User profile data management method and system based on data mining

Abstract

The present invention discloses a user profile data management method and system based on data mining, and relates to the technical field of data management. During operation of the system, user data is collected from various data sources, a first data group, a second data group and a third data group are obtained, and preprocessing is performed to analyze the user data, and the user's shopping behavior patterns, preferences and consumption trends are mined. After calculation by applying a data mining algorithm, a data management index Sjgl is obtained. Based on the data mining result, a user profile is generated. The generated user profile is used, and a recommendation system and a marketing automation tool are used to compare the data management index Sjgl with a preset standard threshold M and a preset standard threshold N to obtain personalized product recommendations and customized marketing activities, collect user feedback and behavior data, continuously monitor system performance and user reactions, iteratively optimize data mining algorithms and system functions, and improve user profiles and recommendation strategies in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a user profile data management method and system based on data mining. Background Art

[0002] In today's highly competitive commercial retail industry, commodity sales not only rely on high-quality products and services, but also require accurate user profile data management methods to improve user experience and promote sales conversion rates. Traditional user profile data management methods are often unable to cope with massive data and diverse user needs, while user profile data management methods based on data mining use advanced data mining technology to deeply analyze users' shopping behaviors, preferences and consumption trends, provide a scientific basis for personalized services and marketing, and greatly enhance the precision marketing capabilities of commercial retail.

[0003] However, existing methods have some shortcomings in practical applications, such as uneven data quality, difficult to ensure data security, and low data storage and access efficiency. By introducing advanced data mining technology, this method can effectively solve these problems, improve the overall level of data management, ensure high quality and high security of data, and then optimize user profiles and personalized recommendation strategies, improve user satisfaction and sales conversion rate. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a user profile data management method and system based on data mining, which solves the problems mentioned in the background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a user profile data management system based on data mining, including a data collection module, a data storage management module, a data mining module, a user profile generation module, a personalized recommendation module and a user feedback module;

[0008] The data collection module is used to collect user data from various data sources, obtain the first data group, the second data group and the third data group, and upload them to the data storage management module after pre-processing such as data cleaning, deduplication and format conversion;

[0009] The data storage management module is used to store the pre-processed data in the database system, supporting fast data reading and writing operations and flexible query functions;

[0010] The data mining module is used to analyze user data, mine the user's shopping behavior patterns, preferences and consumption trends, and obtain the data management index Sjgl by applying the data mining algorithm.

[0011] The user profile generation module is used to generate user profiles based on data mining results, including user personal information, shopping history, behavioral characteristics and preference analysis, to provide a basis for personalized services and marketing;

[0012] The personalized recommendation module is used to utilize the generated user profile, use the recommendation system and marketing automation tools, compare the data management index Sjgl with the preset standard threshold M and the preset standard threshold N, obtain personalized product recommendations and customized marketing activities, and improve user experience and purchase conversion rate;

[0013] The user feedback module is used to collect user feedback and behavior data, continuously monitor system performance and user reactions, iteratively optimize data mining algorithms and system functions, and improve user profiles and recommendation strategies in real time.

[0014] Preferably, the data collection module includes a data quality collection unit, a data security collection unit and a data storage management collection unit;

[0015] The data quality collection unit is used to collect, through a database management system, a data quality monitoring tool, a network monitoring device and a log analysis tool: the proportion of erroneous data entries Cwtm, the number of missing values ​​Qszs, the data update frequency Sjgx and the number of transmission errors Cscw occurring during the data collection process as a first data group;

[0016] The data security collection unit is used to collect, through access control systems, encryption software, privacy protection tools, backup systems and recovery systems: the number of unauthorized access attempts Wsqs, the strength of the encryption algorithm Jmqd, the degree of protection of personal sensitive data Mgbh, the data backup period Bfzq and the data recovery time Sjhf as a second data group;

[0017] The data storage management collection unit is used to collect: storage utilization Ccly, data reading speed Sjdq, data writing speed Xrsd and system failure rate Xtgz as the third data group through a storage management system, a read / write performance testing tool, a system monitoring tool and a performance evaluation tool.

[0018] Preferably, the data storage management module includes a database management unit and a data access unit;

[0019] The database management unit is used to efficiently store the pre-processed data in the database, create and maintain data indexes, back up data at fixed periods, compress data, save storage space and improve storage efficiency;

[0020] The data access unit is used to use a query optimizer to improve query performance, optimize data read and write operations, increase data access speed, manage concurrent access by multiple users and applications, control data access permissions, cache commonly used query results, and avoid overhead caused by repeated queries.

[0021] Preferably, the data mining module includes a data analysis unit, a modeling unit and a data calculation unit;

[0022] The data analysis unit is used to extract and select key features, apply data mining algorithms, and conduct in-depth analysis of user data;

[0023] The modeling unit is used to train the model using a machine learning method, optimize the model parameters, so as to improve the prediction accuracy and evaluate the performance of the model;

[0024] The data calculation unit is used to integrate the results of the data analysis and modeling unit, record the first data group, the second data group and the third data group in digital form, and process them in real time, and obtain the following by combined calculation: data management index Sjgl, data quality coefficient Sjzl, data security coefficient Sjaq and data storage management coefficient Glcc;

[0025] The data management index Sjgl is calculated by the following formula:

[0026]

[0027] Wherein, Sjzl represents the data quality coefficient, Sjaq represents the data security coefficient, Glcc represents the data storage management coefficient, q, w and e represent the proportional coefficients of the data quality coefficient Sjzl, the data security coefficient Sjaq and the data storage management coefficient Glcc respectively;

[0028] Wherein, 0≤q≤1, 0≤w≤1, 0≤e≤1, and q+w+e≤1.0, R represents the first correction constant;

[0029] The data quality coefficient Sjzl is calculated by the following formula:

[0030] Sjzl=[(Cwtm*t)+(Qszs*y)+(Sjgx*u)+(Cscw*i)]+O;

[0031] Where, Cwtm represents the proportion of erroneous data entries, Qszs represents the number of missing values, Sjgx represents the data update frequency, Cscw represents the number of transmission errors that occur during data collection, and t, y, u, and i represent the proportional coefficients of the proportion of erroneous data entries Cwtm, the number of missing values ​​Qszs, the data update frequency Sjgx, and the number of transmission errors that occur during data collection Cscw, respectively;

[0032] Wherein, 0≤t≤1, 0≤y≤1, 0≤u≤1, 0≤i≤1, and t+y+u+i≤1.0, and O represents the second correction constant.

[0033] Preferably, the data security coefficient Sjaq is calculated by the following formula:

[0034] Sjaq=[(Wsqs*a)+(Jmqd*s)+(Mgbh*d)+(Bfzq*f)+(Sjhf*g)]+H;

[0035] Where Wsqs represents the number of unauthorized access attempts, Jmqd represents the strength of the encryption algorithm, Mgbh represents the degree of protection of personal sensitive data, Bfzq represents the data backup cycle, Sjhf represents the data recovery time, a, s, d, f and g represent the proportional coefficients of the number of unauthorized access attempts Wsqs, the strength of the encryption algorithm Jmqd, the degree of protection of personal sensitive data Mgbh, the data backup cycle Bfzq and the data recovery time Sjhf respectively;

[0036] Among them, 0≤a≤1, 0≤s≤1, 0≤d≤1, 0≤f≤1, 0≤g≤1, and a+s+d+f+g≤1.0, and H represents the third correction constant.

[0037] Preferably, the data storage management coefficient Glcc is calculated by the following formula:

[0038] Glcc=[(Ccly*h)+(Sjdq*j)+(Xrsd*k)+(Xtgz*z)]+L;

[0039] Where, Ccly represents storage utilization, Sjdq represents data read speed, Xrsd represents data write speed, Xtgz represents system failure rate, h, j, k and z represent the proportional coefficients of storage utilization Ccly, data read speed Sjdq, data write speed Xrsd and system failure rate Xtgz respectively;

[0040] Wherein, 0≤h≤1, 0≤j≤1, 0≤k≤1, 0≤z≤1, and h+j+k+z≤1.0, and L represents the fourth correction constant.

[0041] Preferably, the user profile generation module includes a user information integration unit and a user portrait analysis unit;

[0042] The user information integration unit is used to integrate the user's personal information, including name, age, gender, contact information and address, collect and integrate the user's purchase records, including purchase time, purchased goods, quantity and amount information, integrate the user's behavior data on the platform, including browsing history, click records and shopping cart content, associate the user's personal information, shopping history and behavior data to form user profile data, and update the information in the user profile at a fixed period;

[0043] The user portrait analysis unit is used to analyze the user's shopping habits, frequency and preferences based on the user's shopping history and behavior data, classify and group the users according to their behavioral characteristics and preferences, and generate a detailed user portrait based on the user's personal information, shopping history, behavioral characteristics and preference analysis. It generates personalized labels for each user, including "high-frequency buyer", "price sensitive", and "brand loyalist", for precision marketing and personalized recommendations.

[0044] Preferably, the personalized recommendation module includes a recommendation system unit and a marketing automation unit;

[0045] The recommendation system unit is used to use the information in the user profile to match the user's interests and preferences, generate a personalized product recommendation list, dynamically adjust the recommended content according to the user's real-time behavior data, and display the recommendation results to the user in the form of the home page, product details page and shopping cart;

[0046] The marketing automation unit is used to obtain personalized product recommendations and customized marketing activities by comparing the data management index Sjgl with the preset standard threshold M and the preset standard threshold N:

[0047] When the data management index Sjgl is less than the preset standard threshold M, it means that the user data management index is below the standard level. Strengthen data cleaning and deduplication. Use data cleaning tools to clean data twice a week. Perform a comprehensive data quality check and report once a month. Establish a user feedback mechanism to collect user opinions and suggestions on data quality.

[0048] When the preset standard threshold M≤data management index Sjgl<preset standard threshold N, it means that the user data management index is consistent with the standard level, improve data protection measures, apply deep learning models for complex data analysis and prediction, optimize data storage and access systems, and apply Redis cache technology to speed up data reading;

[0049] When the data management index Sjgl ≥ the preset standard threshold N, it means that the user data management index is 20% higher than the standard level. Real-time stream processing technology is introduced to realize real-time data analysis and response, establish a user experience feedback mechanism, and continuously collect user opinions and suggestions.

[0050] Preferably, the user feedback module includes a user feedback collection unit;

[0051] The user feedback collection unit is used to collect user feedback, including satisfaction surveys, opinions and suggestions, and complaints, through multiple channels, including websites, apps, emails, and social media, and monitor user behavior data on the platform in real time, including clicks, browsing, purchases, and exit behaviors, classify, organize, and label the collected feedback, and store the collected feedback and behavior data in a unified database.

[0052] The user profile data management method based on data mining includes the following steps:

[0053] Step 1: Collect user data from various data sources, obtain the first data group, the second data group and the third data group, perform pre-processing of data cleaning, deduplication and format conversion, and then upload them to the data storage management module;

[0054] Step 2: Store the preprocessed data in the database system, supporting fast data reading and writing operations and flexible query functions;

[0055] Step 3: Analyze user data to mine users’ shopping behavior patterns, preferences, and consumption trends, and obtain the data management index Sjgl by applying data mining algorithms;

[0056] Step 4: Generate user profiles based on data mining results, including user personal information, shopping history, behavioral characteristics and preference analysis, to provide a basis for personalized services and marketing;

[0057] Step 5: Using the generated user profile, recommendation system and marketing automation tools, compare the data management index Sjgl with the preset standard threshold M and preset standard threshold N to obtain personalized product recommendations and customized marketing activities, thereby improving user experience and purchase conversion rate;

[0058] Step 6: Collect user feedback and behavior data, continuously monitor system performance and user response, iteratively optimize data mining algorithms and system functions, and improve user profiles and recommendation strategies in real time.

[0059] (III) Beneficial effects

[0060] The present invention provides a user profile data management method and system based on data mining, which has the following beneficial effects:

[0061] (1) When the system is running, user data is collected from various data sources to obtain the first data group, the second data group and the third data group, and pre-processed, and the user data is analyzed to mine the user's shopping behavior patterns, preferences and consumption trends. After applying the data mining algorithm, the following data management index Sjgl is obtained: based on the data mining results, a user profile is generated, and the generated user profile is used to compare the data management index Sjgl with the preset standard threshold M and the preset standard threshold N using the recommendation system and marketing automation tools to obtain personalized product recommendations and customized marketing activities, collect user feedback and behavior data, continuously monitor system performance and user response, iteratively optimize the data mining algorithm and system functions, and improve the user profile and recommendation strategy in real time.

[0062] (2) The database management unit is responsible for efficiently storing preprocessed data, creating and maintaining data indexes, and saving storage space and improving storage efficiency through fixed-cycle backup and data compression technology. The data access unit uses query optimizer and cache technology to improve the speed and efficiency of data read and write operations, manage concurrent access by multiple users and applications, control data access rights, avoid system overhead caused by repeated queries, and thus improve overall system performance. The data mining module deeply mines users' shopping behavior patterns, preferences, and consumption trends through the collaborative work of data analysis units, modeling units, and data calculation units. The data management index Sjgl calculated by the data mining algorithm provides a scientific basis for personalized recommendations and marketing strategies. By optimizing model parameters and evaluating model performance, the accuracy and reliability of predictions are improved, helping companies to understand user needs more accurately and formulate effective marketing strategies.

[0063] (3) The personalized recommendation module uses the generated user profiles, combined with the recommendation system and marketing automation tools, to obtain personalized product recommendations and customized marketing activities by comparing the data management index Sjgl with the preset standard thresholds M and N. According to different management index levels, corresponding optimization measures are taken to improve user experience and purchase conversion rate. For example, when the data management index is low, measures to strengthen data cleaning and deduplication are taken; when the data management index is high, real-time stream processing technology is applied to optimize data analysis and response, and continuously improve the accuracy of the recommendation system and user satisfaction. The user feedback module monitors user behavior data and feedback information in real time through the user feedback collection unit, classifies and stores them in a unified database, and provides a basis for continuous monitoring and optimization of system performance and functions. Combined with user feedback data, it iteratively optimizes data mining algorithms and system functions, and improves user profiles and recommendation strategies in real time to ensure that the system always meets user needs and improves user satisfaction and system efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1This is a schematic diagram of the user profile data management system based on data mining in the present invention;

[0065] Figure 2 The figure is a schematic diagram of the steps of the user profile data management method based on data mining of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] In today's highly competitive commercial retail industry, commodity sales not only rely on high-quality products and services, but also require accurate user profile data management methods to improve user experience and promote sales conversion rates. Traditional user profile data management methods are often unable to cope with massive data and diverse user needs, while user profile data management methods based on data mining use advanced data mining technology to deeply analyze users' shopping behaviors, preferences and consumption trends, provide a scientific basis for personalized services and marketing, and greatly enhance the precision marketing capabilities of commercial retail.

[0068] However, existing methods have some shortcomings in practical applications, such as uneven data quality, difficult to ensure data security, and low data storage and access efficiency. By introducing advanced data mining technology, this method can effectively solve these problems, improve the overall level of data management, ensure high quality and high security of data, and then optimize user profiles and personalized recommendation strategies, improve user satisfaction and sales conversion rate.

[0069] Example 1

[0070] The present invention provides a user profile data management system based on data mining, please refer to Figure 1 , including data collection module, data storage management module, data mining module, user profile generation module, personalized recommendation module and user feedback module;

[0071] The data collection module is used to collect user data from various data sources, obtain the first data group, the second data group and the third data group, and upload them to the data storage management module after pre-processing such as data cleaning, deduplication and format conversion;

[0072] The data storage management module is used to store the pre-processed data in the database system, supporting fast data reading and writing operations and flexible query functions;

[0073] The data mining module is used to analyze user data, mine the user's shopping behavior patterns, preferences and consumption trends, and obtain the data management index Sjgl by applying the data mining algorithm.

[0074] The user profile generation module is used to generate user profiles based on data mining results, including user personal information, shopping history, behavioral characteristics and preference analysis, to provide a basis for personalized services and marketing;

[0075] The personalized recommendation module is used to utilize the generated user profile, use the recommendation system and marketing automation tools, compare the data management index Sjgl with the preset standard threshold M and the preset standard threshold N, obtain personalized product recommendations and customized marketing activities, and improve user experience and purchase conversion rate;

[0076] The user feedback module is used to collect user feedback and behavior data, continuously monitor system performance and user reactions, iteratively optimize data mining algorithms and system functions, and improve user profiles and recommendation strategies in real time.

[0077] In this embodiment, user data is collected from various data sources to obtain the first data group, the second data group and the third data group. After preprocessing such as data cleaning, deduplication and format conversion, the data is uploaded to the data storage management module, and the preprocessed data is stored in the database system. Fast data read and write operations and flexible query functions are supported, user data is analyzed, and the user's shopping behavior patterns, preferences and consumption trends are mined. The data management index Sjgl is obtained by applying the data mining algorithm to calculate: based on the data mining results, a user profile is generated, including user personal information, shopping history, behavioral characteristics and preference analysis, to provide a basis for personalized services and marketing, and the generated user profile is used. The recommendation system and marketing automation tools are used to compare the data management index Sjgl with the preset standard threshold M and the preset standard threshold N to obtain personalized product recommendations and customized marketing activities, improve user experience and purchase conversion rate, collect user feedback and behavior data, continuously monitor system performance and user response, iteratively optimize data mining algorithms and system functions, and improve user profiles and recommendation strategies in real time.

[0078] Example 2

[0079] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data collection module includes a data quality collection unit, a data security collection unit and a data storage management collection unit;

[0080] The data quality collection unit is used to collect, through a database management system, a data quality monitoring tool, a network monitoring device and a log analysis tool: the proportion of erroneous data entries Cwtm, the number of missing values ​​Qszs, the data update frequency Sjgx and the number of transmission errors Cscw occurring during the data collection process as a first data group;

[0081] The data security collection unit is used to collect, through access control systems, encryption software, privacy protection tools, backup systems and recovery systems: the number of unauthorized access attempts Wsqs, the strength of the encryption algorithm Jmqd, the degree of protection of personal sensitive data Mgbh, the data backup period Bfzq and the data recovery time Sjhf as a second data group;

[0082] The data storage management collection unit is used to collect: storage utilization Ccly, data reading speed Sjdq, data writing speed Xrsd and system failure rate Xtgz as the third data group through a storage management system, a read / write performance testing tool, a system monitoring tool and a performance evaluation tool.

[0083] The data storage management module includes a database management unit and a data access unit;

[0084] The database management unit is used to efficiently store the pre-processed data in the database, create and maintain data indexes, back up data at fixed periods, compress data, save storage space and improve storage efficiency;

[0085] The data access unit is used to use a query optimizer to improve query performance, optimize data read and write operations, increase data access speed, manage concurrent access by multiple users and applications, control data access permissions, cache commonly used query results, and avoid overhead caused by repeated queries.

[0086] In this embodiment, the data quality collection unit monitors and collects key parameters such as the proportion of erroneous data entries, the number of missing values, the frequency of data updates, and the number of data transmission errors, thereby effectively improving the accuracy and integrity of the data. The preprocessing work of data cleaning, deduplication, and format conversion further ensures the high quality of the data and provides a reliable basis for subsequent data analysis and mining. The data security collection unit monitors parameters such as the number of unauthorized access attempts, the strength of the encryption algorithm, and the degree of protection of personal sensitive data through access control systems, encryption software, and privacy protection tools to ensure the security of data during collection, transmission, and storage. The application of backup systems and recovery systems ensures the recoverability and continuity of data and effectively prevents the risk of data loss and leakage. The data storage management collection unit monitors key parameters such as storage utilization, data reading speed, data writing speed, and system failure rate through storage management systems, read-write performance testing tools, and system monitoring tools to ensure efficient and stable data storage. The collaborative work of the database management unit and the data access unit further optimizes data storage and access performance, improves data reading and writing speed and query efficiency, supports high concurrent access and data access permission management, and improves the overall system performance and user experience.

[0087] Example 3

[0088] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data mining module includes a data analysis unit, a modeling unit and a data calculation unit;

[0089] The data analysis unit is used to extract and select key features, apply data mining algorithms, and conduct in-depth analysis of user data;

[0090] The modeling unit is used to train the model using a machine learning method, optimize the model parameters, so as to improve the prediction accuracy and evaluate the performance of the model;

[0091] The data calculation unit is used to integrate the results of the data analysis and modeling unit, record the first data group, the second data group and the third data group in digital form, and process them in real time, and obtain the following by combined calculation: data management index Sjgl, data quality coefficient Sjzl, data security coefficient Sjaq and data storage management coefficient Glcc;

[0092] The data management index Sjgl is calculated by the following formula:

[0093]

[0094] Wherein, Sjzl represents the data quality coefficient, Sjaq represents the data security coefficient, Glcc represents the data storage management coefficient, q, w and e represent the proportional coefficients of the data quality coefficient Sjzl, the data security coefficient Sjaq and the data storage management coefficient Glcc respectively;

[0095] Wherein, 0≤q≤1, 0≤w≤1, 0≤e≤1, and q+w+e≤1.0, R represents the first correction constant;

[0096] The data quality coefficient Sjzl is calculated by the following formula:

[0097] Sjzl=[(Cwtm*t)+(Qszs*y)+(Sjgx*u)+(Cscw*i)]+O;

[0098] Where, Cwtm represents the proportion of erroneous data entries, Qszs represents the number of missing values, Sjgx represents the data update frequency, Cscw represents the number of transmission errors that occur during data collection, and t, y, u, and i represent the proportional coefficients of the proportion of erroneous data entries Cwtm, the number of missing values ​​Qszs, the data update frequency Sjgx, and the number of transmission errors that occur during data collection Cscw, respectively;

[0099] Wherein, 0≤t≤1, 0≤y≤1, 0≤u≤1, 0≤i≤1, and t+y+u+i≤1.0, and O represents the second correction constant.

[0100] The data security coefficient Sjaq is calculated by the following formula:

[0101] Sjaq=[(Wsqs*a)+(Jmqd*s)+(Mgbh*d)+(Bfzq*f)+(Sjhf*g)]+H;

[0102] Where Wsqs represents the number of unauthorized access attempts, Jmqd represents the strength of the encryption algorithm, Mgbh represents the degree of protection of personal sensitive data, Bfzq represents the data backup cycle, Sjhf represents the data recovery time, a, s, d, f and g represent the proportional coefficients of the number of unauthorized access attempts Wsqs, the strength of the encryption algorithm Jmqd, the degree of protection of personal sensitive data Mgbh, the data backup cycle Bfzq and the data recovery time Sjhf respectively;

[0103] Among them, 0≤a≤1, 0≤s≤1, 0≤d≤1, 0≤f≤1, 0≤g≤1, and a+s+d+f+g≤1.0, and H represents the third correction constant.

[0104] The data storage management coefficient Glcc is calculated by the following formula:

[0105] Glcc=[(Ccly*h)+(Sjdq*j)+(Xrsd*k)+(Xtgz*z)]+L;

[0106] Where, Ccly represents storage utilization, Sjdq represents data read speed, Xrsd represents data write speed, Xtgz represents system failure rate, h, j, k and z represent the proportional coefficients of storage utilization Ccly, data read speed Sjdq, data write speed Xrsd and system failure rate Xtgz respectively;

[0107] Wherein, 0≤h≤1, 0≤j≤1, 0≤k≤1, 0≤z≤1, and h+j+k+z≤1.0, and L represents the fourth correction constant.

[0108] In this embodiment, the data mining module can extract and select key features through the collaborative operation of the data analysis unit and the modeling unit, and apply the data mining algorithm to conduct in-depth analysis of the user data. The model is trained using machine learning methods and the model parameters are optimized to improve the prediction accuracy and evaluate the performance of the model. This precise data analysis and mining capability helps enterprises to more accurately understand the user's shopping behavior patterns, preferences and consumption trends, and provides important support for personalized services and precision marketing. The data calculation unit integrates the results of the data analysis and modeling units, records the first, second and third data groups in digital form, and processes them in real time, thereby calculating the data management index Sjgl, the data quality coefficient Sjzl, the data security coefficient Sjaq and the data storage management coefficient Glcc. These comprehensive indicators can comprehensively evaluate the quality, security and management level of the data, and provide a scientific basis for enterprises to formulate reasonable data management strategies and optimization plans.

[0109] Example 4

[0110] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the user profile generation module includes a user information integration unit and a user portrait analysis unit;

[0111] The user information integration unit is used to integrate the user's personal information, including name, age, gender, contact information and address, collect and integrate the user's purchase records, including purchase time, purchased goods, quantity and amount information, integrate the user's behavior data on the platform, including browsing history, click records and shopping cart content, associate the user's personal information, shopping history and behavior data to form user profile data, and update the information in the user profile at a fixed period;

[0112] The user portrait analysis unit is used to analyze the user's shopping habits, frequency and preferences based on the user's shopping history and behavior data, classify and group the users according to their behavioral characteristics and preferences, and generate a detailed user portrait based on the user's personal information, shopping history, behavioral characteristics and preference analysis. It generates personalized labels for each user, including "high-frequency buyer", "price sensitive", and "brand loyalist", for precision marketing and personalized recommendations.

[0113] The personalized recommendation module includes a recommendation system unit and a marketing automation unit;

[0114] The recommendation system unit is used to use the information in the user profile to match the user's interests and preferences, generate a personalized product recommendation list, dynamically adjust the recommended content according to the user's real-time behavior data, and display the recommendation results to the user in the form of the home page, product details page and shopping cart;

[0115] The marketing automation unit is used to obtain personalized product recommendations and customized marketing activities by comparing the data management index Sjgl with the preset standard threshold M and the preset standard threshold N:

[0116] When the data management index Sjgl is less than the preset standard threshold M, it means that the user data management index is below the standard level. Strengthen data cleaning and deduplication. Use data cleaning tools to clean data twice a week. Perform a comprehensive data quality check and report once a month. Establish a user feedback mechanism to collect user opinions and suggestions on data quality.

[0117] When the preset standard threshold M≤data management index Sjgl<preset standard threshold N, it means that the user data management index is consistent with the standard level, improve data protection measures, apply deep learning models for complex data analysis and prediction, optimize data storage and access systems, and apply Redis cache technology to speed up data reading;

[0118] When the data management index Sjgl ≥ the preset standard threshold N, it means that the user data management index is 20% higher than the standard level. Real-time stream processing technology is introduced to realize real-time data analysis and response, establish a user experience feedback mechanism, and continuously collect user opinions and suggestions.

[0119] The user feedback module includes a user feedback collection unit;

[0120] The user feedback collection unit is used to collect user feedback, including satisfaction surveys, opinions and suggestions, and complaints, through multiple channels, including websites, apps, emails, and social media, and monitor user behavior data on the platform in real time, including clicks, browsing, purchases, and exit behaviors, classify, organize, and label the collected feedback, and store the collected feedback and behavior data in a unified database.

[0121] In this embodiment, the user profile generation module can integrate the user's personal information, shopping history and behavior data to form a detailed user profile through the collaboration of the user information integration unit and the user portrait analysis unit. Based on the user's shopping history and behavior data, the user portrait analysis unit can analyze the user's shopping habits, frequency and preferences, generate a personalized user portrait, and generate personalized tags for each user, such as "high-frequency buyer", "price-sensitive", and "brand loyalist". This personalized user portrait helps companies understand user needs more accurately, provide personalized services and recommendations, and thus improve user satisfaction and loyalty. The personalized recommendation module uses the information in the user profile to match the user's interests and preferences, generate a personalized product recommendation list, and dynamically adjust the recommended content according to the user's real-time behavior data, and display the recommendation results to the user on different pages. Through the marketing automation unit, according to the comparison of the data management index Sjgl with the preset standard threshold M and the preset standard threshold N, personalized product recommendations and customized marketing activities are realized to improve user experience and purchase conversion rate.

[0122] Example 5

[0123] For user profile data management methods based on data mining, please refer to Figure 2 , specifically: including the following steps:

[0124] Step 1: Collect user data from various data sources, obtain the first data group, the second data group and the third data group, perform pre-processing of data cleaning, deduplication and format conversion, and then upload them to the data storage management module;

[0125] Step 2: Store the preprocessed data in the database system, supporting fast data reading and writing operations and flexible query functions;

[0126] Step 3: Analyze user data to mine users’ shopping behavior patterns, preferences, and consumption trends, and obtain the data management index Sjgl by applying data mining algorithms;

[0127] Step 4: Generate user profiles based on data mining results, including user personal information, shopping history, behavioral characteristics and preference analysis, to provide a basis for personalized services and marketing;

[0128] Step 5: Using the generated user profile, recommendation system and marketing automation tools, compare the data management index Sjgl with the preset standard threshold M and preset standard threshold N to obtain personalized product recommendations and customized marketing activities, thereby improving user experience and purchase conversion rate;

[0129] Step 6: Collect user feedback and behavior data, continuously monitor system performance and user response, iteratively optimize data mining algorithms and system functions, and improve user profiles and recommendation strategies in real time.

[0130] In this embodiment, the accuracy and consistency of the data are ensured through data collection and preprocessing. Then, in the data storage management module, an efficient database system is established, which makes the reading, writing and query of data very convenient. Then, through the data mining algorithm, the user's shopping behavior and preferences are deeply understood, and the data management index Sjgl is calculated. After generating the user profile, this information is used to provide users with personalized services and precise marketing. Finally, by collecting user feedback and behavior data, the system is continuously improved and the algorithm is optimized, and the user experience and purchase conversion rate are continuously improved. The beneficial effect of the whole process is that it can better understand user needs, provide products and services that are more in line with user interests and preferences, thereby increasing user satisfaction and loyalty.

[0131] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A user profile data management system based on data mining, characterized by: It includes data collection module, data storage management module, data mining module, user profile generation module, personalized recommendation module and user feedback module; The data collection module is used to collect user data from various data sources, obtain the first data group, the second data group and the third data group, and upload them to the data storage management module after pre-processing such as data cleaning, deduplication and format conversion; The data storage management module is used to store the pre-processed data in the database system, supporting fast data reading and writing operations and flexible query functions; The data mining module is used to analyze user data, mine the user's shopping behavior patterns, preferences and consumption trends, and obtain the data management index Sjgl by applying the data mining algorithm. The data mining module includes a data analysis unit, a modeling unit and a data calculation unit; The data analysis unit is used to extract and select key features, apply data mining algorithms, and conduct in-depth analysis of user data; The modeling unit is used to train the model using a machine learning method, optimize the model parameters, so as to improve the prediction accuracy and evaluate the performance of the model; The data calculation unit is used to integrate the results of the data analysis and modeling unit, record the first data group, the second data group and the third data group in digital form, and process them in real time, and obtain the following by combined calculation: data management index Sjgl, data quality coefficient Sjzl, data security coefficient Sjaq and data storage management coefficient Glcc; The data management index Sjgl is calculated by the following formula: Wherein, Sjzl represents the data quality coefficient, Sjaq represents the data security coefficient, Glcc represents the data storage management coefficient, q, w and e represent the proportional coefficients of the data quality coefficient Sjzl, the data security coefficient Sjaq and the data storage management coefficient Glcc respectively; Wherein, 0≤q≤1, 0≤w≤1, 0≤e≤1, and q+w+e≤1.0, R represents the first correction constant; The data quality coefficient Sjzl is calculated by the following formula: Sjzl=[(Cwtm*t)+(Qszs*y)+(Sjgx*u)+(Cscw*i)]+O; Where, Cwtm represents the proportion of erroneous data entries, Qszs represents the number of missing values, Sjgx represents the data update frequency, Cscw represents the number of transmission errors that occur during data collection, and t, y, u, and i represent the proportional coefficients of the proportion of erroneous data entries Cwtm, the number of missing values ​​Qszs, the data update frequency Sjgx, and the number of transmission errors that occur during data collection Cscw, respectively; Wherein, 0≤t≤1, 0≤y≤1, 0≤u≤1, 0≤i≤1, and t+y+u+i≤1.0, O represents the second correction constant; The data security coefficient Sjaq is calculated by the following formula: Sjaq=[(Wsqs*a)+(Jmqd*s)+(Mgbh*d)+(Bfzq*f)+(Sjhf*g)]+H; Where Wsqs represents the number of unauthorized access attempts, Jmqd represents the strength of the encryption algorithm, Mgbh represents the degree of protection of personal sensitive data, Bfzq represents the data backup cycle, Sjhf represents the data recovery time, a, s, d, f and g represent the proportional coefficients of the number of unauthorized access attempts Wsqs, the strength of the encryption algorithm Jmqd, the degree of protection of personal sensitive data Mgbh, the data backup cycle Bfzq and the data recovery time Sjhf respectively; Wherein, 0≤a≤1, 0≤s≤1, 0≤d≤1, 0≤f≤1, 0≤g≤1, and a+s+d+f+g≤1.0, H represents the third correction constant; The data storage management coefficient Glcc is calculated by the following formula: Glcc=[(Ccly*h)+(Sjdq*j)+(Xrsd*k)+(Xtgz*z)]+L; Where, Ccly represents storage utilization, Sjdq represents data read speed, Xrsd represents data write speed, Xtgz represents system failure rate, h, j, k and z represent the proportional coefficients of storage utilization Ccly, data read speed Sjdq, data write speed Xrsd and system failure rate Xtgz respectively; Wherein, 0≤h≤1, 0≤j≤1, 0≤k≤1, 0≤z≤1, and h+j+k+z≤1.0, L represents the fourth correction constant; The user profile generation module is used to generate user profiles based on data mining results, including user personal information, shopping history, behavioral characteristics and preference analysis, to provide a basis for personalized services and marketing; The personalized recommendation module is used to utilize the generated user profile, use the recommendation system and marketing automation tools, compare the data management index Sjgl with the preset standard threshold M and the preset standard threshold N, obtain personalized product recommendations and customized marketing activities, and improve user experience and purchase conversion rate; The personalized recommendation module includes a recommendation system unit and a marketing automation unit; The recommendation system unit is used to use the information in the user profile to match the user's interests and preferences, generate a personalized product recommendation list, dynamically adjust the recommended content according to the user's real-time behavior data, and display the recommendation results to the user in the form of the home page, product details page and shopping cart; The marketing automation unit is used to obtain personalized product recommendations and customized marketing activities by comparing the data management index Sjgl with the preset standard threshold M and the preset standard threshold N: When the data management index Sjgl is less than the preset standard threshold M, it means that the user data management index is below the standard level. Strengthen data cleaning and deduplication. Use data cleaning tools to clean data twice a week. Perform a comprehensive data quality check and report once a month. Establish a user feedback mechanism to collect user opinions and suggestions on data quality. When the preset standard threshold M≤data management index Sjgl<preset standard threshold N, it means that the user data management index is consistent with the standard level, improve data protection measures, apply deep learning models for complex data analysis and prediction, optimize data storage and access systems, and apply Redis cache technology to speed up data reading; When the data management index Sjgl ≥ the preset standard threshold N, it means that the user data management index is 20% higher than the standard level. Introduce real-time stream processing technology to achieve real-time data analysis and response, establish a user experience feedback mechanism, and continuously collect user opinions and suggestions; The user feedback module is used to collect user feedback and behavior data, continuously monitor system performance and user reactions, iteratively optimize data mining algorithms and system functions, and improve user profiles and recommendation strategies in real time.

2. The user profile data management system based on data mining according to claim 1 is characterized by: The data collection module includes a data quality collection unit, a data security collection unit and a data storage management collection unit; The data quality collection unit is used to collect, through a database management system, a data quality monitoring tool, a network monitoring device and a log analysis tool: the proportion of erroneous data entries Cwtm, the number of missing values ​​Qszs, the data update frequency Sjgx and the number of transmission errors Cscw occurring during the data collection process as a first data group; The data security collection unit is used to collect, through access control systems, encryption software, privacy protection tools, backup systems and recovery systems: the number of unauthorized access attempts Wsqs, the strength of the encryption algorithm Jmqd, the degree of protection of personal sensitive data Mgbh, the data backup period Bfzq and the data recovery time Sjhf as a second data group; The data storage management collection unit is used to collect: storage utilization Ccly, data reading speed Sjdq, data writing speed Xrsd and system failure rate Xtgz as the third data group through a storage management system, a read / write performance testing tool, a system monitoring tool and a performance evaluation tool.

3. The user profile data management system based on data mining according to claim 1 is characterized by: The data storage management module includes a database management unit and a data access unit; The database management unit is used to efficiently store the pre-processed data in the database, create and maintain data indexes, back up data at fixed periods, compress data, save storage space and improve storage efficiency; The data access unit is used to use a query optimizer to improve query performance, optimize data read and write operations, increase data access speed, manage concurrent access by multiple users and applications, control data access permissions, cache commonly used query results, and avoid overhead caused by repeated queries.

4. The user profile data management system based on data mining according to claim 1 is characterized by: The user profile generation module includes a user information integration unit and a user portrait analysis unit; The user information integration unit is used to integrate the user's personal information, including name, age, gender, contact information and address, collect and integrate the user's purchase records, including purchase time, purchased goods, quantity and amount information, integrate the user's behavior data on the platform, including browsing history, click records and shopping cart content, associate the user's personal information, shopping history and behavior data to form user profile data, and update the information in the user profile at a fixed period; The user portrait analysis unit is used to analyze the user's shopping habits, frequency and preferences based on the user's shopping history and behavior data, classify and group the users according to their behavioral characteristics and preferences, and generate a detailed user portrait based on the user's personal information, shopping history, behavioral characteristics and preference analysis. It generates personalized labels for each user, including "high-frequency buyers", "price-sensitive" and "brand loyalists", for precision marketing and personalized recommendations.

5. The user profile data management system based on data mining according to claim 1 is characterized by: The user feedback module includes a user feedback collection unit; The user feedback collection unit is used to collect user feedback, including satisfaction surveys, opinions and suggestions, and complaints, through multiple channels, including websites, apps, emails, and social media, and monitor user behavior data on the platform in real time, including clicks, browsing, purchases, and exit behaviors, classify, organize, and label the collected feedback, and store the collected feedback and behavior data in a unified database.

6. A user profile data management method based on data mining, comprising the user profile data management system based on data mining according to any one of claims 1 to 5, characterized in that: The following steps are involved: Step 1: Collect user data from various data sources, obtain the first data group, the second data group and the third data group, perform pre-processing of data cleaning, deduplication and format conversion, and then upload them to the data storage management module; Step 2: Store the preprocessed data in the database system, supporting fast data reading and writing operations and flexible query functions; Step 3: Analyze user data to mine users’ shopping behavior patterns, preferences, and consumption trends, and obtain the data management index Sjgl by applying data mining algorithms; Step 4: Generate user profiles based on data mining results, including user personal information, shopping history, behavioral characteristics and preference analysis, to provide a basis for personalized services and marketing; Step 5: Using the generated user profile, recommendation system and marketing automation tools, compare the data management index Sjgl with the preset standard threshold M and preset standard threshold N to obtain personalized product recommendations and customized marketing activities, thereby improving user experience and purchase conversion rate; Step 6: Collect user feedback and behavior data, continuously monitor system performance and user response, iteratively optimize data mining algorithms and system functions, and improve user profiles and recommendation strategies in real time.

Images