system

Abstract

We provide the system. [Solution] A means for collecting commercial data, deleting redundant data, and correcting abnormal data, A means of analyzing market trends and consumer purchasing behavior using generative AI, A method for calculating the fair price of a product using a predictive model, A means of presenting the calculated fair price, A means of updating the predictive model by analyzing feedback provided by users, 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 character of the chatbot, 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 the conventional price setting method, it is difficult to accurately grasp commercial data and customer trends, and it often depends on the experience and intuition of sellers. Therefore, there is a problem that the balance between demand and supply cannot be appropriately evaluated, resulting in opportunity losses and profit losses. In addition, for consumers, the price is opaque, making it difficult to make a purchase decision.

Means for Solving the Problems

[0005] This invention provides a system for collecting commercial data, removing redundant data, and correcting anomalous data. This system utilizes generative AI to analyze market trends and consumer purchasing behavior, and uses a predictive model to calculate the appropriate price for a product. Furthermore, it aims to improve the accuracy and transparency of pricing by presenting the calculated appropriate price and updating the predictive model based on user feedback. This enables businesses to maximize profits and consumers to make purchases at reasonable prices.

[0006] "Commercial data" refers to all information related to business activities, such as transaction status, sales volume, pricing information, and customer attribute information.

[0007] "Generative AI" refers to artificial intelligence technology that analyzes large amounts of data, recognizes patterns, and performs predictions and generation.

[0008] "Market trends" refer to changes in price fluctuations, consumer demand, and competitor activities within a specific commercial market.

[0009] "Consumer purchasing behavior" refers to the process and patterns that consumers go through to select and purchase goods and services.

[0010] A "predictive model" refers to mathematical and statistical methods and algorithms used to forecast future demand and trends based on past data.

[0011] "Fair price" refers to a price that takes supply and demand into consideration, maximizes the company's profits, and is acceptable to consumers.

[0012] "Feedback" refers to the opinions and reactions that users give to the system's results or suggestions. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

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

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

[0021] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0034] The system according to the present invention aims to collect commercial data, remove redundant data, and correct anomalous data. This system utilizes generative AI technology to analyze market trends and consumer purchasing behavior, and uses a predictive model to calculate the appropriate price of a product. Furthermore, to ensure that the calculated price maximizes both corporate profits and consumer satisfaction, it effectively incorporates user feedback to improve the accuracy of the model.

[0035] Data collection phase

[0036] The server receives commercial data from terminals. This data is collected from retailers' POS systems and online platforms and includes daily transaction data, customer attributes, and sales history. A specific example is the daily sales information obtained from supermarket checkouts.

[0037] Data Analysis Phase

[0038] The server cleanses the collected data, removing duplicates and errors. The generating AI algorithm then analyzes this cleansed data to identify patterns and interpret consumer trends. For example, it can determine the lunch patterns of office workers who work regular hours.

[0039] Price calculation phase

[0040] The server uses the analysis results to build a predictive model and calculate an appropriate price. Based on supply and demand forecasts, this price calculation is set considering the product's best-selling items and inventory levels. For example, the price of a limited-edition summer product is adjusted to account for the increased sales on hot days.

[0041] Results presentation phase

[0042] The terminal displays the calculated fair price to the user. Consumers and retailers can verify this price on product labels or online shops. For example, it might be displayed as "This Week's Special" in the online store title and sold at the fair price.

[0043] Feedback collection phase

[0044] Users provide feedback on the presented price and purchase experience through their device. This feedback is sent to a server and used to further improve the accuracy of the predictive model. For example, the results of post-purchase satisfaction surveys are reflected in the model and used to help with future pricing.

[0045] As described above, this system maximizes corporate profits and improves consumer satisfaction through the efficient use of commercial data and the calculation of appropriate prices using generated AI.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The terminal collects commercial data from retailers' POS systems and online platforms. This data includes sales history, inventory status, and information about customer purchasing behavior, and is transmitted to a server via secure communication.

[0049] Step 2:

[0050] The server cleanses the received commercial data. During the cleansing process, duplicate and incomplete data is removed, and data is supplemented as needed. For example, if sales data contains incorrect figures, it is converted to the correct format.

[0051] Step 3:

[0052] The server analyzes the cleansed data and applies generative AI algorithms to understand market trends and consumer purchasing behavior. This analysis identifies when and how consumers tend to purchase specific products. For example, it may reveal that sales are concentrated on certain days or time slots.

[0053] Step 4:

[0054] Based on the analysis results, the server uses a predictive model to calculate the appropriate price for the product. The predictive model considers demand forecasts and price elasticity to identify the point at which maximum profit can be obtained through pricing. For example, it can calculate the optimal discount price during a sale period.

[0055] Step 5:

[0056] The server sends the calculated fair price to the terminal. The terminal then displays the fair price on the store's price display system or online platform for the user to verify. This allows consumers to see the latest and fairest prices and make informed purchasing decisions.

[0057] Step 6:

[0058] Users make purchases based on the quoted price and then provide satisfaction and feedback via their devices. This feedback is sent to the server and used to adjust the parameters of the AI ​​model, contributing to improved accuracy in future pricing.

[0059] (Example 1)

[0060] 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."

[0061] In commercial data analysis, data redundancy and the presence of outliers present challenges that reduce analytical accuracy. Furthermore, accurately capturing consumer behavior patterns, predicting market trends, and dynamically setting appropriate product prices are difficult. It is also crucial to incorporate user feedback in a timely manner to improve the accuracy of predictive models. The development of systems that address these challenges is essential.

[0062] 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.

[0063] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting abnormal data; means for cleansing and analyzing the collected data using generative AI technology; and means for constructing a predictive model based on the analysis results and calculating the appropriate price of a product. This enables efficient processing of commercial data, calculation of appropriate prices based on consumer trends, and improvement of the accuracy of the predictive model by utilizing user feedback.

[0064] "Commercial data" refers to all data collected in connection with commercial activities, including transaction information, customer information, and sales history.

[0065] "Redundant data" refers to data that exists in a system or dataset that has the same or similar meaning but is duplicated.

[0066] "Anomalous data" refers to data that deviates from expected patterns or ranges, indicating errors or irregularities.

[0067] "Generative AI technology" refers to a type of artificial intelligence, specifically a technology used for data analysis and pattern recognition.

[0068] "Data cleansing" refers to the process of removing errors, formatting mistakes, redundancies, and other issues from a dataset to make the data accurate and consistent.

[0069] A "predictive model" refers to a mathematical or machine learning model built to predict future events or trends based on past data.

[0070] "Fair price" refers to a reasonable and fair price for a product, set considering the balance of supply and demand in the market.

[0071] "User feedback" refers to information collected from customers or end-users regarding product evaluations and areas for improvement.

[0072] The system according to the present invention aims to efficiently calculate the appropriate price of a product through the collection, cleansing, and analysis of commercial data, and the incorporation of user feedback. This system is configured as follows.

[0073] Data collection:

[0074] The server retrieves commercial data from terminals. Specifically, sales history and customer information are collected via POS systems and online sales platforms. Network interfaces and protocols are used for transferring this data. As a concrete example, the number of sales of a specific product on a given date is collected from the POS system using an API.

[0075] Data cleansing and analysis:

[0076] The server cleanses the collected data using Python scripts to remove duplicates and errors. Then, it analyzes market trends and consumption patterns using generative AI technology. This process utilizes machine learning libraries such as TENSORFLOW® and PyTorch. A concrete example of analysis is the deriving of product sales patterns for specific seasons using an AI model.

[0077] Calculating the fair price:

[0078] The server builds a predictive model based on the analysis results and calculates the appropriate price for the product. A demand forecasting algorithm is used in this process, and high-performance GPUs are utilized to increase calculation speed. Specifically, one example is adjusting the price of a particular product during the summer season in conjunction with weather data.

[0079] Presentation of results and incorporation of feedback:

[0080] The device displays the calculated fair price to the user. This display is presented in a visible format, such as a price label in an online shop or physical store. The device also functions as an interface for collecting user feedback. When a user submits their evaluation via a web form, the server uses this feedback to further improve the accuracy of the model.

[0081] As an example of a prompt, the AI ​​model is designed to function correctly by instructing it to "forecast demand based on this week's new product sales data and calculate an appropriate price."

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1: Data Collection

[0084] The server retrieves commercial data from terminals and external systems. Inputs include detailed transaction records from POS systems and online sales sites. The server receives this data via APIs and stores it in a database. The output is a comprehensive commercial dataset containing date, product ID, sales quantity, price information, and more.

[0085] Step 2: Data Cleansing

[0086] The server cleanses the collected data using a Python script. The input is the raw data collected in step 1. The server removes duplicate records and corrects invalid values ​​(e.g., negative prices or non-integer quantities) from this data. The output is a clean dataset formatted for analysis.

[0087] Step 3: Pattern Analysis

[0088] The server analyzes clean data using a generative AI model. The cleaned data processed in step 2 is used as input. The server uses libraries such as TensorFlow to analyze consumer behavior patterns and market trends. Specifically, it extracts purchase frequency by time of day from the data. The output is an analysis result showing market trends and consumer behavior patterns.

[0089] Step 4: Building a predictive model and calculating prices

[0090] The server builds a predictive model based on the analysis results and calculates the appropriate price for the product. The input is the analysis results from step 3. The server uses a high-performance GPU to execute a demand forecasting algorithm and calculate the appropriate price. Specifically, it takes weather data into consideration and adjusts the price of summer products. The output is multiple price scenarios calculated based on the demand forecast.

[0091] Step 5: Presentation of Results

[0092] The terminal displays the appropriate price to the user. The input is the price information calculated in step 4. The terminal displays this on the online store's product page or on the price tag in a physical store. The output is price information visually presented to the user.

[0093] Step 6: Gathering Feedback and Updating the Model

[0094] Users provide feedback on their purchase experience through their devices. Input consists of user ratings and comments. The device sends this information to a server, and a specific action to reflect this in the model is inputting into a satisfaction survey form. Output is updated data that contributes to improving the accuracy of the predictive model.

[0095] (Application Example 1)

[0096] 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."

[0097] Setting fair prices in commercial transactions is crucial for ensuring corporate profits and gaining consumer satisfaction. However, current systems suffer from the drawbacks of being susceptible to redundancy and outliers in commercial data, making it difficult to accurately analyze consumer purchasing behavior and market trends. Furthermore, the lack of real-time, personalized price recommendations means that the system fails to meet the individual needs of consumers.

[0098] 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.

[0099] In this invention, the server includes means for collecting commercial data, removing redundant data and correcting anomalous data, means for analyzing market trends and consumer purchasing behavior using generative AI, and means for calculating the appropriate price of a product using a predictive model. This makes it possible to propose products and prices suitable for consumers in real time, improving both corporate profits and consumer satisfaction.

[0100] "Commercial data" refers to information related to commercial transactions, including sales history, customer attributes, and transaction status.

[0101] "Deleting redundant data" refers to the act of removing duplicate or unnecessary information contained in commercial data.

[0102] "Correction of abnormal data" is the process of correcting errors and inconsistencies in input commercial data and converting it into accurate data.

[0103] "Generative AI" refers to algorithms that utilize artificial intelligence technology to automatically generate patterns and insights from big data.

[0104] "Market trends" refer to movements in the market over a certain period, such as fluctuations in demand and supply, price changes, and consumer behavior.

[0105] "Consumer purchasing behavior" refers to the series of actions and decision-making processes that consumers take when selecting and purchasing goods and services.

[0106] A "predictive model" is a mathematical model constructed to predict future trends and outcomes using past data and patterns.

[0107] A "fair price" is a price that maintains a balance between supply and demand, ensures the company's profits, and is also acceptable to consumers.

[0108] "User feedback" refers to the opinions, impressions, and evaluations that consumers and users provide regarding products and services.

[0109] "Real-time suggestions" means immediately presenting appropriate information and options based on the current situation.

[0110] The system that realizes this application consists of a server, a user terminal (such as a smartphone), and a generative AI model.

[0111] The server receives commercial data and stores and organizes it using a database management system (e.g., MySQL®, PostgreSQL). This commercial data includes sales history, customer attributes, and transaction status. Data cleansing algorithms are used to remove redundant data and correct anomalous data. Machine learning frameworks such as TensorFlow and PyTorch are used as the generation AI model to analyze market trends and consumer purchasing behavior based on the cleansed data.

[0112] Based on the analysis results, the server builds a predictive model and calculates the appropriate price for the product. This price is designed to maximize both the company's profits and consumer satisfaction while considering the balance of supply and demand.

[0113] The user's device displays the calculated fair price and related information in a format that is easier for consumers to understand, in real time. For example, it may be notified as a personalized special offer on a smartphone. During this process, users can provide feedback on the displayed price and purchase experience, and this feedback is collected on the server and used to improve the accuracy of the predictive model.

[0114] As a concrete example, for users who prefer to buy cold beverages in the summer, analysis incorporating weather forecast data will send push notifications offering cold beverages at special prices on days when high temperatures are expected. This allows for timely suggestions tailored to individual consumer needs.

[0115] An example of a prompt is, "Consider the user's past purchase patterns and current market trends, and suggest a list of potential purchases for the next week along with their optimal prices." This allows the generative AI model to make specific suggestions and provide a personalized consumer experience.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server receives data such as sales history, customer attributes, and transaction status through a commercial data collection system. Inputs are data from POS systems and online platforms, and output is a well-organized dataset of raw data. This dataset is stored in a database management system.

[0119] Step 2:

[0120] The server executes a data cleansing algorithm to remove redundant data and correct outliers from the input dataset. The input is a raw dataset, and after removing duplicates and correcting errors, the output is a clean, purified dataset.

[0121] Step 3:

[0122] The server uses a generative AI model to analyze market trends and consumer purchasing behavior. The input is a cleaned dataset, and the output is the analysis results of consumer trends and purchasing patterns. This analysis uses prompts to extract important patterns of consumer behavior.

[0123] Step 4:

[0124] The server builds a predictive model based on the analysis results and calculates the appropriate price for each product. The input is consumer trends and purchasing patterns, and based on this, it uses a demand forecasting algorithm to determine the optimal pricing strategy. The output is the appropriate price for each product.

[0125] Step 5:

[0126] The server sends the calculated fair price to the user's terminal. The terminal prepares to present the received price information to the consumer. At this stage, a personalized price notification is generated as output, which is displayed on the terminal.

[0127] Step 6:

[0128] Users submit feedback regarding the offered price and purchase experience through their device. The input is the user's feedback, which the device collects and sends to the server. The output is the feedback data received by the server.

[0129] Step 7:

[0130] The server analyzes the received feedback and updates the predictive model. This process uses the feedback data as input and employs optimization algorithms to improve the accuracy of the generated AI model. The output is the improved predictive model.

[0131] 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.

[0132] This invention is a system that combines the collection and analysis of commercial data with an emotion engine that recognizes user emotions. This system improves data quality by collecting commercial data, removing redundant data, and correcting anomalous data. The collected data is analyzed using generative AI to gain a detailed understanding of market trends and consumer purchasing behavior.

[0133] A distinctive feature of this invention is its ability to analyze user emotional data using an emotion engine. Specifically, it can analyze the facial expressions and behaviors that users exhibit during the product purchasing process and product recommendations via their devices, and recognize emotions such as positive or negative. For example, by analyzing in real time what emotions a user is experiencing during the online store purchase process, it is possible to provide more personalized recommendations.

[0134] Furthermore, this sentiment data is incorporated into the generative AI's predictive model and used as a crucial element in calculating the appropriate price for a product. This allows pricing to be optimized not only by considering market and customer trends, but also by taking into account the user's purchasing experience and emotional tendencies. For example, if negative emotions towards a high-priced product are detected, the system can be adjusted to offer a coupon to mitigate those emotions.

[0135] As a result, users receive real-time adjusted fair pricing and product recommendations, and retailers can maximize profits while improving customer satisfaction. By integrating data analysis and emotion recognition technology, this invention functions as a more sophisticated and effective sales strategy support system.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The terminal collects commercial data from retailers' POS systems and online platforms. This data includes sales history, inventory levels, and customer purchasing patterns, and is transmitted to the server via a secure protocol.

[0139] Step 2:

[0140] The server cleanses the received commercial data. It removes redundant data and corrects anomalous data, and stores the data in a database to ensure data integrity. For example, it identifies and deletes duplicate transaction information.

[0141] Step 3:

[0142] The server uses generated AI with well-organized data to analyze market trends and consumer purchasing behavior. This analysis reveals consumer purchasing trends for specific products or catalogs. For example, it reveals that discounted items sell particularly well on weekday evenings.

[0143] Step 4:

[0144] The device collects emotional data through the user's facial expressions and voice input. This emotion engine identifies emotions such as positive and negative in real time based on changes in the user's facial expressions and voice tone shown through the webcam and microphone.

[0145] Step 5:

[0146] The server analyzes emotional data obtained from the emotion engine and incorporates it into the generative AI's predictive model. This integration allows for the quantification of how a user's emotional state affects price elasticity and product recommendations, for example, by suggesting alternative options if a particular product is causing stress to the user.

[0147] Step 6:

[0148] The server calculates the appropriate price for a product based on the analysis results and sends it to the terminal. It then allows users to access new pricing information and promotional suggestions. For example, to increase purchasing intent, it automatically calculates and displays discounts based on the purchase amount.

[0149] Step 7:

[0150] Users review the quoted price and decide to purchase. Post-purchase feedback and satisfaction surveys are provided via the device, and this data is sent back to the server to further improve the AI ​​model.

[0151] In this way, the system integrates user emotions with commercial data to improve the quality of price suggestions and product recommendations. This allows retailers to efficiently increase profits and consumers to enjoy the most satisfying shopping experience.

[0152] (Example 2)

[0153] 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".

[0154] In commercial activities, providing customers with product recommendations and pricing based on appropriate information is crucial. However, traditional methods rely solely on market trends and consumer behavior, making it difficult to consider the emotions of individual customers when making product recommendations. Furthermore, it is difficult to analyze emotion-based feedback in real time and make immediate price adjustments. This creates a challenge in achieving both improved customer satisfaction and maximized retailers' profits.

[0155] 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.

[0156] In this invention, the server includes means for collecting commercial information, deleting redundant information, and correcting anomalous information; means for analyzing emotional states obtained from users; and means for calculating appropriate prices based on product characteristics using a predictive model. This makes it possible to propose products and set prices that take into account the emotions of individual customers.

[0157] "Commercial information" refers to all data related to market activities, including product information, customer reviews, and sales data.

[0158] "Redundant information" refers to repetitive or unnecessary parts of data, including information and noise that have little value for analysis.

[0159] "Aberrant information" refers to data that contains values ​​or errors that deviate from the normal pattern.

[0160] "Generative artificial intelligence" refers to artificial intelligence technology that has natural language processing and analysis capabilities based on large datasets, and uses machine learning models and deep learning techniques.

[0161] "Emotion analysis methods" refer to technologies that evaluate a user's emotional state based on their facial expressions and behavior, and recognize emotions such as positive or negative.

[0162] A "predictive model" refers to a mathematical model used to predict future trends based on past data, employing regression analysis and machine learning algorithms.

[0163] "Fair price" refers to a reasonable product price calculated based on market value, customer demand, and the pricing of competitors.

[0164] "Emotional feedback" refers to information collected from users' emotional responses and opinions, which is used as an evaluation of products and services.

[0165] A "pricing scenario" refers to a pricing strategy under different conditions, and includes methods for considering multiple pricing options that take into account customer price elasticity and emotional tendencies.

[0166] This invention is a system that combines the collection and analysis of commercial information with sentiment analysis technology to recognize user emotions. This system is designed to efficiently support commercial activities. Specifically, it is configured as follows:

[0167] The server collects commercial information via the internet. During collection, data is obtained from numerous sources, and a web crawler is used to improve efficiency. The Python Scrapy library can be used to implement the web crawler.

[0168] Next, the device activates input devices such as a camera and microphone to collect the user's emotional state in real time. For emotion analysis, a common API is used; for example, the Emotion API might be utilized. This analyzes the user's emotional state as positive or negative.

[0169] The collected commercial information is preprocessed on the server. Redundant information is removed from the database using SQL queries, and anomalous information is corrected using mean values ​​or statistical methods. Missing values ​​are also imputed using the KNN method.

[0170] The server then feeds this data into a generative AI model to analyze market trends and consumer purchasing behavior. Deep learning frameworks such as TensorFlow are used to build the generative AI model. An example of a prompt message that might be input at this time is: "Generate personalized recommendations based on the sentiment data the user displayed while browsing products in the online store. If the sentiment is negative, include suggestions for mitigation."

[0171] Furthermore, the server uses a predictive model based on sentiment analysis results to calculate the appropriate price. This makes it possible to provide users with optimized product pricing and recommendations. Users receive this real-time, adjusted information and make purchasing decisions. This allows retailers to improve customer satisfaction and maximize profits.

[0172] Thus, the present invention functions as a system that supports optimal sales strategies by integrating commercial data analysis and sentiment analysis technology.

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

[0174] Step 1:

[0175] The server collects commercial information from the internet. It uses a web crawler to retrieve product information and customer reviews from various data sources. The input is commercial information from the internet, and the output is a raw dataset. Specifically, it uses the Python Scrapy library to perform web crawling and filters the data based on predefined conditions.

[0176] Step 2:

[0177] The server performs preprocessing on the collected raw dataset. The input is the raw dataset obtained in step 1, and the output is a clean dataset. Redundant information is removed using SQL queries, and anomalous information is corrected using the mean. In addition, if there are missing values, imputation is performed using the KNN method. This generates a high-quality dataset suitable for subsequent analysis.

[0178] Step 3:

[0179] The device collects the user's emotional state in real time. Input is the user's facial expressions and voice captured by the camera and microphone, and output is emotional data. The collected data is sent to an emotion recognition service such as the Emotion API, from which an emotional label (positive, negative, etc.) is obtained. This process continues continuously while the user is browsing or purchasing products.

[0180] Step 4:

[0181] The server inputs a clean dataset and user sentiment data into a generating AI model for analysis. The input is the clean dataset from step 2 and the sentiment data from step 3, and the output is the analysis results. A TensorFlow deep learning model is used to predict market trends and consumer purchasing behavior. Specifically, it provides the generating AI model with prompt sentences that define the purpose of the analysis.

[0182] Step 5:

[0183] The server uses a predictive model based on the analysis results to calculate an appropriate price based on product characteristics. The input is the analysis results from step 4, and the output is the appropriate price and product recommendations. The calculated results are provided to the user as optimized product information via email or in-app notifications.

[0184] Step 6:

[0185] Users make purchasing decisions based on information provided by the server. The input is the appropriate price and product suggestions provided in step 5, and the output is the purchase selection. This selection information is also fed back into the system and used to adjust and improve the model. Through this process, the customer experience is optimized, and retailers can maximize their profits.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0188] As consumer purchasing behavior diversifies and online transactions become dominant, understanding consumer emotions and implementing optimal pricing strategies and product recommendations based on them becomes challenging. Furthermore, uniform pricing is insufficient to adequately improve consumer satisfaction, and personalized experiences tailored to individual consumers are required.

[0189] 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.

[0190] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting anomalous data, means for analyzing market trends and consumer purchasing behavior using generating AI, and means for recognizing user emotions. This enables optimal product recommendations and price adjustments based on consumer emotions.

[0191] "Commercial data" refers to all data related to the sale and transaction of goods, and is collected as a comprehensive dataset.

[0192] "Redundant data" refers to data that is duplicated or unnecessary, and which reduces the efficiency of a system.

[0193] "Aberrant data" refers to data within a dataset that deviates from the normal range and may impair the accuracy of predictions and analyses.

[0194] "Generative AI" refers to artificial intelligence technology that learns from data and generates new information and insights.

[0195] "Market trends" refer to changes and tendencies that indicate the current economic environment and consumer purchasing patterns.

[0196] "Consumer purchasing behavior" refers to the series of actions taken by consumers in the process of selecting and purchasing a product.

[0197] A "predictive model" refers to a mathematical model used to estimate future trends and outcomes based on past data.

[0198] "Fair price" refers to the optimal price range determined based on market and consumer conditions.

[0199] "User sentiment" refers to the psychological reactions and emotional states that consumers exhibit when browsing or purchasing products.

[0200] "Optimizing product recommendations" refers to the process of selecting and suggesting products that best match the preferences and emotions of individual consumers.

[0201] Modes for carrying out the invention

[0202] The system realizing this invention is designed to support consumers' actions when they browse, consider, and purchase products on online platforms. The server has the function of collecting commercial data and automatically removing redundant data and correcting anomalous data. After improving the quality of the data, it uses generative AI to analyze market trends and consumer purchasing behavior. The server recognizes emotions from camera images and audio data acquired through the user's terminal and optimizes product recommendations based on that data.

[0203] Specifically, the server first processes the video data sent from the user's terminal using an image recognition library (e.g., OpenCV). During this process, it analyzes the user's facial expressions while they are browsing products and determines whether they are feeling positive or negative emotions. Similarly, audio data collected through the microphone is processed using a speech analysis library (e.g., Google Cloud Speech-to-Text) to recognize emotions from the tone and content of the voice.

[0204] The server analyzes the acquired emotional data using a generative AI model (e.g., built with TensorFlow) and dynamically suggests the most suitable products and services for the user. The user's past purchase history and market data are also considered during this process. Furthermore, a predictive model is used to calculate an appropriate price for the selected product to determine if it is suitable for the user.

[0205] For example, when a user is purchasing a new electronic device, if their facial expression shows a negative reaction, the system will immediately adjust the price or offer a coupon to improve the purchase experience. A concrete example of a prompt message might be: "The user expressed negative feelings about the new laptop due to the price. What action should be taken to alleviate this user's feelings?"

[0206] This allows users to receive optimized product recommendations and price adjustments in real time based on their emotions and purchase history, resulting in a more satisfying shopping experience. Retailers can also improve revenue by optimizing their approach to individual consumers.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server receives commercial data sent from the user's terminal. This commercial data includes product browsing history and purchase history. The server removes redundant data and corrects anomalous data to generate a clean dataset. This process removes data noise and improves the accuracy of the analysis.

[0210] Step 2:

[0211] The server uses a generative AI model to analyze the clean dataset obtained in Step 1. It receives data including market trends and consumer purchasing behavior as input, and the AI ​​model uses this to output detailed consumer profiles and market forecasts. During this process, the server calculates consumption trends and demand forecasts using the generative AI model.

[0212] Step 3:

[0213] The device uses the user's camera and microphone to collect data on the user's facial expressions and voice in real time. It captures the user's facial expressions and tone of voice while they are browsing products and sends this data to the server. The input data consists of facial images and audio data, and the output is data that is ready to be classified as emotion.

[0214] Step 4:

[0215] The server analyzes the facial image and audio data received in step 3. It uses an image recognition library (e.g., OpenCV) and an audio analysis library (e.g., Google Cloud Speech-to-Text) to recognize emotions. It detects emotions such as positive or negative from the input image and audio and outputs this as emotion data.

[0216] Step 5:

[0217] The server passes the emotional data obtained in step 4 to the generating AI model to make optimal product recommendations. Combining the emotional data with consumer profiles, it dynamically makes product recommendations and adjusts prices, which are then sent to the user. Based on the emotional data input, it outputs a personalized product list.

[0218] Step 6:

[0219] The user reviews product suggestions sent from the server on their device. Based on the suggested information, the user can then decide whether to purchase. The system retrieves the user's final opinion and feedback and sends it back to the server.

[0220] Step 7:

[0221] The server analyzes user feedback and updates the predictive model. Based on the acquired feedback, it processes the data to further refine the appropriate price and product recommendations for the product. This results in output that improves the accuracy of the predictive model from the input feedback.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] The system according to the present invention aims to collect commercial data, remove redundant data, and correct anomalous data. This system utilizes generative AI technology to analyze market trends and consumer purchasing behavior, and uses a predictive model to calculate the appropriate price of a product. Furthermore, to ensure that the calculated price maximizes both corporate profits and consumer satisfaction, it effectively incorporates user feedback to improve the accuracy of the model.

[0239] Data collection phase

[0240] The server receives commercial data from terminals. This data is collected from retailers' POS systems and online platforms and includes daily transaction data, customer attributes, and sales history. A specific example is the daily sales information obtained from supermarket checkouts.

[0241] Data Analysis Phase

[0242] The server cleanses the collected data, removing duplicates and errors. The generating AI algorithm then analyzes this cleansed data to identify patterns and interpret consumer trends. For example, it can determine the lunch patterns of office workers who work regular hours.

[0243] Price calculation phase

[0244] The server uses the analysis results to build a predictive model and calculate an appropriate price. Based on supply and demand forecasts, this price calculation is set considering the product's best-selling items and inventory levels. For example, the price of a limited-edition summer product is adjusted to account for the increased sales on hot days.

[0245] Results presentation phase

[0246] The terminal displays the calculated fair price to the user. Consumers and retailers can verify this price on product labels or online shops. For example, it might be displayed as "This Week's Special" in the online store title and sold at the fair price.

[0247] Feedback collection phase

[0248] Users provide feedback on the presented price and purchase experience through their device. This feedback is sent to a server and used to further improve the accuracy of the predictive model. For example, the results of post-purchase satisfaction surveys are reflected in the model and used to help with future pricing.

[0249] As described above, this system maximizes corporate profits and improves consumer satisfaction through the efficient use of commercial data and the calculation of appropriate prices using generated AI.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The terminal collects commercial data from retailers' POS systems and online platforms. This data includes sales history, inventory status, and information about customer purchasing behavior, and is transmitted to a server via secure communication.

[0253] Step 2:

[0254] The server cleanses the received commercial data. During the cleansing process, duplicate and incomplete data is removed, and data is supplemented as needed. For example, if sales data contains incorrect figures, it is converted to the correct format.

[0255] Step 3:

[0256] The server analyzes the cleansed data and applies generative AI algorithms to understand market trends and consumer purchasing behavior. This analysis identifies when and how consumers tend to purchase specific products. For example, it may reveal that sales are concentrated on certain days or time slots.

[0257] Step 4:

[0258] Based on the analysis results, the server uses a predictive model to calculate the appropriate price for the product. The predictive model considers demand forecasts and price elasticity to identify the point at which maximum profit can be obtained through pricing. For example, it can calculate the optimal discount price during a sale period.

[0259] Step 5:

[0260] The server sends the calculated fair price to the terminal. The terminal then displays the fair price on the store's price display system or online platform for the user to verify. This allows consumers to see the latest and fairest prices and make informed purchasing decisions.

[0261] Step 6:

[0262] Users make purchases based on the quoted price and then provide satisfaction and feedback via their devices. This feedback is sent to the server and used to adjust the parameters of the AI ​​model, contributing to improved accuracy in future pricing.

[0263] (Example 1)

[0264] 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".

[0265] In commercial data analysis, data redundancy and the presence of outliers present challenges that reduce analytical accuracy. Furthermore, accurately capturing consumer behavior patterns, predicting market trends, and dynamically setting appropriate product prices are difficult. It is also crucial to incorporate user feedback in a timely manner to improve the accuracy of predictive models. The development of systems that address these challenges is essential.

[0266] 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.

[0267] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting abnormal data; means for cleansing and analyzing the collected data using generative AI technology; and means for constructing a predictive model based on the analysis results and calculating the appropriate price of a product. This enables efficient processing of commercial data, calculation of appropriate prices based on consumer trends, and improvement of the accuracy of the predictive model by utilizing user feedback.

[0268] "Commercial data" refers to all data collected in connection with commercial activities, including transaction information, customer information, and sales history.

[0269] "Redundant data" refers to data that exists in a system or dataset that has the same or similar meaning but is duplicated.

[0270] "Anomalous data" refers to data that deviates from expected patterns or ranges, indicating errors or irregularities.

[0271] "Generative AI technology" refers to a type of artificial intelligence, specifically a technology used for data analysis and pattern recognition.

[0272] "Data cleansing" refers to the process of removing errors, formatting mistakes, redundancies, and other issues from a dataset to make the data accurate and consistent.

[0273] A "predictive model" refers to a mathematical or machine learning model built to predict future events or trends based on past data.

[0274] "Fair price" refers to a reasonable and fair price for a product, set considering the balance of supply and demand in the market.

[0275] "User feedback" refers to information collected from customers or end-users regarding product evaluations and areas for improvement.

[0276] The system according to the present invention aims to efficiently calculate the appropriate price of a product through the collection, cleansing, and analysis of commercial data, and the incorporation of user feedback. This system is configured as follows.

[0277] Data collection:

[0278] The server obtains commercial data from terminals. Specifically, sales histories of products and customer information are collected via a POS system or an online sales platform. A network interface and protocol are used for the transfer of this data. As a specific example, the number of sales of a specific product on a certain date is collected from the POS using an API.

[0279] Data cleansing and analysis:

[0280] The server cleans the collected data using Python scripts to remove duplicates and errors. Then, market trends and consumption patterns are analyzed using generative AI technology. In this process, libraries such as TensorFlow and PyTorch for machine learning are utilized. As a specific example of the analysis, the sales pattern of a product in a specific season may be derived by an AI model.

[0281] Calculation of appropriate price:

[0282] The server constructs a prediction model based on the analysis results and calculates the appropriate price of the product. At this time, a demand prediction algorithm is used, and a high-performance GPU is utilized to increase the calculation speed. Specifically, when setting the price of a specific product in summer, there is an example of adjusting the price in conjunction with weather data.

[0283] Presentation of results and reflection of feedback:

[0284] The terminal presents the calculated appropriate price to the user. This presentation is made in a visible form as a price label in an online store or a physical store. The terminal also functions as an interface for collecting feedback from the user. When the user sends an evaluation through a web form, the server further improves the accuracy of the model based on this feedback.

[0285] As an example of a prompt sentence, by instructing "Please perform demand forecasting based on the new product sales data this week and calculate the appropriate price", the generative AI model operates appropriately.

[0286] The flow of the specific process in Example 1 will be described using FIG. 11.

[0287] Step 1: Data collection

[0288] The server acquires commercial data from terminals and external systems. As inputs, there are detailed transaction records from a POS system or an online sales site. The server receives these data via an API and stores them in a database. The output is a comprehensive commercial data set including date, product ID, sales quantity, price information, etc.

[0289] Step 2: Data cleansing

[0290] The server cleans the collected data using a Python script. The input is the raw data collected in Step 1. The server performs operations such as removing duplicate records and correcting incorrect values (e.g., negative prices or non-integer quantities) on this data. The output is a clean data set formatted in a state suitable for analysis.

[0291] Step 3: Pattern analysis

[0292] The server analyzes the clean data using a generative AI model. As the input, the cleansed data processed in Step 2 is used. The server utilizes libraries such as TensorFlow to analyze patterns of consumer behavior and market trends. As a specific operation, it extracts the purchase frequency by time period from the data. The output is an analysis result indicating market trends and consumer behavior patterns.

[0293] Step 4: Construction of a prediction model and price calculation

[0294] The server builds a predictive model based on the analysis results and calculates the appropriate price for the product. The input is the analysis results from step 3. The server uses a high-performance GPU to execute a demand forecasting algorithm and calculate the appropriate price. Specifically, it takes weather data into consideration and adjusts the price of summer products. The output is multiple price scenarios calculated based on the demand forecast.

[0295] Step 5: Presentation of Results

[0296] The terminal displays the appropriate price to the user. The input is the price information calculated in step 4. The terminal displays this on the online store's product page or on the price tag in a physical store. The output is price information visually presented to the user.

[0297] Step 6: Gathering Feedback and Updating the Model

[0298] Users provide feedback on their purchase experience through their devices. Input consists of user ratings and comments. The device sends this information to a server, and a specific action to reflect this in the model is inputting into a satisfaction survey form. Output is updated data that contributes to improving the accuracy of the predictive model.

[0299] (Application Example 1)

[0300] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0301] Setting fair prices in commercial transactions is crucial for ensuring corporate profits and gaining consumer satisfaction. However, current systems suffer from the drawbacks of being susceptible to redundancy and outliers in commercial data, making it difficult to accurately analyze consumer purchasing behavior and market trends. Furthermore, the lack of real-time, personalized price recommendations means that the system fails to meet the individual needs of consumers.

[0302] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0303] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting abnormal data, means for analyzing market trends and consumer purchase behaviors by utilizing generative AI, and means for calculating the appropriate price of a product using a prediction model. Thereby, it becomes possible to propose products and prices suitable for consumers in real time, and improve the profits of enterprises and the satisfaction of consumers.

[0304] "Commercial data" refers to information related to commercial transactions, including data such as sales history, customer attributes, and transaction status.

[0305] "Deletion of redundant data" refers to the act of eliminating duplicate or unnecessary information contained in commercial data.

[0306] "Correction of abnormal data" is a process of correcting errors and inconsistencies in the input commercial data and converting it into accurate data.

[0307] "Generative AI" is an algorithm that utilizes artificial intelligence technology to automatically generate patterns and insights from big data.

[0308] "Market trends" refer to the movements of market demand, supply, price fluctuations, and consumer behaviors over a certain period.

[0309] "Consumer purchase behavior" refers to the series of actions and decision-making processes when consumers select and purchase products or services.

[0310] "Prediction model" is a mathematical model constructed using past data and patterns to predict future trends and results.

[0311] "Appropriate price" is a price that maintains the balance of supply and demand, ensures the profits of enterprises, and is acceptable to consumers.

[0312] "User feedback" refers to the opinions, impressions, and evaluations that consumers and users provide regarding products and services.

[0313] "Real-time suggestions" means immediately presenting appropriate information and options based on the current situation.

[0314] The system that realizes this application consists of a server, a user terminal (such as a smartphone), and a generative AI model.

[0315] The server receives commercial data and stores and organizes it using a database management system (e.g., MySQL, PostgreSQL). This commercial data includes sales history, customer attributes, and transaction status. Data cleansing algorithms are used to remove redundant data and correct anomalous data. Machine learning frameworks such as TensorFlow and PyTorch are used as the generation AI model to analyze market trends and consumer purchasing behavior based on the cleansed data.

[0316] Based on the analysis results, the server builds a predictive model and calculates the appropriate price for the product. This price is designed to maximize both the company's profits and consumer satisfaction while considering the balance of supply and demand.

[0317] The user's device displays the calculated fair price and related information in a format that is easier for consumers to understand, in real time. For example, it may be notified as a personalized special offer on a smartphone. During this process, users can provide feedback on the displayed price and purchase experience, and this feedback is collected on the server and used to improve the accuracy of the predictive model.

[0318] As a concrete example, for users who prefer to buy cold beverages in the summer, analysis incorporating weather forecast data will send push notifications offering cold beverages at special prices on days when high temperatures are expected. This allows for timely suggestions tailored to individual consumer needs.

[0319] An example of a prompt is, "Consider the user's past purchase patterns and current market trends, and suggest a list of potential purchases for the next week along with their optimal prices." This allows the generative AI model to make specific suggestions and provide a personalized consumer experience.

[0320] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0321] Step 1:

[0322] The server receives data such as sales history, customer attributes, and transaction status through a commercial data collection system. Inputs are data from POS systems and online platforms, and output is a well-organized dataset of raw data. This dataset is stored in a database management system.

[0323] Step 2:

[0324] The server executes a data cleansing algorithm to remove redundant data and correct outliers from the input dataset. The input is a raw dataset, and after removing duplicates and correcting errors, the output is a clean, purified dataset.

[0325] Step 3:

[0326] The server uses a generative AI model to analyze market trends and consumer purchasing behavior. The input is a cleaned dataset, and the output is the analysis results of consumer trends and purchasing patterns. This analysis uses prompts to extract important patterns of consumer behavior.

[0327] Step 4:

[0328] The server builds a predictive model based on the analysis results and calculates the appropriate price for each product. The input is consumer trends and purchasing patterns, and based on this, it uses a demand forecasting algorithm to determine the optimal pricing strategy. The output is the appropriate price for each product.

[0329] Step 5:

[0330] The server sends the calculated fair price to the user's terminal. The terminal prepares to present the received price information to the consumer. At this stage, a personalized price notification is generated as output, which is displayed on the terminal.

[0331] Step 6:

[0332] Users submit feedback regarding the offered price and purchase experience through their device. The input is the user's feedback, which the device collects and sends to the server. The output is the feedback data received by the server.

[0333] Step 7:

[0334] The server analyzes the received feedback and updates the predictive model. This process uses the feedback data as input and employs optimization algorithms to improve the accuracy of the generated AI model. The output is the improved predictive model.

[0335] 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.

[0336] This invention is a system that combines the collection and analysis of commercial data with an emotion engine that recognizes user emotions. This system improves data quality by collecting commercial data, removing redundant data, and correcting anomalous data. The collected data is analyzed using generative AI to gain a detailed understanding of market trends and consumer purchasing behavior.

[0337] A distinctive feature of this invention is its ability to analyze user emotional data using an emotion engine. Specifically, it can analyze the facial expressions and behaviors that users exhibit during the product purchasing process and product recommendations via their devices, and recognize emotions such as positive or negative. For example, by analyzing in real time what emotions a user is experiencing during the online store purchase process, it is possible to provide more personalized recommendations.

[0338] Furthermore, this sentiment data is incorporated into the generative AI's predictive model and used as a crucial element in calculating the appropriate price for a product. This allows pricing to be optimized not only by considering market and customer trends, but also by taking into account the user's purchasing experience and emotional tendencies. For example, if negative emotions towards a high-priced product are detected, the system can be adjusted to offer a coupon to mitigate those emotions.

[0339] As a result, users receive real-time adjusted fair pricing and product recommendations, and retailers can maximize profits while improving customer satisfaction. By integrating data analysis and emotion recognition technology, this invention functions as a more sophisticated and effective sales strategy support system.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The terminal collects commercial data from retailers' POS systems and online platforms. This data includes sales history, inventory levels, and customer purchasing patterns, and is transmitted to the server via a secure protocol.

[0343] Step 2:

[0344] The server cleanses the received commercial data. It removes redundant data and corrects anomalous data, and stores the data in a database to ensure data integrity. For example, it identifies and deletes duplicate transaction information.

[0345] Step 3:

[0346] The server uses generated AI with well-organized data to analyze market trends and consumer purchasing behavior. This analysis reveals consumer purchasing trends for specific products or catalogs. For example, it reveals that discounted items sell particularly well on weekday evenings.

[0347] Step 4:

[0348] The device collects emotional data through the user's facial expressions and voice input. This emotion engine identifies emotions such as positive and negative in real time based on changes in the user's facial expressions and voice tone shown through the webcam and microphone.

[0349] Step 5:

[0350] The server analyzes emotional data obtained from the emotion engine and incorporates it into the generative AI's predictive model. This integration allows for the quantification of how a user's emotional state affects price elasticity and product recommendations, for example, by suggesting alternative options if a particular product is causing stress to the user.

[0351] Step 6:

[0352] The server calculates the appropriate price for a product based on the analysis results and sends it to the terminal. It then allows users to access new pricing information and promotional suggestions. For example, to increase purchasing intent, it automatically calculates and displays discounts based on the purchase amount.

[0353] Step 7:

[0354] Users review the quoted price and decide to purchase. Post-purchase feedback and satisfaction surveys are provided via the device, and this data is sent back to the server to further improve the AI ​​model.

[0355] In this way, the system integrates user emotions with commercial data to improve the quality of price suggestions and product recommendations. This allows retailers to efficiently increase profits and consumers to enjoy the most satisfying shopping experience.

[0356] (Example 2)

[0357] 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".

[0358] In commercial activities, providing customers with product recommendations and pricing based on appropriate information is crucial. However, traditional methods rely solely on market trends and consumer behavior, making it difficult to consider the emotions of individual customers when making product recommendations. Furthermore, it is difficult to analyze emotion-based feedback in real time and make immediate price adjustments. This creates a challenge in achieving both improved customer satisfaction and maximized retailers' profits.

[0359] 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.

[0360] In this invention, the server includes means for collecting commercial information, deleting redundant information, and correcting anomalous information; means for analyzing emotional states obtained from users; and means for calculating appropriate prices based on product characteristics using a predictive model. This makes it possible to propose products and set prices that take into account the emotions of individual customers.

[0361] "Commercial information" refers to all data related to market activities, including product information, customer reviews, and sales data.

[0362] "Redundant information" refers to repetitive or unnecessary parts of data, including information and noise that have little value for analysis.

[0363] "Aberrant information" refers to data that contains values ​​or errors that deviate from the normal pattern.

[0364] "Generative artificial intelligence" refers to artificial intelligence technology that has natural language processing and analysis capabilities based on large datasets, and uses machine learning models and deep learning techniques.

[0365] "Emotion analysis methods" refer to technologies that evaluate a user's emotional state based on their facial expressions and behavior, and recognize emotions such as positive or negative.

[0366] A "predictive model" refers to a mathematical model used to predict future trends based on past data, employing regression analysis and machine learning algorithms.

[0367] "Fair price" refers to a reasonable product price calculated based on market value, customer demand, and the pricing of competitors.

[0368] "Emotional feedback" refers to information collected from users' emotional responses and opinions, which is used as an evaluation of products and services.

[0369] A "pricing scenario" refers to a pricing strategy under different conditions, and includes methods for considering multiple pricing options that take into account customer price elasticity and emotional tendencies.

[0370] This invention is a system that combines the collection and analysis of commercial information with sentiment analysis technology to recognize user emotions. This system is designed to efficiently support commercial activities. Specifically, it is configured as follows:

[0371] The server collects commercial information via the internet. During collection, data is obtained from numerous sources, and a web crawler is used to improve efficiency. The Python Scrapy library can be used to implement the web crawler.

[0372] Next, the device activates input devices such as a camera and microphone to collect the user's emotional state in real time. For emotion analysis, a common API is used; for example, the Emotion API might be utilized. This analyzes the user's emotional state as positive or negative.

[0373] The collected commercial information is preprocessed on the server. Redundant information is removed from the database using SQL queries, and anomalous information is corrected using mean values ​​or statistical methods. Missing values ​​are also imputed using the KNN method.

[0374] The server then feeds this data into a generative AI model to analyze market trends and consumer purchasing behavior. Deep learning frameworks such as TensorFlow are used to build the generative AI model. An example of a prompt message that might be input at this time is: "Generate personalized recommendations based on the sentiment data the user displayed while browsing products in the online store. If the sentiment is negative, include suggestions for mitigation."

[0375] Furthermore, the server uses a predictive model based on sentiment analysis results to calculate the appropriate price. This makes it possible to provide users with optimized product pricing and recommendations. Users receive this real-time, adjusted information and make purchasing decisions. This allows retailers to improve customer satisfaction and maximize profits.

[0376] Thus, the present invention functions as a system that supports optimal sales strategies by integrating commercial data analysis and sentiment analysis technology.

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] The server collects commercial information from the internet. It uses a web crawler to retrieve product information and customer reviews from various data sources. The input is commercial information from the internet, and the output is a raw dataset. Specifically, it uses the Python Scrapy library to perform web crawling and filters the data based on predefined conditions.

[0380] Step 2:

[0381] The server performs preprocessing on the collected raw dataset. The input is the raw dataset obtained in step 1, and the output is a clean dataset. Redundant information is removed using SQL queries, and anomalous information is corrected using the mean. In addition, if there are missing values, imputation is performed using the KNN method. This generates a high-quality dataset suitable for subsequent analysis.

[0382] Step 3:

[0383] The device collects the user's emotional state in real time. Input is the user's facial expressions and voice captured by the camera and microphone, and output is emotional data. The collected data is sent to an emotion recognition service such as the Emotion API, from which an emotional label (positive, negative, etc.) is obtained. This process continues continuously while the user is browsing or purchasing products.

[0384] Step 4:

[0385] The server inputs a clean dataset and user sentiment data into a generating AI model for analysis. The input is the clean dataset from step 2 and the sentiment data from step 3, and the output is the analysis results. A TensorFlow deep learning model is used to predict market trends and consumer purchasing behavior. Specifically, it provides the generating AI model with prompt sentences that define the purpose of the analysis.

[0386] Step 5:

[0387] The server uses a predictive model based on the analysis results to calculate an appropriate price based on product characteristics. The input is the analysis results from step 4, and the output is the appropriate price and product recommendations. The calculated results are provided to the user as optimized product information via email or in-app notifications.

[0388] Step 6:

[0389] Users make purchasing decisions based on information provided by the server. The input is the appropriate price and product suggestions provided in step 5, and the output is the purchase selection. This selection information is also fed back into the system and used to adjust and improve the model. Through this process, the customer experience is optimized, and retailers can maximize their profits.

[0390] (Application Example 2)

[0391] 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."

[0392] As consumer purchasing behavior diversifies and online transactions become dominant, understanding consumer emotions and implementing optimal pricing strategies and product recommendations based on them becomes challenging. Furthermore, uniform pricing is insufficient to adequately improve consumer satisfaction, and personalized experiences tailored to individual consumers are required.

[0393] 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.

[0394] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting anomalous data, means for analyzing market trends and consumer purchasing behavior using generating AI, and means for recognizing user emotions. This enables optimal product recommendations and price adjustments based on consumer emotions.

[0395] "Commercial data" refers to all data related to the sale and transaction of goods, and is collected as a comprehensive dataset.

[0396] "Redundant data" refers to data that is duplicated or unnecessary, and which reduces the efficiency of a system.

[0397] "Aberrant data" refers to data within a dataset that deviates from the normal range and may impair the accuracy of predictions and analyses.

[0398] "Generative AI" refers to artificial intelligence technology that learns from data and generates new information and insights.

[0399] "Market trends" refer to changes and tendencies that indicate the current economic environment and consumer purchasing patterns.

[0400] "Consumer purchasing behavior" refers to the series of actions taken by consumers in the process of selecting and purchasing a product.

[0401] A "predictive model" refers to a mathematical model used to estimate future trends and outcomes based on past data.

[0402] "Fair price" refers to the optimal price range determined based on market and consumer conditions.

[0403] "User sentiment" refers to the psychological reactions and emotional states that consumers exhibit when browsing or purchasing products.

[0404] "Optimizing product recommendations" refers to the process of selecting and suggesting products that best match the preferences and emotions of individual consumers.

[0405] Modes for carrying out the invention

[0406] The system realizing this invention is designed to support consumers' actions when they browse, consider, and purchase products on online platforms. The server has the function of collecting commercial data and automatically removing redundant data and correcting anomalous data. After improving the quality of the data, it uses generative AI to analyze market trends and consumer purchasing behavior. The server recognizes emotions from camera images and audio data acquired through the user's terminal and optimizes product recommendations based on that data.

[0407] Specifically, the server first processes the video data sent from the user's terminal using an image recognition library (e.g., OpenCV). During this process, it analyzes the user's facial expressions while they are browsing products and determines whether they are feeling positive or negative emotions. Similarly, audio data collected through the microphone is processed using a speech analysis library (e.g., Google Cloud Speech-to-Text) to recognize emotions from the tone and content of the voice.

[0408] The server analyzes the acquired emotional data using a generative AI model (e.g., built with TensorFlow) and dynamically suggests the most suitable products and services for the user. The user's past purchase history and market data are also considered during this process. Furthermore, a predictive model is used to calculate an appropriate price for the selected product to determine if it is suitable for the user.

[0409] For example, when a user is purchasing a new electronic device, if their facial expression shows a negative reaction, the system will immediately adjust the price or offer a coupon to improve the purchase experience. A concrete example of a prompt message might be: "The user expressed negative feelings about the new laptop due to the price. What action should be taken to alleviate this user's feelings?"

[0410] This allows users to receive optimized product recommendations and price adjustments in real time based on their emotions and purchase history, resulting in a more satisfying shopping experience. Retailers can also improve revenue by optimizing their approach to individual consumers.

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] The server receives commercial data sent from the user's terminal. This commercial data includes product browsing history and purchase history. The server removes redundant data and corrects anomalous data to generate a clean dataset. This process removes data noise and improves the accuracy of the analysis.

[0414] Step 2:

[0415] The server uses a generative AI model to analyze the clean dataset obtained in Step 1. It receives data including market trends and consumer purchasing behavior as input, and the AI ​​model uses this to output detailed consumer profiles and market forecasts. During this process, the server calculates consumption trends and demand forecasts using the generative AI model.

[0416] Step 3:

[0417] The device uses the user's camera and microphone to collect data on the user's facial expressions and voice in real time. It captures the user's facial expressions and tone of voice while they are browsing products and sends this data to the server. The input data consists of facial images and audio data, and the output is data that is ready to be classified as emotion.

[0418] Step 4:

[0419] The server analyzes the facial image and audio data received in step 3. It uses an image recognition library (e.g., OpenCV) and an audio analysis library (e.g., Google Cloud Speech-to-Text) to recognize emotions. It detects emotions such as positive or negative from the input image and audio and outputs this as emotion data.

[0420] Step 5:

[0421] The server passes the emotional data obtained in step 4 to the generating AI model to make optimal product recommendations. Combining the emotional data with consumer profiles, it dynamically makes product recommendations and adjusts prices, which are then sent to the user. Based on the emotional data input, it outputs a personalized product list.

[0422] Step 6:

[0423] The user reviews product suggestions sent from the server on their device. Based on the suggested information, the user can then decide whether to purchase. The system retrieves the user's final opinion and feedback and sends it back to the server.

[0424] Step 7:

[0425] The server analyzes user feedback and updates the predictive model. Based on the acquired feedback, it processes the data to further refine the appropriate price and product recommendations for the product. This results in output that improves the accuracy of the predictive model from the input feedback.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] [Third Embodiment]

[0430] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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".

[0442] The system according to the present invention aims to collect commercial data, remove redundant data, and correct anomalous data. This system utilizes generative AI technology to analyze market trends and consumer purchasing behavior, and uses a predictive model to calculate the appropriate price of a product. Furthermore, to ensure that the calculated price maximizes both corporate profits and consumer satisfaction, it effectively incorporates user feedback to improve the accuracy of the model.

[0443] Data collection phase

[0444] The server receives commercial data from terminals. This data is collected from retailers' POS systems and online platforms and includes daily transaction data, customer attributes, and sales history. A specific example is the daily sales information obtained from supermarket checkouts.

[0445] Data Analysis Phase

[0446] The server cleanses the collected data, removing duplicates and errors. The generating AI algorithm then analyzes this cleansed data to identify patterns and interpret consumer trends. For example, it can determine the lunch patterns of office workers who work regular hours.

[0447] Price calculation phase

[0448] The server uses the analysis results to build a predictive model and calculate an appropriate price. Based on supply and demand forecasts, this price calculation is set considering the product's best-selling items and inventory levels. For example, the price of a limited-edition summer product is adjusted to account for the increased sales on hot days.

[0449] Results presentation phase

[0450] The terminal displays the calculated fair price to the user. Consumers and retailers can verify this price on product labels or online shops. For example, it might be displayed as "This Week's Special" in the online store title and sold at the fair price.

[0451] Feedback collection phase

[0452] Users provide feedback on the presented price and purchase experience through their device. This feedback is sent to a server and used to further improve the accuracy of the predictive model. For example, the results of post-purchase satisfaction surveys are reflected in the model and used to help with future pricing.

[0453] As described above, this system maximizes corporate profits and improves consumer satisfaction through the efficient use of commercial data and the calculation of appropriate prices using generated AI.

[0454] The following describes the processing flow.

[0455] Step 1:

[0456] The terminal collects commercial data from retailers' POS systems and online platforms. This data includes sales history, inventory status, and information about customer purchasing behavior, and is transmitted to a server via secure communication.

[0457] Step 2:

[0458] The server cleanses the received commercial data. During the cleansing process, duplicate and incomplete data is removed, and data is supplemented as needed. For example, if sales data contains incorrect figures, it is converted to the correct format.

[0459] Step 3:

[0460] The server analyzes the cleansed data and applies generative AI algorithms to understand market trends and consumer purchasing behavior. This analysis identifies when and how consumers tend to purchase specific products. For example, it may reveal that sales are concentrated on certain days or time slots.

[0461] Step 4:

[0462] Based on the analysis results, the server uses a predictive model to calculate the appropriate price for the product. The predictive model considers demand forecasts and price elasticity to identify the point at which maximum profit can be obtained through pricing. For example, it can calculate the optimal discount price during a sale period.

[0463] Step 5:

[0464] The server sends the calculated fair price to the terminal. The terminal then displays the fair price on the store's price display system or online platform for the user to verify. This allows consumers to see the latest and fairest prices and make informed purchasing decisions.

[0465] Step 6:

[0466] Users make purchases based on the quoted price and then provide satisfaction and feedback via their devices. This feedback is sent to the server and used to adjust the parameters of the AI ​​model, contributing to improved accuracy in future pricing.

[0467] (Example 1)

[0468] 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."

[0469] In commercial data analysis, data redundancy and the presence of outliers present challenges that reduce analytical accuracy. Furthermore, accurately capturing consumer behavior patterns, predicting market trends, and dynamically setting appropriate product prices are difficult. It is also crucial to incorporate user feedback in a timely manner to improve the accuracy of predictive models. The development of systems that address these challenges is essential.

[0470] 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.

[0471] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting abnormal data; means for cleansing and analyzing the collected data using generative AI technology; and means for constructing a predictive model based on the analysis results and calculating the appropriate price of a product. This enables efficient processing of commercial data, calculation of appropriate prices based on consumer trends, and improvement of the accuracy of the predictive model by utilizing user feedback.

[0472] "Commercial data" refers to all data collected in connection with commercial activities, including transaction information, customer information, and sales history.

[0473] "Redundant data" refers to data that exists in a system or dataset that has the same or similar meaning but is duplicated.

[0474] "Anomalous data" refers to data that deviates from expected patterns or ranges, indicating errors or irregularities.

[0475] "Generative AI technology" refers to a type of artificial intelligence, specifically a technology used for data analysis and pattern recognition.

[0476] "Data cleansing" refers to the process of removing errors, formatting mistakes, redundancies, and other issues from a dataset to make the data accurate and consistent.

[0477] A "predictive model" refers to a mathematical or machine learning model built to predict future events or trends based on past data.

[0478] "Fair price" refers to a reasonable and fair price for a product, set considering the balance of supply and demand in the market.

[0479] "User feedback" refers to information collected from customers or end-users regarding product evaluations and areas for improvement.

[0480] The system according to the present invention aims to efficiently calculate the appropriate price of a product through the collection, cleansing, and analysis of commercial data, and the incorporation of user feedback. This system is configured as follows.

[0481] Data collection:

[0482] The server retrieves commercial data from terminals. Specifically, sales history and customer information are collected via POS systems and online sales platforms. Network interfaces and protocols are used for transferring this data. As a concrete example, the number of sales of a specific product on a given date is collected from the POS system using an API.

[0483] Data cleansing and analysis:

[0484] The server cleanses the collected data using Python scripts to remove duplicates and errors. Then, it analyzes market trends and consumption patterns using generative AI technology. TensorFlow and PyTorch are used as machine learning libraries in this process. A concrete example of analysis is deriving sales patterns for specific products during certain seasons using an AI model.

[0485] Calculating the fair price:

[0486] The server builds a predictive model based on the analysis results and calculates the appropriate price for the product. A demand forecasting algorithm is used in this process, and high-performance GPUs are utilized to increase calculation speed. Specifically, one example is adjusting the price of a particular product in the summer season in conjunction with weather data.

[0487] Presentation of results and incorporation of feedback:

[0488] The device displays the calculated fair price to the user. This display is presented in a visible format, such as a price label in an online shop or physical store. The device also functions as an interface for collecting user feedback. When a user submits their evaluation via a web form, the server uses this feedback to further improve the accuracy of the model.

[0489] As an example of a prompt, the AI ​​model is designed to function correctly by instructing it to "forecast demand based on this week's new product sales data and calculate an appropriate price."

[0490] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0491] Step 1: Data Collection

[0492] The server retrieves commercial data from terminals and external systems. Inputs include detailed transaction records from POS systems and online sales sites. The server receives this data via APIs and stores it in a database. The output is a comprehensive commercial dataset containing date, product ID, sales quantity, price information, and more.

[0493] Step 2: Data Cleansing

[0494] The server cleanses the collected data using a Python script. The input is the raw data collected in step 1. The server removes duplicate records and corrects invalid values ​​(e.g., negative prices or non-integer quantities) from this data. The output is a clean dataset formatted for analysis.

[0495] Step 3: Pattern Analysis

[0496] The server analyzes clean data using a generative AI model. The cleaned data processed in step 2 is used as input. The server uses libraries such as TensorFlow to analyze consumer behavior patterns and market trends. Specifically, it extracts purchase frequency by time of day from the data. The output is an analysis result showing market trends and consumer behavior patterns.

[0497] Step 4: Building a predictive model and calculating prices

[0498] The server builds a predictive model based on the analysis results and calculates the appropriate price for the product. The input is the analysis results from step 3. The server uses a high-performance GPU to execute a demand forecasting algorithm and calculate the appropriate price. Specifically, it takes weather data into consideration and adjusts the price of summer products. The output is multiple price scenarios calculated based on the demand forecast.

[0499] Step 5: Presentation of Results

[0500] The terminal displays the appropriate price to the user. The input is the price information calculated in step 4. The terminal displays this on the online store's product page or on the price tag in a physical store. The output is price information visually presented to the user.

[0501] Step 6: Gathering Feedback and Updating the Model

[0502] Users provide feedback on their purchase experience through their devices. Input consists of user ratings and comments. The device sends this information to a server, and a specific action to reflect this in the model is inputting into a satisfaction survey form. Output is updated data that contributes to improving the accuracy of the predictive model.

[0503] (Application Example 1)

[0504] 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."

[0505] Setting fair prices in commercial transactions is crucial for ensuring corporate profits and gaining consumer satisfaction. However, current systems suffer from the drawbacks of being susceptible to redundancy and outliers in commercial data, making it difficult to accurately analyze consumer purchasing behavior and market trends. Furthermore, the lack of real-time, personalized price recommendations means that the system fails to meet the individual needs of consumers.

[0506] 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.

[0507] In this invention, the server includes means for collecting commercial data, removing redundant data and correcting anomalous data, means for analyzing market trends and consumer purchasing behavior using generative AI, and means for calculating the appropriate price of a product using a predictive model. This makes it possible to propose products and prices suitable for consumers in real time, improving both corporate profits and consumer satisfaction.

[0508] "Commercial data" refers to information related to commercial transactions, including sales history, customer attributes, and transaction status.

[0509] "Deleting redundant data" refers to the act of removing duplicate or unnecessary information contained in commercial data.

[0510] "Correction of abnormal data" is the process of correcting errors and inconsistencies in input commercial data and converting it into accurate data.

[0511] "Generative AI" refers to algorithms that utilize artificial intelligence technology to automatically generate patterns and insights from big data.

[0512] "Market trends" refer to movements in the market over a certain period, such as fluctuations in demand and supply, price changes, and consumer behavior.

[0513] "Consumer purchasing behavior" refers to the series of actions and decision-making processes that consumers take when selecting and purchasing goods and services.

[0514] A "predictive model" is a mathematical model constructed to predict future trends and outcomes using past data and patterns.

[0515] A "fair price" is a price that maintains a balance between supply and demand, ensures the company's profits, and is also acceptable to consumers.

[0516] "User feedback" refers to the opinions, impressions, and evaluations that consumers and users provide regarding products and services.

[0517] "Real-time suggestions" means immediately presenting appropriate information and options based on the current situation.

[0518] The system that realizes this application consists of a server, a user terminal (such as a smartphone), and a generative AI model.

[0519] The server receives commercial data and stores and organizes it using a database management system (e.g., MySQL, PostgreSQL). This commercial data includes sales history, customer attributes, and transaction status. Data cleansing algorithms are used to remove redundant data and correct anomalous data. Machine learning frameworks such as TensorFlow and PyTorch are used as the generation AI model to analyze market trends and consumer purchasing behavior based on the cleansed data.

[0520] Based on the analysis results, the server builds a predictive model and calculates the appropriate price for the product. This price is designed to maximize both the company's profits and consumer satisfaction while considering the balance of supply and demand.

[0521] The user's device displays the calculated fair price and related information in a format that is easier for consumers to understand, in real time. For example, it may be notified as a personalized special offer on a smartphone. During this process, users can provide feedback on the displayed price and purchase experience, and this feedback is collected on the server and used to improve the accuracy of the predictive model.

[0522] As a concrete example, for users who prefer to buy cold beverages in the summer, analysis incorporating weather forecast data will send push notifications offering cold beverages at special prices on days when high temperatures are expected. This allows for timely suggestions tailored to individual consumer needs.

[0523] An example of a prompt is, "Consider the user's past purchase patterns and current market trends, and suggest a list of potential purchases for the next week along with their optimal prices." This allows the generative AI model to make specific suggestions and provide a personalized consumer experience.

[0524] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0525] Step 1:

[0526] The server receives data such as sales history, customer attributes, and transaction status through a commercial data collection system. Inputs are data from POS systems and online platforms, and output is a well-organized dataset of raw data. This dataset is stored in a database management system.

[0527] Step 2:

[0528] The server executes a data cleansing algorithm to remove redundant data and correct outliers from the input dataset. The input is a raw dataset, and after removing duplicate data and correcting errors, the output is a clean, purified dataset.

[0529] Step 3:

[0530] The server uses a generative AI model to analyze market trends and consumer purchasing behavior. The input is a cleaned dataset, and the output is the analysis results of consumer trends and purchasing patterns. This analysis uses prompts to extract important patterns of consumer behavior.

[0531] Step 4:

[0532] The server builds a predictive model based on the analysis results and calculates the appropriate price for each product. The input is consumer trends and purchasing patterns, and based on this, it uses a demand forecasting algorithm to determine the optimal pricing strategy. The output is the appropriate price for each product.

[0533] Step 5:

[0534] The server sends the calculated fair price to the user's terminal. The terminal prepares to present the received price information to the consumer. At this stage, a personalized price notification is generated as output, which is displayed on the terminal.

[0535] Step 6:

[0536] Users submit feedback regarding the offered price and purchase experience through their device. The input is the user's feedback, which the device collects and sends to the server. The output is the feedback data received by the server.

[0537] Step 7:

[0538] The server analyzes the received feedback and updates the predictive model. This process uses the feedback data as input and employs optimization algorithms to improve the accuracy of the generated AI model. The output is the improved predictive model.

[0539] 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.

[0540] This invention is a system that combines the collection and analysis of commercial data with an emotion engine that recognizes user emotions. This system improves data quality by collecting commercial data, removing redundant data, and correcting anomalous data. The collected data is analyzed using generative AI to gain a detailed understanding of market trends and consumer purchasing behavior.

[0541] A distinctive feature of this invention is its ability to analyze user emotional data using an emotion engine. Specifically, it can analyze the facial expressions and behaviors that users exhibit during the product purchasing process and product recommendations via their devices, and recognize emotions such as positive or negative. For example, by analyzing in real time what emotions a user is experiencing during the online store purchase process, it is possible to provide more personalized recommendations.

[0542] Furthermore, this sentiment data is incorporated into the generative AI's predictive model and used as a crucial element in calculating the appropriate price for a product. This allows pricing to be optimized not only by considering market and customer trends, but also by taking into account the user's purchasing experience and emotional tendencies. For example, if negative emotions towards a high-priced product are detected, the system can be adjusted to offer a coupon to mitigate those emotions.

[0543] As a result, users receive real-time adjusted fair pricing and product recommendations, and retailers can maximize profits while improving customer satisfaction. By integrating data analysis and emotion recognition technology, this invention functions as a more sophisticated and effective sales strategy support system.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The terminal collects commercial data from retailers' POS systems and online platforms. This data includes sales history, inventory levels, and customer purchasing patterns, and is transmitted to the server via a secure protocol.

[0547] Step 2:

[0548] The server cleanses the received commercial data. It removes redundant data and corrects anomalous data, and stores the data in a database to ensure data integrity. For example, it identifies and deletes duplicate transaction information.

[0549] Step 3:

[0550] The server uses generated AI with well-organized data to analyze market trends and consumer purchasing behavior. This analysis reveals consumer purchasing trends for specific products or catalogs. For example, it reveals that discounted items sell particularly well on weekday evenings.

[0551] Step 4:

[0552] The device collects emotional data through the user's facial expressions and voice input. This emotion engine identifies emotions such as positive and negative in real time based on changes in the user's facial expressions and voice tone shown through the webcam and microphone.

[0553] Step 5:

[0554] The server analyzes emotional data obtained from the emotion engine and incorporates it into the generative AI's predictive model. This integration allows for the quantification of how a user's emotional state affects price elasticity and product recommendations, for example, by suggesting alternative options if a particular product is causing stress to the user.

[0555] Step 6:

[0556] The server calculates the appropriate price for a product based on the analysis results and sends it to the terminal. It then allows users to access new pricing information and promotional suggestions. For example, to increase purchasing intent, it automatically calculates and displays discounts based on the purchase amount.

[0557] Step 7:

[0558] Users review the quoted price and decide to purchase. Post-purchase feedback and satisfaction surveys are provided via the device, and this data is sent back to the server to further improve the AI ​​model.

[0559] In this way, the system integrates user emotions with commercial data to improve the quality of price suggestions and product recommendations. This allows retailers to efficiently increase profits and consumers to enjoy the most satisfying shopping experience.

[0560] (Example 2)

[0561] 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."

[0562] In commercial activities, providing customers with product recommendations and pricing based on appropriate information is crucial. However, traditional methods rely solely on market trends and consumer behavior, making it difficult to consider the emotions of individual customers when making product recommendations. Furthermore, it is difficult to analyze emotion-based feedback in real time and make immediate price adjustments. This creates a challenge in achieving both improved customer satisfaction and maximized profits for retailers.

[0563] 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.

[0564] In this invention, the server includes means for collecting commercial information, deleting redundant information, and correcting anomalous information; means for analyzing emotional states obtained from users; and means for calculating appropriate prices based on product characteristics using a predictive model. This makes it possible to propose products and set prices that take into account the emotions of individual customers.

[0565] "Commercial information" refers to all data related to market activities, including product information, customer reviews, and sales data.

[0566] "Redundant information" refers to repetitive or unnecessary parts of data, including information and noise that have little value for analysis.

[0567] "Aberrant information" refers to data that contains values ​​or errors that deviate from the normal pattern.

[0568] "Generative artificial intelligence" refers to artificial intelligence technology that has natural language processing and analysis capabilities based on large datasets, and uses machine learning models and deep learning techniques.

[0569] "Emotion analysis methods" refer to technologies that evaluate a user's emotional state based on their facial expressions and behavior, and recognize emotions such as positive or negative.

[0570] A "predictive model" refers to a mathematical model used to predict future trends based on past data, employing regression analysis and machine learning algorithms.

[0571] "Fair price" refers to a reasonable product price calculated based on market value, customer demand, and the pricing of competitors.

[0572] "Emotional feedback" refers to information collected from users' emotional responses and opinions, which is used as an evaluation of products and services.

[0573] A "pricing scenario" refers to a pricing strategy under different conditions, and includes methods for considering multiple pricing options that take into account customer price elasticity and emotional tendencies.

[0574] This invention is a system that combines the collection and analysis of commercial information with sentiment analysis technology that recognizes user emotions. This system is designed to efficiently support commercial activities. Specifically, it is configured as follows:

[0575] The server collects commercial information via the internet. During collection, data is obtained from numerous sources, and a web crawler is used to improve efficiency. The Python Scrapy library can be used to implement the web crawler.

[0576] Next, the device activates input devices such as a camera and microphone to collect the user's emotional state in real time. For emotion analysis, a common API is used; for example, the Emotion API might be utilized. This analyzes the user's emotional state as positive or negative.

[0577] The collected commercial information is preprocessed on the server. Redundant information is removed from the database using SQL queries, and anomalous information is corrected using mean values ​​or statistical methods. Missing values ​​are also imputed using the KNN method.

[0578] The server then feeds this data into a generative AI model to analyze market trends and consumer purchasing behavior. Deep learning frameworks such as TensorFlow are used to build the generative AI model. An example of a prompt message that might be input at this time is: "Generate personalized recommendations based on the sentiment data the user displayed while browsing products in the online store. If the sentiment is negative, include suggestions for mitigation."

[0579] Furthermore, the server uses a predictive model based on sentiment analysis results to calculate the appropriate price. This makes it possible to provide users with optimized product pricing and recommendations. Users receive this real-time, adjusted information and make purchasing decisions. This allows retailers to improve customer satisfaction and maximize profits.

[0580] Thus, the present invention functions as a system that supports optimal sales strategies by integrating commercial data analysis and sentiment analysis technology.

[0581] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0582] Step 1:

[0583] The server collects commercial information from the internet. It uses a web crawler to retrieve product information and customer reviews from various data sources. The input is commercial information from the internet, and the output is a raw dataset. Specifically, it uses the Python Scrapy library to perform web crawling and filters the data based on predefined conditions.

[0584] Step 2:

[0585] The server performs preprocessing on the collected raw dataset. The input is the raw dataset obtained in step 1, and the output is a clean dataset. Redundant information is removed using SQL queries, and anomalous information is corrected using the mean. In addition, if there are missing values, imputation is performed using the KNN method. This generates a high-quality dataset suitable for subsequent analysis.

[0586] Step 3:

[0587] The device collects the user's emotional state in real time. Input is the user's facial expressions and voice captured by the camera and microphone, and output is emotional data. The collected data is sent to an emotion recognition service such as the Emotion API, from which an emotional label (positive, negative, etc.) is obtained. This process continues continuously while the user is browsing or purchasing products.

[0588] Step 4:

[0589] The server inputs a clean dataset and user sentiment data into a generating AI model for analysis. The input is the clean dataset from step 2 and the sentiment data from step 3, and the output is the analysis results. A TensorFlow deep learning model is used to predict market trends and consumer purchasing behavior. Specifically, it provides the generating AI model with prompt sentences that define the purpose of the analysis.

[0590] Step 5:

[0591] The server uses a predictive model based on the analysis results to calculate an appropriate price based on product characteristics. The input is the analysis results from step 4, and the output is the appropriate price and product recommendations. The calculated results are provided to the user as optimized product information via email or in-app notifications.

[0592] Step 6:

[0593] Users make purchasing decisions based on information provided by the server. The input is the appropriate price and product suggestions provided in step 5, and the output is the purchase selection. This selection information is also fed back into the system and used to adjust and improve the model. Through this process, the customer experience is optimized, and retailers can maximize their profits.

[0594] (Application Example 2)

[0595] 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."

[0596] As consumer purchasing behavior diversifies and online transactions become dominant, understanding consumer emotions and implementing optimal pricing strategies and product recommendations based on them becomes challenging. Furthermore, uniform pricing is insufficient to adequately improve consumer satisfaction, and personalized experiences tailored to individual consumers are required.

[0597] 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.

[0598] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting anomalous data, means for analyzing market trends and consumer purchasing behavior using generating AI, and means for recognizing user emotions. This enables optimal product recommendations and price adjustments based on consumer emotions.

[0599] "Commercial data" refers to all data related to the sale and transaction of goods, and is collected as a comprehensive dataset.

[0600] "Redundant data" refers to data that is duplicated or unnecessary, and which reduces the efficiency of a system.

[0601] "Aberrant data" refers to data within a dataset that deviates from the normal range and may impair the accuracy of predictions and analyses.

[0602] "Generative AI" refers to artificial intelligence technology that learns from data and generates new information and insights.

[0603] "Market trends" refer to changes and tendencies that indicate the current economic environment and consumer purchasing patterns.

[0604] "Consumer purchasing behavior" refers to the series of actions taken by consumers in the process of selecting and purchasing a product.

[0605] A "predictive model" refers to a mathematical model used to estimate future trends and outcomes based on past data.

[0606] "Fair price" refers to the optimal price range determined based on market and consumer conditions.

[0607] "User sentiment" refers to the psychological reactions and emotional states that consumers exhibit when browsing or purchasing products.

[0608] "Optimizing product recommendations" refers to the process of selecting and suggesting products that best match the preferences and emotions of individual consumers.

[0609] Modes for carrying out the invention

[0610] The system realizing this invention is designed to support consumers' actions when they browse, consider, and purchase products on online platforms. The server has the function of collecting commercial data and automatically removing redundant data and correcting anomalous data. After improving the quality of the data, it uses generative AI to analyze market trends and consumer purchasing behavior. The server recognizes emotions from camera images and audio data acquired through the user's terminal and optimizes product recommendations based on that data.

[0611] Specifically, the server first processes the video data sent from the user's terminal using an image recognition library (e.g., OpenCV). During this process, it analyzes the user's facial expressions while they are browsing products and determines whether they are feeling positive or negative emotions. Similarly, audio data collected through the microphone is processed using a speech analysis library (e.g., Google Cloud Speech-to-Text) to recognize emotions from the tone and content of the voice.

[0612] The server analyzes the acquired emotional data using a generative AI model (e.g., built with TensorFlow) and dynamically suggests the most suitable products and services for the user. The user's past purchase history and market data are also considered during this process. Furthermore, a predictive model is used to calculate an appropriate price for the selected product to determine if it is suitable for the user.

[0613] For example, when a user is purchasing a new electronic device, if their facial expression shows a negative reaction, the system will immediately adjust the price or offer a coupon to improve the purchase experience. A concrete example of a prompt message might be: "The user expressed negative feelings about the new laptop due to the price. What action should be taken to alleviate this user's feelings?"

[0614] This allows users to receive optimized product recommendations and price adjustments in real time based on their emotions and purchase history, resulting in a more satisfying shopping experience. Retailers can also improve revenue by optimizing their approach to individual consumers.

[0615] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0616] Step 1:

[0617] The server receives commercial data sent from the user's terminal. This commercial data includes product browsing history and purchase history. The server removes redundant data and corrects anomalous data to generate a clean dataset. This process removes data noise and improves the accuracy of the analysis.

[0618] Step 2:

[0619] The server uses a generative AI model to analyze the clean dataset obtained in Step 1. It receives data including market trends and consumer purchasing behavior as input, and the AI ​​model uses this to output detailed consumer profiles and market forecasts. During this process, the server calculates consumption trends and demand forecasts using the generative AI model.

[0620] Step 3:

[0621] The device uses the user's camera and microphone to collect data on the user's facial expressions and voice in real time. It captures the user's facial expressions and tone of voice while they are browsing products and sends this data to the server. The input data consists of facial images and audio data, and the output is data that is ready to be classified as emotion.

[0622] Step 4:

[0623] The server analyzes the facial image and audio data received in step 3. It uses an image recognition library (e.g., OpenCV) and an audio analysis library (e.g., Google Cloud Speech-to-Text) to recognize emotions. It detects emotions such as positive or negative from the input image and audio and outputs this as emotion data.

[0624] Step 5:

[0625] The server passes the emotional data obtained in step 4 to the generating AI model to make optimal product recommendations. Combining the emotional data with consumer profiles, it dynamically makes product recommendations and adjusts prices, which are then sent to the user. Based on the emotional data input, it outputs a personalized product list.

[0626] Step 6:

[0627] The user reviews product suggestions sent from the server on their device. Based on the suggested information, the user can then decide whether to purchase. The system retrieves the user's final opinion and feedback and sends it back to the server.

[0628] Step 7:

[0629] The server analyzes user feedback and updates the predictive model. Based on the acquired feedback, it processes the data to further refine the appropriate price and product recommendations for the product. This results in output that improves the accuracy of the predictive model from the input feedback.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] [Fourth Embodiment]

[0634] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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".

[0647] The system according to the present invention aims to collect commercial data, remove redundant data, and correct anomalous data. This system utilizes generative AI technology to analyze market trends and consumer purchasing behavior, and uses a predictive model to calculate the appropriate price of a product. Furthermore, to ensure that the calculated price maximizes both corporate profits and consumer satisfaction, it effectively incorporates user feedback to improve the accuracy of the model.

[0648] Data collection phase

[0649] The server receives commercial data from terminals. This data is collected from retailers' POS systems and online platforms and includes daily transaction data, customer attributes, and sales history. A specific example is the daily sales information obtained from supermarket checkouts.

[0650] Data Analysis Phase

[0651] The server cleanses the collected data, removing duplicates and errors. The generating AI algorithm then analyzes this cleansed data to identify patterns and interpret consumer trends. For example, it can determine the lunch patterns of office workers who work regular hours.

[0652] Price calculation phase

[0653] The server uses the analysis results to build a predictive model and calculate an appropriate price. Based on supply and demand forecasts, this price calculation is set considering the product's best-selling items and inventory levels. For example, the price of a limited-edition summer product is adjusted to account for the increased sales on hot days.

[0654] Results presentation phase

[0655] The terminal displays the calculated fair price to the user. Consumers and retailers can verify this price on product labels or online shops. For example, it might be displayed as "This Week's Special" in the online store title and sold at the fair price.

[0656] Feedback collection phase

[0657] Users provide feedback on the presented price and purchase experience through their device. This feedback is sent to a server and used to further improve the accuracy of the predictive model. For example, the results of post-purchase satisfaction surveys are reflected in the model and used to help with future pricing.

[0658] As described above, this system maximizes corporate profits and improves consumer satisfaction through the efficient use of commercial data and the calculation of appropriate prices using generated AI.

[0659] The following describes the processing flow.

[0660] Step 1:

[0661] The terminal collects commercial data from retailers' POS systems and online platforms. This data includes sales history, inventory status, and information about customer purchasing behavior, and is transmitted to a server via secure communication.

[0662] Step 2:

[0663] The server cleanses the received commercial data. During the cleansing process, duplicate and incomplete data is removed, and data is supplemented as needed. For example, if sales data contains incorrect figures, it is converted to the correct format.

[0664] Step 3:

[0665] The server analyzes the cleansed data and applies generative AI algorithms to understand market trends and consumer purchasing behavior. This analysis identifies when and how consumers tend to purchase specific products. For example, it may reveal that sales are concentrated on certain days or time slots.

[0666] Step 4:

[0667] Based on the analysis results, the server uses a predictive model to calculate the appropriate price for the product. The predictive model considers demand forecasts and price elasticity to identify the point at which maximum profit can be obtained through pricing. For example, it can calculate the optimal discount price during a sale period.

[0668] Step 5:

[0669] The server sends the calculated fair price to the terminal. The terminal then displays the fair price on the store's price display system or online platform for the user to verify. This allows consumers to see the latest and fairest prices and make informed purchasing decisions.

[0670] Step 6:

[0671] Users make purchases based on the quoted price and then provide satisfaction and feedback via their devices. This feedback is sent to the server and used to adjust the parameters of the AI ​​model, contributing to improved accuracy in future pricing.

[0672] (Example 1)

[0673] 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".

[0674] In commercial data analysis, data redundancy and the presence of outliers present challenges that reduce analytical accuracy. Furthermore, accurately capturing consumer behavior patterns, predicting market trends, and dynamically setting appropriate product prices are difficult. It is also crucial to incorporate user feedback in a timely manner to improve the accuracy of predictive models. The development of systems that address these challenges is essential.

[0675] 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.

[0676] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting abnormal data; means for cleansing and analyzing the collected data using generative AI technology; and means for constructing a predictive model based on the analysis results and calculating the appropriate price of a product. This enables efficient processing of commercial data, calculation of appropriate prices based on consumer trends, and improvement of the accuracy of the predictive model by utilizing user feedback.

[0677] "Commercial data" refers to all data collected in connection with commercial activities, including transaction information, customer information, and sales history.

[0678] "Redundant data" refers to data that exists in a system or dataset that has the same or similar meaning but is duplicated.

[0679] "Anomalous data" refers to data that deviates from expected patterns or ranges, indicating errors or irregularities.

[0680] "Generative AI technology" refers to a type of artificial intelligence, specifically a technology used for data analysis and pattern recognition.

[0681] "Data cleansing" refers to the process of removing errors, formatting mistakes, redundancies, and other issues from a dataset to make the data accurate and consistent.

[0682] A "predictive model" refers to a mathematical or machine learning model built to predict future events or trends based on past data.

[0683] "Fair price" refers to a reasonable and fair price for a product, set considering the balance of supply and demand in the market.

[0684] "User feedback" refers to information collected from customers or end-users regarding product evaluations and areas for improvement.

[0685] The system according to the present invention aims to efficiently calculate the appropriate price of a product through the collection, cleansing, and analysis of commercial data, and the incorporation of user feedback. This system is configured as follows.

[0686] Data collection:

[0687] The server retrieves commercial data from terminals. Specifically, sales history and customer information are collected via POS systems and online sales platforms. Network interfaces and protocols are used for transferring this data. As a concrete example, the number of sales of a specific product on a given date is collected from the POS system using an API.

[0688] Data cleansing and analysis:

[0689] The server cleanses the collected data using Python scripts to remove duplicates and errors. Then, it analyzes market trends and consumption patterns using generative AI technology. TensorFlow and PyTorch are used as machine learning libraries in this process. A concrete example of analysis is deriving sales patterns for specific products during certain seasons using an AI model.

[0690] Calculating the fair price:

[0691] The server builds a predictive model based on the analysis results and calculates the appropriate price for the product. A demand forecasting algorithm is used in this process, and high-performance GPUs are utilized to increase calculation speed. Specifically, one example is adjusting the price of a particular product in the summer season in conjunction with weather data.

[0692] Presentation of results and incorporation of feedback:

[0693] The device displays the calculated fair price to the user. This display is presented in a visible format, such as a price label in an online shop or physical store. The device also functions as an interface for collecting user feedback. When a user submits their evaluation via a web form, the server uses this feedback to further improve the accuracy of the model.

[0694] As an example of a prompt, the AI ​​model is designed to function correctly by instructing it to "forecast demand based on this week's new product sales data and calculate an appropriate price."

[0695] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0696] Step 1: Data Collection

[0697] The server retrieves commercial data from terminals and external systems. Inputs include detailed transaction records from POS systems and online sales sites. The server receives this data via APIs and stores it in a database. The output is a comprehensive commercial dataset containing date, product ID, sales quantity, price information, and more.

[0698] Step 2: Data Cleansing

[0699] The server cleanses the collected data using a Python script. The input is the raw data collected in step 1. The server removes duplicate records and corrects invalid values ​​(e.g., negative prices or non-integer quantities) from this data. The output is a clean dataset formatted for analysis.

[0700] Step 3: Pattern Analysis

[0701] The server analyzes clean data using a generative AI model. The cleaned data processed in step 2 is used as input. The server uses libraries such as TensorFlow to analyze consumer behavior patterns and market trends. Specifically, it extracts purchase frequency by time of day from the data. The output is an analysis result showing market trends and consumer behavior patterns.

[0702] Step 4: Building a predictive model and calculating prices

[0703] The server builds a predictive model based on the analysis results and calculates the appropriate price for the product. The input is the analysis results from step 3. The server uses a high-performance GPU to execute a demand forecasting algorithm and calculate the appropriate price. Specifically, it takes weather data into consideration and adjusts the price of summer products. The output is multiple price scenarios calculated based on the demand forecast.

[0704] Step 5: Presentation of Results

[0705] The terminal displays the appropriate price to the user. The input is the price information calculated in step 4. The terminal displays this on the online store's product page or on the price tag in a physical store. The output is price information visually presented to the user.

[0706] Step 6: Gathering Feedback and Updating the Model

[0707] Users provide feedback on their purchase experience through their devices. Input consists of user ratings and comments. The device sends this information to a server, and a specific action to reflect this in the model is inputting into a satisfaction survey form. Output is updated data that contributes to improving the accuracy of the predictive model.

[0708] (Application Example 1)

[0709] 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".

[0710] Setting fair prices in commercial transactions is crucial for ensuring corporate profits and gaining consumer satisfaction. However, current systems suffer from the drawbacks of being susceptible to redundancy and outliers in commercial data, making it difficult to accurately analyze consumer purchasing behavior and market trends. Furthermore, the lack of real-time, personalized price recommendations means that the system fails to meet the individual needs of consumers.

[0711] 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.

[0712] In this invention, the server includes means for collecting commercial data, removing redundant data and correcting anomalous data, means for analyzing market trends and consumer purchasing behavior using generative AI, and means for calculating the appropriate price of a product using a predictive model. This makes it possible to propose products and prices suitable for consumers in real time, improving both corporate profits and consumer satisfaction.

[0713] "Commercial data" refers to information related to commercial transactions, including sales history, customer attributes, and transaction status.

[0714] "Deleting redundant data" refers to the act of removing duplicate or unnecessary information contained in commercial data.

[0715] "Correction of abnormal data" is the process of correcting errors and inconsistencies in input commercial data and converting it into accurate data.

[0716] "Generative AI" refers to algorithms that utilize artificial intelligence technology to automatically generate patterns and insights from big data.

[0717] "Market trends" refer to movements in the market over a certain period, such as fluctuations in demand and supply, price changes, and consumer behavior.

[0718] "Consumer purchasing behavior" refers to the series of actions and decision-making processes that consumers take when selecting and purchasing goods and services.

[0719] A "predictive model" is a mathematical model constructed to predict future trends and outcomes using past data and patterns.

[0720] A "fair price" is a price that maintains a balance between supply and demand, ensures the company's profits, and is also acceptable to consumers.

[0721] "User feedback" refers to the opinions, impressions, and evaluations that consumers and users provide regarding products and services.

[0722] "Real-time suggestions" means immediately presenting appropriate information and options based on the current situation.

[0723] The system that realizes this application consists of a server, a user terminal (such as a smartphone), and a generative AI model.

[0724] The server receives commercial data and stores and organizes it using a database management system (e.g., MySQL, PostgreSQL). This commercial data includes sales history, customer attributes, and transaction status. Data cleansing algorithms are used to remove redundant data and correct anomalous data. Machine learning frameworks such as TensorFlow and PyTorch are used as the generation AI model to analyze market trends and consumer purchasing behavior based on the cleansed data.

[0725] Based on the analysis results, the server builds a predictive model and calculates the appropriate price for the product. This price is designed to maximize both the company's profits and consumer satisfaction while considering the balance of supply and demand.

[0726] The user's device displays the calculated fair price and related information in a format that is easier for consumers to understand, in real time. For example, it may be notified as a personalized special offer on a smartphone. During this process, users can provide feedback on the displayed price and purchase experience, and this feedback is collected on the server and used to improve the accuracy of the predictive model.

[0727] As a concrete example, for users who prefer to buy cold beverages in the summer, analysis incorporating weather forecast data will send push notifications offering cold beverages at special prices on days when high temperatures are expected. This allows for timely suggestions tailored to individual consumer needs.

[0728] An example of a prompt is, "Consider the user's past purchase patterns and current market trends, and suggest a list of potential purchases for the next week along with their optimal prices." This allows the generative AI model to make specific suggestions and provide a personalized consumer experience.

[0729] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0730] Step 1:

[0731] The server receives data such as sales history, customer attributes, and transaction status through a commercial data collection system. Inputs are data from POS systems and online platforms, and output is a well-organized dataset of raw data. This dataset is stored in a database management system.

[0732] Step 2:

[0733] The server executes a data cleansing algorithm to remove redundant data and correct outliers from the input dataset. The input is a raw dataset, and after removing duplicate data and correcting errors, the output is a clean, purified dataset.

[0734] Step 3:

[0735] The server uses a generative AI model to analyze market trends and consumer purchasing behavior. The input is a cleaned dataset, and the output is the analysis results of consumer trends and purchasing patterns. This analysis uses prompts to extract important patterns of consumer behavior.

[0736] Step 4:

[0737] The server builds a predictive model based on the analysis results and calculates the appropriate price for each product. The input is consumer trends and purchasing patterns, and based on this, it uses a demand forecasting algorithm to determine the optimal pricing strategy. The output is the appropriate price for each product.

[0738] Step 5:

[0739] The server sends the calculated fair price to the user's terminal. The terminal prepares to present the received price information to the consumer. At this stage, a personalized price notification is generated as output, which is displayed on the terminal.

[0740] Step 6:

[0741] Users submit feedback regarding the offered price and purchase experience through their device. The input is the user's feedback, which the device collects and sends to the server. The output is the feedback data received by the server.

[0742] Step 7:

[0743] The server analyzes the received feedback and updates the predictive model. This process uses the feedback data as input and employs optimization algorithms to improve the accuracy of the generated AI model. The output is the improved predictive model.

[0744] 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.

[0745] This invention is a system that combines the collection and analysis of commercial data with an emotion engine that recognizes user emotions. This system improves data quality by collecting commercial data, removing redundant data, and correcting anomalous data. The collected data is analyzed using generative AI to gain a detailed understanding of market trends and consumer purchasing behavior.

[0746] A distinctive feature of this invention is its ability to analyze user emotional data using an emotion engine. Specifically, it can analyze the facial expressions and behaviors that users exhibit during the product purchasing process and product recommendations via their devices, and recognize emotions such as positive or negative. For example, by analyzing in real time what emotions a user is experiencing during the online store purchase process, it is possible to provide more personalized recommendations.

[0747] Furthermore, this sentiment data is incorporated into the generative AI's predictive model and used as a crucial element in calculating the appropriate price for a product. This allows pricing to be optimized not only by considering market and customer trends, but also by taking into account the user's purchasing experience and emotional tendencies. For example, if negative emotions towards a high-priced product are detected, the system can be adjusted to offer a coupon to mitigate those emotions.

[0748] As a result, users receive real-time adjusted fair pricing and product recommendations, and retailers can maximize profits while improving customer satisfaction. By integrating data analysis and emotion recognition technology, this invention functions as a more sophisticated and effective sales strategy support system.

[0749] The following describes the processing flow.

[0750] Step 1:

[0751] The terminal collects commercial data from retailers' POS systems and online platforms. This data includes sales history, inventory levels, and customer purchasing patterns, and is transmitted to the server via a secure protocol.

[0752] Step 2:

[0753] The server cleanses the received commercial data. It removes redundant data and corrects anomalous data, and stores the data in a database to ensure data integrity. For example, it identifies and deletes duplicate transaction information.

[0754] Step 3:

[0755] The server uses generated AI with well-organized data to analyze market trends and consumer purchasing behavior. This analysis reveals consumer purchasing trends for specific products or catalogs. For example, it reveals that discounted items sell particularly well on weekday evenings.

[0756] Step 4:

[0757] The device collects emotional data through the user's facial expressions and voice input. This emotion engine identifies emotions such as positive and negative in real time based on changes in the user's facial expressions and voice tone shown through the webcam and microphone.

[0758] Step 5:

[0759] The server analyzes emotional data obtained from the emotion engine and incorporates it into the generative AI's predictive model. This integration allows for the quantification of how a user's emotional state affects price elasticity and product recommendations, for example, by suggesting alternative options if a particular product is causing stress to the user.

[0760] Step 6:

[0761] The server calculates the appropriate price for a product based on the analysis results and sends it to the terminal. It then allows users to access new pricing information and promotional suggestions. For example, to increase purchasing intent, it automatically calculates and displays discounts based on the purchase amount.

[0762] Step 7:

[0763] Users review the quoted price and decide to purchase. Post-purchase feedback and satisfaction surveys are provided via the device, and this data is sent back to the server to further improve the AI ​​model.

[0764] In this way, the system integrates user emotions with commercial data to improve the quality of price suggestions and product recommendations. This allows retailers to efficiently increase profits and consumers to enjoy the most satisfying shopping experience.

[0765] (Example 2)

[0766] 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".

[0767] In commercial activities, providing customers with product recommendations and pricing based on appropriate information is crucial. However, traditional methods rely solely on market trends and consumer behavior, making it difficult to consider the emotions of individual customers when making product recommendations. Furthermore, it is difficult to analyze emotion-based feedback in real time and make immediate price adjustments. This creates a challenge in achieving both improved customer satisfaction and maximized profits for retailers.

[0768] 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.

[0769] In this invention, the server includes means for collecting commercial information, deleting redundant information, and correcting anomalous information; means for analyzing emotional states obtained from users; and means for calculating appropriate prices based on product characteristics using a predictive model. This makes it possible to propose products and set prices that take into account the emotions of individual customers.

[0770] "Commercial information" refers to all data related to market activities, including product information, customer reviews, and sales data.

[0771] "Redundant information" refers to repetitive or unnecessary parts of data, including information and noise that have little value for analysis.

[0772] "Aberrant information" refers to data that contains values ​​or errors that deviate from the normal pattern.

[0773] "Generative artificial intelligence" refers to artificial intelligence technology that has natural language processing and analysis capabilities based on large datasets, and uses machine learning models and deep learning techniques.

[0774] "Emotion analysis methods" refer to technologies that evaluate a user's emotional state based on their facial expressions and behavior, and recognize emotions such as positive or negative.

[0775] A "predictive model" refers to a mathematical model used to predict future trends based on past data, employing regression analysis and machine learning algorithms.

[0776] "Fair price" refers to a reasonable product price calculated based on market value, customer demand, and the pricing of competitors.

[0777] "Emotional feedback" refers to information collected from users' emotional responses and opinions, which is used as an evaluation of products and services.

[0778] A "pricing scenario" refers to a pricing strategy under different conditions, and includes methods for considering multiple pricing options that take into account customer price elasticity and emotional tendencies.

[0779] This invention is a system that combines the collection and analysis of commercial information with sentiment analysis technology that recognizes user emotions. This system is designed to efficiently support commercial activities. Specifically, it is configured as follows:

[0780] The server collects commercial information via the internet. During collection, data is obtained from numerous sources, and a web crawler is used to improve efficiency. The Python Scrapy library can be used to implement the web crawler.

[0781] Next, the device activates input devices such as a camera and microphone to collect the user's emotional state in real time. For emotion analysis, a common API is used; for example, the Emotion API might be utilized. This analyzes the user's emotional state as positive or negative.

[0782] The collected commercial information is preprocessed on the server. Redundant information is removed from the database using SQL queries, and anomalous information is corrected using mean values ​​or statistical methods. Missing values ​​are also imputed using the KNN method.

[0783] The server then feeds this data into a generative AI model to analyze market trends and consumer purchasing behavior. Deep learning frameworks such as TensorFlow are used to build the generative AI model. An example of a prompt message that might be input at this time is: "Generate personalized recommendations based on the sentiment data the user displayed while browsing products in the online store. If the sentiment is negative, include suggestions for mitigation."

[0784] Furthermore, the server uses a predictive model based on sentiment analysis results to calculate the appropriate price. This makes it possible to provide users with optimized product pricing and recommendations. Users receive this real-time, adjusted information and make purchasing decisions. This allows retailers to improve customer satisfaction and maximize profits.

[0785] Thus, the present invention functions as a system that supports optimal sales strategies by integrating commercial data analysis and sentiment analysis technology.

[0786] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0787] Step 1:

[0788] The server collects commercial information from the internet. It uses a web crawler to retrieve product information and customer reviews from various data sources. The input is commercial information from the internet, and the output is a raw dataset. Specifically, it uses the Python Scrapy library to perform web crawling and filters the data based on predefined conditions.

[0789] Step 2:

[0790] The server performs preprocessing on the collected raw dataset. The input is the raw dataset obtained in step 1, and the output is a clean dataset. Redundant information is removed using SQL queries, and anomalous information is corrected using the mean. In addition, if there are missing values, imputation is performed using the KNN method. This generates a high-quality dataset suitable for subsequent analysis.

[0791] Step 3:

[0792] The device collects the user's emotional state in real time. Input is the user's facial expressions and voice captured by the camera and microphone, and output is emotional data. The collected data is sent to an emotion recognition service such as the Emotion API, from which an emotional label (positive, negative, etc.) is obtained. This process continues continuously while the user is browsing or purchasing products.

[0793] Step 4:

[0794] The server inputs a clean dataset and user sentiment data into a generating AI model for analysis. The input is the clean dataset from step 2 and the sentiment data from step 3, and the output is the analysis results. A TensorFlow deep learning model is used to predict market trends and consumer purchasing behavior. Specifically, it provides the generating AI model with prompt sentences that define the purpose of the analysis.

[0795] Step 5:

[0796] The server uses a predictive model based on the analysis results to calculate an appropriate price based on product characteristics. The input is the analysis results from step 4, and the output is the appropriate price and product recommendations. The calculated results are provided to the user as optimized product information via email or in-app notifications.

[0797] Step 6:

[0798] Users make purchasing decisions based on information provided by the server. The input is the appropriate price and product suggestions provided in step 5, and the output is the purchase selection. This selection information is also fed back into the system and used to adjust and improve the model. Through this process, the customer experience is optimized, and retailers can maximize their profits.

[0799] (Application Example 2)

[0800] 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".

[0801] As consumer purchasing behavior diversifies and online transactions become dominant, understanding consumer emotions and implementing optimal pricing strategies and product recommendations based on them becomes challenging. Furthermore, uniform pricing is insufficient to adequately improve consumer satisfaction, and personalized experiences tailored to individual consumers are required.

[0802] 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.

[0803] In this invention, the server includes means for collecting commercial data, deleting redundant data and correcting anomalous data, means for analyzing market trends and consumer purchasing behavior using generating AI, and means for recognizing user emotions. This enables optimal product recommendations and price adjustments based on consumer emotions.

[0804] "Commercial data" refers to all data related to the sale and transaction of goods, and is collected as a comprehensive dataset.

[0805] "Redundant data" refers to data that is duplicated or unnecessary, and which reduces the efficiency of a system.

[0806] "Aberrant data" refers to data within a dataset that deviates from the normal range and may impair the accuracy of predictions and analyses.

[0807] "Generative AI" refers to artificial intelligence technology that learns from data and generates new information and insights.

[0808] "Market trends" refer to changes and tendencies that indicate the current economic environment and consumer purchasing patterns.

[0809] "Consumer purchasing behavior" refers to the series of actions taken by consumers in the process of selecting and purchasing a product.

[0810] A "predictive model" refers to a mathematical model used to estimate future trends and outcomes based on past data.

[0811] "Fair price" refers to the optimal price range determined based on market and consumer conditions.

[0812] "User sentiment" refers to the psychological reactions and emotional states that consumers exhibit when browsing or purchasing products.

[0813] "Optimizing product recommendations" refers to the process of selecting and suggesting products that best match the preferences and emotions of individual consumers.

[0814] Modes for carrying out the invention

[0815] The system realizing this invention is designed to support consumers' actions when they browse, consider, and purchase products on online platforms. The server has the function of collecting commercial data and automatically removing redundant data and correcting anomalous data. After improving the quality of the data, it uses generative AI to analyze market trends and consumer purchasing behavior. The server recognizes emotions from camera images and audio data acquired through the user's terminal and optimizes product recommendations based on that data.

[0816] Specifically, the server first processes the video data sent from the user's terminal using an image recognition library (e.g., OpenCV). During this process, it analyzes the user's facial expressions while they are browsing products and determines whether they are feeling positive or negative emotions. Similarly, audio data collected through the microphone is processed using a speech analysis library (e.g., Google Cloud Speech-to-Text) to recognize emotions from the tone and content of the voice.

[0817] The server analyzes the acquired emotional data using a generative AI model (e.g., built with TensorFlow) and dynamically suggests the most suitable products and services for the user. The user's past purchase history and market data are also considered during this process. Furthermore, a predictive model is used to calculate an appropriate price for the selected product to determine if it is suitable for the user.

[0818] For example, when a user is purchasing a new electronic device, if their facial expression shows a negative reaction, the system will immediately adjust the price or offer a coupon to improve the purchase experience. A concrete example of a prompt message might be: "The user expressed negative feelings about the new laptop due to the price. What action should be taken to alleviate this user's feelings?"

[0819] This allows users to receive optimized product recommendations and price adjustments in real time based on their emotions and purchase history, resulting in a more satisfying shopping experience. Retailers can also improve revenue by optimizing their approach to individual consumers.

[0820] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0821] Step 1:

[0822] The server receives commercial data sent from the user's terminal. This commercial data includes product browsing history and purchase history. The server removes redundant data and corrects anomalous data to generate a clean dataset. This process removes data noise and improves the accuracy of the analysis.

[0823] Step 2:

[0824] The server uses a generative AI model to analyze the clean dataset obtained in Step 1. It receives data including market trends and consumer purchasing behavior as input, and the AI ​​model uses this to output detailed consumer profiles and market forecasts. During this process, the server calculates consumption trends and demand forecasts using the generative AI model.

[0825] Step 3:

[0826] The device uses the user's camera and microphone to collect data on the user's facial expressions and voice in real time. It captures the user's facial expressions and tone of voice while they are browsing products and sends this data to the server. The input data consists of facial images and audio data, and the output is data that is ready to be classified as emotion.

[0827] Step 4:

[0828] The server analyzes the facial image and audio data received in step 3. It uses an image recognition library (e.g., OpenCV) and an audio analysis library (e.g., Google Cloud Speech-to-Text) to recognize emotions. It detects emotions such as positive or negative from the input image and audio and outputs this as emotion data.

[0829] Step 5:

[0830] The server passes the emotional data obtained in step 4 to the generating AI model to make optimal product recommendations. Combining the emotional data with consumer profiles, it dynamically makes product recommendations and adjusts prices, which are then sent to the user. Based on the emotional data input, it outputs a personalized product list.

[0831] Step 6:

[0832] The user reviews product suggestions sent from the server on their device. Based on the suggested information, the user can then decide whether to purchase. The system retrieves the user's final opinion and feedback and sends it back to the server.

[0833] Step 7:

[0834] The server analyzes user feedback and updates the predictive model. Based on the acquired feedback, it processes the data to further refine the appropriate price and product recommendations for the product. This results in output that improves the accuracy of the predictive model from the input feedback.

[0835] 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.

[0836] 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.

[0837] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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."

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] The following is further disclosed regarding the embodiments described above.

[0857] (Claim 1)

[0858] A means for collecting commercial data, deleting redundant data, and correcting abnormal data,

[0859] A means of analyzing market trends and consumer purchasing behavior using generative AI,

[0860] A method for calculating the fair price of a product using a predictive model,

[0861] A means of presenting the calculated fair price,

[0862] A means of updating the predictive model by analyzing feedback provided by users,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, further comprising means for analyzing market data and customer behavior data by time series analysis and clustering.

[0866] (Claim 3)

[0867] The system according to claim 1, further comprising means for considering multiple price scenarios that take into account the customer's price elasticity based on the analysis results of the generating AI.

[0868] "Example 1"

[0869] (Claim 1)

[0870] A means for collecting commercial data, deleting redundant data, and correcting abnormal data,

[0871] A method for cleansing and analyzing data collected using generative AI technology,

[0872] Based on the analysis results, a predictive model is constructed, and a means is provided to calculate the appropriate price of the product.

[0873] A means of displaying the calculated fair price on the terminal,

[0874] A means of collecting user feedback and using it to improve the accuracy of predictive models,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, further comprising means for analyzing market data and customer behavior data by time series analysis and clustering to identify consumer purchasing patterns.

[0878] (Claim 3)

[0879] The system according to claim 1, further comprising means for examining multiple pricing scenarios that take into account the customer's price elasticity based on the analysis results of the generation AI technology, and for applying them.

[0880] "Application Example 1"

[0881] (Claim 1)

[0882] A means for collecting commercial data, deleting redundant data, and correcting abnormal data,

[0883] A means of analyzing market trends and consumer purchasing behavior using generative AI,

[0884] A method for calculating the fair price of a product using a predictive model,

[0885] A means of presenting the calculated fair price,

[0886] A means of updating the predictive model by analyzing feedback provided by users,

[0887] A means of suggesting suitable products and prices to consumers in real time using customer purchase history and market data,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, further comprising means for analyzing market data and customer behavior data by time series analysis and clustering.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising means for considering multiple price scenarios that take into account the customer's price elasticity based on the analysis results of the generating AI.

[0893] "Example 2 of combining an emotion engine"

[0894] (Claim 1)

[0895] A means for collecting commercial information, deleting redundant information, and correcting abnormal information,

[0896] A means of analyzing market trends and consumer purchasing behavior using generative artificial intelligence,

[0897] A means of analyzing emotional states obtained from users,

[0898] A method for calculating a fair price based on product characteristics using a predictive model,

[0899] A means of providing users with calculated fair prices and product suggestions,

[0900] A means of analyzing emotional feedback provided by users, updating predictive models, and adjusting prices,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, further comprising means for analyzing market information and customer behavior information by time-series analysis and clustering to generate personalized recommendations that reflect emotional states.

[0904] (Claim 3)

[0905] The system according to claim 1, further comprising means for considering multiple pricing scenarios that take into account customer emotional tendencies based on the analysis results of a generating artificial intelligence, and for implementing measures to improve customer satisfaction.

[0906] "Application example 2 when combining with an emotional engine"

[0907] (Claim 1)

[0908] A means for collecting commercial data, deleting redundant data, and correcting abnormal data,

[0909] A means of analyzing market trends and consumer purchasing behavior using generative AI,

[0910] A method for calculating the fair price of a product using a predictive model,

[0911] A means of presenting the calculated fair price,

[0912] Means of recognizing user emotions,

[0913] A method for optimizing product recommendations using emotional data,

[0914] A means of updating the predictive model by analyzing feedback provided by users,

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, further comprising means for analyzing market data and customer behavior data by time series analysis and clustering.

[0918] (Claim 3)

[0919] The system according to claim 1, further comprising means for considering multiple price scenarios that take into account the customer's price elasticity based on the analysis results of the generating AI. [Explanation of Symbols]

[0920] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting commercial data, deleting redundant data, and correcting abnormal data, A means of analyzing market trends and consumer purchasing behavior using generative AI, A method for calculating the fair price of a product using a predictive model, A means of presenting the calculated fair price, A means of updating the predictive model by analyzing feedback provided by users, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing market data and customer behavior data by time series analysis and clustering.

3. The system according to claim 1, further comprising means for considering multiple price scenarios that take into account the customer's price elasticity based on the analysis results of the generating AI.

Images