A Dynamic Design Method and System for Interactive Interfaces Based on Feature Analysis

Abstract

This invention discloses a dynamic design method and system for interactive interfaces based on feature analysis. The method involves collecting user interface interaction data and user commands through a pre-set network, combining this data with a semantic analysis model to analyze user behavior semantics and user operation features, generating behavior tags and converting them into word vector sets. Further, the word vector sets are transformed into feature matrices, and user behavior features are clustered using a density clustering algorithm. Based on the generated feature clusters, the interface and command priorities are dynamically set according to user interaction data, generating a user interaction behavior feature table. The user terminal interface is then dynamically set based on this feature table, enabling periodic updates to the user terminal interactive interface and effectively improving user interaction efficiency and experience.

Description

Technical Field

[0001] This invention relates to the field of interactive data analysis, and more specifically, to a method and system for dynamic design of interactive interfaces based on feature analysis. Background Technology

[0002] With the rapid development of information technology, user interface design has become increasingly important, especially for platform terminals with high efficiency requirements, such as warehousing and logistics terminals and sales terminals. Traditional interface design methods often rely on default settings, which cannot effectively adapt to different user needs and work requirements. Furthermore, traditional interactive platforms are often based on one-sided interaction data analysis, making it difficult to comprehensively analyze user interaction characteristics and dynamically analyze and set the interface to adapt to the needs of different users or user groups, lacking in-depth analysis and understanding of user behavior.

[0003] Therefore, accurately capturing and analyzing user behavior characteristics, and then dynamically adjusting the user interface, has become an urgent problem to be solved. This invention proposes a feature analysis-based dynamic interface design method, aiming to achieve intelligent dynamic design of the user interface through in-depth analysis and understanding of user behavior characteristics. Summary of the Invention

[0004] This invention overcomes the shortcomings of the prior art and proposes a dynamic design method and system for interactive interfaces based on feature analysis.

[0005] The first aspect of this invention provides a dynamic design method for interactive interfaces based on feature analysis, comprising:

[0006] Within a preset period, a preset network connection is set for the platform terminal and the user terminal, and user interaction data and user interaction commands are collected through the platform terminal.

[0007] By performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction commands respectively, first behavior labels and second behavior labels based on text format are generated.

[0008] Using the GloVe semantic model, a co-occurrence matrix is ​​set based on a preset behavior tag library. Semantic feature analysis is performed on the first behavior tag and the second behavior tag. The first behavior tag and the second behavior tag are then transformed into word vectors to generate a first word vector set and a second word vector set.

[0009] The first word vector set and the second word vector set are transformed into the first feature matrix and the second feature matrix. The first feature matrix and the second feature matrix of each user are used as clustering sample data. The user's behavioral feature clustering analysis is performed by density clustering algorithm, and multiple feature clustering groups are obtained.

[0010] For a feature cluster, obtain all interface interaction data and interaction commands of the corresponding user, mark them as current interaction data and current interaction commands, dynamically set the interface priority and command priority according to the current interaction data, generate a user interaction behavior feature table, and dynamically set the user terminal interface according to the user interaction behavior feature table.

[0011] In this solution, setting a preset network connection between the platform terminal and the user terminal within a preset period, and collecting user interface interaction data and user interaction commands through the platform terminal, specifically includes:

[0012] Within a preset period, a preset dedicated network connection is set up for the platform terminal and the user terminal based on a preset network protocol;

[0013] The platform terminal collects user interface interaction data and user interaction commands.

[0014] Perform data cleaning and preprocessing on user interface interaction data.

[0015] In this solution, the step of performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction commands respectively to generate a first behavior label and a second behavior label based on text format is as follows:

[0016] By analyzing user interface interaction data, behavioral semantics of interface operations are performed, and the first behavioral label is selected by combining it with preset interface behavior label data.

[0017] By analyzing user interaction commands and combining them with preset command behavior label data, a second behavior label is selected.

[0018] In this solution, the first step involves using the GloVe semantic model, setting a co-occurrence matrix based on a preset behavior tag library, performing semantic feature analysis on the first and second behavior tags, and then converting the first and second behavior tags into word vectors to generate a first word vector set and a second word vector set. Specifically:

[0019] Using the GloVe semantic model, text format standardization and contextual word statistics are performed on the pre-defined behavior tag library to calculate the co-occurrence frequency of each word and generate a co-occurrence matrix.

[0020] The first row of labels and the second row of labels are converted into a first word set and a second word set, respectively, and then imported into the GloVe semantic model for word vector conversion, generating a first word vector set and a second word vector set.

[0021] In this scheme, the first word vector set and the second word vector set are transformed into a first feature matrix and a second feature matrix. The first feature matrix and the second feature matrix of each user are used as clustering sample data. A density clustering algorithm is used to perform behavioral feature clustering analysis on the users, resulting in multiple feature cluster groups. Specifically:

[0022] Based on the first word vector set, a first feature matrix is ​​constructed with word vector type as the first dimension and word vector value as the second dimension.

[0023] Word vector types are defined using the GloVe semantic model;

[0024] Analyze the second word vector set and construct the second feature matrix;

[0025] The first feature matrix and the second feature matrix of each user are analyzed, and the corresponding first feature value and second feature value are calculated based on the first feature matrix and the second feature matrix;

[0026] The first and second feature matrices of each user are used as clustering sample data. Users are used as clustering units. Based on the DBSCAN clustering algorithm, behavioral feature clustering analysis is performed on users. The similarity between clustering units is analyzed by the weighted average of the first and second feature values, and finally multiple feature clustering groups are formed.

[0027] In this solution, for a feature cluster group, all interface interaction data and interaction commands of the corresponding user are obtained and marked as current interaction data and current interaction commands. Interface priority and command priority are dynamically set based on the current interaction data and current interaction commands to generate a user interaction behavior feature table. The user terminal interface is then dynamically set based on the user interaction behavior feature table. Specifically:

[0028] Select a feature cluster group, filter and label the interface interaction data and interaction commands of all users in the group, and obtain the current interaction data and current interaction commands;

[0029] By analyzing the current interaction data and current interaction commands, the first behavior label and second behavior label of users in the group are analyzed, the interface priority and command priority are dynamically set, and a user interaction behavior feature table is generated.

[0030] The user interaction behavior characteristic table includes an interface priority table and an instruction priority table;

[0031] By using a user interaction behavior characteristic table, the user terminal interface is dynamically set and matched with interface commands to configure the user terminal interface.

[0032] In this solution, the platform terminal performs data collection and processing based on a cloud computing platform.

[0033] In this solution, the user terminal includes a computer terminal and a mobile terminal.

[0034] A second aspect of the present invention also provides a feature-based dynamic interface design system, the system comprising: a memory and a processor, wherein the memory includes a feature-based dynamic interface design program, and the feature-based dynamic interface design program, when executed by the processor, performs the following steps:

[0035] Within a preset period, a preset network connection is set for the platform terminal and the user terminal, and user interaction data and user interaction commands are collected through the platform terminal.

[0036] By performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction commands respectively, first behavior labels and second behavior labels based on text format are generated.

[0037] Using the GloVe semantic model, a co-occurrence matrix is ​​set based on a preset behavior tag library. Semantic feature analysis is performed on the first behavior tag and the second behavior tag. The first behavior tag and the second behavior tag are then transformed into word vectors to generate a first word vector set and a second word vector set.

[0038] The first word vector set and the second word vector set are transformed into the first feature matrix and the second feature matrix. The first feature matrix and the second feature matrix of each user are used as clustering sample data. The user's behavioral feature clustering analysis is performed by density clustering algorithm, and multiple feature clustering groups are obtained.

[0039] For a feature cluster, obtain all interface interaction data and interaction commands of the corresponding user, mark them as current interaction data and current interaction commands, dynamically set the interface priority and command priority according to the current interaction data, generate a user interaction behavior feature table, and dynamically set the user terminal interface according to the user interaction behavior feature table.

[0040] A third aspect of the present invention also provides a computer-readable storage medium comprising a feature-based dynamic interface design program, wherein when the feature-based dynamic interface design program is executed by a processor, it implements the steps of the feature-based dynamic interface design method as described in any of the preceding claims.

[0041] This invention discloses a dynamic design method and system for interactive interfaces based on feature analysis. The method involves collecting user interface interaction data and user commands through a pre-set network, combining this data with a semantic analysis model to analyze user behavior semantics and user operation features, generating behavior tags and converting them into word vector sets. Further, the word vector sets are transformed into feature matrices, and user behavior features are clustered using a density clustering algorithm. Based on the generated feature clusters, the interface and command priorities are dynamically set according to user interaction data, generating a user interaction behavior feature table. The user terminal interface is then dynamically set based on this feature table, enabling periodic updates to the user terminal interactive interface and effectively improving user interaction efficiency and experience. Attached Figure Description

[0042] Figure 1 A flowchart of a dynamic design method for interactive interfaces based on feature analysis according to the present invention is shown;

[0043] Figure 2 A block diagram of a feature analysis-based dynamic design system for interactive interfaces according to the present invention is shown. Detailed Implementation

[0044] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0045] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0046] Figure 1 A flowchart of a dynamic design method for interactive interfaces based on feature analysis according to the present invention is shown.

[0047] like Figure 1 As shown, the first aspect of the present invention provides a dynamic design method for interactive interfaces based on feature analysis, comprising:

[0048] S102, within a preset period, a preset network connection is set for the platform terminal and the user terminal, and user interaction data and user interaction commands are collected through the platform terminal;

[0049] S104, perform behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction commands respectively, and generate first behavior labels and second behavior labels based on text format;

[0050] S106: Using the GloVe semantic model, based on the preset behavior tag library, a co-occurrence matrix is ​​set, semantic feature analysis is performed on the first behavior tag and the second behavior tag, and word vectors are transformed from the first behavior tag and the second behavior tag to generate the first word vector set and the second word vector set.

[0051] S108, the first word vector set and the second word vector set are transformed into the first feature matrix and the second feature matrix. The first feature matrix and the second feature matrix of each user are used as clustering sample data. The user's behavioral feature clustering analysis is performed by density clustering algorithm, and multiple feature clustering groups are obtained.

[0052] S110: For a feature clustering group, obtain all interface interaction data and interaction commands of the corresponding user, mark them as current interaction data and current interaction commands, dynamically set the interface priority and command priority according to the current interaction data, generate a user interaction behavior feature table, and dynamically set the user terminal interface according to the user interaction behavior feature table.

[0053] It should be noted that the semantic model analysis of user characteristics in this invention is based on two aspects: interaction data and instruction data. Traditional methods often rely on one-sided interaction data analysis, which makes it difficult to comprehensively analyze user interaction characteristics and dynamically analyze and set interfaces to adapt to different users. However, this invention effectively improves the analysis and clustering efficiency of behavioral features by transforming behavioral features and analyzing them in matrix form. This provides an efficient data processing method for dynamically setting interfaces, which helps to improve the efficiency of dynamically setting interfaces and enhance user experience.

[0054] According to an embodiment of the present invention, the step of setting a preset network connection between the platform terminal and the user terminal within a preset period, and collecting user interface interaction data and user interaction commands through the platform terminal, specifically includes:

[0055] Within a preset period, a preset dedicated network connection is set up for the platform terminal and the user terminal based on a preset network protocol;

[0056] The platform terminal collects user interface interaction data and user interaction commands.

[0057] Perform data cleaning and preprocessing on user interface interaction data.

[0058] It should be noted that the platform terminal and user terminal can be in fields such as logistics warehousing, education platforms, and commercial product display.

[0059] According to an embodiment of the present invention, the step of performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction commands respectively to generate a first behavior label and a second behavior label based on text format specifically includes:

[0060] By analyzing user interface interaction data, behavioral semantics of interface operations are performed, and the first behavioral label is selected by combining it with preset interface behavior label data.

[0061] By analyzing user interaction commands and combining them with preset command behavior label data, a second behavior label is selected.

[0062] It should be noted that the preset interface behavior tag data includes a variety of pre-defined interface operation behavior tags, such as user clicks, browsing, entering first-level and second-level interfaces, querying, data import / export, etc., within the interactive interface. These behavior tags can be used for semantic analysis and behavior inference. The preset command behavior tag data includes different command pattern tag information.

[0063] According to an embodiment of the present invention, the step of using the GloVe semantic model, setting a co-occurrence matrix based on a preset behavior tag library, performing semantic feature analysis on the first behavior tag and the second behavior tag, and converting the first behavior tag and the second behavior tag into word vectors to generate a first word vector set and a second word vector set, specifically involves:

[0064] Using the GloVe semantic model, text format standardization and contextual word statistics are performed on the pre-defined behavior tag library to calculate the co-occurrence frequency of each word and generate a co-occurrence matrix.

[0065] The first row of labels and the second row of labels are converted into a first word set and a second word set, respectively, and then imported into the GloVe semantic model for word vector conversion, generating a first word vector set and a second word vector set.

[0066] It should be noted that the preset behavior tag library can be an integrated text data of preset interface behavior tag data and preset instruction behavior tag data, which is used as context for semantic model training.

[0067] According to an embodiment of the present invention, the step of converting the first word vector set and the second word vector set into a first feature matrix and a second feature matrix, using the first feature matrix and the second feature matrix of each user as clustering sample data, performing behavioral feature clustering analysis on users through a density clustering algorithm, and obtaining multiple feature clustering groups, specifically includes:

[0068] Based on the first word vector set, a first feature matrix is ​​constructed with word vector type as the first dimension and word vector value as the second dimension.

[0069] Word vector types are defined using the GloVe semantic model;

[0070] Analyze the second word vector set and construct the second feature matrix;

[0071] The first feature matrix and the second feature matrix of each user are analyzed, and the corresponding first feature value and second feature value are calculated based on the first feature matrix and the second feature matrix;

[0072] The first and second feature matrices of each user are used as clustering sample data. Users are used as clustering units. Based on the DBSCAN clustering algorithm, behavioral feature clustering analysis is performed on users. The similarity between clustering units is analyzed by the weighted average of the first and second feature values, and finally multiple feature clustering groups are formed.

[0073] It should be noted that the similarity between cluster units is analyzed by the weighted average of the first and second eigenvalues. Specifically, the first and second eigenvalue matrices corresponding to a user are calculated, and the eigenvalues ​​of the two matrices are obtained, namely the first eigenvalue and the second eigenvalue. The two eigenvalues ​​are then weighted and averaged to obtain the eigenvalue mean. The similarity between cluster sample data of users is measured by the difference in the eigenvalue mean corresponding to each cluster unit.

[0074] According to an embodiment of the present invention, for a feature clustering group, all interface interaction data and interaction commands of the corresponding user are obtained and marked as current interaction data and current interaction commands. Interface priority and command priority are dynamically set according to the current interaction data and current interaction commands to generate a user interaction behavior feature table. The user terminal interface is then dynamically set according to the user interaction behavior feature table. Specifically, the steps are as follows:

[0075] Select a feature cluster group, filter and label the interface interaction data and interaction commands of all users in the group, and obtain the current interaction data and current interaction commands;

[0076] By analyzing the current interaction data and current interaction commands, the first behavior label and second behavior label of users in the group are analyzed, the interface priority and command priority are dynamically set, and a user interaction behavior feature table is generated.

[0077] The user interaction behavior characteristic table includes an interface priority table and an instruction priority table;

[0078] By using a user interaction behavior characteristic table, the user terminal interface is dynamically set and matched with interface commands to configure the user terminal interface.

[0079] It should be noted that the interface priority table includes display priority and processing priority information for each level of interface and various types of interfaces, while the instruction priority table includes priority information for different operation instructions.

[0080] According to an embodiment of the present invention, the platform terminal performs data acquisition and data processing based on a cloud computing platform.

[0081] It should be noted that the platform terminal can be placed on a cloud computing platform for data processing, thereby reducing the data processing pressure on user terminals.

[0082] According to an embodiment of the present invention, the user terminal includes a computer terminal and a mobile terminal.

[0083] According to an embodiment of the present invention, the step of performing behavioral feature clustering analysis on users using a density clustering algorithm to obtain multiple feature cluster groups further includes:

[0084] Construct a matrix comparison model;

[0085] Two users are defined and labeled as user 1 and user 2. The first feature matrix and the second feature matrix corresponding to user 1 are labeled as feature matrix A and feature matrix B, respectively.

[0086] The first and second feature matrices corresponding to the second user are labeled as feature matrix A' and feature matrix B', respectively.

[0087] Calculate the eigenvectors of A and A', and label them as the first eigenvector and the second eigenvector, respectively.

[0088] In the matrix comparison model, based on PCA analysis, a low-dimensional vector space is constructed, and the first eigenvector and the second eigenvector are spatially mapped through the low-dimensional vector space to generate the first reconstructed eigenvector and the second reconstructed eigenvector.

[0089] D1 is obtained by calculating the distance between the first reconstructed feature vector and the second reconstructed feature vector using standard Euclidean distance.

[0090] The eigenvectors of B and B' are calculated, and the difference between the eigenvectors is analyzed using PCA to obtain the distance value D2 between the eigenvectors.

[0091] The first difference value is obtained by taking a weighted average of D1 and D2;

[0092] Calculate the weighted average of the first feature value and the second feature value of the first user to obtain the first feature mean;

[0093] Calculate the feature mean of the second user and label it as the second feature mean;

[0094] The second difference value is obtained by taking a weighted average of the mean of the first feature and the mean of the second feature;

[0095] The similarity of the feature matrices of two users is evaluated by using the first difference value and the second difference value, and a comparative similarity score is generated.

[0096] It should be noted that the analysis process for D1 and D2 is consistent. Besides difference analysis using the weighted average of the first and second eigenvalues, similarity analysis between cluster units can also be performed based on a matrix comparison model. It's worth mentioning that while this method works well for small-scale user platforms, it can lead to low discrimination for large-scale user platforms, resulting in many users clustered together in a single feature group. Furthermore, the user interaction characteristics within certain feature groups require further analysis and differentiation to refine different dynamic interface settings. Therefore, based on these issues, the matrix comparison model of this invention can be used to refine and compare cluster sample data, effectively improving the discrimination of different user interaction characteristics and enhancing the application scenarios of large-scale user interaction terminals.

[0097] The matrix comparison model uses PCA analysis to simplify and compare the eigenvectors of the feature matrix, and performs difference analysis of the matrix through two dimensions: eigenvectors and eigenvalues, which effectively improves the difference analysis effect of the feature matrix.

[0098] The formula for calculating similarity is as follows:

[0099] ;

[0100] Where P represents the comparison similarity, and K is the correction coefficient. The first difference value, This is the second difference value.

[0101] According to an embodiment of the present invention, it further includes:

[0102] Obtain real-time user interaction data within the current preset time period, perform behavioral feature analysis on real-time users based on the real-time user interaction data, and generate a first feature matrix and a second feature matrix by combining the GloVe semantic model;

[0103] Within a current preset time period, obtain the feature clustering results from the previous preset time period;

[0104] Based on the feature clustering results, obtain the feature clustering group to which the real-time user belongs, randomly select a current user from the feature clustering group, and obtain the corresponding first feature matrix and second feature matrix;

[0105] Calculate the similarity between the feature matrices of the current user and the real-time user. If the corresponding similarity range is within the preset range, then use the user terminal interface set in the previous preset time period.

[0106] If the corresponding similarity range is not within the preset range, the user's first feature matrix and second feature matrix are regenerated based on the user's real-time interaction data, and the user is then subjected to secondary clustering and grouping. The user interaction behavior feature table is dynamically updated, and the user terminal interface is dynamically updated.

[0107] It should be noted that the similarity between the feature matrices of the current user and the real-time user can be obtained through the weighted mean difference analysis method of the first and second eigenvalues ​​for the similarity between clustering units in this embodiment, or it can be evaluated based on a matrix comparison model or other matrix similarity analysis methods. Real-time user interaction data includes real-time interface interaction data and real-time interaction commands.

[0108] Figure 2 A block diagram of a feature analysis-based dynamic design system for interactive interfaces according to the present invention is shown.

[0109] A second aspect of the present invention also provides a feature-based dynamic interface design system 2, the system comprising: a memory 21 and a processor 22, wherein the memory 21 includes a feature-based dynamic interface design program, and the feature-based dynamic interface design program, when executed by the processor 22, performs the following steps:

[0110] Within a preset period, a preset network connection is set for the platform terminal and the user terminal, and user interaction data and user interaction commands are collected through the platform terminal.

[0111] By performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction commands respectively, first behavior labels and second behavior labels based on text format are generated.

[0112] Using the GloVe semantic model, a co-occurrence matrix is ​​set based on a preset behavior tag library. Semantic feature analysis is performed on the first behavior tag and the second behavior tag. The first behavior tag and the second behavior tag are then transformed into word vectors to generate a first word vector set and a second word vector set.

[0113] The first word vector set and the second word vector set are transformed into the first feature matrix and the second feature matrix. The first feature matrix and the second feature matrix of each user are used as clustering sample data. The user's behavioral feature clustering analysis is performed by density clustering algorithm, and multiple feature clustering groups are obtained.

[0114] For a feature cluster, obtain all interface interaction data and interaction commands of the corresponding user, mark them as current interaction data and current interaction commands, dynamically set the interface priority and command priority according to the current interaction data, generate a user interaction behavior feature table, and dynamically set the user terminal interface according to the user interaction behavior feature table.

[0115] It should be noted that the semantic model analysis of user characteristics in this invention is based on two aspects: interaction data and instruction data. Traditional methods often rely on one-sided interaction data analysis, which makes it difficult to comprehensively analyze user interaction characteristics and dynamically analyze and set interfaces to adapt to different users. However, this invention effectively improves the analysis and clustering efficiency of behavioral features by transforming behavioral features and analyzing them in matrix form. This provides an efficient data processing method for dynamically setting interfaces, which helps to improve the efficiency of dynamically setting interfaces and enhance user experience.

[0116] According to an embodiment of the present invention, the step of setting a preset network connection between the platform terminal and the user terminal within a preset period, and collecting user interface interaction data and user interaction commands through the platform terminal, specifically includes:

[0117] Within a preset period, a preset dedicated network connection is set up for the platform terminal and the user terminal based on a preset network protocol;

[0118] The platform terminal collects user interface interaction data and user interaction commands.

[0119] Perform data cleaning and preprocessing on user interface interaction data.

[0120] It should be noted that the platform terminal and user terminal can be in fields such as logistics warehousing, education platforms, and commercial product display.

[0121] According to an embodiment of the present invention, the step of performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction commands respectively to generate a first behavior label and a second behavior label based on text format specifically includes:

[0122] By analyzing user interface interaction data, behavioral semantics of interface operations are performed, and the first behavioral label is selected by combining it with preset interface behavior label data.

[0123] By analyzing user interaction commands and combining them with preset command behavior label data, a second behavior label is selected.

[0124] It should be noted that the preset interface behavior tag data includes a variety of pre-defined interface operation behavior tags, such as user clicks, browsing, entering first-level and second-level interfaces, querying, data import / export, etc., within the interactive interface. These behavior tags can be used for semantic analysis and behavior inference. The preset command behavior tag data includes different command pattern tag information.

[0125] According to an embodiment of the present invention, the step of using the GloVe semantic model, setting a co-occurrence matrix based on a preset behavior tag library, performing semantic feature analysis on the first behavior tag and the second behavior tag, and converting the first behavior tag and the second behavior tag into word vectors to generate a first word vector set and a second word vector set, specifically involves:

[0126] Using the GloVe semantic model, text format standardization and contextual word statistics are performed on the pre-defined behavior tag library to calculate the co-occurrence frequency of each word and generate a co-occurrence matrix.

[0127] The first row of labels and the second row of labels are converted into a first word set and a second word set, respectively, and then imported into the GloVe semantic model for word vector conversion, generating a first word vector set and a second word vector set.

[0128] It should be noted that the preset behavior tag library can be an integrated text data of preset interface behavior tag data and preset instruction behavior tag data, which is used as context for semantic model training.

[0129] According to an embodiment of the present invention, the step of converting the first word vector set and the second word vector set into a first feature matrix and a second feature matrix, using the first feature matrix and the second feature matrix of each user as clustering sample data, performing behavioral feature clustering analysis on users through a density clustering algorithm, and obtaining multiple feature clustering groups, specifically includes:

[0130] Based on the first word vector set, a first feature matrix is ​​constructed with word vector type as the first dimension and word vector value as the second dimension.

[0131] Word vector types are defined using the GloVe semantic model;

[0132] Analyze the second word vector set and construct the second feature matrix;

[0133] The first feature matrix and the second feature matrix of each user are analyzed, and the corresponding first feature value and second feature value are calculated based on the first feature matrix and the second feature matrix;

[0134] The first and second feature matrices of each user are used as clustering sample data. Users are used as clustering units. Based on the DBSCAN clustering algorithm, behavioral feature clustering analysis is performed on users. The similarity between clustering units is analyzed by the weighted average of the first and second feature values, and finally multiple feature clustering groups are formed.

[0135] It should be noted that the similarity between cluster units is analyzed by the weighted average of the first and second eigenvalues. Specifically, the first and second eigenvalue matrices corresponding to a user are calculated, and the eigenvalues ​​of the two matrices are obtained, namely the first eigenvalue and the second eigenvalue. The two eigenvalues ​​are then weighted and averaged to obtain the eigenvalue mean. The similarity between cluster sample data of users is measured by the difference in the eigenvalue mean corresponding to each cluster unit.

[0136] According to an embodiment of the present invention, for a feature clustering group, all interface interaction data and interaction commands of the corresponding user are obtained and marked as current interaction data and current interaction commands. Interface priority and command priority are dynamically set according to the current interaction data and current interaction commands to generate a user interaction behavior feature table. The user terminal interface is then dynamically set according to the user interaction behavior feature table. Specifically, the steps are as follows:

[0137] Select a feature cluster group, filter and label the interface interaction data and interaction commands of all users in the group, and obtain the current interaction data and current interaction commands;

[0138] By analyzing the current interaction data and current interaction commands, the first behavior label and second behavior label of users in the group are analyzed, the interface priority and command priority are dynamically set, and a user interaction behavior feature table is generated.

[0139] The user interaction behavior characteristic table includes an interface priority table and an instruction priority table;

[0140] By using a user interaction behavior characteristic table, the user terminal interface is dynamically set and matched with interface commands to configure the user terminal interface.

[0141] It should be noted that the interface priority table includes display priority and processing priority information for each level of interface and various types of interfaces, while the instruction priority table includes priority information for different operation instructions.

[0142] According to an embodiment of the present invention, the platform terminal performs data acquisition and data processing based on a cloud computing platform.

[0143] It should be noted that the platform terminal can be placed on a cloud computing platform for data processing, thereby reducing the data processing pressure on user terminals.

[0144] According to an embodiment of the present invention, the user terminal includes a computer terminal and a mobile terminal.

[0145] A third aspect of the present invention also provides a computer-readable storage medium comprising a feature-based dynamic interface design program, wherein when the feature-based dynamic interface design program is executed by a processor, it implements the steps of the feature-based dynamic interface design method as described in any of the preceding claims.

[0146] This invention discloses a dynamic design method and system for interactive interfaces based on feature analysis. The method involves collecting user interface interaction data and user commands through a pre-set network, combining this data with a semantic analysis model to analyze user behavior semantics and user operation features, generating behavior tags and converting them into word vector sets. Further, the word vector sets are transformed into feature matrices, and user behavior features are clustered using a density clustering algorithm. Based on the generated feature clusters, the interface and command priorities are dynamically set according to user interaction data, generating a user interaction behavior feature table. The user terminal interface is then dynamically set based on this feature table, enabling periodic updates to the user terminal interactive interface and effectively improving user interaction efficiency and experience.

[0147] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0148] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0149] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0150] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0151] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0152] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A dynamic design method for interactive interfaces based on feature analysis, characterized in that, include: Within a preset period, a preset network connection is set for the platform terminal and the user terminal, and user interaction data and user interaction commands are collected through the platform terminal. By performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction commands respectively, first behavior labels and second behavior labels based on text format are generated. Using the GloVe semantic model, a co-occurrence matrix is ​​set based on a preset behavior tag library. Semantic feature analysis is performed on the first behavior tag and the second behavior tag. The first behavior tag and the second behavior tag are then transformed into word vectors to generate a first word vector set and a second word vector set. Specifically: By analyzing user interface interaction data, behavioral semantics of interface operations are performed, and the first behavioral label is selected by combining it with preset interface behavior label data. User interaction commands are analyzed to identify user operation characteristics, and second behavior tags are selected by combining preset command behavior tag data. Using the GloVe semantic model, text format standardization and contextual word statistics are performed on the pre-defined behavior tag library to calculate the co-occurrence frequency of each word and generate a co-occurrence matrix. The first row of labels and the second row of labels are converted into a first word set and a second word set, respectively, and then imported into the GloVe semantic model for word vector conversion, generating a first word vector set and a second word vector set; The first word vector set and the second word vector set are transformed into the first feature matrix and the second feature matrix. The first feature matrix and the second feature matrix of each user are used as clustering sample data. The user's behavioral feature clustering analysis is performed by density clustering algorithm, and multiple feature clustering groups are obtained. For a feature clustering group, obtain all interface interaction data and interaction commands of the corresponding user, mark them as current interaction data and current interaction commands, dynamically set the interface priority and command priority according to the current interaction data, generate a user interaction behavior feature table, and dynamically set the user terminal interface according to the user interaction behavior feature table. Specifically, the process involves transforming the first word vector set and the second word vector set into a first feature matrix and a second feature matrix, using the first feature matrix and the second feature matrix of each user as clustering sample data, and performing behavioral feature clustering analysis on users using a density clustering algorithm to obtain multiple feature cluster groups. Based on the first word vector set, a first feature matrix is ​​constructed with word vector type as the first dimension and word vector value as the second dimension. Word vector types are defined using the GloVe semantic model; Analyze the second word vector set and construct the second feature matrix; The first feature matrix and the second feature matrix of each user are analyzed, and the corresponding first feature value and second feature value are calculated based on the first feature matrix and the second feature matrix; The first and second feature matrices of each user are used as clustering sample data. Users are used as clustering units. Based on the DBSCAN clustering algorithm, behavioral feature clustering analysis is performed on users. The similarity between clustering units is analyzed by the weighted average of the first and second feature values, and finally multiple feature clustering groups are formed. Specifically, for a feature clustering group, all interface interaction data and interaction commands of the corresponding user are obtained and marked as current interaction data and current interaction commands. Interface priority and command priority are dynamically set based on the current interaction data and current interaction commands to generate a user interaction behavior feature table. The user terminal interface is then dynamically set based on the user interaction behavior feature table. Select a feature cluster group, filter and label the interface interaction data and interaction commands of all users in the group, and obtain the current interaction data and current interaction commands; By analyzing the current interaction data and current interaction commands, the first behavior label and second behavior label of users in the group are analyzed, the interface priority and command priority are dynamically set, and a user interaction behavior feature table is generated. The user interaction behavior characteristic table includes an interface priority table and an instruction priority table; By using a user interaction behavior characteristic table, the user terminal interface is dynamically set and matched with interface commands to configure the user terminal interface.

2. The interactive interface dynamic design method based on feature analysis according to claim 1, characterized in that, Within a preset period, a preset network connection is established between the platform terminal and the user terminal, and user interface interaction data and user interaction commands are collected through the platform terminal. Specifically: Within a preset period, a preset dedicated network connection is set up for the platform terminal and the user terminal based on a preset network protocol; The platform terminal collects user interface interaction data and user interaction commands. Perform data cleaning and preprocessing on user interface interaction data.

3. The interactive interface dynamic design method based on feature analysis according to claim 1, characterized in that, The platform terminal performs data collection and processing based on a cloud computing platform.

4. The interactive interface dynamic design method based on feature analysis according to claim 1, characterized in that, The user terminal includes computer terminals and mobile terminals.

5. A dynamic design system for interactive interfaces based on feature analysis, characterized in that, The system includes: a memory and a processor. The memory includes a feature-based dynamic interface design program. When the feature-based dynamic interface design program is executed by the processor, it implements the steps of the feature-based dynamic interface design method as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a feature-based dynamic interface design program, which, when executed by a processor, implements the steps of the feature-based dynamic interface design method as described in any one of claims 1 to 4.

Images