Data visualization method and device, equipment, storage medium and product

Abstract

The invention discloses a data visualization method and device, equipment, a storage medium and a product, and the method comprises the steps: carrying out the data cleaning and data preprocessing of visual data corresponding to a data visualization demand, and converting the preprocessed data into graph data; and identifying a community structure in the graph data, performing community merging on the graph data based on a community structure identification result, and performing graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. The community structure identification result is determined by identifying the community structure of the graph data corresponding to the data visualization requirement, community merging is performed on the graph data based on the community structure identification result, and graph layout is performed on the graph data subjected to community merging through the preset layout algorithm, so that the data visualization result is obtained. Compared with an existing visualization mode of manually customizing the data by a technician, the data visualization method and device can automatically perform data visualization according to the data visualization requirement, and the data visualization efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to data visualization methods, devices, equipment, storage media and products. Background Art

[0002] With the increasing demand for visualization and the widespread application of data analytics, telecommunications companies are adopting data visualization to improve customer experience and business decision-making efficiency. Data visualization and analytics, a scientific technique that converts structured or unstructured data into visual elements such as charts, graphs, and images, helps users more intuitively understand the information and knowledge contained in the data. However, implementing data visualization faces multiple challenges. The most significant is the large volume of distributed data and the complexity of its data types, which slows processing. Furthermore, new requirements are placed on data quality assurance, visualization targeting capabilities, and user interaction. Data visualization in related technologies generally involves a certain degree of manual customization, leaving all modifications to the user to meet their needs. This can increase user perceived complexity, require a certain level of technical expertise, and result in longer time to generate results. Therefore, improving the efficiency of data visualization has become a pressing technical challenge. Summary of the Invention

[0003] The main purpose of this application is to provide a data visualization method, device, equipment, storage medium and product, aiming to solve the technical problem that existing data visualization requires manual participation, resulting in low data visualization efficiency.

[0004] To achieve the above objectives, this application proposes a data visualization method, which includes:

[0005] Perform data cleaning and data preprocessing on the visualization data corresponding to the data visualization requirements, and convert the preprocessed data into graph data;

[0006] Identifying the community structure in the graph data to obtain a community structure identification result;

[0007] The graph data is community-merged based on the community structure identification result, and the community-merged graph data is laid out using a preset layout algorithm to obtain a data visualization result.

[0008] Optionally, after the step of performing community merging on the graph data based on the community structure identification result, and performing graph layout on the community-merged graph data using a preset layout algorithm to obtain a data visualization result, the method further includes:

[0009] Determine visualization parameters based on data visualization requirements;

[0010] Dividing the data visualization result into data sets based on the visualization parameters to obtain a target data set;

[0011] Determining a parameter playback axis according to the target data set and the visualization parameter;

[0012] A data graphic display is performed based on the parameter playback axis and the target data set.

[0013] Optionally, the step of identifying the community structure in the graph data and obtaining a community structure identification result includes:

[0014] Dividing the nodes in the graph data into leaf nodes and non-leaf nodes;

[0015] Compressing the leaf nodes in the graph data to obtain compressed graph data;

[0016] The community is discovered on the compressed graph data based on a preset community discovery algorithm to obtain a community structure recognition result.

[0017] Optionally, the step of performing graph layout on the community-merged graph data using a preset layout algorithm to obtain a data visualization result includes:

[0018] Perform graph layout on the community-merged graph data using a preset layout algorithm to obtain an initial graph layout result;

[0019] The layout parameters in the initial graph layout result are adjusted based on preset deep reinforcement learning to obtain a data visualization result.

[0020] Optionally, the step of performing data cleaning and data preprocessing on the visualization data corresponding to the data visualization requirement includes:

[0021] Perform at least one of the following data cleaning on the visualization data corresponding to the data visualization requirements: missing value processing, outlier removal, and error correction to obtain cleaned visualization data;

[0022] The cleaned visualization data is subjected to at least one of the following data preprocessing: data standardization, discretization, feature construction, feature selection, data stratification, data encoding, and time series data processing.

[0023] Optionally, the step of performing time series data processing on the visualization data corresponding to the data visualization requirement includes:

[0024] Sort the visualization data corresponding to the data visualization requirements in chronological order to obtain the sorting results;

[0025] Determining a time window based on the data visualization requirements;

[0026] The sorting result is divided according to the time window to obtain a time series data processing result.

[0027] In addition, to achieve the above-mentioned purpose, the present application also proposes a data visualization device, which includes:

[0028] The preprocessing module is used to clean and preprocess the visualization data corresponding to the data visualization requirements, and convert the preprocessed data into graph data;

[0029] A community structure identification module is used to identify the community structure in the graph data and obtain a community structure identification result;

[0030] A graph layout module is used to perform community merging on the graph data based on the community structure identification result, and perform graph layout on the community-merged graph data using a preset layout algorithm to obtain a data visualization result.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a data visualization device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data visualization method described above.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the data visualization method described above are implemented.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the data visualization method described above.

[0034] This application performs data cleaning and data preprocessing on the visualization data corresponding to the data visualization requirements, and converts the preprocessed data into graph data; identifies the community structure in the graph data to obtain a community structure identification result; performs community merging on the graph data based on the community structure identification result, and performs graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. Since this application determines the community structure identification result by identifying the community structure of the graph data corresponding to the data visualization requirements, performs community merging on the graph data based on the community structure identification result, and performs graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. Compared with the existing method of manually customizing data visualization by technical personnel, the above method of this application can automatically perform data visualization according to data visualization requirements, thereby improving data visualization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0037] Figure 1 A flowchart of the first embodiment of the data visualization method of this application is provided;

[0038] Figure 2 A flowchart of the second embodiment of the data visualization method of this application is provided;

[0039] Figure 3 This is a schematic diagram of the module structure of the data visualization device according to an embodiment of the present application;

[0040] Figure 4 Schematic diagram of the device structure of the hardware operating environment involved in the data visualization method in the embodiment of the present application.

[0041] The purpose, features and advantages of this application will be further explained with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0042] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0043] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0044] The main solutions of the embodiments of the present application are: data cleaning and data preprocessing of the visualization data corresponding to the data visualization requirements, and converting the preprocessed data into graph data; identifying the community structure in the graph data to obtain a community structure identification result; merging the graph data into communities based on the community structure identification result, and performing a graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. Since the present application determines the community structure identification result by identifying the community structure of the graph data corresponding to the data visualization requirements, merges the graph data into communities based on the community structure identification result, and performs a graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. Compared with the existing method of manually customizing data visualization by technical personnel, the above method of the present application can automatically perform data visualization according to data visualization requirements, thereby improving data visualization efficiency.

[0045] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device or data visualization device capable of implementing the above functions. The following uses a data visualization device as an example to illustrate this embodiment and the following embodiments.

[0046] Based on this, the embodiment of the present application provides a data visualization method, referring to Figure 1 , Figure 1 A flowchart illustrating the first embodiment of the data visualization method of this application.

[0047] In this embodiment, the data visualization method includes the following steps:

[0048] Step S10: performing data cleaning and data preprocessing on the visualization data corresponding to the data visualization requirements, and converting the preprocessed data into graph data;

[0049] It should be noted that the data visualization requirement may be a command proposed by the user to represent specific data in the form of graphics or images. For example, the user proposes to obtain transaction data from 2021 to 2023 and the number of users in each province in 2020. In this embodiment, it is not only necessary to obtain the corresponding data, but also to display the obtained data to the user in a visual manner. The visual data may be the data corresponding to the visualization requirement. The data cleaning may include missing value processing, outlier removal, and error correction, etc. The data preprocessing may include data standardization, discretization, feature construction, feature selection, etc. The conversion of the preprocessed data into graph data may be converting the preprocessed data into graph data consisting of nodes and edges, where nodes represent entities and edges represent relationships between entities.

[0050] Step S20, identifying the community structure in the graph data to obtain a community structure identification result;

[0051] It should be noted that identifying the community structure in the graph data and obtaining the community structure identification result may be identifying the community structure in the graph data by using a community discovery algorithm based on modularity to obtain the community structure identification result.

[0052] Furthermore, in order to improve data visualization efficiency, the step S20 may include: dividing the nodes in the graph data into leaf nodes and non-leaf nodes;

[0053] Compressing the leaf nodes in the graph data to obtain compressed graph data;

[0054] The community is discovered on the compressed graph data based on a preset community discovery algorithm to obtain a community structure recognition result.

[0055] It should be noted that, in order to simplify the graph data and reduce the amount of computation, in this embodiment, the leaf nodes in the graph data are compressed to obtain compressed graph data. The preset community discovery algorithm can be a modularity-based community discovery algorithm (Fast unfolding of communities in large networks, Louvain).

[0056] Step S30 : merging communities on the graph data based on the community structure identification result, and performing graph layout on the community-merged graph data using a preset layout algorithm to obtain a data visualization result.

[0057] It should be noted that the community merging of the graph data based on the community structure identification result may be a selective merging of the communities in the community structure identification result to obtain a community merging result. The selective merging of the communities in the community structure identification result may be performed by merging strategies such as edge graph-based merging and heuristic merging. The preset layout algorithm may be a ComboForce layout algorithm (ComboForce Layout) and a layout algorithm based on physical simulation, such as simulated annealing or particle swarm optimization algorithm, to replace the traditional force-directed layout method. Drawing on the annealing process in physics, the node position is optimized by a simulated annealing algorithm. This algorithm can find an approximately globally optimal node layout in a larger search space, and balance the breadth and depth of the search by controlling the "temperature" parameter.

[0058] In the specific implementation, the data visualization device processes the obtained compressed graph data using the traditional Louvain algorithm, and then uses selective community merging to replace the iterative community merging process in the second stage of the traditional Louvain algorithm, thereby reducing the amount of computation generated in the second stage of the traditional algorithm. For the community structure and the corresponding graph data, the ComboForce layout algorithm is used to implement force-directed graph layout based on clustering optimization.

[0059] In a specific implementation, this embodiment further includes graph data modeling before step S10. Specifically, this embodiment converts complex data (which may be general data used to build a graph model) into a graph structure, in which nodes represent entities and edges represent relationships between entities; a graph database (such as Neo4j, JanusGraph) is used to store graph data to support efficient query and analysis of the data. Graph construction, data cleaning, and preprocessing are then performed. Graph construction may include using the concepts of graph theory and network analysis to convert data into a structure of nodes and edges. Nodes may represent entities, such as users, products, or events, while edges represent relationships between them, such as interactions, associations, or influences. Afterwards, a graph database (such as Neo4j) or a graph computing framework (such as Giraph, Pregel) is used to construct and store the graph.

[0060] Furthermore, in order to improve the efficiency of data visualization, the step S30 includes: performing a graph layout on the community-merged graph data using a preset layout algorithm to obtain an initial graph layout result;

[0061] The layout parameters in the initial graph layout result are adjusted based on preset deep reinforcement learning to obtain a data visualization result.

[0062] It should be noted that the adjustment of the layout parameters in the initial graph layout result based on the preset deep reinforcement learning to obtain the data visualization result can be to use the deep reinforcement learning framework (Deep Q-Network, DQN) to learn how to adjust the parameters in the force-directed graph layout (i.e., the initial graph layout result), and intelligently learn the optimal layout strategy through interaction with the environment. In this embodiment, a generative adversarial network (GAN) can also be used to generate a layout solution, and then an evaluation network (such as a discriminator) is used to evaluate the quality of the layout. Through this adversarial process, a more innovative and optimized layout solution can be generated.

[0063] Furthermore, in order to improve the user experience, after step S30, the method further includes: determining visualization parameters based on data visualization requirements;

[0064] Dividing the data visualization result into data sets based on the visualization parameters to obtain a target data set;

[0065] Determining a parameter playback axis according to the target data set and the visualization parameter;

[0066] A data graphic display is performed based on the parameter playback axis and the target data set.

[0067] It should be noted that the visualization parameters can be time information, or other information such as user gender, geographic location, etc. Any parameter information that can reflect the characteristics of the data can be used. The data visualization result is divided into data sets based on the visualization parameters to obtain the target data set, which can be divided into multiple data sets according to the visualization parameters to obtain the target data set. The parameter playback axis determined according to the target data set and the visualization parameters can be set to determine the parameter playback axis, determine the scale according to the axis length of the parameter playback axis, and the number of scales is greater than or equal to the number of target data sets; establish a correspondence between the target data set and the scale; when the playback point moves to a different scale of the parameter playback axis, determine the data set corresponding to the current scale based on the correspondence, and display the data graph corresponding to the determined data set. In this way, the content of the data graph display is enriched through the setting of the parameter playback axis, effectively showing the comparison of the data changes at the current node and the previous node, as well as the data change trend of the whole process.

[0068] In specific implementation, this embodiment uses the visualization tool - General Network Analysis and Visualization to design intuitive graph layouts, such as ring, force-directed, and radial, to display the distribution of nodes and edges. Furthermore, visual elements such as color, size, and labels are used to highlight key information and patterns. Specific steps may include obtaining visualization parameter information required for data visualization. This parameter information can be time information or other information such as user gender and geographic location. Any parameter information that can reflect the characteristics of the data can be used. The following detailed explanation uses time information as an example. Time information includes year, month, day, hour, minute, and second, and its accuracy is determined by the specific situation and data display needs. For example, if user growth statistics are to be calculated, only the year is required. If data is to be obtained from 2021 to 2023, only the data corresponding to the time information of 2021, 2022, and 2023 is required. However, if the purpose is to display the effectiveness of a product promotion campaign, the year data may not be the focus of analysis (for a specific promotion campaign, it is generally not across years, that is, the year is the same in the time information for that campaign). Of course, it is also possible to obtain all relevant data with time information and then filter them later. The specific process will not be described here. Then divide the data set. Specifically, divide the data set based on the parameter information. Specifically, the data with the same parameter information is divided into the same data set, and the data with different parameter information is divided into different data sets. Taking time information as an example, the standard of "same time information" can be interpreted in the following two ways: (1) Same time point: For example, when displaying the number of users in each province, the same time information means the same year. For example, the number of users in each province in 2020 (Beijing 2020 data, Hebei 2020 data, Shanxi 2020 data, Henan 2020 data) is divided into a data set (such as named data set 2), while Beijing 2021 data cannot be included in data set 2, but needs to be divided into a new data set (such as data set 3). (2) Same time range: With a certain time point as the center, all time within a certain range of this time point can be considered to have the same time information. This range can be flexibly set based on needs. For example, if a company has a three-year growth plan, the data corresponding to 2021-2023 can be treated as identical and grouped into the same dataset. The previous steps have already determined the number of datasets. In this case, you need to set a parameter playback axis and set the scale based on the axis length. The number of scales must be greater than or equal to the number of datasets, so that each dataset corresponds to a scale.

[0069] In addition, the parameter playback axis can be a long axis, or it can be a ring, or other shapes. As long as it can set the scale, when you click Start by default, the corresponding data or data graph can be displayed from the first scale until the last scale ends, and it is not limited to a specific shape. For example, when the parameter playback axis is set to a circle, the corresponding scale can be set based on the angle or a certain length on the circumference. Establish a correspondence between the data set and the scale: the data set needs to be sorted according to the preset parameter order first, and then the correspondence between the data set and the scale is established in the same or opposite order according to the scale and the sorted data set. Take time information as an example: after determining the data set and the scale, the correspondence between the two needs to be established. Select the user volume data set of each province from 2019 to 2024, set 6 scales, and the specific correspondence is: the 2019 data set corresponds to the first in the scale, the 2024 data set corresponds to the last in the scale (that is, the sixth), and so on. Corresponding Data Graphic Display: When the playback point moves to different scales on the parameter playback axis, the corresponding dataset is determined based on the corresponding relationship and the corresponding data graph is displayed. This enriches the content of the data graph display by setting the parameter playback axis, effectively showing the comparison of data changes at the current node and the previous node, as well as the data change trend throughout the process.

[0070] In order to assist users in data analysis, this embodiment can also perform key node analysis, identify patterns and trends, and predictive analysis. Specifically:

[0071] (1) Key Node Analysis: By analyzing the graph constructed from user behavior data, key nodes in the network are identified. For example, nodes with high connectivity may represent users who frequently use the service or key service facilities. Graph theory metrics such as node degree, betweenness centrality, and closeness centrality can be used to identify these key nodes.

[0072] (2) Pattern and trend identification: Identifying patterns and trends in user behavior. For example, by analyzing call or data usage patterns among users, traffic peaks within common communication groups or time periods can be discovered. These patterns are crucial for network optimization and resource allocation.

[0073] (3) Predictive analysis: Using algorithms from graph theory (such as shortest path algorithms or community detection algorithms) can help predict potential problems or behavioral trends in the network. For example, by analyzing the graph of user behavior, user churn or abnormal behavior can be predicted, allowing for proactive action.

[0074] This embodiment performs data cleaning and data preprocessing on the visualization data corresponding to the data visualization requirements, and converts the preprocessed data into graph data; identifies the community structure in the graph data to obtain a community structure identification result; performs community merging on the graph data based on the community structure identification result, and performs graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. Since this embodiment determines the community structure identification result by identifying the community structure of the graph data corresponding to the data visualization requirements, performs community merging on the graph data based on the community structure identification result, and performs graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. Compared with the existing method of manually customizing data visualization by technical personnel, the above method of this embodiment can automatically perform data visualization according to data visualization requirements, thereby improving data visualization efficiency.

[0075] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 , Figure 2 The flowchart provided in the second embodiment of the data visualization method of this application is as follows: Step S10 further includes the following steps:

[0076] Step S101: performing at least one of the following data cleaning on the visualization data corresponding to the data visualization requirement: missing value processing, outlier removal, and error correction to obtain cleaned visualization data;

[0077] It should be noted that missing value processing can include addressing missing values ​​in visualization data through deletion, filling, or interpolation. Outlier removal can include identifying and addressing outliers in visualization data, which may be caused by erroneous recording or fraudulent behavior. Error correction can include correcting errors or inconsistencies in visualization data, such as incorrect data types, formatting errors, or incorrect entries.

[0078] Step S102: performing at least one of the following data preprocessing on the cleaned visualization data: data standardization, discretization, feature construction, feature selection, data stratification, data encoding, and time series data processing.

[0079] It should be noted that the data preprocessing of the cleaned visualization data may include at least one of the following: 1. Data integration: including merging data sources: merging data from different data sources into a unified data set, and format unification: ensuring that the merged data follows the same format and standards.

[0080] 2. Data conversion: The basic steps of data conversion include:

[0081] 1) Normalization / Standardization: Scale the data so that it falls into a small specific interval (such as [0,1]) to eliminate the influence of different dimensions.

[0082] 2) Discretization: Convert continuous variables into discrete variables, for example, dividing the income range into several intervals.

[0083] 3) Feature construction: Create new features or modify existing features to better represent the data and improve the performance of the model. The main features include the following categories:

[0084] Statistical values: Statistical values ​​such as maximum, minimum, average, standard deviation, etc. can be calculated based on existing data as new features.

[0085] Interaction terms: Create interaction terms between features. For example, if there are two features A and B, you can create A*B as a new feature.

[0086] Polynomial features: Perform polynomial expansion on existing features. For example, for feature X, create X^2 and X^3 as new features.

[0087] Time window statistics: For time series data, you can create statistical features based on time windows, such as the sum, average, and maximum values ​​over the past hour, day, or week.

[0088] Aggregate features: For categorical features, you can create aggregate-based statistical features, such as the number of occurrences and proportions of each category. Specifically, in user behavior analysis, the features that have a significant impact on model performance mainly include the following aspects: User attribute features: including user age, gender, city, etc.; Service attribute features: including network time, value-added services, monthly fees, etc.; Call behavior features: Call frequency and duration: The distribution characteristics of user call frequency, call duration, etc. have a significant impact on model performance; Communication relationships: The temporal communication relationship characteristics of users, such as frequent callers and frequent called parties, have a significant impact on model performance.

[0089] 3. Feature selection. The basic steps include: Select relevant features: Select the features most relevant to the analysis target from the visualized data. This embodiment uses a filtering method to assess the importance of each feature based on statistical indicators. Common statistical indicators include correlation coefficient, chi-square test, analysis of variance, and information gain. For example, correlation analysis can be used to evaluate the relationship between each feature and the target variable, and then features with high correlation can be selected. Reduce dimensionality: Use principal component analysis (PCA) to reduce the number of features, simplify computational complexity, and improve model performance. The steps are as follows: Before applying PCA, the data is usually normalized to ensure that each feature has the same scale. PCA calculates the data's covariance matrix to determine the main directions of variation in the data. The principal components are determined by solving the eigenvalues ​​and eigenvectors of the covariance matrix. These principal components are the directions with the greatest variance in the data. A certain number of principal components is selected based on the cumulative explained variance, typically selecting the number that explains the majority of the variance. For example, the number of principal components that cumulatively explain 95% of the variance can be selected. The original data is projected onto the selected principal components to obtain the reduced dimensionality data.

[0090] 4. Data discretization: This embodiment uses binning to divide continuous numerical variables into different intervals or "bins" for group analysis.

[0091] 5. Encoding categorical variables, specifically including two encoding steps:

[0092] 1) One-hot encoding: Convert categorical variables into a series of binary columns.

[0093] 2) Label encoding: assigning a unique numerical value to each category of a categorical variable.

[0094] 6. Data stratification: When sampling or training models, ensure that different parts of the data (e.g., different user groups) are appropriately represented in the dataset. Basic requirements include: the number of samples for each part (e.g., different user groups) should be proportional to the product of the population size and its standard deviation; and the number of elements in each stratum that form part of the study sample should be proportional to the size of the stratum. These preprocessing steps will lay a solid foundation for subsequent data analysis.

[0095] Furthermore, the step of performing time series data processing on the visualization data corresponding to the data visualization requirement includes: sorting the visualization data corresponding to the data visualization requirement in chronological order to obtain a sorting result;

[0096] Determining a time window based on the data visualization requirements;

[0097] The sorting result is divided according to the time window to obtain a time series data processing result.

[0098] It should be noted that the time series data processing specifically includes: Time alignment: ensuring that the data is arranged in chronological order to facilitate time series analysis. Time window division: dividing continuous time series data into fixed-size windows for sliding window analysis. For example: when processing time series data such as user behavior data, this embodiment adopts sliding window analysis technology. This technology is suitable for large-scale data sets and high-dimensional data environments, and can be combined with other algorithms for processing (such as machine learning models) to improve prediction accuracy. In addition, this technology is also suitable for real-time data stream analysis and can gradually process real-time data. The specific implementation points are as follows:

[0099] 1) Sliding windows capture local features in time series (in time series data processing, local features refer to the properties or patterns exhibited by data within a specific time period), which helps to understand the short-term dynamic changes of data.

[0100] 2) The window size and sliding step size are adjusted according to the analysis requirements to adapt to different analysis tasks.

[0101] 3) By limiting the calculation range to a local window, the amount of calculation and memory usage are reduced, and the processing efficiency is improved.

[0102] This embodiment performs at least one of the following data cleaning steps on the visualization data corresponding to the data visualization requirements: missing value processing, outlier removal, and error correction, to obtain cleaned visualization data. The cleaned visualization data is then subjected to at least one of the following data preprocessing steps: data standardization, discretization, feature construction, feature selection, data stratification, data encoding, and time series data processing. Through data cleaning and preprocessing, this embodiment selects the features most relevant to the analysis objective from the visualization data. Principal component analysis is then used to reduce the number of features and simplify computational complexity.

[0103] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the data visualization method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0104] This application also provides a data visualization device, please refer to Figure 3 , the data visualization device comprises:

[0105] The preprocessing module 10 is used to clean and preprocess the visualization data corresponding to the data visualization requirements, and convert the preprocessed data into graph data;

[0106] A community structure identification module 20 is used to identify the community structure in the graph data and obtain a community structure identification result;

[0107] The graph layout module 30 is configured to perform community merging on the graph data based on the community structure identification result, and perform graph layout on the community-merged graph data using a preset layout algorithm to obtain a data visualization result.

[0108] This embodiment performs data cleaning and data preprocessing on the visualization data corresponding to the data visualization requirements, and converts the preprocessed data into graph data; identifies the community structure in the graph data to obtain a community structure identification result; performs community merging on the graph data based on the community structure identification result, and performs graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. Since this embodiment determines the community structure identification result by identifying the community structure of the graph data corresponding to the data visualization requirements, performs community merging on the graph data based on the community structure identification result, and performs graph layout on the community-merged graph data through a preset layout algorithm to obtain a data visualization result. Compared with the existing method of manually customizing data visualization by technical personnel, the above method of this embodiment can automatically perform data visualization according to data visualization requirements, thereby improving data visualization efficiency.

[0109] The data visualization device provided in this application utilizes the data visualization method described in the aforementioned embodiments, resolving the technical issue of low data visualization efficiency caused by the need for manual intervention in existing data visualization. Compared to the prior art, the data visualization device provided in this application achieves the same beneficial effects as the data visualization method described in the aforementioned embodiments. Other technical features of the data visualization device are the same as those disclosed in the aforementioned embodiments and are not further elaborated upon here.

[0110] The present application provides a data visualization device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the data visualization method in the above-mentioned embodiment one.

[0111] Reference below Figure 4, which shows a schematic diagram of the structure of a data visualization device suitable for implementing the embodiments of the present application. The data visualization device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital televisions and desktop computers. Figure 4 The data visualization device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0112] like Figure 4 As shown, the data visualization device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the data visualization device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 can allow the data visualization device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a data visualization device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or have alternatively.

[0113] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0114] The data visualization device provided in this application utilizes the data visualization method described in the aforementioned embodiment, resolving the technical issue of low data visualization efficiency caused by the need for manual intervention in existing data visualization. Compared to the prior art, the data visualization device provided in this application achieves the same beneficial effects as the data visualization method described in the aforementioned embodiment. Other technical features of the data visualization device are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0115] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0116] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0117] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, wherein the computer-readable program instructions are used to execute the data visualization method in the above-mentioned embodiment.

[0118] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0119] The computer-readable storage medium may be included in the data visualization device, or may exist independently without being assembled into the data visualization device.

[0120] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0121] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0122] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0123] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned data visualization method. This computer-readable storage medium can address the technical issue of low data visualization efficiency due to the need for manual intervention in existing data visualization techniques. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the data visualization method provided in the aforementioned embodiments, and are not further elaborated here.

[0124] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned data visualization method when executed by a processor.

[0125] The computer program product provided in this application can address the technical issue of low data visualization efficiency due to the need for manual intervention in existing data visualization. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the data visualization method provided in the above-mentioned embodiments, and are not further elaborated here.

[0126] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A data visualization method, characterized in that: The data visualization method comprises the following steps: Perform data cleaning and data preprocessing on the visualization data corresponding to the data visualization requirements, and convert the preprocessed data into graph data; Identifying the community structure in the graph data to obtain a community structure identification result; The graph data is community-merged based on the community structure identification result, and the community-merged graph data is laid out using a preset layout algorithm to obtain a data visualization result.

2. The data visualization method according to claim 1, wherein: After the steps of performing community merging on the graph data based on the community structure identification result, and performing graph layout on the community-merged graph data using a preset layout algorithm to obtain a data visualization result, the method further includes: Determine visualization parameters based on data visualization requirements; Dividing the data visualization result into data sets based on the visualization parameters to obtain a target data set; Determining a parameter playback axis according to the target data set and the visualization parameter; A data graphic display is performed based on the parameter playback axis and the target data set.

3. The data visualization method according to claim 1, wherein: The step of identifying the community structure in the graph data and obtaining a community structure identification result includes: Dividing the nodes in the graph data into leaf nodes and non-leaf nodes; Compressing the leaf nodes in the graph data to obtain compressed graph data; The community is discovered on the compressed graph data based on a preset community discovery algorithm to obtain a community structure recognition result.

4. The data visualization method according to claim 1, wherein: The step of performing graph layout on the community-merged graph data using a preset layout algorithm to obtain a data visualization result includes: Perform graph layout on the community-merged graph data using a preset layout algorithm to obtain an initial graph layout result; The layout parameters in the initial graph layout result are adjusted based on preset deep reinforcement learning to obtain a data visualization result.

5. The data visualization method according to any one of claims 1 to 4, characterized in that: The step of performing data cleaning and data preprocessing on the visualization data corresponding to the data visualization requirement includes: Perform at least one of the following data cleaning on the visualization data corresponding to the data visualization requirements: missing value processing, outlier removal, and error correction to obtain cleaned visualization data; The cleaned visualization data is subjected to at least one of the following data preprocessing: data standardization, discretization, feature construction, feature selection, data stratification, data encoding, and time series data processing.

6. The data visualization method according to claim 5, wherein: The step of performing time series data processing on the visualization data corresponding to the data visualization requirement includes: Sort the visualization data corresponding to the data visualization requirements in chronological order to obtain the sorting results; Determining a time window based on the data visualization requirements; The sorting result is divided according to the time window to obtain a time series data processing result.

7. A data visualization device, characterized in that: The data visualization device comprises: The preprocessing module is used to clean and preprocess the visualization data corresponding to the data visualization requirements, and convert the preprocessed data into graph data; A community structure identification module is used to identify the community structure in the graph data and obtain a community structure identification result; A graph layout module is used to perform community merging on the graph data based on the community structure identification result, and perform graph layout on the community-merged graph data using a preset layout algorithm to obtain a data visualization result.

8. A data visualization device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data visualization method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the data visualization method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the data visualization method according to any one of claims 1 to 6 are implemented.

Images