Marketing Data Analysis Method and System

Abstract

An embodiment of the present invention provides a marketing data analysis method and system, belonging to the technical field of data processing. A data acquisition module, a data analysis module, and a user classification module are provided in the system. Among them, the data acquisition module is used to collect marketing data from real-time data sources, preprocess the marketing data, and store the preprocessed marketing data in a database. The data analysis module is used to obtain marketing data from the database, analyze and identify the authenticity of the marketing data according to a preset recognition model, and determine whether there is false marketing behavior of the merchant corresponding to the marketing data according to the recognition result. The user classification module is used to obtain marketing data from the database, classify users according to a preset classification model to obtain a classification result, and determine a push strategy for different categories of users based on the set push strategy and the classification result. Thus, a large amount of marketing data can be processed more quickly and effectively, and accurate classification of users can be achieved.

Description

Technical Field

[0001] The embodiments of the present invention relate to data processing technologies, and particularly to a marketing data analysis method and system. Background Art

[0002] With the rapid development of big data technologies, enterprises increasingly rely on data analysis systems to guide market decisions and enhance competitiveness. Currently, there are already various marketing data analysis systems based on big data on the market, and these systems generally include a data collection module, a database, a data analysis module, an intelligent screening module, and a data usage module.

[0003] For example, in some existing technical solutions, a marketing data analysis system based on big data can collect review data of all merchants in the network through the data collection module, and analyze the data through subsequent modules to screen for false marketing behaviors and identify user needs.

[0004] However, in practical applications, such systems usually suffer from insufficient data classification, resulting in the system being unable to effectively utilize these data for in-depth analysis, thus affecting the formulation of marketing strategies. Additionally, the slow data collection speed leads to poor real-time performance of the data, and the system has weak defense capabilities against network attacks, thus affecting the effectiveness and security of data processing.

[0005] Therefore, it is necessary to propose an improved solution for these problems, which can more effectively process massive data, improve classification accuracy, and enhance data security and collection efficiency. Summary of the Invention

[0006] The embodiments of the present invention provide a marketing data analysis method and system for more quickly and effectively processing massive marketing data and achieving precise classification of users.

[0007] In a first aspect, the embodiments of the present invention provide a marketing data analysis system, including:

[0008] A data collection module, configured to collect marketing data from real-time data sources, preprocess the marketing data, and store the preprocessed marketing data in a database;

[0009] A data analysis module, configured to obtain marketing data from the database, and analyze and identify the authenticity of the marketing data according to a preset recognition model, so as to determine whether there is a false marketing behavior of the merchant corresponding to the marketing data based on the recognition result of the authenticity of the marketing data;

[0010] A user classification module, configured to obtain marketing data from the database, classify users according to a preset classification model to obtain a classification result, and determine a push strategy for different categories of users based on a set push strategy and the classification result.

[0011] In the above solution, marketing data is collected from real-time data sources through a data collection module to achieve efficient collection of marketing data. After the marketing data is collected, it is preprocessed in parallel asynchronously, which can boost the processing speed of the marketing data. Then, the data analysis module can obtain the preprocessed marketing data from the database and analyze and identify the authenticity of the marketing data according to a preset recognition model, so as to determine whether the merchant corresponding to the marketing data has false marketing behavior based on the recognition result of the authenticity of the marketing data. When it is determined that the merchant corresponding to the marketing data has false marketing behavior, the merchant can be marked to reduce the recommendation frequency for the merchant. At the same time, the user classification module can classify users according to the marketing data obtained from the database using a preset classification model to obtain accurate user categories, so as to achieve precise push for different categories of users according to the classification result and the set push strategy.

[0012] In a possible design of the first aspect, the data collection module includes:

[0013] A real-time data collection unit for collecting marketing data from the server corresponding to the real-time data source, and the real-time data source at least includes social media, e-commerce platforms, and real-time log streams;

[0014] An asynchronous data processing unit for asynchronously preprocessing the marketing data collected by the real-time data collection unit and storing the preprocessed marketing data in the database.

[0015] In the above solution, by collecting marketing data from the server corresponding to the real-time data source through the real-time data collection unit, marketing data reflecting the latest market dynamics and consumer behavior can be obtained; by parallel processing of the collected marketing data through the asynchronous data processing unit, the data processing speed can be improved.

[0016] In a possible design of the first aspect, the real-time data collection unit is specifically used for: subscribing to the marketing data of social media, the marketing data of e-commerce platforms, and the marketing data of real-time log streams from the Kafka server; looping through the messages received from the Kafka server, extracting marketing data from the messages; and sending the extracted marketing data to the asynchronous data processing unit for processing.

[0017] In the above solution, considering that the Kafka server, as a distributed stream processing platform, has characteristics such as high performance, durability, distributed structure, publish-subscribe model, fault tolerance, and horizontal scalability. Therefore, in the embodiment of the present invention, when collecting marketing data from the real-time data source, by subscribing to the marketing data of each real-time data source from the Kafka server, the timeliness and diversity of the collected marketing data can be ensured, so as to achieve more accurate user classification and false behavior determination.

[0018] In a possible design of the first aspect, the asynchronous data processing unit is specifically configured to: receive the marketing data from the real-time data acquisition unit, perform data cleaning processing and data format conversion processing on the marketing data through an asynchronous task function, and store the processed marketing data in a database through a data saving function; wherein, the data cleaning processing and data format conversion processing belong to preprocessing.

[0019] In the above solution, a method for processing marketing data through an asynchronous data processing unit is provided, which can process marketing data in parallel during the data acquisition process and improve the data processing speed.

[0020] In a possible design of the first aspect, the data analysis module analyzes and identifies the authenticity of the marketing data according to a preset recognition model, including:

[0021] Extract the text features and numerical features of the marketing data through the preset recognition model;

[0022] Calculate the term frequency-inverse document frequency TF-IDF value and sentiment score corresponding to the text features through the preset recognition model, calculate the text length of the marketing data according to the numerical features and extract the timestamp feature, and encode the product category and user level in the marketing data to obtain the category feature;

[0023] Obtain a feature matrix according to the text features, numerical features, and category features;

[0024] Based on the feature matrix, TF-IDF value, and sentiment score, obtain the recognition result of the authenticity of the marketing data.

[0025] In the above solution, by extracting the features of the marketing data, calculating the TF-IDF value and sentiment score, the recognition result of the authenticity of the marketing data is obtained, so that it is convenient for the system to determine whether the merchant corresponding to the marketing data has false marketing behavior based on the recognition result, and thus screen out the merchants with false marketing behavior.

[0026] In a possible design of the first aspect, the user classification module obtains the marketing data from the database and classifies the users according to a preset classification model to obtain classification results, including:

[0027] Extract the user purchase record feature data from the marketing data; the user purchase record feature data includes user marking features, purchase frequency features, purchase amount features, and geographical location features;

[0028] Perform standardization processing on the user purchase record feature data to obtain the user data to be classified;

[0029] Cluster and classify the user data to be classified through a preset classification model to obtain a classification result.

[0030] In the above solution, the user classification module can extract the user purchase record feature data from the marketing data and obtain the classification result about the user according to the user purchase record feature data, realizing the multi-dimensional classification of the user, which helps to understand the user group more carefully, so as to achieve more accurate push.

[0031] In a possible design of the first aspect, the user classification module standardizes the user purchase record feature data to obtain the user data to be classified, including:

[0032] Through the formula Standardize the user purchase record feature data to obtain the user data to be classified;

[0033] Among them, z represents the user data to be classified, x represents the user purchase record feature data, μ represents the mean value of each feature in the user purchase record feature data, and σ represents the standard deviation of each feature in the user purchase record feature data.

[0034] In the above solution, by standardizing the user purchase record feature data, the numerical ranges and scales between different features can be made more consistent, thus avoiding the influence of some features with larger numerical ranges on the reliability of the preset classification model.

[0035] In a possible design of the first aspect, the system further includes: a data security module, which is used to send an alarm message when a network attack behavior is identified and record the network attack log for security auditing.

[0036] In the above solution, the data security module is used to protect data security, and can send an alarm message when a network attack behavior is identified and record the network attack log, such as information about the time, type, source, etc. of the network attack, which is convenient for relevant staff to take necessary measures in time to find potential security vulnerabilities.

[0037] In a possible design of the first aspect, the data security module is specifically used for: according to the set listening address and port, start a monitoring thread to monitor the data of the network port corresponding to the listening address and port, and obtain the listening data;

[0038] When it is determined that a preset network attack behavior has occurred according to the listening data, send an alarm message, record the network attack log, and send an interrupt signal to disconnect the network connection.

[0039] In the above solution, the data security module starts a monitoring thread to monitor the set listening address and port to obtain monitoring data, so as to be able to judge whether a preset network attack behavior occurs based on the monitoring data, and disconnect the network connection in time through an interrupt signal when it is judged that a preset network attack behavior occurs, preventing the spread of the attack.

[0040] In a second aspect, an embodiment of the present invention provides a marketing data analysis method, which is applied to the marketing data analysis system in any one of the first aspects of the embodiments of the present invention. The method includes:

[0041] The data collection module in the marketing data analysis system collects marketing data from real-time data sources;

[0042] The data collection module preprocesses the marketing data and stores the preprocessed marketing data in a database;

[0043] The data analysis module in the marketing data analysis system obtains marketing data from the database and analyzes and identifies the authenticity of the marketing data according to a preset identification model, so as to determine whether there is false marketing behavior of the merchant corresponding to the marketing data according to the identification result of the authenticity of the marketing data;

[0044] The user classification module in the marketing data analysis system obtains marketing data from the database, classifies users according to a preset classification model to obtain a classification result, and determines a push strategy for different categories of users based on the set push strategy and the classification result.

[0045] In the above solution, the data collection module collects marketing data from real-time data sources, preprocesses the marketing data, and stores the preprocessed marketing data in a database. The data analysis module obtains marketing data from the database and analyzes and identifies the authenticity of the marketing data according to a preset identification model, so as to determine whether there is false marketing behavior of the merchant corresponding to the marketing data according to the identification result. The user classification module obtains marketing data from the database, classifies users according to a preset classification model to obtain a classification result, and determines a push strategy for different categories of users based on the set push strategy and the classification result. Thus, a large amount of marketing data can be processed more quickly and effectively, and accurate classification of users can be achieved.

[0046] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0047] A processor; and,

[0048] A memory for storing executable instructions of the processor;

[0049] Wherein, the processor is configured to execute the method in the second aspect by executing the executable instructions.

[0050] Fourthly, an embodiment of the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method in the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the embodiments of the present invention, and are used together with the specification to explain the principles of the embodiments of the present invention.

[0052] Figure 1 The structure diagram of a marketing data analysis system provided by an embodiment of the present invention is shown;

[0053] Figure 2 The structure diagram of another marketing data analysis system provided by an embodiment of the present invention is shown;

[0054] Figure 3 The structure diagram of yet another marketing data analysis system provided by an embodiment of the present invention is shown;

[0055] Figure 4 The flowchart of a marketing data analysis method provided by an embodiment of the present invention is shown;

[0056] Figure 5 It is the structure diagram of an electronic device shown according to an exemplary embodiment of an embodiment of the present invention.

[0057] Through the above-mentioned accompanying drawings, the embodiments clearly defined by the embodiments of the present invention have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the embodiments of the present invention in any way, but to illustrate the concept of the embodiments of the present invention to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the embodiments of the present invention as detailed in the appended claims.

[0059] Marketing data analysis is a method used by enterprises to evaluate the effectiveness of their marketing strategies and activities. In marketing data analysis, marketing data generally refers to various data related to market promotion, advertising, sales, and customer interaction. These data may include, but are not limited to:

[0060] Sales data (including sales volume, sales quantity, and sales channels, etc.); user data (including user demographic information, purchase history, user satisfaction, etc.); market data (including market size, market share, competitor analysis, etc.); advertising data (including advertising expenditure, click-through rate, conversion rate, and advertising channels, etc.); social media data (including interactions on social media, fan growth, and brand mentions, etc.); website data (including traffic, user behavior, page views, and bounce rate, etc.); user feedback (including user opinions collected through surveys, reviews, or feedback forms); promotion data (including participation in promotions, promotion effectiveness, etc.); product data (including product life cycle, product portfolio, and product features, etc.); pricing data (including sales performance at different price points, price sensitivity, etc.).

[0061] By analyzing these data, enterprises can better understand market trends, consumer behavior, and the effectiveness of marketing activities, so as to optimize marketing strategies and improve return on investment.

[0062] With the rapid development of big data technology, enterprises are increasingly relying on marketing data analysis systems to guide market decisions and enhance competitiveness. To meet this demand, various big data-based marketing data analysis systems have emerged in the market. These marketing data analysis systems generally include data collection modules, databases, data analysis modules, intelligent screening modules, and data usage modules. Although these systems have improved the data processing capabilities and decision-making efficiency of enterprises to a certain extent, there are still some challenges in practical applications, such as insufficient data classification, slow data collection speed, and weak data security protection.

[0063] Specifically, existing marketing data analysis systems often only focus on data classification in a single dimension, such as classifying only based on users' purchase records, while ignoring other important user attributes and behavior characteristics. This results in the inability of marketing data analysis systems to effectively utilize these data for in-depth analysis, thus affecting the formulation of marketing strategies.

[0064] In addition, due to the large volume and scattered data sources of marketing data, the data collection methods used in traditional marketing data analysis systems often make it difficult to collect real-time data, which makes the real-time nature of the collected marketing data poor and reduces the response speed and flexibility of marketing data analysis systems.

[0065] For another example, with the continuous evolution of cyberattack methods, there are many vulnerabilities in the data security protection of existing marketing data analysis systems. This not only may lead to the leakage of marketing data and related analysis result data, but also may affect the effectiveness and security of marketing data processing.

[0066] Therefore, to solve the above problems, it is necessary to propose an improved marketing data analysis system to more effectively process massive marketing data, improve the accuracy of user classification, and enhance data security and collection efficiency.

[0067] The embodiments of the present invention aim to solve the problems of insufficient data classification, slow data collection speed, and weak data security protection in the existing marketing data analysis system.

[0068] Specifically, the concept of the embodiments of the present invention is centered around the following core points:

[0069] Improve the collection efficiency of marketing data: Use real-time data stream collection technology to achieve real-time data collection to ensure the timeliness and integrity of marketing data, and use a parallel processing framework to improve the speed and efficiency of marketing data processing.

[0070] Implement multi-dimensional user classification: When classifying users, in addition to considering purchase records, user attributes such as age, gender, geographical location, hobbies, purchase frequency, and purchase amount are also considered to understand users more comprehensively. At the same time, by analyzing behavioral data such as browsing records, search history, and click-through rate of users, the preferences and behavioral patterns of users are identified; in addition, sentiment analysis of user comments can also be performed through natural language processing technology to understand the satisfaction and reasons for dissatisfaction of users, thereby achieving multi-dimensional classification of users, which helps to understand the user group more carefully and then achieve more accurate push.

[0071] Enhance data security: By setting up a data security module to start a monitoring thread to monitor the set listening address and port to obtain monitoring data, so as to be able to judge whether a preset network attack behavior occurs based on the monitoring data, and when it is judged that a preset network attack behavior occurs, the network connection is disconnected in time through an interrupt signal to prevent the attack from spreading.

[0072] In summary, the concept of the embodiments of the present invention aims to improve the user classification accuracy, the collection efficiency of marketing data, and enhance data security. The marketing data is collected from real-time data sources through the data collection module to achieve efficient collection of marketing data. After the marketing data is collected, the marketing data is preprocessed in parallel asynchronously, which can boost the processing speed of the marketing data. Then, the data analysis module can obtain the preprocessed marketing data from the database and analyze and identify the authenticity of the marketing data according to a preset recognition model, so as to determine whether the merchant corresponding to the marketing data has false marketing behavior based on the recognition result of the authenticity of the marketing data. When it is determined that the merchant corresponding to the marketing data has false marketing behavior, the merchant can be marked to reduce the recommendation frequency for this merchant. At the same time, the user classification module can classify users according to the marketing data obtained from the database using a preset classification model to obtain accurate user categories, so as to achieve precise push for different categories of users according to the classification results and the set push strategy.

[0073] The marketing data analysis method and system provided by the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0074] Figure 1 The structural schematic diagram of a marketing data analysis system provided by the embodiments of the present invention is shown. As Figure 1 shown, the marketing data analysis system 100 provided by the embodiments of the present invention may include: a data collection module 110, a data analysis module 120, and a user classification module 130.

[0075] Specifically, the data collection module 110 is used to collect marketing data from real-time data sources, preprocess the marketing data, and store the preprocessed marketing data in the database.

[0076] The data analysis module 120 is used to obtain marketing data from the database and analyze and identify the authenticity of the marketing data according to a preset recognition model, so as to determine whether the merchant corresponding to the marketing data has false marketing behavior based on the recognition result of the authenticity of the marketing data.

[0077] The user classification module 130 is used to obtain marketing data from the database, classify users according to a preset classification model to obtain classification results, and determine the push strategies for different categories of users based on the set push strategy and the classification results.

[0078] Among them, the preprocessing of marketing data may include data cleaning processing and data format conversion processing. The data cleaning processing is to remove the noise data in the marketing data, and the data format conversion processing can standardize and normalize the marketing data to improve the accuracy of subsequent processing.

[0079] After the data acquisition module 110 preprocesses the marketing data, it stores the preprocessed marketing data in a database. In one implementation, the database can be a database implemented based on a distributed storage architecture, and the distributed storage structure can be implemented based on data compression and indexing technologies to optimize the storage space and accelerate data retrieval, achieving high-speed storage and retrieval of marketing data. In practical applications, the implementation method of the database can be determined according to actual usage requirements, and this embodiment does not make specific limitations on this.

[0080] The preset recognition model used by the data analysis module 120 is trained based on the training sample marketing data and the corresponding user behaviors of the training sample marketing data, and can analyze and identify the authenticity of the marketing data to obtain an identification result regarding authenticity. For example, if the marketing data is identified as false data, it indicates that there is false marketing behavior by the merchant or user corresponding to the marketing data. If the marketing data is identified as true data, it indicates that there is no false marketing behavior by the merchant or user corresponding to the marketing data.

[0081] In a possible implementation, the identification result regarding the authenticity of the marketing data can be a authenticity value. If the authenticity value of the marketing data is greater than the authenticity threshold, it indicates that there is no false marketing behavior by the merchant or user corresponding to the marketing data; if the authenticity value of the marketing data is less than or equal to the authenticity threshold, it indicates that there is false marketing behavior by the merchant or user corresponding to the marketing data.

[0082] Exemplarily, assume that the authenticity threshold is 60, the authenticity value in the authenticity identification result of marketing data A is 50, and the authenticity value in the authenticity identification result of marketing data B is 90. Since the authenticity value 50 of marketing data A is less than the authenticity threshold 60, it is determined that there is false marketing behavior by the merchant or user corresponding to marketing data A. Since the authenticity value 90 of marketing data B is greater than the authenticity threshold 60, it is determined that there is no false marketing behavior by the merchant or user corresponding to marketing data B.

[0083] The preset classification model used by the user classification module 130 is pre-trained by clustering the training sample user purchase record feature data. In actual use, after the user classification module 130 obtains the marketing data, it can input the user purchase record feature data in the marketing data into the preset classification model to obtain the corresponding classification result. Then, according to the classification result and the set push strategy, the push strategy for different categories of users can be determined, thereby realizing personalized recommendations for different categories of users.

[0084] It should be noted that the preset classification model can achieve multi-dimensional classification of users to more accurately understand the preferences and behavior patterns of users, and thus provide more personalized services.

[0085] Exemplarily, the dimensions for classifying users may include: classification based on purchase behavior, classification based on user attributes, classification based on user interaction, classification based on user feedback, and classification based on time series.

[0086] In the classification based on purchase behavior, users can be classified from two dimensions: purchase frequency and purchase amount.

[0087] When classifying by purchase frequency, users can be divided into high-frequency users, medium-frequency users, and low-frequency users. Among them, high-frequency users can refer to users who purchase at least once a week, medium-frequency users can refer to users who purchase 1 - 3 times a month, and low-frequency users can refer to users who purchase once a quarter or less.

[0088] When classifying by purchase amount, users can be divided into high-spending users, medium-spending users, and low-spending users. Among them, high-spending users can refer to users whose purchase amount per time exceeds 500 yuan, medium-spending users can refer to users whose purchase amount per time is between 100 yuan and 500 yuan, and low-spending users can refer to users whose purchase amount per time is less than 100 yuan.

[0089] In the classification based on user attributes, users can be classified from two dimensions: user age and user geographical location.

[0090] When classifying by user age, users can be divided into adolescent users, young users, middle-aged users, and elderly users. Among them, adolescent users refer to users aged 13 to 18, young users refer to users aged 19 to 35, middle-aged users refer to users aged 36 to 60, and elderly users refer to users over 60 years old.

[0091] When classifying by user geographical location, users can be divided into users in first-tier cities, second-tier cities, third-tier cities, and rural areas.

[0092] In the classification based on user interaction, users can be classified according to their activity level on the website. For example, users can be divided into active users, moderately active users, and inactive users. Among them, active users refer to users who log in to the website every day and browse multiple pages, moderately active users refer to users who log in to the website 2 - 3 times a week, and inactive users refer to users who log in to the website once a month or less.

[0093] In the classification based on user feedback, users can be classified according to their evaluations of the product. For example, users can be divided into highly satisfied users, moderately satisfied users, and lowly satisfied users. Among them, highly satisfied users refer to those with an average rating of 4 stars or above, moderately satisfied users refer to those with an average rating of 3 - 4 stars, and lowly satisfied users refer to those with an average rating below 3 stars.

[0094] In the classification based on time series, classification is carried out according to the periodicity of users' product purchases. For example, users can be divided into regular purchase users, occasional purchase users, and very occasional purchase users. Among them, regular purchase users refer to those who purchase on a fixed date every month, occasional purchase users refer to those who purchase once a quarter, and very occasional purchase users refer to those who purchase once a year or less.

[0095] It can be understood that the above descriptions of different dimensions of user classification are only examples. In actual applications, the dimensions of user classification can be set according to different requirements, and specific limitations are not made here.

[0096] After obtaining the user classification results, the user classification module 130 can determine the push strategies for different categories of users based on the set push strategies and classification results. For example, launch a membership program for high-frequency users and send promotional information to low-frequency users. In this way, not only can the user satisfaction be increased, but also the user conversion rate and repurchase rate can be improved.

[0097] In this embodiment, the data collection module 110 collects marketing data from real-time data sources to achieve efficient collection of marketing data. After collecting the marketing data, the marketing data is preprocessed in parallel asynchronously, which can boost the processing speed of the marketing data. Then, the data analysis module 120 can obtain the preprocessed marketing data from the database and analyze and identify the authenticity of the marketing data according to a preset recognition model, so as to determine whether the merchant corresponding to the marketing data has false marketing behavior based on the recognition result of the authenticity of the marketing data. When it is determined that the merchant corresponding to the marketing data has false marketing behavior, the merchant can be marked to reduce the recommendation frequency for this merchant. At the same time, the user classification module 130 can classify users according to the marketing data obtained from the database using a preset classification model to obtain accurate user categories, so as to achieve precise push for different categories of users according to the classification results and the set push strategies.

[0098] In a possible implementation manner, as Figure 2 shown, the data collection module 110 may include a real-time data collection unit 1101 and an asynchronous data processing unit 1102.

[0099] Specifically, the real-time data collection unit 1101 is used to collect marketing data from the servers corresponding to real-time data sources. The real-time data sources at least include social media, e-commerce platforms, and real-time log streams, so as to obtain marketing data reflecting the latest market dynamics and consumer behaviors. The asynchronous data processing unit 1102 is used to asynchronously preprocess the marketing data collected by the real-time data collection unit 1101 and store the preprocessed marketing data in the database, thereby improving the data processing speed by parallel processing of the marketing data.

[0100] Considering that the Kafka server, as a distributed stream processing platform, has characteristics such as high performance, durability, distributed structure, publish-subscribe model, fault tolerance, and horizontal scalability, in this embodiment, the server corresponding to the real-time data source can be a Kafka server. Specifically, the real-time data collection unit 1101 can subscribe to the marketing data of social media, the marketing data of e-commerce platforms, and the marketing data of real-time log streams from the Kafka server; traverse the messages received from the Kafka server in a loop, extract the marketing data from the messages; and send the extracted marketing data to the asynchronous data processing unit 1102 for processing.

[0101] Specifically, the real-time data collection unit 1101 can subscribe to the marketing data of the required real-time data sources according to the specified address and port of the Kafka server. For example, the marketing data of social media, the marketing data of e-commerce platforms, and the marketing data of real-time log streams. The Kafka server will publish the marketing data of social media, the marketing data of e-commerce platforms, and the marketing data of real-time log streams. The real-time data collection unit 1101 receives the subscribed messages, and the messages may include the marketing data of social media, the marketing data of e-commerce platforms, or the marketing data of real-time log streams. The real-time data collection unit 1101 extracts the marketing data from the messages, and then sends the extracted marketing data to the asynchronous data processing unit 1102.

[0102] The asynchronous data processing unit 1102 receives the marketing data of the real-time data collection unit 1101, performs data cleaning processing and data format conversion processing on the marketing data through an asynchronous task function, and stores the processed marketing data in the database through a data saving function; among them, the data cleaning processing and the data format conversion processing belong to preprocessing.

[0103] In this way, by subscribing to the marketing data of each real-time data source from the Kafka server, the timeliness and diversity of the collected marketing data can be guaranteed, so as to achieve more accurate user classification and false behavior determination. And it is possible to parallel process the marketing data during the data collection process to improve the data processing speed.

[0104] In a possible implementation, when analyzing and identifying the authenticity of marketing data according to a preset recognition model, the data analysis module 120 in the above embodiment can extract the text features and numerical features of the marketing data through the preset recognition model; calculate the term frequency-inverse document frequency (TF-IDF) value and sentiment score corresponding to the text features through the preset recognition model, calculate the text length of the marketing data according to the numerical features and extract the timestamp feature, and encode the product category and user level in the marketing data to obtain the category feature; obtain the feature matrix according to the text features, numerical features, and category features; and obtain the recognition result of the authenticity of the marketing data based on the feature matrix, TF-IDF value, and sentiment score.

[0105] Suppose the currently analyzed and identified marketing data is the user comment data of an e-commerce platform. After obtaining the user comment data, the data analysis module 120 extracts the text features and numerical features of the user comment data through a preset recognition model, and calculates the TF-IDF value corresponding to the text features to obtain the frequency of each word appearing in the comment, and uses a sentiment analysis tool to calculate the sentiment score corresponding to the text features of the user comment data. At the same time, according to the numerical features of the user comment data, calculate the text length of the user comment data, that is, the number of words or characters, and extract the timestamp feature, which can be further converted into the hour of the day, day of the week, etc. And encode the product category of the product involved in the user comment data and the user level of the user who sent the user comment data on the e-commerce platform to obtain the category feature. Then, obtain the feature matrix according to the text features, numerical features, and category features, and thus obtain the recognition result of the authenticity of the user comment data based on the feature matrix, TF-IDF value, and sentiment score.

[0106] In the technical solution of this embodiment, by extracting the features of the marketing data, calculating the TF-IDF value and the sentiment score, the recognition result of the authenticity of the marketing data is obtained, so that it is convenient for the system to determine whether there is false marketing behavior of the merchant corresponding to the marketing data based on the recognition result, and then screen out the merchants with false marketing behavior.

[0107] In a possible implementation, the user classification module 130 obtains marketing data from the database and classifies users according to a preset classification model. The classification result includes: extracting user purchase record feature data from the marketing data; the user purchase record feature data includes user label features, purchase frequency features, purchase amount features, and geographical location features. Standardize the user purchase record feature data to obtain the user data to be classified. Perform clustering classification on the user data to be classified through a preset classification model to obtain the classification result.

[0108] In practical applications, after the user classification module 130 obtains marketing data from the database, it can first perform data cleaning and sorting on the obtained marketing data to remove outliers and missing values in the marketing data. Then, extract the purchase record feature data of users from the marketing data that has been cleaned and sorted, including user marking features (such as the user's account name or account ID), purchase frequency features, purchase amount features, and geographical location features, etc.

[0109] After obtaining the purchase record feature data of users, perform feature scaling on the purchase record feature data to achieve standardization processing of the purchase record feature data and obtain the user data to be classified. Among them, the standardization processing of the user purchase record feature data can be achieved through a formula, that is, through the formula Perform standardization processing on the user purchase record feature data to obtain the user data to be classified. Among them, z represents the user data to be classified, x represents the user purchase record feature data, μ represents the mean value of each feature in the user purchase record feature data, that is, the mean value of the user marking feature, purchase frequency feature, purchase amount feature, and geographical location feature, and σ represents the standard deviation of each feature in the user purchase record feature data, that is, the standard deviation of the user marking feature, purchase frequency feature, purchase amount feature, and geographical location feature.

[0110] After that, the user classification module 130 performs clustering classification on the user data to be classified through a preset classification model. The preset classification model can be pre-trained based on a clustering algorithm or a classification algorithm. Among them, the clustering algorithm can be, for example, the K-means clustering algorithm or the hierarchical clustering algorithm, and the classification algorithm can be, for example, the decision tree algorithm or the random forest algorithm. After obtaining the classification result of the user, the personalized marketing strategy of the user can be determined according to the classification result and the set push strategy.

[0111] It can be understood that by performing standardization processing on the user purchase record feature data, the numerical ranges and scales between different features become more consistent, thereby avoiding the influence of some features with larger numerical ranges on the reliability of the preset classification model.

[0112] Taking the classification of users according to the purchase record feature data of users using the K-means clustering algorithm as an example, the user classification module 130 obtains marketing data and performs data preprocessing on the marketing data, that is, data cleaning and sorting, and deletes outliers and missing values in the marketing data. After that, perform feature extraction on the preprocessed marketing data and extract the purchase record feature data in the marketing data, including user age features, purchase frequency features, purchase amount features, and geographical location features.

[0113] After that, calculate the mean values of the user age feature, purchase frequency feature, purchase amount feature, and geographical location feature, as well as the standard deviations of the user age feature, purchase frequency feature, purchase amount feature, and geographical location feature. Then, according to the formula perform standardization processing on the user purchase record feature data to obtain the data of the user to be classified.

[0114] Suppose the eigenvalue of the user purchase record feature data is as follows:

[0115] Purchase frequency Purchase amount User age Geographical location 1 50 25 0 2 100 30 1 3 150 35 2 4 200 40 3

[0116] After standardization processing, the obtained eigenvalues may be as shown in the following table:

[0117] Purchase frequency Purchase amount User age Geographical location -0.5 -1.0 -1.0 -1.0 0.0 0.0 0.0 0.0 0.5 1.0 1.0 1.0 1.0 2.0 2.0 2.0

[0118] In this example, each eigenvalue is scaled to a range with a mean of 0 and a standard deviation of 1, making the numerical ranges and scales between different features more consistent.

[0119] Input the data to be classified into the preset classification model, and output the features of each cluster center as the classification result. A cluster center represents users of a category. Thus, multi-dimensional classification of users is achieved.

[0120] In the above solution, the user classification module 130 can extract the user purchase record feature data from the marketing data, and obtain the classification result about the user according to the user purchase record feature data, realizing multi-dimensional classification of users, which helps to understand the user group more carefully, so as to achieve more accurate push.

[0121] Figure 3 shows a schematic structural diagram of another marketing data analysis system according to an embodiment of the present invention. As Figure 3 shown, on the basis of the above embodiment, in order to protect the marketing data analysis system 100 from the risks of network attacks and data leakage, the marketing data analysis system 100 provided in this embodiment may further include a data security module 140, which is used to send an alarm message when identifying a network attack behavior and record the network attack log for security auditing.

[0122] In practical applications, the data security module 140 can achieve comprehensive protection of the marketing data analysis system 100 through aspects such as encryption technology, intrusion detection, firewall and access control, security auditing and monitoring, backup and recovery strategies, as well as user education and training.

[0123] Exemplarily, encryption technologies can include data encryption and transmission encryption. Among them, data encryption can use encryption algorithms to encrypt sensitive data to ensure that the data cannot be easily decrypted even if intercepted. Transmission encryption can use methods such as the HTTPS protocol to protect the security of marketing data during transmission.

[0124] Intrusion detection can achieve real-time monitoring of network traffic and identify abnormal traffic patterns. It can also analyze system logs to detect unauthorized access attempts and other potential security threats. Behavioral analysis can also be performed to detect and identify abnormal behavior patterns by learning normal behavior patterns to prompt potential attack behaviors.

[0125] Firewalls and access controls can configure network firewalls for the system to block traffic from known malicious IP addresses, protect web applications from attacks through application firewalls, and at the same time, restrict access to sensitive data resources through authentication and authorization.

[0126] Security audits and monitoring can regularly conduct security audits on the system, check the security of the system, and repair any discovered security vulnerabilities. At the same time, through real-time monitoring of the system, a response can be issued immediately when a security event occurs.

[0127] Backup and recovery strategies can achieve regular backups of marketing data and ensure the secure storage of backup data. At the same time, by formulating a disaster recovery plan, it is possible to quickly recover in the event of the loss of marketing data or system failures.

[0128] User education and training can regularly conduct network security awareness training for employees to reduce security risks caused by human errors and provide employees with security operation guides to instruct employees on how to correctly handle sensitive information.

[0129] In this way, the data security module 140 can achieve the protection of data security, and can send alarm messages when network attack behaviors are identified, and record network attack logs, such as information about the time, type, and source of network attacks, which is convenient for relevant staff to take necessary measures in a timely manner to find potential security vulnerabilities.

[0130] In one implementation, the data security module 140 can start a monitoring thread to monitor the data traffic of the network port corresponding to the listening address and port according to the set listening address and port, and obtain the listening data. When it is determined from the listening data that a preset network attack behavior has occurred, an alarm message is sent, a network attack log is recorded, and an interrupt signal is sent to disconnect the network connection.

[0131] Among them, the alarm message can include information in the form of sending emails, text messages, etc. to prompt relevant staff that a network attack behavior has occurred.

[0132] Optionally, when a preset network attack behavior is identified, record a network attack log, that is, record information such as the time, type, and source of the attack, and retain relevant logs and data packets. At the same time, disconnect the network connection to isolate the affected system from the network, prevent the attack from spreading, and close ports and services that may lead to further attacks.

[0133] Furthermore, it is also possible to attempt to trace the source of the attack to gain an in-depth understanding of the means used by the attacker and analyze vulnerabilities in the system that may have led to the success of the attack. After that, install security updates and patches on the affected system and change the configuration to close unnecessary services and ports.

[0134] In the above solution, the data security module 140 starts a monitoring thread for the set listening address and port to obtain monitoring data, so as to be able to determine whether a preset network attack behavior occurs based on the monitoring data, and disconnect the network connection in a timely manner through an interrupt signal when it is determined that a preset network attack behavior occurs, preventing the attack from spreading.

[0135] The technical solution of this embodiment collects marketing data from real-time data sources through the data collection module 110, realizes the efficient collection of marketing data, and after collecting the marketing data, performs parallel preprocessing on the marketing data asynchronously, which can increase the processing speed of the marketing data. Then, the data analysis module 120 can obtain the preprocessed marketing data from the database and analyze and identify the authenticity of the marketing data according to a preset identification model, so as to determine whether there is false marketing behavior of the merchant corresponding to the marketing data based on the identification result of the authenticity of the marketing data. When it is determined that there is false marketing behavior of the merchant corresponding to the marketing data, the merchant can be marked to reduce the recommendation frequency for the merchant. At the same time, the user classification module 130 can classify users according to the marketing data obtained from the database using a preset classification model to obtain accurate user categories, so as to achieve precise push for different categories of users according to the classification results and set push strategies.

[0136] Figure 4 Shows a schematic flowchart of a marketing data analysis method provided by an embodiment of the present invention. As Figure 4 shown, the marketing data analysis method provided in this embodiment can be applied to the marketing data analysis system 100 described in any of the above embodiments. Specifically, the marketing data analysis method of this embodiment may include the following steps:

[0137] 4100. The data collection module 110 in the marketing data analysis system 100 collects marketing data from real-time data sources.

[0138] Among them, the data acquisition module 110 can collect marketing data from the servers corresponding to real-time data sources. The real-time data sources at least include social media, e-commerce platforms, and real-time log streams, so as to obtain marketing data reflecting the latest market dynamics and consumer behaviors.

[0139] 4200. The data acquisition module 110 preprocesses the marketing data and stores the preprocessed marketing data in the database.

[0140] The preprocessing of the marketing data can include data cleaning processing and data format conversion processing. The data cleaning processing is to remove the noise data in the marketing data, and the data format conversion processing can standardize and normalize the marketing data to improve the accuracy of subsequent processing.

[0141] The data acquisition module 110 can asynchronously preprocess the collected marketing data and store the preprocessed marketing data in the database, so as to improve the data processing speed by parallel processing of the marketing data.

[0142] In one implementation, the data acquisition module 110 can subscribe to the marketing data of the required real-time data sources according to the address and port of the specified Kafka server. For example, the marketing data of social media, the marketing data of e-commerce platforms, and the marketing data of real-time log streams. The Kafka server publishes the marketing data of social media, the marketing data of e-commerce platforms, and the marketing data of real-time log streams. The data acquisition module 110 receives the subscribed messages, and the messages may include the marketing data of social media, the marketing data of e-commerce platforms, or the marketing data of real-time log streams. The data acquisition module 110 extracts the marketing data from the messages, performs data cleaning processing and data format conversion processing on the marketing data through an asynchronous task function, and stores the processed marketing data in the database through a data saving function.

[0143] In this way, by subscribing to the marketing data of each real-time data source from the Kafka server, the timeliness and diversity of the collected marketing data can be guaranteed, so as to achieve more accurate user classification and false behavior determination. And it can parallel process the marketing data during the data acquisition process to improve the data processing speed.

[0144] 4300. The data analysis module 120 in the marketing data analysis system 100 obtains the marketing data from the database and analyzes and identifies the authenticity of the marketing data according to a preset identification model, so as to determine whether the merchant corresponding to the marketing data has false marketing behavior according to the identification result of the authenticity of the marketing data.

[0145] When analyzing and identifying the authenticity of marketing data according to a preset identification model, the data analysis module 120 can extract the text features and numerical features of the marketing data through the preset identification model; calculate the term frequency-inverse document frequency (TF-IDF) value and sentiment score corresponding to the text features through the preset identification model, calculate the text length of the marketing data based on the numerical features and extract the timestamp feature, and encode the product category and user level in the marketing data to obtain the category feature; obtain the feature matrix according to the text features, numerical features, and category features; and obtain the identification result of the authenticity of the marketing data based on the feature matrix, TF-IDF value, and sentiment score.

[0146] 4400. The user classification module 130 in the marketing data analysis system 100 obtains marketing data from the database, classifies users according to a preset classification model to obtain a classification result, and determines the push strategy for users of different categories based on the set push strategy and classification result.

[0147] Specifically, the user classification module 130 can extract user purchase record feature data from the marketing data; the user purchase record feature data includes user label features, purchase frequency features, purchase amount features, and geographical location features. Perform standardization processing on the user purchase record feature data to obtain the user data to be classified. Perform clustering classification on the user data to be classified through a preset classification model to obtain a classification result.

[0148] In practical applications, after obtaining the marketing data from the database, the user classification module 130 can first perform data cleaning and sorting on the obtained marketing data to remove outliers and missing values in the marketing data. Then, extract the user's purchase record feature data from the marketing data after data cleaning and sorting, including user label features (such as the user's account name or account ID), purchase frequency features, purchase amount features, and geographical location features, etc.

[0149] After obtaining the user's purchase record feature data, perform feature scaling on the purchase record feature data to achieve standardization processing of the purchase record feature data and obtain the user data to be classified. Among them, the standardization processing of the user purchase record feature data can be achieved through a formula, that is, through the formula Standardize the characteristic data of the user purchase records to obtain the user data to be classified. Here, z represents the user data to be classified, x represents the characteristic data of the user purchase records, μ represents the mean value of each characteristic in the characteristic data of the user purchase records, that is, the mean value of the user label characteristic, purchase frequency characteristic, purchase amount characteristic, and geographical location characteristic, and σ represents the standard deviation of each characteristic in the characteristic data of the user purchase records, that is, the standard deviation of the user label characteristic, purchase frequency characteristic, purchase amount characteristic, and geographical location characteristic. In this way, the numerical ranges and scales between different characteristics can be made more consistent, thereby avoiding the influence of certain characteristics with larger numerical ranges on the reliability of the preset classification model.

[0150] After that, the user classification module 130 performs clustering classification on the user data to be classified through a preset classification model. The preset classification model can be pre-trained based on a clustering algorithm or a classification algorithm. Among them, the clustering algorithm can be, for example, the K-means clustering algorithm or the hierarchical clustering algorithm, and the classification algorithm can be, for example, the decision tree algorithm or the random forest algorithm. After obtaining the classification result of the user, the personalized marketing strategy of the user can be determined according to the classification result and the set push strategy.

[0151] In the technical solution of this embodiment, the data acquisition module 110 is used to collect marketing data from real-time data sources, preprocess the marketing data, and store the preprocessed marketing data in the database. The data analysis module 120 is used to obtain the marketing data from the database and analyze and identify the authenticity of the marketing data according to a preset recognition model, so as to determine whether there is false marketing behavior of the merchant corresponding to the marketing data according to the recognition result. The user classification module 130 is used to obtain the marketing data from the database, classify the users according to a preset classification model to obtain a classification result, and determine the push strategy for different types of users based on the set push strategy and the classification result. Thus, a large amount of marketing data can be processed more quickly and effectively, and accurate classification of users can be achieved.

[0152] Furthermore, the marketing data analysis method provided by the embodiment of the present invention may further include that the data security module 140 of the marketing data analysis system 100 issues an alarm message when identifying a network attack behavior and records the network attack log for security auditing.

[0153] By issuing an alarm message when identifying a network attack behavior, the marketing data analysis system 100 can be protected from the risks of network attacks and data leakage, and comprehensive protection of the marketing data analysis system 100 can be achieved.

[0154] In a specific implementation, a monitoring thread can be started based on the set listening address and port to monitor the data traffic of the network port corresponding to the listening address and port, and obtain the monitoring data. When it is determined according to the monitoring data that a preset network attack behavior has occurred, an alarm message is sent, a network attack log is recorded, and an interrupt signal is sent to disconnect the network connection.

[0155] Among them, the alarm message can include information in the form of sending emails, text messages, etc. to prompt relevant staff of the network attack behavior.

[0156] Optionally, when it is recognized that a preset network attack behavior has occurred, a network attack log is recorded, that is, information such as the time, type, and source of the attack is recorded, and relevant logs and data packets are retained. At the same time, the network connection is disconnected to isolate the affected system from the network, prevent the spread of the attack, and the ports and services that may cause further attacks can be closed.

[0157] Furthermore, it is also possible to try to trace the source of the attack to deeply understand the means used by the attacker and analyze the vulnerabilities in the system that may have led to the success of the attack. After that, security updates and patches are installed on the affected system, and the configuration is changed to close unnecessary services and ports.

[0158] In the technical solution of this embodiment, the data security module 140 starts a monitoring thread to monitor the set listening address and port to obtain the monitoring data, so as to be able to judge whether a preset network attack behavior has occurred based on the monitoring data, and when it is judged that a preset network attack behavior has occurred, the network connection is timely disconnected through an interrupt signal to prevent the spread of the attack.

[0159] Figure 5 It is a schematic structural diagram of an electronic device shown according to an exemplary embodiment of the present invention. As Figure 5 shown, an electronic device 500 provided in this embodiment includes: a processor 501 and a memory 502; wherein:

[0160] The memory 502 is used to store a computer program, and this memory can also be flash (flash memory).

[0161] The processor 501 is used to execute the execution instructions stored in the memory to implement each step in the above method. For specific reference, please refer to the relevant descriptions in the previous method embodiments.

[0162] Optionally, the memory 502 can be either independent or integrated with the processor 501.

[0163] When the memory 502 is a device independent of the processor 501, the electronic device 500 may further include:

[0164] A bus 503 for connecting a memory 502 and a processor 501.

[0165] This embodiment also provides a computer-readable storage medium. A computer program is stored in the readable storage medium. When at least one processor of the electronic device executes the computer program, the electronic device executes the methods provided by the above various embodiments.

[0166] This embodiment also provides a program product. The program product includes a computer program, and the computer program is stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and the execution of the computer program by at least one processor enables the electronic device to implement the methods provided by the above various embodiments.

[0167] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present invention. The embodiments of the present invention are intended to cover any variations, uses, or adaptations of the embodiments of the present invention, which follow the general principles of the embodiments of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed in the embodiments of the present invention. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the embodiments of the present invention are pointed out by the claims.

[0168] It should be understood that the embodiments of the present invention are not limited to the exact structures already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the embodiments of the present invention is only limited by the appended claims.

Claims

1. A marketing data analysis system, characterized in that, Including: A data collection module, configured to collect marketing data from real-time data sources, preprocess the marketing data, and store the preprocessed marketing data in a database; A data analysis module, configured to obtain the marketing data from the database, analyze and identify the authenticity of the marketing data according to a preset recognition model, and determine whether there is false marketing behavior of the merchant corresponding to the marketing data according to the recognition result of the authenticity of the marketing data; A user classification module, configured to obtain the marketing data from the database, classify users according to a preset classification model to obtain a classification result, and determine a push strategy for different categories of users based on a set push strategy and the classification result; Wherein, the data analysis module analyzes and identifies the authenticity of the marketing data according to a preset recognition model, including: Extracting text features and numerical features of the marketing data through the preset recognition model; Calculating the term frequency-inverse document frequency TF-IDF value and sentiment score corresponding to the text features through the preset recognition model, calculating the text length of the marketing data according to the numerical features and extracting timestamp features, and encoding the product category and user level in the marketing data to obtain category features; Obtaining a feature matrix according to the text features, the numerical features, and the category features; Based on the feature matrix, the TF-IDF value, and the sentiment score, obtaining the recognition result of the authenticity of the marketing data; The user classification module obtains the marketing data from the database, and the classification result obtained by classifying users according to a preset classification model includes: Extracting user purchase record feature data from the marketing data; the user purchase record feature data includes user label features, purchase frequency features, purchase amount features, and geographical location features; Performing standardization processing on the user purchase record feature data to obtain user data to be classified; Performing clustering classification on the user data to be classified through the preset classification model to obtain the classification result.

2. The system according to claim 1, wherein The data collection module includes: A real-time data collection unit, configured to collect the marketing data from the server corresponding to the real-time data source, and the real-time data source includes at least social media, e-commerce platforms, and real-time log streams; An asynchronous data processing unit, configured to asynchronously preprocess the marketing data collected by the real-time data collection unit and store the preprocessed marketing data in the database.

3. The system according to claim 2, wherein The real-time data collection unit is specifically configured to: subscribe to the marketing data of the social media, the marketing data of the e-commerce platform, and the marketing data of the real-time log stream from a Kafka server; loop through the messages received from the Kafka server, extract the marketing data from the messages; and send the extracted marketing data to the asynchronous data processing unit for processing.

4. The system according to claim 2, wherein The asynchronous data processing unit is specifically configured to: receive the marketing data from the real-time data acquisition unit, perform data cleaning processing and data format conversion processing on the marketing data through an asynchronous task function, and store the processed marketing data into the database through a data saving function; wherein, the data cleaning processing and the data format conversion processing belong to the preprocessing.

5. The system according to claim 1, wherein The user classification module performs normalization processing on the user purchase record feature data to obtain user data to be classified, including: Through the formula standardize the user purchase record feature data to obtain the user data to be classified; where z represents the user data to be classified, x represents the user purchase record feature data, μ represents the mean of each feature in the user purchase record feature data, and σ represents the standard deviation of each feature in the user purchase record feature data.

6. The system according to claim 1, characterized in that The system further includes: a data security module, configured to send an alarm message when a network attack behavior is identified, and record a network attack log for security auditing.

7. The system according to claim 6, wherein The data security module is specifically configured to: according to the set listening address and port, start a monitoring thread to monitor the data of the network port corresponding to the listening address and port, and obtain the monitoring data; When it is determined according to the monitoring data that the preset network attack behavior has occurred, send the alarm message, record the network attack log, and send an interrupt signal to disconnect the network connection.

8. A marketing data analysis method, applied to the marketing data analysis system according to any one of claims 1-7, characterized in that, The method includes: The data acquisition module in the marketing data analysis system acquires marketing data from a real-time data source; The data acquisition module preprocesses the marketing data and stores the preprocessed marketing data into a database; The data analysis module in the marketing data analysis system acquires the marketing data from the database, and analyzes and identifies the authenticity of the marketing data according to a preset identification model, so as to determine whether there is false marketing behavior of the merchant corresponding to the marketing data according to the identification result of the authenticity of the marketing data; The user classification module in the marketing data analysis system acquires the marketing data from the database, classifies users according to a preset classification model to obtain a classification result, and determines a push strategy for different types of users based on the set push strategy and the classification result; wherein, the data analysis module in the marketing data analysis system analyzes and identifies the authenticity of the marketing data according to a preset identification model, including: extracting text features and numerical features of the marketing data through the preset identification model; calculating the term frequency-inverse document frequency TF-IDF value and the sentiment score corresponding to the text features through the preset identification model, calculating the text length of the marketing data according to the numerical features and extracting the timestamp feature, and encoding the product category and user level in the marketing data to obtain category features; obtaining a feature matrix according to the text features, the numerical features, and the category features; obtaining an identification result of the authenticity of the marketing data based on the feature matrix, the TF-IDF value, and the sentiment score; The user classification module in the marketing data analysis system obtains the marketing data from the database and classifies users according to a preset classification model. The classification results include: Extract user purchase record feature data from the marketing data; the user purchase record feature data includes user label features, purchase frequency features, purchase amount features, and geographical location features; Perform standardization processing on the user purchase record feature data to obtain user data to be classified; Perform clustering classification on the user data to be classified through the preset classification model to obtain the classification results.

Images