Interactive interface dynamic design method and system based on feature analysis

Abstract

The invention discloses an interactive interface dynamic design method and system based on feature analysis. The invention provides an interactive interface dynamic design method based on feature analysis, which comprises the following steps of: collecting user interface interaction data and a user instruction through a preset network, analyzing behavior semantics and user operation features of a user in combination with a semantic analysis model, generating a behavior tag and converting the behavior tag into a word vector set; furthermore, the word vector set is converted into a feature matrix, behavior feature clustering is performed on the user through a density clustering algorithm, a user interaction behavior feature table is generated based on a generated feature clustering group according to a user interaction data dynamic setting interface and instruction priority, and a user terminal interface is dynamically set according to the feature table. The user side interaction interface is periodically updated, and the user interaction efficiency and experience are effectively improved.

Description

Technical Field

[0001] The present 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 Art

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

[0003] Therefore, how to accurately capture and analyze user behavior characteristics and then dynamically adjust the user interface has become an urgent problem to be solved. The present invention proposes a dynamic design method of interactive interface based on feature analysis, aiming to realize intelligent dynamic design of user interface through in-depth analysis and understanding of user behavior characteristics. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and proposes a method and system for dynamic design of interactive interface based on feature analysis.

[0005] The first aspect of the present invention provides a method for dynamic design of interactive interface based on feature analysis, comprising: Within a preset period, a preset network connection is set between the platform terminal and the user terminal, and user interface interaction data and user interaction instructions are collected through the platform terminal; Through the user interface interaction data and the user interaction instructions, behavior semantic analysis and user operation feature analysis are performed respectively to generate a first behavior label and a second behavior label based on a text format; Through 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, and the first behavior tag and the second behavior tag are converted into word vectors to generate a first word vector set and a second word vector set; The first word vector set and the second word vector set are converted 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, and the user's behavior feature clustering analysis is performed through a density clustering algorithm to obtain multiple feature clustering groups; For a feature clustering group, obtain all interface interaction data and interaction instructions of the corresponding user, mark them as current interaction data and current interaction instructions, dynamically set interface priority and instruction 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.

[0006] In this solution, within a preset period, a preset network connection is set between the platform terminal and the user terminal, and user interface interaction data and user interaction instructions are collected through the platform terminal, specifically: Within a preset period, based on a preset network protocol, a preset dedicated network connection is set between the platform terminal and the user terminal; Collect user interface interaction data and user interaction instructions through platform terminals; Perform data cleaning preprocessing on user interface interaction data.

[0007] In this solution, the user interface interaction data and the user interaction instructions are respectively subjected to behavior semantic analysis and user operation feature analysis to generate a first behavior label and a second behavior label based on a text format, specifically: Through the user interface interaction data, the behavior semantic analysis of the interface operation is performed, and the first behavior label is screened out in combination with the preset interface behavior label data; The user operation characteristics are analyzed through the user interaction instructions, and the second behavior label is screened out by combining the preset instruction behavior label data.

[0008] In this solution, the GloVe semantic model is used to set the co-occurrence matrix based on the preset behavior tag library, the semantic feature analysis is performed on the first behavior tag and the second behavior tag, and the first behavior tag and the second behavior tag are converted into word vectors to generate the first word vector set and the second word vector set, specifically: Through the GloVe semantic model, the text format of the preset behavior tag library is standardized and the word statistics of the context are performed, the co-occurrence frequency of each word is calculated, and the co-occurrence matrix is ​​generated; The first behavior label and the second behavior label are converted into a first word set and a second word set and imported into the GloVe semantic model for word vector conversion to generate a first word vector set and a second word vector set respectively.

[0009] In this solution, the first word vector set and the second word vector set are converted into the first feature matrix and the second feature matrix, and the first feature matrix and the second feature matrix of each user are used as clustering sample data. The user's behavior feature clustering analysis is performed through the density clustering algorithm, and multiple feature clustering groups are obtained, specifically: According to the first word vector set, a first feature matrix is ​​constructed with the word vector type as the first dimension data and the word vector value as the second dimension data; The word vector type is defined by the GloVe semantic model; Analyze the second word vector set and construct a second feature matrix; Analyze the first characteristic matrix and the second characteristic matrix of each user, and calculate the corresponding first eigenvalue and second eigenvalue based on the first characteristic matrix and the second characteristic matrix; The first feature matrix and the second feature matrix of each user are used as clustering sample data, and the user is used as the clustering unit. The user's behavioral characteristics are clustered and analyzed based on the DBSCAN clustering algorithm. The similarity between clustering units is analyzed by the weighted mean of the first eigenvalue and the second eigenvalue, and finally multiple feature clustering groups are formed.

[0010] In this solution, for a feature clustering group, all interface interaction data and interaction instructions of the corresponding user are obtained, marked as current interaction data and current interaction instructions, the interface priority and instruction priority are dynamically set according to the current interaction data and current interaction instructions, a user interaction behavior feature table is generated, and the user terminal interface is dynamically set according to the user interaction behavior feature table, specifically: Select a feature clustering group, filter and mark the interface interaction data and interaction instructions of all users in the group, and obtain the current interaction data and current interaction instructions; Analyze the first behavior label and the second behavior label of the users in the group through the current interaction data and the current interaction instruction, dynamically set the interface priority and the instruction priority, and generate a user interaction behavior feature table; The user interaction behavior feature table includes an interface priority table and an instruction priority table; Through the user interaction behavior feature table, the user terminal interface is dynamically set and dynamically matched with the interface instructions to set the user terminal interface.

[0011] In this solution, the platform terminal performs data collection and data processing based on the cloud computing platform.

[0012] In this solution, the user terminal includes a computer terminal and a mobile terminal.

[0013] The second aspect of the present invention further provides a dynamic design system for an interactive interface based on feature analysis, the system comprising: a memory and a processor, the memory comprising a dynamic design program for an interactive interface based on feature analysis, the dynamic design program for an interactive interface based on feature analysis being executed by the processor to implement the following steps: Within a preset period, a preset network connection is set between the platform terminal and the user terminal, and user interface interaction data and user interaction instructions are collected through the platform terminal; Through the user interface interaction data and the user interaction instructions, behavior semantic analysis and user operation feature analysis are performed respectively to generate a first behavior label and a second behavior label based on a text format; Through 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, and the first behavior tag and the second behavior tag are converted into word vectors to generate a first word vector set and a second word vector set; The first word vector set and the second word vector set are converted 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, and the user's behavior feature clustering analysis is performed through a density clustering algorithm to obtain multiple feature clustering groups; For a feature clustering group, obtain all interface interaction data and interaction instructions of the corresponding user, mark them as current interaction data and current interaction instructions, dynamically set interface priority and instruction 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.

[0014] The third aspect of the present invention also provides a computer-readable storage medium, which includes a dynamic design program for an interactive interface based on feature analysis. When the dynamic design program for an interactive interface based on feature analysis is executed by a processor, the steps of the dynamic design method for an interactive interface based on feature analysis as described in any one of the above items are implemented.

[0015] The present invention discloses a method and system for dynamic design of interactive interface based on feature analysis. The present invention proposes a method for dynamic design of interactive interface based on feature analysis, which collects user interface interaction data and user instructions through a preset network, combines with a semantic analysis model, analyzes user behavior semantics and user operation characteristics, generates behavior labels and converts them into word vector sets. Further, the word vector set is converted into a feature matrix, and the user behavior characteristics are clustered by a density clustering algorithm. Based on the generated feature clustering group, the interface and instruction priority are dynamically set according to the user interaction data, a user interaction behavior feature table is generated, and the user terminal interface is dynamically set according to the feature table, so as to realize periodic update of the user terminal interaction interface and effectively improve the user interaction efficiency and experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for dynamic design of an interactive interface based on feature analysis of the present invention is shown; Figure 2 A block diagram of a dynamic design system for an interactive interface based on feature analysis of the present invention is shown. DETAILED DESCRIPTION

[0017] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0019] Figure 1 A flow chart of a method for dynamic design of an interactive interface based on feature analysis of the present invention is shown.

[0020] like Figure 1 As shown, the first aspect of the present invention provides a method for dynamic design of interactive interface based on feature analysis, comprising: S102, within a preset period, setting a preset network connection between the platform terminal and the user terminal, and collecting user interface interaction data and user interaction instructions through the platform terminal; S104, performing behavior semantic analysis and user operation feature analysis on the user interface interaction data and the user interaction instruction, respectively, to generate a first behavior label and a second behavior label in a text format; S106, 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 performing word vector conversion on the first behavior tag and the second behavior tag to generate a first word vector set and a second word vector set; S108, 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 the user through a density clustering algorithm, and obtaining a plurality of feature clustering groups; S110, for a feature clustering group, obtain all interface interaction data and interaction instructions of the corresponding user, mark them as current interaction data and current interaction instructions, dynamically set interface priority and instruction 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.

[0021] It should be noted that the semantic model perspective used in the present invention to analyze user characteristics is based on two aspects, namely, interaction data and command data. The traditional perspective is often based on unilateral interaction data analysis, which makes it difficult to comprehensively analyze the user's interaction characteristics, and it is difficult to dynamically analyze and set the interface to adapt to different users. The present invention converts behavioral characteristics and analyzes them in matrix form to effectively improve the analysis efficiency and clustering efficiency of behavioral characteristics, provides an efficient data processing method for realizing a dynamic setting interface, helps to improve the efficiency of the dynamic setting interface, and improves the user experience.

[0022] According to an embodiment of the present invention, within a preset period, setting a preset network connection between the platform terminal and the user terminal, and collecting user interface interaction data and user interaction instructions through the platform terminal, specifically: Within a preset period, based on a preset network protocol, a preset dedicated network connection is set between the platform terminal and the user terminal; Collect user interface interaction data and user interaction instructions through platform terminals; Perform data cleaning preprocessing on user interface interaction data.

[0023] It should be noted that the platform terminals and user terminals can be in the fields of logistics warehousing, education platform, commercial product display, etc.

[0024] According to an embodiment of the present invention, the user interface interaction data and the user interaction instruction are respectively subjected to behavior semantic analysis and user operation feature analysis to generate a first behavior label and a second behavior label based on a text format, specifically: Through the user interface interaction data, the behavior semantic analysis of the interface operation is performed, and the first behavior label is screened out in combination with the preset interface behavior label data; The user operation characteristics are analyzed through the user interaction instructions, and the second behavior label is screened out by combining the preset instruction behavior label data.

[0025] It should be noted that the preset interface behavior label data includes a plurality of predetermined interface operation behavior labels, such as user clicks, browsing, entering the primary and secondary interfaces, querying, data import and export, etc. in the interactive interface, and the behavior labels can be used for semantic analysis and behavior inference. The preset instruction behavior label data includes different instruction mode label information.

[0026] According to an embodiment of the present invention, the GloVe semantic model is used to set a co-occurrence matrix based on a preset behavior tag library, semantic feature analysis is performed on the first behavior tag and the second behavior tag, and the first behavior tag and the second behavior tag are converted into word vectors to generate a first word vector set and a second word vector set, specifically: Through the GloVe semantic model, the text format of the preset behavior tag library is standardized and the word statistics of the context are performed, the co-occurrence frequency of each word is calculated, and the co-occurrence matrix is ​​generated; The first behavior label and the second behavior label are converted into a first word set and a second word set and imported into the GloVe semantic model for word vector conversion to generate a first word vector set and a second word vector set respectively.

[0027] It should be noted that the preset behavior label library may be integrated text data of preset interface behavior label data and preset instruction behavior label data, which is used as context for semantic model training.

[0028] According to an embodiment of the present invention, the first word vector set and the second word vector set are converted 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, and the user's behavior feature clustering analysis is performed through a density clustering algorithm, and multiple feature clustering groups are obtained, specifically: According to the first word vector set, a first feature matrix is ​​constructed with the word vector type as the first dimension data and the word vector value as the second dimension data; The word vector type is defined by the GloVe semantic model; Analyze the second word vector set and construct a second feature matrix; Analyze the first characteristic matrix and the second characteristic matrix of each user, and calculate the corresponding first eigenvalue and second eigenvalue based on the first characteristic matrix and the second characteristic matrix; The first feature matrix and the second feature matrix of each user are used as clustering sample data, and the user is used as the clustering unit. The user's behavioral characteristics are clustered and analyzed based on the DBSCAN clustering algorithm. The similarity between clustering units is analyzed by the weighted mean of the first eigenvalue and the second eigenvalue, and finally multiple feature clustering groups are formed.

[0029] It should be noted that the similarity between clustering units is analyzed by the weighted mean of the first eigenvalue and the second eigenvalue. Specifically, the first characteristic matrix and the second characteristic matrix corresponding to a certain user are calculated, and two matrix eigenvalues, namely the first eigenvalue and the second eigenvalue, are obtained. The two eigenvalues ​​are weighted averaged to obtain the characteristic mean. The similarity between the clustering sample data between users is measured by the difference in the characteristic mean corresponding to each clustering unit.

[0030] According to an embodiment of the present invention, for a feature clustering group, all interface interaction data and interaction instructions of the corresponding user are obtained, marked as current interaction data and current interaction instructions, the interface priority and instruction priority are dynamically set according to the current interaction data and the current interaction instructions, a user interaction behavior feature table is generated, and the user terminal interface is dynamically set according to the user interaction behavior feature table, specifically: Select a feature clustering group, filter and mark the interface interaction data and interaction instructions of all users in the group, and obtain the current interaction data and current interaction instructions; Analyze the first behavior label and the second behavior label of the users in the group through the current interaction data and the current interaction instruction, dynamically set the interface priority and the instruction priority, and generate a user interaction behavior feature table; The user interaction behavior feature table includes an interface priority table and an instruction priority table; Through the user interaction behavior feature table, the user terminal interface is dynamically set and dynamically matched with the interface instructions to set the user terminal interface.

[0031] It should be noted that the interface priority table includes display priority, processing priority information, etc. of each level of interface and various types of interfaces, and the instruction priority table includes priority information for different operation instructions.

[0032] According to an embodiment of the present invention, the platform terminal performs data collection and data processing based on a cloud computing platform.

[0033] 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 the user terminal.

[0034] According to an embodiment of the present invention, the user terminal includes a computer terminal and a mobile terminal.

[0035] According to an embodiment of the present invention, the method of performing cluster analysis on user behavior characteristics by using a density clustering algorithm and obtaining a plurality of characteristic clustering groups further includes: Construct matrix contrast model; Set two users and mark them as the first user and the second user, and mark the first feature matrix and the second feature matrix corresponding to the first user as feature matrix A and feature matrix B respectively; The first feature matrix and the second feature matrix corresponding to the second user are marked as feature matrix A' and feature matrix B' respectively; Calculate the eigenvectors of A and A' and mark them as the first eigenvector and the second eigenvector respectively; In the matrix comparison model, based on the PCA analysis method, 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 a first reconstructed eigenvector and a second reconstructed eigenvector; Calculate the distance between the first reconstructed feature vector and the second reconstructed feature vector by using the standard Euclidean distance to obtain D1; Calculate the eigenvectors of B and B', and perform a difference analysis of the eigenvectors based on the PCA analysis method to obtain the distance value D2 between the eigenvectors; A first difference value is obtained by weighted averaging D1 and D2; Calculate a weighted average of the first characteristic value and the second characteristic value of the first user to obtain a first characteristic average; Calculate the feature mean of the second user, marked as the second feature mean; Taking a weighted average of the first feature mean and the second feature mean to obtain a second difference value; The similarity of the feature matrices corresponding to the two users is evaluated by using the first difference value and the second difference value, and a comparative similarity is generated.

[0036] It should be noted that the analysis process of D1 and D2 is consistent. In addition to the difference analysis through the weighted mean of the first eigenvalue and the second eigenvalue, the similarity between clustering units can also be analyzed based on the matrix comparison model. It is worth mentioning here that the similarity between clustering units (i.e., the user corresponding feature matrix) can be analyzed based on the eigenvalue of the matrix. This method is better when applied to a small-scale user platform, but it is easy to have a low degree of distinction for large-scale users. It is easy for more users to be set in a feature clustering group, and the user interaction features in certain feature clustering groups need to be further analyzed and distinguished, and different dynamic setting interface schemes need to be refined. Therefore, based on the above problems, the matrix comparison model form of the present invention can be used to refine and compare the clustering sample data, so as to effectively improve the distinction between different user interaction features and improve the application scenarios of large-scale user interaction terminals.

[0037] The matrix comparison model uses the PCA analysis method to simplify and compare the eigenvectors of the feature matrix, and performs matrix difference analysis in two dimensions: eigenvector and eigenvalue, effectively improving the difference analysis effect of the feature matrix; The calculation formula for the comparison similarity is as follows: ; Among them, P is the comparison similarity, K is the correction coefficient, is the first difference value, is the second difference value.

[0038] According to an embodiment of the present invention, it also includes: Obtain the real-time user interaction data within the current preset time period, analyze the behavior characteristics of the real-time users according to the real-time user interaction data, and generate the first feature matrix and the second feature matrix in combination with the GloVe semantic model; In a current preset time period, obtaining the feature clustering results in the previous preset time period; Obtain the feature clustering group to which the real-time user belongs through the feature clustering result, randomly select a current user from the feature clustering group, and obtain the corresponding first feature matrix and second feature matrix; Calculate the similarity between the feature matrix of the current user and the real-time user. If the corresponding similarity range is within the preset range, continue to use the user terminal interface set in the previous preset time period; 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 users are secondary clustered and grouped, the user interaction behavior feature table is dynamically updated, and the user terminal interface is dynamically updated.

[0039] It should be noted that, in calculating the similarity between the feature matrices of the current user and the real-time user, the similarity between the clustering units in this embodiment can be obtained by the weighted mean difference analysis method of the first eigenvalue and the second eigenvalue, or it can be obtained by evaluating based on a matrix comparison model or other matrix similarity analysis methods. User real-time interaction data includes real-time interface interaction data and real-time interaction instructions.

[0040] Figure 2 A block diagram of a dynamic design system for an interactive interface based on feature analysis of the present invention is shown.

[0041] The second aspect of the present invention further provides a dynamic design system 2 for an interactive interface based on feature analysis, the system comprising: a memory 21 and a processor 22, wherein the memory 21 comprises a dynamic design program for an interactive interface based on feature analysis, and when the dynamic design program for an interactive interface based on feature analysis is executed by the processor 22, the following steps are implemented: Within a preset period, a preset network connection is set between the platform terminal and the user terminal, and user interface interaction data and user interaction instructions are collected through the platform terminal; Through the user interface interaction data and the user interaction instructions, behavior semantic analysis and user operation feature analysis are performed respectively to generate a first behavior label and a second behavior label based on a text format; Through 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, and the first behavior tag and the second behavior tag are converted into word vectors to generate a first word vector set and a second word vector set; The first word vector set and the second word vector set are converted 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, and the user's behavior feature clustering analysis is performed through a density clustering algorithm to obtain multiple feature clustering groups; For a feature clustering group, obtain all interface interaction data and interaction instructions of the corresponding user, mark them as current interaction data and current interaction instructions, dynamically set interface priority and instruction 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.

[0042] It should be noted that the semantic model perspective used in the present invention to analyze user characteristics is based on two aspects, namely, interaction data and command data. The traditional perspective is often based on unilateral interaction data analysis, which makes it difficult to comprehensively analyze the user's interaction characteristics, and it is difficult to dynamically analyze and set the interface to adapt to different users. The present invention converts behavioral characteristics and analyzes them in matrix form to effectively improve the analysis efficiency and clustering efficiency of behavioral characteristics, provides an efficient data processing method for realizing a dynamic setting interface, helps to improve the efficiency of the dynamic setting interface, and improves the user experience.

[0043] According to an embodiment of the present invention, within a preset period, setting a preset network connection between the platform terminal and the user terminal, and collecting user interface interaction data and user interaction instructions through the platform terminal, specifically: Within a preset period, based on a preset network protocol, a preset dedicated network connection is set between the platform terminal and the user terminal; Collect user interface interaction data and user interaction instructions through platform terminals; Perform data cleaning preprocessing on user interface interaction data.

[0044] It should be noted that the platform terminals and user terminals can be in the fields of logistics warehousing, education platform, commercial product display, etc.

[0045] According to an embodiment of the present invention, the user interface interaction data and the user interaction instruction are respectively subjected to behavior semantic analysis and user operation feature analysis to generate a first behavior label and a second behavior label based on a text format, specifically: Through the user interface interaction data, the behavior semantic analysis of the interface operation is performed, and the first behavior label is screened out in combination with the preset interface behavior label data; The user operation characteristics are analyzed through the user interaction instructions, and the second behavior label is screened out by combining the preset instruction behavior label data.

[0046] It should be noted that the preset interface behavior label data includes a plurality of predetermined interface operation behavior labels, such as user clicks, browsing, entering the primary and secondary interfaces, querying, data import and export, etc. in the interactive interface, and the behavior labels can be used for semantic analysis and behavior inference. The preset instruction behavior label data includes different instruction mode label information.

[0047] According to an embodiment of the present invention, the GloVe semantic model is used to set a co-occurrence matrix based on a preset behavior tag library, semantic feature analysis is performed on the first behavior tag and the second behavior tag, and the first behavior tag and the second behavior tag are converted into word vectors to generate a first word vector set and a second word vector set, specifically: Through the GloVe semantic model, the text format of the preset behavior tag library is standardized and the word statistics of the context are performed, the co-occurrence frequency of each word is calculated, and the co-occurrence matrix is ​​generated; The first behavior label and the second behavior label are converted into a first word set and a second word set and imported into the GloVe semantic model for word vector conversion to generate a first word vector set and a second word vector set respectively.

[0048] It should be noted that the preset behavior label library may be integrated text data of preset interface behavior label data and preset instruction behavior label data, which is used as context for semantic model training.

[0049] According to an embodiment of the present invention, the first word vector set and the second word vector set are converted 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, and the user's behavior feature clustering analysis is performed through a density clustering algorithm, and multiple feature clustering groups are obtained, specifically: According to the first word vector set, a first feature matrix is ​​constructed with the word vector type as the first dimension data and the word vector value as the second dimension data; The word vector type is defined by the GloVe semantic model; Analyze the second word vector set and construct a second feature matrix; Analyze the first characteristic matrix and the second characteristic matrix of each user, and calculate the corresponding first eigenvalue and second eigenvalue based on the first characteristic matrix and the second characteristic matrix; The first feature matrix and the second feature matrix of each user are used as clustering sample data, and the user is used as the clustering unit. The user's behavioral characteristics are clustered and analyzed based on the DBSCAN clustering algorithm. The similarity between clustering units is analyzed by the weighted mean of the first eigenvalue and the second eigenvalue, and finally multiple feature clustering groups are formed.

[0050] It should be noted that the similarity between clustering units is analyzed by the weighted mean of the first eigenvalue and the second eigenvalue. Specifically, the first characteristic matrix and the second characteristic matrix corresponding to a certain user are calculated, and two matrix eigenvalues, namely the first eigenvalue and the second eigenvalue, are obtained. The two eigenvalues ​​are weighted averaged to obtain the characteristic mean. The similarity between the clustering sample data between users is measured by the difference in the characteristic mean corresponding to each clustering unit.

[0051] According to an embodiment of the present invention, for a feature clustering group, all interface interaction data and interaction instructions of the corresponding user are obtained, marked as current interaction data and current interaction instructions, the interface priority and instruction priority are dynamically set according to the current interaction data and the current interaction instructions, a user interaction behavior feature table is generated, and the user terminal interface is dynamically set according to the user interaction behavior feature table, specifically: Select a feature clustering group, filter and mark the interface interaction data and interaction instructions of all users in the group, and obtain the current interaction data and current interaction instructions; Analyze the first behavior label and the second behavior label of the users in the group through the current interaction data and the current interaction instruction, dynamically set the interface priority and the instruction priority, and generate a user interaction behavior feature table; The user interaction behavior feature table includes an interface priority table and an instruction priority table; Through the user interaction behavior feature table, the user terminal interface is dynamically set and dynamically matched with the interface instructions to set the user terminal interface.

[0052] It should be noted that the interface priority table includes display priority, processing priority information, etc. of each level of interface and various types of interfaces, and the instruction priority table includes priority information for different operation instructions.

[0053] According to an embodiment of the present invention, the platform terminal performs data collection and data processing based on a cloud computing platform.

[0054] 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 the user terminal.

[0055] According to an embodiment of the present invention, the user terminal includes a computer terminal and a mobile terminal.

[0056] The third aspect of the present invention also provides a computer-readable storage medium, which includes a dynamic design program for an interactive interface based on feature analysis. When the dynamic design program for an interactive interface based on feature analysis is executed by a processor, the steps of the dynamic design method for an interactive interface based on feature analysis as described in any one of the above items are implemented.

[0057] The present invention discloses a method and system for dynamic design of interactive interface based on feature analysis. The present invention proposes a method for dynamic design of interactive interface based on feature analysis, which collects user interface interaction data and user instructions through a preset network, combines with a semantic analysis model, analyzes user behavior semantics and user operation characteristics, generates behavior labels and converts them into word vector sets. Further, the word vector set is converted into a feature matrix, and the user behavior characteristics are clustered by a density clustering algorithm. Based on the generated feature clustering group, the interface and instruction priority are dynamically set according to the user interaction data, a user interaction behavior feature table is generated, and the user terminal interface is dynamically set according to the feature table, so as to realize periodic update of the user terminal interaction interface and effectively improve the user interaction efficiency and experience.

[0058] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0059] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0060] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0061] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0062] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0063] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A dynamic design method for interactive interface based on feature analysis, characterized in that: include: Within a preset period, a preset network connection is set between the platform terminal and the user terminal, and user interface interaction data and user interaction instructions are collected through the platform terminal; Performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction instructions, respectively, to generate a first behavior label and a second behavior label in text format; 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, and word vector conversion is performed on the first behavior tag and the second behavior tag to generate the first word vector set and the second word vector set; Convert the first word vector set and the second word vector set into a first feature matrix and a second feature matrix, use the first feature matrix and the second feature matrix of each user as clustering sample data, perform behavioral feature clustering analysis on the user using a density clustering algorithm, and obtain multiple feature clustering groups; For a feature clustering group, all interface interaction data and interaction instructions of the corresponding user are obtained, marked as current interaction data and current interaction instructions, the interface priority and instruction priority are dynamically set according to the current interaction data, a user interaction behavior feature table is generated, and the user terminal interface is dynamically set according to the user interaction behavior feature table.

2. The method for dynamic design of interactive interface based on feature analysis according to claim 1, characterized in that: The method 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 instructions through the platform terminal is as follows: Within a preset period, a preset dedicated network connection is set up between the platform terminal and the user terminal based on a preset network protocol; Collect user interface interaction data and user interaction instructions through platform terminals; Perform data cleaning and preprocessing on user interface interaction data.

3. The method for dynamic design of interactive interface based on feature analysis according to claim 1, characterized in that: The user interface interaction data and the user interaction instructions are respectively subjected to behavioral semantic analysis and user operation feature analysis to generate a first behavior label and a second behavior label based on a text format, specifically: Through the user interface interaction data, the interface operation is analyzed by behavioral semantics, and the first behavior label is selected based on the preset interface behavior label data; The user operation characteristics are analyzed through user interaction instructions, and the second behavior label is screened out by combining the preset instruction behavior label data.

4. The method for dynamic design of interactive interface based on feature analysis according to claim 1, characterized in that: The GloVe semantic model is used to set a co-occurrence matrix based on a preset behavior tag library, perform semantic feature analysis on the first behavior tag and the second behavior tag, and convert 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, Using the GloVe semantic model, the preset behavior tag library is standardized in text format and context word statistics are performed to calculate the co-occurrence frequency of each word and generate a co-occurrence matrix. The first behavior label and the second behavior label are converted into the first word set and the second word set and imported into the GloVe semantic model for word vector conversion to generate the first word vector set and the second word vector set respectively.

5. The method for dynamic design of interactive interface based on feature analysis according to claim 1, characterized in that: The first word vector set and the second word vector set are converted into a first feature matrix and a second feature matrix, and 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 using a density clustering algorithm, and multiple feature clustering groups are obtained, specifically: According to the first word vector set, a first feature matrix is ​​constructed with the word vector type as the first dimension data and the word vector value as the second dimension data; The word vector type is defined by the GloVe semantic model; Analyze the second word vector set and construct the second feature matrix; Analyze the first characteristic matrix and the second characteristic matrix of each user, and calculate the corresponding first eigenvalue and second eigenvalue based on the first characteristic matrix and the second characteristic matrix; The first feature matrix and the second feature matrix of each user are used as clustering sample data, and the user is used as the clustering unit. The user's behavioral characteristics are clustered based on the DBSCAN clustering algorithm. The similarity between clustering units is analyzed by the weighted mean of the first eigenvalue and the second eigenvalue, and finally multiple feature clustering groups are formed.

6. The method for dynamic design of interactive interface based on feature analysis according to claim 1, characterized in that: For a feature cluster group, all interface interaction data and interaction instructions of the corresponding user are obtained, marked as current interaction data and current interaction instructions, interface priority and instruction priority are dynamically set according to the current interaction data and current interaction instructions, a user interaction behavior feature table is generated, and the user terminal interface is dynamically set according to the user interaction behavior feature table, specifically: Select a feature clustering group, filter and mark the interface interaction data and interaction instructions of all users in the group, and obtain the current interaction data and current interaction instructions; Analyze the first behavior tags and second behavior tags of users in the group through current interaction data and current interaction instructions, dynamically set interface priority and instruction priority, and generate a user interaction behavior feature table; The user interaction behavior feature table includes an interface priority table and an instruction priority table; Through the user interaction behavior feature table, the user terminal interface is dynamically set and dynamically matched with the interface instructions to set the user terminal interface.

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

8. The method for dynamic design of interactive interface based on feature analysis according to claim 1, characterized in that: The user terminals include computer terminals and mobile terminals.

9. 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 dynamic design program for an interactive interface based on feature analysis. When the dynamic design program for an interactive interface based on feature analysis is executed by the processor, the following steps are implemented: Within a preset period, a preset network connection is set between the platform terminal and the user terminal, and user interface interaction data and user interaction instructions are collected through the platform terminal; Performing behavioral semantic analysis and user operation feature analysis on user interface interaction data and user interaction instructions, respectively, to generate a first behavior label and a second behavior label in text format; 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, and word vector conversion is performed on the first behavior tag and the second behavior tag to generate the first word vector set and the second word vector set; Convert the first word vector set and the second word vector set into a first feature matrix and a second feature matrix, use the first feature matrix and the second feature matrix of each user as clustering sample data, perform behavioral feature clustering analysis on the user using a density clustering algorithm, and obtain multiple feature clustering groups; For a feature clustering group, all interface interaction data and interaction instructions of the corresponding user are obtained, marked as current interaction data and current interaction instructions, the interface priority and instruction priority are dynamically set according to the current interaction data, a user interaction behavior feature table is generated, and the user terminal interface is dynamically set according to the user interaction behavior feature table.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a dynamic design program for an interactive interface based on feature analysis. When the dynamic design program for an interactive interface based on feature analysis is executed by a processor, the steps of the dynamic design method for an interactive interface based on feature analysis as described in any one of claims 1 to 8 are implemented.

Images