system

Abstract

We provide the system. [Solution] Means for collecting customer data, A means of analyzing collected customer data and classifying customers into segments, A means of generating optimal pricing plans and sales strategies for each customer based on analysis, A means of delivering generated pricing plans and sales strategies to customers in real time, A means to monitor the effectiveness of each measure and reflect the results in the next data analysis, 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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, customer needs have become diversified and sophisticated. In order to improve customer satisfaction and strengthen brand power, companies need to timely provide each customer with an optimal pricing plan and sales measures. However, in the conventional system, the collection and analysis of customer data are insufficient, and as a result, it has been difficult to provide appropriate measures. In addition, there is a problem that it is difficult to provide real-time feedback on the effects of measures and reflect them in the next measures.

Means for Solving the Problems

[0005] This invention provides the following means to solve the above problems: a system including means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This system enables companies to respond to the diverse needs of their customers and improve customer satisfaction. Furthermore, by reflecting the effectiveness of strategies in real time, it is possible to reduce lost opportunities and contribute to improving brand strength.

[0006] "Customer data" refers to information about customers, specifically including purchase history, website browsing history, and survey results.

[0007] "Means of collection" refers to technical or mechanical means for collecting customer data, which have the function of recording customer behavior and opinions and storing them in a database.

[0008] "Means of analysis" include algorithms and machine learning models that extract patterns and trends based on collected data in accordance with specific purposes, and that reveal customer behavior and characteristics.

[0009] "Means of segmentation" refers to methods and tools for dividing customers into groups with similar characteristics and behaviors based on analysis results.

[0010] "Means for generating pricing plans and sales strategies" include systems and algorithms for designing and proposing optimal pricing and promotional activities for each customer based on customer needs and segment information.

[0011] "Means of real-time delivery" include communication technologies and push notification systems for immediately notifying or providing customers with generated pricing plans and sales promotions.

[0012] "Means of monitoring effectiveness" refers to methods and tools for continuously observing the results and impacts of implemented measures, and for collecting and analyzing data.

[0013] "Means of incorporating data analysis" refers to a system that incorporates monitoring results into subsequent data analysis to improve the accuracy and effectiveness of the analysis model. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter will be described an example of an embodiment of a system according to the technology of the present disclosure with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. Specific embodiments for implementing the system of this invention are described below.

[0036] Data collection

[0037] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. When a user browses a website, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server in the same manner.

[0038] Data Analysis

[0039] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. It then applies clustering algorithms to analyze the data and classify customers into segments. For example, K-means clustering is used to divide customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms are used to predict the future needs of customers in each segment. Specifically, random forests and neural networks are used to predict the product categories and applicable discount rates that a particular customer segment is likely to purchase next.

[0040] Generating pricing plans and sales strategies

[0041] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies for customer segments with specific interests, providing relevant new product information and special coupons.

[0042] Timely distribution of measures

[0043] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit a website.

[0044] Monitoring and feedback on the effects

[0045] After each measure is implemented, the server monitors its effects. Specifically, it tracks changes in purchasing and browsing behavior as a result of the measures and collects data. For example, it measures how frequently customers who participated in a particular discount campaign started purchasing products. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0046] In this way, the system of the present invention can provide optimal pricing plans and sales strategies based on customer needs in a timely manner, thereby improving customer satisfaction and brand strength.

[0047] The following describes the processing flow.

[0048] Step 1: Data Collection

[0049] The device records purchase information (product ID, price, purchase date and time, etc.) when a user buys a product from an online store.

[0050] The device records user behavior data (such as the ID of the product viewed, the date and time of viewing, and the duration of time spent on the site) when the user browses a website.

[0051] The device records the user's response data when they answer a survey.

[0052] The device periodically sends all recorded data to the server.

[0053] Step 2: Data preprocessing

[0054] The server integrates the received purchase history, browsing history, and survey data.

[0055] The server performs a cleansing process to remove missing or noisy data.

[0056] The server converts the data format into a format suitable for analysis.

[0057] Step 3: Customer Segmentation

[0058] The server then runs the K-means clustering algorithm on the cleansed data to classify customers into multiple segments.

[0059] The server identifies the characteristics of each segment (e.g., frequent buyers, buyers in specific categories, etc.).

[0060] Step 4: Needs Prediction

[0061] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next.

[0062] The server uses the prediction results to identify the needs of each segment.

[0063] Step 5: Generating pricing plans and sales strategies

[0064] The server designs optimal pricing plans and sales strategies for each customer segment based on predicted needs.

[0065] For example, a server might design a discount plan for frequent customers that offers discounts for purchasing a certain number of items in a specific product category within a set period.

[0066] The server stores the designed plans and strategies in a database.

[0067] Step 6: Timely distribution of measures

[0068] The server delivers the generated pricing plans and sales strategies to the terminals in real time.

[0069] For example, the server sends a push notification to the user's smartphone informing them of a new discount campaign.

[0070] The server instructs the device to display individually optimized advertising banners and promotional messages when a user visits a website.

[0071] Step 7: Monitoring the effectiveness of the measures

[0072] The server monitors changes in user purchasing and browsing behavior after each measure is implemented.

[0073] The server analyzes in detail the purchase frequency and category changes of customers who have taken advantage of specific discount campaigns.

[0074] Step 8: Optimization through feedback

[0075] The server feeds the monitoring results back into the data analysis model and adjusts the parameters of the analysis model.

[0076] The server will use this feedback to improve the effectiveness of future measures.

[0077] Through these processing steps, the system provides timely and optimal pricing plans and sales strategies based on customer needs, thereby improving customer satisfaction and brand strength.

[0078] (Example 1)

[0079] 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."

[0080] Traditional marketing systems struggled to accurately understand customer purchasing behavior and preferences in real time and provide individually optimized pricing plans and sales strategies. Furthermore, the lack of mechanisms to continuously monitor the effectiveness of strategies and incorporate that data into subsequent analyses prevented improvements in the accuracy and effectiveness of those strategies.

[0081] 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.

[0082] In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for distributing the generated pricing plans and sales strategies to the customer's communication device in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to quickly and accurately grasp customer purchasing behavior and preferences and provide individually optimized pricing plans and sales strategies in a timely manner.

[0083] "Customer data" refers to information such as a customer's purchase history in commercial transactions, their browsing history on internet sites, and survey results.

[0084] "Means of collection" refers to devices or software that have the function of acquiring customer data and transmitting it to a server.

[0085] "Means of analysis" refers to devices or software that have the function of analyzing collected customer data and classifying customers based on similar behavioral patterns and interests.

[0086] A "clustering algorithm" is a statistical method for grouping sets of data, and includes techniques such as K-means and hierarchical clustering.

[0087] A "pricing plan" refers to sales conditions such as pricing and discounts offered to customers under specific circumstances.

[0088] "Sales strategies" refer to specific sales plans and promotions aimed at getting customers to purchase a particular product or service.

[0089] "Means of real-time delivery" refers to a device or software that has the function of immediately transmitting information on pricing plans and sales strategies generated based on analysis results to the customer's communication device.

[0090] "Monitoring means" refers to devices or software that have the function of tracking the effectiveness of implemented sales measures and collecting and analyzing the results.

[0091] A "segment" refers to a group of customers that share common characteristics or behaviors.

[0092] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. Specific embodiments for implementing the system of this invention are described below.

[0093] System Overview

[0094] This system operates by coordinating servers and terminals to collect and analyze customer data, generate and distribute optimal pricing plans and sales strategies, and monitor their effectiveness.

[0095] Data collection

[0096] The device records the user's purchasing behavior on online stores and browsing behavior on internet sites, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. Similarly, when a user browses an internet site, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0097] Data Analysis

[0098] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. Then, K-means clustering is used to classify customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms such as random forests and neural networks are used to predict the future needs and likely product categories for each segment.

[0099] Generating pricing plans and sales strategies

[0100] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also creates sales strategies that provide relevant new product information and special coupons to customer segments with specific interests.

[0101] Timely distribution of measures

[0102] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit websites.

[0103] Monitoring and feedback on the effects

[0104] The server monitors the effectiveness of each measure after it has been implemented. For example, it measures how frequently customers who participated in a particular discount campaign began purchasing products. These monitoring results are then incorporated into the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures being generated.

[0105] Specific example

[0106] A user purchases the latest smartphone from an online store. At that time, the device sends data such as the purchase date and time, product ID, and price to the server. The server then integrates and analyzes this data with other user data to predict that the user is likely to purchase a smartphone case next time. Based on this prediction, the server generates a plan offering the user a specific smartphone case at a discounted price and delivers it to the user's smartphone via push notification.

[0107] Example of a prompt

[0108] "Based on the analysis of customer data, we predict the product that the customer is most likely to purchase next and generate the optimal price discount plan for that product."

[0109] This system can improve customer satisfaction and brand strength by providing optimal pricing plans and sales strategies based on customer needs in a timely manner.

[0110] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0111] Step 1: Data Collection

[0112] When a user purchases an item from an online store, the device records data such as the purchase date and time, product ID, and price. For example, if a user purchases a "latest smartphone," this information will be recorded. The device then sends the recorded purchase data to a server. Additionally, when a user browses a website, the device records their browsing history and time spent on the site, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0113] Input: User-generated purchase history, browsing history, and survey results.

[0114] Output: Customer data sent to the server

[0115] Step 2: Data Integration and Preprocessing

[0116] The server integrates all received customer data. This includes the following specific actions: pre-processing to remove incomplete or noisy data. For example, missing data is either filled in or deleted. Noisy data is also filtered out.

[0117] Input: Raw customer data sent from the terminal.

[0118] Output: Pre-processed customer data

[0119] Step 3: Classification of Customer Segments

[0120] The server applies a clustering algorithm based on pre-processed customer data to classify customers into segments. For example, K-means clustering is used to divide customers into groups with similar purchasing behaviors or interests.

[0121] Input: Pre-processed customer data

[0122] Output: Customer data categorized by segment

[0123] Step 4: Predicting future needs

[0124] The server uses machine learning algorithms (such as random forests or neural networks) to predict future needs based on customer data categorized into segments. For example, it calculates the probability that a "customer group that frequently purchases products" will next purchase a "smartphone case."

[0125] Input: Customer data categorized by segment

[0126] Output: Forecast data for future needs for each segment

[0127] Step 5: Generating pricing plans and sales strategies

[0128] The server generates optimal pricing plans and sales strategies for each segment based on future needs prediction data. For example, for "frequent buyers," it designs a discount plan for customers who purchase a certain number of specific products within a certain period. It also generates new product information and special offer coupons.

[0129] Input: Future needs forecast data

[0130] Output: Generated pricing plans and sales strategies

[0131] Step 6: Timely distribution of plans and measures

[0132] The server delivers generated pricing plans and sales promotions to the device in real time. For example, it sends "discount information on smartphone cases" to the user's smartphone via push notification. Furthermore, it displays individually optimized advertising banners and promotional messages when the user visits a website.

[0133] Input: Generated pricing plans and sales strategies

[0134] Output: Pricing plans and sales promotions delivered to user terminals

[0135] Step 7: Monitoring and Feedback on Effects

[0136] The server monitors the effectiveness of each measure after it has been implemented. For example, it tracks how frequently customers who participated in a particular discount campaign began purchasing products. These monitoring results are then incorporated into the next data analysis.

[0137] Input: Effectiveness data of implemented sales measures

[0138] Output: Monitored results data and feedback data for accuracy improvement.

[0139] As a result, this system can provide optimal pricing plans and sales strategies based on customer behavior in real time.

[0140] (Application Example 1)

[0141] 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."

[0142] Traditional purchasing data analysis systems have difficulty providing timely product recommendations and sales strategies that reflect individual customer needs. Furthermore, these systems are primarily designed for desktop environments and do not offer real-time information via mobile devices such as smartphones and tablets. Therefore, improving the quality of the customer experience and stimulating purchasing intent has been challenging.

[0143] 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.

[0144] In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, means for being installed on mobile devices such as smartphones and tablets to provide individually optimized product suggestions and campaigns, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to provide optimal product suggestions and sales strategies that meet the individual needs of customers in real time.

[0145] "Customer data" refers to information about individual customers, such as their purchase history, website browsing history, and survey results.

[0146] "Analysis" refers to the process of processing and analyzing data using collected customer data to identify customer behavior and trends.

[0147] A "segment" refers to a group of customers who have similar purchasing behaviors or interests.

[0148] A "pricing plan" refers to the pricing and discount conditions offered to customers as a sales promotion tool.

[0149] "Sales strategies" refer to means of sales promotion taken towards customers, such as product proposals and campaign implementation.

[0150] "Mobile devices such as smartphones and tablets" refer to portable electronic devices that can receive and display information in real time using communication functions.

[0151] "Real-time" refers to providing results immediately after information has been collected and analyzed.

[0152] "Monitoring" refers to continuously observing the effects of a policy and measuring its fluctuations.

[0153] A "clustering algorithm" refers to a mathematical method for grouping (clustering) data based on specific criteria.

[0154] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. The following describes in detail how to implement the system of this invention.

[0155] Data collection

[0156] The server has the function of collecting customer data from the terminal. This data includes purchase history, website browsing history, and survey results. The terminal records the user's purchasing behavior on the online store and website browsing behavior, and sends this data to the server. For example, when a user purchases a product, information such as the purchase date and time, product ID, and price is collected and sent to the server. In addition, the history of product pages viewed by the user on the website, the time spent on each page, and the number of times they were viewed are also collected and sent to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0157] Data Analysis

[0158] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. It then applies clustering algorithms to analyze the data and segment customers. Specifically, K-means clustering is used to divide customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms are used to predict the future needs of customers in each segment. In particular, generative AI models such as random forests and neural networks are used to predict the product categories and applicable discount rates that specific customer segments are likely to purchase next.

[0159] Generating pricing plans and sales strategies

[0160] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies for customer segments with specific interests, providing relevant new product information and special coupons.

[0161] Timely distribution of measures

[0162] The device has a means of notifying customers in real time about generated pricing plans and sales promotions. Specifically, it sends push notifications to users' smartphones and tablets to inform them about new discount campaigns. It also displays individually optimized advertising banners and promotional messages when users visit websites.

[0163] Monitoring and feedback on the effects

[0164] The server monitors the effectiveness of each measure after it has been implemented. For example, it measures how frequently customers who participated in a particular discount campaign began purchasing products, and incorporates these monitoring results into the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0165] This makes it possible to provide optimal product suggestions and sales strategies tailored to each customer's individual needs in real time.

[0166] Example of a prompt:

[0167] We want to use clustering algorithms and machine learning models to suggest the most suitable sales strategies based on users' purchase and browsing history. Design a system that predicts the product categories and applicable discount rates that users will be interested in next, and generates optimal pricing plans and promotional offers.

[0168] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0169] Step 1:

[0170] Data collection

[0171] The terminal records the user's purchase history, website browsing history, and survey results. For example, when a user purchases a product, it collects information such as the purchase date and time, product ID, and price, and sends it to the server. This allows the server to receive detailed data for each customer. The input data is the customer's behavioral history, and the output is the raw data sent to the server.

[0172] Step 2:

[0173] Data Integration and Preprocessing

[0174] The server integrates the received customer data and performs preprocessing to remove incomplete data and noise. Specifically, it imputes missing values ​​and detects and corrects outliers. This results in clean data suitable for analysis. The input data is the raw data before integration, and the output is the clean data.

[0175] Step 3:

[0176] Customer segment clustering

[0177] The server applies a clustering algorithm (e.g., K-means clustering) to the integrated clean data to classify customers into segments. For example, customers with similar purchasing behavior or browsing history are grouped together. The input for this step is clean data, and the output is segmented customer data.

[0178] Step 4:

[0179] Needs forecasting

[0180] The server uses a generative AI model (e.g., random forest or neural network) based on segmented customer data to predict the product categories and applicable discount rates that customers in each segment are likely to purchase next. The input for this step is segmented customer data, and the output is the predicted customer needs for each segment.

[0181] Step 5:

[0182] Generating pricing plans and sales strategies

[0183] The server generates optimal pricing plans and sales strategies based on customer needs predictions. For example, it might offer a "10% off next purchase" plan to frequent customers and provide discount coupons for related new products to customers interested in specific items. The input for this step is the customer needs prediction, and the output is pricing plans and sales strategies tailored to each customer.

[0184] Step 6:

[0185] Timely distribution of measures

[0186] The device notifies users in real time of pricing plans and sales promotions received from the server. Specifically, it sends push notifications to users' smartphones and tablets, for example, informing them of an offer such as "10% off your next purchase." The input for this step is individually optimized sales promotion information, and the output is push notifications and advertising banners sent to users.

[0187] Step 7:

[0188] Monitoring and feedback on the effects

[0189] The server monitors the effectiveness of each initiative and incorporates the results into the next data analysis. For example, it measures the extent to which a particular discount campaign influenced purchasing behavior. This improves the accuracy of the analytical model. The input for this step is customer behavior data after the implementation of each initiative, and the output is the modified model data that will be reflected in the next analysis.

[0190] 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.

[0191] This invention combines a system that collects and analyzes customer data to provide optimal pricing plans and sales strategies in a timely manner with an emotion engine that recognizes user emotions. The following describes a specific embodiment for implementing the system of this invention.

[0192] Data collection

[0193] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. When a user browses a website, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server in the same manner.

[0194] Collection of emotional data

[0195] The device records the user's emotions through facial expressions, voice, and input text, and sends this data to a server. For example, it uses a webcam and microphone to analyze the user's facial expressions and voice emotional state in real time and sends the results to the server.

[0196] Data preprocessing

[0197] The server integrates received purchase history, browsing history, survey data, and sentiment data, and performs preprocessing to remove incomplete or noisy data. It then converts the data format to one suitable for analysis.

[0198] Customer segmentation

[0199] The server runs a K-means clustering algorithm on all the cleansed data to classify customers into multiple segments. It then identifies the characteristics of each segment (e.g., frequent buyers, buyers of specific categories, etc.).

[0200] Integration of needs prediction and sentiment recognition results

[0201] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next. Furthermore, it integrates sentiment data obtained from the sentiment engine to make predictions that take into account the customer's emotional state.

[0202] Generating pricing plans and sales strategies

[0203] The server designs optimal pricing plans and sales strategies for each customer based on customer segment needs predictions and sentiment data. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies that provide relevant new product information and special coupons to customer segments with specific interests.

[0204] Timely distribution of measures

[0205] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit a website.

[0206] Monitoring the effectiveness of the measures and providing feedback.

[0207] After each measure is implemented, the server monitors its effects. Specifically, it tracks changes in purchasing and browsing behavior as a result of the measures and collects data. For example, it measures how frequently customers who participated in a particular discount campaign started purchasing products. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0208] This system allows for more accurate prediction of customer needs using emotional data, enabling the provision of optimal pricing plans and sales strategies. This is expected to further improve customer satisfaction and brand strength.

[0209] The following describes the processing flow.

[0210] Step 1: Data Collection

[0211] The device records purchase information (product ID, price, purchase date and time, etc.) when a user buys a product from an online store.

[0212] The device records user behavior data (such as the ID of the product viewed, the date and time of viewing, and the duration of time spent on the site) when the user browses a website.

[0213] The device records the user's response data when they answer a survey.

[0214] The device periodically sends all recorded data to the server.

[0215] Step 2: Collecting emotional data

[0216] The device records emotions from the user's facial expressions, voice, and input text.

[0217] The device uses a webcam and microphone to analyze the user's facial expressions and emotional state in real time, and sends the results to a server.

[0218] Step 3: Data Preprocessing

[0219] The server integrates the received purchase history, browsing history, survey data, and sentiment data, and performs preprocessing to remove incomplete or noisy data.

[0220] The server converts the data into a format suitable for analysis.

[0221] Step 4: Customer Segmentation

[0222] The server then runs a K-means clustering algorithm on all the cleansed data to classify customers into multiple segments.

[0223] The server identifies the characteristics of each segment (e.g., frequent buyers, buyers in specific categories, etc.).

[0224] Step 5: Integrating Needs Prediction and Sentiment Recognition Results

[0225] The server applies machine learning algorithms such as random forests and neural networks to predict purchasing needs for each customer segment.

[0226] The server integrates emotional data obtained from the emotion engine and makes predictions that take into account the customer's emotional state.

[0227] Step 6: Generate pricing plans and sales strategies.

[0228] The server designs the optimal pricing plan and sales strategy for each customer based on customer segment needs predictions and sentiment data.

[0229] The server designs discount plans for frequent customers, offering discounts for purchasing a certain number of items in a specific product category within a set period.

[0230] The server designs sales strategies that provide relevant new product information and special offer coupons to customer segments with specific interests.

[0231] Step 7: Timely distribution of measures

[0232] The server delivers the generated pricing plans and sales strategies to the terminals in real time.

[0233] The server sends a push notification to the user's smartphone, informing them of the new discount campaign.

[0234] The server instructs the device to display individually optimized advertising banners and promotional messages when a user visits a website.

[0235] Step 8: Monitoring the effectiveness of the measures

[0236] The server monitors changes in user purchasing and browsing behavior after each measure is implemented.

[0237] The server analyzes in detail the purchase frequency and category changes of customers who have taken advantage of specific discount campaigns.

[0238] Step 9: Optimization through feedback

[0239] The server feeds the monitoring results back into the data analysis model and adjusts the parameters of the analysis model.

[0240] The server incorporates the feedback into the design of future measures, thereby improving the effectiveness of those measures.

[0241] Through these processing steps, the system utilizes customer sentiment data to make more specific and accurate predictions of customer needs, providing optimal pricing plans and sales strategies in a timely manner, thereby improving customer satisfaction and brand strength.

[0242] (Example 2)

[0243] 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".

[0244] Traditional systems have limitations in collecting and analyzing customer data, making it particularly difficult to generate optimal pricing plans and sales strategies that take into account customer emotional states. Furthermore, the inability to adequately distribute strategies in real time and provide feedback on their effectiveness hindered improvements in customer satisfaction and strengthened brand power. To address these challenges, it is crucial to integrate emotional data in addition to customer data to enable real-time strategy distribution and effectiveness monitoring.

[0245] 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.

[0246] In this invention, the server includes means for integrating and pre-processing customer data and sentiment data; means for classifying customers into segments based on the pre-processed data; means for predicting purchases for each segment and generating optimal pricing plans and sales strategies for each customer, taking sentiment data into consideration; means for delivering the generated pricing plans and sales strategies to customers in real time; and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This enables more accurate prediction of customer needs and the timely provision of personalized pricing plans and sales strategies.

[0247] "Customer data" refers to information such as a customer's purchase history, website browsing history, and survey results.

[0248] "Emotional data" refers to information about a user's emotional state, analyzed from their facial expressions, voice, and text.

[0249] "Preprocessing" refers to the process of integrating received data, removing incomplete data and noise, and converting it into a format suitable for analysis.

[0250] A "segment" refers to a group of customers classified based on common characteristics.

[0251] A "clustering algorithm" refers to a method of classifying data into multiple clusters based on common properties or patterns.

[0252] "Purchase forecasting" refers to the process of predicting what products or services a customer is likely to buy next.

[0253] A "pricing plan" refers to the pricing structure or discount plan offered to customers.

[0254] "Sales strategies" refer to promotional and marketing activities conducted for specific segments or customers.

[0255] "Real-time" refers to processing or delivering information immediately.

[0256] "Monitoring" refers to the process of continuously tracking the effects of a measure and changes in customer behavior after its implementation, and collecting data accordingly.

[0257] "Feedback" refers to the process of using monitoring results to inform future data analysis and strategy development.

[0258] This invention relates to a system that collects and analyzes customer data and emotional data, and based on that, provides optimal pricing plans and sales strategies in a timely manner. Specific embodiments for carrying out this invention are described below.

[0259] Specific methods for data collection

[0260] The device records user purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, it captures user actions by embedding JavaScript® code into web pages. It also uses the Google® Analytics API to obtain website browsing history and time spent on the site. Purchase history includes user ID, purchase date and time, product ID, price, etc.

[0261] Collection and analysis of emotional data

[0262] The device collects emotional data through the user's facial expressions, voice, and input text, and sends this data to the server. It uses a webcam to perform facial expression analysis using the OpenCV library, and a microphone to convert speech to text using the Google Speech-to-Text API, which is then analyzed.

[0263] Data preprocessing

[0264] The server integrates and preprocesses the collected purchase history, browsing history, survey data, and sentiment data. This process includes data integration using the Python Pandas library, imputation of incomplete data, and removal of outliers.

[0265] Customer segmentation

[0266] The server uses the K-means clustering algorithm to classify customers into multiple segments based on the pre-processed data. This algorithm uses the Scikit-learn library.

[0267] Integration of needs prediction and emotion recognition results

[0268] The server uses random forests and neural network models to predict which products a specific customer segment is likely to purchase next. This analysis utilizes TENSORFLOW® and Scikit-learn. Furthermore, it integrates the results of an emotion engine, taking into account the customer's emotional state to achieve more accurate predictions.

[0269] Generating pricing plans and sales strategies

[0270] The server designs optimal pricing plans and sales strategies for each customer based on predictive and sentiment data. For example, it might generate a plan for frequent buyers offering a 10% discount for monthly purchases of ¥10,000 or more. Other sales strategies include providing new product information and special coupons.

[0271] Timely distribution of measures

[0272] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it uses Firebase Cloud Messaging to send push notifications to smartphones announcing new discount campaigns.

[0273] Monitoring the effectiveness of the measures and providing feedback.

[0274] The server monitors the effectiveness of each measure after its implementation and tracks changes in purchasing and browsing behavior. This monitoring data is then incorporated into subsequent data analysis to improve the system's accuracy.

[0275] Examples of prompt statements

[0276] Here is a concrete example of an input prompt statement for a generative AI model:

[0277] "Create a model to predict what other products customers who purchase the next item tend to buy together. Available data includes purchase history (user ID, purchase date and time, product ID, price), browsing history (user ID, browsing date and time, product ID, time spent), sentiment data (user ID, facial expression / voice sentiment score), and survey data (user ID, response content)."

[0278] The above describes the embodiment for carrying out the invention. This system enables more accurate prediction of customer needs and the timely provision of personalized pricing plans and sales strategies.

[0279] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0280] Step 1:

[0281] The device records the user's purchasing and browsing behavior and sends this data to the server in real time. Specifically, JavaScript code embedded in the web page captures the user's actions (product purchase, page viewing). Inputs include user ID, purchase date and time, product ID, price, viewing date and time, and time spent on the page. This input data is sent to the server via an HTTP request, and the output is all purchase and browsing history data stored on the server.

[0282] Step 2:

[0283] The terminal collects the user's expressions, voices, and input texts as emotion data and sends this data to the server in real time. Specifically, it analyzes the expressions using a web camera and the OpenCV library, and converts the voice data collected by the microphone into text using the Google Speech-to-Text API. As inputs, expression data (images), voice data (voice files), and text data (converted voice text) are obtained. These input data are sent to the server in real time using WebSocket, and as output, the emotion-analyzed data is stored in the server.

[0284] Step 3:

[0285] The server integrates the received purchase history, browsing history, questionnaire data, and emotion data, and performs preprocessing of the data. Specifically, it uses the Pandas library in Python to clean the data and remove incomplete data and noise. As inputs, purchase history data, browsing history data, questionnaire data, and emotion data are obtained. These data are read from log files or databases, and after data cleaning and format conversion, the output is the cleaned integrated data.

[0286] Step 4:

[0287] The server performs customer segmentation based on the preprocessed data. Specifically, it uses the K-means clustering algorithm to classify customers into multiple segments. This process is executed using the Scikit-learn library. As input, the preprocessed integrated data is obtained. This data is input into the K-means clustering algorithm, and as output, information on which cluster each customer is classified into is obtained.

[0288] Step 5:

[0289] The server performs customer purchase predictions based on clustered segment data. Specifically, it uses random forests and neural network models to analyze and predict which products customers in each segment are likely to purchase next. TensorFlow is used for this analysis. The input consists of segmented customer data and sentiment data. This input data is passed through a machine learning model to obtain prediction results as output.

[0290] Step 6:

[0291] The server generates optimal pricing plans and sales strategies for each customer based on prediction results and sentiment data. Specifically, it executes a script using Python to generate pricing plans and promotional strategies based on various conditions. The input is purchase prediction data and sentiment data. The output is data on pricing plans and sales strategies optimized for each customer.

[0292] Step 7:

[0293] The server delivers generated pricing plans and sales promotions to devices in real time. Specifically, it uses Firebase Cloud Messaging to send push notifications to users' smartphones announcing new discount campaigns. The inputs are optimized pricing plan and sales promotion data and customer IDs. The output is a push notification sent to the device.

[0294] Step 8:

[0295] The server monitors the effectiveness of each initiative and feeds the results back into the next data analysis. Specifically, it uses Google Analytics and internally developed monitoring tools to track changes in purchasing and browsing behavior after an initiative is implemented. The input is purchase history data and browsing history data after the initiative is implemented. The output is data on the effectiveness of the initiative, which is used in the next analysis model.

[0296] (Application Example 2)

[0297] 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".

[0298] While many online stores already offer optimal pricing plans and sales strategies based on user purchasing behavior and website browsing history, it is believed that even more accurate personalization is possible by considering customer emotions. However, current systems do not collect and analyze emotional data, making it difficult to provide optimal suggestions based on the customer's actual emotional state.

[0299] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for collecting and analyzing user emotion data through a webcam and microphone, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to design and provide optimal pricing plans and sales strategies that take into account the emotional state of the customer.

[0300] "Customer data" refers to information including users' purchasing behavior, website browsing history, and survey results.

[0301] "Analysis" is the process of analyzing patterns and trends based on collected data to gain insights.

[0302] A "segment" refers to a group of customers that share common characteristics or behaviors.

[0303] A "price plan" refers to the price structure and charging scheme for specific products or services.

[0304] A "sales strategy" refers to promotions and marketing means to encourage customers to purchase.

[0305] "Emotional data" refers to information regarding the psychological state obtained through a user's expressions, voice, etc.

[0306] A "web camera" refers to a camera device for capturing a user's expressions in real time.

[0307] A "microphone" refers to a device for picking up a user's voice.

[0308] "Real time" refers to the immediate processing and distribution of information and data without significant time lag.

[0309] "Monitoring" refers to the act of continuously monitoring and evaluating whether measures and systems are functioning properly.

[0310] The present invention relates to an emotion recognition-based personalized shopping assistant system. Hereinafter, how to specifically implement the system of the present invention will be described.

[0311] The server collects customer data including a user's purchase behavior, website browsing history, and questionnaire results. This data includes information such as the date and time when the user purchased a product, product ID, price, and browsing history and stay time. The data collected through the terminal is transmitted to the server in real time and stored.

[0312] The server analyzes the collected customer data and classifies customers into segments using the K-means clustering algorithm. Each segment is classified into a customer group with characteristics such as high-frequency purchasers or purchasers of specific categories.

[0313] Furthermore, the server collects user emotional data through the webcam and microphone, and uses an emotion recognition engine to analyze facial expressions and voice. This allows the user's real-time emotional state to be obtained as numerical data, which is also sent to the server.

[0314] The server generates optimal pricing plans and sales strategies for each customer based on the analysis results. In this process, machine learning algorithms such as random forests and neural networks are used to predict promotions and discount rates for specific products, and sentiment data is also integrated to provide more personalized recommendations.

[0315] For example, if a user spends a long time browsing a particular product page and expresses feelings of "joy" during that time, the server will recommend a 10% discount coupon for that product to that user. This information is delivered to the device in real time as a push notification or advertising banner.

[0316] After a measure is implemented, the server monitors its effects and records changes in purchasing and browsing behavior. For example, it measures how frequently customers who participated in a specific discount campaign began purchasing products, and by incorporating these monitoring results into subsequent data analysis, it improves the accuracy of the analysis model and the effectiveness of the measures.

[0317] The following software and hardware will be used for the servers and terminals.

[0318] Hardware required: Smartphone, webcam, microphone

[0319] Software used: Python, TensorFlow, Keras, OpenCV, Pushbullet

[0320] A concrete example of its use is a process where, if a user spends a long time browsing a particular product page or frequently purchases items from a certain category, a push notification offering a "10% discount coupon for a specific product" is sent based on that information and the user's sentiment data.

[0321] An example of a prompt is: "Create Python code that estimates the optimal pricing plan based on the user's purchase history and sentiment data, and sends a push notification."

[0322] In this way, it is possible to design and provide optimal pricing plans and sales strategies that take into account the emotional state of the customer, thereby improving customer satisfaction and maximizing sales.

[0323] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0324] Step 1:

[0325] Customer data collection

[0326] The device collects user purchasing behavior, website browsing history, and survey results. When a user purchases a product, information such as the purchase date and time, product ID, and price is recorded, and website browsing history and time spent on the site are also collected. This data is transmitted to the server in real time. Input data includes purchase history, browsing history, and survey data, while output data is customer data stored on the server.

[0327] Step 2:

[0328] Collection of emotional data

[0329] The device uses a webcam and microphone to collect the user's facial expressions and voice in real time. An emotion recognition engine analyzes the user's facial expressions and voice while they are using the online store and sends the data to the server as emotion data. The input data consists of facial expression data and voice data, while the output data is the emotion data stored on the server.

[0330] Step 3:

[0331] Data preprocessing

[0332] The server integrates collected purchase history, browsing history, survey data, and sentiment data, removing incomplete and noisy data. It converts the data format into a format that can be analyzed by machine learning algorithms. The input data consists of raw customer data and sentiment data, while the output data is cleansed and in an analyzable format.

[0333] Step 4:

[0334] Customer segmentation

[0335] The server runs the K-means clustering algorithm based on the cleansed data, classifying customers into multiple segments. The input data is the cleansed data, and the output data is information about each customer segment.

[0336] Step 5:

[0337] Integration of needs prediction and emotion recognition results

[0338] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next. Simultaneously, it integrates sentiment data to make predictions that take into account the user's emotional state. Input data includes segment information and sentiment data, while output data consists of predicted product categories and discount rates.

[0339] Step 6:

[0340] Generating pricing plans and sales strategies

[0341] The server designs optimal pricing plans and sales strategies for each customer based on customer segment needs prediction results and sentiment data. For example, it might suggest discount coupons for specific products to frequent customers. The input data consists of needs prediction results and sentiment data, while the output data is the designed pricing plan and sales strategy.

[0342] Step 7:

[0343] Timely distribution of measures

[0344] The server delivers generated pricing plans and sales strategies to users' smartphones as push notifications in real time. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit websites. Input data consists of pricing plans and sales strategies, while output data consists of push notifications and advertising banners.

[0345] Step 8:

[0346] Monitoring the effectiveness of the measures and providing feedback.

[0347] The server monitors the effects of each measure after it has been implemented. It tracks changes in purchasing and browsing behavior as a result of the measures and collects this data. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated. The input data is behavioral data after the implementation of the measures, and the output data is used to improve the analysis model.

[0348] 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.

[0349] 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.

[0350] 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.

[0351] [Second Embodiment]

[0352] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0353] 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.

[0354] 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).

[0355] 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.

[0356] 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.

[0357] 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).

[0358] 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.

[0359] 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.

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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".

[0364] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. Specific embodiments for implementing the system of this invention are described below.

[0365] Data collection

[0366] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. When a user browses a website, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server in the same manner.

[0367] Data Analysis

[0368] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. It then applies clustering algorithms to analyze the data and classify customers into segments. For example, K-means clustering is used to divide customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms are used to predict the future needs of customers in each segment. Specifically, random forests and neural networks are used to predict the product categories and applicable discount rates that a particular customer segment is likely to purchase next.

[0369] Generating pricing plans and sales strategies

[0370] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies for customer segments with specific interests, providing relevant new product information and special coupons.

[0371] Timely distribution of measures

[0372] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit a website.

[0373] Monitoring and feedback on the effects

[0374] After each measure is implemented, the server monitors its effects. Specifically, it tracks changes in purchasing and browsing behavior as a result of the measures and collects data. For example, it measures how frequently customers who participated in a particular discount campaign started purchasing products. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0375] In this way, the system of the present invention can provide optimal pricing plans and sales strategies based on customer needs in a timely manner, thereby improving customer satisfaction and brand strength.

[0376] The following describes the processing flow.

[0377] Step 1: Data Collection

[0378] The device records purchase information (product ID, price, purchase date and time, etc.) when a user buys a product from an online store.

[0379] The device records user behavior data (such as the ID of the product viewed, the date and time of viewing, and the duration of time spent on the site) when the user browses a website.

[0380] The device records the user's response data when they answer a survey.

[0381] The device periodically sends all recorded data to the server.

[0382] Step 2: Data preprocessing

[0383] The server integrates the received purchase history, browsing history, and survey data.

[0384] The server performs a cleansing process to remove missing or noisy data.

[0385] The server converts the data format into a format suitable for analysis.

[0386] Step 3: Customer Segmentation

[0387] The server then runs the K-means clustering algorithm on the cleansed data to classify customers into multiple segments.

[0388] The server identifies the characteristics of each segment (e.g., frequent buyers, buyers in specific categories, etc.).

[0389] Step 4: Needs Prediction

[0390] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next.

[0391] The server uses the prediction results to identify the needs of each segment.

[0392] Step 5: Generating pricing plans and sales strategies

[0393] The server designs optimal pricing plans and sales strategies for each customer segment based on predicted needs.

[0394] For example, a server might design a discount plan for frequent customers that offers discounts for purchasing a certain number of items in a specific product category within a set period.

[0395] The server stores the designed plans and strategies in a database.

[0396] Step 6: Timely distribution of measures

[0397] The server delivers the generated pricing plans and sales strategies to the terminals in real time.

[0398] For example, the server sends a push notification to the user's smartphone informing them of a new discount campaign.

[0399] The server instructs the device to display individually optimized advertising banners and promotional messages when a user visits a website.

[0400] Step 7: Monitoring the effectiveness of the measures

[0401] The server monitors changes in user purchasing and browsing behavior after each measure is implemented.

[0402] The server analyzes in detail the purchase frequency and category changes of customers who have taken advantage of specific discount campaigns.

[0403] Step 8: Optimization through feedback

[0404] The server feeds the monitoring results back into the data analysis model and adjusts the parameters of the analysis model.

[0405] The server will use this feedback to improve the effectiveness of future measures.

[0406] Through these processing steps, the system provides timely and optimal pricing plans and sales strategies based on customer needs, thereby improving customer satisfaction and brand strength.

[0407] (Example 1)

[0408] 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."

[0409] Traditional marketing systems struggled to accurately understand customer purchasing behavior and preferences in real time and provide individually optimized pricing plans and sales strategies. Furthermore, the lack of mechanisms to continuously monitor the effectiveness of strategies and incorporate that data into subsequent analyses prevented improvements in the accuracy and effectiveness of those strategies.

[0410] 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.

[0411] In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for distributing the generated pricing plans and sales strategies to the customer's communication device in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to quickly and accurately grasp customer purchasing behavior and preferences and provide individually optimized pricing plans and sales strategies in a timely manner.

[0412] "Customer data" refers to information such as a customer's purchase history in commercial transactions, their browsing history on internet sites, and survey results.

[0413] "Means of collection" refers to devices or software that have the function of acquiring customer data and transmitting it to a server.

[0414] "Means of analysis" refers to devices or software that have the function of analyzing collected customer data and classifying customers based on similar behavioral patterns and interests.

[0415] A "clustering algorithm" is a statistical method for grouping sets of data, and includes techniques such as K-means and hierarchical clustering.

[0416] A "pricing plan" refers to sales conditions such as pricing and discounts offered to customers under specific circumstances.

[0417] "Sales strategies" refer to specific sales plans and promotions aimed at getting customers to purchase a particular product or service.

[0418] "Means of real-time delivery" refers to a device or software that has the function of immediately transmitting information on pricing plans and sales strategies generated based on analysis results to the customer's communication device.

[0419] "Monitoring means" refers to devices or software that have the function of tracking the effectiveness of implemented sales measures and collecting and analyzing the results.

[0420] A "segment" refers to a group of customers that share common characteristics or behaviors.

[0421] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. Specific embodiments for implementing the system of this invention are described below.

[0422] System Overview

[0423] This system operates by coordinating servers and terminals to collect and analyze customer data, generate and distribute optimal pricing plans and sales strategies, and monitor their effectiveness.

[0424] Data collection

[0425] The device records the user's purchasing behavior on online stores and browsing behavior on internet sites, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. Similarly, when a user browses an internet site, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0426] Data Analysis

[0427] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. Then, K-means clustering is used to classify customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms such as random forests and neural networks are used to predict the future needs and likely product categories for each segment.

[0428] Generating pricing plans and sales strategies

[0429] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also creates sales strategies that provide relevant new product information and special coupons to customer segments with specific interests.

[0430] Timely distribution of measures

[0431] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit websites.

[0432] Monitoring and feedback on the effects

[0433] The server monitors the effectiveness of each measure after it has been implemented. For example, it measures how frequently customers who participated in a particular discount campaign began purchasing products. These monitoring results are then incorporated into the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures being generated.

[0434] Specific example

[0435] A user purchases the latest smartphone from an online store. At that time, the device sends data such as the purchase date and time, product ID, and price to the server. The server then integrates and analyzes this data with other user data to predict that the user is likely to purchase a smartphone case next time. Based on this prediction, the server generates a plan offering the user a specific smartphone case at a discounted price and delivers it to the user's smartphone via push notification.

[0436] Example of a prompt

[0437] "Based on the analysis of customer data, we predict the product that the customer is most likely to purchase next and generate the optimal price discount plan for that product."

[0438] This system can improve customer satisfaction and brand strength by providing optimal pricing plans and sales strategies based on customer needs in a timely manner.

[0439] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0440] Step 1: Data Collection

[0441] When a user purchases an item from an online store, the device records data such as the purchase date and time, product ID, and price. For example, if a user purchases a "latest smartphone," this information will be recorded. The device then sends the recorded purchase data to a server. Additionally, when a user browses a website, the device records their browsing history and time spent on the site, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0442] Input: User-generated purchase history, browsing history, and survey results.

[0443] Output: Customer data sent to the server

[0444] Step 2: Data Integration and Preprocessing

[0445] The server integrates all received customer data. This includes the following specific actions: pre-processing to remove incomplete or noisy data. For example, missing data is either filled in or deleted. Noisy data is also filtered out.

[0446] Input: Raw customer data sent from the terminal.

[0447] Output: Pre-processed customer data

[0448] Step 3: Classification of Customer Segments

[0449] The server applies a clustering algorithm based on pre-processed customer data to classify customers into segments. For example, K-means clustering is used to divide customers into groups with similar purchasing behaviors or interests.

[0450] Input: Pre-processed customer data

[0451] Output: Customer data categorized by segment

[0452] Step 4: Predicting future needs

[0453] The server uses machine learning algorithms (such as random forests or neural networks) to predict future needs based on customer data categorized into segments. For example, it calculates the probability that a "customer group that frequently purchases products" will next purchase a "smartphone case."

[0454] Input: Customer data categorized by segment

[0455] Output: Forecast data for future needs for each segment

[0456] Step 5: Generating pricing plans and sales strategies

[0457] The server generates optimal pricing plans and sales strategies for each segment based on future needs prediction data. For example, for "frequent buyers," it designs a discount plan for customers who purchase a certain number of specific products within a certain period. It also generates new product information and special offer coupons.

[0458] Input: Future needs forecast data

[0459] Output: Generated pricing plans and sales strategies

[0460] Step 6: Timely distribution of plans and measures

[0461] The server delivers generated pricing plans and sales promotions to the device in real time. For example, it sends "discount information on smartphone cases" to the user's smartphone via push notification. Furthermore, it displays individually optimized advertising banners and promotional messages when the user visits a website.

[0462] Input: Generated pricing plans and sales strategies

[0463] Output: Pricing plans and sales promotions delivered to user terminals

[0464] Step 7: Monitoring and Feedback on Effects

[0465] The server monitors the effectiveness of each measure after it has been implemented. For example, it tracks how frequently customers who participated in a particular discount campaign began purchasing products. These monitoring results are then incorporated into the next data analysis.

[0466] Input: Effectiveness data of implemented sales measures

[0467] Output: Monitored results data and feedback data for accuracy improvement.

[0468] As a result, this system can provide optimal pricing plans and sales strategies based on customer behavior in real time.

[0469] (Application Example 1)

[0470] 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."

[0471] Traditional purchasing data analysis systems have difficulty providing timely product recommendations and sales strategies that reflect individual customer needs. Furthermore, these systems are primarily designed for desktop environments and do not offer real-time information via mobile devices such as smartphones and tablets. Therefore, improving the quality of the customer experience and stimulating purchasing intent has been challenging.

[0472] 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.

[0473] In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, means for being installed on mobile devices such as smartphones and tablets to provide individually optimized product suggestions and campaigns, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to provide optimal product suggestions and sales strategies that meet the individual needs of customers in real time.

[0474] "Customer data" refers to information about individual customers, such as their purchase history, website browsing history, and survey results.

[0475] "Analysis" refers to the process of processing and analyzing data using collected customer data to identify customer behavior and trends.

[0476] A "segment" refers to a group of customers who have similar purchasing behaviors or interests.

[0477] A "pricing plan" refers to the pricing and discount conditions offered to customers as a sales promotion tool.

[0478] "Sales strategies" refer to means of sales promotion taken towards customers, such as product proposals and campaign implementation.

[0479] "Mobile devices such as smartphones and tablets" refer to portable electronic devices that can receive and display information in real time using communication functions.

[0480] "Real-time" refers to providing results immediately after information has been collected and analyzed.

[0481] "Monitoring" refers to continuously observing the effects of a policy and measuring its fluctuations.

[0482] A "clustering algorithm" refers to a mathematical method for grouping (clustering) data based on specific criteria.

[0483] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. The following describes in detail how to implement the system of this invention.

[0484] Data collection

[0485] The server has the function of collecting customer data from the terminal. This data includes purchase history, website browsing history, and survey results. The terminal records the user's purchasing behavior on the online store and website browsing behavior, and sends this data to the server. For example, when a user purchases a product, information such as the purchase date and time, product ID, and price is collected and sent to the server. In addition, the history of product pages viewed by the user on the website, the time spent on each page, and the number of times they were viewed are also collected and sent to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0486] Data Analysis

[0487] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. It then applies clustering algorithms to analyze the data and segment customers. Specifically, K-means clustering is used to divide customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms are used to predict the future needs of customers in each segment. In particular, generative AI models such as random forests and neural networks are used to predict the product categories and applicable discount rates that specific customer segments are likely to purchase next.

[0488] Generating pricing plans and sales strategies

[0489] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies for customer segments with specific interests, providing relevant new product information and special coupons.

[0490] Timely distribution of measures

[0491] The device has a means of notifying customers in real time about generated pricing plans and sales promotions. Specifically, it sends push notifications to users' smartphones and tablets to inform them about new discount campaigns. It also displays individually optimized advertising banners and promotional messages when users visit websites.

[0492] Monitoring and feedback on the effects

[0493] The server monitors the effectiveness of each measure after it has been implemented. For example, it measures how frequently customers who participated in a particular discount campaign began purchasing products, and incorporates these monitoring results into the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0494] This makes it possible to provide optimal product suggestions and sales strategies tailored to each customer's individual needs in real time.

[0495] Example of a prompt:

[0496] We want to use clustering algorithms and machine learning models to suggest the most suitable sales strategies based on users' purchase and browsing history. Design a system that predicts the product categories and applicable discount rates that users will be interested in next, and generates optimal pricing plans and promotional offers.

[0497] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0498] Step 1:

[0499] Data collection

[0500] The terminal records the user's purchase history, website browsing history, and survey results. For example, when a user purchases a product, it collects information such as the purchase date and time, product ID, and price, and sends it to the server. This allows the server to receive detailed data for each customer. The input data is the customer's behavioral history, and the output is the raw data sent to the server.

[0501] Step 2:

[0502] Data Integration and Preprocessing

[0503] The server integrates the received customer data and performs preprocessing to remove incomplete data and noise. Specifically, it imputes missing values ​​and detects and corrects outliers. This results in clean data suitable for analysis. The input data is the raw data before integration, and the output is the clean data.

[0504] Step 3:

[0505] Customer segment clustering

[0506] The server applies a clustering algorithm (e.g., K-means clustering) to the integrated clean data to classify customers into segments. For example, customers with similar purchasing behavior or browsing history are grouped together. The input for this step is clean data, and the output is segmented customer data.

[0507] Step 4:

[0508] Needs forecasting

[0509] The server uses a generative AI model (e.g., random forest or neural network) based on segmented customer data to predict the product categories and applicable discount rates that customers in each segment are likely to purchase next. The input for this step is segmented customer data, and the output is the predicted customer needs for each segment.

[0510] Step 5:

[0511] Generating pricing plans and sales strategies

[0512] The server generates optimal pricing plans and sales strategies based on customer needs predictions. For example, it might offer a "10% off next purchase" plan to frequent customers and provide discount coupons for related new products to customers interested in specific items. The input for this step is the customer needs prediction, and the output is pricing plans and sales strategies tailored to each customer.

[0513] Step 6:

[0514] Timely distribution of measures

[0515] The device notifies users in real time of pricing plans and sales promotions received from the server. Specifically, it sends push notifications to users' smartphones and tablets, for example, informing them of an offer such as "10% off your next purchase." The input for this step is individually optimized sales promotion information, and the output is push notifications and advertising banners sent to users.

[0516] Step 7:

[0517] Monitoring and feedback on the effects

[0518] The server monitors the effectiveness of each initiative and incorporates the results into the next data analysis. For example, it measures the extent to which a particular discount campaign influenced purchasing behavior. This improves the accuracy of the analytical model. The input for this step is customer behavior data after the implementation of each initiative, and the output is the modified model data that will be reflected in the next analysis.

[0519] 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.

[0520] This invention combines a system that collects and analyzes customer data to provide optimal pricing plans and sales strategies in a timely manner with an emotion engine that recognizes user emotions. The following describes a specific embodiment of the system of this invention.

[0521] Data collection

[0522] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. When a user browses a website, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server in the same manner.

[0523] Collection of emotional data

[0524] The device records the user's emotions through facial expressions, voice, and input text, and sends this data to a server. For example, it uses a webcam and microphone to analyze the user's facial expressions and voice emotional state in real time and sends the results to the server.

[0525] Data preprocessing

[0526] The server integrates received purchase history, browsing history, survey data, and sentiment data, and performs preprocessing to remove incomplete or noisy data. It then converts the data format to one suitable for analysis.

[0527] Customer segmentation

[0528] The server then runs a K-means clustering algorithm on all the cleansed data to classify customers into multiple segments. It identifies the characteristics of each segment (e.g., frequent buyers, buyers of specific categories, etc.).

[0529] Integration of needs prediction and sentiment recognition results

[0530] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next. Furthermore, it integrates sentiment data obtained from the sentiment engine to make predictions that take into account the customer's emotional state.

[0531] Generating pricing plans and sales strategies

[0532] The server designs optimal pricing plans and sales strategies for each customer based on customer segment needs predictions and sentiment data. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies that provide relevant new product information and special coupons to customer segments with specific interests.

[0533] Timely distribution of measures

[0534] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit a website.

[0535] Monitoring the effectiveness of the measures and providing feedback.

[0536] After each measure is implemented, the server monitors its effects. Specifically, it tracks changes in purchasing and browsing behavior as a result of the measures and collects data. For example, it measures how frequently customers who participated in a particular discount campaign started purchasing products. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0537] This system utilizes emotional data to more accurately predict customer needs and provide optimal pricing plans and sales strategies. This is expected to further improve customer satisfaction and brand strength.

[0538] The following describes the processing flow.

[0539] Step 1: Data Collection

[0540] The device records purchase information (product ID, price, purchase date and time, etc.) when a user buys a product from an online store.

[0541] The device records user behavior data (such as the ID of the product viewed, the date and time of viewing, and the duration of time spent on the site) when the user browses a website.

[0542] The device records the user's response data when they answer a survey.

[0543] The device periodically sends all recorded data to the server.

[0544] Step 2: Collecting emotional data

[0545] The device records emotions from the user's facial expressions, voice, and input text.

[0546] The device uses a webcam and microphone to analyze the user's facial expressions and emotional state in real time, and sends the results to a server.

[0547] Step 3: Data Preprocessing

[0548] The server integrates the received purchase history, browsing history, survey data, and sentiment data, and performs preprocessing to remove incomplete or noisy data.

[0549] The server converts the data into a format suitable for analysis.

[0550] Step 4: Customer Segmentation

[0551] The server then runs a K-means clustering algorithm on all the cleansed data to classify customers into multiple segments.

[0552] The server identifies the characteristics of each segment (e.g., frequent buyers, buyers in specific categories, etc.).

[0553] Step 5: Integrating Needs Prediction and Sentiment Recognition Results

[0554] The server applies machine learning algorithms such as random forests and neural networks to predict purchasing needs for each customer segment.

[0555] The server integrates emotional data obtained from the emotion engine and makes predictions that take into account the customer's emotional state.

[0556] Step 6: Generate pricing plans and sales strategies.

[0557] The server designs the optimal pricing plan and sales strategy for each customer based on customer segment needs predictions and sentiment data.

[0558] The server designs discount plans for frequent customers, offering discounts for purchasing a certain number of items in a specific product category within a set period.

[0559] The server designs sales strategies that provide relevant new product information and special offer coupons to customer segments with specific interests.

[0560] Step 7: Timely distribution of measures

[0561] The server delivers the generated pricing plans and sales strategies to the terminals in real time.

[0562] The server sends a push notification to the user's smartphone, informing them of the new discount campaign.

[0563] The server instructs the device to display individually optimized advertising banners and promotional messages when a user visits a website.

[0564] Step 8: Monitoring the effectiveness of the measures

[0565] The server monitors changes in user purchasing and browsing behavior after each measure is implemented.

[0566] The server analyzes in detail the purchase frequency and category changes of customers who have taken advantage of specific discount campaigns.

[0567] Step 9: Optimization through feedback

[0568] The server feeds the monitoring results back into the data analysis model and adjusts the parameters of the analysis model.

[0569] The server incorporates the feedback into the design of future measures, thereby improving the effectiveness of those measures.

[0570] Through these processing steps, the system utilizes customer sentiment data to make more specific and accurate predictions of customer needs, providing optimal pricing plans and sales strategies in a timely manner, thereby improving customer satisfaction and brand strength.

[0571] (Example 2)

[0572] 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".

[0573] Traditional systems have limitations in collecting and analyzing customer data, making it particularly difficult to generate optimal pricing plans and sales strategies that take into account customer emotional states. Furthermore, the inability to adequately distribute strategies in real time and provide feedback on their effectiveness hindered improvements in customer satisfaction and strengthened brand power. To address these challenges, it is crucial to integrate emotional data in addition to customer data to enable real-time strategy distribution and effectiveness monitoring.

[0574] 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.

[0575] In this invention, the server includes means for integrating and pre-processing customer data and sentiment data; means for classifying customers into segments based on the pre-processed data; means for predicting purchases for each segment and generating optimal pricing plans and sales strategies for each customer, taking sentiment data into consideration; means for delivering the generated pricing plans and sales strategies to customers in real time; and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This enables more accurate prediction of customer needs and the timely provision of personalized pricing plans and sales strategies.

[0576] "Customer data" refers to information such as a customer's purchase history, website browsing history, and survey results.

[0577] "Emotional data" refers to information about a user's emotional state, analyzed from their facial expressions, voice, and text.

[0578] "Preprocessing" refers to the process of integrating received data, removing incomplete data and noise, and converting it into a format suitable for analysis.

[0579] A "segment" refers to a group of customers classified based on common characteristics.

[0580] A "clustering algorithm" refers to a method of classifying data into multiple clusters based on common properties or patterns.

[0581] "Purchase forecasting" refers to the process of predicting what products or services a customer is likely to buy next.

[0582] A "pricing plan" refers to the pricing structure or discount plan offered to customers.

[0583] "Sales strategies" refer to promotional and marketing activities conducted for specific segments or customers.

[0584] "Real-time" refers to processing or delivering information immediately.

[0585] "Monitoring" refers to the process of continuously tracking the effects of a measure and changes in customer behavior after its implementation, and collecting data accordingly.

[0586] "Feedback" refers to the process of using monitoring results to inform future data analysis and strategy development.

[0587] This invention relates to a system that collects and analyzes customer data and emotional data, and based on that, provides optimal pricing plans and sales strategies in a timely manner. Specific embodiments for carrying out this invention are described below.

[0588] Specific methods for data collection

[0589] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, it captures user actions by embedding JavaScript code in web pages. It also uses the Google Analytics API to obtain website browsing history and time spent on the site. Purchase history includes user ID, purchase date and time, product ID, price, etc.

[0590] Collection and analysis of emotional data

[0591] The device collects emotional data through the user's facial expressions, voice, and input text, and sends this data to the server. It uses a webcam to perform facial expression analysis using the OpenCV library, and a microphone to convert speech to text using the Google Speech-to-Text API, which is then analyzed.

[0592] Data preprocessing

[0593] The server integrates and preprocesses the collected purchase history, browsing history, survey data, and sentiment data. This process includes data integration using the Python Pandas library, imputation of incomplete data, and removal of outliers.

[0594] Customer segmentation

[0595] The server uses the K-means clustering algorithm to classify customers into multiple segments based on the pre-processed data. This algorithm uses the Scikit-learn library.

[0596] Integration of needs prediction and emotion recognition results

[0597] The server uses random forests and neural network models to predict which products a specific customer segment is likely to purchase next. This analysis utilizes TensorFlow and Scikit-learn. Furthermore, it integrates the results of an emotion engine, taking into account the customer's emotional state to make more accurate predictions.

[0598] Generating pricing plans and sales strategies

[0599] The server designs optimal pricing plans and sales strategies for each customer based on predictive and sentiment data. For example, it might generate a plan for frequent buyers offering a 10% discount for monthly purchases of ¥10,000 or more. Other sales strategies include providing new product information and special coupons.

[0600] Timely distribution of measures

[0601] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it uses Firebase Cloud Messaging to send push notifications to smartphones announcing new discount campaigns.

[0602] Monitoring the effectiveness of the measures and providing feedback.

[0603] The server monitors the effectiveness of each measure after its implementation and tracks changes in purchasing and browsing behavior. This monitoring data is then incorporated into subsequent data analysis to improve the system's accuracy.

[0604] Examples of prompt statements

[0605] Here is a concrete example of an input prompt statement for a generative AI model:

[0606] "Create a model to predict what other products customers who purchase the next item tend to buy together. Available data includes purchase history (user ID, purchase date and time, product ID, price), browsing history (user ID, browsing date and time, product ID, time spent), sentiment data (user ID, facial expression / voice sentiment score), and survey data (user ID, response content)."

[0607] The above describes the embodiment for carrying out the invention. This system enables more accurate prediction of customer needs and the timely provision of personalized pricing plans and sales strategies.

[0608] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0609] Step 1:

[0610] The device records the user's purchasing and browsing behavior and sends this data to the server in real time. Specifically, JavaScript code embedded in the web page captures the user's actions (product purchase, page viewing). Inputs include user ID, purchase date and time, product ID, price, viewing date and time, and time spent on the page. This input data is sent to the server via an HTTP request, and the output is all purchase and browsing history data stored on the server.

[0611] Step 2:

[0612] The device collects the user's facial expressions, voice, and input text as emotion data and sends it to the server in real time. Specifically, it analyzes facial expressions using a webcam and the OpenCV library, and converts audio data collected by the microphone into text using the Google Speech-to-Text API. The inputs are facial expression data (images), audio data (audio files), and text data (converted audio text). This input data is sent to the server in real time using WebSocket, and the output is the emotion-analyzed data stored on the server.

[0613] Step 3:

[0614] The server integrates and preprocesses the received purchase history, browsing history, survey data, and sentiment data. Specifically, it uses the Python Pandas library to cleanse the data and remove incomplete data and noise. The inputs include purchase history data, browsing history data, survey data, and sentiment data. This data is read from log files and databases, and after data cleansing and format conversion, the cleaned integrated data is output.

[0615] Step 4:

[0616] The server performs customer segmentation based on pre-processed data. Specifically, it uses the K-means clustering algorithm to classify customers into multiple segments. This process is performed using the Scikit-learn library. The input is pre-processed integrated data. This data is input to the K-means clustering algorithm, and the output is information on which cluster each customer belongs to.

[0617] Step 5:

[0618] The server performs customer purchase predictions based on clustered segment data. Specifically, it uses random forests and neural network models to analyze and predict which products customers in each segment are likely to purchase next. TensorFlow is used for this analysis. The input consists of segmented customer data and sentiment data. This input data is passed through a machine learning model to obtain prediction results as output.

[0619] Step 6:

[0620] The server generates optimal pricing plans and sales strategies for each customer based on prediction results and sentiment data. Specifically, it executes a script using Python to generate pricing plans and promotional strategies based on various conditions. The input is purchase prediction data and sentiment data. The output is data on pricing plans and sales strategies optimized for each customer.

[0621] Step 7:

[0622] The server delivers generated pricing plans and sales promotions to devices in real time. Specifically, it uses Firebase Cloud Messaging to send push notifications to users' smartphones announcing new discount campaigns. The inputs are optimized pricing plan and sales promotion data and customer IDs. The output is a push notification sent to the device.

[0623] Step 8:

[0624] The server monitors the effectiveness of each initiative and feeds the results back into the next data analysis. Specifically, it uses Google Analytics and internally developed monitoring tools to track changes in purchasing and browsing behavior after an initiative is implemented. The input is purchase history data and browsing history data after the initiative is implemented. The output is data on the effectiveness of the initiative, which is used in the next analysis model.

[0625] (Application Example 2)

[0626] 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."

[0627] While many online stores already offer optimal pricing plans and sales strategies based on user purchasing behavior and website browsing history, it is believed that even more accurate personalization is possible by considering customer emotions. However, current systems do not collect and analyze emotional data, making it difficult to provide optimal suggestions based on the customer's actual emotional state.

[0628] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for collecting and analyzing user emotion data through a webcam and microphone, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to design and provide optimal pricing plans and sales strategies that take into account the emotional state of the customer.

[0629] "Customer data" refers to information including users' purchasing behavior, website browsing history, and survey results.

[0630] "Analysis" is the process of analyzing patterns and trends based on collected data to gain insights.

[0631] A "segment" refers to a group of customers that share common characteristics or behaviors.

[0632] A "pricing plan" refers to the price structure or fee scheme for a specific product or service.

[0633] "Sales strategies" refer to promotional and marketing methods aimed at encouraging customers to make a purchase.

[0634] "Emotional data" refers to information about a user's psychological state obtained through their facial expressions, voice, and other means.

[0635] A "webcam" is a camera device used to capture a user's facial expressions in real time.

[0636] A "microphone" is a device used to capture the user's voice.

[0637] "Real-time" refers to the immediate processing and distribution of information and data without any time lag.

[0638] "Monitoring" refers to the act of continuously monitoring and evaluating whether policies and systems are functioning appropriately.

[0639] This invention relates to an emotion-recognizing personalized shopping assistant system. The following describes how the system of this invention will be specifically implemented.

[0640] The server collects customer data, including users' purchasing behavior, website browsing history, and survey results. This data includes information such as the date and time of purchase, product ID, price, browsing history, and time spent on the site. Data collected through the device is transmitted to and stored on the server in real time.

[0641] The server analyzes the collected customer data and uses the K-means clustering algorithm to classify customers into segments. Each segment is categorized into customer groups with specific characteristics, such as frequent buyers or buyers of a particular category.

[0642] Furthermore, the server collects user emotional data through the webcam and microphone, and uses an emotion recognition engine to analyze facial expressions and voice. This allows the user's real-time emotional state to be obtained as numerical data, which is also sent to the server.

[0643] The server generates optimal pricing plans and sales strategies for each customer based on the analysis results. In this process, machine learning algorithms such as random forests and neural networks are used to predict promotions and discount rates for specific products, and sentiment data is also integrated to provide more personalized recommendations.

[0644] For example, if a user spends a long time browsing a particular product page and expresses feelings of "joy" during that time, the server will recommend a 10% discount coupon for that product to that user. This information is delivered to the device in real time as a push notification or advertising banner.

[0645] After a measure is implemented, the server monitors its effects and records changes in purchasing and browsing behavior. For example, it measures how frequently customers who participated in a specific discount campaign began purchasing products, and by incorporating these monitoring results into subsequent data analysis, it improves the accuracy of the analysis model and the effectiveness of the measures.

[0646] The following software and hardware will be used for the servers and terminals.

[0647] Hardware required: Smartphone, webcam, microphone

[0648] Software used: Python, TensorFlow, Keras, OpenCV, Pushbullet

[0649] A concrete example of its use is a process where, if a user spends a long time browsing a particular product page or frequently purchases items from a certain category, a push notification offering a "10% discount coupon for a specific product" is sent based on that information and the user's sentiment data.

[0650] An example of a prompt is: "Create Python code that estimates the optimal pricing plan based on the user's purchase history and sentiment data, and sends a push notification."

[0651] In this way, it is possible to design and provide optimal pricing plans and sales strategies that take into account the emotional state of the customer, thereby improving customer satisfaction and maximizing sales.

[0652] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0653] Step 1:

[0654] Customer data collection

[0655] The device collects user purchasing behavior, website browsing history, and survey results. When a user purchases a product, information such as the purchase date and time, product ID, and price is recorded, and website browsing history and time spent on the site are also collected. This data is transmitted to the server in real time. Input data includes purchase history, browsing history, and survey data, while output data is customer data stored on the server.

[0656] Step 2:

[0657] Collection of emotional data

[0658] The device uses a webcam and microphone to collect the user's facial expressions and voice in real time. An emotion recognition engine analyzes the user's facial expressions and voice while they are using the online store and sends the data to the server as emotion data. The input data consists of facial expression data and voice data, while the output data is the emotion data stored on the server.

[0659] Step 3:

[0660] Data preprocessing

[0661] The server integrates collected purchase history, browsing history, survey data, and sentiment data, removing incomplete and noisy data. It converts the data format into a format that can be analyzed by machine learning algorithms. The input data consists of raw customer data and sentiment data, while the output data is cleansed and in an analyzable format.

[0662] Step 4:

[0663] Customer segmentation

[0664] The server runs the K-means clustering algorithm based on the cleansed data, classifying customers into multiple segments. The input data is the cleansed data, and the output data is information about each customer segment.

[0665] Step 5:

[0666] Integration of needs prediction and emotion recognition results

[0667] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next. Simultaneously, it integrates sentiment data to make predictions that take into account the user's emotional state. Input data includes segment information and sentiment data, while output data consists of predicted product categories and discount rates.

[0668] Step 6:

[0669] Generating pricing plans and sales strategies

[0670] The server designs optimal pricing plans and sales strategies for each customer based on customer segment needs prediction results and sentiment data. For example, it might suggest discount coupons for specific products to frequent customers. The input data consists of needs prediction results and sentiment data, while the output data is the designed pricing plan and sales strategy.

[0671] Step 7:

[0672] Timely distribution of measures

[0673] The server delivers generated pricing plans and sales strategies to users' smartphones as push notifications in real time. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit websites. Input data consists of pricing plans and sales strategies, while output data consists of push notifications and advertising banners.

[0674] Step 8:

[0675] Monitoring the effectiveness of the measures and providing feedback.

[0676] The server monitors the effects of each measure after it has been implemented. It tracks changes in purchasing and browsing behavior as a result of the measures and collects this data. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated. The input data is behavioral data after the implementation of the measures, and the output data is used to improve the analysis model.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] [Third Embodiment]

[0681] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0682] 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.

[0683] 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).

[0684] 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.

[0685] 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.

[0686] 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).

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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".

[0693] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. Specific embodiments for implementing the system of this invention are described below.

[0694] Data collection

[0695] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. When a user browses a website, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server in the same manner.

[0696] Data Analysis

[0697] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. It then applies clustering algorithms to analyze the data and classify customers into segments. For example, K-means clustering is used to divide customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms are used to predict the future needs of customers in each segment. Specifically, random forests and neural networks are used to predict the product categories and applicable discount rates that a particular customer segment is likely to purchase next.

[0698] Generating pricing plans and sales strategies

[0699] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies for customer segments with specific interests, providing relevant new product information and special coupons.

[0700] Timely distribution of measures

[0701] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit a website.

[0702] Monitoring and feedback on the effects

[0703] After each measure is implemented, the server monitors its effects. Specifically, it tracks changes in purchasing and browsing behavior as a result of the measures and collects data. For example, it measures how frequently customers who participated in a particular discount campaign started purchasing products. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0704] In this way, the system of the present invention can provide optimal pricing plans and sales strategies based on customer needs in a timely manner, thereby improving customer satisfaction and brand strength.

[0705] The following describes the processing flow.

[0706] Step 1: Data Collection

[0707] The device records purchase information (product ID, price, purchase date and time, etc.) when a user buys a product from an online store.

[0708] The device records user behavior data (such as the ID of the product viewed, the date and time of viewing, and the duration of time spent on the site) when the user browses a website.

[0709] The device records the user's response data when they answer a survey.

[0710] The device periodically sends all recorded data to the server.

[0711] Step 2: Data preprocessing

[0712] The server integrates the received purchase history, browsing history, and survey data.

[0713] The server performs a cleansing process to remove missing or noisy data.

[0714] The server converts the data format into a format suitable for analysis.

[0715] Step 3: Customer Segmentation

[0716] The server then runs the K-means clustering algorithm on the cleansed data to classify customers into multiple segments.

[0717] The server identifies the characteristics of each segment (e.g., frequent buyers, buyers in specific categories, etc.).

[0718] Step 4: Needs Prediction

[0719] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next.

[0720] The server uses the prediction results to identify the needs of each segment.

[0721] Step 5: Generating pricing plans and sales strategies

[0722] The server designs optimal pricing plans and sales strategies for each customer segment based on predicted needs.

[0723] For example, a server might design a discount plan for frequent customers that offers discounts for purchasing a certain number of items in a specific product category within a set period.

[0724] The server stores the designed plans and strategies in a database.

[0725] Step 6: Timely distribution of measures

[0726] The server delivers the generated pricing plans and sales strategies to the terminals in real time.

[0727] For example, the server sends a push notification to the user's smartphone informing them of a new discount campaign.

[0728] The server instructs the device to display individually optimized advertising banners and promotional messages when a user visits a website.

[0729] Step 7: Monitoring the effectiveness of the measures

[0730] The server monitors changes in user purchasing and browsing behavior after each measure is implemented.

[0731] The server analyzes in detail the purchase frequency and category changes of customers who have taken advantage of specific discount campaigns.

[0732] Step 8: Optimization through feedback

[0733] The server feeds the monitoring results back into the data analysis model and adjusts the parameters of the analysis model.

[0734] The server will use this feedback to improve the effectiveness of future measures.

[0735] Through these processing steps, the system provides timely and optimal pricing plans and sales strategies based on customer needs, thereby improving customer satisfaction and brand strength.

[0736] (Example 1)

[0737] 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."

[0738] Traditional marketing systems struggled to accurately understand customer purchasing behavior and preferences in real time and provide individually optimized pricing plans and sales strategies. Furthermore, the lack of mechanisms to continuously monitor the effectiveness of strategies and incorporate that data into subsequent analyses prevented improvements in the accuracy and effectiveness of those strategies.

[0739] 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.

[0740] In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for distributing the generated pricing plans and sales strategies to the customer's communication device in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to quickly and accurately grasp customer purchasing behavior and preferences and provide individually optimized pricing plans and sales strategies in a timely manner.

[0741] "Customer data" refers to information such as a customer's purchase history in commercial transactions, their browsing history on internet sites, and survey results.

[0742] "Means of collection" refers to devices or software that have the function of acquiring customer data and transmitting it to a server.

[0743] "Means of analysis" refers to devices or software that have the function of analyzing collected customer data and classifying customers based on similar behavioral patterns and interests.

[0744] A "clustering algorithm" is a statistical method for grouping sets of data, and includes techniques such as K-means and hierarchical clustering.

[0745] A "pricing plan" refers to sales conditions such as pricing and discounts offered to customers under specific circumstances.

[0746] "Sales strategies" refer to specific sales plans and promotions aimed at getting customers to purchase a particular product or service.

[0747] "Means of real-time delivery" refers to a device or software that has the function of immediately transmitting information on pricing plans and sales strategies generated based on analysis results to the customer's communication device.

[0748] "Monitoring means" refers to devices or software that have the function of tracking the effectiveness of implemented sales measures and collecting and analyzing the results.

[0749] A "segment" refers to a group of customers that share common characteristics or behaviors.

[0750] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. Specific embodiments for implementing the system of this invention are described below.

[0751] System Overview

[0752] This system operates by coordinating servers and terminals to collect and analyze customer data, generate and distribute optimal pricing plans and sales strategies, and monitor their effectiveness.

[0753] Data collection

[0754] The device records the user's purchasing behavior on online stores and browsing behavior on internet sites, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. Similarly, when a user browses an internet site, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0755] Data Analysis

[0756] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. Then, K-means clustering is used to classify customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms such as random forests and neural networks are used to predict the future needs and likely product categories for each segment.

[0757] Generating pricing plans and sales strategies

[0758] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also creates sales strategies that provide relevant new product information and special coupons to customer segments with specific interests.

[0759] Timely distribution of measures

[0760] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit websites.

[0761] Monitoring and feedback on the effects

[0762] The server monitors the effectiveness of each measure after it has been implemented. For example, it measures how frequently customers who participated in a particular discount campaign began purchasing products. These monitoring results are then incorporated into the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures being generated.

[0763] Specific example

[0764] A user purchases the latest smartphone from an online store. At that time, the device sends data such as the purchase date and time, product ID, and price to the server. The server then integrates and analyzes this data with other user data to predict that the user is likely to purchase a smartphone case next time. Based on this prediction, the server generates a plan offering the user a specific smartphone case at a discounted price and delivers it to the user's smartphone via push notification.

[0765] Example of a prompt

[0766] "Based on the analysis of customer data, we predict the product that the customer is most likely to purchase next and generate the optimal price discount plan for that product."

[0767] This system can improve customer satisfaction and brand strength by providing optimal pricing plans and sales strategies based on customer needs in a timely manner.

[0768] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0769] Step 1: Data Collection

[0770] When a user purchases an item from an online store, the device records data such as the purchase date and time, product ID, and price. For example, if a user purchases a "latest smartphone," this information will be recorded. The device then sends the recorded purchase data to a server. Additionally, when a user browses a website, the device records their browsing history and time spent on the site, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0771] Input: User-generated purchase history, browsing history, and survey results.

[0772] Output: Customer data sent to the server

[0773] Step 2: Data Integration and Preprocessing

[0774] The server integrates all received customer data. This includes the following specific actions: pre-processing to remove incomplete or noisy data. For example, missing data is either filled in or deleted. Noisy data is also filtered out.

[0775] Input: Raw customer data sent from the terminal.

[0776] Output: Pre-processed customer data

[0777] Step 3: Classification of Customer Segments

[0778] The server applies a clustering algorithm based on pre-processed customer data to classify customers into segments. For example, K-means clustering is used to divide customers into groups with similar purchasing behaviors or interests.

[0779] Input: Pre-processed customer data

[0780] Output: Customer data categorized by segment

[0781] Step 4: Predicting future needs

[0782] The server uses machine learning algorithms (such as random forests or neural networks) to predict future needs based on customer data categorized into segments. For example, it calculates the probability that a "customer group that frequently purchases products" will next purchase a "smartphone case."

[0783] Input: Customer data categorized by segment

[0784] Output: Forecast data for future needs for each segment

[0785] Step 5: Generating pricing plans and sales strategies

[0786] The server generates optimal pricing plans and sales strategies for each segment based on future needs prediction data. For example, for "frequent buyers," it designs a discount plan for customers who purchase a certain number of specific products within a certain period. It also generates new product information and special offer coupons.

[0787] Input: Future needs forecast data

[0788] Output: Generated pricing plans and sales strategies

[0789] Step 6: Timely distribution of plans and measures

[0790] The server delivers generated pricing plans and sales promotions to the device in real time. For example, it sends "discount information on smartphone cases" to the user's smartphone via push notification. Furthermore, it displays individually optimized advertising banners and promotional messages when the user visits a website.

[0791] Input: Generated pricing plans and sales strategies

[0792] Output: Pricing plans and sales promotions delivered to user terminals

[0793] Step 7: Monitoring and Feedback on Effects

[0794] The server monitors the effectiveness of each measure after it has been implemented. For example, it tracks how frequently customers who participated in a particular discount campaign began purchasing products. These monitoring results are then incorporated into the next data analysis.

[0795] Input: Effectiveness data of implemented sales measures

[0796] Output: Monitored results data and feedback data for accuracy improvement.

[0797] As a result, this system can provide optimal pricing plans and sales strategies based on customer behavior in real time.

[0798] (Application Example 1)

[0799] 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."

[0800] Traditional purchasing data analysis systems have difficulty providing timely product recommendations and sales strategies that reflect individual customer needs. Furthermore, these systems are primarily designed for desktop environments and do not offer real-time information via mobile devices such as smartphones and tablets. Therefore, improving the quality of the customer experience and stimulating purchasing intent has been challenging.

[0801] 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.

[0802] In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, means for being installed on mobile devices such as smartphones and tablets to provide individually optimized product suggestions and campaigns, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to provide optimal product suggestions and sales strategies that meet the individual needs of customers in real time.

[0803] "Customer data" refers to information about individual customers, such as their purchase history, website browsing history, and survey results.

[0804] "Analysis" refers to the process of processing and analyzing data using collected customer data to identify customer behavior and trends.

[0805] A "segment" refers to a group of customers who have similar purchasing behaviors or interests.

[0806] A "pricing plan" refers to the pricing and discount conditions offered to customers as a sales promotion tool.

[0807] "Sales strategies" refer to means of sales promotion taken towards customers, such as product proposals and campaign implementation.

[0808] "Mobile devices such as smartphones and tablets" refer to portable electronic devices that can receive and display information in real time using communication functions.

[0809] "Real-time" refers to providing results immediately after information has been collected and analyzed.

[0810] "Monitoring" refers to continuously observing the effects of a policy and measuring its fluctuations.

[0811] A "clustering algorithm" refers to a mathematical method for grouping (clustering) data based on specific criteria.

[0812] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. The following describes in detail how to implement the system of this invention.

[0813] Data collection

[0814] The server has the function of collecting customer data from the terminal. This data includes purchase history, website browsing history, and survey results. The terminal records the user's purchasing behavior on the online store and website browsing behavior, and sends this data to the server. For example, when a user purchases a product, information such as the purchase date and time, product ID, and price is collected and sent to the server. In addition, the history of product pages viewed by the user on the website, the time spent on each page, and the number of times they were viewed are also collected and sent to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[0815] Data Analysis

[0816] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. It then applies clustering algorithms to analyze the data and segment customers. Specifically, K-means clustering is used to divide customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms are used to predict the future needs of customers in each segment. In particular, generative AI models such as random forests and neural networks are used to predict the product categories and applicable discount rates that specific customer segments are likely to purchase next.

[0817] Generating pricing plans and sales strategies

[0818] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies for customer segments with specific interests, providing relevant new product information and special coupons.

[0819] Timely distribution of measures

[0820] The device has a means of notifying customers in real time about generated pricing plans and sales promotions. Specifically, it sends push notifications to users' smartphones and tablets to inform them about new discount campaigns. It also displays individually optimized advertising banners and promotional messages when users visit websites.

[0821] Monitoring and feedback on the effects

[0822] The server monitors the effectiveness of each measure after it has been implemented. For example, it measures how frequently customers who participated in a particular discount campaign began purchasing products, and incorporates these monitoring results into the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0823] This makes it possible to provide optimal product suggestions and sales strategies tailored to each customer's individual needs in real time.

[0824] Example of a prompt:

[0825] We want to use clustering algorithms and machine learning models to suggest the most suitable sales strategies based on users' purchase and browsing history. Design a system that predicts the product categories and applicable discount rates that users will be interested in next, and generates optimal pricing plans and promotional offers.

[0826] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0827] Step 1:

[0828] Data collection

[0829] The terminal records the user's purchase history, website browsing history, and survey results. For example, when a user purchases a product, it collects information such as the purchase date and time, product ID, and price, and sends it to the server. This allows the server to receive detailed data for each customer. The input data is the customer's behavioral history, and the output is the raw data sent to the server.

[0830] Step 2:

[0831] Data Integration and Preprocessing

[0832] The server integrates the received customer data and performs preprocessing to remove incomplete data and noise. Specifically, it imputes missing values ​​and detects and corrects outliers. This results in clean data suitable for analysis. The input data is the raw data before integration, and the output is the clean data.

[0833] Step 3:

[0834] Customer segment clustering

[0835] The server applies a clustering algorithm (e.g., K-means clustering) to the integrated clean data to classify customers into segments. For example, customers with similar purchasing behavior or browsing history are grouped together. The input for this step is clean data, and the output is segmented customer data.

[0836] Step 4:

[0837] Needs forecasting

[0838] The server uses a generative AI model (e.g., random forest or neural network) based on segmented customer data to predict the product categories and applicable discount rates that customers in each segment are likely to purchase next. The input for this step is segmented customer data, and the output is the predicted customer needs for each segment.

[0839] Step 5:

[0840] Generating pricing plans and sales strategies

[0841] The server generates optimal pricing plans and sales strategies based on customer needs predictions. For example, it might offer a "10% off next purchase" plan to frequent customers and provide discount coupons for related new products to customers interested in specific items. The input for this step is the customer needs prediction, and the output is pricing plans and sales strategies tailored to each customer.

[0842] Step 6:

[0843] Timely distribution of measures

[0844] The device notifies users in real time of pricing plans and sales promotions received from the server. Specifically, it sends push notifications to users' smartphones and tablets, for example, informing them of an offer such as "10% off your next purchase." The input for this step is individually optimized sales promotion information, and the output is push notifications and advertising banners sent to users.

[0845] Step 7:

[0846] Monitoring and feedback on the effects

[0847] The server monitors the effectiveness of each initiative and incorporates the results into the next data analysis. For example, it measures the extent to which a particular discount campaign influenced purchasing behavior. This improves the accuracy of the analytical model. The input for this step is customer behavior data after the implementation of each initiative, and the output is the modified model data that will be reflected in the next analysis.

[0848] 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.

[0849] This invention combines a system that collects and analyzes customer data to provide optimal pricing plans and sales strategies in a timely manner with an emotion engine that recognizes user emotions. The following describes a specific embodiment of the system of this invention.

[0850] Data collection

[0851] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. When a user browses a website, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server in the same manner.

[0852] Collection of emotional data

[0853] The device records the user's emotions through facial expressions, voice, and input text, and sends this data to a server. For example, it uses a webcam and microphone to analyze the user's facial expressions and voice emotional state in real time and sends the results to the server.

[0854] Data preprocessing

[0855] The server integrates received purchase history, browsing history, survey data, and sentiment data, and performs preprocessing to remove incomplete or noisy data. It then converts the data format to one suitable for analysis.

[0856] Customer segmentation

[0857] The server then runs a K-means clustering algorithm on all the cleansed data to classify customers into multiple segments. It identifies the characteristics of each segment (e.g., frequent buyers, buyers of specific categories, etc.).

[0858] Integration of needs prediction and sentiment recognition results

[0859] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next. Furthermore, it integrates sentiment data obtained from the sentiment engine to make predictions that take into account the customer's emotional state.

[0860] Generating pricing plans and sales strategies

[0861] The server designs optimal pricing plans and sales strategies for each customer based on customer segment needs predictions and sentiment data. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies that provide relevant new product information and special coupons to customer segments with specific interests.

[0862] Timely distribution of measures

[0863] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit a website.

[0864] Monitoring the effectiveness of the measures and providing feedback.

[0865] After each measure is implemented, the server monitors its effects. Specifically, it tracks changes in purchasing and browsing behavior as a result of the measures and collects data. For example, it measures how frequently customers who participated in a particular discount campaign started purchasing products. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[0866] This system utilizes emotional data to more accurately predict customer needs and provide optimal pricing plans and sales strategies. This is expected to further improve customer satisfaction and brand strength.

[0867] The following describes the processing flow.

[0868] Step 1: Data Collection

[0869] The device records purchase information (product ID, price, purchase date and time, etc.) when a user buys a product from an online store.

[0870] The device records user behavior data (such as the ID of the product viewed, the date and time of viewing, and the duration of time spent on the site) when the user browses a website.

[0871] The device records the user's response data when they answer a survey.

[0872] The device periodically sends all recorded data to the server.

[0873] Step 2: Collecting emotional data

[0874] The device records emotions from the user's facial expressions, voice, and input text.

[0875] The device uses a webcam and microphone to analyze the user's facial expressions and emotional state in real time, and sends the results to a server.

[0876] Step 3: Data Preprocessing

[0877] The server integrates the received purchase history, browsing history, survey data, and sentiment data, and performs preprocessing to remove incomplete or noisy data.

[0878] The server converts the data into a format suitable for analysis.

[0879] Step 4: Customer Segmentation

[0880] The server then runs a K-means clustering algorithm on all the cleansed data to classify customers into multiple segments.

[0881] The server identifies the characteristics of each segment (e.g., frequent buyers, buyers in specific categories, etc.).

[0882] Step 5: Integrating Needs Prediction and Sentiment Recognition Results

[0883] The server applies machine learning algorithms such as random forests and neural networks to predict purchasing needs for each customer segment.

[0884] The server integrates emotional data obtained from the emotion engine and makes predictions that take into account the customer's emotional state.

[0885] Step 6: Generate pricing plans and sales strategies.

[0886] The server designs the optimal pricing plan and sales strategy for each customer based on customer segment needs predictions and sentiment data.

[0887] The server designs discount plans for frequent customers, offering discounts for purchasing a certain number of items in a specific product category within a set period.

[0888] The server designs sales strategies that provide relevant new product information and special offer coupons to customer segments with specific interests.

[0889] Step 7: Timely distribution of measures

[0890] The server delivers the generated pricing plans and sales strategies to the terminals in real time.

[0891] The server sends a push notification to the user's smartphone, informing them of the new discount campaign.

[0892] The server instructs the device to display individually optimized advertising banners and promotional messages when a user visits a website.

[0893] Step 8: Monitoring the effectiveness of the measures

[0894] The server monitors changes in user purchasing and browsing behavior after each measure is implemented.

[0895] The server analyzes in detail the purchase frequency and category changes of customers who have taken advantage of specific discount campaigns.

[0896] Step 9: Optimization through feedback

[0897] The server feeds the monitoring results back into the data analysis model and adjusts the parameters of the analysis model.

[0898] The server incorporates the feedback into the design of future measures, thereby improving the effectiveness of those measures.

[0899] Through these processing steps, the system utilizes customer sentiment data to make more specific and accurate predictions of customer needs, providing optimal pricing plans and sales strategies in a timely manner, thereby improving customer satisfaction and brand strength.

[0900] (Example 2)

[0901] 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."

[0902] Traditional systems have limitations in collecting and analyzing customer data, making it particularly difficult to generate optimal pricing plans and sales strategies that take into account customer emotional states. Furthermore, the inability to adequately distribute strategies in real time and provide feedback on their effectiveness hindered improvements in customer satisfaction and strengthened brand power. To address these challenges, it is crucial to integrate emotional data in addition to customer data to enable real-time strategy distribution and effectiveness monitoring.

[0903] 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.

[0904] In this invention, the server includes means for integrating and pre-processing customer data and sentiment data; means for classifying customers into segments based on the pre-processed data; means for predicting purchases for each segment and generating optimal pricing plans and sales strategies for each customer, taking sentiment data into consideration; means for delivering the generated pricing plans and sales strategies to customers in real time; and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This enables more accurate prediction of customer needs and the timely provision of personalized pricing plans and sales strategies.

[0905] "Customer data" refers to information such as a customer's purchase history, website browsing history, and survey results.

[0906] "Emotional data" refers to information about a user's emotional state, analyzed from their facial expressions, voice, and text.

[0907] "Preprocessing" refers to the process of integrating received data, removing incomplete data and noise, and converting it into a format suitable for analysis.

[0908] A "segment" refers to a group of customers classified based on common characteristics.

[0909] A "clustering algorithm" refers to a method of classifying data into multiple clusters based on common properties or patterns.

[0910] "Purchase forecasting" refers to the process of predicting what products or services a customer is likely to buy next.

[0911] A "pricing plan" refers to the pricing structure or discount plan offered to customers.

[0912] "Sales strategies" refer to promotional and marketing activities conducted for specific segments or customers.

[0913] "Real-time" refers to processing or delivering information immediately.

[0914] "Monitoring" refers to the process of continuously tracking the effects of a measure and changes in customer behavior after its implementation, and collecting data accordingly.

[0915] "Feedback" refers to the process of using monitoring results to inform future data analysis and strategy development.

[0916] This invention relates to a system that collects and analyzes customer data and emotional data, and based on that, provides optimal pricing plans and sales strategies in a timely manner. Specific embodiments for carrying out this invention are described below.

[0917] Specific methods for data collection

[0918] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, it captures user actions by embedding JavaScript code in web pages. It also uses the Google Analytics API to obtain website browsing history and time spent on the site. Purchase history includes user ID, purchase date and time, product ID, price, etc.

[0919] Collection and analysis of emotional data

[0920] The device collects emotional data through the user's facial expressions, voice, and input text, and sends this data to the server. It uses a webcam to perform facial expression analysis using the OpenCV library, and a microphone to convert speech to text using the Google Speech-to-Text API, which is then analyzed.

[0921] Data preprocessing

[0922] The server integrates and preprocesses the collected purchase history, browsing history, survey data, and sentiment data. This process includes data integration using the Python Pandas library, imputation of incomplete data, and removal of outliers.

[0923] Customer segmentation

[0924] The server uses the K-means clustering algorithm to classify customers into multiple segments based on the pre-processed data. This algorithm uses the Scikit-learn library.

[0925] Integration of needs prediction and emotion recognition results

[0926] The server uses random forests and neural network models to predict which products a specific customer segment is likely to purchase next. This analysis utilizes TensorFlow and Scikit-learn. Furthermore, it integrates the results of an emotion engine, taking into account the customer's emotional state to make more accurate predictions.

[0927] Generating pricing plans and sales strategies

[0928] The server designs optimal pricing plans and sales strategies for each customer based on predictive and sentiment data. For example, it might generate a plan for frequent buyers offering a 10% discount for monthly purchases of ¥10,000 or more. Other sales strategies include providing new product information and special coupons.

[0929] Timely distribution of measures

[0930] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it uses Firebase Cloud Messaging to send push notifications to smartphones announcing new discount campaigns.

[0931] Monitoring the effectiveness of the measures and providing feedback.

[0932] The server monitors the effectiveness of each measure after its implementation and tracks changes in purchasing and browsing behavior. This monitoring data is then incorporated into subsequent data analysis to improve the system's accuracy.

[0933] Examples of prompt statements

[0934] Here is a concrete example of an input prompt statement for a generative AI model:

[0935] "Create a model to predict what other products customers who purchase the next item tend to buy together. Available data includes purchase history (user ID, purchase date and time, product ID, price), browsing history (user ID, browsing date and time, product ID, time spent), sentiment data (user ID, facial expression / voice sentiment score), and survey data (user ID, response content)."

[0936] The above describes the embodiment for carrying out the invention. This system enables more accurate prediction of customer needs and the timely provision of personalized pricing plans and sales strategies.

[0937] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0938] Step 1:

[0939] The device records the user's purchasing and browsing behavior and sends this data to the server in real time. Specifically, JavaScript code embedded in the web page captures the user's actions (product purchase, page viewing). Inputs include user ID, purchase date and time, product ID, price, viewing date and time, and time spent on the page. This input data is sent to the server via an HTTP request, and the output is all purchase and browsing history data stored on the server.

[0940] Step 2:

[0941] The device collects the user's facial expressions, voice, and input text as emotion data and sends it to the server in real time. Specifically, it analyzes facial expressions using a webcam and the OpenCV library, and converts audio data collected by the microphone into text using the Google Speech-to-Text API. The inputs are facial expression data (images), audio data (audio files), and text data (converted audio text). This input data is sent to the server in real time using WebSocket, and the output is the emotion-analyzed data stored on the server.

[0942] Step 3:

[0943] The server integrates and preprocesses the received purchase history, browsing history, survey data, and sentiment data. Specifically, it uses the Python Pandas library to cleanse the data and remove incomplete data and noise. The inputs include purchase history data, browsing history data, survey data, and sentiment data. This data is read from log files and databases, and after data cleansing and format conversion, the cleaned integrated data is output.

[0944] Step 4:

[0945] The server performs customer segmentation based on pre-processed data. Specifically, it uses the K-means clustering algorithm to classify customers into multiple segments. This process is performed using the Scikit-learn library. The input is pre-processed integrated data. This data is input to the K-means clustering algorithm, and the output is information on which cluster each customer belongs to.

[0946] Step 5:

[0947] The server performs customer purchase predictions based on clustered segment data. Specifically, it uses random forests and neural network models to analyze and predict which products customers in each segment are likely to purchase next. TensorFlow is used for this analysis. The input consists of segmented customer data and sentiment data. This input data is passed through a machine learning model to obtain prediction results as output.

[0948] Step 6:

[0949] The server generates optimal pricing plans and sales strategies for each customer based on prediction results and sentiment data. Specifically, it executes a script using Python to generate pricing plans and promotional strategies based on various conditions. The input is purchase prediction data and sentiment data. The output is data on pricing plans and sales strategies optimized for each customer.

[0950] Step 7:

[0951] The server delivers generated pricing plans and sales promotions to devices in real time. Specifically, it uses Firebase Cloud Messaging to send push notifications to users' smartphones announcing new discount campaigns. The inputs are optimized pricing plan and sales promotion data and customer IDs. The output is a push notification sent to the device.

[0952] Step 8:

[0953] The server monitors the effectiveness of each initiative and feeds the results back into the next data analysis. Specifically, it uses Google Analytics and internally developed monitoring tools to track changes in purchasing and browsing behavior after an initiative is implemented. The input is purchase history data and browsing history data after the initiative is implemented. The output is data on the effectiveness of the initiative, which is used in the next analysis model.

[0954] (Application Example 2)

[0955] 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."

[0956] While many online stores already offer optimal pricing plans and sales strategies based on user purchasing behavior and website browsing history, it is believed that even more accurate personalization is possible by considering customer emotions. However, current systems do not collect and analyze emotional data, making it difficult to provide optimal suggestions based on the customer's actual emotional state.

[0957] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for collecting and analyzing user emotion data through a webcam and microphone, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to design and provide optimal pricing plans and sales strategies that take into account the emotional state of the customer.

[0958] "Customer data" refers to information including users' purchasing behavior, website browsing history, and survey results.

[0959] "Analysis" is the process of analyzing patterns and trends based on collected data to gain insights.

[0960] A "segment" refers to a group of customers that share common characteristics or behaviors.

[0961] A "pricing plan" refers to the price structure or fee scheme for a specific product or service.

[0962] "Sales strategies" refer to promotional and marketing methods aimed at encouraging customers to make a purchase.

[0963] "Emotional data" refers to information about a user's psychological state obtained through their facial expressions, voice, and other means.

[0964] A "webcam" is a camera device used to capture a user's facial expressions in real time.

[0965] A "microphone" is a device used to capture the user's voice.

[0966] "Real-time" refers to the immediate processing and distribution of information and data without any time lag.

[0967] "Monitoring" refers to the act of continuously monitoring and evaluating whether policies and systems are functioning appropriately.

[0968] This invention relates to an emotion-recognizing personalized shopping assistant system. The following describes how the system of this invention will be specifically implemented.

[0969] The server collects customer data, including users' purchasing behavior, website browsing history, and survey results. This data includes information such as the date and time of purchase, product ID, price, browsing history, and time spent on the site. Data collected through the device is transmitted to and stored on the server in real time.

[0970] The server analyzes the collected customer data and uses the K-means clustering algorithm to classify customers into segments. Each segment is categorized into customer groups with specific characteristics, such as frequent buyers or buyers of a particular category.

[0971] Furthermore, the server collects user emotional data through the webcam and microphone, and uses an emotion recognition engine to analyze facial expressions and voice. This allows the user's real-time emotional state to be obtained as numerical data, which is also sent to the server.

[0972] The server generates optimal pricing plans and sales strategies for each customer based on the analysis results. In this process, machine learning algorithms such as random forests and neural networks are used to predict promotions and discount rates for specific products, and sentiment data is also integrated to provide more personalized recommendations.

[0973] For example, if a user spends a long time browsing a particular product page and expresses feelings of "joy" during that time, the server will recommend a 10% discount coupon for that product to that user. This information is delivered to the device in real time as a push notification or advertising banner.

[0974] After a measure is implemented, the server monitors its effects and records changes in purchasing and browsing behavior. For example, it measures how frequently customers who participated in a specific discount campaign began purchasing products, and by incorporating these monitoring results into subsequent data analysis, it improves the accuracy of the analysis model and the effectiveness of the measures.

[0975] The following software and hardware will be used for the servers and terminals.

[0976] Hardware required: Smartphone, webcam, microphone

[0977] Software used: Python, TensorFlow, Keras, OpenCV, Pushbullet

[0978] A concrete example of its use is a process where, if a user spends a long time browsing a particular product page or frequently purchases items from a certain category, a push notification offering a "10% discount coupon for a specific product" is sent based on that information and the user's sentiment data.

[0979] An example of a prompt is: "Create Python code that estimates the optimal pricing plan based on the user's purchase history and sentiment data, and sends a push notification."

[0980] In this way, it is possible to design and provide optimal pricing plans and sales strategies that take into account the emotional state of the customer, thereby improving customer satisfaction and maximizing sales.

[0981] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0982] Step 1:

[0983] Customer data collection

[0984] The device collects user purchasing behavior, website browsing history, and survey results. When a user purchases a product, information such as the purchase date and time, product ID, and price is recorded, and website browsing history and time spent on the site are also collected. This data is transmitted to the server in real time. Input data includes purchase history, browsing history, and survey data, while output data is customer data stored on the server.

[0985] Step 2:

[0986] Collection of emotional data

[0987] The device uses a webcam and microphone to collect the user's facial expressions and voice in real time. An emotion recognition engine analyzes the user's facial expressions and voice while they are using the online store and sends the data to the server as emotion data. The input data consists of facial expression data and voice data, while the output data is the emotion data stored on the server.

[0988] Step 3:

[0989] Data preprocessing

[0990] The server integrates collected purchase history, browsing history, survey data, and sentiment data, removing incomplete and noisy data. It converts the data format into a format that can be analyzed by machine learning algorithms. The input data consists of raw customer data and sentiment data, while the output data is cleansed and in an analyzable format.

[0991] Step 4:

[0992] Customer segmentation

[0993] The server runs the K-means clustering algorithm based on the cleansed data, classifying customers into multiple segments. The input data is the cleansed data, and the output data is information about each customer segment.

[0994] Step 5:

[0995] Integration of needs prediction and emotion recognition results

[0996] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next. Simultaneously, it integrates sentiment data to make predictions that take into account the user's emotional state. Input data includes segment information and sentiment data, while output data consists of predicted product categories and discount rates.

[0997] Step 6:

[0998] Generating pricing plans and sales strategies

[0999] The server designs optimal pricing plans and sales strategies for each customer based on customer segment needs prediction results and sentiment data. For example, it might suggest discount coupons for specific products to frequent customers. The input data consists of needs prediction results and sentiment data, while the output data is the designed pricing plan and sales strategy.

[1000] Step 7:

[1001] Timely distribution of measures

[1002] The server delivers generated pricing plans and sales strategies to users' smartphones as push notifications in real time. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit websites. Input data consists of pricing plans and sales strategies, while output data consists of push notifications and advertising banners.

[1003] Step 8:

[1004] Monitoring the effectiveness of the measures and providing feedback.

[1005] The server monitors the effects of each measure after it has been implemented. It tracks changes in purchasing and browsing behavior as a result of the measures and collects this data. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated. The input data is behavioral data after the implementation of the measures, and the output data is used to improve the analysis model.

[1006] 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1007] 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.

[1008] 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.

[1009] [Fourth Embodiment]

[1010] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1011] 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.

[1012] 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).

[1013] 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.

[1014] 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.

[1015] 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).

[1016] 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.

[1017] 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.

[1018] 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.

[1019] 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.

[1020] 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.

[1021] 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.

[1022] 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".

[1023] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. Specific embodiments for implementing the system of this invention are described below.

[1024] Data collection

[1025] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. When a user browses a website, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server in the same manner.

[1026] Data Analysis

[1027] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. It then applies clustering algorithms to analyze the data and classify customers into segments. For example, K-means clustering is used to divide customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms are used to predict the future needs of customers in each segment. Specifically, random forests and neural networks are used to predict the product categories and applicable discount rates that a particular customer segment is likely to purchase next.

[1028] Generating pricing plans and sales strategies

[1029] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies for customer segments with specific interests, providing relevant new product information and special coupons.

[1030] Timely distribution of measures

[1031] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit a website.

[1032] Monitoring and feedback on the effects

[1033] After each measure is implemented, the server monitors its effects. Specifically, it tracks changes in purchasing and browsing behavior as a result of the measures and collects data. For example, it measures how frequently customers who participated in a particular discount campaign started purchasing products. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[1034] In this way, the system of the present invention can provide optimal pricing plans and sales strategies based on customer needs in a timely manner, thereby improving customer satisfaction and brand strength.

[1035] The following describes the processing flow.

[1036] Step 1: Data Collection

[1037] The device records purchase information (product ID, price, purchase date and time, etc.) when a user buys a product from an online store.

[1038] The device records user behavior data (such as the ID of the product viewed, the date and time of viewing, and the duration of time spent on the site) when the user browses a website.

[1039] The device records the user's response data when they answer a survey.

[1040] The device periodically sends all recorded data to the server.

[1041] Step 2: Data preprocessing

[1042] The server integrates the received purchase history, browsing history, and survey data.

[1043] The server performs a cleansing process to remove missing or noisy data.

[1044] The server converts the data format into a format suitable for analysis.

[1045] Step 3: Customer Segmentation

[1046] The server then runs the K-means clustering algorithm on the cleansed data to classify customers into multiple segments.

[1047] The server identifies the characteristics of each segment (e.g., frequent buyers, buyers in specific categories, etc.).

[1048] Step 4: Needs Prediction

[1049] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next.

[1050] The server uses the prediction results to identify the needs of each segment.

[1051] Step 5: Generating pricing plans and sales strategies

[1052] The server designs optimal pricing plans and sales strategies for each customer segment based on predicted needs.

[1053] For example, a server might design a discount plan for frequent customers that offers discounts for purchasing a certain number of items in a specific product category within a set period.

[1054] The server stores the designed plans and strategies in a database.

[1055] Step 6: Timely distribution of measures

[1056] The server delivers the generated pricing plans and sales strategies to the terminals in real time.

[1057] For example, the server sends a push notification to the user's smartphone informing them of a new discount campaign.

[1058] The server instructs the device to display individually optimized advertising banners and promotional messages when a user visits a website.

[1059] Step 7: Monitoring the effectiveness of the measures

[1060] The server monitors changes in user purchasing and browsing behavior after each measure is implemented.

[1061] The server analyzes in detail the purchase frequency and category changes of customers who have taken advantage of specific discount campaigns.

[1062] Step 8: Optimization through feedback

[1063] The server feeds the monitoring results back into the data analysis model and adjusts the parameters of the analysis model.

[1064] The server will use this feedback to improve the effectiveness of future measures.

[1065] Through these processing steps, the system provides timely and optimal pricing plans and sales strategies based on customer needs, thereby improving customer satisfaction and brand strength.

[1066] (Example 1)

[1067] 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".

[1068] Traditional marketing systems struggled to accurately understand customer purchasing behavior and preferences in real time and provide individually optimized pricing plans and sales strategies. Furthermore, the lack of mechanisms to continuously monitor the effectiveness of strategies and incorporate that data into subsequent analyses prevented improvements in the accuracy and effectiveness of those strategies.

[1069] 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.

[1070] In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for distributing the generated pricing plans and sales strategies to the customer's communication device in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to quickly and accurately grasp customer purchasing behavior and preferences and provide individually optimized pricing plans and sales strategies in a timely manner.

[1071] "Customer data" refers to information such as a customer's purchase history in commercial transactions, their browsing history on internet sites, and survey results.

[1072] "Means of collection" refers to devices or software that have the function of acquiring customer data and transmitting it to a server.

[1073] "Means of analysis" refers to devices or software that have the function of analyzing collected customer data and classifying customers based on similar behavioral patterns and interests.

[1074] A "clustering algorithm" is a statistical method for grouping sets of data, and includes techniques such as K-means and hierarchical clustering.

[1075] A "pricing plan" refers to sales conditions such as pricing and discounts offered to customers under specific circumstances.

[1076] "Sales strategies" refer to specific sales plans and promotions aimed at getting customers to purchase a particular product or service.

[1077] "Means of real-time delivery" refers to a device or software that has the function of immediately transmitting information on pricing plans and sales strategies generated based on analysis results to the customer's communication device.

[1078] "Monitoring means" refers to devices or software that have the function of tracking the effectiveness of implemented sales measures and collecting and analyzing the results.

[1079] A "segment" refers to a group of customers that share common characteristics or behaviors.

[1080] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. Specific embodiments for implementing the system of this invention are described below.

[1081] System Overview

[1082] This system operates by coordinating servers and terminals to collect and analyze customer data, generate and distribute optimal pricing plans and sales strategies, and monitor their effectiveness.

[1083] Data collection

[1084] The device records the user's purchasing behavior on online stores and browsing behavior on internet sites, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. Similarly, when a user browses an internet site, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[1085] Data Analysis

[1086] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. Then, K-means clustering is used to classify customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms such as random forests and neural networks are used to predict the future needs and likely product categories for each segment.

[1087] Generating pricing plans and sales strategies

[1088] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also creates sales strategies that provide relevant new product information and special coupons to customer segments with specific interests.

[1089] Timely distribution of measures

[1090] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit websites.

[1091] Monitoring and feedback on the effects

[1092] The server monitors the effectiveness of each measure after it has been implemented. For example, it measures how frequently customers who participated in a particular discount campaign began purchasing products. These monitoring results are then incorporated into the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures being generated.

[1093] Specific example

[1094] A user purchases the latest smartphone from an online store. At that time, the device sends data such as the purchase date and time, product ID, and price to the server. The server then integrates and analyzes this data with other user data to predict that the user is likely to purchase a smartphone case next time. Based on this prediction, the server generates a plan offering the user a specific smartphone case at a discounted price and delivers it to the user's smartphone via push notification.

[1095] Example of a prompt

[1096] "Based on the analysis of customer data, we predict the product that the customer is most likely to purchase next and generate the optimal price discount plan for that product."

[1097] This system can improve customer satisfaction and brand strength by providing optimal pricing plans and sales strategies based on customer needs in a timely manner.

[1098] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1099] Step 1: Data Collection

[1100] When a user purchases an item from an online store, the device records data such as the purchase date and time, product ID, and price. For example, if a user purchases a "latest smartphone," this information will be recorded. The device then sends the recorded purchase data to a server. Additionally, when a user browses a website, the device records their browsing history and time spent on the site, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[1101] Input: User-generated purchase history, browsing history, and survey results.

[1102] Output: Customer data sent to the server

[1103] Step 2: Data Integration and Preprocessing

[1104] The server integrates all received customer data. This includes the following specific actions: pre-processing to remove incomplete or noisy data. For example, missing data is either filled in or deleted. Noisy data is also filtered out.

[1105] Input: Raw customer data sent from the terminal.

[1106] Output: Pre-processed customer data

[1107] Step 3: Classification of Customer Segments

[1108] The server applies a clustering algorithm based on pre-processed customer data to classify customers into segments. For example, K-means clustering is used to divide customers into groups with similar purchasing behaviors or interests.

[1109] Input: Pre-processed customer data

[1110] Output: Customer data categorized by segment

[1111] Step 4: Predicting future needs

[1112] The server uses machine learning algorithms (such as random forests or neural networks) to predict future needs based on customer data categorized into segments. For example, it calculates the probability that a "customer group that frequently purchases products" will next purchase a "smartphone case."

[1113] Input: Customer data categorized by segment

[1114] Output: Forecast data for future needs for each segment

[1115] Step 5: Generating pricing plans and sales strategies

[1116] The server generates optimal pricing plans and sales strategies for each segment based on future needs prediction data. For example, for "frequent buyers," it designs a discount plan for customers who purchase a certain number of specific products within a certain period. It also generates new product information and special offer coupons.

[1117] Input: Future needs forecast data

[1118] Output: Generated pricing plans and sales strategies

[1119] Step 6: Timely distribution of plans and measures

[1120] The server delivers generated pricing plans and sales promotions to the device in real time. For example, it sends "discount information on smartphone cases" to the user's smartphone via push notification. Furthermore, it displays individually optimized advertising banners and promotional messages when the user visits a website.

[1121] Input: Generated pricing plans and sales strategies

[1122] Output: Pricing plans and sales promotions delivered to user terminals

[1123] Step 7: Monitoring and Feedback on Effects

[1124] The server monitors the effectiveness of each measure after it has been implemented. For example, it tracks how frequently customers who participated in a particular discount campaign began purchasing products. These monitoring results are then incorporated into the next data analysis.

[1125] Input: Effectiveness data of implemented sales measures

[1126] Output: Monitored results data and feedback data for accuracy improvement.

[1127] As a result, this system can provide optimal pricing plans and sales strategies based on customer behavior in real time.

[1128] (Application Example 1)

[1129] 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".

[1130] Traditional purchasing data analysis systems have difficulty providing timely product recommendations and sales strategies that reflect individual customer needs. Furthermore, these systems are primarily designed for desktop environments and do not offer real-time information via mobile devices such as smartphones and tablets. Therefore, improving the quality of the customer experience and stimulating purchasing intent has been challenging.

[1131] 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.

[1132] In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, means for being installed on mobile devices such as smartphones and tablets to provide individually optimized product suggestions and campaigns, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to provide optimal product suggestions and sales strategies that meet the individual needs of customers in real time.

[1133] "Customer data" refers to information about individual customers, such as their purchase history, website browsing history, and survey results.

[1134] "Analysis" refers to the process of processing and analyzing data using collected customer data to identify customer behavior and trends.

[1135] A "segment" refers to a group of customers who have similar purchasing behaviors or interests.

[1136] A "pricing plan" refers to the pricing and discount conditions offered to customers as a sales promotion tool.

[1137] "Sales strategies" refer to means of sales promotion taken towards customers, such as product proposals and campaign implementation.

[1138] "Mobile devices such as smartphones and tablets" refer to portable electronic devices that can receive and display information in real time using communication functions.

[1139] "Real-time" refers to providing results immediately after information has been collected and analyzed.

[1140] "Monitoring" refers to continuously observing the effects of a policy and measuring its fluctuations.

[1141] A "clustering algorithm" refers to a mathematical method for grouping (clustering) data based on specific criteria.

[1142] This invention relates to a system for collecting and analyzing customer data and providing optimal pricing plans and sales strategies in a timely manner. The following describes in detail how to implement the system of this invention.

[1143] Data collection

[1144] The server has the function of collecting customer data from the terminal. This data includes purchase history, website browsing history, and survey results. The terminal records the user's purchasing behavior on the online store and website browsing behavior, and sends this data to the server. For example, when a user purchases a product, information such as the purchase date and time, product ID, and price is collected and sent to the server. In addition, the history of product pages viewed by the user on the website, the time spent on each page, and the number of times they were viewed are also collected and sent to the server. Furthermore, if a user answers a survey, the results are also sent to the server.

[1145] Data Analysis

[1146] The server integrates all received customer data and performs preprocessing to remove incomplete data and noise. It then applies clustering algorithms to analyze the data and segment customers. Specifically, K-means clustering is used to divide customers into groups with similar purchasing behaviors and interests. Furthermore, machine learning algorithms are used to predict the future needs of customers in each segment. In particular, generative AI models such as random forests and neural networks are used to predict the product categories and applicable discount rates that specific customer segments are likely to purchase next.

[1147] Generating pricing plans and sales strategies

[1148] The server generates optimal pricing plans and sales strategies for each customer based on customer segment needs predictions. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies for customer segments with specific interests, providing relevant new product information and special coupons.

[1149] Timely distribution of measures

[1150] The device has a means of notifying customers in real time about generated pricing plans and sales promotions. Specifically, it sends push notifications to users' smartphones and tablets to inform them about new discount campaigns. It also displays individually optimized advertising banners and promotional messages when users visit websites.

[1151] Monitoring and feedback on the effects

[1152] The server monitors the effectiveness of each measure after it has been implemented. For example, it measures how frequently customers who participated in a particular discount campaign began purchasing products, and incorporates these monitoring results into the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[1153] This makes it possible to provide optimal product suggestions and sales strategies tailored to each customer's individual needs in real time.

[1154] Example of a prompt:

[1155] We want to use clustering algorithms and machine learning models to suggest the most suitable sales strategies based on users' purchase and browsing history. Design a system that predicts the product categories and applicable discount rates that users will be interested in next, and generates optimal pricing plans and promotional offers.

[1156] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1157] Step 1:

[1158] Data collection

[1159] The terminal records the user's purchase history, website browsing history, and survey results. For example, when a user purchases a product, it collects information such as the purchase date and time, product ID, and price, and sends it to the server. This allows the server to receive detailed data for each customer. The input data is the customer's behavioral history, and the output is the raw data sent to the server.

[1160] Step 2:

[1161] Data Integration and Preprocessing

[1162] The server integrates the received customer data and performs preprocessing to remove incomplete data and noise. Specifically, it imputes missing values ​​and detects and corrects outliers. This results in clean data suitable for analysis. The input data is the raw data before integration, and the output is the clean data.

[1163] Step 3:

[1164] Customer segment clustering

[1165] The server applies a clustering algorithm (e.g., K-means clustering) to the integrated clean data to classify customers into segments. For example, customers with similar purchasing behavior or browsing history are grouped together. The input for this step is clean data, and the output is segmented customer data.

[1166] Step 4:

[1167] Needs forecasting

[1168] The server uses a generative AI model (e.g., random forest or neural network) based on segmented customer data to predict the product categories and applicable discount rates that customers in each segment are likely to purchase next. The input for this step is segmented customer data, and the output is the predicted customer needs for each segment.

[1169] Step 5:

[1170] Generating pricing plans and sales strategies

[1171] The server generates optimal pricing plans and sales strategies based on customer needs predictions. For example, it might offer a "10% off next purchase" plan to frequent customers and provide discount coupons for related new products to customers interested in specific items. The input for this step is the customer needs prediction, and the output is pricing plans and sales strategies tailored to each customer.

[1172] Step 6:

[1173] Timely distribution of measures

[1174] The device notifies users in real time of pricing plans and sales promotions received from the server. Specifically, it sends push notifications to users' smartphones and tablets, for example, informing them of an offer such as "10% off your next purchase." The input for this step is individually optimized sales promotion information, and the output is push notifications and advertising banners sent to users.

[1175] Step 7:

[1176] Monitoring and feedback on the effects

[1177] The server monitors the effectiveness of each initiative and incorporates the results into the next data analysis. For example, it measures the extent to which a particular discount campaign influenced purchasing behavior. This improves the accuracy of the analytical model. The input for this step is customer behavior data after the implementation of each initiative, and the output is the modified model data that will be reflected in the next analysis.

[1178] 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.

[1179] This invention combines a system that collects and analyzes customer data to provide optimal pricing plans and sales strategies in a timely manner with an emotion engine that recognizes user emotions. The following describes a specific embodiment of the system of this invention.

[1180] Data collection

[1181] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, when a user purchases a product, it records information such as the purchase date and time, product ID, and price, and sends this purchase history to the server. When a user browses a website, it records the browsing history of that product page, the time spent on the page, and the number of times it was viewed, and sends this information to the server. Furthermore, if a user answers a survey, the results are also sent to the server in the same manner.

[1182] Collection of emotional data

[1183] The device records the user's emotions through facial expressions, voice, and input text, and sends this data to a server. For example, it uses a webcam and microphone to analyze the user's facial expressions and voice emotional state in real time and sends the results to the server.

[1184] Data preprocessing

[1185] The server integrates received purchase history, browsing history, survey data, and sentiment data, and performs preprocessing to remove incomplete or noisy data. It then converts the data format to one suitable for analysis.

[1186] Customer segmentation

[1187] The server then runs a K-means clustering algorithm on all the cleansed data to classify customers into multiple segments. It identifies the characteristics of each segment (e.g., frequent buyers, buyers of specific categories, etc.).

[1188] Integration of needs prediction and sentiment recognition results

[1189] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next. Furthermore, it integrates sentiment data obtained from the sentiment engine to make predictions that take into account the customer's emotional state.

[1190] Generating pricing plans and sales strategies

[1191] The server designs optimal pricing plans and sales strategies for each customer based on customer segment needs predictions and sentiment data. For example, for frequent buyers, it designs a discount plan for those who purchase a certain number of items in a specific product category within a certain period. It also designs sales strategies that provide relevant new product information and special coupons to customer segments with specific interests.

[1192] Timely distribution of measures

[1193] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it sends push notifications to users' smartphones to provide real-time information about new discount campaigns. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit a website.

[1194] Monitoring the effectiveness of the measures and providing feedback.

[1195] After each measure is implemented, the server monitors its effects. Specifically, it tracks changes in purchasing and browsing behavior as a result of the measures and collects data. For example, it measures how frequently customers who participated in a particular discount campaign started purchasing products. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated.

[1196] This system utilizes emotional data to more accurately predict customer needs and provide optimal pricing plans and sales strategies. This is expected to further improve customer satisfaction and brand strength.

[1197] The following describes the processing flow.

[1198] Step 1: Data Collection

[1199] The device records purchase information (product ID, price, purchase date and time, etc.) when a user buys a product from an online store.

[1200] The device records user behavior data (such as the ID of the product viewed, the date and time of viewing, and the duration of time spent on the site) when the user browses a website.

[1201] The device records the user's response data when they answer a survey.

[1202] The device periodically sends all recorded data to the server.

[1203] Step 2: Collecting emotional data

[1204] The device records emotions from the user's facial expressions, voice, and input text.

[1205] The device uses a webcam and microphone to analyze the user's facial expressions and emotional state in real time, and sends the results to a server.

[1206] Step 3: Data Preprocessing

[1207] The server integrates the received purchase history, browsing history, survey data, and sentiment data, and performs preprocessing to remove incomplete or noisy data.

[1208] The server converts the data into a format suitable for analysis.

[1209] Step 4: Customer Segmentation

[1210] The server then runs a K-means clustering algorithm on all the cleansed data to classify customers into multiple segments.

[1211] The server identifies the characteristics of each segment (e.g., frequent buyers, buyers in specific categories, etc.).

[1212] Step 5: Integrating Needs Prediction and Sentiment Recognition Results

[1213] The server applies machine learning algorithms such as random forests and neural networks to predict purchasing needs for each customer segment.

[1214] The server integrates emotional data obtained from the emotion engine and makes predictions that take into account the customer's emotional state.

[1215] Step 6: Generate pricing plans and sales strategies.

[1216] The server designs the optimal pricing plan and sales strategy for each customer based on customer segment needs predictions and sentiment data.

[1217] The server designs discount plans for frequent customers, offering discounts for purchasing a certain number of items in a specific product category within a set period.

[1218] The server designs sales strategies that provide relevant new product information and special offer coupons to customer segments with specific interests.

[1219] Step 7: Timely distribution of measures

[1220] The server delivers the generated pricing plans and sales strategies to the terminals in real time.

[1221] The server sends a push notification to the user's smartphone, informing them of the new discount campaign.

[1222] The server instructs the device to display individually optimized advertising banners and promotional messages when a user visits a website.

[1223] Step 8: Monitoring the effectiveness of the measures

[1224] The server monitors changes in user purchasing and browsing behavior after each measure is implemented.

[1225] The server analyzes in detail the purchase frequency and category changes of customers who have taken advantage of specific discount campaigns.

[1226] Step 9: Optimization through feedback

[1227] The server feeds the monitoring results back into the data analysis model and adjusts the parameters of the analysis model.

[1228] The server incorporates the feedback into the design of future measures, thereby improving the effectiveness of those measures.

[1229] Through these processing steps, the system utilizes customer sentiment data to make more specific and accurate predictions of customer needs, providing optimal pricing plans and sales strategies in a timely manner, thereby improving customer satisfaction and brand strength.

[1230] (Example 2)

[1231] 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".

[1232] Traditional systems have limitations in collecting and analyzing customer data, making it particularly difficult to generate optimal pricing plans and sales strategies that take into account customer emotional states. Furthermore, the inability to adequately distribute strategies in real time and provide feedback on their effectiveness hindered improvements in customer satisfaction and strengthened brand power. To address these challenges, it is crucial to integrate emotional data in addition to customer data to enable real-time strategy distribution and effectiveness monitoring.

[1233] 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.

[1234] In this invention, the server includes means for integrating and pre-processing customer data and sentiment data; means for classifying customers into segments based on the pre-processed data; means for predicting purchases for each segment and generating optimal pricing plans and sales strategies for each customer, taking sentiment data into consideration; means for delivering the generated pricing plans and sales strategies to customers in real time; and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This enables more accurate prediction of customer needs and the timely provision of personalized pricing plans and sales strategies.

[1235] "Customer data" refers to information such as a customer's purchase history, website browsing history, and survey results.

[1236] "Emotional data" refers to information about a user's emotional state, analyzed from their facial expressions, voice, and text.

[1237] "Preprocessing" refers to the process of integrating received data, removing incomplete data and noise, and converting it into a format suitable for analysis.

[1238] A "segment" refers to a group of customers classified based on common characteristics.

[1239] A "clustering algorithm" refers to a method of classifying data into multiple clusters based on common properties or patterns.

[1240] "Purchase forecasting" refers to the process of predicting what products or services a customer is likely to buy next.

[1241] A "pricing plan" refers to the pricing structure or discount plan offered to customers.

[1242] "Sales strategies" refer to promotional and marketing activities conducted for specific segments or customers.

[1243] "Real-time" refers to processing or delivering information immediately.

[1244] "Monitoring" refers to the process of continuously tracking the effects of a measure and changes in customer behavior after its implementation, and collecting data accordingly.

[1245] "Feedback" refers to the process of using monitoring results to inform future data analysis and strategy development.

[1246] This invention relates to a system that collects and analyzes customer data and emotional data, and based on that, provides optimal pricing plans and sales strategies in a timely manner. Specific embodiments for carrying out this invention are described below.

[1247] Specific methods for data collection

[1248] The device records the user's purchasing behavior on online stores and website browsing behavior, and sends this data to the server. Specifically, it captures user actions by embedding JavaScript code in web pages. It also uses the Google Analytics API to obtain website browsing history and time spent on the site. Purchase history includes user ID, purchase date and time, product ID, price, etc.

[1249] Collection and analysis of emotional data

[1250] The device collects emotional data through the user's facial expressions, voice, and input text, and sends this data to the server. It uses a webcam to perform facial expression analysis using the OpenCV library, and a microphone to convert speech to text using the Google Speech-to-Text API, which is then analyzed.

[1251] Data preprocessing

[1252] The server integrates and preprocesses the collected purchase history, browsing history, survey data, and sentiment data. This process includes data integration using the Python Pandas library, imputation of incomplete data, and removal of outliers.

[1253] Customer segmentation

[1254] The server uses the K-means clustering algorithm to classify customers into multiple segments based on the pre-processed data. This algorithm uses the Scikit-learn library.

[1255] Integration of needs prediction and emotion recognition results

[1256] The server uses random forests and neural network models to predict which products a specific customer segment is likely to purchase next. This analysis utilizes TensorFlow and Scikit-learn. Furthermore, it integrates the results of an emotion engine, taking into account the customer's emotional state to make more accurate predictions.

[1257] Generating pricing plans and sales strategies

[1258] The server designs optimal pricing plans and sales strategies for each customer based on predictive and sentiment data. For example, it might generate a plan for frequent buyers offering a 10% discount for monthly purchases of ¥10,000 or more. Other sales strategies include providing new product information and special coupons.

[1259] Timely distribution of measures

[1260] The server delivers generated pricing plans and sales promotions to devices in real time. For example, it uses Firebase Cloud Messaging to send push notifications to smartphones announcing new discount campaigns.

[1261] Monitoring the effectiveness of the measures and providing feedback.

[1262] The server monitors the effectiveness of each measure after its implementation and tracks changes in purchasing and browsing behavior. This monitoring data is then incorporated into subsequent data analysis to improve the system's accuracy.

[1263] Examples of prompt statements

[1264] Here is a concrete example of an input prompt statement for a generative AI model:

[1265] "Create a model to predict what other products customers who purchase the next item tend to buy together. Available data includes purchase history (user ID, purchase date and time, product ID, price), browsing history (user ID, browsing date and time, product ID, time spent), sentiment data (user ID, facial expression / voice sentiment score), and survey data (user ID, response content)."

[1266] The above describes the embodiment for carrying out the invention. This system enables more accurate prediction of customer needs and the timely provision of personalized pricing plans and sales strategies.

[1267] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1268] Step 1:

[1269] The device records the user's purchasing and browsing behavior and sends this data to the server in real time. Specifically, JavaScript code embedded in the web page captures the user's actions (product purchase, page viewing). Inputs include user ID, purchase date and time, product ID, price, viewing date and time, and time spent on the page. This input data is sent to the server via an HTTP request, and the output is all purchase and browsing history data stored on the server.

[1270] Step 2:

[1271] The device collects the user's facial expressions, voice, and input text as emotion data and sends it to the server in real time. Specifically, it analyzes facial expressions using a webcam and the OpenCV library, and converts audio data collected by the microphone into text using the Google Speech-to-Text API. The inputs are facial expression data (images), audio data (audio files), and text data (converted audio text). This input data is sent to the server in real time using WebSocket, and the output is the emotion-analyzed data stored on the server.

[1272] Step 3:

[1273] The server integrates and preprocesses the received purchase history, browsing history, survey data, and sentiment data. Specifically, it uses the Python Pandas library to cleanse the data and remove incomplete data and noise. The inputs include purchase history data, browsing history data, survey data, and sentiment data. This data is read from log files and databases, and after data cleansing and format conversion, the cleaned integrated data is output.

[1274] Step 4:

[1275] The server performs customer segmentation based on pre-processed data. Specifically, it uses the K-means clustering algorithm to classify customers into multiple segments. This process is performed using the Scikit-learn library. The input is pre-processed integrated data. This data is input to the K-means clustering algorithm, and the output is information on which cluster each customer belongs to.

[1276] Step 5:

[1277] The server performs customer purchase predictions based on clustered segment data. Specifically, it uses random forests and neural network models to analyze and predict which products customers in each segment are likely to purchase next. TensorFlow is used for this analysis. The input consists of segmented customer data and sentiment data. This input data is passed through a machine learning model to obtain prediction results as output.

[1278] Step 6:

[1279] The server generates optimal pricing plans and sales strategies for each customer based on prediction results and sentiment data. Specifically, it executes a script using Python to generate pricing plans and promotional strategies based on various conditions. The input is purchase prediction data and sentiment data. The output is data on pricing plans and sales strategies optimized for each customer.

[1280] Step 7:

[1281] The server delivers generated pricing plans and sales promotions to devices in real time. Specifically, it uses Firebase Cloud Messaging to send push notifications to users' smartphones announcing new discount campaigns. The inputs are optimized pricing plan and sales promotion data and customer IDs. The output is a push notification sent to the device.

[1282] Step 8:

[1283] The server monitors the effectiveness of each initiative and feeds the results back into the next data analysis. Specifically, it uses Google Analytics and internally developed monitoring tools to track changes in purchasing and browsing behavior after an initiative is implemented. The input is purchase history data and browsing history data after the initiative is implemented. The output is data on the effectiveness of the initiative, which is used in the next analysis model.

[1284] (Application Example 2)

[1285] 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".

[1286] While many online stores already offer optimal pricing plans and sales strategies based on user purchasing behavior and website browsing history, it is believed that even more accurate personalization is possible by considering customer emotions. However, current systems do not collect and analyze emotional data, making it difficult to provide optimal suggestions based on the customer's actual emotional state.

[1287] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting customer data, means for analyzing the collected customer data and classifying customers into segments, means for collecting and analyzing user emotion data through a webcam and microphone, means for generating optimal pricing plans and sales strategies for each customer based on the analysis, means for delivering the generated pricing plans and sales strategies to customers in real time, and means for monitoring the effectiveness of each strategy and reflecting the results in the next data analysis. This makes it possible to design and provide optimal pricing plans and sales strategies that take into account the emotional state of the customer.

[1288] "Customer data" refers to information including users' purchasing behavior, website browsing history, and survey results.

[1289] "Analysis" is the process of analyzing patterns and trends based on collected data to gain insights.

[1290] A "segment" refers to a group of customers that share common characteristics or behaviors.

[1291] A "pricing plan" refers to the price structure or fee scheme for a specific product or service.

[1292] "Sales strategies" refer to promotional and marketing methods aimed at encouraging customers to make a purchase.

[1293] "Emotional data" refers to information about a user's psychological state obtained through their facial expressions, voice, and other means.

[1294] A "webcam" is a camera device used to capture a user's facial expressions in real time.

[1295] A "microphone" is a device used to capture the user's voice.

[1296] "Real-time" refers to the immediate processing and distribution of information and data without any time lag.

[1297] "Monitoring" refers to the act of continuously monitoring and evaluating whether policies and systems are functioning appropriately.

[1298] This invention relates to an emotion-recognizing personalized shopping assistant system. The following describes how the system of this invention will be specifically implemented.

[1299] The server collects customer data, including users' purchasing behavior, website browsing history, and survey results. This data includes information such as the date and time of purchase, product ID, price, browsing history, and time spent on the site. Data collected through the device is transmitted to and stored on the server in real time.

[1300] The server analyzes the collected customer data and uses the K-means clustering algorithm to classify customers into segments. Each segment is categorized into customer groups with specific characteristics, such as frequent buyers or buyers of a particular category.

[1301] Furthermore, the server collects user emotional data through the webcam and microphone, and uses an emotion recognition engine to analyze facial expressions and voice. This allows the user's real-time emotional state to be obtained as numerical data, which is also sent to the server.

[1302] The server generates optimal pricing plans and sales strategies for each customer based on the analysis results. In this process, machine learning algorithms such as random forests and neural networks are used to predict promotions and discount rates for specific products, and sentiment data is also integrated to provide more personalized recommendations.

[1303] For example, if a user spends a long time browsing a particular product page and expresses feelings of "joy" during that time, the server will recommend a 10% discount coupon for that product to that user. This information is delivered to the device in real time as a push notification or advertising banner.

[1304] After a measure is implemented, the server monitors its effects and records changes in purchasing and browsing behavior. For example, it measures how frequently customers who participated in a specific discount campaign began purchasing products, and by incorporating these monitoring results into subsequent data analysis, it improves the accuracy of the analysis model and the effectiveness of the measures.

[1305] The following software and hardware will be used for the servers and terminals.

[1306] Hardware required: Smartphone, webcam, microphone

[1307] Software used: Python, TensorFlow, Keras, OpenCV, Pushbullet

[1308] A concrete example of its use is a process where, if a user spends a long time browsing a particular product page or frequently purchases items from a certain category, a push notification offering a "10% discount coupon for a specific product" is sent based on that information and the user's sentiment data.

[1309] An example of a prompt is: "Create Python code that estimates the optimal pricing plan based on the user's purchase history and sentiment data, and sends a push notification."

[1310] In this way, it is possible to design and provide optimal pricing plans and sales strategies that take into account the emotional state of the customer, thereby improving customer satisfaction and maximizing sales.

[1311] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1312] Step 1:

[1313] Customer data collection

[1314] The device collects user purchasing behavior, website browsing history, and survey results. When a user purchases a product, information such as the purchase date and time, product ID, and price is recorded, and website browsing history and time spent on the site are also collected. This data is transmitted to the server in real time. Input data includes purchase history, browsing history, and survey data, while output data is customer data stored on the server.

[1315] Step 2:

[1316] Collection of emotional data

[1317] The device uses a webcam and microphone to collect the user's facial expressions and voice in real time. An emotion recognition engine analyzes the user's facial expressions and voice while they are using the online store and sends the data to the server as emotion data. The input data consists of facial expression data and voice data, while the output data is the emotion data stored on the server.

[1318] Step 3:

[1319] Data preprocessing

[1320] The server integrates collected purchase history, browsing history, survey data, and sentiment data, removing incomplete and noisy data. It converts the data format into a format that can be analyzed by machine learning algorithms. The input data consists of raw customer data and sentiment data, while the output data is cleansed and in an analyzable format.

[1321] Step 4:

[1322] Customer segmentation

[1323] The server runs the K-means clustering algorithm based on the cleansed data, classifying customers into multiple segments. The input data is the cleansed data, and the output data is information about each customer segment.

[1324] Step 5:

[1325] Integration of needs prediction and emotion recognition results

[1326] The server applies machine learning algorithms such as random forests and neural networks to predict the product categories and applicable discount rates that customers in a specific segment are likely to purchase next. Simultaneously, it integrates sentiment data to make predictions that take into account the user's emotional state. Input data includes segment information and sentiment data, while output data consists of predicted product categories and discount rates.

[1327] Step 6:

[1328] Generating pricing plans and sales strategies

[1329] The server designs optimal pricing plans and sales strategies for each customer based on customer segment needs prediction results and sentiment data. For example, it might suggest discount coupons for specific products to frequent customers. The input data consists of needs prediction results and sentiment data, while the output data is the designed pricing plan and sales strategy.

[1330] Step 7:

[1331] Timely distribution of measures

[1332] The server delivers generated pricing plans and sales strategies to users' smartphones as push notifications in real time. It also instructs devices to display individually optimized advertising banners and promotional messages when users visit websites. Input data consists of pricing plans and sales strategies, while output data consists of push notifications and advertising banners.

[1333] Step 8:

[1334] Monitoring the effectiveness of the measures and providing feedback.

[1335] The server monitors the effects of each measure after it has been implemented. It tracks changes in purchasing and browsing behavior as a result of the measures and collects this data. These monitoring results are reflected in the next data analysis to improve the accuracy of the analysis model and the effectiveness of the measures generated. The input data is behavioral data after the implementation of the measures, and the output data is used to improve the analysis model.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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 based, for example, 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.

[1344] 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."

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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.

[1356] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1357] The following is further disclosed regarding the embodiments described above.

[1358] (Claim 1)

[1359] Means of collecting customer data,

[1360] A means of analyzing collected customer data and classifying customers into segments,

[1361] A means of generating optimal pricing plans and sales strategies for each customer based on analysis,

[1362] A means of delivering generated pricing plans and sales strategies to customers in real time,

[1363] A means to monitor the effectiveness of each measure and reflect the results in the next data analysis,

[1364] A system that includes this.

[1365] (Claim 2)

[1366] The system according to claim 1, comprising means for collecting purchase history, website browsing history, and survey results as customer data.

[1367] (Claim 3)

[1368] The system according to claim 1, comprising means for classifying customers using a clustering algorithm for analyzing customer data.

[1369] "Example 1"

[1370] (Claim 1)

[1371] Means of collecting customer data,

[1372] A means of analyzing collected customer data and classifying customers into segments,

[1373] A means of generating optimal pricing plans and sales strategies for each customer based on analysis,

[1374] A means of delivering generated pricing plans and sales strategies to customers' communication devices in real time,

[1375] A means to monitor the effectiveness of each measure and reflect the results in the next data analysis,

[1376] A system that includes this.

[1377] (Claim 2)

[1378] The system according to claim 1, comprising means for collecting customer data such as purchase history, internet site browsing history, and survey results.

[1379] (Claim 3)

[1380] The system according to claim 1, comprising means for classifying customers using a clustering algorithm for analyzing customer data.

[1381] "Application Example 1"

[1382] (Claim 1)

[1383] Means of collecting customer data,

[1384] A means of analyzing collected customer data and classifying customers into segments,

[1385] A means of generating optimal pricing plans and sales strategies for each customer based on analysis,

[1386] A means of delivering generated pricing plans and sales strategies to customers in real time,

[1387] A means of providing individually optimized product suggestions and campaigns that are installed on mobile devices such as smartphones and tablets,

[1388] A means to monitor the effectiveness of each measure and reflect the results in the next data analysis,

[1389] A system that includes this.

[1390] (Claim 2)

[1391] The system according to claim 1, comprising means for collecting purchase history, website browsing history, and survey results as customer data.

[1392] (Claim 3)

[1393] The system according to claim 1, comprising means for classifying customers using a clustering algorithm for analyzing customer data.

[1394] "Example 2 of combining an emotion engine"

[1395] (Claim 1)

[1396] Means of collecting customer data,

[1397] A means for integrating and pre-processing collected customer data and sentiment data,

[1398] A means of classifying customers into segments based on pre-processed data,

[1399] A method for predicting purchases in each segment and generating optimal pricing plans and sales strategies for each customer, taking sentiment data into consideration.

[1400] A means of delivering generated pricing plans and sales strategies to customers in real time,

[1401] A means to monitor the effectiveness of each measure and reflect the results in the next data analysis,

[1402] A system that includes this.

[1403] (Claim 2)

[1404] The system according to claim 1, comprising means for collecting purchase history, website browsing history, and survey results as customer data.

[1405] (Claim 3)

[1406] The system according to claim 1, comprising means for classifying customers using a clustering algorithm for analyzing customer data.

[1407] "Application example 2 when combining with an emotional engine"

[1408] (Claim 1)

[1409] Means of collecting customer data,

[1410] A means of analyzing collected customer data and classifying customers into segments,

[1411] A means of generating optimal pricing plans and sales strategies for each customer based on analysis,

[1412] A means of collecting and analyzing user emotional data through webcams and microphones,

[1413] A means of delivering generated pricing plans and sales strategies to customers in real time,

[1414] A means to monitor the effectiveness of each measure and reflect the results in the next data analysis,

[1415] A system that includes this.

[1416] (Claim 2)

[1417] The system according to claim 1, comprising means for collecting purchase history, website browsing history, and survey results as customer data.

[1418] (Claim 3)

[1419] The system according to claim 1, comprising means for classifying customers using a clustering algorithm for analyzing customer data. [Explanation of symbols]

[1420] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting customer data, A means of analyzing collected customer data and classifying customers into segments, A means of generating optimal pricing plans and sales strategies for each customer based on analysis, A means of delivering generated pricing plans and sales strategies to customers in real time, A means to monitor the effectiveness of each measure and reflect the results in the next data analysis, A system that includes this.

2. The system according to claim 1, comprising means for collecting customer data such as purchase history, website browsing history, and survey results.

3. The system according to claim 1, further comprising means for classifying customers using a clustering algorithm for analyzing customer data.

Images