system

Abstract

We provide the system. [Solution] A means for collecting market data from an external data source, A means for analyzing collected market data to perform demand forecasting and competitive analysis, A means for dynamically determining the optimal price based on the analysis results, A means of reflecting the determined price in the advertising medium, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In today's highly competitive market, maintaining an effective pricing strategy is an important and difficult task for many companies. Without quickly and flexibly responding to market demand fluctuations and the price settings of competing companies, a company may lose its competitiveness and suffer a decline in sales and profits. However, traditional pricing systems lacked the ability to collect market information in real time and immediately reflect the optimal price, so companies were unable to maintain an appropriate pricing strategy in a timely manner.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that combines means for collecting market data from an external data source with means for analyzing the collected market data to perform demand forecasting and competitive analysis. This system can dynamically determine the optimal price based on the analysis results and reflect the determined price in advertising media. Furthermore, by optimizing prices while taking into account the company's sales history and market demand fluctuations, it is possible to respond immediately to changes in the market environment. In addition, this system updates prices in advertising media in real time and displays them on user terminals, thereby executing pricing strategies quickly and effectively.

[0006] "Market data" refers to information that shows trends in a specific market, such as the price of goods or services, demand, and the activities of competitors.

[0007] "External data sources" refer to information providers located outside of a company's own systems, such as internet platforms and databases that provide market information and competitor data.

[0008] "Means of collection" refers to methods and techniques used to obtain information from external data sources, such as API integration and web scraping.

[0009] "Means of analysis" refers to the techniques or processes used to process collected market data and derive meaningful patterns or predictions from that data.

[0010] "Demand forecasting" is an analytical method that predicts the future demand for goods and services in the market.

[0011] "Competitive analysis" is an evaluation method used to understand the activities, pricing, and strategies of competitors in the market in order to enhance one's own competitiveness.

[0012] A "means for dynamically determining the optimal price" refers to an algorithm and process for automatically setting an appropriate price that is in line with market conditions based on analysis results.

[0013] "Advertising media" refers to channels used to convey information about products and services to consumers, and includes online advertising and print media.

[0014] "Real-time updates" refers to a process where changes and corrections to information are made immediately, and the results are reflected instantly.

[0015] A "user terminal" is an electronic device used to receive and display advertised product information, and includes PCs, smartphones, tablets, and other similar devices. [Brief explanation of the drawing]

[0016] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a 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 CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0020] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] The system of this invention enables the realization of dynamic pricing strategies in the market. This system effectively exchanges information between servers, terminals, and users to achieve price optimization.

[0038] First, the server retrieves market data from external data sources. This data is collected using APIs and web scraping techniques and includes product prices, demand information, and information about competitor activities. The collected data is first stored in a database and then organized and formatted.

[0039] Next, the server uses a generative AI model to analyze the collected market data. This analysis includes demand forecasting and competitive analysis. Based on these analysis results, the server determines the optimal price. This generative AI takes into account past sales history and market demand fluctuations to calculate the price with the highest profit margin under specific conditions.

[0040] Next, the server sends this optimized pricing information to the terminal. The terminal uses the received pricing information to reflect it on the advertising media and e-commerce platforms managed by the company. As a result, when users access these platforms, they are presented with the latest and most optimized prices for each product.

[0041] Users view updated pricing information via their devices and decide whether to purchase. For example, when a user tries to buy clothes online, the server displays dynamic pricing based on real-time data analysis, allowing them to see prices that are more attractive than those of competitors. As a result, users determine that the price is appropriate and decide to purchase, thereby increasing the company's revenue.

[0042] Furthermore, user purchasing behavior and advertising response data are fed back from the terminal to the server. This feedback data is used in the next price optimization process. This allows the system to continuously learn and provide more efficient pricing strategies.

[0043] Thus, the system of the present invention helps companies respond to market fluctuations efficiently and effectively through a cycle of acquiring and analyzing market data, setting optimized prices, incorporating advertising, and generating user feedback.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server acquires market data from external data sources. Using API integration and web scraping techniques, the server collects product prices, demand trends, and competitor activity information in real time.

[0047] Step 2:

[0048] The server stores the acquired market data in a database and performs data preprocessing. The server cleans the data, imputing missing values, correcting outliers, and standardizing the format to prepare it for analysis.

[0049] Step 3:

[0050] The server analyzes market data using a generative AI model. The server applies a demand forecasting model to predict future demand and analyzes competitors' pricing trends and market share.

[0051] Step 4:

[0052] The server dynamically determines the optimal price based on the analysis results. Using a price optimization algorithm, the server selects the appropriate price from multiple simulation patterns, aiming to maximize profits and expand sales.

[0053] Step 5:

[0054] The server sends optimized pricing information to the terminal. The server distributes the new pricing data through the company's advertising platform management system.

[0055] Step 6:

[0056] The device automatically updates prices on advertising media and e-commerce sites based on the received new price information. The device reflects the latest prices in real time and prepares to present them to the user.

[0057] Step 7:

[0058] Users view advertisements and product pages displaying the latest prices through their devices. Seeing more attractive prices than competitors prompts them to consider purchasing.

[0059] Step 8:

[0060] The device records the user's browsing history and purchase activity and provides this feedback to the server. The server uses this feedback data to improve future price optimization processes and further refine its approach.

[0061] (Example 1)

[0062] 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."

[0063] Pricing strategies in the market are highly competitive, and companies need to set prices that can quickly respond to dynamic market conditions. However, traditional methods often fail to adequately consider past sales history and fluctuations in market demand, making it difficult to set optimal prices. Furthermore, providing consumers with real-time pricing information is challenging, sometimes resulting in missed market opportunities.

[0064] 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.

[0065] In this invention, the server includes means for acquiring market information from external sources, means for analyzing the acquired market information to perform demand forecasting and competitive analysis, and means for performing data analysis using a generative AI model, taking into account past transaction history and market demand fluctuations. This enables companies to calculate optimal transaction conditions in real time and provide them quickly to consumers.

[0066] "Market information" refers to data about market trends and conditions, and is a general term for information including product prices, demand information, and the activities of competitors.

[0067] "External information sources" refer to data sources that are not located within a company and are provided objectively or by third parties, such as online platforms and research databases.

[0068] A "generative AI model" is an artificial intelligence system that uses algorithms to perform pattern recognition and prediction based on large amounts of data, and is a model that performs the analytical processing necessary for optimizing pricing strategies.

[0069] "Consumer terminals" refer to devices such as computers, smartphones, and tablets used by consumers, through which price information and transaction terms provided by companies are displayed.

[0070] "Feedback" refers to data manipulation that involves collecting consumer behavior data and advertising response data, and using that data to improve the overall performance of the system.

[0071] This invention provides a system that enables dynamic pricing strategies in the market through the cooperation of a server, a terminal, and a user.

[0072] The server first obtains market information from external sources. This includes data collection using APIs and web scraping techniques. For example, it collects data on product prices, demand trends, and competitor activities from a specific online store or market research site. This information is then stored in a database and processed for analysis.

[0073] Next, the server uses a generative AI model to analyze this market information in detail. The generative AI model performs demand forecasting and competitive analysis based on a large amount of aggregated data. Past sales history and market demand fluctuation information are taken into consideration to calculate the optimal trading conditions under specific circumstances. In this analysis process, for example, a prompt such as "Please suggest the optimal pricing strategy that reflects this week's trends" is input to the generative AI model, and the analysis is performed.

[0074] The transaction terms determined by the analysis are transmitted from the server to the terminal. The terminal then uses the received information to reflect the content in the company's advertising media and e-commerce platforms. In this way, when a user accesses the site through their terminal, the latest and most optimized pricing information is displayed instantly.

[0075] Users view this latest pricing information on their devices and make purchasing decisions. If a user wants to buy a specific product online, they can verify that the dynamic price calculated by the server is more attractive than competitors' and then decide to purchase the product.

[0076] Furthermore, the device tracks user purchasing behavior and responses to advertisements, and feeds the collected data back to the server. The server analyzes this feedback data and uses it in the next price analysis and optimization process. This allows the system to continuously learn and provide more accurate pricing strategies.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server obtains market information from external sources. It receives access parameters to these external sources as input and collects data using APIs and web scraping. Specifically, it periodically retrieves pricing information for specific online shops and sales data from competitors. This information is stored in a structured format in a database.

[0080] Step 2:

[0081] The server formats the collected market information and prepares it for analysis. It uses raw data as input and processes it by removing unnecessary information and standardizing the format. Specifically, it organizes price and inventory level data by item and stores it in a database in a table format.

[0082] Step 3:

[0083] The server uses a generative AI model to perform data analysis. It receives formatted data as input and performs demand forecasting and competitive analysis. Specifically, it inputs prompts such as "Forecast the demand for next week and propose the optimal pricing strategy" into the generative AI model. This analysis then outputs the optimal trading conditions.

[0084] Step 4:

[0085] The server calculates the optimal price based on the analysis results. It uses demand forecasts and competitive analysis results obtained from the generating AI model as input. Specifically, it performs multiple price simulations to determine the price that maximizes profit. The calculated price information is saved for the next step.

[0086] Step 5:

[0087] The server sends the determined price information to the terminal. It receives optimized price data as input and delivers it to the terminal as output. Specifically, it creates and sends data packages to update the prices of products displayed on e-commerce platforms and advertising media.

[0088] Step 6:

[0089] The device reflects the received price information on advertising media and e-commerce platforms. It receives data sent from the server as input. Specifically, it updates the price display section of the website to show the latest transaction conditions.

[0090] Step 7:

[0091] Users check the latest price information via their device and make purchasing decisions. They receive price and product details displayed on their device as input. Specifically, users check attractive prices and add items to their online shopping cart.

[0092] Step 8:

[0093] The device collects user purchasing behavior data and feeds it back to the server. It receives user activity logs and transaction results as input and sends this information to the server. Specifically, it tracks which products sold well and which advertisements were effective.

[0094] Step 9:

[0095] The server utilizes the feedback data for subsequent analysis and optimization processes. Using the feedback data collected from the terminals as input, it adjusts the analysis model and updates the database. Based on this feedback, the system continues to learn, enabling highly accurate predictions.

[0096] (Application Example 1)

[0097] 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."

[0098] Current e-commerce platforms struggle to respond quickly to market trends and competitor pricing, making it difficult to offer products at optimal prices. This can result in missed sales opportunities and reduced profit margins. Furthermore, users only have access to static pricing information, preventing them from making the best purchasing decisions.

[0099] 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.

[0100] In this invention, the server includes means for collecting market data from external sources, means for analyzing the collected market information to forecast demand and compare it with competitors' products, means for dynamically determining the optimal price based on the analysis results and reflecting it in the e-commerce platform, and means for confirming the optimized price in real time via the user terminal. This enables companies to set optimal prices in real time in response to market fluctuations and always offer attractive prices to users.

[0101] "Market data" refers to information about the price, demand, and competitor activities of products and services in the market.

[0102] "External information sources" refer to sources of information that can be obtained from outside the company, such as the internet or publicly available databases.

[0103] "Analysis" refers to the process of evaluating demand and the competitive environment based on collected data, and deriving specific pricing strategies.

[0104] "Dynamically optimal pricing" refers to the price of a product or service that is adjusted in real time to obtain the best possible profit in response to changes in market conditions and demand.

[0105] An "e-commerce platform" refers to a digital marketplace where goods and services are bought and sold over the internet.

[0106] "User terminal" refers to devices such as smartphones, computers, and tablets that users use to obtain information and perform actions.

[0107] "Real-time verification" refers to the process of instantly obtaining and displaying the latest information without any time delay.

[0108] This invention provides a system for effectively managing market data and implementing dynamic pricing strategies. The server uses APIs and web scraping techniques to collect market data from external sources. The obtained data is stored in a database and organized and formatted in preparation for data analysis.

[0109] The server uses Python to perform data analysis and employs generative AI models using TENSORFLOW® or PyTorch to forecast market demand and conduct competitive analysis. Based on this analysis, the optimal price is dynamically calculated. The calculated price information is then reflected on the e-commerce platform via a RESTful API.

[0110] Users can access this platform using their smartphones or tablets and see optimized prices displayed in real time. This user experience supports purchasing decisions by providing highly immediate pricing information.

[0111] For example, when a user opens the app and browses new sneakers, the server instantly analyzes market data, including the latest pricing information from competitors, and presents the user with the most attractive price. This allows the user to enjoy the maximum price benefit when making a purchase.

[0112] As an example of a prompt, it is possible to instruct the generative AI model to optimize the price by saying something like, "Considering the current market competition, please calculate the optimal price for this product."

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

[0114] Step 1:

[0115] The server retrieves market data from external sources. Using APIs and web scraping techniques, it collects data on product prices, demand information, and competitor pricing trends. This input data is stored in a database and undergoes initial formatting.

[0116] Step 2:

[0117] The server starts data analysis using Python. It extracts data collected from the database and performs demand forecasting and competitive analysis. A generative AI model is used for data calculation, and TensorFlow or PyTorch supports the execution of the model. The analysis yields outputs such as demand trends and competitive intensity under specific market conditions.

[0118] Step 3:

[0119] The server performs dynamic pricing based on the analysis results. It determines the optimal selling price based on demand and competition data calculated by the generating AI model. The output of this calculation is price information for each product, which is updated instantly.

[0120] Step 4:

[0121] The server sends the determined price information to the e-commerce platform via a RESTful API. A specific action in this step is to apply the new price data on the platform and update the display. At this point, users can access the platform to see the latest competitive prices compared to other companies.

[0122] Step 5:

[0123] Users view updated product pricing information using their smartphones or tablets. Prices displayed on the platform are updated in real time, allowing users to intuitively make optimal purchasing decisions. A dedicated application provides a user interface throughout this process, supporting responsive customer acquisition.

[0124] Step 6:

[0125] User purchasing activity and price response data are retransmitted to the server via the terminal. This feedback information is incorporated into the next pricing cycle, leading to improvements in system accuracy. In this step, user interaction information is analyzed and used as input data for further optimization.

[0126] 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.

[0127] This invention combines a sentiment engine with a dynamic pricing system based on the collection and analysis of market data, enabling more sophisticated price optimization and advertising adjustments that respond to user emotions. This system functions through the interaction of servers, terminals, and users.

[0128] First, the server collects market data in real time from external data sources. This includes information such as product prices, demand trends, and competitor activities. The server utilizes analytical models to process the collected data and uses generative AI to perform demand forecasting and competitor analysis. This allows for a comprehensive understanding of market fluctuations and the dynamic calculation of optimal prices.

[0129] The emotion engine utilizes input data from the user's device (e.g., camera footage, audio, and operation patterns) to recognize the user's emotions in real time. The server incorporates the user's emotion data recognized by the emotion engine into its analysis process, thereby optimizing pricing according to the user's emotional state. Considering the impact of emotions on the user's purchasing intent, adjustments are made, such as offering a more attractive price when the user indicates purchasing intent.

[0130] The device dynamically updates advertising media and product pages using optimized pricing and ad content obtained from the server. When users view ads, ads tailored to their emotional state are displayed, resulting in a more personalized purchasing experience. For example, if a user expresses anxiety about making a purchase, ads highlighting limited discounts or guarantees will be displayed.

[0131] As a concrete example, consider an online bookstore. Suppose a user searches for a book and the camera footage detects an emotion of excitement. The emotion engine sends this information to the server, which analyzes this emotion information along with market data to determine a special price that is slightly lower than that of competing bookstores. The terminal updates its advertisements based on this information and displays them to the user at a special price. As a result, the user is more likely to purchase the book, which has the effect of increasing the bookstore's sales.

[0132] This system enhances a company's market competitiveness and improves the customer experience by performing sophisticated market analysis and pricing that takes user emotions into account.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server collects market data from external data sources. Using APIs and web scraping techniques, the server gathers product prices, consumer trends, and competitor pricing information in real time and stores it in a database.

[0136] Step 2:

[0137] The server cleanses the collected data and formats it into an analyzable format. By imputing missing data and standardizing the format, it improves the accuracy and consistency of the data.

[0138] Step 3:

[0139] The server uses a generative AI model to analyze data. Specifically, it performs market demand forecasting and competitive price analysis, and then uses the insights gained to perform basic price optimization.

[0140] Step 4:

[0141] The device acquires user emotion data. The device analyzes the user's facial expressions and voice through its built-in camera and microphone, and the emotion engine analyzes this in real time to recognize emotions such as excitement, joy, and anxiety.

[0142] Step 5:

[0143] The emotion engine sends its output to the server. The server uses the user's emotion data, combined with the analysis results, to perform dynamic price adjustments. Specifically, it changes the price based on a particular emotional state. For example, if the user is very excited, the price of the product is set a little higher, while if the user shows anxiety, a discount is applied.

[0144] Step 6:

[0145] The server sends optimized pricing and ad content to the device. The device then uses this information to update the information on online stores and advertising platforms, and reflects it in the user's view.

[0146] Step 7:

[0147] Users view the latest prices and advertisements through their devices. Presenting dynamically tailored information based on the user's emotions increases the likelihood of stimulating purchasing intent and encouraging purchases.

[0148] Step 8:

[0149] The device records the user's browsing history and new sentiment data, and feeds this information back to the server. The server uses this feedback to learn and further improve the accuracy of future pricing and ad adjustments.

[0150] (Example 2)

[0151] 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".

[0152] It is necessary to set appropriate prices and maximize sales by simultaneously considering market trends and user sentiment. However, conventional systems have found it difficult to integrate market data analysis and user sentiment, making it impossible to reliably achieve optimal pricing.

[0153] 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.

[0154] In this invention, the server includes means for collecting market information from external sources, means for analyzing the collected market information to perform demand forecasting and competitor analysis, and means for sensing the emotional state of the user. This makes it possible to dynamically determine the optimal price based on the analysis results and the emotional state.

[0155] "Market information" refers to data about the current state of the market collected from external sources, such as product prices, demand trends, and competitor activities.

[0156] "External information sources" refer to information providers outside the system, such as data providers and web APIs used to provide market information.

[0157] "Demand forecasting" refers to the process of predicting future consumer demand trends based on past and present market information.

[0158] "Competitor analysis" refers to the analysis conducted to investigate the activities and strategies of competitors in the market and to obtain information necessary to maintain a competitive advantage.

[0159] "User emotional state" refers to the emotional state perceived from a user's behavior, facial expressions, voice, etc., and includes factors that influence purchasing intent.

[0160] "Pricing" refers to the process of determining an appropriate selling price for a product or service, taking into account market information and the emotional state of users.

[0161] "Display medium" refers to a medium, such as a terminal or digital display, used to display price information and advertising content to users.

[0162] "Information terminal" refers to electronic devices such as computers and mobile devices that users use to receive information about products and services.

[0163] This invention relates to a dynamic pricing system in which a server, terminal, and user work together to collect and analyze market information and sentiment data, thereby optimizing the user experience.

[0164] Server role:

[0165] The server collects market information in real time from external sources via APIs. This includes data on product pricing, demand trends, and competitor activity. The collected market information is stored in a database and analyzed using a generative AI model. The generative AI model performs demand forecasting and competitor analysis, and takes into account user sentiment to determine optimal pricing.

[0166] Terminal role:

[0167] The device uses a camera and microphone to sense the user's emotional state. This allows the user's facial expressions and voice tone to be collected in real time and analyzed by an emotion engine. As a result, the user's emotional data is sent to a server and used to determine pricing. Based on the optimized pricing information received from the server, the device updates its display media and provides the user with personalized advertisements and pricing information.

[0168] User roles:

[0169] Users interact with the device when selecting products and services, and their emotional state is sensed by the system. This allows for attractive pricing that takes the user's purchasing intent into consideration.

[0170] As a concrete example, consider a case where an online bookstore has implemented this system. When a user views a particular book, if the device's camera detects excitement from the user's facial expression, the emotion engine analyzes this information and sends it to the server. The server analyzes this emotion data along with market information to determine a special price that is slightly lower than that of competing bookstores. The device uses this price to update its advertisements and offer them to the user, increasing the likelihood that the user will purchase the book.

[0171] An example of a prompt would be: "Design an algorithm that performs dynamic pricing based on user emotions. In this case, explain how to obtain user emotion information (excitement, anxiety, etc.) in real time from an emotion engine, analyze market data and emotion data using a generative AI model, and calculate the optimal price."

[0172] This system enhances a company's competitiveness while improving the user's purchasing experience by comprehensively analyzing market and user sentiment and enabling dynamic pricing.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server collects market information from external sources. It retrieves data such as product prices, demand trends, and competitor activity via APIs. Input is raw data from the API, and output is formalized data stored in a database. Specifically, the server completes the API authentication process, sends information retrieval requests, and structures and stores the obtained data.

[0176] Step 2:

[0177] The device uses a camera and microphone to sense the user's emotional state. The input is real-time audio and video data from the user, and the output is emotion analysis data from the emotion engine. Specifically, the device activates sensors, the collected data is analyzed by a machine learning algorithm within the emotion engine, and the user's emotional state is determined.

[0178] Step 3:

[0179] The server uses a generative AI model to analyze collected market information and user sentiment data. The input is market information and real-time sentiment data pulled from a database, and the output is optimized price information. Specifically, the server provides these inputs to the generative AI model and runs a predictive algorithm to determine a price that takes into account supply and demand conditions and sentiment feedback.

[0180] Step 4:

[0181] The terminal uses optimized pricing information received from the server to update the display media. The input is optimized pricing information from the server, and the output is the updated product page or advertisement display. Specifically, the terminal stores the pricing information in temporary memory and updates the user screen in real time using a display template.

[0182] Step 5:

[0183] Users view updated product information, which influences their purchasing decisions. Input is the information displayed on the device, and output is the user's action—purchase or continued consideration. Specifically, users refer to displayed special offers and personalized advertisements, and make decisions by proceeding with or canceling the purchase process. The user's emotional state is also continuously monitored on the device, and advertising is further adjusted as needed.

[0184] (Application Example 2)

[0185] 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 device 14 will be referred to as the "terminal."

[0186] Traditional dynamic pricing systems optimized prices based on market data, but they did not take into account user emotions or emotional factors. Therefore, they were unable to respond quickly to fluctuations in user purchasing intent, resulting in pricing that could not be considered optimized. The challenge now is to achieve price and advertising optimization that takes user emotions into account.

[0187] 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.

[0188] In this invention, the server includes means for collecting market data from an external data source, means for analyzing the collected market data to perform demand forecasting and competitive analysis, and means for analyzing sentiment information obtained from the user's terminal and reflecting it in pricing. This enables more precise pricing and advertising adjustments based on the user's emotional state.

[0189] "Market data" refers to information collected from external data sources and used for analysis, such as product prices, demand trends, and competitor activities.

[0190] "Methods for dynamically determining the optimal price" refer to the process of optimizing product prices in real time based on the results of market data analysis.

[0191] "Emotional information obtained from the user's device" refers to data that indicates the user's current emotional state, obtained through methods such as facial recognition and voice analysis.

[0192] "Advertising media" refers to means or platforms used to present information to users, such as product pages on the internet or online advertisements.

[0193] "Analysis" is the process of using collected data to forecast demand, analyze competitors, and analyze user sentiment, thereby guiding decisions regarding pricing and advertising.

[0194] The system for realizing this invention consists of a server, a terminal, and a user terminal.

[0195] The server first collects market data from external data sources. This includes product pricing information, demand trends, and competitor activities. The collected market data is then used with a generative AI model to forecast demand and perform competitive analysis, dynamically optimizing pricing.

[0196] Furthermore, the user's device acquires emotional information using sensors such as cameras and microphones. For example, facial recognition and voice analysis technologies are used to analyze the user's emotional state in real time. This emotional information is sent to a server and incorporated into pricing and advertising adjustments.

[0197] The device receives optimized pricing and sentiment-based ad content from the server, reflecting it on the advertising platform and presenting it to the user. This makes it possible to provide a personalized purchasing experience that aligns with the user's emotions.

[0198] As a concrete example, consider a scenario where a user is browsing an e-commerce site on their smartphone and the device detects the user's excited state. Based on this information, the server immediately sets a special discounted price and sends it to the device. The user's device then instantly displays an advertisement for the special price based on this information. As a result, the likelihood of the user purchasing the product increases, leading to increased sales opportunities.

[0199] An example of a prompt message might be: "Design a smartphone app that recognizes user emotions in real time and displays corresponding prices and advertisements. Optimize the user experience using Python and OpenCV."

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The server collects market data from external data sources. Inputs include product pricing information, demand trends, and competitor activity data. By collecting and organizing this data, it prepares the foundational data necessary for subsequent analysis.

[0203] Step 2:

[0204] The server analyzes the collected market data using a generating AI model. The input is the market data collected in step 1. Through the analysis, it obtains demand forecasts and competitive analysis results, and based on these, it performs calculations to derive the optimal pricing strategy.

[0205] Step 3:

[0206] The user's device acquires emotional information using sensors such as cameras and microphones. The input consists of real-time image and audio data. This data is processed by an emotion analysis engine to detect the user's emotional state in real time.

[0207] Step 4:

[0208] The device sends the sentiment information acquired in step 3 to the server. The input is the sentiment analysis result, and by transmitting this to the server, the server uses the sentiment information for pricing and ad adjustments.

[0209] Step 5:

[0210] The server dynamically adjusts pricing and ad content, taking sentiment information into account. Inputs include previously analyzed market data and user sentiment information. Based on this data, it calculates attractive pricing and ad content, generating optimized pricing and ad content as output.

[0211] Step 6:

[0212] The server sends optimized pricing and ad content to the device. The input is the pricing and ad data calculated in step 5. The output is dynamically adjusted information that is reflected on the user's device, providing data for display to the user.

[0213] Step 7:

[0214] The terminal receives price and advertisement content from the server, reflects it on the advertising medium, and presents it to the user. The input is optimized information from the server. Based on this, it displays price information and advertisements tailored to the user in real time, stimulating purchasing intent and achieving effective sales activities.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] [Second Embodiment]

[0219] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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".

[0231] The system of this invention enables the realization of dynamic pricing strategies in the market. This system effectively exchanges information between servers, terminals, and users to achieve price optimization.

[0232] First, the server retrieves market data from external data sources. This data is collected using APIs and web scraping techniques and includes product prices, demand information, and information about competitor activities. The collected data is first stored in a database and then organized and formatted.

[0233] Next, the server uses a generative AI model to analyze the collected market data. This analysis includes demand forecasting and competitive analysis. Based on these analysis results, the server determines the optimal price. This generative AI takes into account past sales history and market demand fluctuations to calculate the price with the highest profit margin under specific conditions.

[0234] Next, the server sends this optimized pricing information to the terminal. The terminal uses the received pricing information to reflect it on the advertising media and e-commerce platforms managed by the company. As a result, when users access these platforms, they are presented with the latest and most optimized prices for each product.

[0235] Users view updated pricing information via their devices and decide whether to purchase. For example, when a user tries to buy clothes online, the server displays dynamic pricing based on real-time data analysis, allowing them to see prices that are more attractive than those of competitors. As a result, users determine that the price is appropriate and decide to purchase, thereby increasing the company's revenue.

[0236] Furthermore, user purchasing behavior and advertising response data are fed back from the terminal to the server. This feedback data is used in the next price optimization process. This allows the system to continuously learn and provide more efficient pricing strategies.

[0237] Thus, the system of the present invention helps companies respond to market fluctuations efficiently and effectively through a cycle of acquiring and analyzing market data, setting optimized prices, incorporating advertising, and generating user feedback.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The server acquires market data from external data sources. Using API integration and web scraping techniques, the server collects product prices, demand trends, and competitor activity information in real time.

[0241] Step 2:

[0242] The server stores the acquired market data in a database and performs data preprocessing. The server cleans the data, imputing missing values, correcting outliers, and standardizing the format to prepare it for analysis.

[0243] Step 3:

[0244] The server analyzes market data using a generative AI model. The server applies a demand forecasting model to predict future demand and analyzes competitors' pricing trends and market share.

[0245] Step 4:

[0246] The server dynamically determines the optimal price based on the analysis results. Using a price optimization algorithm, the server selects the appropriate price from multiple simulation patterns, aiming to maximize profits and expand sales.

[0247] Step 5:

[0248] The server sends optimized pricing information to the terminal. The server distributes the new pricing data through the company's advertising platform management system.

[0249] Step 6:

[0250] The device automatically updates prices on advertising media and e-commerce sites based on the received new price information. The device reflects the latest prices in real time and prepares to present them to the user.

[0251] Step 7:

[0252] Users view advertisements and product pages displaying the latest prices through their devices. Seeing more attractive prices than competitors prompts them to consider purchasing.

[0253] Step 8:

[0254] The device records the user's browsing history and purchase activity and provides this feedback to the server. The server uses this feedback data to improve future price optimization processes and further refine its approach.

[0255] (Example 1)

[0256] 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."

[0257] Pricing strategies in the market are highly competitive, and companies need to set prices that can quickly respond to dynamic market conditions. However, traditional methods often fail to adequately consider past sales history and fluctuations in market demand, making it difficult to set optimal prices. Furthermore, providing consumers with real-time pricing information is challenging, sometimes resulting in missed market opportunities.

[0258] 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.

[0259] In this invention, the server includes means for acquiring market information from external sources, means for analyzing the acquired market information to perform demand forecasting and competitive analysis, and means for performing data analysis using a generative AI model, taking into account past transaction history and market demand fluctuations. This enables companies to calculate optimal transaction conditions in real time and provide them quickly to consumers.

[0260] "Market information" refers to data about market trends and conditions, and is a general term for information including product prices, demand information, and the activities of competitors.

[0261] "External information sources" refer to data sources that are not located within a company and are provided objectively or by third parties, such as online platforms and research databases.

[0262] A "generative AI model" is an artificial intelligence system that uses algorithms to perform pattern recognition and prediction based on large amounts of data, and is a model that performs the analytical processing necessary for optimizing pricing strategies.

[0263] "Consumer terminals" refer to devices such as computers, smartphones, and tablets used by consumers, through which price information and transaction terms provided by companies are displayed.

[0264] "Feedback" refers to data manipulation that involves collecting consumer behavior data and advertising response data, and using that data to improve the overall performance of the system.

[0265] This invention provides a system that enables dynamic pricing strategies in the market through the cooperation of a server, a terminal, and a user.

[0266] The server first obtains market information from external sources. This includes data collection using APIs and web scraping techniques. For example, it collects data on product prices, demand trends, and competitor activities from a specific online store or market research site. This information is then stored in a database and processed for analysis.

[0267] Next, the server uses a generative AI model to analyze this market information in detail. The generative AI model performs demand forecasting and competitive analysis based on a large amount of aggregated data. Past sales history and market demand fluctuation information are taken into consideration to calculate the optimal trading conditions under specific circumstances. In this analysis process, for example, a prompt such as "Please suggest the optimal pricing strategy that reflects this week's trends" is input to the generative AI model, and the analysis is performed.

[0268] The transaction terms determined by the analysis are transmitted from the server to the terminal. The terminal then uses the received information to reflect the content in the company's advertising media and e-commerce platforms. In this way, when a user accesses the site through their terminal, the latest and most optimized pricing information is displayed instantly.

[0269] Users view this latest pricing information on their devices and make purchasing decisions. If a user wants to buy a specific product online, they can verify that the dynamic price calculated by the server is more attractive than competitors' and then decide to purchase the product.

[0270] Furthermore, the device tracks user purchasing behavior and responses to advertisements, and feeds the collected data back to the server. The server analyzes this feedback data and uses it in the next price analysis and optimization process. This allows the system to continuously learn and provide more accurate pricing strategies.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The server obtains market information from external sources. It receives access parameters to these external sources as input and collects data using APIs and web scraping. Specifically, it periodically retrieves pricing information for specific online shops and sales data from competitors. This information is stored in a structured format in a database.

[0274] Step 2:

[0275] The server formats the collected market information and prepares it for analysis. It uses raw data as input and processes it by removing unnecessary information and standardizing the format. Specifically, it organizes price and inventory level data by item and stores it in a database in a table format.

[0276] Step 3:

[0277] The server performs data analysis using the generative AI model. It receives the data formatted as input and conducts demand forecasting and competitive analysis. As a specific operation, it inputs a prompt sentence such as "Please predict the demand for the next week and propose an optimal pricing strategy" into the generative AI model. Through this analysis, optimal trading conditions are output.

[0278] Step 4:

[0279] Based on the analysis results, the server calculates the optimal price. It uses the demand forecasting and competitive analysis results obtained from the generative AI model as input. As a specific operation, it conducts multiple price simulations to determine the price that maximizes profit. The calculated price information is saved in preparation for the next step.

[0280] Step 5:

[0281] The server sends the determined price information to the terminal. It receives the optimized price data as input and distributes it to the terminal as output. In a specific operation, it creates and sends a data package for updating the prices of products displayed on e-commerce platforms and advertising media.

[0282] Step 6:

[0283] The terminal reflects the received price information on advertising media and e-commerce platforms. It receives the data sent from the server as input. As a specific operation, it updates the price display part of the website and displays the latest trading conditions.

[0284] Step 7:

[0285] The user checks the latest price information through the terminal and makes a purchase decision. It receives as input the price and detailed product information displayed from the terminal. As a specific action, the user checks the attractive price of the product and adds the product to the online shopping cart.

[0286] Step 8:

[0287] The terminal collects the user's purchase behavior data and provides feedback to the server. As input, it receives the user's action log and transaction results, and transmits this information to the server. Specifically, it tracks which products sell well and which advertisements are effective.

[0288] Step 9:

[0289] The server utilizes the feedback data in the next analysis and optimization process. Using the feedback data collected from the terminal as input, it adjusts the analysis model and updates the database. Based on this feedback, the system continues to learn, enabling highly accurate predictions.

[0290] (Application Example 1)

[0291] Next, Application Example 1 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".

[0292] In the current e-commerce trading platform, it is difficult to quickly respond to market trends and the price settings of competing companies, and it is difficult to offer products at the optimal price. As a result, sales opportunities may be missed, and the profit rate may decrease. Furthermore, there is a problem that users can only obtain static price information and cannot always make the best purchase decisions.

[0293] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0294] In this invention, the server includes means for collecting market data from external sources, means for analyzing the collected market information to forecast demand and compare it with competitors' products, means for dynamically determining the optimal price based on the analysis results and reflecting it in the e-commerce platform, and means for confirming the optimized price in real time via the user terminal. This enables companies to set optimal prices in real time in response to market fluctuations and always offer attractive prices to users.

[0295] "Market data" refers to information about the price, demand, and competitor activities of products and services in the market.

[0296] "External information sources" refer to sources of information that can be obtained from outside the company, such as the internet or publicly available databases.

[0297] "Analysis" refers to the process of evaluating demand and the competitive environment based on collected data, and deriving specific pricing strategies.

[0298] "Dynamically optimal pricing" refers to the price of a product or service that is adjusted in real time to obtain the best possible profit in response to changes in market conditions and demand.

[0299] An "e-commerce platform" refers to a digital marketplace where goods and services are bought and sold over the internet.

[0300] "User terminal" refers to devices such as smartphones, computers, and tablets that users use to obtain information and perform actions.

[0301] "Real-time verification" refers to the process of instantly obtaining and displaying the latest information without any time delay.

[0302] The present invention is a system that effectively manages market data and realizes a dynamic pricing strategy. The server uses APIs and web scraping technologies to collect market data from external information sources. The obtained data is stored in a database and organized and formatted in preparation for data analysis.

[0303] The server performs data analysis using Python and conducts market demand forecasting and competitive analysis with a generated AI model using TensorFlow or PyTorch. Based on this analysis, an optimally dynamic price is calculated. The calculated price information is reflected in the e-commerce platform through a RESTful API.

[0304] Users can use smartphones or tablet terminals to access this platform and confirm that the optimally dynamic price is displayed in real time. This user experience supports the purchasing decision-making by providing price information with excellent immediacy.

[0305] As a specific example, when a user opens an app and browses new sneakers, the server immediately analyzes market data including the latest price information of competing companies and presents the most attractive price for the user. Thereby, the user can maximize the benefits in terms of price when purchasing.

[0306] As an example of a prompt sentence, it is possible to give an instruction for price optimization to the generated AI model in the form of "Please calculate the optimal price of this product considering the current market competition situation."

[0307] The flow of a specific process in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] The server retrieves market data from external sources. Using APIs and web scraping techniques, it collects data on product prices, demand information, and competitor pricing trends. This input data is stored in a database and undergoes initial formatting.

[0310] Step 2:

[0311] The server starts data analysis using Python. It extracts data collected from the database and performs demand forecasting and competitive analysis. A generative AI model is used for data calculation, and TensorFlow or PyTorch supports the execution of the model. The analysis yields outputs such as demand trends and competitive intensity under specific market conditions.

[0312] Step 3:

[0313] The server performs dynamic pricing based on the analysis results. It determines the optimal selling price based on demand and competition data calculated by the generating AI model. The output of this calculation is price information for each product, which is updated instantly.

[0314] Step 4:

[0315] The server sends the determined price information to the e-commerce platform via a RESTful API. A specific action in this step is to apply the new price data on the platform and update the display. At this point, users can access the platform to see the latest competitive prices compared to other companies.

[0316] Step 5:

[0317] Users view updated product pricing information using their smartphones or tablets. Prices displayed on the platform are updated in real time, allowing users to intuitively make optimal purchasing decisions. A dedicated application provides a user interface throughout this process, supporting responsive customer acquisition.

[0318] Step 6:

[0319] User purchasing activity and price response data are retransmitted to the server via the terminal. This feedback information is incorporated into the next pricing cycle, leading to improvements in system accuracy. In this step, user interaction information is analyzed and used as input data for further optimization.

[0320] 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.

[0321] This invention combines a sentiment engine with a dynamic pricing system based on the collection and analysis of market data, enabling more sophisticated price optimization and advertising adjustments that respond to user emotions. This system functions through the interaction of servers, terminals, and users.

[0322] First, the server collects market data in real time from external data sources. This includes information such as product prices, demand trends, and competitor activities. The server utilizes analytical models to process the collected data and uses generative AI to perform demand forecasting and competitor analysis. This allows for a comprehensive understanding of market fluctuations and the dynamic calculation of optimal prices.

[0323] The emotion engine utilizes input data from the user's device (e.g., camera footage, audio, and operation patterns) to recognize the user's emotions in real time. The server incorporates the user's emotion data recognized by the emotion engine into its analysis process, thereby optimizing pricing according to the user's emotional state. Considering the impact of emotions on the user's purchasing intent, adjustments are made, such as offering a more attractive price when the user indicates purchasing intent.

[0324] The device dynamically updates advertising media and product pages using optimized pricing and ad content obtained from the server. When users view ads, ads tailored to their emotional state are displayed, resulting in a more personalized purchasing experience. For example, if a user expresses anxiety about making a purchase, ads highlighting limited discounts or guarantees will be displayed.

[0325] As a concrete example, consider an online bookstore. Suppose a user searches for a book and the camera footage detects an emotion of excitement. The emotion engine sends this information to the server, which analyzes this emotion information along with market data to determine a special price that is slightly lower than that of competing bookstores. The terminal updates its advertisements based on this information and displays them to the user at a special price. As a result, the user is more likely to purchase the book, which has the effect of increasing the bookstore's sales.

[0326] This system enhances a company's market competitiveness and improves the customer experience by performing sophisticated market analysis and pricing that takes user emotions into account.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The server collects market data from external data sources. Using APIs and web scraping techniques, the server gathers product prices, consumer trends, and competitor pricing information in real time and stores it in a database.

[0330] Step 2:

[0331] The server cleanses the collected data and formats it into an analyzable format. By imputing missing data and standardizing the format, it improves the accuracy and consistency of the data.

[0332] Step 3:

[0333] The server uses a generative AI model to analyze data. Specifically, it performs market demand forecasting and competitive price analysis, and then uses the insights gained to perform basic price optimization.

[0334] Step 4:

[0335] The device acquires user emotion data. The device analyzes the user's facial expressions and voice through its built-in camera and microphone, and the emotion engine analyzes this in real time to recognize emotions such as excitement, joy, and anxiety.

[0336] Step 5:

[0337] The emotion engine sends its output to the server. The server uses the user's emotion data, combined with the analysis results, to perform dynamic price adjustments. Specifically, it changes the price based on a particular emotional state. For example, if the user is very excited, the price of the product is set a little higher, while if the user shows anxiety, a discount is applied.

[0338] Step 6:

[0339] The server sends optimized pricing and ad content to the device. The device then uses this information to update the information on online stores and advertising platforms, and reflects it in the user's view.

[0340] Step 7:

[0341] Users view the latest prices and advertisements through their devices. Presenting dynamically tailored information based on the user's emotions increases the likelihood of stimulating purchasing intent and encouraging purchases.

[0342] Step 8:

[0343] The device records the user's browsing history and new sentiment data, and feeds this information back to the server. The server uses this feedback to learn and further improve the accuracy of future pricing and ad adjustments.

[0344] (Example 2)

[0345] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0346] It is necessary to set appropriate prices and maximize sales by simultaneously considering market trends and user sentiment. However, conventional systems have found it difficult to integrate market data analysis and user sentiment, making it impossible to reliably achieve optimal pricing.

[0347] 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.

[0348] In this invention, the server includes means for collecting market information from external sources, means for analyzing the collected market information to perform demand forecasting and competitor analysis, and means for sensing the emotional state of the user. This makes it possible to dynamically determine the optimal price based on the analysis results and the emotional state.

[0349] "Market information" refers to data about the current state of the market collected from external sources, such as product prices, demand trends, and competitor activities.

[0350] "External information sources" refer to information providers outside the system, such as data providers and web APIs used to provide market information.

[0351] "Demand forecasting" refers to the process of predicting future consumer demand trends based on past and present market information.

[0352] "Competitor analysis" refers to the analysis conducted to investigate the activities and strategies of competitors in the market and to obtain information necessary to maintain a competitive advantage.

[0353] "User emotional state" refers to the emotional state perceived from a user's behavior, facial expressions, voice, etc., and includes factors that influence purchasing intent.

[0354] "Pricing" refers to the process of determining an appropriate selling price for a product or service, taking into account market information and the emotional state of users.

[0355] "Display medium" refers to a medium, such as a terminal or digital display, used to display price information and advertising content to users.

[0356] "Information terminal" refers to electronic devices such as computers and mobile devices that users use to receive information about products and services.

[0357] This invention relates to a dynamic pricing system in which a server, terminal, and user work together to collect and analyze market information and sentiment data, thereby optimizing the user experience.

[0358] Server role:

[0359] The server collects market information in real time from external sources via APIs. This includes data on product pricing, demand trends, and competitor activity. The collected market information is stored in a database and analyzed using a generative AI model. The generative AI model performs demand forecasting and competitor analysis, and takes into account user sentiment to determine optimal pricing.

[0360] Terminal role:

[0361] The device uses a camera and microphone to sense the user's emotional state. This allows the user's facial expressions and voice tone to be collected in real time and analyzed by an emotion engine. As a result, the user's emotional data is sent to a server and used to determine pricing. Based on the optimized pricing information received from the server, the device updates its display media and provides the user with personalized advertisements and pricing information.

[0362] User roles:

[0363] Users interact with the device when selecting products and services, and their emotional state is sensed by the system. This allows for attractive pricing that takes the user's purchasing intent into consideration.

[0364] As a concrete example, consider a case where an online bookstore has implemented this system. When a user views a particular book, if the device's camera detects excitement from the user's facial expression, the emotion engine analyzes this information and sends it to the server. The server analyzes this emotion data along with market information to determine a special price that is slightly lower than that of competing bookstores. The device uses this price to update its advertisements and offer them to the user, increasing the likelihood that the user will purchase the book.

[0365] An example of a prompt would be: "Design an algorithm that performs dynamic pricing based on user emotions. In this case, explain how to obtain user emotion information (excitement, anxiety, etc.) in real time from an emotion engine, analyze market data and emotion data using a generative AI model, and calculate the optimal price."

[0366] This system enhances a company's competitiveness while improving the user's purchasing experience by comprehensively analyzing market and user sentiment and enabling dynamic pricing.

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The server collects market information from external sources. It retrieves data such as product prices, demand trends, and competitor activity via APIs. Input is raw data from the API, and output is formalized data stored in a database. Specifically, the server completes the API authentication process, sends information retrieval requests, and structures and stores the obtained data.

[0370] Step 2:

[0371] The device uses a camera and microphone to sense the user's emotional state. The input is real-time audio and video data from the user, and the output is emotion analysis data from the emotion engine. Specifically, the device activates sensors, the collected data is analyzed by a machine learning algorithm within the emotion engine, and the user's emotional state is determined.

[0372] Step 3:

[0373] The server uses a generative AI model to analyze collected market information and user sentiment data. The input is market information and real-time sentiment data pulled from a database, and the output is optimized price information. Specifically, the server provides these inputs to the generative AI model and runs a predictive algorithm to determine a price that takes into account supply and demand conditions and sentiment feedback.

[0374] Step 4:

[0375] The terminal uses optimized pricing information received from the server to update the display media. The input is optimized pricing information from the server, and the output is the updated product page or advertisement display. Specifically, the terminal stores the pricing information in temporary memory and updates the user screen in real time using a display template.

[0376] Step 5:

[0377] Users view updated product information, which influences their purchasing decisions. Input is the information displayed on the device, and output is the user's action—purchase or continued consideration. Specifically, users refer to displayed special offers and personalized advertisements, and make decisions by proceeding with or canceling the purchase process. The user's emotional state is also continuously monitored on the device, and advertising is further adjusted as needed.

[0378] (Application Example 2)

[0379] 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."

[0380] Traditional dynamic pricing systems optimized prices based on market data, but they did not take into account user emotions or emotional factors. Therefore, they were unable to respond quickly to fluctuations in user purchasing intent, resulting in pricing that could not be considered optimized. The challenge now is to achieve price and advertising optimization that takes user emotions into account.

[0381] 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.

[0382] In this invention, the server includes means for collecting market data from an external data source, means for analyzing the collected market data to perform demand forecasting and competitive analysis, and means for analyzing sentiment information obtained from the user's terminal and reflecting it in pricing. This enables more precise pricing and advertising adjustments based on the user's emotional state.

[0383] "Market data" refers to information collected from external data sources and used for analysis, such as product prices, demand trends, and competitor activities.

[0384] "Methods for dynamically determining the optimal price" refer to the process of optimizing product prices in real time based on the results of market data analysis.

[0385] "Emotional information obtained from the user's device" refers to data that indicates the user's current emotional state, obtained through methods such as facial recognition and voice analysis.

[0386] "Advertising media" refers to means or platforms used to present information to users, such as product pages on the internet or online advertisements.

[0387] "Analysis" is the process of using collected data to forecast demand, analyze competitors, and analyze user sentiment, thereby guiding decisions regarding pricing and advertising.

[0388] The system for realizing this invention consists of a server, a terminal, and a user terminal.

[0389] The server first collects market data from external data sources. This includes product pricing information, demand trends, and competitor activities. The collected market data is then used with a generative AI model to forecast demand and perform competitive analysis, dynamically optimizing pricing.

[0390] Furthermore, the user's device acquires emotional information using sensors such as cameras and microphones. For example, facial recognition and voice analysis technologies are used to analyze the user's emotional state in real time. This emotional information is sent to a server and incorporated into pricing and advertising adjustments.

[0391] The device receives optimized pricing and sentiment-based ad content from the server, reflecting it on the advertising platform and presenting it to the user. This makes it possible to provide a personalized purchasing experience that aligns with the user's emotions.

[0392] As a concrete example, consider a scenario where a user is browsing an e-commerce site on their smartphone and the device detects the user's excited state. Based on this information, the server immediately sets a special discounted price and sends it to the device. The user's device then instantly displays an advertisement for the special price based on this information. As a result, the likelihood of the user purchasing the product increases, leading to increased sales opportunities.

[0393] An example of a prompt message might be: "Design a smartphone app that recognizes user emotions in real time and displays corresponding prices and advertisements. Optimize the user experience using Python and OpenCV."

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The server collects market data from external data sources. Inputs include product pricing information, demand trends, and competitor activity data. By collecting and organizing this data, it prepares the foundational data necessary for subsequent analysis.

[0397] Step 2:

[0398] The server analyzes the collected market data using a generating AI model. The input is the market data collected in step 1. Through the analysis, it obtains demand forecasts and competitive analysis results, and based on these, it performs calculations to derive the optimal pricing strategy.

[0399] Step 3:

[0400] The user's device acquires emotional information using sensors such as cameras and microphones. The input consists of real-time image and audio data. This data is processed by an emotion analysis engine to detect the user's emotional state in real time.

[0401] Step 4:

[0402] The device sends the sentiment information acquired in step 3 to the server. The input is the sentiment analysis result, and by transmitting this to the server, the server uses the sentiment information for pricing and ad adjustments.

[0403] Step 5:

[0404] The server dynamically adjusts pricing and ad content, taking sentiment information into account. Inputs include previously analyzed market data and user sentiment information. Based on this data, it calculates attractive pricing and ad content, generating optimized pricing and ad content as output.

[0405] Step 6:

[0406] The server sends optimized pricing and ad content to the device. The input is the pricing and ad data calculated in step 5. The output is dynamically adjusted information that is reflected on the user's device, providing data for display to the user.

[0407] Step 7:

[0408] The terminal receives price and advertisement content from the server and displays it on the advertising medium for the user. The input is optimized information from the server. Based on this, it displays price information and advertisements tailored to the user in real time, stimulating purchasing intent and achieving effective sales activities.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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".

[0425] The system of this invention enables the realization of dynamic pricing strategies in the market. This system effectively exchanges information between servers, terminals, and users to achieve price optimization.

[0426] First, the server retrieves market data from external data sources. This data is collected using APIs and web scraping techniques and includes product prices, demand information, and information about competitor activities. The collected data is first stored in a database and then organized and formatted.

[0427] Next, the server uses a generative AI model to analyze the collected market data. This analysis includes demand forecasting and competitive analysis. Based on these analysis results, the server determines the optimal price. This generative AI takes into account past sales history and market demand fluctuations to calculate the price with the highest profit margin under specific conditions.

[0428] Next, the server sends this optimized pricing information to the terminal. The terminal uses the received pricing information to reflect it on the advertising media and e-commerce platforms managed by the company. As a result, when users access these platforms, they are presented with the latest and most optimized prices for each product.

[0429] Users view updated pricing information via their devices and decide whether to purchase. For example, when a user tries to buy clothes online, the server displays dynamic pricing based on real-time data analysis, allowing them to see prices that are more attractive than those of competitors. As a result, users determine that the price is appropriate and decide to purchase, thereby increasing the company's revenue.

[0430] Furthermore, user purchasing behavior and advertising response data are fed back from the terminal to the server. This feedback data is used in the next price optimization process. This allows the system to continuously learn and provide more efficient pricing strategies.

[0431] Thus, the system of the present invention helps companies respond to market fluctuations efficiently and effectively through a cycle of acquiring and analyzing market data, setting optimized prices, incorporating advertising, and generating user feedback.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The server acquires market data from external data sources. Using API integration and web scraping techniques, the server collects product prices, demand trends, and competitor activity information in real time.

[0435] Step 2:

[0436] The server stores the acquired market data in a database and performs data preprocessing. The server cleans the data, imputing missing values, correcting outliers, and standardizing the format to prepare it for analysis.

[0437] Step 3:

[0438] The server analyzes market data using a generative AI model. The server applies a demand forecasting model to predict future demand and analyzes competitors' pricing trends and market share.

[0439] Step 4:

[0440] The server dynamically determines the optimal price based on the analysis results. Using a price optimization algorithm, the server selects the appropriate price from multiple simulation patterns, aiming to maximize profits and expand sales.

[0441] Step 5:

[0442] The server sends optimized pricing information to the terminal. The server distributes the new pricing data through the company's advertising platform management system.

[0443] Step 6:

[0444] The device automatically updates prices on advertising media and e-commerce sites based on the received new price information. The device reflects the latest prices in real time and prepares to present them to the user.

[0445] Step 7:

[0446] Users view advertisements and product pages displaying the latest prices through their devices. Seeing more attractive prices than competitors prompts them to consider purchasing.

[0447] Step 8:

[0448] The device records the user's browsing history and purchase activity and provides this feedback to the server. The server uses this feedback data to improve future price optimization processes and further refine its approach.

[0449] (Example 1)

[0450] 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."

[0451] Pricing strategies in the market are highly competitive, and companies need to set prices that can quickly respond to dynamic market conditions. However, traditional methods often fail to adequately consider past sales history and fluctuations in market demand, making it difficult to set optimal prices. Furthermore, providing consumers with real-time pricing information is challenging, sometimes resulting in missed market opportunities.

[0452] 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.

[0453] In this invention, the server includes means for acquiring market information from external sources, means for analyzing the acquired market information to perform demand forecasting and competitive analysis, and means for performing data analysis using a generative AI model, taking into account past transaction history and market demand fluctuations. This enables companies to calculate optimal transaction conditions in real time and provide them quickly to consumers.

[0454] "Market information" refers to data about market trends and conditions, and is a general term for information including product prices, demand information, and the activities of competitors.

[0455] "External information sources" refer to data sources that are not located within a company and are provided objectively or by third parties, such as online platforms and research databases.

[0456] A "generative AI model" is an artificial intelligence system that uses algorithms to perform pattern recognition and prediction based on large amounts of data, and is a model that performs the analytical processing necessary for optimizing pricing strategies.

[0457] "Consumer terminals" refer to devices such as computers, smartphones, and tablets used by consumers, through which price information and transaction terms provided by companies are displayed.

[0458] "Feedback" refers to data manipulation that involves collecting consumer behavior data and advertising response data, and using that data to improve the overall performance of the system.

[0459] This invention provides a system that enables dynamic pricing strategies in the market through the cooperation of a server, a terminal, and a user.

[0460] The server first obtains market information from external sources. This includes data collection using APIs and web scraping techniques. For example, it collects data on product prices, demand trends, and competitor activities from a specific online store or market research site. This information is then stored in a database and processed for analysis.

[0461] Next, the server uses a generative AI model to analyze this market information in detail. The generative AI model performs demand forecasting and competitive analysis based on a large amount of aggregated data. Past sales history and market demand fluctuation information are taken into consideration to calculate the optimal trading conditions under specific circumstances. In this analysis process, for example, a prompt such as "Please suggest the optimal pricing strategy that reflects this week's trends" is input to the generative AI model, and the analysis is performed.

[0462] The transaction terms determined by the analysis are transmitted from the server to the terminal. The terminal then uses the received information to reflect the content in the company's advertising media and e-commerce platforms. In this way, when a user accesses the site through their terminal, the latest and most optimized pricing information is displayed instantly.

[0463] Users view this latest pricing information on their devices and make purchasing decisions. If a user wants to buy a specific product online, they can verify that the dynamic price calculated by the server is more attractive than competitors' and then decide to purchase the product.

[0464] Furthermore, the device tracks user purchasing behavior and responses to advertisements, and feeds the collected data back to the server. The server analyzes this feedback data and uses it in the next price analysis and optimization process. This allows the system to continuously learn and provide more accurate pricing strategies.

[0465] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0466] Step 1:

[0467] The server obtains market information from external sources. It receives access parameters to these external sources as input and collects data using APIs and web scraping. Specifically, it periodically retrieves pricing information for specific online shops and sales data from competitors. This information is stored in a structured format in a database.

[0468] Step 2:

[0469] The server formats the collected market information and prepares it for analysis. It uses raw data as input and processes it by removing unnecessary information and standardizing the format. Specifically, it organizes price and inventory level data by item and stores it in a database in a table format.

[0470] Step 3:

[0471] The server uses a generative AI model to perform data analysis. It receives formatted data as input and performs demand forecasting and competitive analysis. Specifically, it inputs prompts such as "Forecast the demand for next week and propose the optimal pricing strategy" into the generative AI model. This analysis then outputs the optimal trading conditions.

[0472] Step 4:

[0473] The server calculates the optimal price based on the analysis results. It uses demand forecasts and competitive analysis results obtained from the generating AI model as input. Specifically, it performs multiple price simulations to determine the price that maximizes profit. The calculated price information is saved for the next step.

[0474] Step 5:

[0475] The server sends the determined price information to the terminal. It receives optimized price data as input and delivers it to the terminal as output. Specifically, it creates and sends data packages to update the prices of products displayed on e-commerce platforms and advertising media.

[0476] Step 6:

[0477] The device reflects the received price information on advertising media and e-commerce platforms. It receives data sent from the server as input. Specifically, it updates the price display section of the website to show the latest transaction conditions.

[0478] Step 7:

[0479] Users check the latest price information via their device and make purchasing decisions. They receive price and product details displayed on their device as input. Specifically, users check attractive prices and add items to their online shopping cart.

[0480] Step 8:

[0481] The device collects user purchasing behavior data and feeds it back to the server. It receives user activity logs and transaction results as input and sends this information to the server. Specifically, it tracks which products sold well and which advertisements were effective.

[0482] Step 9:

[0483] The server utilizes the feedback data for subsequent analysis and optimization processes. Using the feedback data collected from the terminals as input, it adjusts the analysis model and updates the database. Based on this feedback, the system continues to learn, enabling highly accurate predictions.

[0484] (Application Example 1)

[0485] 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."

[0486] Current e-commerce platforms struggle to respond quickly to market trends and competitor pricing, making it difficult to offer products at optimal prices. This can result in missed sales opportunities and reduced profit margins. Furthermore, users only have access to static pricing information, preventing them from making the best purchasing decisions.

[0487] 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.

[0488] In this invention, the server includes means for collecting market data from external sources, means for analyzing the collected market information to forecast demand and compare it with competitors' products, means for dynamically determining the optimal price based on the analysis results and reflecting it in the e-commerce platform, and means for confirming the optimized price in real time via the user terminal. This enables companies to set optimal prices in real time in response to market fluctuations and always offer attractive prices to users.

[0489] "Market data" refers to information about the price, demand, and competitor activities of products and services in the market.

[0490] "External information sources" refer to sources of information that can be obtained from outside the company, such as the internet or publicly available databases.

[0491] "Analysis" refers to the process of evaluating demand and the competitive environment based on collected data, and deriving specific pricing strategies.

[0492] "Dynamically optimal pricing" refers to the price of a product or service that is adjusted in real time to obtain the best possible profit in response to changes in market conditions and demand.

[0493] An "e-commerce platform" refers to a digital marketplace where goods and services are bought and sold over the internet.

[0494] "User terminal" refers to devices such as smartphones, computers, and tablets that users use to obtain information and perform actions.

[0495] "Real-time verification" refers to the process of instantly obtaining and displaying the latest information without any time delay.

[0496] This invention provides a system for effectively managing market data and implementing dynamic pricing strategies. The server uses APIs and web scraping techniques to collect market data from external sources. The obtained data is stored in a database and organized and formatted in preparation for data analysis.

[0497] The server uses Python to perform data analysis and employs TensorFlow or PyTorch to generate AI models for market demand forecasting and competitive analysis. Based on this analysis, the optimal price is dynamically calculated. The calculated price information is then reflected on the e-commerce platform via a RESTful API.

[0498] Users can access this platform using their smartphones or tablets and see optimized prices displayed in real time. This user experience supports purchasing decisions by providing highly immediate pricing information.

[0499] For example, when a user opens the app and browses new sneakers, the server instantly analyzes market data, including the latest pricing information from competitors, and presents the user with the most attractive price. This allows the user to enjoy the maximum price benefit when making a purchase.

[0500] As an example of a prompt, it is possible to instruct the generative AI model to optimize the price by saying something like, "Considering the current market competition, please calculate the optimal price for this product."

[0501] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0502] Step 1:

[0503] The server retrieves market data from external sources. Using APIs and web scraping techniques, it collects data on product prices, demand information, and competitor pricing trends. This input data is stored in a database and undergoes initial formatting.

[0504] Step 2:

[0505] The server starts data analysis using Python. It extracts data collected from the database and performs demand forecasting and competitive analysis. A generative AI model is used for data calculation, and TensorFlow or PyTorch supports the execution of the model. The analysis yields outputs such as demand trends and competitive intensity under specific market conditions.

[0506] Step 3:

[0507] The server performs dynamic pricing based on the analysis results. It determines the optimal selling price based on demand and competition data calculated by the generating AI model. The output of this calculation is price information for each product, which is updated instantly.

[0508] Step 4:

[0509] The server sends the determined price information to the e-commerce platform via a RESTful API. A specific action in this step is to apply the new price data on the platform and update the display. At this point, users can access the platform to see the latest competitive prices compared to other companies.

[0510] Step 5:

[0511] Users view updated product pricing information using their smartphones or tablets. Prices displayed on the platform are updated in real time, allowing users to intuitively make optimal purchasing decisions. A dedicated application provides a user interface throughout this process, supporting responsive customer acquisition.

[0512] Step 6:

[0513] User purchasing activity and price response data are retransmitted to the server via the terminal. This feedback information is incorporated into the next pricing cycle, leading to improvements in system accuracy. In this step, user interaction information is analyzed and used as input data for further optimization.

[0514] 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.

[0515] This invention combines a sentiment engine with a dynamic pricing system based on the collection and analysis of market data, enabling more sophisticated price optimization and advertising adjustments that respond to user emotions. This system functions through the interaction of servers, terminals, and users.

[0516] First, the server collects market data in real time from external data sources. This includes information such as product prices, demand trends, and competitor activities. The server utilizes analytical models to process the collected data and uses generative AI to perform demand forecasting and competitor analysis. This allows for a comprehensive understanding of market fluctuations and the dynamic calculation of optimal prices.

[0517] The emotion engine utilizes input data from the user's device (e.g., camera footage, audio, and operation patterns) to recognize the user's emotions in real time. The server incorporates the user's emotion data recognized by the emotion engine into its analysis process, thereby optimizing pricing according to the user's emotional state. Considering the impact of emotions on the user's purchasing intent, adjustments are made, such as offering a more attractive price when the user indicates purchasing intent.

[0518] The device dynamically updates advertising media and product pages using optimized pricing and ad content obtained from the server. When users view ads, ads tailored to their emotional state are displayed, resulting in a more personalized purchasing experience. For example, if a user expresses anxiety about making a purchase, ads highlighting limited discounts or guarantees will be displayed.

[0519] As a concrete example, consider an online bookstore. Suppose a user searches for a book and the camera footage detects an emotion of excitement. The emotion engine sends this information to the server, which analyzes this emotion information along with market data to determine a special price that is slightly lower than that of competing bookstores. The terminal updates its advertisements based on this information and displays them to the user at a special price. As a result, the user is more likely to purchase the book, which has the effect of increasing the bookstore's sales.

[0520] This system enhances a company's market competitiveness and improves the customer experience by performing sophisticated market analysis and pricing that takes user emotions into account.

[0521] The following describes the processing flow.

[0522] Step 1:

[0523] The server collects market data from external data sources. Using APIs and web scraping techniques, the server gathers product prices, consumer trends, and competitor pricing information in real time and stores it in a database.

[0524] Step 2:

[0525] The server cleanses the collected data and formats it into an analyzable format. By imputing missing data and standardizing the format, it improves the accuracy and consistency of the data.

[0526] Step 3:

[0527] The server uses a generative AI model to analyze data. Specifically, it performs market demand forecasting and competitive price analysis, and then uses the insights gained to perform basic price optimization.

[0528] Step 4:

[0529] The device acquires user emotion data. The device analyzes the user's facial expressions and voice through its built-in camera and microphone, and the emotion engine analyzes this in real time to recognize emotions such as excitement, joy, and anxiety.

[0530] Step 5:

[0531] The emotion engine sends its output to the server. The server uses the user's emotion data, combined with the analysis results, to perform dynamic price adjustments. Specifically, it changes the price based on a particular emotional state. For example, if the user is very excited, the price of the product is set a little higher, while if the user shows anxiety, a discount is applied.

[0532] Step 6:

[0533] The server sends optimized pricing and ad content to the device. The device then uses this information to update the information on online stores and advertising platforms, and reflects it in the user's view.

[0534] Step 7:

[0535] Users view the latest prices and advertisements through their devices. Presenting dynamically tailored information based on the user's emotions increases the likelihood of stimulating purchasing intent and encouraging purchases.

[0536] Step 8:

[0537] The device records the user's browsing history and new sentiment data, and feeds this information back to the server. The server uses this feedback to learn and further improve the accuracy of future pricing and ad adjustments.

[0538] (Example 2)

[0539] 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."

[0540] It is necessary to set appropriate prices and maximize sales by simultaneously considering market trends and user sentiment. However, conventional systems have found it difficult to integrate market data analysis and user sentiment, making it impossible to reliably achieve optimal pricing.

[0541] 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.

[0542] In this invention, the server includes means for collecting market information from external sources, means for analyzing the collected market information to perform demand forecasting and competitor analysis, and means for sensing the emotional state of the user. This makes it possible to dynamically determine the optimal price based on the analysis results and the emotional state.

[0543] "Market information" refers to data about the current state of the market collected from external sources, such as product prices, demand trends, and competitor activities.

[0544] "External information sources" refer to information providers outside the system, such as data providers and web APIs used to provide market information.

[0545] "Demand forecasting" refers to the process of predicting future consumer demand trends based on past and present market information.

[0546] "Competitor analysis" refers to the analysis conducted to investigate the activities and strategies of competitors in the market and to obtain information necessary to maintain a competitive advantage.

[0547] "User emotional state" refers to the emotional state perceived from a user's behavior, facial expressions, voice, etc., and includes factors that influence purchasing intent.

[0548] "Pricing" refers to the process of determining an appropriate selling price for a product or service, taking into account market information and the emotional state of users.

[0549] "Display medium" refers to a medium, such as a terminal or digital display, used to display price information and advertising content to users.

[0550] "Information terminal" refers to electronic devices such as computers and mobile devices that users use to receive information about products and services.

[0551] This invention relates to a dynamic pricing system in which a server, terminal, and user work together to collect and analyze market information and sentiment data, thereby optimizing the user experience.

[0552] Server role:

[0553] The server collects market information in real time from external sources via APIs. This includes data on product pricing, demand trends, and competitor activity. The collected market information is stored in a database and analyzed using a generative AI model. The generative AI model performs demand forecasting and competitor analysis, and takes into account user sentiment to determine optimal pricing.

[0554] Terminal role:

[0555] The device uses a camera and microphone to sense the user's emotional state. This allows the user's facial expressions and voice tone to be collected in real time and analyzed by an emotion engine. As a result, the user's emotional data is sent to a server and used to determine pricing. Based on the optimized pricing information received from the server, the device updates its display media and provides the user with personalized advertisements and pricing information.

[0556] User roles:

[0557] Users interact with the device when selecting products and services, and their emotional state is sensed by the system. This allows for attractive pricing that takes the user's purchasing intent into consideration.

[0558] As a concrete example, consider a case where an online bookstore has implemented this system. When a user views a particular book, if the device's camera detects excitement from the user's facial expression, the emotion engine analyzes this information and sends it to the server. The server analyzes this emotion data along with market information to determine a special price that is slightly lower than that of competing bookstores. The device uses this price to update its advertisements and offer them to the user, increasing the likelihood that the user will purchase the book.

[0559] An example of a prompt would be: "Design an algorithm that performs dynamic pricing based on user emotions. In this case, explain how to obtain user emotion information (excitement, anxiety, etc.) in real time from an emotion engine, analyze market data and emotion data using a generative AI model, and calculate the optimal price."

[0560] This system enhances a company's competitiveness while improving the user's purchasing experience by comprehensively analyzing market and user sentiment and enabling dynamic pricing.

[0561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0562] Step 1:

[0563] The server collects market information from external sources. It retrieves data such as product prices, demand trends, and competitor activity via APIs. Input is raw data from the API, and output is formalized data stored in a database. Specifically, the server completes the API authentication process, sends information retrieval requests, and structures and stores the obtained data.

[0564] Step 2:

[0565] The device uses a camera and microphone to sense the user's emotional state. The input is real-time audio and video data from the user, and the output is emotion analysis data from the emotion engine. Specifically, the device activates sensors, the collected data is analyzed by a machine learning algorithm within the emotion engine, and the user's emotional state is determined.

[0566] Step 3:

[0567] The server uses a generative AI model to analyze collected market information and user sentiment data. The input is market information and real-time sentiment data pulled from a database, and the output is optimized price information. Specifically, the server provides these inputs to the generative AI model and runs a predictive algorithm to determine a price that takes into account supply and demand conditions and sentiment feedback.

[0568] Step 4:

[0569] The terminal uses optimized pricing information received from the server to update the display media. The input is optimized pricing information from the server, and the output is the updated product page or advertisement display. Specifically, the terminal stores the pricing information in temporary memory and updates the user screen in real time using a display template.

[0570] Step 5:

[0571] Users view updated product information, which influences their purchasing decisions. Input is the information displayed on the device, and output is the user's action—purchase or continued consideration. Specifically, users refer to displayed special offers and personalized advertisements, and make decisions by proceeding with or canceling the purchase process. The user's emotional state is also continuously monitored on the device, and advertising is further adjusted as needed.

[0572] (Application Example 2)

[0573] 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."

[0574] Traditional dynamic pricing systems optimized prices based on market data, but they did not take into account user emotions or emotional factors. Therefore, they were unable to respond quickly to fluctuations in user purchasing intent, resulting in pricing that could not be considered optimized. The challenge now is to achieve price and advertising optimization that takes user emotions into account.

[0575] 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.

[0576] In this invention, the server includes means for collecting market data from an external data source, means for analyzing the collected market data to perform demand forecasting and competitive analysis, and means for analyzing sentiment information obtained from the user's terminal and reflecting it in pricing. This enables more precise pricing and advertising adjustments based on the user's emotional state.

[0577] "Market data" refers to information collected from external data sources and used for analysis, such as product prices, demand trends, and competitor activities.

[0578] "Methods for dynamically determining the optimal price" refer to the process of optimizing product prices in real time based on the results of market data analysis.

[0579] "Emotional information obtained from the user's device" refers to data that indicates the user's current emotional state, obtained through methods such as facial recognition and voice analysis.

[0580] "Advertising media" refers to means or platforms used to present information to users, such as product pages on the internet or online advertisements.

[0581] "Analysis" is the process of using collected data to forecast demand, analyze competitors, and analyze user sentiment, thereby guiding decisions regarding pricing and advertising.

[0582] The system for realizing this invention consists of a server, a terminal, and a user terminal.

[0583] The server first collects market data from external data sources. This includes product pricing information, demand trends, and competitor activities. The collected market data is then used with a generative AI model to forecast demand and perform competitive analysis, dynamically optimizing pricing.

[0584] Furthermore, the user's device acquires emotional information using sensors such as cameras and microphones. For example, facial recognition and voice analysis technologies are used to analyze the user's emotional state in real time. This emotional information is sent to a server and incorporated into pricing and advertising adjustments.

[0585] The device receives optimized pricing and sentiment-based ad content from the server, reflecting it on the advertising platform and presenting it to the user. This makes it possible to provide a personalized purchasing experience that aligns with the user's emotions.

[0586] As a concrete example, consider a scenario where a user is browsing an e-commerce site on their smartphone and the device detects the user's excited state. Based on this information, the server immediately sets a special discounted price and sends it to the device. The user's device then instantly displays an advertisement for the special price based on this information. As a result, the likelihood of the user purchasing the product increases, leading to increased sales opportunities.

[0587] An example of a prompt message might be: "Design a smartphone app that recognizes user emotions in real time and displays corresponding prices and advertisements. Optimize the user experience using Python and OpenCV."

[0588] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0589] Step 1:

[0590] The server collects market data from external data sources. Inputs include product pricing information, demand trends, and competitor activity data. By collecting and organizing this data, it prepares the foundational data necessary for subsequent analysis.

[0591] Step 2:

[0592] The server analyzes the collected market data using a generating AI model. The input is the market data collected in step 1. Through the analysis, it obtains demand forecasts and competitive analysis results, and based on these, it performs calculations to derive the optimal pricing strategy.

[0593] Step 3:

[0594] The user's device acquires emotional information using sensors such as cameras and microphones. The input consists of real-time image and audio data. This data is processed by an emotion analysis engine to detect the user's emotional state in real time.

[0595] Step 4:

[0596] The device sends the sentiment information acquired in step 3 to the server. The input is the sentiment analysis result, and by transmitting this to the server, the server uses the sentiment information for pricing and ad adjustments.

[0597] Step 5:

[0598] The server dynamically adjusts pricing and ad content, taking sentiment information into account. Inputs include previously analyzed market data and user sentiment information. Based on this data, it calculates attractive pricing and ad content, generating optimized pricing and ad content as output.

[0599] Step 6:

[0600] The server sends optimized pricing and ad content to the device. The input is the pricing and ad data calculated in step 5. The output is dynamically adjusted information that is reflected on the user's device, providing data for display to the user.

[0601] Step 7:

[0602] The terminal receives price and advertisement content from the server and displays it on the advertising medium for the user. The input is optimized information from the server. Based on this, it displays price information and advertisements tailored to the user in real time, stimulating purchasing intent and achieving effective sales activities.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] [Fourth Embodiment]

[0607] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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).

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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".

[0620] The system of this invention enables the realization of dynamic pricing strategies in the market. This system effectively exchanges information between servers, terminals, and users to achieve price optimization.

[0621] First, the server retrieves market data from external data sources. This data is collected using APIs and web scraping techniques and includes product prices, demand information, and information about competitor activities. The collected data is first stored in a database and then organized and formatted.

[0622] Next, the server uses a generative AI model to analyze the collected market data. This analysis includes demand forecasting and competitive analysis. Based on these analysis results, the server determines the optimal price. This generative AI takes into account past sales history and market demand fluctuations to calculate the price with the highest profit margin under specific conditions.

[0623] Next, the server sends this optimized pricing information to the terminal. The terminal uses the received pricing information to reflect it on the advertising media and e-commerce platforms managed by the company. As a result, when users access these platforms, they are presented with the latest and most optimized prices for each product.

[0624] Users view updated pricing information via their devices and decide whether to purchase. For example, when a user tries to buy clothes online, the server displays dynamic pricing based on real-time data analysis, allowing them to see prices that are more attractive than those of competitors. As a result, users determine that the price is appropriate and decide to purchase, thereby increasing the company's revenue.

[0625] Furthermore, user purchasing behavior and advertising response data are fed back from the terminal to the server. This feedback data is used in the next price optimization process. This allows the system to continuously learn and provide more efficient pricing strategies.

[0626] Thus, the system of the present invention helps companies respond to market fluctuations efficiently and effectively through a cycle of acquiring and analyzing market data, setting optimized prices, incorporating advertising, and generating user feedback.

[0627] The following describes the processing flow.

[0628] Step 1:

[0629] The server acquires market data from external data sources. Using API integration and web scraping techniques, the server collects product prices, demand trends, and competitor activity information in real time.

[0630] Step 2:

[0631] The server stores the acquired market data in a database and performs data preprocessing. The server cleans the data, imputing missing values, correcting outliers, and standardizing the format to prepare it for analysis.

[0632] Step 3:

[0633] The server analyzes market data using a generative AI model. The server applies a demand forecasting model to predict future demand and analyzes competitors' pricing trends and market share.

[0634] Step 4:

[0635] The server dynamically determines the optimal price based on the analysis results. Using a price optimization algorithm, the server selects the appropriate price from multiple simulation patterns, aiming to maximize profits and expand sales.

[0636] Step 5:

[0637] The server sends optimized pricing information to the terminal. The server distributes the new pricing data through the company's advertising platform management system.

[0638] Step 6:

[0639] The device automatically updates prices on advertising media and e-commerce sites based on the received new price information. The device reflects the latest prices in real time and prepares to present them to the user.

[0640] Step 7:

[0641] Users view advertisements and product pages displaying the latest prices through their devices. Seeing more attractive prices than competitors prompts them to consider purchasing.

[0642] Step 8:

[0643] The device records the user's browsing history and purchase activity and provides this feedback to the server. The server uses this feedback data to improve future price optimization processes and further refine its approach.

[0644] (Example 1)

[0645] 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".

[0646] Pricing strategies in the market are highly competitive, and companies need to set prices that can quickly respond to dynamic market conditions. However, traditional methods often fail to adequately consider past sales history and fluctuations in market demand, making it difficult to set optimal prices. Furthermore, providing consumers with real-time pricing information is challenging, sometimes resulting in missed market opportunities.

[0647] 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.

[0648] In this invention, the server includes means for acquiring market information from external sources, means for analyzing the acquired market information to perform demand forecasting and competitive analysis, and means for performing data analysis using a generative AI model, taking into account past transaction history and market demand fluctuations. This enables companies to calculate optimal transaction conditions in real time and provide them quickly to consumers.

[0649] "Market information" refers to data about market trends and conditions, and is a general term for information including product prices, demand information, and the activities of competitors.

[0650] "External information sources" refer to data sources that are not located within a company and are provided objectively or by third parties, such as online platforms and research databases.

[0651] A "generative AI model" is an artificial intelligence system that uses algorithms to perform pattern recognition and prediction based on large amounts of data, and is a model that performs the analytical processing necessary for optimizing pricing strategies.

[0652] "Consumer terminals" refer to devices such as computers, smartphones, and tablets used by consumers, through which price information and transaction terms provided by companies are displayed.

[0653] "Feedback" refers to data manipulation that involves collecting consumer behavior data and advertising response data, and using that data to improve the overall performance of the system.

[0654] This invention provides a system that enables dynamic pricing strategies in the market through the cooperation of a server, a terminal, and a user.

[0655] The server first obtains market information from external sources. This includes data collection using APIs and web scraping techniques. For example, it collects data on product prices, demand trends, and competitor activities from a specific online store or market research site. This information is then stored in a database and processed for analysis.

[0656] Next, the server uses a generative AI model to analyze this market information in detail. The generative AI model performs demand forecasting and competitive analysis based on a large amount of aggregated data. Past sales history and market demand fluctuation information are taken into consideration to calculate the optimal trading conditions under specific circumstances. In this analysis process, for example, a prompt such as "Please suggest the optimal pricing strategy that reflects this week's trends" is input to the generative AI model, and the analysis is performed.

[0657] The transaction terms determined by the analysis are transmitted from the server to the terminal. The terminal then uses the received information to reflect the content in the company's advertising media and e-commerce platforms. In this way, when a user accesses the site through their terminal, the latest and most optimized pricing information is displayed instantly.

[0658] Users view this latest pricing information on their devices and make purchasing decisions. If a user wants to buy a specific product online, they can verify that the dynamic price calculated by the server is more attractive than competitors' and then decide to purchase the product.

[0659] Furthermore, the device tracks user purchasing behavior and responses to advertisements, and feeds the collected data back to the server. The server analyzes this feedback data and uses it in the next price analysis and optimization process. This allows the system to continuously learn and provide more accurate pricing strategies.

[0660] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0661] Step 1:

[0662] The server obtains market information from external sources. It receives access parameters to these external sources as input and collects data using APIs and web scraping. Specifically, it periodically retrieves pricing information for specific online shops and sales data from competitors. This information is stored in a structured format in a database.

[0663] Step 2:

[0664] The server formats the collected market information and prepares it for analysis. It uses raw data as input and processes it by removing unnecessary information and standardizing the format. Specifically, it organizes price and inventory level data by item and stores it in a database in a table format.

[0665] Step 3:

[0666] The server uses a generative AI model to perform data analysis. It receives formatted data as input and performs demand forecasting and competitive analysis. Specifically, it inputs prompts such as "Forecast the demand for next week and propose the optimal pricing strategy" into the generative AI model. This analysis then outputs the optimal trading conditions.

[0667] Step 4:

[0668] The server calculates the optimal price based on the analysis results. It uses demand forecasts and competitive analysis results obtained from the generating AI model as input. Specifically, it performs multiple price simulations to determine the price that maximizes profit. The calculated price information is saved for the next step.

[0669] Step 5:

[0670] The server sends the determined price information to the terminal. It receives optimized price data as input and delivers it to the terminal as output. Specifically, it creates and sends data packages to update the prices of products displayed on e-commerce platforms and advertising media.

[0671] Step 6:

[0672] The device reflects the received price information on advertising media and e-commerce platforms. It receives data sent from the server as input. Specifically, it updates the price display section of the website to show the latest transaction conditions.

[0673] Step 7:

[0674] Users check the latest price information via their device and make purchasing decisions. They receive price and product details displayed on their device as input. Specifically, users check attractive prices and add items to their online shopping cart.

[0675] Step 8:

[0676] The device collects user purchasing behavior data and feeds it back to the server. It receives user activity logs and transaction results as input and sends this information to the server. Specifically, it tracks which products sold well and which advertisements were effective.

[0677] Step 9:

[0678] The server utilizes the feedback data for subsequent analysis and optimization processes. Using the feedback data collected from the terminals as input, it adjusts the analysis model and updates the database. Based on this feedback, the system continues to learn, enabling highly accurate predictions.

[0679] (Application Example 1)

[0680] 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".

[0681] Current e-commerce platforms struggle to respond quickly to market trends and competitor pricing, making it difficult to offer products at optimal prices. This can result in missed sales opportunities and reduced profit margins. Furthermore, users only have access to static pricing information, preventing them from making the best purchasing decisions.

[0682] 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.

[0683] In this invention, the server includes means for collecting market data from external sources, means for analyzing the collected market information to forecast demand and compare it with competitors' products, means for dynamically determining the optimal price based on the analysis results and reflecting it in the e-commerce platform, and means for confirming the optimized price in real time via the user terminal. This enables companies to set optimal prices in real time in response to market fluctuations and always offer attractive prices to users.

[0684] "Market data" refers to information about the price, demand, and competitor activities of products and services in the market.

[0685] "External information sources" refer to sources of information that can be obtained from outside the company, such as the internet or publicly available databases.

[0686] "Analysis" refers to the process of evaluating demand and the competitive environment based on collected data, and deriving specific pricing strategies.

[0687] "Dynamically optimal pricing" refers to the price of a product or service that is adjusted in real time to obtain the best possible profit in response to changes in market conditions and demand.

[0688] An "e-commerce platform" refers to a digital marketplace where goods and services are bought and sold over the internet.

[0689] "User terminal" refers to devices such as smartphones, computers, and tablets that users use to obtain information and perform actions.

[0690] "Real-time verification" refers to the process of instantly obtaining and displaying the latest information without any time delay.

[0691] This invention provides a system for effectively managing market data and implementing dynamic pricing strategies. The server uses APIs and web scraping techniques to collect market data from external sources. The obtained data is stored in a database and organized and formatted in preparation for data analysis.

[0692] The server uses Python to perform data analysis and employs TensorFlow or PyTorch to generate AI models for market demand forecasting and competitive analysis. Based on this analysis, the optimal price is dynamically calculated. The calculated price information is then reflected on the e-commerce platform via a RESTful API.

[0693] Users can access this platform using their smartphones or tablets and see optimized prices displayed in real time. This user experience supports purchasing decisions by providing highly immediate pricing information.

[0694] For example, when a user opens the app and browses new sneakers, the server instantly analyzes market data, including the latest pricing information from competitors, and presents the user with the most attractive price. This allows the user to enjoy the maximum price benefit when making a purchase.

[0695] As an example of a prompt, it is possible to instruct the generative AI model to optimize the price by saying something like, "Considering the current market competition, please calculate the optimal price for this product."

[0696] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0697] Step 1:

[0698] The server retrieves market data from external sources. Using APIs and web scraping techniques, it collects data on product prices, demand information, and competitor pricing trends. This input data is stored in a database and undergoes initial formatting.

[0699] Step 2:

[0700] The server starts data analysis using Python. It extracts data collected from the database and performs demand forecasting and competitive analysis. A generative AI model is used for data calculation, and TensorFlow or PyTorch supports the execution of the model. The analysis yields outputs such as demand trends and competitive intensity under specific market conditions.

[0701] Step 3:

[0702] The server performs dynamic pricing based on the analysis results. It determines the optimal selling price based on demand and competition data calculated by the generating AI model. The output of this calculation is price information for each product, which is updated instantly.

[0703] Step 4:

[0704] The server sends the determined price information to the e-commerce platform via a RESTful API. A specific action in this step is to apply the new price data on the platform and update the display. At this point, users can access the platform to see the latest competitive prices compared to other companies.

[0705] Step 5:

[0706] Users view updated product pricing information using their smartphones or tablets. Prices displayed on the platform are updated in real time, allowing users to intuitively make optimal purchasing decisions. A dedicated application provides a user interface throughout this process, supporting responsive customer acquisition.

[0707] Step 6:

[0708] User purchasing activity and price response data are retransmitted to the server via the terminal. This feedback information is incorporated into the next pricing cycle, leading to improvements in system accuracy. In this step, user interaction information is analyzed and used as input data for further optimization.

[0709] 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.

[0710] This invention combines a sentiment engine with a dynamic pricing system based on the collection and analysis of market data, enabling more sophisticated price optimization and advertising adjustments that respond to user emotions. This system functions through the interaction of servers, terminals, and users.

[0711] First, the server collects market data in real time from external data sources. This includes information such as product prices, demand trends, and competitor activities. The server utilizes analytical models to process the collected data and uses generative AI to perform demand forecasting and competitor analysis. This allows for a comprehensive understanding of market fluctuations and the dynamic calculation of optimal prices.

[0712] The emotion engine utilizes input data from the user's device (e.g., camera footage, audio, and operation patterns) to recognize the user's emotions in real time. The server incorporates the user's emotion data recognized by the emotion engine into its analysis process, thereby optimizing pricing according to the user's emotional state. Considering the impact of emotions on the user's purchasing intent, adjustments are made, such as offering a more attractive price when the user indicates purchasing intent.

[0713] The device dynamically updates advertising media and product pages using optimized pricing and ad content obtained from the server. When users view ads, ads tailored to their emotional state are displayed, resulting in a more personalized purchasing experience. For example, if a user expresses anxiety about making a purchase, ads highlighting limited discounts or guarantees will be displayed.

[0714] As a concrete example, consider an online bookstore. Suppose a user searches for a book and the camera footage detects an emotion of excitement. The emotion engine sends this information to the server, which analyzes this emotion information along with market data to determine a special price that is slightly lower than that of competing bookstores. The terminal updates its advertisements based on this information and displays them to the user at a special price. As a result, the user is more likely to purchase the book, which has the effect of increasing the bookstore's sales.

[0715] This system enhances a company's market competitiveness and improves the customer experience by performing sophisticated market analysis and pricing that takes user emotions into account.

[0716] The following describes the processing flow.

[0717] Step 1:

[0718] The server collects market data from external data sources. Using APIs and web scraping techniques, the server gathers product prices, consumer trends, and competitor pricing information in real time and stores it in a database.

[0719] Step 2:

[0720] The server cleanses the collected data and formats it into an analyzable format. By imputing missing data and standardizing the format, it improves the accuracy and consistency of the data.

[0721] Step 3:

[0722] The server uses a generative AI model to analyze data. Specifically, it performs market demand forecasting and competitive price analysis, and then uses the insights gained to perform basic price optimization.

[0723] Step 4:

[0724] The device acquires user emotion data. The device analyzes the user's facial expressions and voice through its built-in camera and microphone, and the emotion engine analyzes this in real time to recognize emotions such as excitement, joy, and anxiety.

[0725] Step 5:

[0726] The emotion engine sends its output to the server. The server uses the user's emotion data, combined with the analysis results, to perform dynamic price adjustments. Specifically, it changes the price based on a particular emotional state. For example, if the user is very excited, the price of the product is set a little higher, while if the user shows anxiety, a discount is applied.

[0727] Step 6:

[0728] The server sends optimized pricing and ad content to the device. The device then uses this information to update the information on online stores and advertising platforms, and reflects it in the user's view.

[0729] Step 7:

[0730] Users view the latest prices and advertisements through their devices. Presenting dynamically tailored information based on the user's emotions increases the likelihood of stimulating purchasing intent and encouraging purchases.

[0731] Step 8:

[0732] The device records the user's browsing history and new sentiment data, and feeds this information back to the server. The server uses this feedback to learn and further improve the accuracy of future pricing and ad adjustments.

[0733] (Example 2)

[0734] 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".

[0735] It is necessary to set appropriate prices and maximize sales by simultaneously considering market trends and user sentiment. However, conventional systems have found it difficult to integrate market data analysis and user sentiment, making it impossible to reliably achieve optimal pricing.

[0736] 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.

[0737] In this invention, the server includes means for collecting market information from external sources, means for analyzing the collected market information to perform demand forecasting and competitor analysis, and means for sensing the emotional state of the user. This makes it possible to dynamically determine the optimal price based on the analysis results and the emotional state.

[0738] "Market information" refers to data about the current state of the market collected from external sources, such as product prices, demand trends, and competitor activities.

[0739] "External information sources" refer to information providers outside the system, such as data providers and web APIs used to provide market information.

[0740] "Demand forecasting" refers to the process of predicting future consumer demand trends based on past and present market information.

[0741] "Competitor analysis" refers to the analysis conducted to investigate the activities and strategies of competitors in the market and to obtain information necessary to maintain a competitive advantage.

[0742] "User emotional state" refers to the emotional state perceived from a user's behavior, facial expressions, voice, etc., and includes factors that influence purchasing intent.

[0743] "Pricing" refers to the process of determining an appropriate selling price for a product or service, taking into account market information and the emotional state of users.

[0744] "Display medium" refers to a medium, such as a terminal or digital display, used to display price information and advertising content to users.

[0745] "Information terminal" refers to electronic devices such as computers and mobile devices that users use to receive information about products and services.

[0746] This invention relates to a dynamic pricing system in which a server, terminal, and user work together to collect and analyze market information and sentiment data, thereby optimizing the user experience.

[0747] Server role:

[0748] The server collects market information in real time from external sources via APIs. This includes data on product pricing, demand trends, and competitor activity. The collected market information is stored in a database and analyzed using a generative AI model. The generative AI model performs demand forecasting and competitor analysis, and takes into account user sentiment to determine optimal pricing.

[0749] Terminal role:

[0750] The device uses a camera and microphone to sense the user's emotional state. This allows the user's facial expressions and voice tone to be collected in real time and analyzed by an emotion engine. As a result, the user's emotional data is sent to a server and used to determine pricing. Based on the optimized pricing information received from the server, the device updates its display media and provides the user with personalized advertisements and pricing information.

[0751] User roles:

[0752] Users interact with the device when selecting products and services, and their emotional state is sensed by the system. This allows for attractive pricing that takes the user's purchasing intent into consideration.

[0753] As a concrete example, consider a case where an online bookstore has implemented this system. When a user views a particular book, if the device's camera detects excitement from the user's facial expression, the emotion engine analyzes this information and sends it to the server. The server analyzes this emotion data along with market information to determine a special price that is slightly lower than that of competing bookstores. The device uses this price to update its advertisements and offer them to the user, increasing the likelihood that the user will purchase the book.

[0754] An example of a prompt would be: "Design an algorithm that performs dynamic pricing based on user emotions. In this case, explain how to obtain user emotion information (excitement, anxiety, etc.) in real time from an emotion engine, analyze market data and emotion data using a generative AI model, and calculate the optimal price."

[0755] This system enhances a company's competitiveness while improving the user's purchasing experience by comprehensively analyzing market and user sentiment and enabling dynamic pricing.

[0756] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0757] Step 1:

[0758] The server collects market information from external sources. It retrieves data such as product prices, demand trends, and competitor activity via APIs. Input is raw data from the API, and output is formalized data stored in a database. Specifically, the server completes the API authentication process, sends information retrieval requests, and structures and stores the obtained data.

[0759] Step 2:

[0760] The device uses a camera and microphone to sense the user's emotional state. The input is real-time audio and video data from the user, and the output is emotion analysis data from the emotion engine. Specifically, the device activates sensors, the collected data is analyzed by a machine learning algorithm within the emotion engine, and the user's emotional state is determined.

[0761] Step 3:

[0762] The server uses a generative AI model to analyze collected market information and user sentiment data. The input is market information and real-time sentiment data pulled from a database, and the output is optimized price information. Specifically, the server provides these inputs to the generative AI model and runs a predictive algorithm to determine a price that takes into account supply and demand conditions and sentiment feedback.

[0763] Step 4:

[0764] The terminal uses optimized pricing information received from the server to update the display media. The input is optimized pricing information from the server, and the output is the updated product page or advertisement display. Specifically, the terminal stores the pricing information in temporary memory and updates the user screen in real time using a display template.

[0765] Step 5:

[0766] Users view updated product information, which influences their purchasing decisions. Input is the information displayed on the device, and output is the user's action—purchase or continued consideration. Specifically, users refer to displayed special offers and personalized advertisements, and make decisions by proceeding with or canceling the purchase process. The user's emotional state is also continuously monitored on the device, and advertising is further adjusted as needed.

[0767] (Application Example 2)

[0768] 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".

[0769] Traditional dynamic pricing systems optimized prices based on market data, but they did not take into account user emotions or emotional factors. Therefore, they were unable to respond quickly to fluctuations in user purchasing intent, resulting in pricing that could not be considered optimized. The challenge now is to achieve price and advertising optimization that takes user emotions into account.

[0770] 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.

[0771] In this invention, the server includes means for collecting market data from an external data source, means for analyzing the collected market data to perform demand forecasting and competitive analysis, and means for analyzing sentiment information obtained from the user's terminal and reflecting it in pricing. This enables more precise pricing and advertising adjustments based on the user's emotional state.

[0772] "Market data" refers to information collected from external data sources and used for analysis, such as product prices, demand trends, and competitor activities.

[0773] "Methods for dynamically determining the optimal price" refer to the process of optimizing product prices in real time based on the results of market data analysis.

[0774] "Emotional information obtained from the user's device" refers to data that indicates the user's current emotional state, obtained through methods such as facial recognition and voice analysis.

[0775] "Advertising media" refers to means or platforms used to present information to users, such as product pages on the internet or online advertisements.

[0776] "Analysis" is the process of using collected data to forecast demand, analyze competitors, and analyze user sentiment, thereby guiding decisions regarding pricing and advertising.

[0777] The system for realizing this invention consists of a server, a terminal, and a user terminal.

[0778] The server first collects market data from external data sources. This includes product pricing information, demand trends, and competitor activities. The collected market data is then used with a generative AI model to forecast demand and perform competitive analysis, dynamically optimizing pricing.

[0779] Furthermore, the user's device acquires emotional information using sensors such as cameras and microphones. For example, facial recognition and voice analysis technologies are used to analyze the user's emotional state in real time. This emotional information is sent to a server and incorporated into pricing and advertising adjustments.

[0780] The device receives optimized pricing and sentiment-based ad content from the server, reflecting it on the advertising platform and presenting it to the user. This makes it possible to provide a personalized purchasing experience that aligns with the user's emotions.

[0781] As a concrete example, consider a scenario where a user is browsing an e-commerce site on their smartphone and the device detects the user's excited state. Based on this information, the server immediately sets a special discounted price and sends it to the device. The user's device then instantly displays an advertisement for the special price based on this information. As a result, the likelihood of the user purchasing the product increases, leading to increased sales opportunities.

[0782] An example of a prompt message might be: "Design a smartphone app that recognizes user emotions in real time and displays corresponding prices and advertisements. Optimize the user experience using Python and OpenCV."

[0783] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0784] Step 1:

[0785] The server collects market data from external data sources. Inputs include product pricing information, demand trends, and competitor activity data. By collecting and organizing this data, it prepares the foundational data necessary for subsequent analysis.

[0786] Step 2:

[0787] The server analyzes the collected market data using a generating AI model. The input is the market data collected in step 1. Through the analysis, it obtains demand forecasts and competitive analysis results, and based on these, it performs calculations to derive the optimal pricing strategy.

[0788] Step 3:

[0789] The user's device acquires emotional information using sensors such as cameras and microphones. The input consists of real-time image and audio data. This data is processed by an emotion analysis engine to detect the user's emotional state in real time.

[0790] Step 4:

[0791] The device sends the sentiment information acquired in step 3 to the server. The input is the sentiment analysis result, and by transmitting this to the server, the server uses the sentiment information for pricing and ad adjustments.

[0792] Step 5:

[0793] The server dynamically adjusts pricing and ad content, taking sentiment information into account. Inputs include previously analyzed market data and user sentiment information. Based on this data, it calculates attractive pricing and ad content, generating optimized pricing and ad content as output.

[0794] Step 6:

[0795] The server sends optimized pricing and ad content to the device. The input is the pricing and ad data calculated in step 5. The output is dynamically adjusted information that is reflected on the user's device, providing data for display to the user.

[0796] Step 7:

[0797] The terminal receives price and advertisement content from the server and displays it on the advertising medium for the user. The input is optimized information from the server. Based on this, it displays price information and advertisements tailored to the user in real time, stimulating purchasing intent and achieving effective sales activities.

[0798] 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.

[0799] 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.

[0800] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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."

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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 as being incorporated by reference.

[0819] The following is further disclosed regarding the embodiments described above.

[0820] (Claim 1)

[0821] Means for collecting market data from external data sources,

[0822] A means for analyzing collected market data to perform demand forecasting and competitive analysis,

[0823] A means for dynamically determining the optimal price based on the analysis results,

[0824] A means of reflecting the determined price in the advertising medium,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, which optimizes prices by taking into account the company's sales history and market demand fluctuations along with the analysis results.

[0828] (Claim 3)

[0829] The system according to claim 1, which updates the price in an advertising medium in real time and displays it on the user's terminal.

[0830] "Example 1"

[0831] (Claim 1)

[0832] A device for obtaining market information from external sources,

[0833] A device for analyzing acquired market information to perform demand forecasting and competitive analysis,

[0834] A device that dynamically calculates optimal trading conditions based on analysis results,

[0835] A device for reflecting the calculated transaction conditions in advertising media,

[0836] A device that uses a generative AI model to perform data analysis and takes into account past transaction history and market demand fluctuations,

[0837] A device that connects to consumer terminals and provides price information in real time,

[0838] A device that collects consumer behavior data as feedback,

[0839] A device that utilizes feedback data for the next analysis process,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, comprising a device that optimizes trading conditions by using an AI model generated based on analysis results, taking into account past trading history and market demand fluctuations.

[0843] (Claim 3)

[0844] The system according to claim 1, comprising a device that updates the terms and conditions of a transaction in an advertising medium in real time and displays them on a consumer terminal.

[0845] "Application Example 1"

[0846] (Claim 1)

[0847] Means for collecting market data from external sources,

[0848] A means of analyzing collected market information to forecast demand and compare it with other companies' products,

[0849] A means to dynamically determine the optimal price based on the analysis results and reflect it in the e-commerce platform,

[0850] A means of checking optimized prices in real time via the user's terminal,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, which optimizes prices by considering the company's sales history and fluctuations in market demand along with the analysis results, and always presents the latest price information when the user accesses it.

[0854] (Claim 3)

[0855] The system according to claim 1, which updates prices in real time on an e-commerce platform and improves the customer experience displayed on the user's terminal.

[0856] "Example 2 of combining an emotion engine"

[0857] (Claim 1)

[0858] Means for collecting market information from external sources,

[0859] A means for analyzing collected market information and conducting demand forecasting and competitor analysis,

[0860] Means for sensing the user's emotional state,

[0861] A means of dynamically determining the optimal price based on analysis results and emotional state,

[0862] A means of reflecting the determined price and related information on the display medium,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, which performs price optimization based on analysis results and emotional state.

[0866] (Claim 3)

[0867] The system according to claim 1, which updates the price on a display medium in real time and displays it on an information terminal.

[0868] "Application example 2 of combining emotional engines"

[0869] (Claim 1)

[0870] Means for collecting market data from external data sources,

[0871] A means for analyzing collected market data to perform demand forecasting and competitive analysis,

[0872] A means for dynamically determining the optimal price based on the analysis results,

[0873] A means of analyzing emotional information obtained from the user's device and reflecting it in pricing,

[0874] A means of reflecting the determined price and advertising content in the advertising medium,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, which optimizes prices by considering the company's sales history and market demand fluctuations along with the analysis results, and further adjusts the advertising content by considering the user's emotions.

[0878] (Claim 3)

[0879] The system according to claim 1, which updates the price and content of an advertisement in an advertising medium in real time and displays them on the user's terminal. [Explanation of Symbols]

[0880] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting market data from external data sources, A means for analyzing collected market data to perform demand forecasting and competitive analysis, A means for dynamically determining the optimal price based on the analysis results, A means of reflecting the determined price in the advertising medium, A system that includes this.

2. The system according to claim 1, which optimizes prices by taking into account the company's sales history and market demand fluctuations along with the analysis results.

3. The system according to claim 1, which updates the price of an advertising medium in real time and displays it on the user's terminal.

Images