system

Abstract

We provide the system. [Solution] A data collection method for obtaining ticket transfer information, A data analysis means for detecting inappropriate prices based on the above transfer information, A price adjustment mechanism that corrects and resets the detected price to a reference price, A data transfer means for notifying the user of adjustment information, Transaction management methods to ensure fair resale prices through electronic transactions, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] Illegal high-price reselling of tickets for events and concerts is widespread, resulting in many cases where tickets are traded at prices higher than the original price range. As a result, it has become difficult for ordinary consumers to obtain tickets at a proper price, which also has an adverse impact on the reliability and customer satisfaction of event companies. Therefore, it is required to prevent illegal high-price reselling of tickets and provide a fair trading environment for consumers.

Means for Solving the Problems

[0005] This invention provides a means for automatically acquiring and analyzing ticket resale information. Specifically, it has a function to detect inappropriate prices using a machine learning model and correct the price of detected overpriced resale tickets to a standard price. It also provides a system that includes means for notifying users of this correction information using an information and communication service API. This ensures that tickets are always available at a fair price and suppresses fraudulent overpriced resales.

[0006] "Information acquisition means" refers to an element that has the function of automatically collecting ticket resale information from online resale platforms.

[0007] A "price analysis tool" is an element that uses a machine learning model to evaluate price data in order to determine whether the collected resale information is priced appropriately.

[0008] A "price revision mechanism" is an element that has the function of correcting and resetting a price to a standard or fixed price when an inappropriate price is detected.

[0009] "Information transmission means" refers to an element that has the function of automatically notifying users of revised ticket prices via an information and communication service API.

[0010] A "machine learning model" is a group of algorithms that learn from large amounts of data and perform analysis and predictions with high accuracy even on new data.

[0011] An "information and communication service API" is a mechanism that provides an interface for sending and receiving information between applications, enabling communication using specific services. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

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

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

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

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention relates to the resale of event tickets and is a system for preventing the fraudulent and high-priced resale of tickets conducted through online platforms. This system is composed of a combination of information acquisition means, price analysis means, price revision means, and information transmission means.

[0034] The server periodically collects ticket resale information from the resale platform. Using APIs or web scraping techniques, it obtains ticket prices, seller information, and sales status. This information is stored in a database for subsequent steps.

[0035] The server passes the acquired resale information to a price analysis tool. The price analysis tool uses a machine learning model to analyze the data and determine whether the resale price is inappropriately high compared to the original price. This analysis utilizes historical data and standard price ranges for similar events.

[0036] Next, the server uses a price adjustment mechanism to correct the prices of tickets that the analysis determined to be overpriced to their face value. This correction information is reflected in the resale platform in real time, ensuring that the prices of tickets currently on sale are always kept within the standard range.

[0037] Finally, the server uses information transmission methods, including APIs from information and communication services such as LINE, to notify the user's device of the revised price. This notification clearly states that the revised ticket price is fair, allowing the user to proceed with the purchase with confidence.

[0038] As a concrete example, if concert tickets for a famous artist are being resold at inflated prices on resale websites, this system can automatically adjust the price back to the original retail price. As a result, consumers can purchase tickets with confidence, and problems caused by illegal resale can be prevented. Through this entire process, event organizers can increase customer trust and continue to provide a fair trading environment.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server accesses the resale platform to retrieve ticket resale information. Specifically, it collects data such as ticket IDs, resale prices, seller information, and sales status via API or web scraping, and stores it in a database.

[0042] Step 2:

[0043] The server prepares the collected data for the price analysis tool. It formats the data to make it suitable for analysis so that the AI ​​model can begin processing it.

[0044] Step 3:

[0045] The AI ​​agent uses price analysis tools and machine learning models to evaluate ticket prices. It compares them with past sales data and market standards to determine whether the current price is inappropriately high.

[0046] Step 4:

[0047] The server receives the analysis results from the AI ​​agent and adjusts the prices of tickets deemed inappropriate. Using a price revision method, it corrects the price of the relevant tickets to the regular price and updates the information.

[0048] Step 5:

[0049] The server uses an information and communication service API to notify users that prices have been revised. It sends a message on the digital platform registered by the user, informing them that the revised tickets are available at the correct price.

[0050] Step 6:

[0051] Users check the received notification and purchase tickets offered at a fair price. After completing the purchase, users can participate in the event with peace of mind.

[0052] (Example 1)

[0053] 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."

[0054] The illegal resale of tickets at exorbitant prices on online platforms is a serious problem, and there is a need for a fair and secure trading environment. Traditional systems are insufficient to address this issue, and a mechanism is needed to monitor and adjust prices in real time.

[0055] 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.

[0056] In this invention, the server includes means for acquiring data related to ticket resale using an information gathering medium, means for analyzing fraudulent prices by comparing them with market prices using the above data, and means for changing prices determined to be fraudulent to market standard prices. This makes it possible to correct fraudulent resale prices in real time on an online platform and provide a fair and secure trading environment.

[0057] "Information gathering media" refers to technical means for obtaining data related to ticket resale from online platforms, and includes APIs and web scraping technologies.

[0058] "Analysis means" refers to technical means for detecting fraudulent pricing in ticket resales by comparing acquired data with market prices.

[0059] A "computational model" is a model that uses machine learning algorithms to analyze data and determine fraudulent pricing.

[0060] "Means of modification" refers to technical means for correcting an unfair price to a market-standard price after detection, and includes a function to reflect the correction information on the resale platform.

[0061] A "notification means" is a technical means for informing users of updated price information via a communication interface.

[0062] An "information transmission device" is a technology that transmits updated price information to external devices or user terminals using a communication network, and uses protocols such as APIs.

[0063] This invention is a system aimed at preventing the illegal resale of tickets on online platforms. Specific embodiments of the invention are described below.

[0064] The server first uses data collection tools to retrieve information about ticket resales from the resale platform. This process utilizes APIs and web scraping techniques to collect data such as ticket prices, seller information, and sales status. The collected information is stored in a database, preparing it for subsequent processing.

[0065] Next, the server passes the collected data to the analysis tool. The analysis tool uses a computational model to analyze the data and determine whether the resale price is inappropriately high compared to the original price. This model is trained on historical data and price information from similar events, and it is possible to incorporate a generative AI model.

[0066] If an invalid price is detected, the server uses a modification mechanism to correct the resale price to the market standard price. This operation is immediately reflected on the resale platform, ensuring that users can always purchase at a fair price.

[0067] Finally, the server uses a notification system to send the updated price information to the user's terminal via an information transmission device. This allows the user to confirm that the price is correct and proceed with the transaction with confidence.

[0068] For example, if concert tickets for a famous artist are being traded at unfairly high prices on resale sites, this system can automatically adjust the price to the face value. This allows consumers to purchase tickets at a fair price and prevents problems caused by illegal resale. An example of a prompt message might be, "Please describe a system that monitors the resale prices of tickets for famous artists in real time and adjusts the price to the face value if it is unfairly high."

[0069] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0070] Step 1:

[0071] The server uses information gathering media to retrieve ticket resale information from resale platforms. Inputs include requests using APIs and web scraping techniques, and output includes data such as ticket prices, seller information, and sales status. The server temporarily caches this data and stores it in a database for subsequent processing.

[0072] Step 2:

[0073] The server passes resale data retrieved from the database to the analysis tool. The data obtained as input is analyzed using a computational model. Utilizing a generative AI model, it determines whether the pricing is fraudulent by comparing it with past event data and market trends. As output, a list of resale data deemed fraudulent is generated.

[0074] Step 3:

[0075] The server uses a mechanism to change the price of tickets that are determined to be priced unfairly based on the analysis. As input, it receives data on the unfair pricing and adjusts the price to the market standard price based on this data. As output, the corrected price information is immediately reflected on the resale platform, and the list of tickets for sale is updated.

[0076] Step 4:

[0077] The server sends the updated price information to the user's terminal via a notification system. The revised price information is provided as input, and a push notification is sent to the user via an information transmission device as output. The notification includes justification for the price change and its details, allowing the user to trade with confidence.

[0078] (Application Example 1)

[0079] 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."

[0080] The resale of tickets at inflated prices on online platforms poses a problem that harms consumers through unfair pricing. Furthermore, such fraudulent practices undermine the fair market for events and erode consumer trust. Moreover, maintaining unfair prices through electronic transactions is difficult to address quickly, resulting in many consumers being unable to purchase goods at fair prices.

[0081] 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.

[0082] In this invention, the server includes data collection means, data analysis means, and price adjustment means. This makes it possible to detect fraudulent resale of tickets on an online platform and enable transactions at a fair price based on the original price.

[0083] "Data collection methods" refer to technical techniques for obtaining ticket transfer information from online platforms.

[0084] "Data analysis methods" refer to algorithms and tools used to detect inappropriate pricing based on acquired transfer information.

[0085] A "price adjustment measure" is a process for correcting and resetting detected inappropriate prices to a reference price.

[0086] "Data transfer means" refers to communication technology used to transmit adjusted price information to users.

[0087] A "transaction management system" is a system that regulates ticket resale prices through electronic transactions and supervises and manages buying and selling transactions.

[0088] The system that implements this invention operates with a server at its core. The server first uses data collection methods to obtain ticket transfer information from online platforms. This typically involves using APIs or web scraping techniques. The obtained information is stored in a database, preparing the system for the next steps.

[0089] Next, the server uses data analysis tools to evaluate whether the transfer price is inappropriate based on the collected information. Here, machine learning algorithms (e.g., TENSORFLOW® or Scikit-learn) are used to enable analysis based on historical data and market trends. If an inappropriate price is detected as a result of the analysis, the price is adjusted to a benchmark price using price adjustment tools.

[0090] The corrected price information is communicated to the user via a data transfer method. This communication utilizes information exchange service APIs such as the LINE Messaging API. This allows users to receive accurate price information in real time and purchase tickets with confidence.

[0091] As a concrete example, if concert tickets for a famous music group are being resold at inflated prices on a resale site, this system can be used to automatically adjust the price to the standard price and notify the user of the fair price. As a result, consumers benefit from being able to purchase tickets without being bothered by unfair pricing.

[0092] An example of a prompt for a generated AI model is, "Develop a machine learning model to detect ticket resale prices and write Python code to prevent price gouging."

[0093] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0094] Step 1:

[0095] The server uses data collection methods to obtain ticket transfer information from online platforms. In this step, APIs or web scraping techniques are used to collect ticket prices, transfer status, seller information, etc., and store them in a database. The input is the transfer information from the online platform, and the output is the raw data stored in the database.

[0096] Step 2:

[0097] The server uses data analysis tools to detect inappropriate pricing based on collected transfer information. It employs machine learning algorithms, analyzing data based on past sales data and standard market price ranges. The input is transfer information obtained from a database, and the output is the result of the inappropriate pricing determination.

[0098] Step 3:

[0099] The server uses price adjustment mechanisms to correct detected inappropriate prices to the standard price. This correction resets the ticket price to the correct price. The input is the result of the inappropriate price detection, and the output is the corrected price information.

[0100] Step 4:

[0101] The server notifies the user's terminal of the corrected price information via a data transfer method. Price information is transmitted in real time using communication methods such as the LINE Messaging API. The input is the corrected price information, and the output is a notification of the appropriate price to the user.

[0102] Step 5:

[0103] The user receives a notification and considers purchasing a ticket based on the optimized price information. In this step, the user checks the price information on their device and decides whether to proceed with the transaction with confidence. The input is the price information displayed on the device, and the output is the user's purchase decision.

[0104] 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.

[0105] This invention is a system that combines an emotion engine not only to prevent the fraudulent resale of tickets at inflated prices, but also to improve the user's purchasing experience. The system comprises an information acquisition means, a price analysis means, a price revision means, an information transmission means, and an emotion engine.

[0106] The server retrieves ticket resale information from the resale platform and uses price analysis tools to identify inappropriate prices based on that information. A machine learning model is used to analyze the prices while comparing them to a standard price range. Tickets deemed overpriced are then adjusted to their face value using a price revision mechanism.

[0107] Price revision information is sent from the server to the terminal, and the emotion engine plays a crucial role in this process. The emotion engine analyzes user patterns and behavior logs to infer the user's emotional state. Specifically, it detects emotions such as purchase intent and satisfaction, and personalizes the information presented to each user according to their needs.

[0108] For example, if it is detected that a user has been a fan of a particular artist in the past, the emotion engine uses that information to directly notify the user that the ticket price has been adjusted and sends a personalized message encouraging them to purchase. This increases the user's willingness to buy and ensures a trustworthy transaction.

[0109] Furthermore, based on the notifications users receive, they are directed to the pages of events they are interested in. There, they can purchase tickets with confidence and enjoy a satisfying user experience. By considering the individual emotions of each user, this system aims not only to deter illegal resale but also to personalize and enhance the entire user purchasing process. This contributes to improving the brand value of event companies and attracting new customers.

[0110] The following describes the processing flow.

[0111] Step 1:

[0112] The server periodically collects ticket resale information from multiple resale platforms via scraping or APIs. The collected information includes ticket prices, seller information, and sales status, and this is temporarily stored in a database.

[0113] Step 2:

[0114] The server inputs the collected resale information into a price analysis system and uses a machine learning model to diagnose whether the price is inappropriate. Based on past transaction history and market prices, it determines whether the ticket price deviates from the market price.

[0115] Step 3:

[0116] The server receives the results of the price analysis and corrects any prices detected as inappropriate to the standard price or list price using the price revision mechanism. This correction is automatically reflected on the resale platform.

[0117] Step 4:

[0118] The server activates the emotion engine and performs sentiment analysis based on the user profile. It infers the user's current emotional state (e.g., excitement, willingness to buy) from past purchase history, browsing patterns, and behavioral history.

[0119] Step 5:

[0120] The server optimizes notification messages based on the output of the emotion engine and sends the revised price information to the user's device using an information transmission method. The notification content is personalized according to the user's emotional state.

[0121] Step 6:

[0122] Users check the notifications they receive on their devices and visit the resale platform based on those notifications. They can then purchase tickets offered at a fair price and prepare to attend the event with peace of mind.

[0123] (Example 2)

[0124] 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".

[0125] To provide a system that prevents fraudulent price gouging and improves the user's purchasing experience. In particular, to promote purchase intent and establish reliable transactions by considering the user's emotional state and providing personalized information.

[0126] 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.

[0127] In this invention, the server includes acquisition means for acquiring transaction information, analysis means for detecting inappropriate prices based on the transaction information, revision means for correcting and resetting the detected price to a reference price, sentiment analysis means for analyzing the user's behavior log to infer their emotional state, and transmission means for individualizing and notifying information based on the sentiment analysis results. This makes it possible to provide appropriate price notifications that take emotions into account for each user, and to provide a personalized user experience that enhances purchasing intent.

[0128] "Transaction information" refers to detailed data related to the buying and selling of goods, including price, date and time, and seller information.

[0129] "Means of acquisition" refers to functions or devices used to collect specific information or data from external sources.

[0130] "Analysis methods" refer to methods and techniques for identifying trends and anomalies based on collected data and for conducting evaluations.

[0131] "Revision methods" refer to functions or processes for making changes to new values ​​or states that conform to standards, based on existing information.

[0132] "Emotional analysis methods" refer to technologies and methods for inferring and evaluating a user's emotional state based on their behavioral logs and usage history.

[0133] "Transmission means" refers to the equipment and methods used to deliver information or data to a specific destination.

[0134] "Reference price" refers to a price that is considered fair in the fair trade of goods, set within the standard price range in the market.

[0135] This invention is a system for processing transaction information, preventing fraudulent resale at inflated prices, and improving the user's purchasing experience. This system is realized through the involvement of three entities: a server, a terminal, and a user, each fulfilling their respective roles.

[0136] The server first retrieves transaction information from the resale platform using an API. The hardware used here is a server computer, and programming languages ​​such as Python and JavaScript (registered trademark) are used to process API requests. The retrieved information includes product price, seller information, and sale date and time.

[0137] Next, the server performs price analysis using a machine learning model. This analysis utilizes Python libraries such as TensorFlow and Scikit-learn. If an inappropriate price is detected, it is corrected to a benchmark price using a price revision mechanism and updated in the database.

[0138] The device collects user activity logs and usage history. Based on this, an emotion analysis system analyzes the user's emotional state. This analysis uses data such as the user's click history and access times to infer specific emotional states and purchase intentions. This triggers an emotion engine to generate personalized messages based on the user's interests.

[0139] The generated message is sent to the user's device by the server. Information and communication services such as email and push notifications are used, and the information is personalized during this process. Based on the content of the notification, the user is guided to the event page of interest and can purchase the desired ticket with confidence.

[0140] For example, if a user's past purchase history indicates they are a fan of a particular artist, the sentiment engine will notify them of appropriate pricing information related to that artist's events. For instance, by passing the prompt "Please tell me what message the sentiment engine should send to a specific user, along with the reason why" to the generating AI model, an appropriate message will be created.

[0141] Thus, this system provides an effective means of preventing illegal resale and making the user's purchasing experience personalized and appealing.

[0142] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0143] Step 1:

[0144] The server retrieves transaction information through the resale platform's API. The input is response data from the API, which includes ticket prices, seller information, and the date and time of sale. The retrieved data is stored in JSON format, and this data stream forms the basis for the next processing step. Specifically, periodic API calls are made, and data collection and storage are performed as routine processes.

[0145] Step 2:

[0146] The server passes the acquired transaction information to an analysis tool for price analysis. The input is the transaction information in JSON format saved in step 1. A machine learning model, such as TensorFlow, is used to compare the price with standard price levels. At this stage, inappropriate prices are detected, and the results are recorded in the data as flags. Specifically, the model uses historical price data to find price anomalies.

[0147] Step 3:

[0148] If an inappropriate price is detected, the server corrects it to the baseline price using a revision mechanism. The input is the ticket information flagged as an anomaly in step 2. The output is the corrected price data, which is updated in the database. Specifically, an SQL query is executed, and the price field is replaced with the baseline price.

[0149] Step 4:

[0150] The device collects user behavior logs and usage history and analyzes them using sentiment analysis techniques. Inputs include click history and access times when the user interacts with the application. This allows the system to estimate the user's purchase intent and satisfaction level, and generate an emotional state evaluation as output. Specifically, the sentiment model is triggered by the log data to profile the user's needs.

[0151] Step 5:

[0152] The server executes a means of sending personalized notifications based on the sentiment analysis results. The inputs are the sentiment evaluation results from step 4 and the adjusted price data from step 3. The output is a notification message customized for each user, which is sent as email or push notification. Specifically, the message generation and delivery process is performed via an API. In this process, prompts are given to the generation AI model, which then determines "what kind of message is appropriate for a particular user" and creates the message.

[0153] (Application Example 2)

[0154] 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".

[0155] Preventing the fraudulent resale of tickets at inflated prices is paramount, as is the urgent need to personalize the user's purchasing experience and increase their willingness to buy. However, conventional systems have the problem of not being able to appropriately judge the emotions and interests of buyers and provide a personalized experience accordingly. Therefore, the present invention aims to provide a technology that realizes a purchasing experience that reflects the emotional state of the user.

[0156] 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.

[0157] In this invention, the server includes information acquisition means for generating buyer options, emotion analysis means for analyzing the user's emotions, and information generation means for composing notifications according to the user's emotional state. This makes it possible to provide a more attractive purchasing experience through personalized notifications that take into account each user's individual interests and preferences.

[0158] "Buyer options" refer to the types and content of products and services that users can choose from.

[0159] "Information acquisition means" refers to methods and technologies for obtaining necessary data and information.

[0160] "Emotional analysis techniques" refer to technologies that analyze a user's behavior and data to determine their emotions and psychological state.

[0161] "Information generation means" refers to a technology or method for creating information to be provided to users based on collected data.

[0162] "Composing a notification" refers to organizing the information that needs to be conveyed to the user and preparing it in a specific format.

[0163] "Information transmission means" refers to the technologies and methods used to deliver generated information to users via a network.

[0164] A "system" refers to a collection of devices, software, and networks that are combined to realize a series of processes or functions.

[0165] A "user" refers to an individual or group that uses a system or service.

[0166] A "machine learning model" refers to an algorithm that learns patterns and rules from large amounts of data to perform predictions and analyses.

[0167] An "information and communication service API" is an interface for exchanging data between various services and platforms.

[0168] This system first uses an information acquisition tool to collect ticket options from the resale platform. Next, it uses sentiment analysis tools to capture activity logs of potential buyers and analyzes this data to infer the user's interests and emotional state. In this process, the server primarily uses machine learning models (e.g., TensorFlow) written in Python to process the data.

[0169] For example, by analyzing past purchase history, browsing history, and click data, sentiment analysis can be used to identify a user's high level of interest in a particular music artist. Based on this information, the server uses information generation tools to create specialized notifications about events that the user is likely to be interested in.

[0170] As a concrete example, suppose a user has previously purchased concert tickets for the same band multiple times. Using this data, a generative AI model can be used to create a prompt message like this: "Predict and suggest the user's potential interest in a new live event."

[0171] Finally, the server sends a personalized notification, generated through the information transmission means, to the user's terminal. This notification is delivered quickly and securely using an information and communication service API. In this way, personalized information tailored to the user's interests can be provided, improving the purchasing experience.

[0172] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0173] Step 1:

[0174] The server retrieves ticket sales information from the resale platform using an information acquisition method. The input is data obtained from the resale platform's API, which includes ticket prices and event information. The output generates a list of tickets necessary for subsequent analysis.

[0175] Step 2:

[0176] The server uses a machine learning model to analyze the fairness of prices based on acquired ticket data. The input is ticket price data, which the AI ​​model compares to an appropriate price range. For data processing, the model uses historical price data to calculate a standard price range. The output is the detection result for inappropriate prices.

[0177] Step 3:

[0178] If a price is deemed inappropriate, the server uses price revision mechanisms to correct them to the standard price. The input is a list of tickets with invalid prices, and the algorithm generates price data corrected to the standard price. The output is the corrected price data.

[0179] Step 4:

[0180] The server acquires user activity logs through sentiment analysis and analyzes the user's interests and emotional state. It uses past purchase and browsing history data as input, and based on this, it uses an AI model to generate AI prompts to predict user interests. The output is the analysis result reflecting the user's interests and emotional state.

[0181] Step 5:

[0182] Based on the analysis results, the server generates personalized notifications for each user using information generation methods. The input is the sentiment analysis results from the previous stage, and a customized message based on those results is generated as output.

[0183] Step 6:

[0184] The server sends notifications generated through information transmission means to the user's terminal using an information communication service API. The input is the generated notification message, and the output is the notification content displayed on the user's terminal that receives it.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Second Embodiment]

[0189] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0190] 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.

[0191] 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).

[0192] 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.

[0193] 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.

[0194] 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).

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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".

[0201] This invention relates to the resale of event tickets and is a system for preventing the fraudulent and high-priced resale of tickets conducted through online platforms. This system is composed of a combination of information acquisition means, price analysis means, price revision means, and information transmission means.

[0202] The server periodically collects ticket resale information from the resale platform. Using APIs or web scraping techniques, it obtains ticket prices, seller information, and sales status. This information is stored in a database for subsequent steps.

[0203] The server passes the acquired resale information to a price analysis tool. The price analysis tool uses a machine learning model to analyze the data and determine whether the resale price is inappropriately high compared to the original price. This analysis utilizes historical data and standard price ranges for similar events.

[0204] Next, the server uses a price adjustment mechanism to correct the prices of tickets that the analysis determined to be overpriced to their face value. This correction information is reflected in the resale platform in real time, ensuring that the prices of tickets currently on sale are always kept within the standard range.

[0205] Finally, the server uses information transmission methods, including APIs from information and communication services such as LINE, to notify the user's device of the revised price. This notification clearly states that the revised ticket price is fair, allowing the user to proceed with the purchase with confidence.

[0206] As a concrete example, if concert tickets for a famous artist are being resold at inflated prices on resale websites, this system can automatically adjust the price back to the original retail price. As a result, consumers can purchase tickets with confidence, and problems caused by illegal resale can be prevented. Through this entire process, event organizers can increase customer trust and continue to provide a fair trading environment.

[0207] The following describes the processing flow.

[0208] Step 1:

[0209] The server accesses the resale platform to retrieve ticket resale information. Specifically, it collects data such as ticket IDs, resale prices, seller information, and sales status via API or web scraping, and stores it in a database.

[0210] Step 2:

[0211] The server prepares the collected data for the price analysis tool. It formats the data to make it suitable for analysis so that the AI ​​model can begin processing it.

[0212] Step 3:

[0213] The AI ​​agent uses price analysis tools and machine learning models to evaluate ticket prices. It compares them with past sales data and market standards to determine whether the current price is inappropriately high.

[0214] Step 4:

[0215] The server receives the analysis results from the AI ​​agent and adjusts the prices of tickets deemed inappropriate. Using a price revision method, it corrects the price of the relevant tickets to the regular price and updates the information.

[0216] Step 5:

[0217] The server uses an information and communication service API to notify users that prices have been revised. It sends a message on the digital platform registered by the user, informing them that the revised tickets are available at the correct price.

[0218] Step 6:

[0219] Users check the received notification and purchase tickets offered at a fair price. After completing the purchase, users can participate in the event with peace of mind.

[0220] (Example 1)

[0221] 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".

[0222] The illegal resale of tickets at exorbitant prices on online platforms is a serious problem, and there is a need for a fair and secure trading environment. Traditional systems are insufficient to address this issue, and a mechanism is needed to monitor and adjust prices in real time.

[0223] 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.

[0224] In this invention, the server includes means for acquiring data related to ticket resale using an information gathering medium, means for analyzing fraudulent prices by comparing them with market prices using the above data, and means for changing prices determined to be fraudulent to market standard prices. This makes it possible to correct fraudulent resale prices in real time on an online platform and provide a fair and secure trading environment.

[0225] "Information gathering media" refers to technical means for obtaining data related to ticket resale from online platforms, and includes APIs and web scraping technologies.

[0226] "Analysis means" refers to technical means for detecting fraudulent pricing in ticket resales by comparing acquired data with market prices.

[0227] A "computational model" is a model that uses machine learning algorithms to analyze data and determine fraudulent pricing.

[0228] "Means of modification" refers to technical means for correcting an unfair price to a market-standard price after detection, and includes a function to reflect the correction information on the resale platform.

[0229] A "notification means" is a technical means for informing users of updated price information via a communication interface.

[0230] An "information transmission device" is a technology that transmits updated price information to external devices or user terminals using a communication network, and uses protocols such as APIs.

[0231] This invention is a system aimed at preventing the illegal resale of tickets on online platforms. Specific embodiments of the invention are described below.

[0232] The server first uses data collection tools to retrieve information about ticket resales from the resale platform. This process utilizes APIs and web scraping techniques to collect data such as ticket prices, seller information, and sales status. The collected information is stored in a database, preparing it for subsequent processing.

[0233] Next, the server passes the collected data to the analysis tool. The analysis tool uses a computational model to analyze the data and determine whether the resale price is inappropriately high compared to the original price. This model is trained on historical data and price information from similar events, and it is possible to incorporate a generative AI model.

[0234] If an invalid price is detected, the server uses a modification mechanism to correct the resale price to the market standard price. This operation is immediately reflected on the resale platform, ensuring that users can always purchase at a fair price.

[0235] Finally, the server uses a notification system to send the updated price information to the user's terminal via an information transmission device. This allows the user to confirm that the price is correct and proceed with the transaction with confidence.

[0236] For example, if concert tickets for a famous artist are being traded at unfairly high prices on resale sites, this system can automatically adjust the price to the face value. This allows consumers to purchase tickets at a fair price and prevents problems caused by illegal resale. An example of a prompt message might be, "Please describe a system that monitors the resale prices of tickets for famous artists in real time and adjusts the price to the face value if it is unfairly high."

[0237] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0238] Step 1:

[0239] The server uses information gathering media to retrieve ticket resale information from resale platforms. Inputs include requests using APIs and web scraping techniques, and output includes data such as ticket prices, seller information, and sales status. The server temporarily caches this data and stores it in a database for subsequent processing.

[0240] Step 2:

[0241] The server passes resale data retrieved from the database to the analysis tool. The data obtained as input is analyzed using a computational model. Utilizing a generative AI model, it determines whether the pricing is fraudulent by comparing it with past event data and market trends. As output, a list of resale data deemed fraudulent is generated.

[0242] Step 3:

[0243] The server uses a mechanism to change the price of tickets that are determined to be priced unfairly based on the analysis. As input, it receives data on the unfair pricing and adjusts the price to the market standard price based on this data. As output, the corrected price information is immediately reflected on the resale platform, and the list of tickets for sale is updated.

[0244] Step 4:

[0245] The server sends the updated price information to the user's terminal via a notification system. The revised price information is provided as input, and a push notification is sent to the user via an information transmission device as output. The notification includes justification for the price change and its details, allowing the user to trade with confidence.

[0246] (Application Example 1)

[0247] 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."

[0248] The resale of tickets at inflated prices on online platforms poses a problem that harms consumers through unfair pricing. Furthermore, such fraudulent practices undermine the fair market for events and erode consumer trust. Moreover, maintaining unfair prices through electronic transactions is difficult to address quickly, resulting in many consumers being unable to purchase goods at fair prices.

[0249] 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.

[0250] In this invention, the server includes data collection means, data analysis means, and price adjustment means. This makes it possible to detect fraudulent resale of tickets on an online platform and enable transactions at a fair price based on the original price.

[0251] "Data collection methods" refer to technical techniques for obtaining ticket transfer information from online platforms.

[0252] "Data analysis methods" refer to algorithms and tools used to detect inappropriate pricing based on acquired transfer information.

[0253] A "price adjustment measure" is a process for correcting and resetting detected inappropriate prices to a reference price.

[0254] "Data transfer means" refers to communication technology used to transmit adjusted price information to users.

[0255] A "transaction management system" is a system that regulates ticket resale prices through electronic transactions and supervises and manages buying and selling transactions.

[0256] The system that implements this invention operates with a server at its core. The server first uses data collection methods to obtain ticket transfer information from online platforms. This typically involves using APIs or web scraping techniques. The obtained information is stored in a database, preparing the system for the next steps.

[0257] Next, the server uses data analysis tools to evaluate whether the transfer price is inappropriate based on the collected information. Here, machine learning algorithms (e.g., TensorFlow or Scikit-learn) can be used to perform analysis based on historical data and market trends. If an inappropriate price is detected as a result of the analysis, the price is adjusted to a benchmark price using price adjustment tools.

[0258] The corrected price information is communicated to the user via a data transfer method. This communication utilizes information exchange service APIs such as the LINE Messaging API. This allows users to receive accurate price information in real time and purchase tickets with confidence.

[0259] As a concrete example, if concert tickets for a famous music group are being resold at inflated prices on a resale site, this system can be used to automatically adjust the price to the standard price and notify the user of the fair price. As a result, consumers benefit from being able to purchase tickets without being bothered by unfair pricing.

[0260] An example of a prompt for a generated AI model is, "Develop a machine learning model to detect ticket resale prices and write Python code to prevent price gouging."

[0261] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0262] Step 1:

[0263] The server uses data collection methods to obtain ticket transfer information from online platforms. In this step, APIs or web scraping techniques are used to collect ticket prices, transfer status, seller information, etc., and store them in a database. The input is the transfer information from the online platform, and the output is the raw data stored in the database.

[0264] Step 2:

[0265] The server uses data analysis tools to detect inappropriate pricing based on collected transfer information. It employs machine learning algorithms, analyzing data based on past sales data and standard market price ranges. The input is transfer information obtained from a database, and the output is the result of the inappropriate pricing determination.

[0266] Step 3:

[0267] The server uses price adjustment mechanisms to correct detected inappropriate prices to the standard price. This correction resets the ticket price to the correct price. The input is the result of the inappropriate price detection, and the output is the corrected price information.

[0268] Step 4:

[0269] The server notifies the user's terminal of the corrected price information via a data transfer method. Price information is transmitted in real time using communication methods such as the LINE Messaging API. The input is the corrected price information, and the output is a notification of the appropriate price to the user.

[0270] Step 5:

[0271] The user receives a notification and considers purchasing a ticket based on the optimized price information. In this step, the user checks the price information on their device and decides whether to proceed with the transaction with confidence. The input is the price information displayed on the device, and the output is the user's purchase decision.

[0272] 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.

[0273] This invention is a system that combines an emotion engine not only to prevent the fraudulent resale of tickets at inflated prices, but also to improve the user's purchasing experience. The system comprises an information acquisition means, a price analysis means, a price revision means, an information transmission means, and an emotion engine.

[0274] The server retrieves ticket resale information from the resale platform and uses price analysis tools to identify inappropriate prices based on that information. A machine learning model is used to analyze the prices while comparing them to a standard price range. Tickets deemed overpriced are then adjusted to their face value using a price revision mechanism.

[0275] Price revision information is sent from the server to the terminal, and the emotion engine plays a crucial role in this process. The emotion engine analyzes user patterns and behavior logs to infer the user's emotional state. Specifically, it detects emotions such as purchase intent and satisfaction, and personalizes the information presented to each user according to their needs.

[0276] For example, if it is detected that a user has been a fan of a particular artist in the past, the emotion engine uses that information to directly notify the user that the ticket price has been adjusted and sends a personalized message encouraging them to purchase. This increases the user's willingness to buy and ensures a trustworthy transaction.

[0277] Furthermore, based on the notifications users receive, they are directed to the pages of events they are interested in. There, they can purchase tickets with confidence and enjoy a satisfying user experience. By considering the individual emotions of each user, this system aims not only to deter illegal resale but also to personalize and enhance the entire user purchasing process. This contributes to improving the brand value of event companies and attracting new customers.

[0278] The following describes the processing flow.

[0279] Step 1:

[0280] The server periodically collects ticket resale information from multiple resale platforms via scraping or APIs. The collected information includes ticket prices, seller information, and sales status, and this is temporarily stored in a database.

[0281] Step 2:

[0282] The server inputs the collected resale information into a price analysis system and uses a machine learning model to diagnose whether the price is inappropriate. Based on past transaction history and market prices, it determines whether the ticket price deviates from the market price.

[0283] Step 3:

[0284] The server receives the result of the price analysis means, and revises the price detected as inappropriate to the reference price or the list price by the price revision means. This revision is automatically reflected on the resale platform.

[0285] Step 4:

[0286] The server activates the emotion engine and performs emotion analysis based on the user profile. Infer the user's current emotional state (e.g., excitement, willingness to purchase) from past purchase history, browsing patterns, and behavior history.

[0287] Step 5:

[0288] The server optimizes the notification message based on the output of the emotion engine, and transmits the revised price information to the user's terminal using the information transmission means. The notification content is personalized according to the user's emotional state.

[0289] Step 6:

[0290] The user checks the notification received on their terminal and visits the resale platform based on it. Tickets provided at the appropriate price can be purchased, and preparations for event participation can be advanced with peace of mind.

[0291] (Example 2)

[0292] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0293] To provide a system that can prevent illegal high - price reselling and improve the user's purchase experience. In particular, by considering the user's emotional state and providing individualized information, it promotes the willingness to purchase and establishes a reliable transaction.

[0294] 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.

[0295] In this invention, the server includes acquisition means for acquiring transaction information, analysis means for detecting inappropriate prices based on the transaction information, revision means for correcting and resetting the detected price to a reference price, sentiment analysis means for analyzing the user's behavior log to infer their emotional state, and transmission means for individualizing and notifying information based on the sentiment analysis results. This makes it possible to provide appropriate price notifications that take emotions into account for each user, and to provide a personalized user experience that enhances purchasing intent.

[0296] "Transaction information" refers to detailed data related to the buying and selling of goods, including price, date and time, and seller information.

[0297] "Means of acquisition" refers to functions or devices used to collect specific information or data from external sources.

[0298] "Analysis methods" refer to methods and techniques for identifying trends and anomalies based on collected data and for conducting evaluations.

[0299] "Revision methods" refer to functions or processes for making changes to new values ​​or states that conform to standards, based on existing information.

[0300] "Emotional analysis methods" refer to technologies and methods for inferring and evaluating a user's emotional state based on their behavioral logs and usage history.

[0301] "Transmission means" refers to the equipment and methods used to deliver information or data to a specific destination.

[0302] "Reference price" refers to a price that is considered fair in the fair trade of goods, set within the standard price range in the market.

[0303] This invention is a system for processing transaction information to prevent illegal reselling at high prices while improving the user's purchase experience. This system is realized by three entities, namely the server, the terminal, and the user, each playing their respective roles.

[0304] First, the server obtains transaction information from the resale platform using an API. The hardware used here is a server computer, and programming languages such as Python or JavaScript are used to process API requests. The information obtained includes product prices, seller information, sales dates and times, etc.

[0305] Subsequently, the server performs price analysis using a machine learning model. Libraries in Python such as TensorFlow and Scikit-learn are utilized for this analysis. If an inappropriate price is detected, it is corrected to the reference price by the price revision means and updated in the database.

[0306] On the terminal, the user's behavior logs and usage history are collected. Based on this, sentiment analysis means analyzes the user's sentiment state. Data such as the user's click history and access time zone are used for this analysis, and a specific sentiment state and purchase intention are inferred. As a result, the sentiment engine operates to generate a specialized message based on the user's interests.

[0307] The generated message is sent by the server to the user's terminal. Information communication services such as email or push notifications are used, and at this time, the information is individualized. Based on the notified content, the user is guided to an event page of interest and can purchase the target ticket with confidence.

[0308] For example, if a user's past purchase history indicates they are a fan of a particular artist, the sentiment engine will notify them of appropriate pricing information related to that artist's events. For instance, by passing the prompt "Please tell me what message the sentiment engine should send to a specific user, along with the reason why" to the generating AI model, an appropriate message will be created.

[0309] Thus, this system provides an effective means of preventing illegal resale and making the user's purchasing experience personalized and appealing.

[0310] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0311] Step 1:

[0312] The server retrieves transaction information through the resale platform's API. The input is response data from the API, which includes ticket prices, seller information, and the date and time of sale. The retrieved data is stored in JSON format, and this data stream forms the basis for the next processing step. Specifically, periodic API calls are made, and data collection and storage are performed as routine processes.

[0313] Step 2:

[0314] The server passes the acquired transaction information to an analysis tool for price analysis. The input is the transaction information in JSON format saved in step 1. A machine learning model, such as TensorFlow, is used to compare the price with standard price levels. At this stage, inappropriate prices are detected, and the results are recorded in the data as flags. Specifically, the model uses historical price data to find price anomalies.

[0315] Step 3:

[0316] If an inappropriate price is detected, the server corrects it to the baseline price using a revision mechanism. The input is the ticket information flagged as an anomaly in step 2. The output is the corrected price data, which is updated in the database. Specifically, an SQL query is executed, and the price field is replaced with the baseline price.

[0317] Step 4:

[0318] The device collects user behavior logs and usage history and analyzes them using sentiment analysis techniques. Inputs include click history and access times when the user interacts with the application. This allows the system to estimate the user's purchase intent and satisfaction level, and generate an emotional state evaluation as output. Specifically, the sentiment model is triggered by the log data to profile the user's needs.

[0319] Step 5:

[0320] The server executes a means of sending personalized notifications based on the sentiment analysis results. The inputs are the sentiment evaluation results from step 4 and the adjusted price data from step 3. The output is a notification message customized for each user, which is sent as email or push notification. Specifically, the message generation and delivery process is performed via an API. In this process, prompts are given to the generation AI model, which then determines "what kind of message is appropriate for a particular user" and creates the message.

[0321] (Application Example 2)

[0322] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0323] Preventing the fraudulent resale of tickets at inflated prices is paramount, as is the urgent need to personalize the user's purchasing experience and increase their willingness to buy. However, conventional systems have the problem of not being able to appropriately judge the emotions and interests of buyers and provide a personalized experience accordingly. Therefore, the present invention aims to provide a technology that realizes a purchasing experience that reflects the emotional state of the user.

[0324] 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.

[0325] In this invention, the server includes information acquisition means for generating buyer options, emotion analysis means for analyzing the user's emotions, and information generation means for composing notifications according to the user's emotional state. This makes it possible to provide a more attractive purchasing experience through personalized notifications that take into account each user's individual interests and preferences.

[0326] "Buyer options" refer to the types and content of products and services that users can choose from.

[0327] "Information acquisition means" refers to methods and technologies for obtaining necessary data and information.

[0328] "Emotional analysis techniques" refer to technologies that analyze a user's behavior and data to determine their emotions and psychological state.

[0329] "Information generation means" refers to a technology or method for creating information to be provided to users based on collected data.

[0330] "Composing a notification" refers to organizing the information that needs to be conveyed to the user and preparing it in a specific format.

[0331] "Information transmission means" refers to the technologies and methods used to deliver generated information to users via a network.

[0332] A "system" refers to a collection of devices, software, and networks that are combined to realize a series of processes or functions.

[0333] A "user" refers to an individual or group that uses a system or service.

[0334] A "machine learning model" refers to an algorithm that learns patterns and rules from large amounts of data to perform predictions and analyses.

[0335] An "information and communication service API" is an interface for exchanging data between various services and platforms.

[0336] This system first uses an information acquisition tool to collect ticket options from the resale platform. Next, it uses sentiment analysis tools to capture activity logs of potential buyers and analyzes this data to infer the user's interests and emotional state. In this process, the server primarily uses machine learning models (e.g., TensorFlow) written in Python to process the data.

[0337] For example, by analyzing past purchase history, browsing history, and click data, sentiment analysis can be used to identify a user's high level of interest in a particular music artist. Based on this information, the server uses information generation tools to create specialized notifications about events that the user is likely to be interested in.

[0338] As a concrete example, suppose a user has previously purchased concert tickets for the same band multiple times. Using this data, a generative AI model can be used to create a prompt message like this: "Predict and suggest the user's potential interest in a new live event."

[0339] Finally, the server sends a personalized notification, generated through the information transmission means, to the user's terminal. This notification is delivered quickly and securely using an information and communication service API. In this way, personalized information tailored to the user's interests can be provided, improving the purchasing experience.

[0340] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0341] Step 1:

[0342] The server retrieves ticket sales information from the resale platform using an information acquisition method. The input is data obtained from the resale platform's API, which includes ticket prices and event information. The output generates a list of tickets necessary for subsequent analysis.

[0343] Step 2:

[0344] The server uses a machine learning model to analyze the fairness of prices based on acquired ticket data. The input is ticket price data, which the AI ​​model compares to an appropriate price range. For data processing, the model uses historical price data to calculate a standard price range. The output is the detection result for inappropriate prices.

[0345] Step 3:

[0346] If a price is deemed inappropriate, the server uses price revision mechanisms to correct them to the standard price. The input is a list of tickets with invalid prices, and the algorithm generates price data corrected to the standard price. The output is the corrected price data.

[0347] Step 4:

[0348] The server acquires user activity logs through sentiment analysis and analyzes the user's interests and emotional state. It uses past purchase and browsing history data as input, and based on this, it uses an AI model to generate AI prompts to predict user interests. The output is the analysis result reflecting the user's interests and emotional state.

[0349] Step 5:

[0350] Based on the analysis results, the server generates personalized notifications for each user using information generation methods. The input is the sentiment analysis results from the previous stage, and a customized message based on those results is generated as output.

[0351] Step 6:

[0352] The server sends notifications generated through information transmission means to the user's terminal using an information communication service API. The input is the generated notification message, and the output is the notification content displayed on the user's terminal that receives it.

[0353] 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.

[0354] 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.

[0355] 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.

[0356] [Third Embodiment]

[0357] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0358] 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.

[0359] 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).

[0360] 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.

[0361] 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.

[0362] 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).

[0363] 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.

[0364] 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.

[0365] 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.

[0366] 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.

[0367] 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.

[0368] 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".

[0369] This invention relates to the resale of event tickets and is a system for preventing the fraudulent and high-priced resale of tickets conducted through online platforms. This system is composed of a combination of information acquisition means, price analysis means, price revision means, and information transmission means.

[0370] The server periodically collects ticket resale information from the resale platform. Using APIs or web scraping techniques, it obtains ticket prices, seller information, and sales status. This information is stored in a database for subsequent steps.

[0371] The server passes the acquired resale information to a price analysis tool. The price analysis tool uses a machine learning model to analyze the data and determine whether the resale price is inappropriately high compared to the original price. This analysis utilizes historical data and standard price ranges for similar events.

[0372] Next, the server uses a price adjustment mechanism to correct the prices of tickets that the analysis determined to be overpriced to their face value. This correction information is reflected in the resale platform in real time, ensuring that the prices of tickets currently on sale are always kept within the standard range.

[0373] Finally, the server uses information transmission methods, including APIs from information and communication services such as LINE, to notify the user's device of the revised price. This notification clearly states that the revised ticket price is fair, allowing the user to proceed with the purchase with confidence.

[0374] As a concrete example, if concert tickets for a famous artist are being resold at inflated prices on resale websites, this system can automatically adjust the price back to the original retail price. As a result, consumers can purchase tickets with confidence, and problems caused by illegal resale can be prevented. Through this entire process, event organizers can increase customer trust and continue to provide a fair trading environment.

[0375] The following describes the processing flow.

[0376] Step 1:

[0377] The server accesses the resale platform to retrieve ticket resale information. Specifically, it collects data such as ticket IDs, resale prices, seller information, and sales status via API or web scraping, and stores it in a database.

[0378] Step 2:

[0379] The server prepares the collected data for the price analysis tool. It formats the data to make it suitable for analysis so that the AI ​​model can begin processing it.

[0380] Step 3:

[0381] The AI ​​agent uses price analysis tools and machine learning models to evaluate ticket prices. It compares them with past sales data and market standards to determine whether the current price is inappropriately high.

[0382] Step 4:

[0383] The server receives the analysis results from the AI ​​agent and adjusts the prices of tickets deemed inappropriate. Using a price revision method, it corrects the price of the relevant tickets to the regular price and updates the information.

[0384] Step 5:

[0385] The server uses an information and communication service API to notify users that prices have been revised. It sends a message on the digital platform registered by the user, informing them that the revised tickets are available at the correct price.

[0386] Step 6:

[0387] Users check the received notification and purchase tickets offered at a fair price. After completing the purchase, users can participate in the event with peace of mind.

[0388] (Example 1)

[0389] 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."

[0390] The illegal resale of tickets at exorbitant prices on online platforms is a serious problem, and there is a need for a fair and secure trading environment. Traditional systems are insufficient to address this issue, and a mechanism is needed to monitor and adjust prices in real time.

[0391] 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.

[0392] In this invention, the server includes means for acquiring data related to ticket resale using an information gathering medium, means for analyzing fraudulent prices by comparing them with market prices using the above data, and means for changing prices determined to be fraudulent to market standard prices. This makes it possible to correct fraudulent resale prices in real time on an online platform and provide a fair and secure trading environment.

[0393] "Information gathering media" refers to technical means for obtaining data related to ticket resale from online platforms, and includes APIs and web scraping technologies.

[0394] "Analysis means" refers to technical means for detecting fraudulent pricing in ticket resales by comparing acquired data with market prices.

[0395] A "computational model" is a model that uses machine learning algorithms to analyze data and determine fraudulent pricing.

[0396] "Means of modification" refers to technical means for correcting an unfair price to a market-standard price after detection, and includes a function to reflect the correction information on the resale platform.

[0397] A "notification means" is a technical means for informing users of updated price information via a communication interface.

[0398] An "information transmission device" is a technology that transmits updated price information to external devices or user terminals using a communication network, and uses protocols such as APIs.

[0399] This invention is a system aimed at preventing the illegal resale of tickets on online platforms. Specific embodiments of the invention are described below.

[0400] The server first uses data collection tools to retrieve information about ticket resales from the resale platform. This process utilizes APIs and web scraping techniques to collect data such as ticket prices, seller information, and sales status. The collected information is stored in a database, preparing it for subsequent processing.

[0401] Next, the server passes the collected data to the analysis tool. The analysis tool uses a computational model to analyze the data and determine whether the resale price is inappropriately high compared to the original price. This model is trained on historical data and price information from similar events, and it is possible to incorporate a generative AI model.

[0402] If an invalid price is detected, the server uses a modification mechanism to correct the resale price to the market standard price. This operation is immediately reflected on the resale platform, ensuring that users can always purchase at a fair price.

[0403] Finally, the server uses a notification system to send the updated price information to the user's terminal via an information transmission device. This allows the user to confirm that the price is correct and proceed with the transaction with confidence.

[0404] For example, if concert tickets for a famous artist are being traded at unfairly high prices on resale sites, this system can automatically adjust the price to the face value. This allows consumers to purchase tickets at a fair price and prevents problems caused by illegal resale. An example of a prompt message might be, "Please describe a system that monitors the resale prices of tickets for famous artists in real time and adjusts the price to the face value if it is unfairly high."

[0405] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0406] Step 1:

[0407] The server uses information gathering media to retrieve ticket resale information from resale platforms. Inputs include requests using APIs and web scraping techniques, and output includes data such as ticket prices, seller information, and sales status. The server temporarily caches this data and stores it in a database for subsequent processing.

[0408] Step 2:

[0409] The server passes resale data retrieved from the database to the analysis tool. The data obtained as input is analyzed using a computational model. Utilizing a generative AI model, it determines whether the pricing is fraudulent by comparing it with past event data and market trends. As output, a list of resale data deemed fraudulent is generated.

[0410] Step 3:

[0411] The server uses a mechanism to change the price of tickets that are determined to be priced unfairly based on the analysis. As input, it receives data on the unfair pricing and adjusts the price to the market standard price based on this data. As output, the corrected price information is immediately reflected on the resale platform, and the list of tickets for sale is updated.

[0412] Step 4:

[0413] The server sends the updated price information to the user's terminal via a notification system. The revised price information is provided as input, and a push notification is sent to the user via an information transmission device as output. The notification includes justification for the price change and its details, allowing the user to trade with confidence.

[0414] (Application Example 1)

[0415] 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."

[0416] The resale of tickets at inflated prices on online platforms poses a problem that harms consumers through unfair pricing. Furthermore, such fraudulent practices undermine the fair market for events and erode consumer trust. Moreover, maintaining unfair prices through electronic transactions is difficult to address quickly, resulting in many consumers being unable to purchase goods at fair prices.

[0417] 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.

[0418] In this invention, the server includes data collection means, data analysis means, and price adjustment means. This makes it possible to detect fraudulent resale of tickets on an online platform and enable transactions at a fair price based on the original price.

[0419] "Data collection methods" refer to technical techniques for obtaining ticket transfer information from online platforms.

[0420] "Data analysis methods" refer to algorithms and tools used to detect inappropriate pricing based on acquired transfer information.

[0421] A "price adjustment measure" is a process for correcting and resetting detected inappropriate prices to a reference price.

[0422] "Data transfer means" refers to communication technology used to transmit adjusted price information to users.

[0423] A "transaction management system" is a system that regulates ticket resale prices through electronic transactions and supervises and manages buying and selling transactions.

[0424] The system that implements this invention operates with a server at its core. The server first uses data collection methods to obtain ticket transfer information from online platforms. This typically involves using APIs or web scraping techniques. The obtained information is stored in a database, preparing the system for the next steps.

[0425] Next, the server uses data analysis tools to evaluate whether the transfer price is inappropriate based on the collected information. Here, machine learning algorithms (e.g., TensorFlow or Scikit-learn) can be used to perform analysis based on historical data and market trends. If an inappropriate price is detected as a result of the analysis, the price is adjusted to a benchmark price using price adjustment tools.

[0426] The corrected price information is communicated to the user via a data transfer method. This communication utilizes information exchange service APIs such as the LINE Messaging API. This allows users to receive accurate price information in real time and purchase tickets with confidence.

[0427] As a concrete example, if concert tickets for a famous music group are being resold at inflated prices on a resale site, this system can be used to automatically adjust the price to the standard price and notify the user of the fair price. As a result, consumers benefit from being able to purchase tickets without being bothered by unfair pricing.

[0428] An example of a prompt for a generated AI model is, "Develop a machine learning model to detect ticket resale prices and write Python code to prevent price gouging."

[0429] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0430] Step 1:

[0431] The server uses data collection methods to obtain ticket transfer information from online platforms. In this step, APIs or web scraping techniques are used to collect ticket prices, transfer status, seller information, etc., and store them in a database. The input is the transfer information from the online platform, and the output is the raw data stored in the database.

[0432] Step 2:

[0433] The server uses data analysis tools to detect inappropriate pricing based on collected transfer information. It employs machine learning algorithms, analyzing data based on past sales data and standard market price ranges. The input is transfer information obtained from a database, and the output is the result of the inappropriate pricing determination.

[0434] Step 3:

[0435] The server uses price adjustment mechanisms to correct detected inappropriate prices to the standard price. This correction resets the ticket price to the correct price. The input is the result of the inappropriate price detection, and the output is the corrected price information.

[0436] Step 4:

[0437] The server notifies the user's terminal of the corrected price information via a data transfer method. Price information is transmitted in real time using communication methods such as the LINE Messaging API. The input is the corrected price information, and the output is a notification of the appropriate price to the user.

[0438] Step 5:

[0439] The user receives a notification and considers purchasing a ticket based on the optimized price information. In this step, the user checks the price information on their device and decides whether to proceed with the transaction with confidence. The input is the price information displayed on the device, and the output is the user's purchase decision.

[0440] 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.

[0441] This invention is a system that combines an emotion engine not only to prevent the fraudulent resale of tickets at inflated prices, but also to improve the user's purchasing experience. The system comprises an information acquisition means, a price analysis means, a price revision means, an information transmission means, and an emotion engine.

[0442] The server retrieves ticket resale information from the resale platform and uses price analysis tools to identify inappropriate prices based on that information. A machine learning model is used to analyze the prices while comparing them to a standard price range. Tickets deemed overpriced are then adjusted to their face value using a price revision mechanism.

[0443] Price revision information is sent from the server to the terminal, and the emotion engine plays a crucial role in this process. The emotion engine analyzes user patterns and behavior logs to infer the user's emotional state. Specifically, it detects emotions such as purchase intent and satisfaction, and personalizes the information presented to each user according to their needs.

[0444] For example, if it is detected that a user has been a fan of a particular artist in the past, the emotion engine uses that information to directly notify the user that the ticket price has been adjusted and sends a personalized message encouraging them to purchase. This increases the user's willingness to buy and ensures a trustworthy transaction.

[0445] Furthermore, based on the notifications users receive, they are directed to the pages of events they are interested in. There, they can purchase tickets with confidence and enjoy a satisfying user experience. By considering the individual emotions of each user, this system aims not only to deter illegal resale but also to personalize and enhance the entire user purchasing process. This contributes to improving the brand value of event companies and attracting new customers.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server periodically collects ticket resale information from multiple resale platforms via scraping or APIs. The collected information includes ticket prices, seller information, and sales status, and this is temporarily stored in a database.

[0449] Step 2:

[0450] The server inputs the collected resale information into a price analysis system and uses a machine learning model to diagnose whether the price is inappropriate. Based on past transaction history and market prices, it determines whether the ticket price deviates from the market price.

[0451] Step 3:

[0452] The server receives the results of the price analysis and corrects any prices detected as inappropriate to the standard price or list price using the price revision mechanism. This correction is automatically reflected on the resale platform.

[0453] Step 4:

[0454] The server activates the emotion engine and performs sentiment analysis based on the user profile. It infers the user's current emotional state (e.g., excitement, willingness to buy) from past purchase history, browsing patterns, and behavioral history.

[0455] Step 5:

[0456] The server optimizes notification messages based on the output of the emotion engine and sends the revised price information to the user's device using an information transmission method. The notification content is personalized according to the user's emotional state.

[0457] Step 6:

[0458] Users check the notifications they receive on their devices and visit the resale platform based on those notifications. They can then purchase tickets offered at a fair price and prepare to attend the event with peace of mind.

[0459] (Example 2)

[0460] 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."

[0461] To provide a system that prevents fraudulent price gouging and improves the user's purchasing experience. In particular, to promote purchase intent and establish reliable transactions by considering the user's emotional state and providing personalized information.

[0462] 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.

[0463] In this invention, the server includes acquisition means for acquiring transaction information, analysis means for detecting inappropriate prices based on the transaction information, revision means for correcting and resetting the detected price to a reference price, sentiment analysis means for analyzing the user's behavior log to infer their emotional state, and transmission means for individualizing and notifying information based on the sentiment analysis results. This makes it possible to provide appropriate price notifications that take emotions into account for each user, and to provide a personalized user experience that enhances purchasing intent.

[0464] "Transaction information" refers to detailed data related to the buying and selling of goods, including price, date and time, and seller information.

[0465] "Means of acquisition" refers to functions or devices used to collect specific information or data from external sources.

[0466] "Analysis methods" refer to methods and techniques for identifying trends and anomalies based on collected data and for conducting evaluations.

[0467] "Revision methods" refer to functions or processes for making changes to new values ​​or states that conform to standards, based on existing information.

[0468] "Emotional analysis methods" refer to technologies and methods for inferring and evaluating a user's emotional state based on their behavioral logs and usage history.

[0469] "Transmission means" refers to the equipment and methods used to deliver information or data to a specific destination.

[0470] "Reference price" refers to a price that is considered fair in the fair trade of goods, set within the standard price range in the market.

[0471] This invention is a system for processing transaction information, preventing fraudulent resale at inflated prices, and improving the user's purchasing experience. This system is realized through the involvement of three entities: a server, a terminal, and a user, each fulfilling their respective roles.

[0472] The server first retrieves transaction information from the resale platform using an API. The hardware used here is a server computer, and programming languages ​​such as Python or JavaScript are used to process API requests. The retrieved information includes product price, seller information, and sale date and time.

[0473] Next, the server performs price analysis using a machine learning model. This analysis utilizes Python libraries such as TensorFlow and Scikit-learn. If an inappropriate price is detected, it is corrected to a benchmark price using a price revision mechanism and updated in the database.

[0474] The device collects user activity logs and usage history. Based on this, an emotion analysis system analyzes the user's emotional state. This analysis uses data such as the user's click history and access times to infer specific emotional states and purchase intentions. This triggers an emotion engine to generate personalized messages based on the user's interests.

[0475] The generated message is sent to the user's device by the server. Information and communication services such as email and push notifications are used, and the information is personalized during this process. Based on the content of the notification, the user is guided to the event page of interest and can purchase the desired ticket with confidence.

[0476] For example, if a user's past purchase history indicates they are a fan of a particular artist, the sentiment engine will notify them of appropriate pricing information related to that artist's events. For instance, by passing the prompt "Please tell me what message the sentiment engine should send to a specific user, along with the reason why" to the generating AI model, an appropriate message will be created.

[0477] Thus, this system provides an effective means of preventing illegal resale and making the user's purchasing experience personalized and appealing.

[0478] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0479] Step 1:

[0480] The server retrieves transaction information through the resale platform's API. The input is response data from the API, which includes ticket prices, seller information, and the date and time of sale. The retrieved data is stored in JSON format, and this data stream forms the basis for the next processing step. Specifically, periodic API calls are made, and data collection and storage are performed as routine processes.

[0481] Step 2:

[0482] The server passes the acquired transaction information to an analysis tool for price analysis. The input is the transaction information in JSON format saved in step 1. A machine learning model, such as TensorFlow, is used to compare the price with standard price levels. At this stage, inappropriate prices are detected, and the results are recorded in the data as flags. Specifically, the model uses historical price data to find price anomalies.

[0483] Step 3:

[0484] If an inappropriate price is detected, the server corrects it to the baseline price using a revision mechanism. The input is the ticket information flagged as an anomaly in step 2. The output is the corrected price data, which is updated in the database. Specifically, an SQL query is executed, and the price field is replaced with the baseline price.

[0485] Step 4:

[0486] The device collects user behavior logs and usage history and analyzes them using sentiment analysis techniques. Inputs include click history and access times when the user interacts with the application. This allows the system to estimate the user's purchase intent and satisfaction level, and generate an emotional state evaluation as output. Specifically, the sentiment model is triggered by the log data to profile the user's needs.

[0487] Step 5:

[0488] The server executes a means of sending personalized notifications based on the sentiment analysis results. The inputs are the sentiment evaluation results from step 4 and the adjusted price data from step 3. The output is a notification message customized for each user, which is sent as email or push notification. Specifically, the message generation and delivery process is performed via an API. In this process, prompts are given to the generation AI model, which then determines "what kind of message is appropriate for a particular user" and creates the message.

[0489] (Application Example 2)

[0490] 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."

[0491] Preventing the fraudulent resale of tickets at inflated prices is paramount, as is the urgent need to personalize the user's purchasing experience and increase their willingness to buy. However, conventional systems have the problem of not being able to appropriately judge the emotions and interests of buyers and provide a personalized experience accordingly. Therefore, the present invention aims to provide a technology that realizes a purchasing experience that reflects the emotional state of the user.

[0492] 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.

[0493] In this invention, the server includes information acquisition means for generating buyer options, emotion analysis means for analyzing the user's emotions, and information generation means for composing notifications according to the user's emotional state. This makes it possible to provide a more attractive purchasing experience through personalized notifications that take into account each user's individual interests and preferences.

[0494] "Buyer options" refer to the types and content of products and services that users can choose from.

[0495] "Information acquisition means" refers to methods and technologies for obtaining necessary data and information.

[0496] "Emotional analysis techniques" refer to technologies that analyze a user's behavior and data to determine their emotions and psychological state.

[0497] "Information generation means" refers to a technology or method for creating information to be provided to users based on collected data.

[0498] "Composing a notification" refers to organizing the information that needs to be conveyed to the user and preparing it in a specific format.

[0499] "Information transmission means" refers to the technologies and methods used to deliver generated information to users via a network.

[0500] A "system" refers to a collection of devices, software, and networks that are combined to realize a series of processes or functions.

[0501] A "user" refers to an individual or group that uses a system or service.

[0502] A "machine learning model" refers to an algorithm that learns patterns and rules from large amounts of data to perform predictions and analyses.

[0503] An "information and communication service API" is an interface for exchanging data between various services and platforms.

[0504] This system first uses an information acquisition tool to collect ticket options from the resale platform. Next, it uses sentiment analysis tools to capture activity logs of potential buyers and analyzes this data to infer the user's interests and emotional state. In this process, the server primarily uses machine learning models (e.g., TensorFlow) written in Python to process the data.

[0505] For example, by analyzing past purchase history, browsing history, and click data, sentiment analysis can be used to identify a user's high level of interest in a particular music artist. Based on this information, the server uses information generation tools to create specialized notifications about events that the user is likely to be interested in.

[0506] As a concrete example, suppose a user has previously purchased concert tickets for the same band multiple times. Using this data, a generative AI model can be used to create a prompt message like this: "Predict and suggest the user's potential interest in a new live event."

[0507] Finally, the server sends a personalized notification, generated through the information transmission means, to the user's terminal. This notification is delivered quickly and securely using an information and communication service API. In this way, personalized information tailored to the user's interests can be provided, improving the purchasing experience.

[0508] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0509] Step 1:

[0510] The server retrieves ticket sales information from the resale platform using an information acquisition method. The input is data obtained from the resale platform's API, which includes ticket prices and event information. The output generates a list of tickets necessary for subsequent analysis.

[0511] Step 2:

[0512] The server uses a machine learning model to analyze the fairness of prices based on acquired ticket data. The input is ticket price data, which the AI ​​model compares to an appropriate price range. For data processing, the model uses historical price data to calculate a standard price range. The output is the detection result for inappropriate prices.

[0513] Step 3:

[0514] If a price is deemed inappropriate, the server uses price revision mechanisms to correct them to the standard price. The input is a list of tickets with invalid prices, and the algorithm generates price data corrected to the standard price. The output is the corrected price data.

[0515] Step 4:

[0516] The server acquires user activity logs through sentiment analysis and analyzes the user's interests and emotional state. It uses past purchase and browsing history data as input, and based on this, it uses an AI model to generate AI prompts to predict user interests. The output is the analysis result reflecting the user's interests and emotional state.

[0517] Step 5:

[0518] Based on the analysis results, the server generates personalized notifications for each user using information generation methods. The input is the sentiment analysis results from the previous stage, and a customized message based on those results is generated as output.

[0519] Step 6:

[0520] The server sends notifications generated through information transmission means to the user's terminal using an information communication service API. The input is the generated notification message, and the output is the notification content displayed on the user's terminal that receives it.

[0521] 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.

[0522] 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.

[0523] 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.

[0524] [Fourth Embodiment]

[0525] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0526] 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.

[0527] 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).

[0528] 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.

[0529] 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.

[0530] 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).

[0531] 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] 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".

[0538] This invention relates to the resale of event tickets and is a system for preventing the fraudulent and high-priced resale of tickets conducted through online platforms. This system is composed of a combination of information acquisition means, price analysis means, price revision means, and information transmission means.

[0539] The server periodically collects ticket resale information from the resale platform. Using APIs or web scraping techniques, it obtains ticket prices, seller information, and sales status. This information is stored in a database for subsequent steps.

[0540] The server passes the acquired resale information to a price analysis tool. The price analysis tool uses a machine learning model to analyze the data and determine whether the resale price is inappropriately high compared to the original price. This analysis utilizes historical data and standard price ranges for similar events.

[0541] Next, the server uses a price adjustment mechanism to correct the prices of tickets that the analysis determined to be overpriced to their face value. This correction information is reflected in the resale platform in real time, ensuring that the prices of tickets currently on sale are always kept within the standard range.

[0542] Finally, the server uses information transmission methods, including APIs from information and communication services such as LINE, to notify the user's device of the revised price. This notification clearly states that the revised ticket price is fair, allowing the user to proceed with the purchase with confidence.

[0543] As a concrete example, if concert tickets for a famous artist are being resold at inflated prices on resale websites, this system can automatically adjust the price back to the original retail price. As a result, consumers can purchase tickets with confidence, and problems caused by illegal resale can be prevented. Through this entire process, event organizers can increase customer trust and continue to provide a fair trading environment.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The server accesses the resale platform to retrieve ticket resale information. Specifically, it collects data such as ticket IDs, resale prices, seller information, and sales status via API or web scraping, and stores it in a database.

[0547] Step 2:

[0548] The server prepares the collected data for the price analysis tool. It formats the data to make it suitable for analysis so that the AI ​​model can begin processing it.

[0549] Step 3:

[0550] The AI ​​agent uses price analysis tools and machine learning models to evaluate ticket prices. It compares them with past sales data and market standards to determine whether the current price is inappropriately high.

[0551] Step 4:

[0552] The server receives the analysis results from the AI ​​agent and adjusts the prices of tickets deemed inappropriate. Using a price revision method, it corrects the price of the relevant tickets to the regular price and updates the information.

[0553] Step 5:

[0554] The server uses an information and communication service API to notify users that prices have been revised. It sends a message on the digital platform registered by the user, informing them that the revised tickets are available at the correct price.

[0555] Step 6:

[0556] Users check the received notification and purchase tickets offered at a fair price. After completing the purchase, users can participate in the event with peace of mind.

[0557] (Example 1)

[0558] 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".

[0559] The illegal resale of tickets at exorbitant prices on online platforms is a serious problem, and there is a need for a fair and secure trading environment. Traditional systems are insufficient to address this issue, and a mechanism is needed to monitor and adjust prices in real time.

[0560] 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.

[0561] In this invention, the server includes means for acquiring data related to ticket resale using an information gathering medium, means for analyzing fraudulent prices by comparing them with market prices using the above data, and means for changing prices determined to be fraudulent to market standard prices. This makes it possible to correct fraudulent resale prices in real time on an online platform and provide a fair and secure trading environment.

[0562] "Information gathering media" refers to technical means for obtaining data related to ticket resale from online platforms, and includes APIs and web scraping technologies.

[0563] "Analysis means" refers to technical means for detecting fraudulent pricing in ticket resales by comparing acquired data with market prices.

[0564] A "computational model" is a model that uses machine learning algorithms to analyze data and determine fraudulent pricing.

[0565] "Means of modification" refers to technical means for correcting an unfair price to a market-standard price after detection, and includes a function to reflect the correction information on the resale platform.

[0566] A "notification means" is a technical means for informing users of updated price information via a communication interface.

[0567] An "information transmission device" is a technology that transmits updated price information to external devices or user terminals using a communication network, and uses protocols such as APIs.

[0568] This invention is a system aimed at preventing the illegal resale of tickets on online platforms. Specific embodiments of the invention are described below.

[0569] The server first uses data collection tools to retrieve information about ticket resales from the resale platform. This process utilizes APIs and web scraping techniques to collect data such as ticket prices, seller information, and sales status. The collected information is stored in a database, preparing it for subsequent processing.

[0570] Next, the server passes the collected data to the analysis tool. The analysis tool uses a computational model to analyze the data and determine whether the resale price is inappropriately high compared to the original price. This model is trained on historical data and price information from similar events, and it is possible to incorporate a generative AI model.

[0571] If an invalid price is detected, the server uses a modification mechanism to correct the resale price to the market standard price. This operation is immediately reflected on the resale platform, ensuring that users can always purchase at a fair price.

[0572] Finally, the server uses a notification system to send the updated price information to the user's terminal via an information transmission device. This allows the user to confirm that the price is correct and proceed with the transaction with confidence.

[0573] For example, if concert tickets for a famous artist are being traded at unfairly high prices on resale sites, this system can automatically adjust the price to the face value. This allows consumers to purchase tickets at a fair price and prevents problems caused by illegal resale. An example of a prompt message might be, "Please describe a system that monitors the resale prices of tickets for famous artists in real time and adjusts the price to the face value if it is unfairly high."

[0574] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0575] Step 1:

[0576] The server uses information gathering media to retrieve ticket resale information from resale platforms. Inputs include requests using APIs and web scraping techniques, and output includes data such as ticket prices, seller information, and sales status. The server temporarily caches this data and stores it in a database for subsequent processing.

[0577] Step 2:

[0578] The server passes resale data retrieved from the database to the analysis tool. The data obtained as input is analyzed using a computational model. Utilizing a generative AI model, it determines whether the pricing is fraudulent by comparing it with past event data and market trends. As output, a list of resale data deemed fraudulent is generated.

[0579] Step 3:

[0580] The server uses a mechanism to change the price of tickets that are determined to be priced unfairly based on the analysis. As input, it receives data on the unfair pricing and adjusts the price to the market standard price based on this data. As output, the corrected price information is immediately reflected on the resale platform, and the list of tickets for sale is updated.

[0581] Step 4:

[0582] The server sends the updated price information to the user's terminal via a notification system. The revised price information is provided as input, and a push notification is sent to the user via an information transmission device as output. The notification includes justification for the price change and its details, allowing the user to trade with confidence.

[0583] (Application Example 1)

[0584] 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".

[0585] The resale of tickets at inflated prices on online platforms poses a problem that harms consumers through unfair pricing. Furthermore, such fraudulent practices undermine the fair market for events and erode consumer trust. Moreover, maintaining unfair prices through electronic transactions is difficult to address quickly, resulting in many consumers being unable to purchase goods at fair prices.

[0586] 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.

[0587] In this invention, the server includes data collection means, data analysis means, and price adjustment means. This makes it possible to detect fraudulent resale of tickets on an online platform and enable transactions at a fair price based on the original price.

[0588] "Data collection methods" refer to technical techniques for obtaining ticket transfer information from online platforms.

[0589] "Data analysis methods" refer to algorithms and tools used to detect inappropriate pricing based on acquired transfer information.

[0590] A "price adjustment measure" is a process for correcting and resetting detected inappropriate prices to a reference price.

[0591] "Data transfer means" refers to communication technology used to transmit adjusted price information to users.

[0592] A "transaction management system" is a system that regulates ticket resale prices through electronic transactions and supervises and manages buying and selling transactions.

[0593] The system that implements this invention operates with a server at its core. The server first uses data collection methods to obtain ticket transfer information from online platforms. This typically involves using APIs or web scraping techniques. The obtained information is stored in a database, preparing the system for the next steps.

[0594] Next, the server uses data analysis tools to evaluate whether the transfer price is inappropriate based on the collected information. Here, machine learning algorithms (e.g., TensorFlow or Scikit-learn) can be used to perform analysis based on historical data and market trends. If an inappropriate price is detected as a result of the analysis, the price is adjusted to a benchmark price using price adjustment tools.

[0595] The corrected price information is communicated to the user via a data transfer method. This communication utilizes information exchange service APIs such as the LINE Messaging API. This allows users to receive accurate price information in real time and purchase tickets with confidence.

[0596] As a concrete example, if concert tickets for a famous music group are being resold at inflated prices on a resale site, this system can be used to automatically adjust the price to the standard price and notify the user of the fair price. As a result, consumers benefit from being able to purchase tickets without being bothered by unfair pricing.

[0597] An example of a prompt for a generated AI model is, "Develop a machine learning model to detect ticket resale prices and write Python code to prevent price gouging."

[0598] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0599] Step 1:

[0600] The server uses data collection methods to obtain ticket transfer information from online platforms. In this step, APIs or web scraping techniques are used to collect ticket prices, transfer status, seller information, etc., and store them in a database. The input is the transfer information from the online platform, and the output is the raw data stored in the database.

[0601] Step 2:

[0602] The server uses data analysis tools to detect inappropriate pricing based on collected transfer information. It employs machine learning algorithms, analyzing data based on past sales data and standard market price ranges. The input is transfer information obtained from a database, and the output is the result of the inappropriate pricing determination.

[0603] Step 3:

[0604] The server uses price adjustment mechanisms to correct detected inappropriate prices to the standard price. This correction resets the ticket price to the correct price. The input is the result of the inappropriate price detection, and the output is the corrected price information.

[0605] Step 4:

[0606] The server notifies the user's terminal of the corrected price information via a data transfer method. Price information is transmitted in real time using communication methods such as the LINE Messaging API. The input is the corrected price information, and the output is a notification of the appropriate price to the user.

[0607] Step 5:

[0608] The user receives a notification and considers purchasing a ticket based on the optimized price information. In this step, the user checks the price information on their device and decides whether to proceed with the transaction with confidence. The input is the price information displayed on the device, and the output is the user's purchase decision.

[0609] 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.

[0610] This invention is a system that combines an emotion engine not only to prevent the fraudulent resale of tickets at inflated prices, but also to improve the user's purchasing experience. The system comprises an information acquisition means, a price analysis means, a price revision means, an information transmission means, and an emotion engine.

[0611] The server retrieves ticket resale information from the resale platform and uses price analysis tools to identify inappropriate prices based on that information. A machine learning model is used to analyze the prices while comparing them to a standard price range. Tickets deemed overpriced are then adjusted to their face value using a price revision mechanism.

[0612] Price revision information is sent from the server to the terminal, and the emotion engine plays a crucial role in this process. The emotion engine analyzes user patterns and behavior logs to infer the user's emotional state. Specifically, it detects emotions such as purchase intent and satisfaction, and personalizes the information presented to each user according to their needs.

[0613] For example, if it is detected that a user has been a fan of a particular artist in the past, the emotion engine uses that information to directly notify the user that the ticket price has been adjusted and sends a personalized message encouraging them to purchase. This increases the user's willingness to buy and ensures a trustworthy transaction.

[0614] Furthermore, based on the notifications users receive, they are directed to the pages of events they are interested in. There, they can purchase tickets with confidence and enjoy a satisfying user experience. By considering the individual emotions of each user, this system aims not only to deter illegal resale but also to personalize and enhance the entire user purchasing process. This contributes to improving the brand value of event companies and attracting new customers.

[0615] The following describes the processing flow.

[0616] Step 1:

[0617] The server periodically collects ticket resale information from multiple resale platforms via scraping or APIs. The collected information includes ticket prices, seller information, and sales status, and this is temporarily stored in a database.

[0618] Step 2:

[0619] The server inputs the collected resale information into a price analysis system and uses a machine learning model to diagnose whether the price is inappropriate. Based on past transaction history and market prices, it determines whether the ticket price deviates from the market price.

[0620] Step 3:

[0621] The server receives the results of the price analysis and corrects any prices detected as inappropriate to the standard price or list price using the price revision mechanism. This correction is automatically reflected on the resale platform.

[0622] Step 4:

[0623] The server activates the emotion engine and performs sentiment analysis based on the user profile. It infers the user's current emotional state (e.g., excitement, willingness to buy) from past purchase history, browsing patterns, and behavioral history.

[0624] Step 5:

[0625] The server optimizes notification messages based on the output of the emotion engine and sends the revised price information to the user's device using an information transmission method. The notification content is personalized according to the user's emotional state.

[0626] Step 6:

[0627] Users check the notifications they receive on their devices and visit the resale platform based on those notifications. They can then purchase tickets offered at a fair price and prepare to attend the event with peace of mind.

[0628] (Example 2)

[0629] 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".

[0630] To provide a system that prevents fraudulent price gouging and improves the user's purchasing experience. In particular, to promote purchase intent and establish reliable transactions by considering the user's emotional state and providing personalized information.

[0631] 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.

[0632] In this invention, the server includes acquisition means for acquiring transaction information, analysis means for detecting inappropriate prices based on the transaction information, revision means for correcting and resetting the detected price to a reference price, sentiment analysis means for analyzing the user's behavior log to infer their emotional state, and transmission means for individualizing and notifying information based on the sentiment analysis results. This makes it possible to provide appropriate price notifications that take emotions into account for each user, and to provide a personalized user experience that enhances purchasing intent.

[0633] "Transaction information" refers to detailed data related to the buying and selling of goods, including price, date and time, and seller information.

[0634] "Means of acquisition" refers to functions or devices used to collect specific information or data from external sources.

[0635] "Analysis methods" refer to methods and techniques for identifying trends and anomalies based on collected data and for conducting evaluations.

[0636] "Revision methods" refer to functions or processes for making changes to new values ​​or states that conform to standards, based on existing information.

[0637] "Emotional analysis methods" refer to technologies and methods for inferring and evaluating a user's emotional state based on their behavioral logs and usage history.

[0638] "Transmission means" refers to the equipment and methods used to deliver information or data to a specific destination.

[0639] "Reference price" refers to a price that is considered fair in the fair trade of goods, set within the standard price range in the market.

[0640] This invention is a system for processing transaction information, preventing fraudulent resale at inflated prices, and improving the user's purchasing experience. This system is realized through the involvement of three entities: a server, a terminal, and a user, each fulfilling their respective roles.

[0641] The server first retrieves transaction information from the resale platform using an API. The hardware used here is a server computer, and programming languages ​​such as Python or JavaScript are used to process API requests. The retrieved information includes product price, seller information, and sale date and time.

[0642] Next, the server performs price analysis using a machine learning model. This analysis utilizes Python libraries such as TensorFlow and Scikit-learn. If an inappropriate price is detected, it is corrected to a benchmark price using a price revision mechanism and updated in the database.

[0643] The device collects user activity logs and usage history. Based on this, an emotion analysis system analyzes the user's emotional state. This analysis uses data such as the user's click history and access times to infer specific emotional states and purchase intentions. This triggers an emotion engine to generate personalized messages based on the user's interests.

[0644] The generated message is sent to the user's device by the server. Information and communication services such as email and push notifications are used, and the information is personalized during this process. Based on the content of the notification, the user is guided to the event page of interest and can purchase the desired ticket with confidence.

[0645] For example, if a user's past purchase history indicates they are a fan of a particular artist, the sentiment engine will notify them of appropriate pricing information related to that artist's events. For instance, by passing the prompt "Please tell me what message the sentiment engine should send to a specific user, along with the reason why" to the generating AI model, an appropriate message will be created.

[0646] Thus, this system provides an effective means of preventing illegal resale and making the user's purchasing experience personalized and appealing.

[0647] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0648] Step 1:

[0649] The server retrieves transaction information through the resale platform's API. The input is response data from the API, which includes ticket prices, seller information, and the date and time of sale. The retrieved data is stored in JSON format, and this data stream forms the basis for the next processing step. Specifically, periodic API calls are made, and data collection and storage are performed as routine processes.

[0650] Step 2:

[0651] The server passes the acquired transaction information to an analysis tool for price analysis. The input is the transaction information in JSON format saved in step 1. A machine learning model, such as TensorFlow, is used to compare the price with standard price levels. At this stage, inappropriate prices are detected, and the results are recorded in the data as flags. Specifically, the model uses historical price data to find price anomalies.

[0652] Step 3:

[0653] If an inappropriate price is detected, the server corrects it to the baseline price using a revision mechanism. The input is the ticket information flagged as an anomaly in step 2. The output is the corrected price data, which is updated in the database. Specifically, an SQL query is executed, and the price field is replaced with the baseline price.

[0654] Step 4:

[0655] The device collects user behavior logs and usage history and analyzes them using sentiment analysis techniques. Inputs include click history and access times when the user interacts with the application. This allows the system to estimate the user's purchase intent and satisfaction level, and generate an emotional state evaluation as output. Specifically, the sentiment model is triggered by the log data to profile the user's needs.

[0656] Step 5:

[0657] The server executes a means of sending personalized notifications based on the sentiment analysis results. The inputs are the sentiment evaluation results from step 4 and the adjusted price data from step 3. The output is a notification message customized for each user, which is sent as email or push notification. Specifically, the message generation and delivery process is performed via an API. In this process, prompts are given to the generation AI model, which then determines "what kind of message is appropriate for a particular user" and creates the message.

[0658] (Application Example 2)

[0659] 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".

[0660] Preventing the fraudulent resale of tickets at inflated prices is paramount, as is the urgent need to personalize the user's purchasing experience and increase their willingness to buy. However, conventional systems have the problem of not being able to appropriately judge the emotions and interests of buyers and provide a personalized experience accordingly. Therefore, the present invention aims to provide a technology that realizes a purchasing experience that reflects the emotional state of the user.

[0661] 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.

[0662] In this invention, the server includes information acquisition means for generating buyer options, emotion analysis means for analyzing the user's emotions, and information generation means for composing notifications according to the user's emotional state. This makes it possible to provide a more attractive purchasing experience through personalized notifications that take into account each user's individual interests and preferences.

[0663] "Buyer options" refer to the types and content of products and services that users can choose from.

[0664] "Information acquisition means" refers to methods and technologies for obtaining necessary data and information.

[0665] "Emotional analysis techniques" refer to technologies that analyze a user's behavior and data to determine their emotions and psychological state.

[0666] "Information generation means" refers to a technology or method for creating information to be provided to users based on collected data.

[0667] "Composing a notification" refers to organizing the information that needs to be conveyed to the user and preparing it in a specific format.

[0668] "Information transmission means" refers to the technologies and methods used to deliver generated information to users via a network.

[0669] A "system" refers to a collection of devices, software, and networks that are combined to realize a series of processes or functions.

[0670] A "user" refers to an individual or group that uses a system or service.

[0671] A "machine learning model" refers to an algorithm that learns patterns and rules from large amounts of data to perform predictions and analyses.

[0672] An "information and communication service API" is an interface for exchanging data between various services and platforms.

[0673] This system first uses an information acquisition tool to collect ticket options from the resale platform. Next, it uses sentiment analysis tools to capture activity logs of potential buyers and analyzes this data to infer the user's interests and emotional state. In this process, the server primarily uses machine learning models (e.g., TensorFlow) written in Python to process the data.

[0674] For example, by analyzing past purchase history, browsing history, and click data, sentiment analysis can be used to identify a user's high level of interest in a particular music artist. Based on this information, the server uses information generation tools to create specialized notifications about events that the user is likely to be interested in.

[0675] As a concrete example, suppose a user has previously purchased concert tickets for the same band multiple times. Using this data, a generative AI model can be used to create a prompt message like this: "Predict and suggest the user's potential interest in a new live event."

[0676] Finally, the server sends a personalized notification, generated through the information transmission means, to the user's terminal. This notification is delivered quickly and securely using an information and communication service API. In this way, personalized information tailored to the user's interests can be provided, improving the purchasing experience.

[0677] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0678] Step 1:

[0679] The server retrieves ticket sales information from the resale platform using an information acquisition method. The input is data obtained from the resale platform's API, which includes ticket prices and event information. The output generates a list of tickets necessary for subsequent analysis.

[0680] Step 2:

[0681] The server uses a machine learning model to analyze the fairness of prices based on acquired ticket data. The input is ticket price data, which the AI ​​model compares to an appropriate price range. For data processing, the model uses historical price data to calculate a standard price range. The output is the detection result for inappropriate prices.

[0682] Step 3:

[0683] If a price is deemed inappropriate, the server uses price revision mechanisms to correct them to the standard price. The input is a list of tickets with invalid prices, and the algorithm generates price data corrected to the standard price. The output is the corrected price data.

[0684] Step 4:

[0685] The server acquires user activity logs through sentiment analysis and analyzes the user's interests and emotional state. It uses past purchase and browsing history data as input, and based on this, it uses an AI model to generate AI prompts to predict user interests. The output is the analysis result reflecting the user's interests and emotional state.

[0686] Step 5:

[0687] Based on the analysis results, the server generates personalized notifications for each user using information generation methods. The input is the sentiment analysis results from the previous stage, and a customized message based on those results is generated as output.

[0688] Step 6:

[0689] The server sends notifications generated through information transmission means to the user's terminal using an information communication service API. The input is the generated notification message, and the output is the notification content displayed on the user's terminal that receives it.

[0690] 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.

[0691] 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.

[0692] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] 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.

[0697] 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.

[0698] 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."

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0706] 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.

[0707] 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.

[0708] 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.

[0709] 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.

[0710] 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.

[0711] The following is further disclosed regarding the embodiments described above.

[0712] (Claim 1)

[0713] Information acquisition methods for obtaining ticket resale information,

[0714] A price analysis method that detects inappropriate prices based on the above resale information,

[0715] A price revision method that adjusts and resets the detected price to the base price,

[0716] A means of transmitting information to notify users of revision information,

[0717] A system that includes this.

[0718] (Claim 2)

[0719] The system according to claim 1, characterized in that the price analysis means detects inappropriate prices using a machine learning model.

[0720] (Claim 3)

[0721] The system according to claim 1, characterized in that the information transmission means notifies the user of revised information through an information communication service API.

[0722] "Example 1"

[0723] (Claim 1)

[0724] A means of obtaining data on ticket resale using information gathering media,

[0725] A method for analyzing fraudulent pricing by comparing the above data with market prices,

[0726] A means to change a price deemed unfair to a market reference price,

[0727] A means for notifying an external device of the revised price information via a communication interface,

[0728] A system that includes this.

[0729] (Claim 2)

[0730] The system according to claim 1, characterized in that the analysis means analyzes fraudulent pricing using a calculation model.

[0731] (Claim 3)

[0732] The system according to claim 1, characterized in that the notification means notifies an external device of the changed price information through an information transmission device.

[0733] "Application Example 1"

[0734] (Claim 1)

[0735] A data collection method for obtaining ticket transfer information,

[0736] A data analysis means for detecting inappropriate prices based on the above transfer information,

[0737] A price adjustment mechanism that corrects and resets the detected price to a reference price,

[0738] A data transfer means for notifying the user of adjustment information,

[0739] Transaction management methods to ensure fair resale prices through electronic transactions,

[0740] A system that includes this.

[0741] (Claim 2)

[0742] The system according to claim 1, characterized in that the data analysis means detects inappropriate prices using a machine learning algorithm.

[0743] (Claim 3)

[0744] The system according to claim 1, characterized in that the data transfer means notifies the user of adjustment information through an information exchange service API.

[0745] "Example 2 of combining an emotion engine"

[0746] (Claim 1)

[0747] Means of obtaining transaction information,

[0748] An analytical means for detecting inappropriate prices based on the above transaction information,

[0749] A revision method that adjusts and resets the detected price to the base price,

[0750] A sentiment analysis method that analyzes user behavior logs to infer emotional states,

[0751] A transmission means that personalizeds and notifies information based on the results of emotion analysis,

[0752] A system that includes this.

[0753] (Claim 2)

[0754] The system according to claim 1, characterized in that the analysis means detects inappropriate prices using a data processing model.

[0755] (Claim 3)

[0756] The system according to claim 1, characterized in that the transmission means notifies the user of revision information through an electronic communication service and generates a personalized message based on the user's interests.

[0757] "Application example 2 when combining with an emotional engine"

[0758] (Claim 1)

[0759] Information acquisition means for generating buyer options,

[0760] A sentiment analysis tool for analyzing user interest in the above options,

[0761] Information generation means that constitutes notifications that personalize the purchasing experience according to the user's emotional state,

[0762] Information transmission means for sending the above notification to the user terminal,

[0763] A system that includes this.

[0764] (Claim 2)

[0765] The system according to claim 1, characterized in that the emotion analysis means uses a machine learning model to infer the user's interests and concerns.

[0766] (Claim 3)

[0767] The system according to claim 1, characterized in that the information transmission means sends notifications to users via an information communication service API. [Explanation of symbols]

[0768] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method for obtaining ticket transfer information, A data analysis means for detecting inappropriate prices based on the above transfer information, A price adjustment mechanism that corrects and resets the detected price to a reference price, A data transfer means for notifying the user of adjustment information, Transaction management methods to ensure fair resale prices through electronic transactions, A system that includes this.

2. The system according to claim 1, characterized in that the data analysis means detects inappropriate prices using a machine learning algorithm.

3. The system according to claim 1, characterized in that the data transfer means notifies the user of adjustment information through an information exchange service API.

Images