system

Abstract

We provide the system. [Solution] A means for collecting and pre-processing customer information, A means for applying a generative AI model to analyze pre-processed customer information, A means for generating a user interface to provide analysis results to the user, A means of collecting user feedback and improving the generated AI model, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the management of customer information, there is a time-consuming and laborious burden caused by manually processing a huge amount of data, which has become a factor hindering the effective implementation of promotion measures. In such a situation, there is a demand for a system that can quickly and accurately grasp the purchase tendency of customers and the progress of contract procedures, and enable efficient business processing and accurate promotion measures.

Means for Solving the Problems

[0005] This invention provides a system that includes means for collecting and pre-processing customer information. The system further includes means for applying a generative AI model to analyze the pre-processed customer information. The system also includes means for generating a user interface for providing the analysis results to the user, and means for collecting user feedback to improve the generative AI model. This enables effective customer management and promotional strategies.

[0006] "Customer information" refers to all data related to a customer, primarily including their profile, transaction history, and contract details.

[0007] "Data collection means" refers to methods and devices for acquiring data from external databases or existing systems and managing it centrally according to the purpose.

[0008] "Preprocessing" refers to the process of organizing and cleansing collected raw data in order to convert it into a format suitable for analysis.

[0009] A "generative AI model" is a model that includes artificial intelligence used to analyze collected and pre-processed data and extract insights that are useful for a specific purpose.

[0010] "Analysis results" refer to the correlations and insights obtained from data acquired through the application of a generative AI model.

[0011] "User interface" refers to the screen or means through which a user interacts with a system and confirms and manipulates information.

[0012] "Feedback" refers to evaluations and opinions provided by users regarding the system's functions and the results obtained, and is information that can be used to improve the system.

[0013] "Promotional measures" refer to marketing activities and strategies aimed at encouraging customers to purchase products or services. [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] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

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

[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 a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

[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 customer information management system in which a server, terminal, and user work in cooperation. Specific embodiments for carrying out this invention are described below.

[0036] The server first collects vast amounts of customer information from external databases and existing information systems. This collected data undergoes cleansing and formatting processes, including correcting inaccurate data and verifying consistency. The server then applies a generative AI model to this organized data. This AI model analyzes customer attributes and automatically extracts business-useful insights, such as purchasing trends and the progress of contract procedures.

[0037] The terminal receives analysis results from the server and generates a user interface that provides information to the user. This interface is in a dashboard format, visually displaying, for example, customer purchasing patterns, and is designed to be easily understood and utilized by sales representatives. The terminal also proposes personalized promotional strategies, which users can use to decide on specific actions.

[0038] Based on these insights provided via the device, users make specific decisions to implement targeted marketing strategies and optimize contract procedures. Furthermore, users provide feedback on the results and areas for improvement obtained during system operation. This feedback information is stored on the server and used to improve the accuracy of the generated AI model. As a result, overall system performance improves, enabling more effective customer management over time.

[0039] As a concrete example, when a company launches a new product, the server analyzes customers' past purchase and inquiry history to calculate their potential interest in the new product. The terminal then presents this insight to the user, who can then send targeted promotional emails to customers with high interest levels.

[0040] Therefore, the present invention supports the efficient management of customer information and the effective implementation of promotional measures.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server periodically collects customer information from multiple external databases and internal data systems. This includes new contract information, customer profile information, and past purchase history.

[0044] Step 2:

[0045] The server cleanses the collected data. Specifically, it removes duplicate data and corrects incomplete or incorrect data. This process is automated based on cleansing rules.

[0046] Step 3:

[0047] The server passes the cleansed data to an AI model for analysis. The AI ​​model analyzes the data patterns to identify customer purchasing trends and product categories of interest.

[0048] Step 4:

[0049] The server aggregates the analysis results and organizes them as insights. This includes appropriate promotional recommendations for each customer and the progress of contract procedures.

[0050] Step 5:

[0051] The terminal generates a dashboard based on insights received from the server. This dashboard is designed to provide users with information in a visually appealing and easy-to-understand format.

[0052] Step 6:

[0053] Users can check their device's dashboard and determine appropriate actions for each customer. For example, they can implement marketing campaigns focused on customers interested in specific products.

[0054] Step 7:

[0055] Users provide feedback on system processing results and areas for improvement through their terminals. This feedback is collected on the server and used to retrain the AI ​​model, thereby improving the accuracy of future analyses.

[0056] Step 8:

[0057] The server uses the newly received feedback to improve the accuracy of the generated AI model and incorporates these improvements into the next data analysis. This allows the entire system to continuously evolve.

[0058] (Example 1)

[0059] 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."

[0060] In an environment where there is a growing demand for increased efficiency and effectiveness in marketing strategies utilizing customer information, a system is needed that can effectively collect, organize, and analyze vast amounts of data, and quickly generate appropriate insights to improve the accuracy of targeted promotions. Furthermore, continuous improvement of the system is required to guide more appropriate and effective decisions by incorporating feedback from users.

[0061] 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.

[0062] In this invention, the server includes means for collecting and preprocessing information, means for applying a generative AI model for analyzing the preprocessed information, and means for generating an interface for providing the analysis results. This enables effective management of customer data and rapid generation of insights for highly accurate promotional strategies.

[0063] "Information" refers to a collection of data and knowledge that is gathered, including customer profiles and purchase history.

[0064] "Preprocessing" refers to the process of shaping and cleaning up collected information in order to effectively analyze it, and includes correcting inaccurate data and imputing missing values.

[0065] A "generative AI model" refers to an algorithm or method that uses machine learning or artificial intelligence techniques to analyze information and generate specific insights or predictions.

[0066] "Interface" refers to a visual or interactive means of presenting analysis results to the user, including dashboards and graphical user interfaces.

[0067] "User" refers to an individual or organization that receives the output of a system and makes business decisions based on that information.

[0068] "Feedback" refers to the results of using the system and improvement suggestions received from users, and is information that can be used to improve the accuracy of the system and optimize its effectiveness.

[0069] "Insight" refers to the insights and knowledge gained from analyzed information, and is information that serves as concrete action guidelines in marketing and business strategy.

[0070] "Measures" refer to action plans or strategies formulated to achieve specific goals, and primarily include strategies and campaigns in marketing activities.

[0071] This invention is a system that utilizes a digital information processing device and generative AI technology to efficiently manage customer information and optimize marketing strategies. This system consists of three elements: a server, a terminal, and a user. Each element plays a specific role, enabling effective data analysis and decision support.

[0072] The server collects a vast amount of information and performs appropriate preprocessing. It organizes the information using a database management system and extracts the necessary data using SQL queries. It also utilizes the Python Pandas library to correct inaccurate data and ensure consistency. Based on the preprocessed information, a generative AI model is executed. Here, deep learning frameworks such as TENSORFLOW® and PyTorch are used to analyze customer purchasing trends and attribute information in detail. As a result of the analysis, insights are generated based on prompts such as, "Identify the customers who have made the most purchases and inquiries in the past six months, and predict their interest in new products."

[0073] The terminal generates a user-friendly interface based on analysis results obtained from the server. This interface visually displays data using Tableau or Power BI, creating dashboards with bar charts and line graphs, for example. This allows users to instantly grasp customer trends and use this information to develop marketing strategies.

[0074] Users plan specific marketing strategies based on insights provided on their devices. For example, they can extract lists of highly interested customers and implement email campaigns to efficiently reach them. They also provide feedback on the results of their strategies and areas for improvement, and this information is stored on the server, contributing to further improvements in the accuracy of the generated AI model.

[0075] In this way, the present invention utilizes information technology to achieve customer information management and optimization of marketing strategies.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server collects customer data from external sources. Inputs to this process include external database APIs and CSV files. API requests are sent to retrieve information from each database, and the data is received in JSON format. The output is an integrated customer dataset.

[0079] Step 2:

[0080] The server preprocesses the acquired dataset. The input is the raw data obtained in step 1. It uses the Pandas library to create a dataframe, correct inaccurate data, and impute missing values. The output is a formatted and cleansed dataset.

[0081] Step 3:

[0082] The server performs data analysis by applying a generative AI model. The input data is the data formatted in step 2. Using a TensorFlow model, customer attribute information and purchasing trends are analyzed from the dataset. From the results of this analysis, information such as purchase prediction values ​​and customer segmentation is output.

[0083] Step 4:

[0084] The terminal generates a user interface using analysis results sent from the server. The input is the insights obtained in step 3. Using the visualization tool Tableau, graphs and charts representing customer trends are created and displayed as a dashboard. This outputs the insights in a visually easy-to-understand format.

[0085] Step 5:

[0086] The user plans marketing strategies based on information provided through the interface on their device. The input is the dashboard from step 4. They consider campaign strategies and, for example, send promotional emails to highly interested customers. They analyze the results of the strategies and provide feedback to the server indicating areas for improvement. The output includes feedback information along with specific action plans.

[0087] (Application Example 1)

[0088] 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."

[0089] In customer information management, there is a need to understand each customer's purchasing trends and individual needs, and to automate efficient and personalized product recommendations and sales promotion measures. This challenge aims to provide a system that can respond immediately to diversifying customer demands, improve customer satisfaction, and build long-term customer relationships.

[0090] 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.

[0091] In this invention, the server includes means for collecting customer information and formatting the information, means for applying generative AI technology to analyze the formatted information, means for generating a display screen to provide the analysis results to the user, means for collecting user feedback and improving the generative AI technology, and means for automatically providing personalized product suggestions based on the user's purchase history and browsing history. This makes it possible to provide product suggestions and implement promotional measures that meet customer needs.

[0092] "Customer information" refers to data such as attributes, purchase history, and inquiry history related to individual customers.

[0093] "Information formatting" is the process of organizing collected data, correcting inaccurate data, and adjusting the format.

[0094] "Generative AI technology" is a technology that uses machine learning models to analyze data and automatically extract customer attributes and purchasing trends.

[0095] A "display screen" is a visual user interface designed to allow users to intuitively understand the analysis results.

[0096] "Product recommendation" refers to the action of recommending the most suitable product based on the customer's purchase history and needs.

[0097] "Sales promotion measures" are marketing activities conducted to persuade customers to purchase specific products or services.

[0098] "User ratings" refer to feedback information from users based on their experience using the system.

[0099] This invention is a customer information management system designed for e-commerce websites. This system functions through the cooperation of three elements: a server, a terminal, and a user.

[0100] The server first collects customer information by storing customer purchase and browsing history in a database. A Python script is used for data formatting, including removing duplicates and adjusting the format. The formatted data is then applied to AI technology. During this process, an AI model built using TensorFlow analyzes customer purchasing trends and attributes, generating personalized product recommendations and insights. These insights are then sent from the server to the user's device.

[0101] The device generates a display screen built using React Native based on insights provided by the server. This display screen visually presents product suggestions optimized for each individual customer. It also includes a feedback function to implement sales promotion strategies tailored to the user.

[0102] Based on the information provided through this interface, users can develop and implement appropriate marketing strategies. Furthermore, user feedback is fed back to the server using GOOGLE FI® rebase, which helps improve the generation AI technology.

[0103] For example, if a customer has previously purchased multiple electronic devices and has recently shown interest in wearable devices, the system will offer that customer a special coupon for their next purchase and recommend a new wearable device. An example of a prompt used in this process would be, "Identify users who are likely to be interested in the new product and what kind of promotion should be offered to them?"

[0104] This invention is a system that allows for the implementation of detailed marketing strategies for each customer, and is expected to improve customer satisfaction and increase sales.

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The server collects user purchase and browsing history from a database. This data serves as input, and a Python script is used to format the data, removing duplicates and adjusting the format, resulting in formatted data as output.

[0108] Step 2:

[0109] The server takes pre-formatted data as input and applies a generative AI model built with TensorFlow. By supplying data to the AI ​​model, it analyzes customer purchasing trends and attributes, and outputs personalized product recommendation insights as a result of the analysis.

[0110] Step 3:

[0111] The server sends the generated insights to the terminal. The insights become the input data, and this transmission process securely transfers the data to the terminal using a communication protocol.

[0112] Step 4:

[0113] The terminal receives insights from the server as input and generates a user interface built with React Native. To visually display the insights, it presents product suggestions optimized for each customer on the screen, with the user interface as the output.

[0114] Step 5:

[0115] Users develop and execute marketing strategies based on information provided through the device's user interface. User feedback serves as input, and this feedback is sent to the server via Google® Firebase to help improve the generated AI model. The successful submission of feedback is considered output.

[0116] 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.

[0117] This invention is a system that enables customer interaction based on customer emotions by combining an emotion engine with a customer information management system. One specific embodiment of this invention is shown below.

[0118] The server aggregates customer information obtained from external databases and existing information systems. The data collected here includes customer profile information, purchase history, customer support inquiries, and online behavior history. The collected data is then cleansed and fed into the generated AI model as clean data.

[0119] The generative AI model analyzes customer purchasing trends based on the input clean data and performs clustering. The clustering results obtained here contribute to extracting customer preferences and potential needs. However, this invention further incorporates an emotion engine to perform analysis that takes user emotions into account.

[0120] The terminal builds a user-facing dashboard based on clustering results sent from the server and emotion recognition results generated by the emotion engine. This dashboard visually shows what the customer is interested in and what emotions they are experiencing. The terminal also suggests appropriate promotional strategies to the user and adjusts those strategies as needed based on their emotional state.

[0121] Users make decisions based on this information via their devices. For example, when developing new market strategies, the emotion engine's analysis can be used to implement aggressive promotions for emotionally positive customers and consider follow-up measures for customers who have provided negative feedback. Furthermore, users can provide feedback to the system based on their interaction experiences. This feedback is stored on the server and used to improve the accuracy of both the generative AI model and the emotion engine.

[0122] As a concrete example, suppose a server analyzes a customer's purchase history and inquiry logs and discovers that the customer has repeatedly shown interest in and considered purchasing the same product in the past, but has never actually made a purchase. In this case, if the emotion engine, through text analysis within the logs, indicates that the customer may be feeling uneasy about the product, the terminal will notify the user of this information and suggest measures such as providing additional promotional materials or samples.

[0123] Thus, the present invention enables a more detailed and effective customer approach by optimizing customer management and promotional strategies, including taking into account customer emotions.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] The server collects customer information from an external database. This information includes customer profiles, purchase history, product reviews, and inquiries.

[0127] Step 2:

[0128] The server cleanses the collected data, removing unnecessary information and formatting it. This generates a clean dataset suitable for analysis.

[0129] Step 3:

[0130] The server generates clean data, inputs it into an AI model, and analyzes customer purchasing trends. The AI ​​model classifies customers into multiple clusters and clarifies the characteristics of each cluster.

[0131] Step 4:

[0132] The server uses an emotion engine to analyze each customer's emotional state. This analyzes text data contained in customer inquiry logs and reviews to recognize emotions such as positive and negative.

[0133] Step 5:

[0134] The terminal generates a user-facing dashboard based on clustering results and sentiment analysis results received from the server. This dashboard visually displays each customer's purchase intent and sentiment tendencies.

[0135] Step 6:

[0136] Users check their device dashboards and consider specific promotional strategies. For example, based on sentiment analysis, they might decide on measures to strengthen customer support for customers who exhibit negative emotions.

[0137] Step 7:

[0138] Users provide feedback to the system via their devices, based on the effectiveness of the implemented measures and new customer reactions. This feedback is stored and analyzed on the server and used to improve the AI ​​model.

[0139] Step 8:

[0140] Based on user feedback, the server readjusts the parameters of the generative AI model and emotion engine, incorporating these adjustments into subsequent analyses. This continuously improves the system's analysis accuracy and the effectiveness of its strategies.

[0141] (Example 2)

[0142] 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".

[0143] Current customer information management systems often propose strategies based only on customer purchasing trends and basic information, making it difficult to consider customer emotions and latent needs. As a result, it is difficult to implement optimal promotions and follow-ups for each customer, leading to challenges in achieving effective customer engagement.

[0144] 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.

[0145] In this invention, the server includes means for collecting and cleansing customer information, means for applying a generative AI model for analyzing the pre-processed customer information, and means for using an emotion engine for recognizing the emotions of the analyzed customers. This enables more sophisticated customer analysis that takes customer emotions into account, and the proposal of effective promotional measures based on that analysis.

[0146] "Customer information" refers to data including customer profiles, purchase history, inquiries, and online behavior history.

[0147] "Data cleansing" is a process that maintains data consistency and quality by removing duplicates, imputing missing data, and correcting outliers in collected data.

[0148] A "generative AI model" is an artificial intelligence algorithm that analyzes customer purchasing trends based on input data and recognizes specific patterns.

[0149] An "emotion engine" is a system that analyzes customer language and behavioral data to recognize positive or negative emotions.

[0150] Clustering is a data analysis technique that groups customers based on their characteristics to extract common preferences and potential needs.

[0151] A "user interface" is a screen display method that visually presents analysis results and makes it easier for users to understand the information.

[0152] "Feedback" refers to opinions and information that users input based on their experience using the system, for the purpose of improvement.

[0153] A "promotional strategy" refers to specific proposals or plans aimed at encouraging customers to purchase products or services.

[0154] This invention aims to build a detailed customer information management system that takes customer emotions into account. The server effectively collects customer information from external sources. This data includes customer profiles, purchase history, inquiries, and online behavior history. The server then cleanses the collected data to ensure consistency and quality. This process generates clean data, ready for further analysis.

[0155] The server inputs clean data into a generating AI model. This AI model analyzes customer purchasing trends within the data, recognizes patterns, and performs clustering. Furthermore, the server utilizes an emotion engine to extract emotions from customer inquiries and behaviors, identifying positive or negative emotions.

[0156] The terminal constructs a visual user interface based on clustering results and sentiment recognition results received from the server. This interface, or dashboard, helps users easily understand customer interests and emotional states, and assists them in making better decisions. The terminal also proposes promotional strategies to users that take customer emotional states into consideration. Specifically, it promotes proactive campaigns for customers with positive emotions and presents follow-up measures for customers with negative feedback.

[0157] Users can use this dashboard to develop and implement customer service strategies. Furthermore, users can provide feedback on their interaction results and experiences to the system. This feedback is stored on the server and used to improve the accuracy of the generative AI models and emotion engine.

[0158] As a concrete example, suppose a server analyzes a customer's purchase history and frequent inquiries and determines that the customer is interested in a particular product but has not yet made a purchase. In this case, the emotion engine analyzes the customer's inquiries and detects any concerns about the product. The terminal provides this information to the user, who can then suggest promotions such as providing additional materials or samples.

[0159] An example of a prompt message is, "Analyze the customer's purchase history and inquiry content, and propose promotional strategies that take their emotional state into consideration." This system enables detailed marketing tailored to each customer's individual needs and emotions.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The server collects customer information from external sources. This data includes customer profile information, purchase history, inquiries, and online behavior history. This data is temporarily stored on the server in preparation for subsequent processing.

[0163] Step 2:

[0164] The server performs data cleansing on the collected data. Specifically, it removes duplicate data, imputes missing data, and corrects outliers. This process generates high-quality clean data. This clean data is used as preparation for analysis using generative AI models.

[0165] Step 3:

[0166] The server inputs clean data into a generating AI model. Based on the input data, the generating AI model analyzes customer purchasing trends and clusters customers using a pattern recognition algorithm. The output results in clusters categorized by customer. These clusters represent customer preferences and potential needs.

[0167] Step 4:

[0168] The server uses an emotion engine to extract emotions from customer inquiries and behavioral history. Text data is provided as input, and natural language processing techniques are used to identify positive or negative emotions. This output is sent to the terminal as the emotion recognition result.

[0169] Step 5:

[0170] The terminal creates a user-facing dashboard based on clustering results and sentiment recognition results received from the server. It receives cluster groups and sentiment recognition results as input, and uses this information to create a graphical visual representation. This dashboard shows customer interests and emotional states, helping users intuitively grasp the information.

[0171] Step 6:

[0172] The device proposes appropriate promotional strategies to the user. It receives information displayed on the dashboard and the customer's emotional state as input, and uses an algorithm to determine promotional priorities. The output includes specific promotional information and follow-up strategies.

[0173] Step 7:

[0174] Users develop customer service strategies using the device's dashboard. They execute promotions and measures based on the entered information and evaluate the results. This evaluation feedback is sent to the server and used to further improve the generative AI model and emotion engine.

[0175] Through this series of steps, the system implements nuanced marketing strategies that take customer emotions into consideration.

[0176] (Application Example 2)

[0177] 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".

[0178] In today's market, sophisticated marketing strategies based on each customer's purchasing behavior and emotions are required. However, traditional systems struggle to optimize promotions while taking customer emotions into account, resulting in a lack of improvement in customer satisfaction.

[0179] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0180] In this invention, the server includes means for collecting and pre-processing customer information, means for applying a generative AI model for analyzing the pre-processed customer information, and means for analyzing customer emotions and proposing benefits related to purchasing behavior based on the analysis results. This makes it possible to optimize promotions according to customer emotions.

[0181] "Customer information" refers to a collection of data that includes customer profile information, purchase history, inquiries, and online behavior history.

[0182] "Preprocessing" is the process of removing noise from collected customer information to generate clean data suitable for analysis.

[0183] A "generative AI model" is an artificial intelligence algorithm that learns specific patterns from data and outputs analysis results.

[0184] "User interface" refers to the screen layout and operating methods used to visually present analysis results to the user.

[0185] "Feedback" refers to opinions and evaluations provided by users based on their interaction experiences, and is used to improve the system.

[0186] "Emotional analysis results" refer to an evaluation of emotions extracted from customer text data and behavioral data.

[0187] "Benefits" refer to discounts or services offered to encourage customer purchasing behavior.

[0188] "Providing information in real time" means presenting promotional information to the user's device immediately based on customer sentiment analysis results and other factors.

[0189] In this invention, the server, terminal, and user work together to operate the system.

[0190] The server collects customer information, performs data cleansing, and inputs the clean data into a generating AI model. The generating AI model performs clustering and sentiment analysis to generate analysis results of customer purchasing trends and sentiment. For these analyses, Pandas is used for data cleansing, Scikit-learn for clustering, and the RoBERTa model for sentiment analysis.

[0191] The device generates a user interface based on analysis results sent from the server and provides users with visual promotional information in real time. The device is responsible for building a dashboard using React Native and presenting the results in a user-friendly format.

[0192] Users review promotional information provided via their devices and select suitable marketing strategies. Furthermore, users send feedback based on their experiences from their devices to the server, contributing to improving the accuracy of the generated AI model.

[0193] As a concrete example, if a user adds the same product to their cart multiple times but does not make a purchase, the device will use sentiment analysis results received from the server to suggest a "trial campaign with a satisfaction guarantee." This can alleviate the user's concerns and encourage them to make a purchase.

[0194] Examples of prompt messages in this system are as follows:

[0195] "The user's purchase history is as follows:... Analyze the user's sentiment from this data and propose appropriate promotions."

[0196] Through this invention, it becomes possible to implement detailed marketing strategies based on customer emotions, thereby achieving a more effective customer approach.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server collects customer information from external databases and existing information systems. Inputs include customer profile information, purchase history, inquiries, and online behavior history. The collected data undergoes data cleansing to remove noise, generating clean data. This results in a dataset suitable for analysis.

[0200] Step 2:

[0201] The server applies a generative AI model based on clean data to cluster customer purchasing trends. This step uses machine learning libraries such as Scikit-learn to classify the data into clusters. The input is the cleaned dataset, and the output is the clustered result showing customer purchasing trends.

[0202] Step 3:

[0203] The server uses text data to analyze customer sentiment using the RoBERTa model. It takes customer inquiries and review comments as input and outputs sentiment scores. This allows the server to understand each customer's current emotional state.

[0204] Step 4:

[0205] The server generates highly personalized promotional strategies for customers based on clustering results and sentiment analysis results. The input is the output from steps 2 and 3, and the output is personalized promotional information.

[0206] Step 5:

[0207] The terminal receives promotional information sent from the server and presents it to the user in real time through the user interface. The input is promotional information from the server, and the output is visually displayed campaign and special offer information.

[0208] Step 6:

[0209] Users review promotional information displayed on their devices and make choices based on their purchasing behavior. They also provide feedback to the server via their devices. The input is the user's actions, and the output is feedback data that is generated and sent to the server.

[0210] Step 7:

[0211] The server collects feedback data from users and adds it to the training dataset of the generative AI model. This improves the accuracy of the generative AI model, making it possible to derive more accurate analysis results.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] This invention relates to a customer information management system in which a server, terminal, and user work in cooperation. Specific embodiments for carrying out this invention are described below.

[0229] The server first collects vast amounts of customer information from external databases and existing information systems. This collected data undergoes cleansing and formatting processes, including correcting inaccurate data and verifying consistency. The server then applies a generative AI model to this organized data. This AI model analyzes customer attributes and automatically extracts business-useful insights, such as purchasing trends and the progress of contract procedures.

[0230] The terminal receives analysis results from the server and generates a user interface that provides information to the user. This interface is in a dashboard format, visually displaying, for example, customer purchasing patterns, and is designed to be easily understood and utilized by sales representatives. The terminal also proposes personalized promotional strategies, which users can use to decide on specific actions.

[0231] Based on these insights provided via the device, users make specific decisions to implement targeted marketing strategies and optimize contract procedures. Furthermore, users provide feedback on the results and areas for improvement obtained during system operation. This feedback information is stored on the server and used to improve the accuracy of the generated AI model. As a result, overall system performance improves, enabling more effective customer management over time.

[0232] As a concrete example, when a company launches a new product, the server analyzes customers' past purchase and inquiry history to calculate their potential interest in the new product. The terminal then presents this insight to the user, who can then send targeted promotional emails to customers with high interest levels.

[0233] Therefore, the present invention supports the efficient management of customer information and the effective implementation of promotional measures.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The server periodically collects customer information from multiple external databases and internal data systems. This includes new contract information, customer profile information, and past purchase history.

[0237] Step 2:

[0238] The server cleanses the collected data. Specifically, it removes duplicate data and corrects incomplete or incorrect data. This process is automated based on cleansing rules.

[0239] Step 3:

[0240] The server passes the cleansed data to an AI model for analysis. The AI ​​model analyzes the data patterns to identify customer purchasing trends and product categories of interest.

[0241] Step 4:

[0242] The server aggregates the analysis results and organizes them as insights. This includes appropriate promotional recommendations for each customer and the progress of contract procedures.

[0243] Step 5:

[0244] The terminal generates a dashboard based on insights received from the server. This dashboard is designed to provide users with information in a visually appealing and easy-to-understand format.

[0245] Step 6:

[0246] Users can check their device's dashboard and determine appropriate actions for each customer. For example, they can implement marketing campaigns focused on customers interested in specific products.

[0247] Step 7:

[0248] Users provide feedback on system processing results and areas for improvement through their terminals. This feedback is collected on the server and used to retrain the AI ​​model, thereby improving the accuracy of future analyses.

[0249] Step 8:

[0250] The server uses the newly received feedback to improve the accuracy of the generated AI model and incorporates these improvements into the next data analysis. This allows the entire system to continuously evolve.

[0251] (Example 1)

[0252] 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."

[0253] In an environment where there is a growing demand for increased efficiency and effectiveness in marketing strategies utilizing customer information, a system is needed that can effectively collect, organize, and analyze vast amounts of data, and quickly generate appropriate insights to improve the accuracy of targeted promotions. Furthermore, continuous improvement of the system is required to guide more appropriate and effective decisions by incorporating feedback from users.

[0254] 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.

[0255] In this invention, the server includes means for collecting and preprocessing information, means for applying a generative AI model for analyzing the preprocessed information, and means for generating an interface for providing the analysis results. This enables effective management of customer data and rapid generation of insights for highly accurate promotional strategies.

[0256] "Information" refers to a collection of data and knowledge that is gathered, including customer profiles and purchase history.

[0257] "Preprocessing" refers to the process of shaping and cleaning up collected information in order to effectively analyze it, and includes correcting inaccurate data and imputing missing values.

[0258] A "generative AI model" refers to an algorithm or method that uses machine learning or artificial intelligence techniques to analyze information and generate specific insights or predictions.

[0259] "Interface" refers to a visual or interactive means of presenting analysis results to the user, including dashboards and graphical user interfaces.

[0260] "User" refers to an individual or organization that receives the output of a system and makes business decisions based on that information.

[0261] "Feedback" refers to the results of using the system and improvement suggestions received from users, and is information that can be used to improve the accuracy of the system and optimize its effectiveness.

[0262] "Insight" refers to the insights and knowledge gained from analyzed information, and is information that serves as concrete action guidelines in marketing and business strategy.

[0263] "Measures" refer to action plans or strategies formulated to achieve specific goals, and primarily include strategies and campaigns in marketing activities.

[0264] This invention is a system that utilizes a digital information processing device and generative AI technology to efficiently manage customer information and optimize marketing strategies. This system consists of three elements: a server, a terminal, and a user. Each element plays a specific role, enabling effective data analysis and decision support.

[0265] The server collects a vast amount of information and performs appropriate preprocessing. It organizes the information using a database management system and extracts the necessary data using SQL queries. It also utilizes the Python Pandas library to correct inaccurate data and ensure consistency. Based on the preprocessed information, a generative AI model is executed. Here, deep learning frameworks such as TensorFlow and PyTorch are used to analyze customer purchasing trends and attribute information in detail. As a result of the analysis, insights are generated based on prompts such as, "Identify the customers who have made the most purchases and inquiries in the past six months, and predict their interest in new products."

[0266] The terminal generates a user-friendly interface based on analysis results obtained from the server. This interface visually displays data using Tableau or Power BI, creating dashboards with bar charts and line graphs, for example. This allows users to instantly grasp customer trends and use this information to develop marketing strategies.

[0267] Users plan specific marketing strategies based on insights provided on their devices. For example, they can extract lists of highly interested customers and implement email campaigns to efficiently reach them. They also provide feedback on the results of their strategies and areas for improvement, and this information is stored on the server, contributing to further improvements in the accuracy of the generated AI model.

[0268] In this way, the present invention utilizes information technology to achieve customer information management and optimization of marketing strategies.

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] The server collects customer data from external sources. Inputs to this process include external database APIs and CSV files. API requests are sent to retrieve information from each database, and the data is received in JSON format. The output is an integrated customer dataset.

[0272] Step 2:

[0273] The server preprocesses the acquired dataset. The input is the raw data obtained in step 1. It uses the Pandas library to create a dataframe, correct inaccurate data, and impute missing values. The output is a formatted and cleansed dataset.

[0274] Step 3:

[0275] The server performs data analysis by applying a generative AI model. The input data is the data formatted in step 2. Using a TensorFlow model, customer attribute information and purchasing trends are analyzed from the dataset. From the results of this analysis, information such as purchase prediction values ​​and customer segmentation is output.

[0276] Step 4:

[0277] The terminal generates a user interface using analysis results sent from the server. The input is the insights obtained in step 3. Using the visualization tool Tableau, graphs and charts representing customer trends are created and displayed as a dashboard. This outputs the insights in a visually easy-to-understand format.

[0278] Step 5:

[0279] Based on the information provided through the interface on the terminal, the user plans marketing measures. The input includes the dashboard in Step 4. Consider the campaign strategy and send promotional emails to, for example, highly interested customers. Analyze the implementation results of the measures and provide the improvement points as feedback to the server. As output, feedback information is obtained along with a specific action plan.

[0280] (Application Example 1)

[0281] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0282] In customer information management, it is required to understand the purchase trends and individual needs of each customer and automate efficient and personalized product proposals and sales promotion measures. This issue aims to build long-term customer relationships by providing a system that can respond promptly to the diverse needs of customers and improve customer satisfaction.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0284] In this invention, the server includes means for collecting customer information and performing information formatting processing, means for applying generative AI technology for analyzing the formatted information, means for generating a display screen for providing the analysis result to the user, means for collecting evaluations from the user and improving the generative AI technology, and means for automatically making individualized product proposals based on the user's purchase history and browsing history. Thereby, it becomes possible to implement product proposals and promotional measures that meet the needs of customers.

[0285] "Customer information" refers to data such as attributes, purchase history, and inquiry history related to individual customers.

[0286] "Information formatting process" refers to the process of organizing the collected data, correcting inaccurate data, and adjusting the format.

[0287] "Generative AI technology" refers to the technology that uses machine learning models to analyze data and automatically extract customer attributes and purchase tendencies.

[0288] "Display screen" refers to the visual user interface for enabling users to intuitively understand the analysis results.

[0289] "Product recommendation" refers to the action of recommending the optimal products based on the customer's purchase history and needs.

[0290] "Sales promotion measures" refer to the marketing activities carried out to encourage customers to purchase specific products or services.

[0291] "User evaluation" refers to the feedback information from users based on the results of using the system.

[0292] The present invention is a customer information management system designed for an e-commerce site. This system functions through the cooperation of three elements: a server, a terminal, and a user.

[0293] First, the server accumulates the customer's purchase history and browsing history in the database to collect customer information. For data formatting, scripts using Python are used to perform data deduplication and format adjustment. Then, the formatted data is applied to the generative AI technology. At this time, an AI model built using TensorFlow analyzes the customer's purchase tendencies and attributes and generates insights for personalized product recommendations. The generated insights are sent from the server to the terminal.

[0294] The device generates a display screen built using React Native based on insights provided by the server. This display screen visually presents product suggestions optimized for each individual customer. It also includes a feedback function to implement sales promotion strategies tailored to the user.

[0295] Based on the information provided through this interface, users can develop and implement appropriate marketing strategies. Furthermore, user feedback is fed back to the server using Google Firebase and used to improve the generative AI technology.

[0296] For example, if a customer has previously purchased multiple electronic devices and has recently shown interest in wearable devices, the system will offer that customer a special coupon for their next purchase and recommend a new wearable device. An example of a prompt used in this process would be, "Identify users who are likely to be interested in the new product and what kind of promotion should be offered to them?"

[0297] This invention is a system that allows for the implementation of detailed marketing strategies for each customer, and is expected to improve customer satisfaction and increase sales.

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The server collects user purchase and browsing history from a database. This data serves as input, and a Python script is used to format the data, removing duplicates and adjusting the format, resulting in formatted data as output.

[0301] Step 2:

[0302] The server applies a generative AI model built with TensorFlow using the preprocessed data as input. By feeding the data into the AI model, it analyzes the customer's purchase trends and attributes and outputs insights on personalized product recommendations as the analysis result.

[0303] Step 3:

[0304] The server sends the generated insights to the terminal. The insights serve as input data, and in this transmission process, the data is securely transferred to the terminal using a communication protocol.

[0305] Step 4:

[0306] The terminal generates a user interface built with React Native using the insights received from the server as input. To visually display the insights, it presents product recommendations optimized for each customer on the screen, and the user interface becomes the output.

[0307] Step 5:

[0308] The user formulates and executes a marketing strategy based on the information provided through the terminal's user interface. Feedback information from the user serves as input, and this feedback is sent to the server through Google Firebase and used to improve the generative AI model. The completion of feedback transmission becomes the output.

[0309] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0310] The present invention is a system that enables interactions based on the customer's emotions by combining an emotion engine with a customer information management system. One embodiment for specifically implementing the present invention is shown below.

[0311] The server aggregates customer information obtained from external databases and existing information systems. The data collected here includes customer profile information, purchase history, customer support inquiries, and online behavior history. The collected data is then cleansed and fed into the generated AI model as clean data.

[0312] The generative AI model analyzes customer purchasing trends based on the input clean data and performs clustering. The clustering results obtained here contribute to extracting customer preferences and potential needs. However, this invention further incorporates an emotion engine to perform analysis that takes user emotions into account.

[0313] The terminal builds a user-facing dashboard based on clustering results sent from the server and emotion recognition results generated by the emotion engine. This dashboard visually shows what the customer is interested in and what emotions they are experiencing. The terminal also suggests appropriate promotional strategies to the user and adjusts those strategies as needed based on their emotional state.

[0314] Users make decisions based on this information via their devices. For example, when developing new market strategies, the emotion engine's analysis can be used to implement aggressive promotions for emotionally positive customers and consider follow-up measures for customers who have provided negative feedback. Furthermore, users can provide feedback to the system based on their interaction experiences. This feedback is stored on the server and used to improve the accuracy of both the generative AI model and the emotion engine.

[0315] As a concrete example, suppose a server analyzes a customer's purchase history and inquiry logs and discovers that the customer has repeatedly shown interest in and considered purchasing the same product in the past, but has never actually made a purchase. In this case, if the emotion engine, through text analysis within the logs, indicates that the customer may be feeling uneasy about the product, the terminal will notify the user of this information and suggest measures such as providing additional promotional materials or samples.

[0316] Thus, the present invention enables a more detailed and effective customer approach by optimizing customer management and promotional strategies, including taking into account customer emotions.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The server collects customer information from an external database. This information includes customer profiles, purchase history, product reviews, and inquiries.

[0320] Step 2:

[0321] The server cleanses the collected data, removing unnecessary information and formatting it. This generates a clean dataset suitable for analysis.

[0322] Step 3:

[0323] The server generates clean data, inputs it into an AI model, and analyzes customer purchasing trends. The AI ​​model classifies customers into multiple clusters and clarifies the characteristics of each cluster.

[0324] Step 4:

[0325] The server uses an emotion engine to analyze each customer's emotional state. This analyzes text data contained in customer inquiry logs and reviews to recognize emotions such as positive and negative.

[0326] Step 5:

[0327] The terminal generates a user-facing dashboard based on clustering results and sentiment analysis results received from the server. This dashboard visually displays each customer's purchase intent and sentiment tendencies.

[0328] Step 6:

[0329] Users check their device dashboards and consider specific promotional strategies. For example, based on sentiment analysis, they might decide on measures to strengthen customer support for customers who exhibit negative emotions.

[0330] Step 7:

[0331] Users provide feedback to the system via their devices, based on the effectiveness of the implemented measures and new customer reactions. This feedback is stored and analyzed on the server and used to improve the AI ​​model.

[0332] Step 8:

[0333] Based on user feedback, the server readjusts the parameters of the generative AI model and emotion engine, incorporating these adjustments into subsequent analyses. This continuously improves the system's analysis accuracy and the effectiveness of its strategies.

[0334] (Example 2)

[0335] 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".

[0336] Current customer information management systems often propose strategies based only on customer purchasing trends and basic information, making it difficult to consider customer emotions and latent needs. As a result, it is difficult to implement optimal promotions and follow-ups for each customer, leading to challenges in achieving effective customer engagement.

[0337] 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.

[0338] In this invention, the server includes means for collecting and cleansing customer information, means for applying a generative AI model for analyzing the pre-processed customer information, and means for using an emotion engine for recognizing the emotions of the analyzed customers. This enables more sophisticated customer analysis that takes customer emotions into account, and the proposal of effective promotional measures based on that analysis.

[0339] "Customer information" refers to data including customer profiles, purchase history, inquiries, and online behavior history.

[0340] "Data cleansing" is a process that maintains data consistency and quality by removing duplicates, imputing missing data, and correcting outliers in collected data.

[0341] A "generative AI model" is an artificial intelligence algorithm that analyzes customer purchasing trends based on input data and recognizes specific patterns.

[0342] An "emotion engine" is a system that analyzes customer language and behavioral data to recognize positive or negative emotions.

[0343] Clustering is a data analysis technique that groups customers based on their characteristics to extract common preferences and potential needs.

[0344] A "user interface" is a screen display method that visually presents analysis results and makes it easier for users to understand the information.

[0345] "Feedback" refers to opinions and information that users input based on their experience using the system, for the purpose of improvement.

[0346] A "promotional strategy" refers to specific proposals or plans aimed at encouraging customers to purchase products or services.

[0347] This invention aims to build a detailed customer information management system that takes customer emotions into account. The server effectively collects customer information from external sources. This data includes customer profiles, purchase history, inquiries, and online behavior history. The server then cleanses the collected data to ensure consistency and quality. This process generates clean data, ready for further analysis.

[0348] The server inputs clean data into a generating AI model. This AI model analyzes customer purchasing trends within the data, recognizes patterns, and performs clustering. Furthermore, the server utilizes an emotion engine to extract emotions from customer inquiries and behaviors, identifying positive or negative emotions.

[0349] The terminal constructs a visual user interface based on clustering results and sentiment recognition results received from the server. This interface, or dashboard, helps users easily understand customer interests and emotional states, and assists them in making better decisions. The terminal also proposes promotional strategies to users that take customer emotional states into consideration. Specifically, it promotes proactive campaigns for customers with positive emotions and presents follow-up measures for customers with negative feedback.

[0350] Users can use this dashboard to develop and implement customer service strategies. Furthermore, users can provide feedback on their interaction results and experiences to the system. This feedback is stored on the server and used to improve the accuracy of the generative AI models and emotion engine.

[0351] As a concrete example, suppose a server analyzes a customer's purchase history and frequent inquiries and determines that the customer is interested in a particular product but has not yet made a purchase. In this case, the emotion engine analyzes the customer's inquiries and detects any concerns about the product. The terminal provides this information to the user, who can then suggest promotions such as providing additional materials or samples.

[0352] An example of a prompt message is, "Analyze the customer's purchase history and inquiry content, and propose promotional strategies that take their emotional state into consideration." This system enables detailed marketing tailored to each customer's individual needs and emotions.

[0353] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0354] Step 1:

[0355] The server collects customer information from external sources. This data includes customer profile information, purchase history, inquiries, and online behavior history. This data is temporarily stored on the server in preparation for subsequent processing.

[0356] Step 2:

[0357] The server performs data cleansing on the collected data. Specifically, it removes duplicate data, imputes missing data, and corrects outliers. This process generates high-quality clean data. This clean data is used as preparation for analysis using generative AI models.

[0358] Step 3:

[0359] The server inputs clean data into a generating AI model. Based on the input data, the generating AI model analyzes customer purchasing trends and clusters customers using a pattern recognition algorithm. The output results in clusters categorized by customer. These clusters represent customer preferences and potential needs.

[0360] Step 4:

[0361] The server uses an emotion engine to extract emotions from customer inquiries and behavioral history. Text data is provided as input, and natural language processing techniques are used to identify positive or negative emotions. This output is sent to the terminal as the emotion recognition result.

[0362] Step 5:

[0363] The terminal creates a user-facing dashboard based on clustering results and sentiment recognition results received from the server. It receives cluster groups and sentiment recognition results as input, and uses this information to create a graphical visual representation. This dashboard shows customer interests and emotional states, helping users intuitively grasp the information.

[0364] Step 6:

[0365] The device proposes appropriate promotional strategies to the user. It receives information displayed on the dashboard and the customer's emotional state as input, and uses an algorithm to determine promotional priorities. The output includes specific promotional information and follow-up strategies.

[0366] Step 7:

[0367] Users develop customer service strategies using the device's dashboard. They execute promotions and measures based on the entered information and evaluate the results. This evaluation feedback is sent to the server and used to further improve the generative AI model and emotion engine.

[0368] Through this series of steps, the system implements nuanced marketing strategies that take customer emotions into consideration.

[0369] (Application Example 2)

[0370] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0371] In today's market, sophisticated marketing strategies based on each customer's purchasing behavior and emotions are required. However, traditional systems struggle to optimize promotions while taking customer emotions into account, resulting in a lack of improvement in customer satisfaction.

[0372] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0373] In this invention, the server includes means for collecting and pre-processing customer information, means for applying a generative AI model for analyzing the pre-processed customer information, and means for analyzing customer emotions and proposing benefits related to purchasing behavior based on the analysis results. This makes it possible to optimize promotions according to customer emotions.

[0374] "Customer information" refers to a collection of data that includes customer profile information, purchase history, inquiries, and online behavior history.

[0375] "Preprocessing" is the process of removing noise from collected customer information to generate clean data suitable for analysis.

[0376] A "generative AI model" is an artificial intelligence algorithm that learns specific patterns from data and outputs analysis results.

[0377] "User interface" refers to the screen layout and operating methods used to visually present analysis results to the user.

[0378] "Feedback" refers to opinions and evaluations provided by users based on their interaction experiences, and is used to improve the system.

[0379] "Emotional analysis results" refer to an evaluation of emotions extracted from customer text data and behavioral data.

[0380] "Benefits" refer to discounts or services offered to encourage customer purchasing behavior.

[0381] "Providing information in real time" means presenting promotional information to the user's device immediately based on customer sentiment analysis results and other factors.

[0382] In this invention, the server, terminal, and user work together to operate the system.

[0383] The server collects customer information, performs data cleansing, and inputs the clean data into a generating AI model. The generating AI model performs clustering and sentiment analysis to generate analysis results of customer purchasing trends and sentiment. For these analyses, Pandas is used for data cleansing, Scikit-learn for clustering, and the RoBERTa model for sentiment analysis.

[0384] The device generates a user interface based on analysis results sent from the server and provides users with visual promotional information in real time. The device is responsible for building a dashboard using React Native and presenting the results in a user-friendly format.

[0385] Users review promotional information provided via their devices and select suitable marketing strategies. Furthermore, users send feedback based on their experiences from their devices to the server, contributing to improving the accuracy of the generated AI model.

[0386] As a concrete example, if a user adds the same product to their cart multiple times but does not make a purchase, the device will use sentiment analysis results received from the server to suggest a "trial campaign with a satisfaction guarantee." This can alleviate the user's concerns and encourage them to make a purchase.

[0387] Examples of prompt messages in this system are as follows:

[0388] "The user's purchase history is as follows:... Analyze the user's sentiment from this data and propose appropriate promotions."

[0389] Through this invention, it becomes possible to implement detailed marketing strategies based on customer emotions, thereby achieving a more effective customer approach.

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The server collects customer information from external databases and existing information systems. Inputs include customer profile information, purchase history, inquiries, and online behavior history. The collected data undergoes data cleansing to remove noise, generating clean data. This results in a dataset suitable for analysis.

[0393] Step 2:

[0394] The server applies a generative AI model based on clean data to cluster customer purchasing trends. This step uses machine learning libraries such as Scikit-learn to classify the data into clusters. The input is the cleaned dataset, and the output is the clustered result showing customer purchasing trends.

[0395] Step 3:

[0396] The server uses text data to analyze customer sentiment using the RoBERTa model. It takes customer inquiries and review comments as input and outputs sentiment scores. This allows the server to understand each customer's current emotional state.

[0397] Step 4:

[0398] The server generates highly personalized promotional strategies for customers based on clustering results and sentiment analysis results. The input is the output from steps 2 and 3, and the output is personalized promotional information.

[0399] Step 5:

[0400] The terminal receives promotional information sent from the server and presents it to the user in real time through the user interface. The input is promotional information from the server, and the output is visually displayed campaign and special offer information.

[0401] Step 6:

[0402] Users review promotional information displayed on their devices and make choices based on their purchasing behavior. They also provide feedback to the server via their devices. The input is the user's actions, and the output is feedback data that is generated and sent to the server.

[0403] Step 7:

[0404] The server collects feedback data from users and adds it to the training dataset of the generative AI model. This improves the accuracy of the generative AI model, making it possible to derive more accurate analysis results.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] [Third Embodiment]

[0409] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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".

[0421] This invention relates to a customer information management system in which a server, terminal, and user work in cooperation. Specific embodiments for carrying out this invention are described below.

[0422] The server first collects vast amounts of customer information from external databases and existing information systems. This collected data undergoes cleansing and formatting processes, including correcting inaccurate data and verifying consistency. The server then applies a generative AI model to this organized data. This AI model analyzes customer attributes and automatically extracts business-useful insights, such as purchasing trends and the progress of contract procedures.

[0423] The terminal receives analysis results from the server and generates a user interface that provides information to the user. This interface is in a dashboard format, visually displaying, for example, customer purchasing patterns, and is designed to be easily understood and utilized by sales representatives. The terminal also proposes personalized promotional strategies, which users can use to decide on specific actions.

[0424] Based on these insights provided via the device, users make specific decisions to implement targeted marketing strategies and optimize contract procedures. Furthermore, users provide feedback on the results and areas for improvement obtained during system operation. This feedback information is stored on the server and used to improve the accuracy of the generated AI model. As a result, overall system performance improves, enabling more effective customer management over time.

[0425] As a concrete example, when a company launches a new product, the server analyzes customers' past purchase and inquiry history to calculate their potential interest in the new product. The terminal then presents this insight to the user, who can then send targeted promotional emails to customers with high interest levels.

[0426] Therefore, the present invention supports the efficient management of customer information and the effective implementation of promotional measures.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] The server periodically collects customer information from multiple external databases and internal data systems. This includes new contract information, customer profile information, and past purchase history.

[0430] Step 2:

[0431] The server cleanses the collected data. Specifically, it removes duplicate data and corrects incomplete or incorrect data. This process is automated based on cleansing rules.

[0432] Step 3:

[0433] The server passes the cleansed data to an AI model for analysis. The AI ​​model analyzes the data patterns to identify customer purchasing trends and product categories of interest.

[0434] Step 4:

[0435] The server aggregates the analysis results and organizes them as insights. This includes appropriate promotional recommendations for each customer and the progress of contract procedures.

[0436] Step 5:

[0437] The terminal generates a dashboard based on insights received from the server. This dashboard is designed to provide users with information in a visually appealing and easy-to-understand format.

[0438] Step 6:

[0439] Users can check their device's dashboard and determine appropriate actions for each customer. For example, they can implement marketing campaigns focused on customers interested in specific products.

[0440] Step 7:

[0441] Users provide feedback on system processing results and areas for improvement through their terminals. This feedback is collected on the server and used to retrain the AI ​​model, thereby improving the accuracy of future analyses.

[0442] Step 8:

[0443] The server uses the newly received feedback to improve the accuracy of the generated AI model and incorporates these improvements into the next data analysis. This allows the entire system to continuously evolve.

[0444] (Example 1)

[0445] 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."

[0446] In an environment where there is a growing demand for increased efficiency and effectiveness in marketing strategies utilizing customer information, a system is needed that can effectively collect, organize, and analyze vast amounts of data, and quickly generate appropriate insights to improve the accuracy of targeted promotions. Furthermore, continuous improvement of the system is required to guide more appropriate and effective decisions by incorporating feedback from users.

[0447] 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.

[0448] In this invention, the server includes means for collecting and preprocessing information, means for applying a generative AI model for analyzing the preprocessed information, and means for generating an interface for providing the analysis results. This enables effective management of customer data and rapid generation of insights for highly accurate promotional strategies.

[0449] "Information" refers to a collection of data and knowledge that is gathered, including customer profiles and purchase history.

[0450] "Preprocessing" refers to the process of shaping and cleaning up collected information in order to effectively analyze it, and includes correcting inaccurate data and imputing missing values.

[0451] A "generative AI model" refers to an algorithm or method that uses machine learning or artificial intelligence techniques to analyze information and generate specific insights or predictions.

[0452] "Interface" refers to a visual or interactive means of presenting analysis results to the user, including dashboards and graphical user interfaces.

[0453] "User" refers to an individual or organization that receives the output of a system and makes business decisions based on that information.

[0454] "Feedback" refers to the results of using the system and improvement suggestions received from users, and is information that can be used to improve the accuracy of the system and optimize its effectiveness.

[0455] "Insight" refers to the insights and knowledge gained from analyzed information, and is information that serves as concrete action guidelines in marketing and business strategy.

[0456] "Measures" refer to action plans or strategies formulated to achieve specific goals, and primarily include strategies and campaigns in marketing activities.

[0457] This invention is a system that utilizes a digital information processing device and generative AI technology to efficiently manage customer information and optimize marketing strategies. This system consists of three elements: a server, a terminal, and a user. Each element plays a specific role, enabling effective data analysis and decision support.

[0458] The server collects a vast amount of information and performs appropriate preprocessing. It organizes the information using a database management system and extracts the necessary data using SQL queries. It also utilizes the Python Pandas library to correct inaccurate data and ensure consistency. Based on the preprocessed information, a generative AI model is executed. Here, deep learning frameworks such as TensorFlow and PyTorch are used to analyze customer purchasing trends and attribute information in detail. As a result of the analysis, insights are generated based on prompts such as, "Identify the customers who have made the most purchases and inquiries in the past six months, and predict their interest in new products."

[0459] The terminal generates a user-friendly interface based on analysis results obtained from the server. This interface visually displays data using Tableau or Power BI, creating dashboards with bar charts and line graphs, for example. This allows users to instantly grasp customer trends and use this information to develop marketing strategies.

[0460] Users plan specific marketing strategies based on insights provided on their devices. For example, they can extract lists of highly interested customers and implement email campaigns to efficiently reach them. They also provide feedback on the results of their strategies and areas for improvement, and this information is stored on the server, contributing to further improvements in the accuracy of the generated AI model.

[0461] In this way, the present invention utilizes information technology to achieve customer information management and optimization of marketing strategies.

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The server collects customer data from external sources. Inputs to this process include external database APIs and CSV files. API requests are sent to retrieve information from each database, and the data is received in JSON format. The output is an integrated customer dataset.

[0465] Step 2:

[0466] The server preprocesses the acquired dataset. The input is the raw data obtained in step 1. It uses the Pandas library to create a dataframe, correct inaccurate data, and impute missing values. The output is a formatted and cleansed dataset.

[0467] Step 3:

[0468] The server performs data analysis by applying a generative AI model. The input data is the data formatted in step 2. Using a TensorFlow model, customer attribute information and purchasing trends are analyzed from the dataset. From the results of this analysis, information such as purchase prediction values ​​and customer segmentation is output.

[0469] Step 4:

[0470] The terminal generates a user interface using analysis results sent from the server. The input is the insights obtained in step 3. Using the visualization tool Tableau, graphs and charts representing customer trends are created and displayed as a dashboard. This outputs the insights in a visually easy-to-understand format.

[0471] Step 5:

[0472] The user plans marketing strategies based on information provided through the interface on their device. The input is the dashboard from step 4. They consider campaign strategies and, for example, send promotional emails to highly interested customers. They analyze the results of the strategies and provide feedback to the server indicating areas for improvement. The output includes feedback information along with specific action plans.

[0473] (Application Example 1)

[0474] 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."

[0475] In customer information management, there is a need to understand each customer's purchasing trends and individual needs, and to automate efficient and personalized product recommendations and sales promotion measures. This challenge aims to provide a system that can respond immediately to diversifying customer demands, improve customer satisfaction, and build long-term customer relationships.

[0476] 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.

[0477] In this invention, the server includes means for collecting customer information and formatting the information, means for applying generative AI technology to analyze the formatted information, means for generating a display screen to provide the analysis results to the user, means for collecting user feedback and improving the generative AI technology, and means for automatically providing personalized product suggestions based on the user's purchase history and browsing history. This makes it possible to provide product suggestions and implement promotional measures that meet customer needs.

[0478] "Customer information" refers to data such as attributes, purchase history, and inquiry history related to individual customers.

[0479] "Information formatting" is the process of organizing collected data, correcting inaccurate data, and adjusting the format.

[0480] "Generative AI technology" is a technology that uses machine learning models to analyze data and automatically extract customer attributes and purchasing trends.

[0481] A "display screen" is a visual user interface designed to allow users to intuitively understand the analysis results.

[0482] "Product recommendation" refers to the action of recommending the most suitable product based on the customer's purchase history and needs.

[0483] "Sales promotion measures" are marketing activities conducted to persuade customers to purchase specific products or services.

[0484] "User ratings" refer to feedback information from users based on their experience using the system.

[0485] This invention is a customer information management system designed for e-commerce websites. This system functions through the cooperation of three elements: a server, a terminal, and a user.

[0486] The server first collects customer information by storing customer purchase and browsing history in a database. A Python script is used for data formatting, including removing duplicates and adjusting the format. The formatted data is then applied to AI technology. During this process, an AI model built using TensorFlow analyzes customer purchasing trends and attributes, generating personalized product recommendations and insights. These insights are then sent from the server to the user's device.

[0487] The device generates a display screen built using React Native based on insights provided by the server. This display screen visually presents product suggestions optimized for each individual customer. It also includes a feedback function to implement sales promotion strategies tailored to the user.

[0488] Based on the information provided through this interface, users can develop and implement appropriate marketing strategies. Furthermore, user feedback is fed back to the server using Google Firebase and used to improve the generative AI technology.

[0489] For example, if a customer has previously purchased multiple electronic devices and has recently shown interest in wearable devices, the system will offer that customer a special coupon for their next purchase and recommend a new wearable device. An example of a prompt used in this process would be, "Identify users who are likely to be interested in the new product and what kind of promotion should be offered to them?"

[0490] This invention is a system that allows for the implementation of detailed marketing strategies for each customer, and is expected to improve customer satisfaction and increase sales.

[0491] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0492] Step 1:

[0493] The server collects user purchase and browsing history from a database. This data serves as input, and a Python script is used to format the data, removing duplicates and adjusting the format, resulting in formatted data as output.

[0494] Step 2:

[0495] The server takes pre-formatted data as input and applies a generative AI model built with TensorFlow. By supplying data to the AI ​​model, it analyzes customer purchasing trends and attributes, and outputs personalized product recommendation insights as a result of the analysis.

[0496] Step 3:

[0497] The server sends the generated insights to the terminal. The insights become the input data, and this transmission process securely transfers the data to the terminal using a communication protocol.

[0498] Step 4:

[0499] The terminal receives insights from the server as input and generates a user interface built with React Native. To visually display the insights, it presents product suggestions optimized for each customer on the screen, with the user interface as the output.

[0500] Step 5:

[0501] Users develop and execute marketing strategies based on information provided through the device's user interface. User feedback serves as input, and this feedback is sent to the server via Google Firebase to help improve the generated AI model. The successful submission of feedback is considered output.

[0502] 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.

[0503] This invention is a system that enables customer interaction based on customer emotions by combining an emotion engine with a customer information management system. One specific embodiment of this invention is shown below.

[0504] The server aggregates customer information obtained from external databases and existing information systems. The data collected here includes customer profile information, purchase history, customer support inquiries, and online behavior history. The collected data is then cleansed and fed into the generated AI model as clean data.

[0505] The generative AI model analyzes customer purchasing trends based on the input clean data and performs clustering. The clustering results obtained here contribute to extracting customer preferences and potential needs. However, this invention further incorporates an emotion engine to perform analysis that takes user emotions into account.

[0506] The terminal builds a user-facing dashboard based on clustering results sent from the server and emotion recognition results generated by the emotion engine. This dashboard visually shows what the customer is interested in and what emotions they are experiencing. The terminal also suggests appropriate promotional strategies to the user and adjusts those strategies as needed based on their emotional state.

[0507] Users make decisions based on this information via their devices. For example, when developing new market strategies, the emotion engine's analysis can be used to implement aggressive promotions for emotionally positive customers and consider follow-up measures for customers who have provided negative feedback. Furthermore, users can provide feedback to the system based on their interaction experiences. This feedback is stored on the server and used to improve the accuracy of both the generative AI model and the emotion engine.

[0508] As a concrete example, suppose a server analyzes a customer's purchase history and inquiry logs and discovers that the customer has repeatedly shown interest in and considered purchasing the same product in the past, but has never actually made a purchase. In this case, if the emotion engine, through text analysis within the logs, indicates that the customer may be feeling uneasy about the product, the terminal will notify the user of this information and suggest measures such as providing additional promotional materials or samples.

[0509] Thus, the present invention enables a more detailed and effective customer approach by optimizing customer management and promotional strategies, including taking into account customer emotions.

[0510] The following describes the processing flow.

[0511] Step 1:

[0512] The server collects customer information from an external database. This information includes customer profiles, purchase history, product reviews, and inquiries.

[0513] Step 2:

[0514] The server cleanses the collected data, removing unnecessary information and formatting it. This generates a clean dataset suitable for analysis.

[0515] Step 3:

[0516] The server generates clean data, inputs it into an AI model, and analyzes customer purchasing trends. The AI ​​model classifies customers into multiple clusters and clarifies the characteristics of each cluster.

[0517] Step 4:

[0518] The server uses an emotion engine to analyze each customer's emotional state. This analyzes text data contained in customer inquiry logs and reviews to recognize emotions such as positive and negative.

[0519] Step 5:

[0520] The terminal generates a user-facing dashboard based on clustering results and sentiment analysis results received from the server. This dashboard visually displays each customer's purchase intent and sentiment tendencies.

[0521] Step 6:

[0522] Users check their device dashboards and consider specific promotional strategies. For example, based on sentiment analysis, they might decide on measures to strengthen customer support for customers who exhibit negative emotions.

[0523] Step 7:

[0524] Users provide feedback to the system via their devices, based on the effectiveness of the implemented measures and new customer reactions. This feedback is stored and analyzed on the server and used to improve the AI ​​model.

[0525] Step 8:

[0526] Based on user feedback, the server readjusts the parameters of the generative AI model and emotion engine, incorporating these adjustments into subsequent analyses. This continuously improves the system's analysis accuracy and the effectiveness of its strategies.

[0527] (Example 2)

[0528] 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."

[0529] Current customer information management systems often propose strategies based only on customer purchasing trends and basic information, making it difficult to consider customer emotions and latent needs. As a result, it is difficult to implement optimal promotions and follow-ups for each customer, leading to challenges in achieving effective customer engagement.

[0530] 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.

[0531] In this invention, the server includes means for collecting and cleansing customer information, means for applying a generative AI model for analyzing the pre-processed customer information, and means for using an emotion engine for recognizing the emotions of the analyzed customers. This enables more sophisticated customer analysis that takes customer emotions into account, and the proposal of effective promotional measures based on that analysis.

[0532] "Customer information" refers to data including customer profiles, purchase history, inquiries, and online behavior history.

[0533] "Data cleansing" is a process that maintains data consistency and quality by removing duplicates, imputing missing data, and correcting outliers in collected data.

[0534] A "generative AI model" is an artificial intelligence algorithm that analyzes customer purchasing trends based on input data and recognizes specific patterns.

[0535] An "emotion engine" is a system that analyzes customer language and behavioral data to recognize positive or negative emotions.

[0536] Clustering is a data analysis technique that groups customers based on their characteristics to extract common preferences and potential needs.

[0537] A "user interface" is a screen display method that visually presents analysis results and makes it easier for users to understand the information.

[0538] "Feedback" refers to opinions and information that users input based on their experience using the system, for the purpose of improvement.

[0539] A "promotional strategy" refers to specific proposals or plans aimed at encouraging customers to purchase products or services.

[0540] This invention aims to build a detailed customer information management system that takes customer emotions into account. The server effectively collects customer information from external sources. This data includes customer profiles, purchase history, inquiries, and online behavior history. The server then cleanses the collected data to ensure consistency and quality. This process generates clean data, ready for further analysis.

[0541] The server inputs clean data into a generating AI model. This AI model analyzes customer purchasing trends within the data, recognizes patterns, and performs clustering. Furthermore, the server utilizes an emotion engine to extract emotions from customer inquiries and behaviors, identifying positive or negative emotions.

[0542] The terminal constructs a visual user interface based on clustering results and sentiment recognition results received from the server. This interface, or dashboard, helps users easily understand customer interests and emotional states, and assists them in making better decisions. The terminal also proposes promotional strategies to users that take customer emotional states into consideration. Specifically, it promotes proactive campaigns for customers with positive emotions and presents follow-up measures for customers with negative feedback.

[0543] Users can use this dashboard to develop and implement customer service strategies. Furthermore, users can provide feedback on their interaction results and experiences to the system. This feedback is stored on the server and used to improve the accuracy of the generative AI models and emotion engine.

[0544] As a concrete example, suppose a server analyzes a customer's purchase history and frequent inquiries and determines that the customer is interested in a particular product but has not yet made a purchase. In this case, the emotion engine analyzes the customer's inquiries and detects any concerns about the product. The terminal provides this information to the user, who can then suggest promotions such as providing additional materials or samples.

[0545] An example of a prompt message is, "Analyze the customer's purchase history and inquiry content, and propose promotional strategies that take their emotional state into consideration." This system enables detailed marketing tailored to each customer's individual needs and emotions.

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1:

[0548] The server collects customer information from external sources. This data includes customer profile information, purchase history, inquiries, and online behavior history. This data is temporarily stored on the server in preparation for subsequent processing.

[0549] Step 2:

[0550] The server performs data cleansing on the collected data. Specifically, it removes duplicate data, imputes missing data, and corrects outliers. This process generates high-quality clean data. This clean data is used as preparation for analysis using generative AI models.

[0551] Step 3:

[0552] The server inputs clean data into a generating AI model. Based on the input data, the generating AI model analyzes customer purchasing trends and clusters customers using a pattern recognition algorithm. The output results in clusters categorized by customer. These clusters represent customer preferences and potential needs.

[0553] Step 4:

[0554] The server uses an emotion engine to extract emotions from customer inquiries and behavioral history. Text data is provided as input, and natural language processing techniques are used to identify positive or negative emotions. This output is sent to the terminal as the emotion recognition result.

[0555] Step 5:

[0556] The terminal creates a user-facing dashboard based on clustering results and sentiment recognition results received from the server. It receives cluster groups and sentiment recognition results as input, and uses this information to create a graphical visual representation. This dashboard shows customer interests and emotional states, helping users intuitively grasp the information.

[0557] Step 6:

[0558] The device proposes appropriate promotional strategies to the user. It receives information displayed on the dashboard and the customer's emotional state as input, and uses an algorithm to determine promotional priorities. The output includes specific promotional information and follow-up strategies.

[0559] Step 7:

[0560] Users develop customer service strategies using the device's dashboard. They execute promotions and measures based on the entered information and evaluate the results. This evaluation feedback is sent to the server and used to further improve the generative AI model and emotion engine.

[0561] Through this series of steps, the system implements nuanced marketing strategies that take customer emotions into consideration.

[0562] (Application Example 2)

[0563] 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."

[0564] In today's market, sophisticated marketing strategies based on each customer's purchasing behavior and emotions are required. However, traditional systems struggle to optimize promotions while taking customer emotions into account, resulting in a lack of improvement in customer satisfaction.

[0565] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0566] In this invention, the server includes means for collecting and pre-processing customer information, means for applying a generative AI model for analyzing the pre-processed customer information, and means for analyzing customer emotions and proposing benefits related to purchasing behavior based on the analysis results. This makes it possible to optimize promotions according to customer emotions.

[0567] "Customer information" refers to a collection of data that includes customer profile information, purchase history, inquiries, and online behavior history.

[0568] "Preprocessing" is the process of removing noise from collected customer information to generate clean data suitable for analysis.

[0569] A "generative AI model" is an artificial intelligence algorithm that learns specific patterns from data and outputs analysis results.

[0570] "User interface" refers to the screen layout and operating methods used to visually present analysis results to the user.

[0571] "Feedback" refers to opinions and evaluations provided by users based on their interaction experiences, and is used to improve the system.

[0572] "Emotional analysis results" refer to an evaluation of emotions extracted from customer text data and behavioral data.

[0573] "Benefits" refer to discounts or services offered to encourage customer purchasing behavior.

[0574] "Providing information in real time" means presenting promotional information to the user's device immediately based on customer sentiment analysis results and other factors.

[0575] In this invention, the server, terminal, and user work together to operate the system.

[0576] The server collects customer information, performs data cleansing, and inputs the clean data into a generating AI model. The generating AI model performs clustering and sentiment analysis to generate analysis results of customer purchasing trends and sentiment. For these analyses, Pandas is used for data cleansing, Scikit-learn for clustering, and the RoBERTa model for sentiment analysis.

[0577] The device generates a user interface based on analysis results sent from the server and provides users with visual promotional information in real time. The device is responsible for building a dashboard using React Native and presenting the results in a user-friendly format.

[0578] Users review promotional information provided via their devices and select suitable marketing strategies. Furthermore, users send feedback based on their experiences from their devices to the server, contributing to improving the accuracy of the generated AI model.

[0579] As a concrete example, if a user adds the same product to their cart multiple times but does not make a purchase, the device will use sentiment analysis results received from the server to suggest a "trial campaign with a satisfaction guarantee." This can alleviate the user's concerns and encourage them to make a purchase.

[0580] Examples of prompt messages in this system are as follows:

[0581] "The user's purchase history is as follows:... Analyze the user's sentiment from this data and propose appropriate promotions."

[0582] Through this invention, it becomes possible to implement detailed marketing strategies based on customer emotions, thereby achieving a more effective customer approach.

[0583] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0584] Step 1:

[0585] The server collects customer information from external databases and existing information systems. Inputs include customer profile information, purchase history, inquiries, and online behavior history. The collected data undergoes data cleansing to remove noise, generating clean data. This results in a dataset suitable for analysis.

[0586] Step 2:

[0587] The server applies a generative AI model based on clean data to cluster customer purchasing trends. This step uses machine learning libraries such as Scikit-learn to classify the data into clusters. The input is the cleaned dataset, and the output is the clustered result showing customer purchasing trends.

[0588] Step 3:

[0589] The server uses text data to analyze customer sentiment using the RoBERTa model. It takes customer inquiries and review comments as input and outputs sentiment scores. This allows the server to understand each customer's current emotional state.

[0590] Step 4:

[0591] The server generates highly personalized promotional strategies for customers based on clustering results and sentiment analysis results. The input is the output from steps 2 and 3, and the output is personalized promotional information.

[0592] Step 5:

[0593] The terminal receives promotional information sent from the server and presents it to the user in real time through the user interface. The input is promotional information from the server, and the output is visually displayed campaign and special offer information.

[0594] Step 6:

[0595] Users review promotional information displayed on their devices and make choices based on their purchasing behavior. They also provide feedback to the server via their devices. The input is the user's actions, and the output is feedback data that is generated and sent to the server.

[0596] Step 7:

[0597] The server collects feedback data from users and adds it to the training dataset of the generative AI model. This improves the accuracy of the generative AI model, making it possible to derive more accurate analysis results.

[0598] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0599] 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.

[0600] 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.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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".

[0615] This invention relates to a customer information management system in which a server, terminal, and user work in cooperation. Specific embodiments for carrying out this invention are described below.

[0616] The server first collects vast amounts of customer information from external databases and existing information systems. This collected data undergoes cleansing and formatting processes, including correcting inaccurate data and verifying consistency. The server then applies a generative AI model to this organized data. This AI model analyzes customer attributes and automatically extracts business-useful insights, such as purchasing trends and the progress of contract procedures.

[0617] The terminal receives analysis results from the server and generates a user interface that provides information to the user. This interface is in a dashboard format, visually displaying, for example, customer purchasing patterns, and is designed to be easily understood and utilized by sales representatives. The terminal also proposes personalized promotional strategies, which users can use to decide on specific actions.

[0618] Based on these insights provided via the device, users make specific decisions to implement targeted marketing strategies and optimize contract procedures. Furthermore, users provide feedback on the results and areas for improvement obtained during system operation. This feedback information is stored on the server and used to improve the accuracy of the generated AI model. As a result, overall system performance improves, enabling more effective customer management over time.

[0619] As a concrete example, when a company launches a new product, the server analyzes customers' past purchase and inquiry history to calculate their potential interest in the new product. The terminal then presents this insight to the user, who can then send targeted promotional emails to customers with high interest levels.

[0620] Therefore, the present invention supports the efficient management of customer information and the effective implementation of promotional measures.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] The server periodically collects customer information from multiple external databases and internal data systems. This includes new contract information, customer profile information, and past purchase history.

[0624] Step 2:

[0625] The server cleanses the collected data. Specifically, it removes duplicate data and corrects incomplete or incorrect data. This process is automated based on cleansing rules.

[0626] Step 3:

[0627] The server passes the cleansed data to an AI model for analysis. The AI ​​model analyzes the data patterns to identify customer purchasing trends and product categories of interest.

[0628] Step 4:

[0629] The server aggregates the analysis results and organizes them as insights. This includes appropriate promotional recommendations for each customer and the progress of contract procedures.

[0630] Step 5:

[0631] The terminal generates a dashboard based on insights received from the server. This dashboard is designed to provide users with information in a visually appealing and easy-to-understand format.

[0632] Step 6:

[0633] Users can check their device's dashboard and determine appropriate actions for each customer. For example, they can implement marketing campaigns focused on customers interested in specific products.

[0634] Step 7:

[0635] Users provide feedback on system processing results and areas for improvement through their terminals. This feedback is collected on the server and used to retrain the AI ​​model, thereby improving the accuracy of future analyses.

[0636] Step 8:

[0637] The server uses the newly received feedback to improve the accuracy of the generated AI model and incorporates these improvements into the next data analysis. This allows the entire system to continuously evolve.

[0638] (Example 1)

[0639] 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".

[0640] In an environment where there is a growing demand for increased efficiency and effectiveness in marketing strategies utilizing customer information, a system is needed that can effectively collect, organize, and analyze vast amounts of data, and quickly generate appropriate insights to improve the accuracy of targeted promotions. Furthermore, continuous improvement of the system is required to guide more appropriate and effective decisions by incorporating feedback from users.

[0641] 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.

[0642] In this invention, the server includes means for collecting and preprocessing information, means for applying a generative AI model for analyzing the preprocessed information, and means for generating an interface for providing the analysis results. This enables effective management of customer data and rapid generation of insights for highly accurate promotional strategies.

[0643] "Information" refers to a collection of data and knowledge that is gathered, including customer profiles and purchase history.

[0644] "Preprocessing" refers to the process of shaping and cleaning up collected information in order to effectively analyze it, and includes correcting inaccurate data and imputing missing values.

[0645] A "generative AI model" refers to an algorithm or method that uses machine learning or artificial intelligence techniques to analyze information and generate specific insights or predictions.

[0646] "Interface" refers to a visual or interactive means of presenting analysis results to the user, including dashboards and graphical user interfaces.

[0647] "User" refers to an individual or organization that receives the output of a system and makes business decisions based on that information.

[0648] "Feedback" refers to the results of using the system and improvement suggestions received from users, and is information that can be used to improve the accuracy of the system and optimize its effectiveness.

[0649] "Insight" refers to the insights and knowledge gained from analyzed information, and is information that serves as concrete action guidelines in marketing and business strategy.

[0650] "Measures" refer to action plans or strategies formulated to achieve specific goals, and primarily include strategies and campaigns in marketing activities.

[0651] This invention is a system that utilizes a digital information processing device and generative AI technology to efficiently manage customer information and optimize marketing strategies. This system consists of three elements: a server, a terminal, and a user. Each element plays a specific role, enabling effective data analysis and decision support.

[0652] The server collects a vast amount of information and performs appropriate preprocessing. It organizes the information using a database management system and extracts the necessary data using SQL queries. It also utilizes the Python Pandas library to correct inaccurate data and ensure consistency. Based on the preprocessed information, a generative AI model is executed. Here, deep learning frameworks such as TensorFlow and PyTorch are used to analyze customer purchasing trends and attribute information in detail. As a result of the analysis, insights are generated based on prompts such as, "Identify the customers who have made the most purchases and inquiries in the past six months, and predict their interest in new products."

[0653] The terminal generates a user-friendly interface based on analysis results obtained from the server. This interface visually displays data using Tableau or Power BI, creating dashboards with bar charts and line graphs, for example. This allows users to instantly grasp customer trends and use this information to develop marketing strategies.

[0654] Users plan specific marketing strategies based on insights provided on their devices. For example, they can extract lists of highly interested customers and implement email campaigns to efficiently reach them. They also provide feedback on the results of their strategies and areas for improvement, and this information is stored on the server, contributing to further improvements in the accuracy of the generated AI model.

[0655] In this way, the present invention utilizes information technology to achieve customer information management and optimization of marketing strategies.

[0656] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0657] Step 1:

[0658] The server collects customer data from external sources. Inputs to this process include external database APIs and CSV files. API requests are sent to retrieve information from each database, and the data is received in JSON format. The output is an integrated customer dataset.

[0659] Step 2:

[0660] The server preprocesses the acquired dataset. The input is the raw data obtained in step 1. It uses the Pandas library to create a dataframe, correct inaccurate data, and impute missing values. The output is a formatted and cleansed dataset.

[0661] Step 3:

[0662] The server performs data analysis by applying a generative AI model. The input data is the data formatted in step 2. Using a TensorFlow model, customer attribute information and purchasing trends are analyzed from the dataset. From the results of this analysis, information such as purchase prediction values ​​and customer segmentation is output.

[0663] Step 4:

[0664] The terminal generates a user interface using analysis results sent from the server. The input is the insights obtained in step 3. Using the visualization tool Tableau, graphs and charts representing customer trends are created and displayed as a dashboard. This outputs the insights in a visually easy-to-understand format.

[0665] Step 5:

[0666] The user plans marketing strategies based on information provided through the interface on their device. The input is the dashboard from step 4. They consider campaign strategies and, for example, send promotional emails to highly interested customers. They analyze the results of the strategies and provide feedback to the server indicating areas for improvement. The output includes feedback information along with specific action plans.

[0667] (Application Example 1)

[0668] 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".

[0669] In customer information management, there is a need to understand each customer's purchasing trends and individual needs, and to automate efficient and personalized product recommendations and sales promotion measures. This challenge aims to provide a system that can respond immediately to diversifying customer demands, improve customer satisfaction, and build long-term customer relationships.

[0670] 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.

[0671] In this invention, the server includes means for collecting customer information and formatting the information, means for applying generative AI technology to analyze the formatted information, means for generating a display screen to provide the analysis results to the user, means for collecting user feedback and improving the generative AI technology, and means for automatically providing personalized product suggestions based on the user's purchase history and browsing history. This makes it possible to provide product suggestions and implement promotional measures that meet customer needs.

[0672] "Customer information" refers to data such as attributes, purchase history, and inquiry history related to individual customers.

[0673] "Information formatting" is the process of organizing collected data, correcting inaccurate data, and adjusting the format.

[0674] "Generative AI technology" is a technology that uses machine learning models to analyze data and automatically extract customer attributes and purchasing trends.

[0675] A "display screen" is a visual user interface designed to allow users to intuitively understand the analysis results.

[0676] "Product recommendation" refers to the action of recommending the most suitable product based on the customer's purchase history and needs.

[0677] "Sales promotion measures" are marketing activities conducted to persuade customers to purchase specific products or services.

[0678] "User ratings" refer to feedback information from users based on their experience using the system.

[0679] This invention is a customer information management system designed for e-commerce websites. This system functions through the cooperation of three elements: a server, a terminal, and a user.

[0680] The server first collects customer information by storing customer purchase and browsing history in a database. A Python script is used for data formatting, including removing duplicates and adjusting the format. The formatted data is then applied to AI technology. During this process, an AI model built using TensorFlow analyzes customer purchasing trends and attributes, generating personalized product recommendations and insights. These insights are then sent from the server to the user's device.

[0681] The device generates a display screen built using React Native based on insights provided by the server. This display screen visually presents product suggestions optimized for each individual customer. It also includes a feedback function to implement sales promotion strategies tailored to the user.

[0682] Based on the information provided through this interface, users can develop and implement appropriate marketing strategies. Furthermore, user feedback is fed back to the server using Google Firebase and used to improve the generative AI technology.

[0683] For example, if a customer has previously purchased multiple electronic devices and has recently shown interest in wearable devices, the system will offer that customer a special coupon for their next purchase and recommend a new wearable device. An example of a prompt used in this process would be, "Identify users who are likely to be interested in the new product and what kind of promotion should be offered to them?"

[0684] This invention is a system that allows for the implementation of detailed marketing strategies for each customer, and is expected to improve customer satisfaction and increase sales.

[0685] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0686] Step 1:

[0687] The server collects user purchase and browsing history from a database. This data serves as input, and a Python script is used to format the data, removing duplicates and adjusting the format, resulting in formatted data as output.

[0688] Step 2:

[0689] The server takes pre-formatted data as input and applies a generative AI model built with TensorFlow. By supplying data to the AI ​​model, it analyzes customer purchasing trends and attributes, and outputs personalized product recommendation insights as a result of the analysis.

[0690] Step 3:

[0691] The server sends the generated insights to the terminal. The insights become the input data, and this transmission process securely transfers the data to the terminal using a communication protocol.

[0692] Step 4:

[0693] The terminal receives insights from the server as input and generates a user interface built with React Native. To visually display the insights, it presents product suggestions optimized for each customer on the screen, with the user interface as the output.

[0694] Step 5:

[0695] Users develop and execute marketing strategies based on information provided through the device's user interface. User feedback serves as input, and this feedback is sent to the server via Google Firebase to help improve the generated AI model. The successful submission of feedback is considered output.

[0696] 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.

[0697] This invention is a system that enables customer interaction based on customer emotions by combining an emotion engine with a customer information management system. One specific embodiment of this invention is shown below.

[0698] The server aggregates customer information obtained from external databases and existing information systems. The data collected here includes customer profile information, purchase history, customer support inquiries, and online behavior history. The collected data is then cleansed and fed into the generated AI model as clean data.

[0699] The generative AI model analyzes customer purchasing trends based on the input clean data and performs clustering. The clustering results obtained here contribute to extracting customer preferences and potential needs. However, this invention further incorporates an emotion engine to perform analysis that takes user emotions into account.

[0700] The terminal builds a user-facing dashboard based on clustering results sent from the server and emotion recognition results generated by the emotion engine. This dashboard visually shows what the customer is interested in and what emotions they are experiencing. The terminal also suggests appropriate promotional strategies to the user and adjusts those strategies as needed based on their emotional state.

[0701] Users make decisions based on this information via their devices. For example, when developing new market strategies, the emotion engine's analysis can be used to implement aggressive promotions for emotionally positive customers and consider follow-up measures for customers who have provided negative feedback. Furthermore, users can provide feedback to the system based on their interaction experiences. This feedback is stored on the server and used to improve the accuracy of both the generative AI model and the emotion engine.

[0702] As a concrete example, suppose a server analyzes a customer's purchase history and inquiry logs and discovers that the customer has repeatedly shown interest in and considered purchasing the same product in the past, but has never actually made a purchase. In this case, if the emotion engine, through text analysis within the logs, indicates that the customer may be feeling uneasy about the product, the terminal will notify the user of this information and suggest measures such as providing additional promotional materials or samples.

[0703] Thus, the present invention enables a more detailed and effective customer approach by optimizing customer management and promotional strategies, including taking into account customer emotions.

[0704] The following describes the processing flow.

[0705] Step 1:

[0706] The server collects customer information from an external database. This information includes customer profiles, purchase history, product reviews, and inquiries.

[0707] Step 2:

[0708] The server cleanses the collected data, removing unnecessary information and formatting it. This generates a clean dataset suitable for analysis.

[0709] Step 3:

[0710] The server generates clean data, inputs it into an AI model, and analyzes customer purchasing trends. The AI ​​model classifies customers into multiple clusters and clarifies the characteristics of each cluster.

[0711] Step 4:

[0712] The server uses an emotion engine to analyze each customer's emotional state. This analyzes text data contained in customer inquiry logs and reviews to recognize emotions such as positive and negative.

[0713] Step 5:

[0714] The terminal generates a user-facing dashboard based on clustering results and sentiment analysis results received from the server. This dashboard visually displays each customer's purchase intent and sentiment tendencies.

[0715] Step 6:

[0716] Users check their device dashboards and consider specific promotional strategies. For example, based on sentiment analysis, they might decide on measures to strengthen customer support for customers who exhibit negative emotions.

[0717] Step 7:

[0718] Users provide feedback to the system via their devices, based on the effectiveness of the implemented measures and new customer reactions. This feedback is stored and analyzed on the server and used to improve the AI ​​model.

[0719] Step 8:

[0720] Based on user feedback, the server readjusts the parameters of the generative AI model and emotion engine, incorporating these adjustments into subsequent analyses. This continuously improves the system's analysis accuracy and the effectiveness of its strategies.

[0721] (Example 2)

[0722] 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".

[0723] Current customer information management systems often propose strategies based only on customer purchasing trends and basic information, making it difficult to consider customer emotions and latent needs. As a result, it is difficult to implement optimal promotions and follow-ups for each customer, leading to challenges in achieving effective customer engagement.

[0724] 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.

[0725] In this invention, the server includes means for collecting and cleansing customer information, means for applying a generative AI model for analyzing the pre-processed customer information, and means for using an emotion engine for recognizing the emotions of the analyzed customers. This enables more sophisticated customer analysis that takes customer emotions into account, and the proposal of effective promotional measures based on that analysis.

[0726] "Customer information" refers to data including customer profiles, purchase history, inquiries, and online behavior history.

[0727] "Data cleansing" is a process that maintains data consistency and quality by removing duplicates, imputing missing data, and correcting outliers in collected data.

[0728] A "generative AI model" is an artificial intelligence algorithm that analyzes customer purchasing trends based on input data and recognizes specific patterns.

[0729] An "emotion engine" is a system that analyzes customer language and behavioral data to recognize positive or negative emotions.

[0730] Clustering is a data analysis technique that groups customers based on their characteristics to extract common preferences and potential needs.

[0731] A "user interface" is a screen display method that visually presents analysis results and makes it easier for users to understand the information.

[0732] "Feedback" refers to opinions and information that users input based on their experience using the system, for the purpose of improvement.

[0733] A "promotional strategy" refers to specific proposals or plans aimed at encouraging customers to purchase products or services.

[0734] This invention aims to build a detailed customer information management system that takes customer emotions into account. The server effectively collects customer information from external sources. This data includes customer profiles, purchase history, inquiries, and online behavior history. The server then cleanses the collected data to ensure consistency and quality. This process generates clean data, ready for further analysis.

[0735] The server inputs clean data into a generating AI model. This AI model analyzes customer purchasing trends within the data, recognizes patterns, and performs clustering. Furthermore, the server utilizes an emotion engine to extract emotions from customer inquiries and behaviors, identifying positive or negative emotions.

[0736] The terminal constructs a visual user interface based on clustering results and sentiment recognition results received from the server. This interface, or dashboard, helps users easily understand customer interests and emotional states, and assists them in making better decisions. The terminal also proposes promotional strategies to users that take customer emotional states into consideration. Specifically, it promotes proactive campaigns for customers with positive emotions and presents follow-up measures for customers with negative feedback.

[0737] Users can use this dashboard to develop and implement customer service strategies. Furthermore, users can provide feedback on their interaction results and experiences to the system. This feedback is stored on the server and used to improve the accuracy of the generative AI models and emotion engine.

[0738] As a concrete example, suppose a server analyzes a customer's purchase history and frequent inquiries and determines that the customer is interested in a particular product but has not yet made a purchase. In this case, the emotion engine analyzes the customer's inquiries and detects any concerns about the product. The terminal provides this information to the user, who can then suggest promotions such as providing additional materials or samples.

[0739] An example of a prompt message is, "Analyze the customer's purchase history and inquiry content, and propose promotional strategies that take their emotional state into consideration." This system enables detailed marketing tailored to each customer's individual needs and emotions.

[0740] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0741] Step 1:

[0742] The server collects customer information from external sources. This data includes customer profile information, purchase history, inquiries, and online behavior history. This data is temporarily stored on the server in preparation for subsequent processing.

[0743] Step 2:

[0744] The server performs data cleansing on the collected data. Specifically, it removes duplicate data, imputes missing data, and corrects outliers. This process generates high-quality clean data. This clean data is used as preparation for analysis using generative AI models.

[0745] Step 3:

[0746] The server inputs clean data into a generating AI model. Based on the input data, the generating AI model analyzes customer purchasing trends and clusters customers using a pattern recognition algorithm. The output results in clusters categorized by customer. These clusters represent customer preferences and potential needs.

[0747] Step 4:

[0748] The server uses an emotion engine to extract emotions from customer inquiries and behavioral history. Text data is provided as input, and natural language processing techniques are used to identify positive or negative emotions. This output is sent to the terminal as the emotion recognition result.

[0749] Step 5:

[0750] The terminal creates a user-facing dashboard based on clustering results and sentiment recognition results received from the server. It receives cluster groups and sentiment recognition results as input, and uses this information to create a graphical visual representation. This dashboard shows customer interests and emotional states, helping users intuitively grasp the information.

[0751] Step 6:

[0752] The device proposes appropriate promotional strategies to the user. It receives information displayed on the dashboard and the customer's emotional state as input, and uses an algorithm to determine promotional priorities. The output includes specific promotional information and follow-up strategies.

[0753] Step 7:

[0754] Users develop customer service strategies using the device's dashboard. They execute promotions and measures based on the entered information and evaluate the results. This evaluation feedback is sent to the server and used to further improve the generative AI model and emotion engine.

[0755] Through this series of steps, the system implements nuanced marketing strategies that take customer emotions into consideration.

[0756] (Application Example 2)

[0757] 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".

[0758] In today's market, sophisticated marketing strategies based on each customer's purchasing behavior and emotions are required. However, traditional systems struggle to optimize promotions while taking customer emotions into account, resulting in a lack of improvement in customer satisfaction.

[0759] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0760] In this invention, the server includes means for collecting and pre-processing customer information, means for applying a generative AI model for analyzing the pre-processed customer information, and means for analyzing customer emotions and proposing benefits related to purchasing behavior based on the analysis results. This makes it possible to optimize promotions according to customer emotions.

[0761] "Customer information" refers to a collection of data that includes customer profile information, purchase history, inquiries, and online behavior history.

[0762] "Preprocessing" is the process of removing noise from collected customer information to generate clean data suitable for analysis.

[0763] A "generative AI model" is an artificial intelligence algorithm that learns specific patterns from data and outputs analysis results.

[0764] "User interface" refers to the screen layout and operating methods used to visually present analysis results to the user.

[0765] "Feedback" refers to opinions and evaluations provided by users based on their interaction experiences, and is used to improve the system.

[0766] "Emotional analysis results" refer to an evaluation of emotions extracted from customer text data and behavioral data.

[0767] "Benefits" refer to discounts or services offered to encourage customer purchasing behavior.

[0768] "Providing information in real time" means presenting promotional information to the user's device immediately based on customer sentiment analysis results and other factors.

[0769] In this invention, the server, terminal, and user work together to operate the system.

[0770] The server collects customer information, performs data cleansing, and inputs the clean data into a generating AI model. The generating AI model performs clustering and sentiment analysis to generate analysis results of customer purchasing trends and sentiment. For these analyses, Pandas is used for data cleansing, Scikit-learn for clustering, and the RoBERTa model for sentiment analysis.

[0771] The device generates a user interface based on analysis results sent from the server and provides users with visual promotional information in real time. The device is responsible for building a dashboard using React Native and presenting the results in a user-friendly format.

[0772] Users review promotional information provided via their devices and select suitable marketing strategies. Furthermore, users send feedback based on their experiences from their devices to the server, contributing to improving the accuracy of the generated AI model.

[0773] As a concrete example, if a user adds the same product to their cart multiple times but does not make a purchase, the device will use sentiment analysis results received from the server to suggest a "trial campaign with a satisfaction guarantee." This can alleviate the user's concerns and encourage them to make a purchase.

[0774] Examples of prompt messages in this system are as follows:

[0775] "The user's purchase history is as follows:... Analyze the user's sentiment from this data and propose appropriate promotions."

[0776] Through this invention, it becomes possible to implement detailed marketing strategies based on customer emotions, thereby achieving a more effective customer approach.

[0777] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0778] Step 1:

[0779] The server collects customer information from external databases and existing information systems. Inputs include customer profile information, purchase history, inquiries, and online behavior history. The collected data undergoes data cleansing to remove noise, generating clean data. This results in a dataset suitable for analysis.

[0780] Step 2:

[0781] The server applies a generative AI model based on clean data to cluster customer purchasing trends. This step uses machine learning libraries such as Scikit-learn to classify the data into clusters. The input is the cleaned dataset, and the output is the clustered result showing customer purchasing trends.

[0782] Step 3:

[0783] The server uses text data to analyze customer sentiment using the RoBERTa model. It takes customer inquiries and review comments as input and outputs sentiment scores. This allows the server to understand each customer's current emotional state.

[0784] Step 4:

[0785] The server generates highly personalized promotional strategies for customers based on clustering results and sentiment analysis results. The input is the output from steps 2 and 3, and the output is personalized promotional information.

[0786] Step 5:

[0787] The terminal receives promotional information sent from the server and presents it to the user in real time through the user interface. The input is promotional information from the server, and the output is visually displayed campaign and special offer information.

[0788] Step 6:

[0789] Users review promotional information displayed on their devices and make choices based on their purchasing behavior. They also provide feedback to the server via their devices. The input is the user's actions, and the output is feedback data that is generated and sent to the server.

[0790] Step 7:

[0791] The server collects feedback data from users and adds it to the training dataset of the generative AI model. This improves the accuracy of the generative AI model, making it possible to derive more accurate analysis results.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0800] 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."

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] The following is further disclosed regarding the embodiments described above.

[0814] (Claim 1)

[0815] A means for collecting and pre-processing customer information,

[0816] A means for applying a generative AI model to analyze pre-processed customer information,

[0817] A means for generating a user interface to provide analysis results to the user,

[0818] A means of collecting user feedback and improving the generated AI model,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, comprising an algorithm for clustering customer purchasing trends.

[0822] (Claim 3)

[0823] The system according to claim 1, comprising means for generating insights for promotional measures tailored to customers.

[0824] "Example 1"

[0825] (Claim 1)

[0826] A means for collecting and pre-processing information,

[0827] A means for applying a generative AI model to analyze the information after preprocessing,

[0828] Means for generating an interface for providing analysis results,

[0829] A means of collecting user feedback and improving the generated AI model,

[0830] A means of making suggestions based on analyzed attribute information and trend information,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, comprising a method for classifying information trends.

[0834] (Claim 3)

[0835] The system according to claim 1, comprising means for generating insights for appropriate measures.

[0836] "Application Example 1"

[0837] (Claim 1)

[0838] A means for collecting customer information and processing the information,

[0839] A means of applying generative AI technology to analyze information after formatting,

[0840] A means for generating a display screen to provide the user with the analysis results,

[0841] A means to improve AI technology that collects and generates user feedback,

[0842] A means of automatically providing personalized product suggestions based on the user's purchase and browsing history,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, comprising an algorithm for classifying customer purchasing trends into specific groups.

[0846] (Claim 3)

[0847] The system according to claim 1, comprising means for generating insights into sales promotion measures suitable for customers and providing personalized campaign information.

[0848] "Example 2 of combining an emotion engine"

[0849] (Claim 1)

[0850] Means for collecting and cleansing customer information,

[0851] A means for applying a generative AI model to analyze pre-processed customer information,

[0852] A means of using an emotion engine to recognize the emotions of analyzed customers,

[0853] A method for clustering customer preferences and potential needs based on the analysis results,

[0854] A means for generating a user interface that visually presents the results to the user,

[0855] A means of proposing promotional strategies to users,

[0856] A means of collecting user feedback to improve the generated AI model and emotion engine,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, comprising means for adjusting promotional measures based on the emotional state of the customer.

[0860] (Claim 3)

[0861] The system according to claim 1, comprising means for creating a user dashboard and displaying customer interests and sentiments.

[0862] "Application example 2 when combining with an emotional engine"

[0863] (Claim 1)

[0864] A means for collecting and pre-processing customer information,

[0865] A means for applying a generative AI model to analyze pre-processed customer information,

[0866] A means for generating a user interface to provide analysis results to the user,

[0867] A means of collecting user feedback and improving the generated AI model,

[0868] A means of analyzing customer emotions and proposing benefits related to purchasing behavior based on the analysis results,

[0869] A means of providing promotional information to users' devices in real time,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, comprising an algorithm that clusters customer purchasing trends and enables personalized marketing measures based on sentiment analysis results.

[0873] (Claim 3)

[0874] The system according to claim 1, comprising means for generating insights for promotional measures suitable for customers and adjusting promotional materials based on sentiment analysis. [Explanation of symbols]

[0875] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting and pre-processing customer information, A means for applying a generative AI model to analyze pre-processed customer information, A means for generating a user interface to provide analysis results to the user, A means of collecting user feedback and improving the generated AI model, A system that includes this.

2. The system according to claim 1, comprising an algorithm for clustering customer purchasing trends.

3. The system according to claim 1, comprising means for generating insights for promotional measures suitable for customers.

Images