User data management system and method based on data analysis

Abstract

The invention discloses a user data management system and method based on data analysis, and relates to the technical field of data management. The system comprises 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 the user data and the interactive design element information, and establishes a mapping relation between the user data and the interactive design element information; the improvement direction analysis and user classification module analyzes the improvement direction of the interactive design element based on the mapping relation, and divides the users into a plurality of categories according to the improvement direction; a key improvement direction screening module analyzes the user improvement direction of each category and extracts a key improvement direction; the user feedback evaluation and recognition module analyzes the correlation between different types of key improvement directions, evaluates the user satisfaction of the interactive design element group based on user feedback, and determines a target interactive design element group.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and specifically to a user data management system and method based on data analysis. Background Technique

[0002] Interaction design is the process of creating effective interactions between users and products or services. Its core goal is to enhance the user experience. Through carefully designed interfaces and smooth interaction processes, interaction design aims to maximize user satisfaction and engagement, thereby promoting the attractiveness of the product and user stickiness. In this process, the collection and analysis of user data play a crucial role. User data covers users' activity records, behavior habits, preference settings, and subsequent feedback, all of which are important references for optimizing interaction design. By deeply analyzing this data, designers can gain insights into users' needs and expectations, thereby making more precise designs and functional adjustments.

[0003] Although the existing technology has made certain progress in the collection and analysis of user data, there are still deficiencies in the application of interaction design. Specifically: In the process of interaction design, designers usually rely on users' feedback to make improvements. However, since users' feedback is often subjective and may be contradictory or exclusive, designers may make wrong optimization decisions without effectively distinguishing this feedback, thereby affecting the design effect and user satisfaction. Summary of the Invention

[0004] The purpose of the present invention is to provide a user data management system and method based on data analysis to solve the problems raised in the above background technique.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A user data management method based on data analysis, including the following steps: Step S100. Obtain user data and interaction design element information from the database, and analyze the user data and interaction design element information respectively, so as to obtain the mapping relationship between the user data and the interaction design element information; Step S200. Based on the mapping relationship between the user data and the interaction design element information, correspond the user data and the interaction design element information, so as to obtain the improvement direction of the interaction design element; 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 the interaction design element of each user, so as to extract the common improvement direction of the interaction design element existing in each user in the corresponding category as the key improvement direction; Step S400. Analyze the correlation between the key improvement directions of different categories, and obtain several groups of interaction design elements according to the results of the correlation analysis; collect the user feedback data of each group of interaction design elements, and evaluate the user satisfaction of each group of interaction design elements according to the user feedback data, so as to obtain the target group of interaction design elements.

[0006] Further, step S100 includes: S101. Obtain user data and interaction design element information from the database. The user data refers to the feedback information collected by the system during the user interaction regarding the user's response to the interaction design elements; the interaction design element information refers to the relevant information of all interface elements involved when the user interacts with the system, such as the number, page position, and shape description of the interface elements, etc.; perform keyword extraction and format conversion on the user data and the interaction design element information respectively. Among them, the keyword extraction methods include TF-IDF, Word Embedding (Word2Vec), or deep learning models (such as BERT), etc.; thus, obtain the user data set U and the interaction design element information set E, and U = {u1, u2,..., un}, E = {e1, e2,..., em}, where u1 represents the keyword set of the user data of the first user, u2 represents the keyword set of the user data of the second user, and so on, un represents the keyword set of the user data 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; S102. For each element ui in the user data set U, where i ranges from 1 to n; obtain the interaction design element numbers corresponding to each keyword in the element ui, and divide them into several keyword groups according to the interaction design element numbers corresponding to each keyword, and each keyword group corresponds to an interaction design element number; based on the interaction design element numbers corresponding to each keyword group and the interaction design element numbers corresponding to each element in the interaction design element information set E, thus obtain the mapping relationship between each keyword group and the elements in the interaction design element information set E.

[0007] Further, step S200 includes: S201. According to the mapping relationship between each keyword group and the elements in the interaction design element information set E, correspond the keyword groups with the same interaction design element number to the element 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, and correspond the user data segment and the interaction design element information, thus generating the improvement direction of the interaction design element. S202. For each interaction design element, summarize the improvement directions of the interaction design elements of all users, and perform semantic analysis and format conversion on the improvement directions of the interaction design elements of each user, so as to obtain an improvement direction vector Vj, and Vj = [v1j, v2j,..., vkj], where v1j represents the first feature of the improvement direction of the jth interaction design element, v2 represents the second feature of the improvement direction of the jth interaction design element, and so on, vk represents the kth feature of the improvement direction of the jth 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 the improvement direction of each interaction design element into several categories based on the similarity calculation results.

[0008] Further, step S300 includes: S301. For each category of users of 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 hth user in the corresponding category, and h represents the number of users in the corresponding category; S302. For each category of improvement direction vector set 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, denoted as the intersection set J, and use the elements corresponding to the intersection set J as the improvement direction of the interaction design element of the corresponding category, and mark it as the key improvement direction.

[0009] Further, step S400 includes: S401. Obtain the key improvement directions for different categories of each interaction design element, search in the preset operation database according to the key improvement directions, and find the operation paths of the key improvement directions for each category; analyze the overlap degree C between the operation paths of the key improvement directions for different categories, and use the overlap degree C to represent the correlation between the key improvement directions for different categories. 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, it means that the key improvement directions of two different categories are independent, and the key improvement directions of the two different categories are merged; if 0 < C < C0, where C0 represents the threshold, it means that the relationship between the key improvement directions of two different categories needs to be further analyzed, and the key improvement directions of the two different categories are output to the relevant personnel for corresponding processing; if C0 ≤ C ≤ 1, it means that there is a contradictory or exclusive relationship between the key improvement directions of two different categories, and the key improvement directions of the two different categories are retained; traverse all categories of all interaction design elements, and randomly combine the key improvement directions corresponding to different interaction design elements in turn, so as to obtain the key improvement directions of several groups of interaction design elements. Each group of interaction design elements corresponds to all interaction design elements, and the key improvement direction corresponding to each interaction design element is unique; S402. Summarize the key improvement directions corresponding to each group of interaction design elements to generate a comprehensive interaction design element improvement plan; collect the user feedback data of the interaction design element improvement plan corresponding to each group of interaction design elements, perform semantic analysis and keyword extraction on the user feedback data, and mark each keyword with three category labels: positive, negative, and neutral, and assign values of 1, -1, and 0 respectively; summarize the keyword sets of the user feedback data corresponding to each group of interaction design elements, and calculate the sum of the category labels of all elements in the keyword set as the user satisfaction of each group of interaction design elements. Select the group of interaction design elements with the highest user satisfaction as the target group of interaction design elements and output the target group of interaction design elements to the relevant personnel.

[0010] A user data management system based on data analysis, including: a data collection and preprocessing module, an improvement direction analysis and user classification module, a key improvement direction screening module, and a user feedback evaluation and recognition module; The data collection and preprocessing module obtains user data and interaction design element information, analyzes the user data and interaction design element information respectively, so as to obtain the mapping relationship between the user data and the interaction design element information; The improvement direction analysis and user classification module corresponds user data and interactive design element information based on the mapping relationship between them, so as to obtain the improvement direction of interactive design elements; according to the improvement direction of interactive design elements, the users corresponding to the user data are divided into several categories; The key improvement direction screening module obtains the corresponding user data and interactive design element information for each category of users, analyzes the improvement direction of the interactive design elements of each user, and thus extracts the common improvement direction of the interactive design elements of each user in the corresponding category as the key improvement direction; The user feedback evaluation and recognition module analyzes the correlation between the key improvement directions of different categories, and obtains several groups of interactive design elements according to the correlation analysis results; collects the user feedback data of each group of interactive design elements, and evaluates the user satisfaction of each group of interactive design elements according to the user feedback data, so as to obtain the target group of interactive design elements.

[0011] Furthermore, the data acquisition and preprocessing module includes a data acquisition and processing unit and a mapping relationship establishment unit; The data acquisition and processing unit obtains user data and interactive design element information from the database, extracts keywords and converts the format of these data, and generates a user data set and an interactive design element information set; the mapping relationship establishment unit divides them into multiple keyword groups according to the corresponding relationship between the keywords in the user data set and the interactive design element numbers, and establishes the mapping relationship between each keyword group and the elements in the interactive design element information set.

[0012] Furthermore, 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 interactive design element information according to the mapping relationship between the keyword group and the interactive design element information, so as to generate the improvement direction of the interactive design element; the user classification unit summarizes the improvement directions of the users for each interactive design element, performs semantic analysis and format conversion, and generates an improvement direction vector; by calculating the similarity between the user improvement direction vectors, the users are classified according to the similarity based on the Euclidean distance.

[0013] Furthermore, the key improvement direction screening module includes an improvement direction vector summarization unit and a key improvement direction marking unit; The improvement direction vector summarization unit summarizes the corresponding improvement direction vectors for each category of users of each interaction design element to form an improvement direction vector set; the key improvement direction marking unit calculates the intersection of the characteristic dimensions of the improvement direction vectors of different users for each category of improvement direction vector set to obtain an intersection set; and marks the elements in the intersection set as the key improvement directions of the corresponding category of interaction design elements.

[0014] Further, the user feedback evaluation and recognition module includes a key improvement direction analysis unit and a user feedback analysis and recognition unit; The key improvement direction analysis unit analyzes the correlation between the key improvement directions of different categories and obtains several groups of interaction design elements according to the correlation analysis results; the user feedback analysis and recognition unit collects the user feedback data of each group of interaction design elements and evaluates the user satisfaction of each group of interaction design elements according to the user feedback data, so as to obtain the target group of interaction design elements.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: Through the user data management method based on data analysis, the present invention can effectively extract keywords and relevant 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 the design improvement direction more scientific and reasonable. Through keyword extraction and semantic analysis of user data, the present invention classifies and clusters user feedback data efficiently. Based on the improvement direction of interaction design elements, the similarity between users is evaluated by Euclidean distance, so as to extract common improvement directions for different categories of users; this intelligent data analysis method can help designers more accurately identify the needs of different user groups and achieve more precise design optimization. Through set analysis of the improvement directions of each category of users, the present invention extracts the key improvement directions that commonly exist in each category; this method helps to clarify which design improvements have the greatest value for most users, so as to concentrate resources for effective optimization. Through semantic analysis, keyword extraction and assignment of category labels of user feedback data, the present invention quantifies the user satisfaction with the improvement direction of interaction design elements; by comprehensively considering the user satisfaction of each group of interaction design elements, the present invention can clearly identify the most satisfactory improvement scheme for users, and further provide a clear optimization direction for designers, avoiding human decision-making errors. Brief Description of the Drawings

[0016] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings: Figure 1 It is a module schematic diagram of a user data management system based on data analysis according to the present invention. Detailed Embodiments

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Please refer to Figure 1 , the technical solution provided by the present invention: A user data management method based on data analysis, comprising the following steps: Step S100. Obtain user data and interaction design element information from a database, and analyze the user data and the interaction design element information respectively, so as to obtain the mapping relationship between the user data and the interaction design element information; Step S200. Based on the mapping relationship between the user data and the interaction design element information, correspond the user data and the interaction design element information, so as to obtain the improvement direction of the interaction design element; 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 the interaction design element of each user, so as to extract the common improvement direction of the interaction design element existing in each user in the corresponding category as the key improvement direction; Step S400. Analyze the correlation between the key improvement directions of different categories, and obtain several groups of interaction design elements according to the correlation analysis result; collect the user feedback data of each group of interaction design elements, and evaluate the user satisfaction of each group of interaction design elements according to the user feedback data, so as to obtain the target group of interaction design elements.

[0019] Step S100 includes: S101. Obtain user data and interaction design element information from the database. The user data refers to the feedback information collected by the system during user interaction regarding the user's response to interaction design elements. The interaction design element information refers to the relevant information of all interface elements involved in the user's interaction with the system, such as the number, page location, and shape description of the interface elements, etc. Extract keywords and perform format conversion on the user data and interaction design element information respectively. Among them, the keyword extraction methods include TF-IDF, Word2Vec, or deep learning models (such as BERT), etc. Thus, obtain the user data set U and the interaction design element information set E, and U = {u1, u2,..., un}, E = {e1, e2,..., em}, where u1 represents the keyword set of the user data of the first user, u2 represents the keyword set of the user data of the second user, and so on, un represents the keyword set of the user data 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; S102. For each element ui in the user data set U, where i ranges from 1 to n; obtain the interaction design element numbers corresponding to each keyword in the element ui, and perform division according to the interaction design element numbers corresponding to each keyword, dividing them into several keyword groups, and each keyword group corresponds to an interaction design element number; based on the interaction design element numbers corresponding to each keyword group and the interaction design element numbers corresponding to each element in the interaction design element information set E, thus obtain the mapping relationship between each keyword group and the elements in the interaction design element information set E.

[0020] Step S200 includes: S201. According to the mapping relationship between each keyword group and the elements in the interaction design element information set E, correspond the keyword groups with the same interaction design element number to the element 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, and correspond the user data segment and the interaction design element information, thus generating the improvement direction of the interaction design element. In this embodiment, identify the problems existing in the design according to the mapping between the user data segment and the interaction design element. For example: If the keyword in the user feedback is "slow button response", then the interaction design element corresponding to this keyword group is "button"; the corresponding problem is: the button response is slow, which may be caused by slow processing of the button click event, or due to factors such as network latency and interface lag.

[0021] For each identified problem, conduct a deep - level root cause analysis: Performance issues: If there are problems such as slow button responses, it may be necessary to check whether there are performance bottlenecks in front - end loading, server response speed, animation effects, etc.

[0022] Visual issues: If there are problems such as a cluttered interface layout, it is necessary to evaluate whether the arrangement of interface elements conforms to the user's visual perception habits, whether it is too crowded or unclear.

[0023] Based on the root cause analysis, generate targeted improvement directions: The improvement direction for button response issues is: Optimize the button response time, for example, optimize the front - end code, reduce asynchronous request latency, reduce unnecessary animation effects, etc.

[0024] The improvement direction for a cluttered interface layout is: Redesign the interface layout, adopting a clearer and more hierarchical layout method.

[0025] S202. For each interaction design element, summarize the improvement directions of all users' interaction design elements, and conduct semantic analysis and format conversion on the improvement directions of each user's interaction design elements, so as to obtain an improvement direction vector Vj, and 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 the improvement direction of each interaction design element into several categories based on the similarity calculation result.

[0026] In this embodiment, the similarity is evaluated by calculating the Euclidean distance between the improvement direction vectors Vj of users. Assume that the K - means clustering algorithm is used to divide users into K categories based on the similarity calculation result; The specific analysis process is as follows: Initialize K cluster centers; Assign users to the nearest cluster according to the similarity, and update the cluster centers until the cluster centers no longer change.

[0027] Step S300 includes: S301. For each category of users of 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 set G of improvement direction vectors for each category, sequentially calculate the intersection of the characteristic dimensions of the improvement direction vectors Vj corresponding to different users, so as to obtain the intersection result for the corresponding category, denoted as the intersection set J, and use the elements corresponding to the intersection set J as the improvement directions of the interactive design elements for the corresponding category, and mark them as key improvement directions.

[0028] In this embodiment, it is assumed that the user categories of the j-th interactive design element are divided into 2 categories, which are respectively denoted as user category 1 and user category 2, where the number of users corresponding to user category 1 is 3, that is, the corresponding set G of improvement direction vectors = {g1, g2, g3}; it is assumed to be user A, user B, and user C, corresponding improvement direction vectors VjA, improvement direction vector VjB, and improvement direction vector VjC, that is, the set G of direction vectors = {g1, g2, g3} = {VjA, VjB, VjC}; it is assumed that the characteristic dimension of the corresponding improvement direction vector is 5. Taking the improvement direction vector VjA as an example, VjA = [v1j, v2j, v3j, v4j, v5j]; sequentially compare the intersection of the element characteristics between the improvement direction vector VjA, the improvement direction vector VjB, and the improvement direction vector VjC. Assume 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. Assume the obtained result is: J2 = {VjA ∩ VjB ∩ VjC} = {v3j, v4j}; mark the intersection set J1 in user category 1 as the key improvement direction for user category 1; similarly, mark the intersection set J2 in user category 2 as the key improvement direction for user category 2.

[0029] Step S400 includes: S401. Obtain the key improvement directions for different categories of each interaction design element, search in the preset operation database according to the key improvement directions to find the operation paths of the key improvement directions for each category; analyze the overlap degree C between the operation paths of the key improvement directions for different categories, and use the overlap degree C to represent the correlation between the key improvement directions of different categories. 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, it means that the key improvement directions of two different categories are independent, and the key improvement directions of the two different categories are merged; if 0 < C < C0, where C0 represents the threshold, it means that the relationship between the key improvement directions of two different categories needs further analysis, and the key improvement directions of the two different categories are output to the relevant personnel for corresponding processing; if C0 ≤ C ≤ 1, it means that there is a contradictory or exclusive relationship between the key improvement directions of two different categories, and the key improvement directions of the two different categories are retained; 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 the key improvement directions of several interaction design element groups. Each interaction design element group corresponds to all interaction design elements, and the key improvement direction corresponding to each interaction design element is unique; S402. Summarize the key improvement directions corresponding to each interaction design element group to generate a comprehensive interaction design element improvement plan; collect the user feedback data of the interaction design element improvement plans corresponding to each interaction design element group, perform semantic analysis and keyword extraction on the user feedback data, and mark each keyword with three category labels: positive, negative, and neutral, and assign values of 1, -1, and 0 respectively; summarize the keyword sets of the user feedback data corresponding to each interaction design element group, and 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 the relevant personnel.

[0030] In this embodiment, it is assumed that the user categories of the j-th interactive 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}; according to the key improvement directions J and J2, search in the preset operation database to find the operation paths of the key improvement directions for each category, so as to obtain the operation paths P1 and P2 corresponding to the key improvement directions J and J2, and analyze the overlap degree C between the operation paths P1 and P2. If the overlap degree C = 0, then merge the key improvement directions J1 and J2, so the key improvement direction for the user category of the j-th interactive design element is the result after the merger of J1 and J2; if 0 ≤ C ≤ 1, then retain the key improvement directions J1 and J2; Suppose there are 5 interactive design elements, and through analysis, it is obtained that the second interactive design element has two key improvement directions, which are expressed as: J2(1) and J2(2); the other four interactive design elements each correspond to 1 key improvement direction, which are expressed as: J1, J3, J4, and J5; through random combination, several groups of interactive design elements obtained are: {J1, J2(1), J3, J4, J5} and {J1, J2(2), J3, J4, J5}; generate a comprehensive interactive design element improvement plan according to the groups of interactive design elements, which are expressed as: Interactive Design Element Improvement Plan 1 and Interactive Design Element Improvement Plan 2; collect the user feedback data of the interactive design element improvement plans corresponding to each group of interactive design elements, perform semantic analysis and keyword extraction on the user feedback data, and mark each keyword with three category labels: positive, negative, and neutral, and assign values of 1, -1, and 0 respectively; summarize the keyword sets of the user feedback data corresponding to each group of interactive design elements, and calculate the sum of the category labels of all elements in the keyword set as the user satisfaction of each group of interactive design elements. Select the group of interactive design elements with the highest user satisfaction as the target group of interactive design elements, and output the target group of interactive design elements to the relevant personnel; assume that the user satisfaction corresponding to Interactive Design Element Improvement Plan 1 is greater than that of Interactive Design Element Improvement Plan 2, then select the group of interactive design elements corresponding to Interactive Design Element Improvement Plan 2 as the target group of interactive design elements, and output the target group of interactive design elements to the relevant personnel.

[0031] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall 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 interactive design element information from the database, and analyze the user data and the interactive design element information respectively, so as to obtain the mapping relationship between the user data and the interactive design element information; Step S200. Based on the mapping relationship between the user data and the interactive design element information, correspond the user data and the interactive design element information, so as to obtain the improvement direction of the interactive design element; according to the improvement direction of each interactive 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 interactive design element information, and analyze the improvement direction of the interactive design element of each user, so as to extract the improvement direction of the interactive design element that each user in the corresponding category has in common as the key improvement direction; Step S400. Analyze the correlation between the key improvement directions of different categories, and obtain several groups of interactive design elements according to the correlation analysis results; collect the user feedback data of each group of interactive design elements, and evaluate the user satisfaction of each group of interactive design elements according to the user feedback data, so as to obtain the target group of interactive design elements.

2. The user data management method based on data analysis according to claim 1, wherein: The said step S100 includes; S101. Obtain user data and interactive design element information from the database. The user data refers to the feedback information collected by the system on the user's interaction with the interactive design element during the user interaction process; the interactive design element information refers to the relevant information of all interface elements involved in the user's interaction with the system; Extract keywords and convert the format of the user data and the interactive design element information respectively, so as to obtain the user data set U and the interactive design element information set E, and U={u1, u2,..., un}, E={e1, e2,..., em}, where u1 represents the keyword set of the user data of the first user, u2 represents the keyword set of the user data of the second user, and so on, un represents the keyword set of the user data of the nth user, n represents the total number of users; e1 represents the keyword set corresponding to the first interactive design element, e2 represents the keyword set corresponding to the second interactive design element, and so on, em represents the keyword set corresponding to the mth interactive design element, m represents the number of interactive design elements; S102. For each element ui in the user data set U, where i ranges from 1 to n; Obtain the interactive design element numbers corresponding to each keyword in the element ui, and divide them into several keyword groups according to the interactive design element numbers corresponding to each keyword, and each keyword group corresponds to an interactive design element number; Based on the interactive design element number corresponding to each keyword group and the interactive design element number corresponding to each element in the interactive design element information set E, obtain the mapping relationship between each keyword group and the elements in the interactive design element information set E.

3. The user data management method based on data analysis according to claim 2, wherein: The said step S200 includes: S201. According to the mapping relationship between each keyword group and the elements in the interaction design element information set E, the keyword groups with the same interaction design element number are corresponded to the element 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, and correspond the user data segment and the interaction design element information, so as to generate the improvement direction of the interaction design element. S202. For each interaction design element, summarize the improvement directions of the interaction design elements of all users, and perform semantic analysis and format conversion on the improvement directions of the interaction design elements of each user, so as to obtain the improvement direction vector Vj, and Vj = [v1j, v2j,..., vkj], where v1j represents the first feature of the improvement direction of the jth interaction design element, v2 represents the second feature of the improvement direction of the jth interaction design element, and so on, vk represents the kth feature of the improvement direction of the jth 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 the improvement direction of each interaction design element into several categories based on the similarity calculation result.

4. A user data management method based on data analysis according to claim 3, characterized in that: The step S300 includes: S301. For each category of users of 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 hth user in the corresponding category, and h represents the number of users in the corresponding category. S302. For each category of improvement direction vector set 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, denoted as the intersection set J, and use the elements corresponding to the intersection set J as the improvement direction of the interaction design element of the corresponding category, and mark it as the key improvement direction.

5. A user data management method based on data analysis according to claim 4, characterized in that: The step S400 includes: S401. Obtain the key improvement directions of different categories of each interaction design element, search in the preset operation database according to the key improvement directions, and find the operation paths of the key improvement directions of each category; analyze the overlap degree C between the operation paths of the key improvement directions of different categories, and use the overlap degree C to represent the correlation between the key improvement directions of different categories. 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, merge the key improvement directions of the two different categories; if 0 < C < C0, where C0 represents the threshold, output the key improvement directions of the two different categories to the relevant personnel for corresponding processing; if C0 ≤ C ≤ 1, it means that there is a contradictory or exclusive relationship between the key improvement directions of the two different categories, and keep the key improvement directions of the two different categories; traverse all categories of all interaction design elements, and randomly combine the key improvement directions corresponding to different interaction design elements in turn, so as to obtain the key improvement directions of several groups of interaction design elements. Each group of interaction design elements corresponds to all interaction design elements, and the key improvement direction corresponding to each interaction design element is unique; S402. Summarize the key improvement directions corresponding to each group of interaction design elements to generate a comprehensive interaction design element improvement plan; collect the user feedback data of the interaction design element improvement plan corresponding to each group of interaction design elements, perform semantic analysis and keyword extraction on the user feedback data, and mark each keyword with three category labels: positive, negative, and neutral, and assign values of 1, -1, and 0 respectively; summarize the keyword sets of the user feedback data corresponding to each group of interaction design elements, and calculate the sum of the category labels of all elements in the keyword set as the user satisfaction of each group of interaction design elements. Select the group of interaction design elements with the highest user satisfaction as the target group of interaction design elements, and output the target group of interaction design elements to the relevant personnel.

6. A user data management system based on data analysis, which is applied to a user data management method based on data analysis described in any one of claims 1-5, and is characterized in that: The system includes: a data collection and preprocessing module, an improvement direction analysis and user classification module, a key improvement direction screening module, and a user feedback evaluation and recognition module; The data collection and preprocessing module obtains user data and interaction design element information, and analyzes the user data and interaction design element information respectively to obtain the mapping relationship between the user data and the interaction design element information; The improvement direction analysis and user classification module, based on the mapping relationship between the user data and the interaction design element information, corresponds the user data and the interaction design element information to obtain the improvement direction of the interaction design element; according to the improvement direction of the interaction design element, divide the users corresponding to the user data into several categories; The key improvement direction screening module obtains corresponding user data and interactive design element information for each category of users, analyzes the improvement directions of the interactive design elements of each user, and thus extracts the common improvement directions of the interactive design elements of each user in the corresponding category as the key improvement directions; The user feedback evaluation and recognition module analyzes the correlation between the key improvement directions of different categories, and obtains several groups of interactive design elements according to the correlation analysis results; collects the user feedback data of each group of interactive design elements, and evaluates the user satisfaction of each group of interactive design elements according to the user feedback data, so as to obtain the target group of interactive design elements.

7. A user data management system based on data analysis according to claim 6, characterized in that: The data collection and preprocessing module includes a data acquisition and processing unit and a mapping relationship establishment unit; The data acquisition and processing unit obtains user data and interactive design element information from the database, extracts keywords and converts the format of these data, and generates a user data set and an interactive design element information set; The mapping relationship establishment unit divides into multiple keyword groups according to the corresponding relationship between the keywords in the user data set and the interactive design element numbers, and establishes the mapping relationship between each keyword group and the elements in the interactive design element information set.

8. A user data management system based on data analysis according to claim 6, 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 interactive design element information according to the mapping relationship between the keyword group and the interactive design element information, so as to generate the improvement direction of the interactive design element; The user classification unit summarizes the improvement directions of users for each interactive design element, performs semantic analysis and format conversion to generate an improvement direction vector; by calculating the similarity between the user improvement direction vectors, the users are classified according to the similarity based on the Euclidean distance.

9. The user data management system based on data analysis according to claim 6, wherein: The key improvement direction screening module includes an improvement direction vector summarization unit and a key improvement direction marking unit; The improvement direction vector summarization unit summarizes the corresponding improvement direction vectors for each category of users of each interactive design element to form an improvement direction vector set; the key improvement direction marking unit calculates the intersection of the characteristic dimensions of the improvement direction vectors of different users for each category of improvement direction vector sets to obtain an intersection set; the elements in the intersection set are marked as the key improvement directions of the interactive design elements of the corresponding category.

10. A user data management system based on data analysis according to claim 6, characterized in that: The user feedback evaluation and recognition module includes a key improvement direction analysis unit and a user feedback analysis and recognition unit; The key improvement direction analysis unit analyzes the correlation between the key improvement directions of different categories, and obtains several groups of interactive design elements according to the correlation analysis results; The user feedback analysis and recognition unit collects the user feedback data of each group of interactive design elements, and evaluates the user satisfaction of each group of interactive design elements according to the user feedback data, so as to obtain the target group of interactive design elements.

Images