systems do not adequately consider user sentiment when adjusting transaction prices, which can lead to dissatisfaction and resistance from sellers. To solve these problems and ensure smooth transactions, effective measures are needed to prevent fraudulent transactions while taking user sentiment into consideration.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes means for collecting information from an information processing network, means for identifying transactions where the transaction price exceeds a benchmark price from the collected information, and means for generating notification messages that take into account the user's feelings regarding the identified transactions and transmitting the information. This makes it possible to prevent fraudulent transactions while transmitting information in a way that takes into account the feelings of the seller.

[0182] An "information processing network" is a system in which multiple computers and systems are interconnected in order to effectively collect, analyze, and transmit data and information.

[0183] "Transaction price" refers to the monetary value set in the buying and selling of goods or services, and is the basis for comparison with the benchmark price.

[0184] A "reference price" is a standard price used for evaluating and comparing transaction prices, and serves as an indicator for maintaining fair trade.

[0185] "Trade" refers to the exchange or sale of goods and services, and in this context specifically refers to transactions involving tickets and electronic payment products.

[0186] "Identification" is the process of identifying and classifying items that meet specific criteria based on collected information, and it is a technique used for monitoring and verifying transactions.

[0187] A "notification message" is a short message in which a system communicates information or instructions to a user, and in this context, it specifically refers to messages that are generated with emotions in mind.

[0188] "Considering the user's emotions" means predicting the recipient's emotional state during information transmission and adjusting the content and expression accordingly.

[0189] The system for implementing this invention consists of a server and a user terminal. The server operates on an information processing network and collects various transaction information from the platform. Specifically, the server uses crawling technology to periodically retrieve price information for goods and services from the trading platform. This process is typically implemented using the Python library BeautifulSoup.

[0190] The server manages the collected information as a Pandas DataFrame and uses an inference model built with TENSORFLOW® to analyze whether the trading price exceeds the benchmark price. If an exceedance is detected, the server uses NLTK and OpenAI® GPT to generate a notification message that takes the user's sentiment into account. Based on the user's past trading data and reaction history, it generates prompts to create a message with an appropriate tone, and this message is notified to the user via the LINE API.

[0191] As a concrete example, if the server detects a potentially fraudulent transaction involving tax evasion within the electronic payment platform, it sends a message to the seller stating, "Based on market analysis, we request that you revise the transaction price. We appreciate your understanding." This generated message helps users reduce emotional resistance while promoting transactions at fair prices.

[0192] An example of a prompt might be: "Analyze the seller's sentiment based on their past response patterns and generate a message requesting a price adjustment in an appropriate tone." This setting allows the server to provide flexible and effective notifications based on sentiment.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The server periodically accesses the trading platform from the information processing network and retrieves the latest trading data using the API or web crawling technology it employs. This retrieved data includes product ID, event name, trading price, and base price. It receives data collected from the trading platform as input and transforms it into a structured dataset as output.

[0196] Step 2:

[0197] The server organizes the collected data into a Pandas DataFrame, preparing it for analysis. This DataFrame is managed using Python data analysis tools, which take the raw data as input and generate data in DataFrame format as output.

[0198] Step 3:

[0199] The server executes an inference model built using TensorFlow to determine whether a transaction price exceeds a baseline price. The input is price information in dataframe format, and the output is a list of transactions whose prices exceed the baseline price. This step involves performing price determination based on the model as a data calculation.

[0200] Step 4:

[0201] The server analyzes the seller's past transaction history and response data for transactions where an excess has been detected, and generates a sentiment-sensitive notification message using NLTK and OpenAI GPT. The input is the identified transaction and the seller's past data, and the output is a sentiment-sensitive notification message.

[0202] Step 5:

[0203] The server sends the generated notification message to the seller using the LINE API. The input is the generated notification message, and the output is confirmation that the message was sent successfully. The server monitors the message delivery status via the communication interface.

[0204] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0205] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0206] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0210] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0211] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0212] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0213] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0214] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0215] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0216] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0217] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0218] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0219] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0220] The present invention provides a method for detecting fraudulent price gouging on ticket trading platforms and enabling resale at fairer prices. This system is primarily managed by a server and is designed to automatically monitor and adjust ticket pricing.

[0221] First, the server periodically retrieves the latest ticket information from the ticket trading platform. This involves collecting ticket IDs, event names, listing prices, and reference prices through scraping techniques and publicly available APIs.

[0222] Next, the server analyzes the collected data and uses a generated inference model to identify transactions where the listing price exceeds a set benchmark price. This model enables price anomaly detection based on historical data and market trends.

[0223] The server sends a warning message via a communication interface to ticket sellers whose prices exceed the benchmark price. This message is implemented using a messaging service such as the LINE API, allowing sellers to immediately know that their listings will be adjusted based on the benchmark price.

[0224] The server then adjusts the price of any tickets exceeding the standard price on the platform and re-registers them on the platform. This process ensures that potential buyers can obtain tickets at a fair price.

[0225] As a concrete example, consider a case where tickets for a music event are being sold at a base price of 5,000 yen. If the server detects that a ticket is being offered for 7,000 yen on a resale platform, the price of that listing will be adjusted. The server will notify the seller and ask them to revise the listing to 5,000 yen and re-register it. In this way, event organizers can more easily manage the distribution of tickets at fair prices, and consumers can be provided with a market where they can trade with peace of mind.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The server accesses the ticket trading platform as a regularly scheduled task and begins collecting data. Specifically, it uses APIs or web scraping techniques to retrieve all ticket listing information and saves it to a local database.

[0229] Step 2:

[0230] The server analyzes the ticket information stored in the local database. Here, it uses a generated inference model to determine if the listing price of each ticket exceeds the benchmark price. The benchmark price is the official selling price set by the organizer and is automatically referenced according to the list.

[0231] Step 3:

[0232] The server lists tickets that are being offered at a price exceeding the benchmark price. It also cross-references the excess price and seller information to create a detailed list.

[0233] Step 4:

[0234] The server sends a notification to the seller using a messaging service such as the LINE API for tickets with prices exceeding the limit. This notification includes the message, "The listing price has exceeded the standard price. An adjustment will be made."

[0235] Step 5:

[0236] The server automatically adjusts any listing price exceeding the limit to the base price. This process is performed remotely using the resale site's API, and the price is corrected immediately.

[0237] Step 6:

[0238] The server then relists the tickets for which price adjustments have been completed. The listing information on the platform is re-registered at the base price, making it possible to purchase them at the appropriate price.

[0239] Step 7:

[0240] The server logs the completion of a series of processes and prepares for the next scheduled task. This includes detailed information such as the time taken for the actions performed and the number of adjustments made.

[0241] (Example 1)

[0242] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0243] In the current ticket market, fraudulent price gouging is depriving prospective buyers of the opportunity to purchase tickets at a fair price. This problem is particularly pronounced for popular events and undermines the health of the market. Therefore, there is a need for a method that automatically detects and adjusts listings with unfair pricing while maintaining a benchmark ticket price.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes means for an information processing device to collect data from a ticket trading medium, means for the information processing device to identify data exceeding a benchmark price using a data analysis function, and means for the information processing device to transmit a notification using an information transmission device in order to adjust the price of the identified data. This makes it possible to create a fair trading market by automatically detecting and adjusting unfair prices.

[0246] An "information processing device" is a device that has the functions of collecting, analyzing, and managing data, and is primarily used as a server to process information in ticket transactions.

[0247] A "ticket trading platform" refers to any platform that facilitates the buying and selling of tickets online or offline, and the platform that manages the ticket information circulating within it.

[0248] "Data analysis functionality" refers to technologies used to detect specific patterns or anomalies based on collected data, and involves the use of specific algorithms or generative AI models.

[0249] The "benchmark price" refers to a standard selling price that is recognized as fair in ticket transactions, and is a basic benchmark price set by the platform.

[0250] An "information transmission device" is a device used to send notifications and information to sellers and prospective buyers, and it uses messaging services via a communication interface.

[0251] A "generated intelligent reasoning model" is an algorithm created based on past data and market trends, and is a data analysis model aimed at price setting and detecting anomalies in transactions.

[0252] "Digital media" refers to a medium for transmitting data and information online, and is a broad concept that includes internet services and applications.

[0253] A "data provider" refers to an individual or legal entity that registers sales information with a ticket trading platform, and is a user who acts as a seller.

[0254] One embodiment of the present invention is a method in which the information processing device is used as a server. The server connects to a ticket trading medium via the internet and periodically collects ticket sales information. This mainly utilizes web scraping technology and publicly available APIs.

[0255] The server stores the collected data in its internal database and performs data analysis using a generated intelligent inference model. This inference model learns from past transaction data and existing market trends, making it capable of detecting abnormal pricing that exceeds the benchmark price.

[0256] If an anomaly is detected, the server uses an information transmission device to send a notification to the data provider on the ticket trading platform, prompting them to adjust the price. Since the notification is sent in real time using digital media, sellers can quickly understand the situation and take action.

[0257] As a concrete example, consider a scenario where the benchmark price for tickets to a certain music event is set at 5,000 yen. When the server collects data from ticket trading platforms and identifies a listing at 7,000 yen, a notification is sent to the seller, and the price is adjusted to the benchmark price. This ensures fair trading.

[0258] A concrete example of a prompt message is, "Check the current ticket price and what adjustments should be made to maintain a fair price?" This prompt is the driving force behind the data analysis and price adjustment process, which utilizes a generative AI model.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1:

[0261] The server connects to ticket trading platforms and uses web scraping techniques and APIs to collect data such as ticket IDs, event names, listing prices, and reference prices from those platforms. It accepts URLs of trading platforms or API endpoints as input and constructs the acquired dataset as output. Specifically, the server sends HTTP requests, parses the returned JSON data, and extracts the necessary information.

[0262] Step 2:

[0263] The server stores the collected data in an internal database. Using the dataset collected in step 1 as input, it generates information stored in the database as output. Specifically, it inserts the analyzed data into the appropriate table in the database and saves it in a searchable and updateable format.

[0264] Step 3:

[0265] The server analyzes the stored data using the generated intelligent reasoning model. The input includes ticket information retrieved from the database, and the output identifies listings that exceed the base price. In this step, the AI ​​model analyzes the input data and detects abnormal pricing. Specifically, the AI ​​model compares each price to the base price and sets an outlier flag based on the result.

[0266] Step 4:

[0267] The server uses a data transmission device to send notifications to sellers regarding listings whose prices exceed a certain threshold. It receives data with an abnormal flag as input and generates a notification message as output. Specifically, it sends a notification to the seller's registered device via the LINE API or other messaging services stating, "Your listing exceeds the price limit. Please adjust the price."

[0268] Step 5:

[0269] The server automatically adjusts the prices of identified anomaly tickets. Input includes listing information and a base price, and output generates adjusted price information. Specifically, it updates the relevant entries in the database and corrects the ticket prices to match the base price.

[0270] Step 6:

[0271] The server re-registers the adjusted data with the platform. The updated ticket data is used as input, and the normalized price information is delivered as output. Specifically, the server calls the platform's update API, re-edits the ticket with the corrected price, and publishes it.

[0272] (Application Example 1)

[0273] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] On e-commerce platforms, product prices can be unfairly set, resulting in consumers being at risk of purchasing goods at unreasonably high prices. There is a need to detect such unfair pricing and provide consumers with goods at fair prices.

[0275] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0276] In this invention, the server includes means for collecting information from an e-commerce platform, means for detecting transactions where the product price exceeds a benchmark price from the collected information, and means for sending notifications to adjust the product price of the detected transactions to the benchmark price. This makes it possible to create an environment in which consumers can purchase goods at a fair price.

[0277] An "e-commerce platform" is an online platform used for buying and selling goods and services over the internet.

[0278] "Means for collecting information" refers to devices or technologies that have the function of automatically acquiring the prices and transaction information of products on the platform.

[0279] "Means for detecting transactions where the commodity price exceeds the benchmark price" refers to a device or technology that has the function of determining whether the commodity price exceeds a predetermined benchmark price based on collected information.

[0280] "Means for sending notifications" refers to a device or technology equipped with communication functions for transmitting information about detected transactions to sellers and related parties.

[0281] The "reference price" is a price benchmark that is set in advance as reasonable and fair in the selling prices of goods and services.

[0282] To implement this invention, it is necessary to construct a system through the cooperation of a server, a terminal, and a user.

[0283] The server collects product information from the e-commerce platform. This is done using API or scraping technology. The collected data is analyzed based on the generated learning model by utilizing the Scikit-learn library developed in Python. Through this analysis, transactions where the product price exceeds the reference price are detected.

[0284] When a transaction exceeding the reference price is detected, the server sends a notification to the seller via communication means. In this case, a messaging API is utilized. Through the notification, the seller is informed that the price of the product will be immediately adjusted based on the reference price.

[0285] After that, the transaction with the adjusted product price is registered on the platform again, enabling users to purchase products at a fair price. Users using the terminal can confirm the appropriate price of the product and obtain information through the application.

[0286] As a specific example, assume that the reference price of a newly launched clothing product is 1000 yen. If the server detects that it is being sold at 1200 yen on the e-commerce platform, a notification is sent to the seller and the product price is adjusted to 1000 yen. In this way, a more transparent market environment can be provided for consumers.

[0287] Examples of prompt sentences input to the generative AI model include "Teach me how to monitor illegal prices on the generative AI model and direct sales websites and perform appropriate displays."

[0288] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0289] Step 1:

[0290] The server collects product information from e-commerce platforms. It uses the platform's API or scraping techniques as input to obtain product names, prices, product IDs, etc. The output is formally organized product information stored in a database.

[0291] Step 2:

[0292] The server uses a generative AI model to detect price anomalies based on the collected product information. The input is a dataset of product information, and data processing such as price standardization and filtering is performed. The output is a list of anomaly prices that exceed the baseline price.

[0293] Step 3:

[0294] The server, upon detecting an abnormal price, sends a notification to the seller via a communication method. The input is a list of abnormal prices and the seller's contact information, and the output is the notification message sent via the messaging API. The seller is informed that the product price will be adjusted based on the benchmark price.

[0295] Step 4:

[0296] The server re-registers product transactions adjusted to the benchmark price. The input is the correct adjusted product price, and the output is the transaction information re-registered on the platform. This provides an environment where consumers can purchase goods at a fair price.

[0297] Step 5:

[0298] Users can check the fair price of products through an application on their device. The input is the latest product information obtained from the platform, and the output is the fair price information displayed on the device screen. Based on this information, users can make purchasing decisions.

[0299] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0300] This invention provides a system that monitors sales pricing on a ticket trading platform to prevent fraudulent price gouging, and also enables effective notifications that take user sentiment into consideration. This system operates server-centric and integrates multiple functions.

[0301] First, the server periodically accesses the ticket trading platform to retrieve the latest ticket listing information. This data includes ticket IDs, event names, listing prices, and reference prices. This data is stored in a local database and used in the next analysis step.

[0302] Next, the server analyzes the collected data using the generated inference model. This model determines whether the listing price of each ticket exceeds the threshold price. For listings that exceed the threshold price, the sentiment engine prepares to analyze the user's emotional state.

[0303] The emotion engine estimates the emotions a particular user might be currently experiencing based on past interaction data with that user. For example, if emotions such as dissatisfaction or surprise are detected, the server takes this into account and adjusts the content and tone of notification messages accordingly.

[0304] After that, the server sends an appropriately adjusted notification message to the publisher via a communication interface such as the LINE API. In this step, the publisher is notified in a way that takes into account their feelings that their listing has been adjusted in line with the benchmark price.

[0305] As a specific example, consider the case where the server adjusts the ticket price of a certain publisher from 7,000 yen to the benchmark price of 5,000 yen. If the publisher may show resistance to the price change, the emotion engine anticipates their feelings and adjusts the notification text to be polite and facilitative of understanding. For example, a message such as "Based on the current market analysis, an appropriate price revision has been made. Please kindly understand." is sent.

[0306] In this way, the system incorporating the emotion engine not only adjusts the ticket price but also contributes to building a smoother trading environment by sending notifications in a way that appeals to the emotions of the publishers.

[0307] The processing flow will be described below.

[0308] Step 1:

[0309] The server accesses the ticket trading platform according to a preset schedule and collects the ticket information being offered. This includes data such as the ticket ID, event name, offering price, and benchmark price, which is obtained using an API or scraping technology.

[0310] Step 2:

[0311] After the server saves the collected ticket information in the local database, it analyzes the data using an inference model to be generated and detects transactions where the offering price exceeds the benchmark price. Based on this analysis result, a list of overpriced transactions is created together with the publisher information.

[0312] Step 3:

[0313] The emotion engine receives a list of detected listings exceeding the listed price and analyzes the user's past interaction data to estimate their current emotional state. Emotions such as dissatisfaction, resistance, and understanding are considered.

[0314] Step 4:

[0315] Based on the analysis results of the emotion engine, the server creates a customized notification message tailored to the user's emotions. This message aims to reduce the psychological burden on sellers by carefully explaining why a price revision is necessary.

[0316] Step 5:

[0317] The server sends a notification message to the seller, which has been adjusted using a communication interface such as the LINE API. Here, the server confirms that the seller has received the notification, and their response can be used for future analysis.

[0318] Step 6:

[0319] The server automatically adjusts the listing price that exceeds the limit to the base price and re-registers it with the resale site. It verifies whether the re-registration was successful and saves the result as a log in the database.

[0320] Step 7:

[0321] The server logs the completion of a series of processes and prepares for the next scheduled process. This information will be used to optimize and improve future transactions.

[0322] (Example 2)

[0323] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0324] In current ticket trading, the problem of reselling tickets at prices significantly exceeding the standard price is a major issue. Furthermore, it is difficult to properly notify sellers when adjusting the selling price, hindering smooth transactions. In this situation, there is a need for a method that can effectively notify sellers while taking their feelings into consideration.

[0325] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0326] In this invention, the server includes means for collecting data from an information processing device, means for detecting transactions where the sales amount exceeds a standard amount from the collected data, and means for sending notifications adjusted based on sentiment analysis for the detected transactions. This enables smooth transactions by providing notifications regarding adjustments to the sales amount in a manner that takes into account the seller's sentiment.

[0327] An "information processing device" is a computer system used to collect and analyze data, and it is responsible for connecting to databases and networks to acquire various types of information.

[0328] "Data" is a general term for information related to ticket transactions, and includes information such as ticket ID, event name, sales price, and base price.

[0329] "Selling price" refers to the price set by the seller when selling tickets on the ticket trading platform.

[0330] The "standard price" refers to a benchmark value set as the appropriate selling price for tickets, and is an indicator used to determine whether the selling price exceeds this value.

[0331] "Transaction" refers to a sales contract and related activities conducted on a ticket trading platform.

[0332] "Sentiment analysis" refers to the analytical process performed to estimate a user's emotional state based on their past behavior and transaction history.

[0333] "Notification" refers to the activity of sending appropriate information or messages to the seller based on detected transactions.

[0334] "Communication means" is a general term for the lines and protocols used to transmit data and messages between an information processing device and an exhibitor, and includes network interfaces and APIs.

[0335] This invention relates to a system for preventing fraudulent resale at inflated prices in ticket transactions and for providing effective notifications that take into account the user's psychological state. The system is composed of multiple functions, mainly integrating an information processing device, a generative AI model, and an emotion analysis engine.

[0336] First, the server periodically retrieves the latest data through the ticket trading platform's API. This data includes ticket IDs, event names, sales amounts, and base amounts, and is stored in a local database in a structured format.

[0337] Next, the server uses a generative AI model to analyze the collected data. The AI ​​model has learned from past price trends and market information, and determines whether the sales amount exceeds a certain threshold. Data suspected of being fraudulent transactions is extracted separately.

[0338] The sentiment analysis engine is activated by the server and estimates the potential emotions a seller might be experiencing based on past interaction data with the user. This allows for measures to be taken to minimize the psychological impact that price adjustment notifications have on sellers.

[0339] Subsequently, the server generates a notification message based on the sentiment analysis results and sends it to the seller via the network interface, which is the means of communication. This procedure ensures that the seller receives a message with appropriate content, facilitating a smooth transaction.

[0340] For example, if a ticket listed for 7,000 yen has a baseline price of 5,000 yen, the AI ​​model will determine this price difference to be abnormal. The sentiment analysis engine considers the seller's past transaction history and, if it determines that the seller may be dissatisfied, the notification message will be designed to encourage understanding.

[0341] This invention makes it possible to send price adjustment notifications in a way that takes into account the seller's feelings, thereby greatly contributing to the smooth operation of the transaction environment. An example of a prompt message to the generating AI model would be, "In setting the price for ticket transactions, how should we analyze each user's feelings and adjust the notification content based on that?"

[0342] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0343] Step 1:

[0344] The server accesses the ticket trading platform's API to retrieve the latest listing data.

[0345] Input: API endpoint of the ticket trading platform.

[0346] Specific operation: Send an API request to retrieve listing information including ticket ID, event name, selling price, and base price.

[0347] Output: The retrieved listing data is saved in a structured format to the server's local database.

[0348] Step 2:

[0349] The server collects data, which is then input into an AI model for analysis.

[0350] Input: Listing data stored on the server.

[0351] Specific operation: Data is fed into the AI ​​model to determine whether the sales price of each listing exceeds a certain threshold.

[0352] Output: A list of transactions that were determined to exceed the threshold amount is created.

[0353] Step 3:

[0354] The server uses an emotion analysis engine to estimate the seller's emotional state.

[0355] Input: Transaction data exceeding a certain threshold and past user interaction data.

[0356] Specific operation: The emotion analysis engine estimates the emotions the seller might be experiencing (e.g., dissatisfaction or surprise).

[0357] Output: Estimated results are generated based on the emotional state.

[0358] Step 4:

[0359] The server generates a notification message based on the sentiment analysis results and sends it to the seller.

[0360] Input: Sentiment analysis results and transaction data exceeding a threshold amount.

[0361] Specific actions: Generate a notification message with emotionally sensitive content and tone, and send it to the seller via communication means.

[0362] Output: The adjusted notification message received by the seller.

[0363] (Application Example 2)

[0364] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0365] In recent years, fraudulent high-priced transactions and resales have become a social problem on ticket trading platforms and electronic payment networks. However, current systems do not adequately consider user sentiment when adjusting transaction prices, which can lead to dissatisfaction and resistance from sellers. To solve these problems and ensure smooth transactions, effective measures are needed to prevent fraudulent transactions while taking user sentiment into consideration.

[0366] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0367] In this invention, the server includes means for collecting information from an information processing network, means for identifying transactions where the transaction price exceeds a benchmark price from the collected information, and means for generating notification messages that take into account the user's feelings regarding the identified transactions and transmitting the information. This makes it possible to prevent fraudulent transactions while transmitting information in a way that takes into account the feelings of the seller.

[0368] An "information processing network" is a system in which multiple computers and systems are interconnected in order to effectively collect, analyze, and transmit data and information.

[0369] "Transaction price" refers to the monetary value set in the buying and selling of goods or services, and is the basis for comparison with the benchmark price.

[0370] A "reference price" is a standard price used for evaluating and comparing transaction prices, and serves as an indicator for maintaining fair trade.

[0371] "Trade" refers to the exchange or sale of goods and services, and in this context specifically refers to transactions involving tickets and electronic payment products.

[0372] "Identification" is the process of identifying and classifying items that meet specific criteria based on collected information, and it is a technique used for monitoring and verifying transactions.

[0373] A "notification message" is a short message in which a system communicates information or instructions to a user, and in this context, it specifically refers to messages that are generated with emotions in mind.

[0374] "Considering the user's emotions" means predicting the recipient's emotional state during information transmission and adjusting the content and expression accordingly.

[0375] The system for implementing this invention consists of a server and a user terminal. The server operates on an information processing network and collects various transaction information from the platform. Specifically, the server uses crawling technology to periodically retrieve price information for goods and services from the trading platform. This process is typically implemented using the Python library BeautifulSoup.

[0376] The server manages the collected information as a Pandas DataFrame and uses an inference model built with TensorFlow to analyze whether the trading price exceeds the benchmark price. If an excess is detected, the server uses NLTK and OpenAI GPT to generate a notification message that takes the user's sentiment into account. Based on the user's past trading data and reaction history, it generates prompts to create a message with an appropriate tone, and this message is sent to the user via the LINE API.

[0377] As a concrete example, if the server detects a potentially fraudulent transaction involving tax evasion within the electronic payment platform, it sends a message to the seller stating, "Based on market analysis, we request that you revise the transaction price. We appreciate your understanding." This generated message helps users reduce emotional resistance while promoting transactions at fair prices.

[0378] An example of a prompt might be: "Analyze the seller's sentiment based on their past response patterns and generate a message requesting a price adjustment in an appropriate tone." This setting allows the server to provide flexible and effective notifications based on sentiment.

[0379] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0380] Step 1:

[0381] The server periodically accesses the trading platform from the information processing network and retrieves the latest trading data using the API or web crawling technology it employs. This retrieved data includes product ID, event name, trading price, and base price. It receives data collected from the trading platform as input and transforms it into a structured dataset as output.

[0382] Step 2:

[0383] The server organizes the collected data into a Pandas DataFrame, preparing it for analysis. This DataFrame is managed using Python data analysis tools, which take the raw data as input and generate data in DataFrame format as output.

[0384] Step 3:

[0385] The server executes an inference model built using TensorFlow to determine whether a transaction price exceeds a baseline price. The input is price information in dataframe format, and the output is a list of transactions whose prices exceed the baseline price. This step involves performing price determination based on the model as a data calculation.

[0386] Step 4:

[0387] The server analyzes the seller's past transaction history and response data for transactions where an excess has been detected, and generates a sentiment-sensitive notification message using NLTK and OpenAI GPT. The input is the identified transaction and the seller's past data, and the output is a sentiment-sensitive notification message.

[0388] Step 5:

[0389] The server sends the generated notification message to the seller using the LINE API. The input is the generated notification message, and the output is confirmation that the message was sent successfully. The server monitors the message delivery status via the communication interface.

[0390] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0391] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0392] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0393] [Third Embodiment]

[0394] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0395] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0396] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0397] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0398] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0399] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0400] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0401] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0402] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0403] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0404] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0405] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0406] The present invention provides a method for detecting fraudulent price gouging on ticket trading platforms and enabling resale at fairer prices. This system is primarily managed by a server and is designed to automatically monitor and adjust ticket pricing.

[0407] First, the server periodically retrieves the latest ticket information from the ticket trading platform. This involves collecting ticket IDs, event names, listing prices, and reference prices through scraping techniques and publicly available APIs.

[0408] Next, the server analyzes the collected data and uses a generated inference model to identify transactions where the listing price exceeds a set benchmark price. This model enables price anomaly detection based on historical data and market trends.

[0409] The server sends a warning message via a communication interface to ticket sellers whose prices exceed the benchmark price. This message is implemented using a messaging service such as the LINE API, allowing sellers to immediately know that their listings will be adjusted based on the benchmark price.

[0410] The server then adjusts the price of any tickets exceeding the standard price on the platform and re-registers them on the platform. This process ensures that potential buyers can obtain tickets at a fair price.

[0411] As a concrete example, consider a case where tickets for a music event are being sold at a base price of 5,000 yen. If the server detects that a ticket is being offered for 7,000 yen on a resale platform, the price of that listing will be adjusted. The server will notify the seller and ask them to revise the listing to 5,000 yen and re-register it. In this way, event organizers can more easily manage the distribution of tickets at fair prices, and consumers can be provided with a market where they can trade with peace of mind.

[0412] The following describes the processing flow.

[0413] Step 1:

[0414] The server accesses the ticket trading platform as a regularly scheduled task and begins collecting data. Specifically, it uses APIs or web scraping techniques to retrieve all ticket listing information and saves it to a local database.

[0415] Step 2:

[0416] The server analyzes the ticket information stored in the local database. Here, it uses a generated inference model to determine if the listing price of each ticket exceeds the benchmark price. The benchmark price is the official selling price set by the organizer and is automatically referenced according to the list.

[0417] Step 3:

[0418] The server lists tickets that are being offered at a price exceeding the benchmark price. It also cross-references the excess price and seller information to create a detailed list.

[0419] Step 4:

[0420] The server sends a notification to the seller using a messaging service such as the LINE API for tickets with prices exceeding the limit. This notification includes the message, "The listing price has exceeded the standard price. An adjustment will be made."

[0421] Step 5:

[0422] The server automatically adjusts any listing price exceeding the limit to the base price. This process is performed remotely using the resale site's API, and the price is corrected immediately.

[0423] Step 6:

[0424] The server then relists the tickets for which price adjustments have been completed. The listing information on the platform is re-registered at the base price, making it possible to purchase them at the appropriate price.

[0425] Step 7:

[0426] The server logs the completion of a series of processes and prepares for the next scheduled task. This includes detailed information such as the time taken for the actions performed and the number of adjustments made.

[0427] (Example 1)

[0428] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0429] In the current ticket market, fraudulent price gouging is depriving prospective buyers of the opportunity to purchase tickets at a fair price. This problem is particularly pronounced for popular events and undermines the health of the market. Therefore, there is a need for a method that automatically detects and adjusts listings with unfair pricing while maintaining a benchmark ticket price.

[0430] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0431] In this invention, the server includes means for an information processing device to collect data from a ticket trading medium, means for the information processing device to identify data exceeding a benchmark price using a data analysis function, and means for the information processing device to transmit a notification using an information transmission device in order to adjust the price of the identified data. This makes it possible to create a fair trading market by automatically detecting and adjusting unfair prices.

[0432] An "information processing device" is a device that has the functions of collecting, analyzing, and managing data, and is primarily used as a server to process information in ticket transactions.

[0433] A "ticket trading platform" refers to any platform that facilitates the buying and selling of tickets online or offline, and the platform that manages the ticket information circulating within it.

[0434] "Data analysis functionality" refers to technologies used to detect specific patterns or anomalies based on collected data, and involves the use of specific algorithms or generative AI models.

[0435] The "benchmark price" refers to a standard selling price that is recognized as fair in ticket transactions, and is a basic benchmark price set by the platform.

[0436] An "information transmission device" is a device used to send notifications and information to sellers and prospective buyers, and it uses messaging services via a communication interface.

[0437] A "generated intelligent reasoning model" is an algorithm created based on past data and market trends, and is a data analysis model aimed at price setting and detecting anomalies in transactions.

[0438] "Digital media" refers to a medium for transmitting data and information online, and is a broad concept that includes internet services and applications.

[0439] A "data provider" refers to an individual or legal entity that registers sales information with a ticket trading platform, and is a user who acts as a seller.

[0440] One embodiment of the present invention is a method in which the information processing device is used as a server. The server connects to a ticket trading medium via the internet and periodically collects ticket sales information. This mainly utilizes web scraping technology and publicly available APIs.

[0441] The server stores the collected data in its internal database and performs data analysis using a generated intelligent inference model. This inference model learns from past transaction data and existing market trends, making it capable of detecting abnormal pricing that exceeds the benchmark price.

[0442] If an anomaly is detected, the server uses an information transmission device to send a notification to the data provider on the ticket trading platform, prompting them to adjust the price. Since the notification is sent in real time using digital media, sellers can quickly understand the situation and take action.

[0443] As a concrete example, consider a scenario where the benchmark price for tickets to a certain music event is set at 5,000 yen. When the server collects data from ticket trading platforms and identifies a listing at 7,000 yen, a notification is sent to the seller, and the price is adjusted to the benchmark price. This ensures fair trading.

[0444] A concrete example of a prompt message is, "Check the current ticket price and what adjustments should be made to maintain a fair price?" This prompt is the driving force behind the data analysis and price adjustment process, which utilizes a generative AI model.

[0445] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0446] Step 1:

[0447] The server connects to ticket trading platforms and uses web scraping techniques and APIs to collect data such as ticket IDs, event names, listing prices, and reference prices from those platforms. It accepts URLs of trading platforms or API endpoints as input and constructs the acquired dataset as output. Specifically, the server sends HTTP requests, parses the returned JSON data, and extracts the necessary information.

[0448] Step 2:

[0449] The server stores the collected data in an internal database. Using the dataset collected in step 1 as input, it generates information stored in the database as output. Specifically, it inserts the analyzed data into the appropriate table in the database and saves it in a searchable and updateable format.

[0450] Step 3:

[0451] The server analyzes the stored data using the generated intelligent reasoning model. The input includes ticket information retrieved from the database, and the output identifies listings that exceed the base price. In this step, the AI ​​model analyzes the input data and detects abnormal pricing. Specifically, the AI ​​model compares each price to the base price and sets an outlier flag based on the result.

[0452] Step 4:

[0453] The server uses a data transmission device to send notifications to sellers regarding listings whose prices exceed a certain threshold. It receives data with an abnormal flag as input and generates a notification message as output. Specifically, it sends a notification to the seller's registered device via the LINE API or other messaging services stating, "Your listing exceeds the price limit. Please adjust the price."

[0454] Step 5:

[0455] The server automatically adjusts the prices of identified anomaly tickets. Input includes listing information and a base price, and output generates adjusted price information. Specifically, it updates the relevant entries in the database and corrects the ticket prices to match the base price.

[0456] Step 6:

[0457] The server re-registers the adjusted data with the platform. The updated ticket data is used as input, and the normalized price information is delivered as output. Specifically, the server calls the platform's update API, re-edits the ticket with the corrected price, and publishes it.

[0458] (Application Example 1)

[0459] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0460] On e-commerce platforms, product prices can be unfairly set, resulting in consumers being at risk of purchasing goods at unreasonably high prices. There is a need to detect such unfair pricing and provide consumers with goods at fair prices.

[0461] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0462] In this invention, the server includes means for collecting information from an e-commerce platform, means for detecting transactions where the product price exceeds a benchmark price from the collected information, and means for sending notifications to adjust the product price of the detected transactions to the benchmark price. This makes it possible to create an environment in which consumers can purchase goods at a fair price.

[0463] An "e-commerce platform" is an online platform used for buying and selling goods and services over the internet.

[0464] "Means for collecting information" refers to devices or technologies that have the function of automatically acquiring the prices and transaction information of products on the platform.

[0465] "Means for detecting transactions where the commodity price exceeds the benchmark price" refers to a device or technology that has the function of determining whether the commodity price exceeds a predetermined benchmark price based on collected information.

[0466] "Means for sending notifications" refers to a device or technology equipped with communication functions for transmitting information about detected transactions to sellers and related parties.

[0467] A "standard price" is a price standard that is set in advance as reasonable and fair for the selling price of goods or services.

[0468] In order to implement this invention, it is necessary to build a system that involves the cooperation of a server, a terminal, and a user.

[0469] The server collects product information from e-commerce platforms. This is done using APIs or scraping techniques. The collected data is analyzed based on a trained model generated using the Scikit-learn library developed in Python. This analysis detects transactions where the product price exceeds a set benchmark price.

[0470] If a transaction exceeding the benchmark price is detected, the server sends a notification to the seller via a communication method. A messaging API is used for this purpose. The notification immediately informs the seller that the product price will be adjusted based on the benchmark price.

[0471] After the price adjustment is made, the transaction is re-registered on the platform, allowing users to purchase the product at a fair price. Users with devices can check the fair price of the product and obtain information through the application.

[0472] As a concrete example, suppose a newly released clothing item has a base price of 1000 yen. If the server detects that the item is being sold for 1200 yen on an e-commerce platform, a notification is sent to the seller, and the price of the item is adjusted to 1000 yen. In this way, a more transparent market environment can be provided to consumers.

[0473] Examples of prompts to input to a generative AI model include: "Generative AI model, tell me how to monitor for fraudulent pricing on e-commerce sites and display accurate prices."

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The server collects product information from e-commerce platforms. It uses the platform's API or scraping techniques as input to obtain product names, prices, product IDs, etc. The output is formally organized product information stored in a database.

[0477] Step 2:

[0478] The server uses a generative AI model to detect price anomalies based on the collected product information. The input is a dataset of product information, and data processing such as price standardization and filtering is performed. The output is a list of anomaly prices that exceed the baseline price.

[0479] Step 3:

[0480] The server, upon detecting an abnormal price, sends a notification to the seller via a communication method. The input is a list of abnormal prices and the seller's contact information, and the output is the notification message sent via the messaging API. The seller is informed that the product price will be adjusted based on the benchmark price.

[0481] Step 4:

[0482] The server re-registers product transactions adjusted to the benchmark price. The input is the correct adjusted product price, and the output is the transaction information re-registered on the platform. This provides an environment where consumers can purchase goods at a fair price.

[0483] Step 5:

[0484] Users can check the fair price of products through an application on their device. The input is the latest product information obtained from the platform, and the output is the fair price information displayed on the device screen. Based on this information, users can make purchasing decisions.

[0485] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0486] This invention provides a system that monitors sales pricing on a ticket trading platform to prevent fraudulent price gouging, and also enables effective notifications that take user sentiment into consideration. This system operates server-centric and integrates multiple functions.

[0487] First, the server periodically accesses the ticket trading platform to retrieve the latest ticket listing information. This data includes ticket IDs, event names, listing prices, and reference prices. This data is stored in a local database and used in the next analysis step.

[0488] Next, the server analyzes the collected data using the generated inference model. This model determines whether the listing price of each ticket exceeds the threshold price. For listings that exceed the threshold price, the sentiment engine prepares to analyze the user's emotional state.

[0489] The emotion engine estimates the emotions a particular user might be currently experiencing based on past interaction data with that user. For example, if emotions such as dissatisfaction or surprise are detected, the server takes this into account and adjusts the content and tone of notification messages accordingly.

[0490] Subsequently, the server sends a appropriately tailored notification message to the seller via a communication interface such as the LINE API. In this step, the seller is notified in a way that is sensitive to their feelings that their listing will be adjusted to match the benchmark price.

[0491] As a specific example, consider a case where a server adjusts a seller's ticket price from 7,000 yen to a base price of 5,000 yen. If the seller might resist the price change, the emotion engine anticipates their feelings and adjusts the notification message to be polite and easy to understand. For example, a message such as, "Based on current market analysis, we have made an appropriate price adjustment. We appreciate your understanding," might be sent.

[0492] Thus, this system, which incorporates an emotion engine, not only adjusts ticket prices but also contributes to creating a smoother transaction environment by providing notifications that appeal to the seller's emotions.

[0493] The following describes the processing flow.

[0494] Step 1:

[0495] The server accesses the ticket trading platform according to a pre-configured schedule and collects information on tickets being offered for sale. This includes data such as ticket ID, event name, listing price, and reference price, and is obtained using APIs or scraping techniques.

[0496] Step 2:

[0497] The server stores the collected ticket information in a local database, then uses a generated inference model to analyze the data and detect transactions where the listing price exceeds the benchmark price. Based on this analysis, a list of these excess transactions is created along with seller information.

[0498] Step 3:

[0499] The emotion engine receives a list of detected listings exceeding the listed price and analyzes the user's past interaction data to estimate their current emotional state. Emotions such as dissatisfaction, resistance, and understanding are considered.

[0500] Step 4:

[0501] Based on the analysis results of the emotion engine, the server creates a customized notification message tailored to the user's emotions. This message aims to reduce the psychological burden on sellers by carefully explaining why a price revision is necessary.

[0502] Step 5:

[0503] The server sends a notification message to the seller, which has been adjusted using a communication interface such as the LINE API. Here, the server confirms that the seller has received the notification, and their response can be used for future analysis.

[0504] Step 6:

[0505] The server automatically adjusts the listing price that exceeds the limit to the base price and re-registers it with the resale site. It verifies whether the re-registration was successful and saves the result as a log in the database.

[0506] Step 7:

[0507] The server logs the completion of a series of processes and prepares for the next scheduled process. This information will be used to optimize and improve future transactions.

[0508] (Example 2)

[0509] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0510] In current ticket trading, the problem of reselling tickets at prices significantly exceeding the standard price is a major issue. Furthermore, it is difficult to properly notify sellers when adjusting the selling price, hindering smooth transactions. In this situation, there is a need for a method that can effectively notify sellers while taking their feelings into consideration.

[0511] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0512] In this invention, the server includes means for collecting data from an information processing device, means for detecting transactions where the sales amount exceeds a standard amount from the collected data, and means for sending notifications adjusted based on sentiment analysis for the detected transactions. This enables smooth transactions by providing notifications regarding adjustments to the sales amount in a manner that takes into account the seller's sentiment.

[0513] An "information processing device" is a computer system used to collect and analyze data, and it is responsible for connecting to databases and networks to acquire various types of information.

[0514] "Data" is a general term for information related to ticket transactions, and includes information such as ticket ID, event name, sales price, and base price.

[0515] "Selling price" refers to the price set by the seller when selling tickets on the ticket trading platform.

[0516] The "standard price" refers to a benchmark value set as the appropriate selling price for tickets, and is an indicator used to determine whether the selling price exceeds this value.

[0517] "Transaction" refers to a sales contract and related activities conducted on a ticket trading platform.

[0518] "Sentiment analysis" refers to the analytical process performed to estimate a user's emotional state based on their past behavior and transaction history.

[0519] "Notification" refers to the activity of sending appropriate information or messages to the seller based on detected transactions.

[0520] "Communication means" is a general term for the lines and protocols used to transmit data and messages between an information processing device and an exhibitor, and includes network interfaces and APIs.

[0521] This invention relates to a system for preventing fraudulent resale at inflated prices in ticket transactions and for providing effective notifications that take into account the user's psychological state. The system is composed of multiple functions, mainly integrating an information processing device, a generative AI model, and an emotion analysis engine.

[0522] First, the server periodically retrieves the latest data through the ticket trading platform's API. This data includes ticket IDs, event names, sales amounts, and base amounts, and is stored in a local database in a structured format.

[0523] Next, the server uses a generative AI model to analyze the collected data. The AI ​​model has learned from past price trends and market information, and determines whether the sales amount exceeds a certain threshold. Data suspected of being fraudulent transactions is extracted separately.

[0524] The sentiment analysis engine is activated by the server and estimates the potential emotions a seller might be experiencing based on past interaction data with the user. This allows for measures to be taken to minimize the psychological impact that price adjustment notifications have on sellers.

[0525] Subsequently, the server generates a notification message based on the sentiment analysis results and sends it to the seller via the network interface, which is the means of communication. This procedure ensures that the seller receives a message with appropriate content, facilitating a smooth transaction.

[0526] For example, if a ticket listed for 7,000 yen has a baseline price of 5,000 yen, the AI ​​model will determine this price difference to be abnormal. The sentiment analysis engine considers the seller's past transaction history and, if it determines that the seller may be dissatisfied, the notification message will be designed to encourage understanding.

[0527] This invention makes it possible to send price adjustment notifications in a way that takes into account the seller's feelings, thereby greatly contributing to the smooth operation of the transaction environment. An example of a prompt message to the generating AI model would be, "In setting the price for ticket transactions, how should we analyze each user's feelings and adjust the notification content based on that?"

[0528] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0529] Step 1:

[0530] The server accesses the ticket trading platform's API to retrieve the latest listing data.

[0531] Input: API endpoint of the ticket trading platform.

[0532] Specific operation: Send an API request to retrieve listing information including ticket ID, event name, selling price, and base price.

[0533] Output: The retrieved listing data is saved in a structured format to the server's local database.

[0534] Step 2:

[0535] The server collects data, which is then input into an AI model for analysis.

[0536] Input: Listing data stored on the server.

[0537] Specific operation: Data is fed into the AI ​​model to determine whether the sales price of each listing exceeds a certain threshold.

[0538] Output: A list of transactions that were determined to exceed the threshold amount is created.

[0539] Step 3:

[0540] The server uses an emotion analysis engine to estimate the seller's emotional state.

[0541] Input: Transaction data exceeding a certain threshold and past user interaction data.

[0542] Specific operation: The emotion analysis engine estimates the emotions the seller might be experiencing (e.g., dissatisfaction or surprise).

[0543] Output: Estimated results are generated based on the emotional state.

[0544] Step 4:

[0545] The server generates a notification message based on the sentiment analysis results and sends it to the seller.

[0546] Input: Sentiment analysis results and transaction data exceeding a threshold amount.

[0547] Specific actions: Generate a notification message with emotionally sensitive content and tone, and send it to the seller via communication means.

[0548] Output: The adjusted notification message received by the seller.

[0549] (Application Example 2)

[0550] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0551] In recent years, fraudulent high-priced transactions and resales have become a social problem on ticket trading platforms and electronic payment networks. However, current systems do not adequately consider user sentiment when adjusting transaction prices, which can lead to dissatisfaction and resistance from sellers. To solve these problems and ensure smooth transactions, effective measures are needed to prevent fraudulent transactions while taking user sentiment into consideration.

[0552] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0553] In this invention, the server includes means for collecting information from an information processing network, means for identifying transactions where the transaction price exceeds a benchmark price from the collected information, and means for generating notification messages that take into account the user's feelings regarding the identified transactions and transmitting the information. This makes it possible to prevent fraudulent transactions while transmitting information in a way that takes into account the feelings of the seller.

[0554] An "information processing network" is a system in which multiple computers and systems are interconnected in order to effectively collect, analyze, and transmit data and information.

[0555] "Transaction price" refers to the monetary value set in the buying and selling of goods or services, and is the basis for comparison with the benchmark price.

[0556] A "reference price" is a standard price used for evaluating and comparing transaction prices, and serves as an indicator for maintaining fair trade.

[0557] "Trade" refers to the exchange or sale of goods and services, and in this context specifically refers to transactions involving tickets and electronic payment products.

[0558] "Identification" is the process of identifying and classifying items that meet specific criteria based on collected information, and it is a technique used for monitoring and verifying transactions.

[0559] A "notification message" is a short message in which a system communicates information or instructions to a user, and in this context, it specifically refers to messages that are generated with emotions in mind.

[0560] "Considering the user's emotions" means predicting the recipient's emotional state during information transmission and adjusting the content and expression accordingly.

[0561] The system for implementing this invention consists of a server and a user terminal. The server operates on an information processing network and collects various transaction information from the platform. Specifically, the server uses crawling technology to periodically retrieve price information for goods and services from the trading platform. This process is typically implemented using the Python library BeautifulSoup.

[0562] The server manages the collected information as a Pandas DataFrame and uses an inference model built with TensorFlow to analyze whether the trading price exceeds the benchmark price. If an excess is detected, the server uses NLTK and OpenAI GPT to generate a notification message that takes the user's sentiment into account. Based on the user's past trading data and reaction history, it generates prompts to create a message with an appropriate tone, and this message is sent to the user via the LINE API.

[0563] As a concrete example, if the server detects a potentially fraudulent transaction involving tax evasion within the electronic payment platform, it sends a message to the seller stating, "Based on market analysis, we request that you revise the transaction price. We appreciate your understanding." This generated message helps users reduce emotional resistance while promoting transactions at fair prices.

[0564] An example of a prompt might be: "Analyze the seller's sentiment based on their past response patterns and generate a message requesting a price adjustment in an appropriate tone." This setting allows the server to provide flexible and effective notifications based on sentiment.

[0565] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0566] Step 1:

[0567] The server periodically accesses the trading platform from the information processing network and retrieves the latest trading data using the API or web crawling technology it employs. This retrieved data includes product ID, event name, trading price, and base price. It receives data collected from the trading platform as input and transforms it into a structured dataset as output.

[0568] Step 2:

[0569] The server organizes the collected data into a Pandas DataFrame, preparing it for analysis. This DataFrame is managed using Python data analysis tools, which take the raw data as input and generate data in DataFrame format as output.

[0570] Step 3:

[0571] The server executes an inference model built using TensorFlow to determine whether a transaction price exceeds a baseline price. The input is price information in dataframe format, and the output is a list of transactions whose prices exceed the baseline price. This step involves performing price determination based on the model as a data calculation.

[0572] Step 4:

[0573] The server analyzes the seller's past transaction history and response data for transactions where an excess has been detected, and generates a sentiment-sensitive notification message using NLTK and OpenAI GPT. The input is the identified transaction and the seller's past data, and the output is a sentiment-sensitive notification message.

[0574] Step 5:

[0575] The server sends the generated notification message to the seller using the LINE API. The input is the generated notification message, and the output is confirmation that the message was sent successfully. The server monitors the message delivery status via the communication interface.

[0576] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0577] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0578] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0579] [Fourth Embodiment]

[0580] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0581] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0582] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0583] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0584] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0585] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0586] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0587] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0588] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0589] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0590] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0591] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0592] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0593] The present invention provides a method for detecting fraudulent price gouging on ticket trading platforms and enabling resale at fairer prices. This system is primarily managed by a server and is designed to automatically monitor and adjust ticket pricing.

[0594] First, the server periodically retrieves the latest ticket information from the ticket trading platform. This involves collecting ticket IDs, event names, listing prices, and reference prices through scraping techniques and publicly available APIs.

[0595] Next, the server analyzes the collected data and uses a generated inference model to identify transactions where the listing price exceeds a set benchmark price. This model enables price anomaly detection based on historical data and market trends.

[0596] The server sends a warning message via a communication interface to ticket sellers whose prices exceed the benchmark price. This message is implemented using a messaging service such as the LINE API, allowing sellers to immediately know that their listings will be adjusted based on the benchmark price.

[0597] The server then adjusts the price of any tickets exceeding the standard price on the platform and re-registers them on the platform. This process ensures that potential buyers can obtain tickets at a fair price.

[0598] As a concrete example, consider a case where tickets for a music event are being sold at a base price of 5,000 yen. If the server detects that a ticket is being offered for 7,000 yen on a resale platform, the price of that listing will be adjusted. The server will notify the seller and ask them to revise the listing to 5,000 yen and re-register it. In this way, event organizers can more easily manage the distribution of tickets at fair prices, and consumers can be provided with a market where they can trade with peace of mind.

[0599] The following describes the processing flow.

[0600] Step 1:

[0601] The server accesses the ticket trading platform as a regularly scheduled task and begins collecting data. Specifically, it uses APIs or web scraping techniques to retrieve all ticket listing information and saves it to a local database.

[0602] Step 2:

[0603] The server analyzes the ticket information stored in the local database. Here, it uses a generated inference model to determine if the listing price of each ticket exceeds the benchmark price. The benchmark price is the official selling price set by the organizer and is automatically referenced according to the list.

[0604] Step 3:

[0605] The server lists tickets that are being offered at a price exceeding the benchmark price. It also cross-references the excess price and seller information to create a detailed list.

[0606] Step 4:

[0607] The server sends a notification to the seller using a messaging service such as the LINE API for tickets with prices exceeding the limit. This notification includes the message, "The listing price has exceeded the standard price. An adjustment will be made."

[0608] Step 5:

[0609] The server automatically adjusts any listing price exceeding the limit to the base price. This process is performed remotely using the resale site's API, and the price is corrected immediately.

[0610] Step 6:

[0611] The server then relists the tickets for which price adjustments have been completed. The listing information on the platform is re-registered at the base price, making it possible to purchase them at the appropriate price.

[0612] Step 7:

[0613] The server logs the completion of a series of processes and prepares for the next scheduled task. This includes detailed information such as the time taken for the actions performed and the number of adjustments made.

[0614] (Example 1)

[0615] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0616] In the current ticket market, fraudulent price gouging is depriving prospective buyers of the opportunity to purchase tickets at a fair price. This problem is particularly pronounced for popular events and undermines the health of the market. Therefore, there is a need for a method that automatically detects and adjusts listings with unfair pricing while maintaining a benchmark ticket price.

[0617] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0618] In this invention, the server includes means for an information processing device to collect data from a ticket trading medium, means for the information processing device to identify data exceeding a benchmark price using a data analysis function, and means for the information processing device to transmit a notification using an information transmission device in order to adjust the price of the identified data. This makes it possible to create a fair trading market by automatically detecting and adjusting unfair prices.

[0619] An "information processing device" is a device that has the functions of collecting, analyzing, and managing data, and is primarily used as a server to process information in ticket transactions.

[0620] A "ticket trading platform" refers to any platform that facilitates the buying and selling of tickets online or offline, and the platform that manages the ticket information circulating within it.

[0621] "Data analysis functionality" refers to technologies used to detect specific patterns or anomalies based on collected data, and involves the use of specific algorithms or generative AI models.

[0622] The "benchmark price" refers to a standard selling price that is recognized as fair in ticket transactions, and is a basic benchmark price set by the platform.

[0623] An "information transmission device" is a device used to send notifications and information to sellers and prospective buyers, and it uses messaging services via a communication interface.

[0624] A "generated intelligent reasoning model" is an algorithm created based on past data and market trends, and is a data analysis model aimed at price setting and detecting anomalies in transactions.

[0625] "Digital media" refers to a medium for transmitting data and information online, and is a broad concept that includes internet services and applications.

[0626] A "data provider" refers to an individual or legal entity that registers sales information with a ticket trading platform, and is a user who acts as a seller.

[0627] One embodiment of the present invention is a method in which the information processing device is used as a server. The server connects to a ticket trading medium via the internet and periodically collects ticket sales information. This mainly utilizes web scraping technology and publicly available APIs.

[0628] The server stores the collected data in its internal database and performs data analysis using a generated intelligent inference model. This inference model learns from past transaction data and existing market trends, making it capable of detecting abnormal pricing that exceeds the benchmark price.

[0629] If an anomaly is detected, the server uses an information transmission device to send a notification to the data provider on the ticket trading platform, prompting them to adjust the price. Since the notification is sent in real time using digital media, sellers can quickly understand the situation and take action.

[0630] As a concrete example, consider a scenario where the benchmark price for tickets to a certain music event is set at 5,000 yen. When the server collects data from ticket trading platforms and identifies a listing at 7,000 yen, a notification is sent to the seller, and the price is adjusted to the benchmark price. This ensures fair trading.

[0631] A concrete example of a prompt message is, "Check the current ticket price and what adjustments should be made to maintain a fair price?" This prompt is the driving force behind the data analysis and price adjustment process, which utilizes a generative AI model.

[0632] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0633] Step 1:

[0634] The server connects to ticket trading platforms and uses web scraping techniques and APIs to collect data such as ticket IDs, event names, listing prices, and reference prices from those platforms. It accepts URLs of trading platforms or API endpoints as input and constructs the acquired dataset as output. Specifically, the server sends HTTP requests, parses the returned JSON data, and extracts the necessary information.

[0635] Step 2:

[0636] The server stores the collected data in an internal database. Using the dataset collected in step 1 as input, it generates information stored in the database as output. Specifically, it inserts the analyzed data into the appropriate table in the database and saves it in a searchable and updateable format.

[0637] Step 3:

[0638] The server analyzes the stored data using the generated intelligent reasoning model. The input includes ticket information retrieved from the database, and the output identifies listings that exceed the base price. In this step, the AI ​​model analyzes the input data and detects abnormal pricing. Specifically, the AI ​​model compares each price to the base price and sets an outlier flag based on the result.

[0639] Step 4:

[0640] The server uses a data transmission device to send notifications to sellers regarding listings whose prices exceed a certain threshold. It receives data with an abnormal flag as input and generates a notification message as output. Specifically, it sends a notification to the seller's registered device via the LINE API or other messaging services stating, "Your listing exceeds the price limit. Please adjust the price."

[0641] Step 5:

[0642] The server automatically adjusts the prices of identified anomaly tickets. Input includes listing information and a base price, and output generates adjusted price information. Specifically, it updates the relevant entries in the database and corrects the ticket prices to match the base price.

[0643] Step 6:

[0644] The server re-registers the adjusted data with the platform. The updated ticket data is used as input, and the normalized price information is delivered as output. Specifically, the server calls the platform's update API, re-edits the ticket with the corrected price, and publishes it.

[0645] (Application Example 1)

[0646] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] On e-commerce platforms, product prices can be unfairly set, resulting in consumers being at risk of purchasing goods at unreasonably high prices. There is a need to detect such unfair pricing and provide consumers with goods at fair prices.

[0648] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0649] In this invention, the server includes means for collecting information from an e-commerce platform, means for detecting transactions where the product price exceeds a benchmark price from the collected information, and means for sending notifications to adjust the product price of the detected transactions to the benchmark price. This makes it possible to create an environment in which consumers can purchase goods at a fair price.

[0650] An "e-commerce platform" is an online platform used for buying and selling goods and services over the internet.

[0651] "Means for collecting information" refers to devices or technologies that have the function of automatically acquiring the prices and transaction information of products on the platform.

[0652] "Means for detecting transactions where the commodity price exceeds the benchmark price" refers to a device or technology that has the function of determining whether the commodity price exceeds a predetermined benchmark price based on collected information.

[0653] "Means for sending notifications" refers to a device or technology equipped with communication functions for transmitting information about detected transactions to sellers and related parties.

[0654] A "standard price" is a price standard that is set in advance as reasonable and fair for the selling price of goods or services.

[0655] In order to implement this invention, it is necessary to build a system that involves the cooperation of a server, a terminal, and a user.

[0656] The server collects product information from e-commerce platforms. This is done using APIs or scraping techniques. The collected data is analyzed based on a trained model generated using the Scikit-learn library developed in Python. This analysis detects transactions where the product price exceeds a set benchmark price.

[0657] If a transaction exceeding the benchmark price is detected, the server sends a notification to the seller via a communication method. A messaging API is used for this purpose. The notification immediately informs the seller that the product price will be adjusted based on the benchmark price.

[0658] After the price adjustment is made, the transaction is re-registered on the platform, allowing users to purchase the product at a fair price. Users with devices can check the fair price of the product and obtain information through the application.

[0659] As a concrete example, suppose a newly released clothing item has a base price of 1000 yen. If the server detects that the item is being sold for 1200 yen on an e-commerce platform, a notification is sent to the seller, and the price of the item is adjusted to 1000 yen. In this way, a more transparent market environment can be provided to consumers.

[0660] Examples of prompts to input to a generative AI model include: "Generative AI model, tell me how to monitor for fraudulent pricing on e-commerce sites and display accurate prices."

[0661] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0662] Step 1:

[0663] The server collects product information from e-commerce platforms. It uses the platform's API or scraping techniques as input to obtain product names, prices, product IDs, etc. The output is formally organized product information stored in a database.

[0664] Step 2:

[0665] The server uses a generative AI model to detect price anomalies based on the collected product information. The input is a dataset of product information, and data processing such as price standardization and filtering is performed. The output is a list of anomaly prices that exceed the baseline price.

[0666] Step 3:

[0667] The server, upon detecting an abnormal price, sends a notification to the seller via a communication method. The input is a list of abnormal prices and the seller's contact information, and the output is the notification message sent via the messaging API. The seller is informed that the product price will be adjusted based on the benchmark price.

[0668] Step 4:

[0669] The server re-registers product transactions adjusted to the benchmark price. The input is the correct adjusted product price, and the output is the transaction information re-registered on the platform. This provides an environment where consumers can purchase goods at a fair price.

[0670] Step 5:

[0671] Users can check the fair price of products through an application on their device. The input is the latest product information obtained from the platform, and the output is the fair price information displayed on the device screen. Based on this information, users can make purchasing decisions.

[0672] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0673] This invention provides a system that monitors sales pricing on a ticket trading platform to prevent fraudulent price gouging, and also enables effective notifications that take user sentiment into consideration. This system operates server-centric and integrates multiple functions.

[0674] First, the server periodically accesses the ticket trading platform to retrieve the latest ticket listing information. This data includes ticket IDs, event names, listing prices, and reference prices. This data is stored in a local database and used in the next analysis step.

[0675] Next, the server analyzes the collected data using the generated inference model. This model determines whether the listing price of each ticket exceeds the threshold price. For listings that exceed the threshold price, the sentiment engine prepares to analyze the user's emotional state.

[0676] The emotion engine estimates the emotions a particular user might be currently experiencing based on past interaction data with that user. For example, if emotions such as dissatisfaction or surprise are detected, the server takes this into account and adjusts the content and tone of notification messages accordingly.

[0677] Subsequently, the server sends a appropriately tailored notification message to the seller via a communication interface such as the LINE API. In this step, the seller is notified in a way that is sensitive to their feelings that their listing will be adjusted to match the benchmark price.

[0678] As a specific example, consider a case where a server adjusts a seller's ticket price from 7,000 yen to a base price of 5,000 yen. If the seller might resist the price change, the emotion engine anticipates their feelings and adjusts the notification message to be polite and easy to understand. For example, a message such as, "Based on current market analysis, we have made an appropriate price adjustment. We appreciate your understanding," might be sent.

[0679] Thus, this system, which incorporates an emotion engine, not only adjusts ticket prices but also contributes to creating a smoother transaction environment by providing notifications that appeal to the seller's emotions.

[0680] The following describes the processing flow.

[0681] Step 1:

[0682] The server accesses the ticket trading platform according to a pre-configured schedule and collects information on tickets being offered for sale. This includes data such as ticket ID, event name, listing price, and reference price, and is obtained using APIs or scraping techniques.

[0683] Step 2:

[0684] The server stores the collected ticket information in a local database, then uses a generated inference model to analyze the data and detect transactions where the listing price exceeds the benchmark price. Based on this analysis, a list of these excess transactions is created along with seller information.

[0685] Step 3:

[0686] The emotion engine receives a list of detected listings exceeding the listed price and analyzes the user's past interaction data to estimate their current emotional state. Emotions such as dissatisfaction, resistance, and understanding are considered.

[0687] Step 4:

[0688] Based on the analysis results of the emotion engine, the server creates a customized notification message tailored to the user's emotions. This message aims to reduce the psychological burden on sellers by carefully explaining why a price revision is necessary.

[0689] Step 5:

[0690] The server sends a notification message to the seller, which has been adjusted using a communication interface such as the LINE API. Here, the server confirms that the seller has received the notification, and their response can be used for future analysis.

[0691] Step 6:

[0692] The server automatically adjusts the listing price that exceeds the limit to the base price and re-registers it with the resale site. It verifies whether the re-registration was successful and saves the result as a log in the database.

[0693] Step 7:

[0694] The server logs the completion of a series of processes and prepares for the next scheduled process. This information will be used to optimize and improve future transactions.

[0695] (Example 2)

[0696] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] In current ticket trading, the problem of reselling tickets at prices significantly exceeding the standard price is a major issue. Furthermore, it is difficult to properly notify sellers when adjusting the selling price, hindering smooth transactions. In this situation, there is a need for a method that can effectively notify sellers while taking their feelings into consideration.

[0698] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0699] In this invention, the server includes means for collecting data from an information processing device, means for detecting transactions where the sales amount exceeds a standard amount from the collected data, and means for sending notifications adjusted based on sentiment analysis for the detected transactions. This enables smooth transactions by providing notifications regarding adjustments to the sales amount in a manner that takes into account the seller's sentiment.

[0700] An "information processing device" is a computer system used to collect and analyze data, and it is responsible for connecting to databases and networks to acquire various types of information.

[0701] "Data" is a general term for information related to ticket transactions, and includes information such as ticket ID, event name, sales price, and base price.

[0702] "Selling price" refers to the price set by the seller when selling tickets on the ticket trading platform.

[0703] The "standard price" refers to a benchmark value set as the appropriate selling price for tickets, and is an indicator used to determine whether the selling price exceeds this value.

[0704] "Transaction" refers to a sales contract and related activities conducted on a ticket trading platform.

[0705] "Sentiment analysis" refers to the analytical process performed to estimate a user's emotional state based on their past behavior and transaction history.

[0706] "Notification" refers to the activity of sending appropriate information or messages to the seller based on detected transactions.

[0707] "Communication means" is a general term for the lines and protocols used to transmit data and messages between an information processing device and an exhibitor, and includes network interfaces and APIs.

[0708] This invention relates to a system for preventing fraudulent resale at inflated prices in ticket transactions and for providing effective notifications that take into account the user's psychological state. The system is composed of multiple functions, mainly integrating an information processing device, a generative AI model, and an emotion analysis engine.

[0709] First, the server periodically retrieves the latest data through the ticket trading platform's API. This data includes ticket IDs, event names, sales amounts, and base amounts, and is stored in a local database in a structured format.

[0710] Next, the server uses a generative AI model to analyze the collected data. The AI ​​model has learned from past price trends and market information, and determines whether the sales amount exceeds a certain threshold. Data suspected of being fraudulent transactions is extracted separately.

[0711] The sentiment analysis engine is activated by the server and estimates the potential emotions a seller might be experiencing based on past interaction data with the user. This allows for measures to be taken to minimize the psychological impact that price adjustment notifications have on sellers.

[0712] Subsequently, the server generates a notification message based on the sentiment analysis results and sends it to the seller via the network interface, which is the means of communication. This procedure ensures that the seller receives a message with appropriate content, facilitating a smooth transaction.

[0713] For example, if a ticket listed for 7,000 yen has a baseline price of 5,000 yen, the AI ​​model will determine this price difference to be abnormal. The sentiment analysis engine considers the seller's past transaction history and, if it determines that the seller may be dissatisfied, the notification message will be designed to encourage understanding.

[0714] This invention makes it possible to send price adjustment notifications in a way that takes into account the seller's feelings, thereby greatly contributing to the smooth operation of the transaction environment. An example of a prompt message to the generating AI model would be, "In setting the price for ticket transactions, how should we analyze each user's feelings and adjust the notification content based on that?"

[0715] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0716] Step 1:

[0717] The server accesses the ticket trading platform's API to retrieve the latest listing data.

[0718] Input: API endpoint of the ticket trading platform.

[0719] Specific operation: Send an API request to retrieve listing information including ticket ID, event name, selling price, and base price.

[0720] Output: The retrieved listing data is saved in a structured format to the server's local database.

[0721] Step 2:

[0722] The server collects data, which is then input into an AI model for analysis.

[0723] Input: Listing data stored on the server.

[0724] Specific operation: Data is fed into the AI ​​model to determine whether the sales price of each listing exceeds a certain threshold.

[0725] Output: A list of transactions that were determined to exceed the threshold amount is created.

[0726] Step 3:

[0727] The server uses an emotion analysis engine to estimate the seller's emotional state.

[0728] Input: Transaction data exceeding a certain threshold and past user interaction data.

[0729] Specific operation: The emotion analysis engine estimates the emotions the seller might be experiencing (e.g., dissatisfaction or surprise).

[0730] Output: Estimated results are generated based on the emotional state.

[0731] Step 4:

[0732] The server generates a notification message based on the sentiment analysis results and sends it to the seller.

[0733] Input: Sentiment analysis results and transaction data exceeding a threshold amount.

[0734] Specific actions: Generate a notification message with emotionally sensitive content and tone, and send it to the seller via communication means.

[0735] Output: The adjusted notification message received by the seller.

[0736] (Application Example 2)

[0737] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0738] In recent years, fraudulent high-priced transactions and resales have become a social problem on ticket trading platforms and electronic payment networks. However, current systems do not adequately consider user sentiment when adjusting transaction prices, which can lead to dissatisfaction and resistance from sellers. To solve these problems and ensure smooth transactions, effective measures are needed to prevent fraudulent transactions while taking user sentiment into consideration.

[0739] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0740] In this invention, the server includes means for collecting information from an information processing network, means for identifying transactions where the transaction price exceeds a benchmark price from the collected information, and means for generating notification messages that take into account the user's feelings regarding the identified transactions and transmitting the information. This makes it possible to prevent fraudulent transactions while transmitting information in a way that takes into account the feelings of the seller.

[0741] An "information processing network" is a system in which multiple computers and systems are interconnected in order to effectively collect, analyze, and transmit data and information.

[0742] "Transaction price" refers to the monetary value set in the buying and selling of goods or services, and is the basis for comparison with the benchmark price.

[0743] A "reference price" is a standard price used for evaluating and comparing transaction prices, and serves as an indicator for maintaining fair trade.

[0744] "Trade" refers to the exchange or sale of goods and services, and in this context specifically refers to transactions involving tickets and electronic payment products.

[0745] "Identification" is the process of identifying and classifying items that meet specific criteria based on collected information, and it is a technique used for monitoring and verifying transactions.

[0746] A "notification message" is a short message in which a system communicates information or instructions to a user, and in this context, it specifically refers to messages that are generated with emotions in mind.

[0747] "Considering the user's emotions" means predicting the recipient's emotional state during information transmission and adjusting the content and expression accordingly.

[0748] The system for implementing this invention consists of a server and a user terminal. The server operates on an information processing network and collects various transaction information from the platform. Specifically, the server uses crawling technology to periodically retrieve price information for goods and services from the trading platform. This process is typically implemented using the Python library BeautifulSoup.

[0749] The server manages the collected information as a Pandas DataFrame and uses an inference model built with TensorFlow to analyze whether the trading price exceeds the benchmark price. If an excess is detected, the server uses NLTK and OpenAI GPT to generate a notification message that takes the user's sentiment into account. Based on the user's past trading data and reaction history, it generates prompts to create a message with an appropriate tone, and this message is sent to the user via the LINE API.

[0750] As a concrete example, if the server detects a potentially fraudulent transaction involving tax evasion within the electronic payment platform, it sends a message to the seller stating, "Based on market analysis, we request that you revise the transaction price. We appreciate your understanding." This generated message helps users reduce emotional resistance while promoting transactions at fair prices.

[0751] An example of a prompt might be: "Analyze the seller's sentiment based on their past response patterns and generate a message requesting a price adjustment in an appropriate tone." This setting allows the server to provide flexible and effective notifications based on sentiment.

[0752] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0753] Step 1:

[0754] The server periodically accesses the trading platform from the information processing network and retrieves the latest trading data using the API or web crawling technology it employs. This retrieved data includes product ID, event name, trading price, and base price. It receives data collected from the trading platform as input and transforms it into a structured dataset as output.

[0755] Step 2:

[0756] The server organizes the collected data into a Pandas DataFrame, preparing it for analysis. This DataFrame is managed using Python data analysis tools, which take the raw data as input and generate data in DataFrame format as output.

[0757] Step 3:

[0758] The server executes an inference model built using TensorFlow to determine whether a transaction price exceeds a baseline price. The input is price information in dataframe format, and the output is a list of transactions whose prices exceed the baseline price. This step involves performing price determination based on the model as a data calculation.

[0759] Step 4:

[0760] The server analyzes the seller's past transaction history and response data for transactions where an excess has been detected, and generates a sentiment-sensitive notification message using NLTK and OpenAI GPT. The input is the identified transaction and the seller's past data, and the output is a sentiment-sensitive notification message.

[0761] Step 5:

[0762] The server sends the generated notification message to the seller using the LINE API. The input is the generated notification message, and the output is confirmation that the message was sent successfully. The server monitors the message delivery status via the communication interface.

[0763] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0764] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0765] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0766] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0767] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0768] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0769] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0770] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0771] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0772] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0773] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0774] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0775] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0776] 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.

[0777] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0778] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using this memory.

[0779] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0780] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0781] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0782] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0783] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0784] The following is further disclosed regarding the embodiments described above.

[0785] (Claim 1)

[0786] Means of collecting information from ticket trading platforms,

[0787] A means of detecting transactions where the selling price exceeds the benchmark price from the collected information,

[0788] A means of sending a notification to adjust the selling price of detected transactions to the base price,

[0789] A means to re-register transactions adjusted to the benchmark price,

[0790] A system that includes this.

[0791] (Claim 2)

[0792] The system according to claim 1, wherein the data collection means includes the step of analyzing data using a generated inference model and comparing the selling price with a reference price.

[0793] (Claim 3)

[0794] The system according to claim 1, wherein the notification means includes the step of transmitting information to the seller via a communication interface.

[0795] "Example 1"

[0796] (Claim 1)

[0797] The means by which the information processing device collects data from the ticket transaction medium,

[0798] The information processing device uses its data analysis function to identify data that exceeds the benchmark price,

[0799] A means for sending a notification using an information transmission device in order to adjust the price of the identified data,

[0800] A means for the information processing device to re-register the adjusted data,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the data collection means includes the step of analyzing the data using a generated intelligent inference model and comparing it with a reference price.

[0804] (Claim 3)

[0805] The system according to claim 1, wherein the information transmission means includes the step of transmitting information to a data provider via a digital medium.

[0806] "Application Example 1"

[0807] (Claim 1)

[0808] Means of collecting information from e-commerce platforms,

[0809] A means of detecting transactions where the commodity price exceeds the benchmark price from the collected information,

[0810] A means of sending a notification to adjust the product price to the base price for detected transactions,

[0811] A means to re-register transactions adjusted to the benchmark price,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, wherein the collection means includes the step of analyzing data using a generated learning model and comparing product prices with a reference price.

[0815] (Claim 3)

[0816] The system according to claim 1, wherein the notification means includes the step of transmitting information to the seller via a communication means.

[0817] "Example 2 of combining an emotion engine"

[0818] (Claim 1)

[0819] A means of collecting data from an information processing device,

[0820] A means of detecting transactions in which the sales amount exceeds a certain threshold from the collected data,

[0821] A means of sending notifications adjusted based on sentiment analysis for detected transactions,

[0822] A means to re-register transactions that have been adjusted to the base amount,

[0823] A system that includes this.

[0824] (Claim 2)

[0825] The system according to claim 1, wherein the data collection means includes the step of analyzing the data using a generative inference method and comparing the sales amount with a reference amount.

[0826] (Claim 3)

[0827] The system according to claim 1, wherein the notification means includes the step of transmitting information via a communication means.

[0828] "Application example 2 when combining with an emotional engine"

[0829] (Claim 1)

[0830] Means for collecting information from an information processing network,

[0831] A means of identifying transactions where the transaction price exceeds the benchmark price from the collected information,

[0832] Regarding identified trades, a means of transmitting information in order to adjust the transaction price to a base price,

[0833] A means of generating notification messages that take user emotions into consideration and conveying information,

[0834] A means of re-registering trades adjusted to a benchmark price,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, wherein the collection means includes the step of analyzing data using a generated inference model and comparing the transaction price with a reference price.

[0838] (Claim 3)

[0839] The system according to claim 1, wherein the notification means includes the step of supplying information to a trader via a communication interface. [Explanation of Symbols]

[0840] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting information from ticket trading platforms, A means of detecting transactions where the selling price exceeds the benchmark price from the collected information, A means of sending a notification to adjust the selling price of detected transactions to the base price, A means to re-register transactions adjusted to the benchmark price, A system that includes this.

2. The system according to claim 1, wherein the data collection means includes the step of analyzing data using a generated inference model and comparing the selling price with a reference price.

3. The system according to claim 1, wherein the notification means includes the step of transmitting information to the seller via a communication interface.

Images