A user data management system and method based on data analysis

Abstract

This invention discloses a user data management system and method based on data analysis, relating to the field of data management technology. The system includes: a data acquisition and preprocessing module, an improvement direction analysis and user classification module, a key improvement direction screening module, and a user feedback evaluation and identification module. The data acquisition and preprocessing module acquires and analyzes user data and interaction design element information, establishing a mapping relationship between user data and interaction design element information. The improvement direction analysis and user classification module analyzes the improvement directions of interaction design elements based on the mapping relationship and classifies users into multiple categories according to the improvement directions. The key improvement direction screening module analyzes the user improvement directions for each category and extracts key improvement directions. The user feedback evaluation and identification module analyzes the correlation between key improvement directions in different categories and evaluates user satisfaction with interaction design element groups based on user feedback, determining the target interaction design element group.

Description

Technical Field

[0001] This invention relates to the field of data management technology, specifically to a user data management system and method based on data analysis. Background Technology

[0002] Interaction design is the process of creating effective interactions between users and products or services, with the core goal of enhancing user experience. Through well-designed interfaces and smooth interaction flows, interaction design aims to maximize user satisfaction and engagement, thereby increasing product appeal and user stickiness. In this process, the collection and analysis of user data plays a crucial role. User data encompasses user activity records, behavioral habits, preference settings, and subsequent feedback, all of which are important references for optimizing interaction design. Through in-depth analysis of this data, designers can gain insights into user needs and expectations, enabling more precise design and functional adjustments.

[0003] While existing technologies have made some progress in the collection and analysis of user data, there are still shortcomings in their application to interaction design. Specifically, in the interaction design process, designers often rely on user feedback to make improvements. However, because user feedback is often subjective and may contain contradictions or rejections, designers may make incorrect optimization decisions without effectively distinguishing these feedbacks, thereby affecting the design's effectiveness and user satisfaction. Summary of the Invention

[0004] The purpose of this invention is to provide a user data management system and method based on data analysis to solve the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] A user data management method based on data analysis includes the following steps:

[0007] Step S100. Obtain user data and interaction design element information from the database, analyze the user data and interaction design element information respectively, and obtain the mapping relationship between user data and interaction design element information;

[0008] Step S200. Based on the mapping relationship between user data and interaction design element information, match user data with interaction design element information to obtain the improvement direction of interaction design elements; according to the improvement direction of each interaction design element, divide the users corresponding to the user data into several categories;

[0009] Step S300. For each category of users, obtain the corresponding user data and interaction design element information, analyze the improvement direction of each user's interaction design elements, and extract the improvement direction of the interaction design elements that exist in common to each user in the corresponding category as the key improvement direction;

[0010] Step S400. Analyze the correlation between key improvement directions of different categories, and obtain several interaction design element groups based on the correlation analysis results; collect user feedback data for each interaction design element group, evaluate user satisfaction for each interaction design element group based on the user feedback data, and thus obtain the target interaction design element group.

[0011] Furthermore, step S100 includes:

[0012] S101. Obtain user data and interaction design element information from the database. The user data refers to feedback information collected by the system regarding user interactions with interaction design elements. The interaction design element information refers to relevant information about all interface elements involved in the user's interaction with the system, such as element numbers, page positions, and shape descriptions. Extract keywords and convert formats from the user data and interaction design element information respectively. Keyword extraction methods include TF-IDF, Word2Vec, or deep learning models (such as BERT). This yields the desired user data. Let U be a user dataset and E be an interaction design element information set, where U = {u1, u2, ..., un} and E = {e1, e2, ..., em}, where u1 represents the user data keyword set of the first user, u2 represents the user data keyword set of the second user, and so on, un represents the user data keyword set of the nth user, and n represents the total number of users; e1 represents the keyword set corresponding to the first interaction design element, e2 represents the keyword set corresponding to the second interaction design element, and so on, em represents the keyword set corresponding to the mth interaction design element, and m represents the number of interaction design elements;

[0013] S102. For each element ui in the user dataset U, where i ranges from 1 to n; obtain the interaction design element number corresponding to each keyword in element ui, divide it into several keyword groups according to the interaction design element number corresponding to each keyword, and each keyword group corresponds to an interaction design element number; based on the interaction design element number corresponding to each keyword group and the interaction design element number corresponding to each element in the interaction design element information set E, obtain the mapping relationship between each keyword group and the elements in the interaction design element information set E.

[0014] Furthermore, step S200 includes:

[0015] S201. Based on the mapping relationship between each keyword group and the elements in the interaction design element information set E, match the keyword groups with the same interaction design element number with the elements ej in the interaction design element information set E, where j ranges from 1 to m; obtain the user data segment corresponding to the keyword group and the interaction design element information corresponding to the element ej in the interaction design element information set E, match the user data segment with the interaction design element information, and thus generate the improvement direction of the interaction design element;

[0016] S202. For each interaction design element, summarize the improvement directions of all users' interaction design elements, and perform semantic analysis and format conversion on the improvement directions of each user's interaction design elements to obtain the improvement direction vector Vj, where Vj=[v1j,v2j,...,vkj], where v1j represents the first feature of the improvement direction of the j-th interaction design element, v2 represents the second feature of the improvement direction of the j-th interaction design element, and so on, vk represents the k-th feature of the improvement direction of the j-th interaction design element, where k represents the feature dimension of the improvement direction vector; evaluate the similarity by calculating the Euclidean distance between the improvement direction vectors Vj of users, and divide the users of each interaction design element's improvement direction into several categories based on the similarity calculation results.

[0017] Furthermore, step S300 includes:

[0018] S301. For each category of users for each interaction design element, summarize the corresponding improvement direction vectors Vj to form an improvement direction vector set G, and G={g1,g2,...,gh}, where g1 represents the improvement direction vector corresponding to the first user in the corresponding category, g2 represents the improvement direction vector corresponding to the second user in the corresponding category, and so on, gh represents the improvement direction vector corresponding to the h-th user in the corresponding category, and h represents the number of users in the corresponding category;

[0019] S302. For each category's set of improvement direction vectors G, calculate the intersection of the feature dimensions of the improvement direction vectors Vj corresponding to different users in turn, so as to obtain the intersection result of the corresponding category, which is represented as the intersection set J. The elements corresponding to the intersection set J are taken as the improvement directions of the interaction design elements of the corresponding category, and they are marked as key improvement directions.

[0020] Furthermore, step S400 includes:

[0021] S401. Obtain the key improvement directions for different categories of each interaction design element. Search the preset operation database based on these key improvement directions to find the operation path for each category's key improvement direction. Analyze the overlap C between the operation paths of different categories' key improvement directions, and use the overlap C to represent the correlation between different categories' key improvement directions. The specific calculation formula is: C=|Pa∩Pb| / |Pa∪Pb|, where Pa represents the operation path of the key improvement direction corresponding to the a-th category of an interaction design element, and Pb represents the operation path of the key improvement direction corresponding to the b-th category of an interaction design element. If C=0, it means that the two different categories of key improvement directions are independent. Merge the key improvement directions; if 0 < C < C0, where C0 represents the threshold, it means that the relationship between the two different categories of key improvement directions needs further analysis, and output the two different categories of key improvement directions to the relevant personnel for appropriate processing; if C0 ≤ C ≤ 1, it means that the two different categories of key improvement directions have a contradictory or exclusive relationship, and retain the two different categories of key improvement directions; traverse all categories of all interaction design elements, and randomly combine the key improvement directions corresponding to different interaction design elements in turn to obtain several key improvement directions of interaction design element groups, and each interaction design element group corresponds to all interaction design elements, and the key improvement direction corresponding to each interaction element is unique;

[0022] S402. Summarize the key improvement directions for each interaction design element group to generate a comprehensive interaction design element improvement plan; collect user feedback data for the interaction design element improvement plan for each interaction design element group, perform semantic analysis and keyword extraction on the user feedback data, and label each keyword as a positive, negative, or neutral category label, with values ​​of 1, -1, and 0 respectively; summarize the keyword set of the user feedback data for each interaction design element group, calculate the sum of the category labels of all elements in the keyword set as the user satisfaction of each interaction design element group, select the interaction design element group with the highest user satisfaction as the target interaction design element group, and output the target interaction design element group to relevant personnel.

[0023] A user data management system based on data analysis includes: a data acquisition and preprocessing module, an improvement direction analysis and user classification module, a key improvement direction screening module, and a user feedback evaluation and identification module;

[0024] The data acquisition and preprocessing module acquires user data and interaction design element information, analyzes the user data and interaction design element information respectively, and obtains the mapping relationship between the user data and interaction design element information.

[0025] The improvement direction analysis and user classification module is based on the mapping relationship between user data and interaction design element information. It maps user data to interaction design element information to obtain the improvement direction of interaction design elements. Based on the improvement direction of interaction design elements, the users corresponding to the user data are divided into several categories.

[0026] The key improvement direction screening module acquires corresponding user data and interaction design element information for each user category, analyzes the improvement direction of each user's interaction design elements, and extracts the improvement direction of the interaction design elements that exist in common to each user in the corresponding category as the key improvement direction.

[0027] The user feedback evaluation and identification module analyzes the correlation between key improvement directions in different categories and obtains several interaction design element groups based on the correlation analysis results; it collects user feedback data for each interaction design element group, evaluates user satisfaction for each interaction design element group based on the user feedback data, and thus obtains the target interaction design element group.

[0028] Furthermore, the data acquisition and preprocessing module includes a data acquisition and processing unit and a mapping relationship establishment unit;

[0029] The data acquisition and processing unit retrieves user data and interaction design element information from the database, and performs keyword extraction and format conversion on this data to generate user datasets and interaction design element information sets. The mapping relationship establishment unit divides the user dataset into multiple keyword groups according to the correspondence between keywords and interaction design element numbers, and establishes a mapping relationship between each keyword group and elements in the interaction design element information set.

[0030] Furthermore, the improvement direction analysis and user classification module includes an improvement direction analysis unit and a user classification unit;

[0031] The improvement direction analysis unit matches the user data segments corresponding to the keyword groups with the interaction design element information based on the mapping relationship between keyword groups and interaction design element information, thereby generating improvement directions for interaction design elements; the user classification unit summarizes the user's improvement directions for each interaction design element and performs semantic analysis and format conversion to generate an improvement direction vector; by calculating the similarity between user improvement direction vectors, users are classified according to similarity based on Euclidean distance.

[0032] Furthermore, the key improvement direction filtering module includes an improvement direction vector summarization unit and a key improvement direction marking unit;

[0033] The Improvement Direction Vector Summarization Unit summarizes the corresponding improvement direction vectors for each category of users for each interaction design element, forming an Improvement Direction Vector Set; the Key Improvement Direction Marking Unit calculates the intersection of the feature dimensions of the improvement direction vectors of different users for each category of the Improvement Direction Vector Set, obtaining the Intersection Set; and marks the elements in the Intersection Set as the key improvement directions of the corresponding category of interaction design element.

[0034] Furthermore, the user feedback evaluation and identification module includes a key improvement direction analysis unit and a user feedback analysis and identification unit;

[0035] The Key Improvement Direction Analysis Unit analyzes the correlation between different categories of key improvement directions and obtains several interaction design element groups based on the correlation analysis results; the User Feedback Analysis and Identification Unit collects user feedback data for each interaction design element group, evaluates user satisfaction for each interaction design element group based on the user feedback data, and thus obtains the target interaction design element group.

[0036] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention, through a user data management method based on data analysis, can effectively extract keywords and related information from a large amount of user feedback, accurately analyze the relationship between user needs and interaction design elements, thereby reducing subjective bias and making design improvement directions more scientific and reasonable. This invention efficiently classifies and clusters user feedback data through keyword extraction and semantic analysis. Based on the improvement directions of interaction design elements, it assesses the similarity between users using Euclidean distance, thereby extracting common improvement directions for different categories of users; this intelligent data analysis method helps designers more accurately identify the needs of different user groups and achieve more precise design optimization. This invention extracts the key improvement directions common to each category of users through set analysis of the improvement directions; this method helps to clarify which design improvements have the greatest value for most users, thereby concentrating resources for effective optimization. This invention quantifies user satisfaction with the improvement directions of interaction design elements through semantic analysis, keyword extraction, and category label assignment of user feedback data; by comprehensively considering the user satisfaction of each interaction design element group, it can clearly identify the most satisfactory improvement solutions for users, thus providing designers with clear optimization directions and avoiding human decision-making errors. Attached Figure Description

[0037] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0038] Figure 1This is a schematic diagram of a user data management system based on data analysis according to the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Please see Figure 1 The present invention provides the following technical solution:

[0041] A user data management method based on data analysis includes the following steps:

[0042] Step S100. Obtain user data and interaction design element information from the database, analyze the user data and interaction design element information respectively, and obtain the mapping relationship between user data and interaction design element information;

[0043] Step S200. Based on the mapping relationship between user data and interaction design element information, match user data with interaction design element information to obtain the improvement direction of interaction design elements; according to the improvement direction of each interaction design element, divide the users corresponding to the user data into several categories;

[0044] Step S300. For each category of users, obtain the corresponding user data and interaction design element information, analyze the improvement direction of each user's interaction design elements, and extract the improvement direction of the interaction design elements that exist in common to each user in the corresponding category as the key improvement direction;

[0045] Step S400. Analyze the correlation between key improvement directions of different categories, and obtain several interaction design element groups based on the correlation analysis results; collect user feedback data for each interaction design element group, evaluate user satisfaction for each interaction design element group based on the user feedback data, and thus obtain the target interaction design element group.

[0046] Step S100 includes:

[0047] S101. Obtain user data and interaction design element information from the database. The user data refers to feedback information collected by the system regarding user interactions with interaction design elements. The interaction design element information refers to relevant information about all interface elements involved in the user's interaction with the system, such as element numbers, page positions, and shape descriptions. Extract keywords and convert formats from the user data and interaction design element information respectively. Keyword extraction methods include TF-IDF, Word2Vec, or deep learning models (such as BERT). This yields the desired user data. Let U be a user dataset and E be an interaction design element information set, where U = {u1, u2, ..., un} and E = {e1, e2, ..., em}, where u1 represents the user data keyword set of the first user, u2 represents the user data keyword set of the second user, and so on, un represents the user data keyword set of the nth user, and n represents the total number of users; e1 represents the keyword set corresponding to the first interaction design element, e2 represents the keyword set corresponding to the second interaction design element, and so on, em represents the keyword set corresponding to the mth interaction design element, and m represents the number of interaction design elements;

[0048] S102. For each element ui in the user dataset U, where i ranges from 1 to n; obtain the interaction design element number corresponding to each keyword in element ui, divide it into several keyword groups according to the interaction design element number corresponding to each keyword, and each keyword group corresponds to an interaction design element number; based on the interaction design element number corresponding to each keyword group and the interaction design element number corresponding to each element in the interaction design element information set E, obtain the mapping relationship between each keyword group and the elements in the interaction design element information set E.

[0049] Step S200 includes:

[0050] S201. Based on the mapping relationship between each keyword group and the elements in the interaction design element information set E, match the keyword groups with the same interaction design element number with the elements ej in the interaction design element information set E, where j ranges from 1 to m; obtain the user data segment corresponding to the keyword group and the interaction design element information corresponding to the element ej in the interaction design element information set E, match the user data segment with the interaction design element information, and thus generate the improvement direction of the interaction design element;

[0051] In this embodiment, problems in the design are identified based on the mapping between user data segments and interaction design elements. For example:

[0052] If the keyword in user feedback is "slow button response", then the corresponding interaction design element is "button"; the corresponding problem is: slow button response may be due to slow button click event processing, or due to network latency, interface lag, or other factors.

[0053] For each identified problem, conduct an in-depth root cause analysis:

[0054] Performance issues: If the problem is slow button response, you may need to check if there are performance bottlenecks in front-end loading, server response speed, animation effects, etc.

[0055] Visual issues: If the problem is a cluttered interface layout, it is necessary to assess whether the arrangement of interface elements conforms to the user's visual perception habits, and whether it is too crowded or unclear.

[0056] Based on the root cause analysis, targeted improvement directions are generated:

[0057] To improve button response issues, we should optimize button response time, such as by optimizing front-end code, reducing asynchronous request latency, and minimizing unnecessary animation effects.

[0058] The direction for improving the cluttered interface layout is to redesign the interface layout and adopt a clearer, more hierarchical layout.

[0059] S202. For each interaction design element, summarize the improvement directions of all users' interaction design elements, and perform semantic analysis and format conversion on the improvement directions of each user's interaction design elements to obtain the improvement direction vector Vj, where Vj=[v1j,v2j,...,vkj], where v1j represents the first feature of the improvement direction of the j-th interaction design element, v2 represents the second feature of the improvement direction of the j-th interaction design element, and so on, vk represents the k-th feature of the improvement direction of the j-th interaction design element, where k represents the feature dimension of the improvement direction vector; evaluate the similarity by calculating the Euclidean distance between the improvement direction vectors Vj of users, and divide the users of each interaction design element's improvement direction into several categories based on the similarity calculation results.

[0060] In this embodiment, similarity is evaluated by calculating the Euclidean distance between the improved direction vectors Vj of users. It is assumed that the K-means clustering algorithm is used to divide users into K categories based on the similarity calculation results. The specific analysis process is as follows: initialize K cluster centers; assign users to the nearest cluster according to similarity, update the cluster centers, until the cluster centers no longer change.

[0061] Step S300 includes:

[0062] S301. For each category of users for each interaction design element, summarize the corresponding improvement direction vectors Vj to form an improvement direction vector set G, and G={g1,g2,...,gh}, where g1 represents the improvement direction vector corresponding to the first user in the corresponding category, g2 represents the improvement direction vector corresponding to the second user in the corresponding category, and so on, gh represents the improvement direction vector corresponding to the h-th user in the corresponding category, and h represents the number of users in the corresponding category;

[0063] S302. For each category's set of improvement direction vectors G, calculate the intersection of the feature dimensions of the improvement direction vectors Vj corresponding to different users in turn, so as to obtain the intersection result of the corresponding category, which is represented as the intersection set J. The elements corresponding to the intersection set J are taken as the improvement directions of the interaction design elements of the corresponding category, and they are marked as key improvement directions.

[0064] In this embodiment, it is assumed that the user category of the j-th interaction design element is divided into two categories, represented as user category 1 and user category 2, respectively. The number of users in user category 1 is 3, which corresponds to the set of improvement direction vectors G={g1,g2,g3}. It is assumed that users A, B, and C are represented by improvement direction vectors VjA, VjB, and VjC, respectively, i.e., the set of direction vectors G={g1,g2,g3}={VjA,VjB,VjC}. It is assumed that the feature dimension of the corresponding improvement direction vector is 5. Taking improvement direction vector VjA as an example, VjA=[v1j,v2j] [v3j,v4j,v5j]; sequentially compare the intersection of the element features of the improvement direction vectors VjA, VjB, and VjC, assuming the final result is: J1={VjA∩VjB∩VjC}={v1j,v2j,v5j}; similarly, perform the same operation on user category 2 as on user category 1, assuming the result is: J2={VjA∩VjB∩VjC}={v3j,v4j}; mark the intersection set J1 in user category 1 as the key improvement direction of user category 1; similarly, mark the intersection set J2 in user category 2 as the key improvement direction of user category 2.

[0065] Step S400 includes:

[0066] S401. Obtain the key improvement directions for different categories of each interaction design element. Search the preset operation database based on these key improvement directions to find the operation path for each category's key improvement direction. Analyze the overlap C between the operation paths of different categories' key improvement directions, and use the overlap C to represent the correlation between different categories' key improvement directions. The specific calculation formula is: C=|Pa∩Pb| / |Pa∪Pb|, where Pa represents the operation path of the key improvement direction corresponding to the a-th category of an interaction design element, and Pb represents the operation path of the key improvement direction corresponding to the b-th category of an interaction design element. If C=0, it means that the two different categories of key improvement directions are independent. Merge the key improvement directions; if 0 < C < C0, where C0 represents the threshold, it means that the relationship between the two different categories of key improvement directions needs further analysis, and output the two different categories of key improvement directions to the relevant personnel for appropriate processing; if C0 ≤ C ≤ 1, it means that the two different categories of key improvement directions have a contradictory or exclusive relationship, and retain the two different categories of key improvement directions; traverse all categories of all interaction design elements, and randomly combine the key improvement directions corresponding to different interaction design elements in turn to obtain several key improvement directions of interaction design element groups, and each interaction design element group corresponds to all interaction design elements, and the key improvement direction corresponding to each interaction element is unique;

[0067] S402. Summarize the key improvement directions for each interaction design element group to generate a comprehensive interaction design element improvement plan; collect user feedback data for the interaction design element improvement plan for each interaction design element group, perform semantic analysis and keyword extraction on the user feedback data, and label each keyword as a positive, negative, or neutral category label, with values ​​of 1, -1, and 0 respectively; summarize the keyword set of the user feedback data for each interaction design element group, calculate the sum of the category labels of all elements in the keyword set as the user satisfaction of each interaction design element group, select the interaction design element group with the highest user satisfaction as the target interaction design element group, and output the target interaction design element group to relevant personnel.

[0068] In this embodiment, it is assumed that the user categories of the j-th interaction design element are divided into two categories, and the intersection set J1 is marked as the key improvement direction for user category 1, J1={v1j,v2j,v5j}; the intersection set J2 is marked as the key improvement direction for user category 2, J2={v3j,v4j}; based on the key improvement directions J and J2, a search is performed in the preset operation database to find the operation path of the key improvement direction for each category, thereby obtaining the operation paths P1 and P2 corresponding to the key improvement directions J and J2. The overlap degree C between the operation paths P1 and P2 is analyzed. If the overlap degree C=0, the key improvement directions J1 and J2 are merged. Therefore, the key improvement direction for the user category of the j-th interaction design element is the result of merging J1 and J2; if C0≤C≤1, the key improvement directions J1 and J2 are retained.

[0069] Assume there are 5 interaction design elements. Analysis shows that the second interaction design element has two key improvement directions, denoted as J2(1) and J2(2). The other four interaction design elements each correspond to one key improvement direction, denoted as J1, J3, J4, and J5. Through random combination, several interaction design element groups are obtained as {J1,J2(1),J3,J4,J5} and {J1,J2(2),J3,J4,J5}. A comprehensive interaction design element improvement scheme is generated based on the interaction design element groups, denoted as Interaction Design Element Improvement Scheme 1 and Interaction Design Element Improvement Scheme 2, respectively. User feedback data for the interaction design element improvement scheme corresponding to each interaction design element group is collected, and user feedback is analyzed. The data undergoes semantic analysis and keyword extraction. Each keyword is labeled with three categories: positive, negative, and neutral, with values ​​of 1, -1, and 0 respectively. The keyword set of user feedback data corresponding to each interaction design element group is summarized, and the sum of the category labels of all elements in the keyword set is calculated as the user satisfaction for each interaction design element group. The group with the highest user satisfaction is selected as the target interaction design element group and output to relevant personnel. If the user satisfaction corresponding to interaction design element improvement scheme 1 is greater than that of interaction design element improvement scheme 2, then the interaction element group corresponding to interaction design element improvement scheme 2 is selected as the target interaction design element group and output to relevant personnel.

[0070] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A user data management method based on data analysis, characterized in that: The method includes the following steps: Step S100. Obtain user data and interaction design element information from the database, analyze the user data and interaction design element information respectively, and obtain the mapping relationship between user data and interaction design element information; Step S200. Based on the mapping relationship between user data and interaction design element information, match user data with interaction design element information to obtain the improvement direction of interaction design elements; according to the improvement direction of each interaction design element, divide the users corresponding to the user data into several categories; Step S300. For each category of users, obtain the corresponding user data and interaction design element information, analyze the improvement direction of each user's interaction design elements, and extract the improvement direction of the interaction design elements that exist in common to each user in the corresponding category as the key improvement direction; Step S400. Analyze the correlation between key improvement directions of different categories, and obtain several interaction design element groups based on the correlation analysis results; collect user feedback data for each interaction design element group, evaluate user satisfaction for each interaction design element group based on the user feedback data, and thus obtain the target interaction design element group. Step S200 includes: S201. Based on the mapping relationship between each keyword group and the elements in the interaction design element information set E, match the keyword groups with the same interaction design element number with the elements ej in the interaction design element information set E, where j ranges from 1 to m; obtain the user data segment corresponding to the keyword group and the interaction design element information corresponding to the element ej in the interaction design element information set E, match the user data segment with the interaction design element information, and thus generate the improvement direction of the interaction design element; S202. For each interaction design element, summarize the improvement directions of all users' interaction design elements, and perform semantic analysis and format conversion on the improvement directions of each user's interaction design elements to obtain the improvement direction vector Vj, where Vj=[v1j,v2j,...,vkj], where v1j represents the first feature of the improvement direction of the j-th interaction design element, v2j represents the second feature of the improvement direction of the j-th interaction design element, and so on, vkj represents the k-th feature of the improvement direction of the j-th interaction design element, where k represents the feature dimension of the improvement direction vector; evaluate the similarity by calculating the Euclidean distance between the improvement direction vectors Vj of users, and divide the users of each interaction design element's improvement direction into several categories based on the similarity calculation results; Step S300 includes: S301. For each category of users for each interaction design element, summarize the corresponding improvement direction vectors Vj to form an improvement direction vector set G, and G={g1,g2,...,gh}, where g1 represents the improvement direction vector corresponding to the first user in the corresponding category, g2 represents the improvement direction vector corresponding to the second user in the corresponding category, and so on, gh represents the improvement direction vector corresponding to the h-th user in the corresponding category, and h represents the number of users in the corresponding category; S302. For each category's set of improvement direction vectors G, calculate the intersection of the feature dimensions of the improvement direction vectors Vj corresponding to different users in turn, so as to obtain the intersection result of the corresponding category, which is represented as the intersection set J. The elements corresponding to the intersection set J are taken as the improvement directions of the interaction design elements of the corresponding category, and they are marked as key improvement directions.

2. The user data management method based on data analysis according to claim 1, characterized in that: Step S100 includes: S101. Obtain user data and interaction design element information from the database. The user data refers to the feedback information about user interaction design elements collected by the system during user interaction. The interaction design element information refers to the relevant information of all interface elements involved when the user interacts with the system. Keyword extraction and format conversion are performed on user data and interaction design element information respectively to obtain user dataset U and interaction design element information set E, where U={u1,u2,...,un} and E={e1,e2,...,em}, where u1 represents the keyword set of the first user's user data, u2 represents the keyword set of the second user's user data, and so on, un represents the keyword set of the nth user's user data, and n represents the total number of users; e1 represents the keyword set corresponding to the first interaction design element, e2 represents the keyword set corresponding to the second interaction design element, and so on, em represents the keyword set corresponding to the mth interaction design element, and m represents the number of interaction design elements; S102. For each element ui in the user dataset U, where i ranges from 1 to n; Get the interaction design element number corresponding to each keyword in the UI element, divide it into several keyword groups according to the interaction design element number corresponding to each keyword, and each keyword group corresponds to an interaction design element number. Based on the interaction design element number corresponding to each keyword group and the interaction design element number corresponding to each element in the interaction design element information set E, the mapping relationship between each keyword group and the elements in the interaction design element information set E is obtained.

3. The user data management method based on data analysis according to claim 1, characterized in that: Step S400 includes: S401. Obtain the key improvement directions for different categories of each interaction design element, and search the preset operation database according to the key improvement directions to find the operation path of the key improvement direction for each category; analyze the overlap C between the operation paths of the key improvement directions of different categories, and use the overlap C to represent the correlation between the key improvement directions of different categories, and the specific calculation formula is: C=|Pa∩Pb| / |Pa∪Pb|, where Pa represents the operation path of the key improvement direction corresponding to the a-th category of a certain interaction design element, and Pb represents the operation path of the key improvement direction corresponding to the b-th category of a certain interaction design element; if C=0, the two different categories The key improvement directions are merged; if 0 < C < C0, where C0 represents the threshold, the two different categories of key improvement directions are output to the relevant personnel for processing; if C0 ≤ C ≤ 1, it indicates that the two different categories of key improvement directions have a contradictory or exclusive relationship, and the two different categories of key improvement directions are retained; iterate through all categories of all interaction design elements, and randomly combine the key improvement directions corresponding to different interaction design elements to obtain several key improvement directions of interaction design element groups, and each interaction design element group corresponds to all interaction design elements, and the key improvement direction corresponding to each interaction element is unique; S402. Summarize the key improvement directions for each interaction design element group to generate a comprehensive interaction design element improvement plan; collect user feedback data for the interaction design element improvement plan for each interaction design element group, perform semantic analysis and keyword extraction on the user feedback data, and label each keyword as a positive, negative, or neutral category label, with values ​​of 1, -1, and 0 respectively; summarize the keyword set of the user feedback data for each interaction design element group, calculate the sum of the category labels of all elements in the keyword set as the user satisfaction of each interaction design element group, select the interaction design element group with the highest user satisfaction as the target interaction design element group, and output the target interaction design element group to relevant personnel.

4. A user data management system based on data analysis, applied to the user data management method based on data analysis as described in any one of claims 1-3, characterized in that: The system includes: a data acquisition and preprocessing module, an improvement direction analysis and user classification module, a key improvement direction screening module, and a user feedback evaluation and identification module. The data acquisition and preprocessing module acquires user data and interaction design element information, analyzes the user data and interaction design element information respectively, and obtains the mapping relationship between user data and interaction design element information. The improvement direction analysis and user classification module is based on the mapping relationship between user data and interaction design element information. It maps user data and interaction design element information to obtain the improvement direction of interaction design elements. Based on the improvement direction of interaction design elements, the users corresponding to the user data are divided into several categories. The key improvement direction screening module acquires corresponding user data and interaction design element information for each category of users, analyzes the improvement direction of each user's interaction design elements, and extracts the improvement direction of the interaction design elements that exist in common to each user in the corresponding category as the key improvement direction. The user feedback evaluation and identification module analyzes the correlation between key improvement directions in different categories and obtains several interaction design element groups based on the correlation analysis results; it collects user feedback data for each interaction design element group, evaluates user satisfaction for each interaction design element group based on the user feedback data, and thus obtains the target interaction design element group.

5. A user data management system based on data analysis according to claim 4, characterized in that: The improvement direction analysis and user classification module includes an improvement direction analysis unit and a user classification unit; The improvement direction analysis unit matches the user data segment corresponding to the keyword group with the interaction design element information based on the mapping relationship between the keyword group and the interaction design element information, thereby generating the improvement direction of the interaction design element. The user classification unit summarizes the user's improvement directions for each interaction design element and performs semantic analysis and format conversion to generate an improvement direction vector. By calculating the similarity between user improvement direction vectors, users are classified according to similarity based on Euclidean distance.

6. A user data management system based on data analysis according to claim 4, characterized in that: The key improvement direction filtering module includes an improvement direction vector aggregation unit and a key improvement direction marking unit; The improvement direction vector aggregation unit aggregates the corresponding improvement direction vectors for each category of users for each interaction design element, forming an improvement direction vector set; the key improvement direction marking unit calculates the intersection of the feature dimensions of the improvement direction vectors of different users for each category of improvement direction vector set, obtaining an intersection set; and marks the elements in the intersection set as key improvement directions for the corresponding category of interaction design element.

Images