A data visualization processing method, system, storage medium and electronic device

Abstract

The application provides a data visualization processing method and system, a storage medium and an electronic device, and relates to the technical field of data processing. The technical scheme provided by the application can identify key visualization data and auxiliary visualization data in data by inputting original data into a correlation analysis model corresponding to a data partition, so as to realize hierarchical processing of the data. Finally, by combining the first visualization result and the second visualization result, the display of key information is highlighted while the integrity of the data is maintained, which not only avoids the problem of key information being submerged due to data congestion in the traditional method, but also ensures the accuracy of the visualization result, thereby meeting the needs of users for high-precision analysis of data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a data visualization processing method and system. BACKGROUND

[0002] Data visualization processing is the process of converting raw data into visual representations, making complex data intuitive and easy to understand through graphs, charts, maps, and other ways. This processing method can help people quickly identify patterns, trends, and anomalies in data, thereby supporting decision analysis and information transmission. With the advent of the big data era, data volume is growing exponentially, and data types are becoming increasingly diverse, posing a serious challenge to traditional data visualization processing methods.

[0003] Currently, the most common data visualization processing method in related technologies is to display data through two-dimensional or three-dimensional charts combined with interactive functions. However, this method has the following problems when dealing with massive and diversified data: the visualization chart is prone to overcrowding, and all correlations cannot be effectively presented in a single view, resulting in key information being overwhelmed or distorted, making it difficult to provide sufficiently accurate visualization results and unable to meet the needs of high-precision analysis by users. SUMMARY

[0004] The present application provides a data visualization processing method, system, storage medium and electronic device, which can improve the accuracy of the visualization results, thereby meeting the needs of high-precision analysis by users.

[0005] In a first aspect, the present application provides a data visualization processing method, the method comprising:

[0006] responding to a plurality of raw data input by a user;

[0007] determining a data partition corresponding to each of the raw data according to a data label corresponding to each of the raw data;

[0008] inputting the raw data into a correlation analysis model corresponding to the data partition corresponding to the raw data, to determine key visualization data and auxiliary visualization data in the raw data;

[0009] performing visualization processing on the auxiliary visualization data according to a standard visualization parameter corresponding to the auxiliary visualization data, to obtain a first visualization result corresponding to the auxiliary visualization data;

[0010] performing visualization processing on the key visualization data according to a target visualization parameter corresponding to the key visualization data, to obtain a second visualization result corresponding to the key visualization data;

[0011] combining the first visualization result and the second visualization result to obtain a target visualization result corresponding to the plurality of original data.

[0012] Optionally, the data partition corresponding to each of the original data is determined according to a data label corresponding to each of the original data.

[0013] Each of the original data is labeled to obtain a data label corresponding to each of the original data.

[0014] The data label is compared with a preset initial label of the data partition to obtain a label comparison result.

[0015] If the label comparison result meets a preset condition, the data partition corresponding to the original data is determined.

[0016] Optionally, before the original data is input into the correlation analysis model corresponding to the data partition corresponding to the original data to filter out the key visualization data and the auxiliary visualization data in the original data, the method further comprises:

[0017] According to the initial label preset by each of the data partitions, a knowledge graph between the initial labels is constructed.

[0018] According to the correlation in the knowledge graph, a training data set and a test data set are established.

[0019] The preset model is trained using the training data set and the test data set to obtain a correlation analysis model.

[0020] Optionally, the original data is input into the correlation analysis model corresponding to the data partition corresponding to the original data to determine the key visualization data and the auxiliary visualization data in the original data, comprising:

[0021] The original data is input into the correlation analysis model corresponding to the data partition corresponding to the original data to obtain a correlation score corresponding to the original data.

[0022] The original data with a correlation score greater than a preset threshold is determined as key visualization data, and the original data with a correlation score not greater than a preset threshold is determined as auxiliary visualization data.

[0023] Optionally, after the original data with a correlation score greater than a preset threshold is determined as key visualization data, and the original data with a correlation score not greater than a preset threshold is determined as auxiliary visualization data, the method further comprises:

[0024] According to a difference between the correlation score and the preset threshold, the standard visualization parameter is adjusted to obtain a target visualization parameter corresponding to the key visualization data.

[0025] Optionally, before the visualizing the auxiliary visualization data according to the standard visualization parameter corresponding to the auxiliary visualization data to obtain a first visualization result corresponding to the auxiliary visualization data, the method further includes:

[0026] According to the standard visualization parameter corresponding to the auxiliary visualization data, the auxiliary visualization data is de-duplicated.

[0027] Optionally, after the combining the first visualization result and the second visualization result to obtain a target visualization result corresponding to the plurality of original data, the method further includes:

[0028] Extracting a keyword of the first visualization result and labeling the keyword in the target visualization result.

[0029] In a second aspect, the present application provides a data visualization processing system, the system comprising:

[0030] An input module configured to input a plurality of original data in response to a user input;

[0031] A data labeling module configured to determine a data partition corresponding to each of the original data according to a data label corresponding to each of the original data;

[0032] A data division module configured to input the original data into a correlation analysis model corresponding to the data partition corresponding to the original data to determine key visualization data and auxiliary visualization data in the original data;

[0033] A first visualization processing module configured to visualize the auxiliary visualization data according to a standard visualization parameter corresponding to the auxiliary visualization data to obtain a first visualization result corresponding to the auxiliary visualization data;

[0034] A second visualization processing module configured to visualize the key visualization data according to a target visualization parameter corresponding to the key visualization data to obtain a second visualization result corresponding to the key visualization data;

[0035] An output module configured to combine the first visualization result and the second visualization result to obtain a target visualization result corresponding to the plurality of original data.

[0036] In a third aspect, the present application provides a computer storage medium storing a plurality of instructions, the instructions being adapted to be loaded by a processor and executed to perform any of the above methods.

[0037] In a fourth aspect, the present application provides an electronic device, comprising a processor, a memory and a transceiver, the memory is configured to store instructions, the transceiver is configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to perform any of the above methods.

[0038] In summary, the beneficial effects brought by the technical scheme of the present application include:

[0039] By adopting the above technical scheme, the multiple original data input by the user are subjected to data label partition processing, so that different types of data can be allocated to corresponding processing units, avoiding the loss of data features caused by unified processing. By inputting the original data into the correlation analysis model corresponding to the data partition, the key visual data and auxiliary visual data in the data can be identified, and the hierarchical processing of the data is realized. For the auxiliary visual data, the standard visual parameter is used for processing to obtain the first visual result, ensuring the basic display effect of the background data; for the key visual data, the target visual parameter is used for processing to obtain the second visual result, highlighting the visual expression of important data. Finally, by combining the first visual result and the second visual result, the display of key information is highlighted while maintaining the integrity of the data, avoiding the problem of key information being submerged caused by data congestion in traditional methods, and ensuring the accuracy of the visual result, thereby meeting the user's demand for high-precision data analysis. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 is a flowchart of a data visualization processing method according to an embodiment of the present application;

[0041] Figure 2 is a structural schematic diagram of a data visualization processing system according to an embodiment of the present application;

[0042] Figure 3 is a structural schematic diagram of an electronic device according to an embodiment of the present application.

[0043] Legend of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the technical solutions in the present specification, the technical solutions in the present specification will be described clearly and completely in conjunction with the drawings in the embodiments of the present specification. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments.

[0045] In the description of the embodiments of the present application, the words "exemplary", "for example", or "e.g." are used to mean "an example of" or "an example, only". Any embodiment or design solution described as "exemplary", "for example", or "e.g." in the embodiments of the present application should not be construed as being more advantageous or superior than other embodiments or design solutions. In fact, the words "exemplary", "for example", or "e.g." are used to present relevant concepts in a concrete manner.

[0046] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used only for the purpose of description, and should not be interpreted or implied to indicate or suggest relative importance or implicitly indicate the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized.

[0047] Please refer to Figure 1 A flowchart of a data visualization processing method provided by the embodiments of the present application is shown. The method can be implemented by relying on a computer program, relying on a single-chip microcomputer, or running on a data visualization processing system based on the von Neumann architecture. The computer program can be integrated in an application or run as an independent tool application. The specific steps of the data visualization processing method are described in detail below.

[0048] S101: Responding to a plurality of original data input by a user.

[0049] Among them, the original data refers to the initial data set collected by the user or the system without processing and analysis. These data may contain various types of information, such as numerical data, text data, time series data, geographic location data, etc. In the embodiments of the present application, it can be understood as a basic data resource for visualization analysis and display.

[0050] In this embodiment, it is first necessary to obtain a plurality of original data input by the user. Specifically, when the user inputs or uploads various data through the system interaction interface, the system will respond to this operation and receive these original data. These original data can come from various channels such as sales records, production monitoring data, user behavior logs, financial statements, etc. of the enterprise, and the data types can include numerical data, text data, time series data or geographic location data, etc. For example, the user can input a sales data set containing product sales, sales area, customer type, time node and other multi-dimensional information. The system receives these original data through the data interface module and temporarily stores them in the data cache area of the system, preparing for subsequent data partitioning and correlation analysis.

[0051] S102: Determine the data partition corresponding to each original data according to the data label corresponding to each original data.

[0052] Among them, the data label refers to the descriptive information attached to the original data, which is used to identify the type, attribute, source or other characteristic of the data. These labels usually exist in the form of metadata, which can reflect the internal characteristics and business meaning of the data. In the embodiments of the present application, it can be understood that the basis for classifying, archiving and correlation analysis of original data is an important clue for the system to identify the relationship between different data sets. Data labels can be pre-defined category identifiers (such as "sales data", "user behavior", "device status", etc.), or system-generated feature identifiers based on data content. They serve as the basis for data partitioning, guiding the system to allocate original data to corresponding processing modules, and providing a semantic basis for subsequent correlation analysis.

[0053] Among them, the data partition refers to an organizational method of dividing original data into different processing units according to the internal attributes, business characteristics or application scenarios of the data. This division is based on the data categories, structural features or semantic associations reflected by the data labels, forming data collections with certain cohesion. In the embodiments of the present application, it can be understood as a logical container for classifying and managing original data and differential processing. Each data partition corresponds to a specific type of data processing strategy and a dedicated correlation analysis model. Through the data partition mechanism, the system can process different types of data specifically, improving the specificity and efficiency of data processing.

[0054] In this embodiment, after obtaining a plurality of original data input by a user, the system needs to determine the data partitions corresponding to each original data according to the data labels corresponding to each original data. In specific implementation, the system pre-processes and analyzes the received original data, extracts the structured information and semantic features contained in the data, labels each original data through a data labeling engine, and obtains the data labels corresponding to each original data. These data labels can include data type labels (such as "time series data", "geospatial data"), business domain labels (such as "sales data", "user behavior data"), or data attribute labels (such as "high-frequency data", "sparse data"), and the like.

[0055] The reason for data partitioning is that different types of data have different characteristics and requirements in the visualization process, and it is often difficult to achieve ideal visualization effects by using a unified processing method for different data types. Through data partitioning, the system can provide specialized processing strategies and analysis models for different types of data, improving the accuracy and efficiency of data processing.

[0056] On the basis of the above embodiment, as an optional implementation, step S102 further includes S201-S203.

[0057] S201: Labeling each original data to obtain data labels corresponding to each original data.

[0058] In specific implementation, the system first calls a data analysis engine to extract features and analyze attributes of the received original data, identifies the basic types, format features and content semantics of the data by scanning data content, structural features and meta information, and the like. Subsequently, the system maps the identified data features to corresponding label categories according to a pre-defined labeling rule library. These labeling rules can be based on data structural features (such as whether the data contains timestamps, geographic coordinates, and the like), content features (such as whether it contains specific business domain terms, index names, and the like), or metadata features (such as data source system, collection frequency, and the like) for judgment. For example, when the system detects that the original data contains a timestamp and a continuously changing numerical field, it will be labeled as "time series data". In addition, the system can also label business labels such as "operation data" or "user behavior data" according to the business attributes of the data. For complex original data, the system can intelligently label through a machine learning model, comprehensively consider the multi-dimensional features of the data, and generate a multi-level data label system.

[0059] S202: Comparing the data labels with the initial labels preset for the data partition to obtain a label comparison result.

[0060] The initial label refers to a set of standardized data feature descriptors preset by the system, which constitutes the basic framework of data classification and categorization, and reflects the system's priori cognition and processing ability for different types of data. In the embodiments of the present application, it can be understood that the reference standard for defining the basic features and boundaries of each data partition is the basis for the system to map the original data to the appropriate data partition.

[0061] In specific implementation, the system first retrieves the initial label set preset for each data partition from the label management module. These initial label sets are standardized feature descriptors predefined by the system in the design stage for various data characteristics, which clearly define the basic attributes and applicable scope of each data partition. Subsequently, the system starts the label comparison engine and performs multi-dimensional matching calculation on the data label corresponding to each original data and the initial labels of all data partitions in the system. The comparison process uses a semantic similarity algorithm, which first converts the data label and the initial label into a standardized feature vector, and then calculates the cosine similarity or other semantic similarity indicators between the vectors. In addition, the comparison process also considers the hierarchical relationship and weight factors of the labels, for example, core labels (such as data type labels) usually have higher weights, while auxiliary labels (such as data source labels) have lower weights. Through comprehensive calculation, the system finally generates a label comparison result matrix, which contains the matching degree scores between the data label of each original data and the initial labels of each data partition.

[0062] S203: If the label comparison result meets the preset condition, determine the data partition corresponding to the original data.

[0063] After obtaining the comparison results of the data label of the original data and the initial label of each data partition, the system needs to determine the final data partition to which each original data belongs according to a certain decision mechanism. In the specific implementation process, the system first sets the judgment threshold and decision rules of the label comparison result to form a complete preset condition system. These preset conditions usually include label matching degree threshold (such as similarity score needs to exceed 0.7), label priority rule (such as core label matching is prior to auxiliary label), and partition load balancing parameters, etc. Subsequently, the system sequentially checks the label comparison result matrix of each original data to judge whether its matching with each data partition meets the preset condition. When the label comparison result of a certain original data with a specific data partition reaches or exceeds the preset threshold, and has the highest matching degree among multiple candidate partitions, the system will determine that the original data belongs to the data partition.

[0064] Specifically, if the original data matches multiple data partitions with similar degrees of closeness and all meet the basic threshold requirements, the system will further apply secondary decision rules, such as considering the current load status, processing priority or user-specified preference settings of the data partitions, and make a final decision after comprehensive evaluation. For special cases where automatic determination cannot determine the partition ownership, the system will mark the data as "to be classified" status, and optionally introduce artificial auxiliary decision mechanism. The necessity of setting preset conditions for partition determination is that the label comparison process provides the matching degree information between the original data and each partition, but the quantitative comparison results need to be converted into deterministic partition decisions through explicit decision mechanisms, and complex situations such as insufficient label matching or multiple partition competition need to be handled. By setting reasonable preset conditions, the system can ensure the accuracy of partition decision while improving the degree of automation and processing efficiency.

[0065] S103: input the original data into the corresponding correlation analysis model corresponding to the data partition to determine the key visualization data and auxiliary visualization data in the original data.

[0066] Among them, the key visualization data refers to the core data elements or data subsets in the original data set that have a decisive role in expressing specific information or have an important influence on user understanding and decision-making, which usually contains the most representative, most reflects the trend change or abnormal characteristics of the key information points in the data set. In the embodiments of the present application, it can be understood as high-value data content for priority presentation and emphasis, which needs to use more eye-catching visual coding means, more delicate processing method and higher display priority in the visualization process, to ensure that users can quickly capture the most critical information in the complex data visualization interface, improve the data transmission efficiency and decision support ability.

[0067] Among them, the auxiliary visualization data refers to the secondary data elements or data subsets in the original data set that are used to supplement the explanation, provide background information or assist in understanding the key data, which can be understood in the embodiments of the present application as supportive data content for building complete data narrative and enhancing analysis depth.

[0068] In this embodiment, the system first inputs the original data into the corresponding data partition corresponding to the correlation analysis model. Each data partition is configured with a special correlation analysis model, which is based on the characteristics and structure of different types of data and uses different algorithm strategies to evaluate the data correlation. For example, the correlation analysis model of the time series partition may focus on trend changes and anomaly point detection in the time dimension, while the correlation analysis model of the geographic information partition may focus more on spatial clustering and regional correlation analysis. In the correlation analysis process, the system first preprocesses the original data, including data cleaning, standardization, and feature extraction, etc. operations to ensure that the analysis is based on high-quality data input. Subsequently, the system applies the correlation analysis model to evaluate the mutual relationship between data elements in multiple dimensions, including correlation analysis, causal relationship inference, information entropy calculation, clustering analysis and other technical means. The implementation effect of this step is that the system can distinguish the importance of data elements on the basis of preserving the integrity of the original data, and form a clear data value hierarchy.

[0069] On the basis of the above embodiment, as an optional implementation manner, the step of constructing the correlation analysis model specifically includes S301-S303.

[0070] S301: Construct a knowledge graph between the initial labels according to the initial labels preset by each data partition.

[0071] In specific implementation, the system first extracts the initial label set of each data partition from the label management module, including the name, definition, attribute characteristics of each label and the association relationship with the data partition. Subsequently, the system starts the knowledge graph construction engine to perform semantic analysis and relationship mining on these initial labels. In the analysis process, the system uses natural language processing and semantic understanding technology to identify the potential associations between labels, including hierarchical relationships (such as “time series data” is a lower concept of “dynamic data”), similarity relationships (such as “geographical distribution” and “spatial distribution” have semantic similarity), combination relationships (such as “high-frequency sampling” and “real-time monitoring” are often used in combination), and mutually exclusive relationships (such as “discrete data” and “continuous data” are mutually exclusive in concept) and other semantic relationship types. After determining the relationship between labels, the system constructs the network structure of the knowledge graph, in which the nodes represent each initial label and the edges represent the semantic relationship between the labels, and different types of relationships are given different weights and characteristic descriptions. In addition, the system will also combine the actual application situation of the data partition and expert knowledge to verify and optimize the automatically constructed knowledge graph, to ensure that it accurately reflects the real semantic relationship and domain knowledge between the labels.

[0072] S302: Establish a training data set and a test data set according to the correlation relationship in the knowledge graph.

[0073] In implementation, the system first deeply analyzes the knowledge graph to extract various association relationships between tags and their strength characteristics. These association relationships include semantic connections such as hierarchical relationships, similarity relationships, combination relationships, and mutually exclusive relationships between tags, which collectively constitute the structured expression of tag knowledge. Subsequently, the system designs a sampling strategy based on these association relationships to filter data samples that meet specific tag combination patterns from the historical data repository. During the sampling process, the system pays special attention to tag sets with close associations in the knowledge graph, preferentially selecting data samples that reflect these association relationships, while also appropriately incorporating some boundary samples with relatively loose tag relationships to enhance the representativeness and generalization ability of the dataset. Based on sampling, the system divides the filtered data samples into training and testing datasets according to a certain proportion. During the division process, the system uses stratified sampling methods to ensure that the data distribution of various tag combinations in the training and testing sets remains consistent, avoiding model training bias caused by distribution bias. In addition, the system also performs quality assessment on the dataset, removes noise data and redundant samples, and performs necessary data augmentation and balancing processing to ensure that the final training and testing sets have good quality and representativeness.

[0074] S303: Train the preset model using the training dataset and the testing dataset to obtain an association degree analysis model.

[0075] The system first selects a preset model architecture from the model library that is suitable for the characteristics of the current data partition. These preset models typically include various classic machine learning models and deep learning architectures, such as random forests, gradient boosting trees, convolutional neural networks, recurrent neural networks, graph neural networks, or attention mechanism models, etc. The choice of model will vary depending on the type and characteristics of the data partition. For example, for time series partitions, long short-term memory networks (LSTM) or temporal convolutional networks (TCN) may be selected, while for geographic information partitions, spatial convolutional networks or graph convolutional networks may be used. After selecting the preset model, the system performs preliminary configuration of the model architecture, including determining the model hierarchy, node number, activation function type, and initialization parameters, etc. basic settings. Subsequently, the system trains the preset model using the training dataset constructed in the previous step. The training process uses batch gradient descent or its variants, optimizing model parameters through multiple iterations to enable the model to gradually learn the association patterns and feature relationships contained in the data.

[0076] Based on the above embodiment, as an optional implementation, step S103 specifically further includes S401-S402.

[0077] S401: Input the original data into the association degree analysis model corresponding to the corresponding data partition to obtain the association degree score corresponding to the original data.

[0078] In implementation, the system first performs preprocessing operations on the input raw data, including data cleaning, format conversion, feature extraction, and standardization processing, etc. steps to ensure that the data format matches the input requirements of the correlation analysis model. The preprocessing process pays special attention to preserving the original characteristics and structural information of the data, avoiding excessive processing that leads to the loss of valuable information. Subsequently, the system inputs the preprocessed data into the correlation analysis model corresponding to the data partition. During the input process, the system adopts batch processing or streaming processing methods, selects appropriate processing strategies according to the data size and timeliness requirements, and ensures the efficiency and stability of data processing. After receiving the data input, the correlation analysis model generates correlation analysis results through a forward calculation process, including correlation assessment between data elements, causal relationship inference, information value quantification, and other multi-dimensional analysis indicators. Based on the model calculation, the system comprehensively considers various analysis indicators and calculates the correlation score of each data element or data subset according to the preset scoring rules.

[0079] S402: Determine the raw data with a correlation score greater than the preset threshold as key visualization data, and determine the raw data with a correlation score not greater than the preset threshold as auxiliary visualization data.

[0080] In the implementation process, the system first needs to determine an appropriate preset threshold. The setting of this threshold is crucial, directly affecting the division ratio and boundary clarity of key visualization data and auxiliary visualization data. The system usually adopts multiple methods to determine the threshold, including statistical analysis method (such as percentile based on correlation score distribution), domain knowledge method (based on expert experience in specific fields), and adaptive calculation method (dynamic adjustment according to data characteristics), etc. After determining the threshold, the system evaluates and compares the correlation scores of the raw data, and marks the data elements or data subsets with a correlation score greater than the preset threshold as key visualization data, and marks the data elements or data subsets with a correlation score not greater than the preset threshold as auxiliary visualization data. During the data marking process, the system maintains a data index table, recording the identifier, category (key or auxiliary), correlation score, and other related attributes of each data element, forming a structured management of the raw data.

[0081] Based on the above embodiment, as an optional implementation, the standard visualization parameters are adjusted according to the difference between the correlation score and the preset threshold, to obtain the target visualization parameters corresponding to the key visualization data.

[0082] The visualization parameters refer to a set of technical parameters that control the presentation form of data visualization, which directly determines how the data is encoded and presented at the visual level. The visualization parameters include but are not limited to visual attribute parameters (such as color, size, shape, transparency, etc.), spatial layout parameters (such as position, spacing, direction, etc.), time dynamic parameters (such as animation speed, transition effect, etc.), and interactive response parameters (such as hover effect, click feedback, etc.). In the embodiments of the present application, it can be understood that the technical indicators for quantitatively regulating the visual expression intensity and characteristics in the data visualization process are the core conversion mechanism for the system to map data values to visual presentations.

[0083] In specific implementation, the system first calculates the correlation degree enhancement coefficient for each key visualization data. This coefficient is usually calculated based on the difference between the correlation degree score and the preset threshold, and the calculation formula can be expressed as: enhancement coefficient = a + b x (correlation degree score - preset threshold) / (1 - preset threshold), where a is the basic enhancement parameter (usually set to 1.0-1.2), b is the difference amplification coefficient (usually set to 0.5-2.0). This calculation method ensures that the data with a higher correlation degree score obtains a larger enhancement coefficient, thereby obtaining a stronger visual highlighting effect in the visualization expression. After calculating the enhancement coefficient, the system extracts the standard visualization parameter set corresponding to the current data partition from the standard visualization parameter library. These standard parameters include various dimensions of visual encoding, such as color parameters (hue, saturation, lightness, etc.), size parameters (diameter, area, width, etc.), shape parameters (geometric type, edge sharpness, etc.), transparency parameters, position parameters, animation parameters (speed, frequency, etc.), and interactive parameters. Subsequently, the system parameterizes the standard visualization parameters according to the calculated enhancement coefficient to generate target visualization parameters. During the adjustment process, the system defines the adjustment method and amplitude of different visual encoding dimensions using parameter mapping rules.

[0084] S104: visualizing the auxiliary visualization data according to the standard visualization parameters corresponding to the auxiliary visualization data to obtain a first visualization result corresponding to the auxiliary visualization data.

[0085] In implementation, the system first retrieves the standard visualization parameter set corresponding to the current data partition from the visualization parameter library. These standard parameters are the default visual encoding rules optimized by design, including the default color scheme, standard element size, regular shape setting, basic transparency value, and general layout pattern, etc., which are suitable for the basic visualization processing of regular data. The selection of standard visualization parameters considers various factors such as data partition type, data attribute characteristics, visualization target, and user preferences, etc. The system selects the appropriate visualization type and form according to the characteristics and structure of the auxiliary visualization data. The selection of visualization type is usually based on the dimension characteristics, variable type, and analysis target of the data, such as selecting a line chart for time series data, a bar chart for classification comparison, a scatter plot for correlation analysis, etc. Subsequently, the system performs mapping processing on the auxiliary visualization data and the standard visualization parameters to generate preliminary visual expression elements. The mapping process involves data value to visual attribute conversion, such as mapping numerical size to element size, mapping data categories to different colors, mapping data sequences to spatial positions, etc. After completing the basic mapping, the system further optimizes the visual expression, including adjusting the spacing and alignment between visual elements, optimizing color and contrast, adding necessary labels and legends, adjusting coordinate axis proportion, and optimizing overall layout, etc., to ensure the clarity and readability of the visualization result.

[0086] Optionally, the above auxiliary visualization data is de-duplicated according to the standard visualization parameters corresponding to the auxiliary visualization data.

[0087] In implementation, the system first needs to determine the necessity and applicable conditions of de-duplication processing. Auxiliary visualization data, as the background part of the overall data, often contains a large number of similar or repeated data points. These repeated data not only do not provide additional information value in the final visualization, but also increase visual complexity, reduce rendering efficiency, and may cause visual confusion. Therefore, under the premise of ensuring data integrity and representation, appropriate de-duplication processing of auxiliary visualization data can effectively reduce redundant information and improve the clarity and computational efficiency of visualization. The implementation of de-duplication processing is based on standard visualization parameters, because these parameters define the performance characteristics of data in the visual space, directly affecting the degree of data similarity that is perceived as repeated in vision. The system determines the data de-duplication criteria according to the visual resolution threshold in the standard visualization parameters (such as the minimum recognizable color difference, the minimum recognizable size difference, etc.).

[0088] S105: According to the target visualization parameters corresponding to the key visualization data, the key visualization data is visualized to obtain the second visualization result corresponding to the key visualization data.

[0089] In the implementation process, the system first obtains the target visualization parameters that have been adjusted and optimized for the key visualization data from the previous step. These target visualization parameters are a set of enhanced parameters obtained by parameterizing adjustment based on the difference between the correlation score and the preset threshold value from the standard visualization parameters. The characteristic is that the visual expression intensity is positively correlated with the data importance, and it can provide differentiated visual coding schemes for key data. The system then performs data preprocessing and feature enhancement on the key visualization data. Unlike auxiliary visualization data, key visualization data usually does not undergo de-duplication or simplification processing, but retains its integrity and accuracy to ensure that important information is not missed or weakened. The system also performs appropriate feature enhancement on the key data, such as improving data accuracy through interpolation algorithms, reducing noise interference through smoothing algorithms, and highlighting data change characteristics through contrast enhancement, to lay a data foundation for subsequent fine visualization processing. After data preprocessing is completed, the system performs visual mapping and coding on the key visualization data according to the target visualization parameters. During the mapping process, the system will correspondingly strengthen the expression intensity of visual coding according to the enhancement coefficient in the target visualization parameters.

[0090] S106: Combine the first visualization result and the second visualization result to obtain a target visualization result corresponding to the plurality of original data.

[0091] In the implementation process, the system first needs to clarify the necessity and value of combination. Although the first visualization result alone contains complete data background, it lacks emphasis; although the second visualization result alone emphasizes key data, it may lack necessary context support. Only by organically combining the two can a comprehensive and focused visualization expression be created, which presents both the overall structure and background environment of the data and highlights the most valuable key information points, enabling users to accurately grasp the core content while understanding the overall situation. The system uses a multi-layer synthesis strategy to combine the visualization results. This strategy takes the first visualization result (auxiliary visualization data) as the basic background layer and the second visualization result (key visualization data) as the foreground focus layer, and integrates the two into a unified visualization expression through carefully designed hierarchical relationships and visual fusion rules. The combination process first locates the visual hierarchy. The system assigns different visual hierarchy priorities to the first visualization result and the second visualization result, usually setting the first visualization result as a lower visual priority (background layer) and the second visualization result as a higher visual priority (foreground layer). The setting of visual priority is achieved through the coordinated adjustment of multiple visual attributes, such as controlling the z-index values of different layers, adjusting the visual weight of elements (such as color saturation, contrast, element size, etc.), and setting appropriate transparency differences, to ensure a clear visual primary and secondary relationship in the final combination. Subsequently, the system coordinates the spatial layout.

[0092] Optionally, keywords of the first visualization result are extracted, and the keywords are marked in the target visualization result.

[0093] In a specific implementation, the system adopts a multi-level keyword extraction strategy to analyze the auxiliary visualization data corresponding to the first visualization result. The keyword extraction is not directly based on the visual result, but traces back to the auxiliary visualization data that produces the visual result, and mines representative concepts and terms from the data content, structure and attributes. The extraction process first performs semantic analysis on the auxiliary visualization data, including text content analysis, attribute name resolution, numerical feature identification, etc. For data containing text fields, the system uses natural language processing techniques such as term frequency statistics (TF-IDF), topic modeling (LDA / LSA), named entity recognition, etc. to extract potential keywords; for numerical data, the system identifies representative data features through statistical feature analysis (such as extreme points, inflection points, outliers, etc.) and converts them into descriptive keywords; for categorical data, the system extracts main category names and their feature descriptions as candidate keywords. After preliminary keyword extraction, the system performs keyword screening and optimization. The screening process considers multiple factors: first, evaluate the relevance of keywords to auxiliary visualization data, retain the words that best represent data features and content; second, consider the discriminability of keywords, filter out general or common terms, and retain specific concepts with high discriminability; third, evaluate the semantic overlap between keywords, merge similar concepts, and avoid redundant expressions; finally, consider the ease of understanding of keywords to ensure that the extracted words can be accurately understood by the target user group. After comprehensive evaluation, the system selects a number of keywords that are most representative and have the highest information content as the final marked content.

[0094] The following is an embodiment of the system of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the system embodiments of the present application, please refer to the method embodiments of the present application.

[0095] Please refer to Figure 2 which shows a structural schematic diagram of a data visualization processing system provided by an example embodiment of the present application. The system can be realized by software, hardware or a combination of both to become all or part of the system. The data visualization processing system comprises:

[0096] An input module for responding to a plurality of original data input by a user;

[0097] A data labeling module for determining a data partition corresponding to each original data according to a data label corresponding to each original data;

[0098] A data division module for inputting the original data into a correlation analysis model corresponding to the data partition corresponding to the original data to determine key visualization data and auxiliary visualization data in the original data;

[0099] The first visualization processing module is configured to perform visualization processing on the auxiliary visualization data according to the standard visualization parameter corresponding to the auxiliary visualization data, to obtain a first visualization result corresponding to the auxiliary visualization data.

[0100] The second visualization processing module is configured to perform visualization processing on the key visualization data according to the target visualization parameter corresponding to the key visualization data, to obtain a second visualization result corresponding to the key visualization data.

[0101] The output module is configured to combine the first visualization result and the second visualization result, to obtain a target visualization result corresponding to the plurality of original data.

[0102] On the basis of the above embodiment, as an optional embodiment, the data labeling module is further configured to label each original data to obtain a data label corresponding to each original data; compare the data label with an initial label preset for the data partition to obtain a label comparison result; and if the label comparison result meets a preset condition, determine the data partition corresponding to the original data.

[0103] On the basis of the above embodiment, as an optional embodiment, the data division module is further configured to construct a knowledge graph among the initial labels according to the initial labels preset for each data partition; establish a training data set and a test data set according to the association relationship in the knowledge graph; and train the preset model using the training data set and the test data set to obtain an association degree analysis model.

[0104] On the basis of the above embodiment, as an optional embodiment, the data division module is further configured to input the original data into the association degree analysis model corresponding to the data partition corresponding to the original data to obtain an association degree score corresponding to the original data; determine the original data with an association degree score greater than a preset threshold as the key visualization data, and determine the original data with an association degree score not greater than the preset threshold as the auxiliary visualization data.

[0105] On the basis of the above embodiment, as an optional embodiment, the data division module is further configured to adjust the standard visualization parameter according to a difference between the association degree score and the preset threshold, to obtain the target visualization parameter corresponding to the key visualization data.

[0106] On the basis of the above embodiment, as an optional embodiment, the first visualization processing module is further configured to perform deduplication processing on the auxiliary visualization data according to the standard visualization parameter corresponding to the auxiliary visualization data.

[0107] On the basis of the above embodiment, as an optional embodiment, the output module is further configured to extract a keyword from the first visualization result, and label the keyword in the target visualization result.

[0108] The embodiment of the present application further provides a computer storage medium, which can store a plurality of instructions, and the instructions are suitable for being loaded and executed by a processor to implement the data visualization processing method of the above embodiment. The specific implementation process can be referred to the specific description of the embodiment, and will not be repeated here.

[0109] Please refer to Figure 3 The embodiment of the present application provides a structural schematic diagram of an electronic device. As shown in the figure, Figure 3 The electronic device 300 can include at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0110] The communication bus 302 is used to realize the connection and communication between the components.

[0111] The user interface 303 can include a standard wired interface and a wireless interface.

[0112] The network interface 304 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0113] The processor 301 can include one or more processing cores. The processor 301 connects various parts of the server through various interfaces and lines, executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be realized in at least one of the following hardware forms: digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 301 can be integrated with a combination of one or more of the following: central processing unit (CPU), graphics processing unit (GPU), and modem. Among them, the CPU is mainly used to process the operating system, user interface and application programs; the GPU is used to render and draw the content to be displayed on the display screen; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be realized by a separate chip.

[0114] The memory 305 can include a random access memory (RAM) and can also include a read-only memory (ROM). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 305 can include a program storage area and a data storage area, where the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, etc.; the data storage area can store data involved in the various method embodiments described above, etc. The memory 305 can also optionally be at least one storage device located away from the aforementioned processor 301. As shown in Figure 3 The memory 305, as a computer storage medium, can include an operating system, a network communication module, a user interface module, and an application program of a data visualization processing method.

[0115] In the electronic device 300 shown in Figure 3 In the electronic device 300 shown in, the user interface 303 is mainly used to provide an interface for user input and obtain data input by the user; and the processor 301 can be used to call an application program of a data visualization processing method stored in the memory 305, which, when executed by one or more processors, causes the electronic device to perform the method of one or more of the above embodiments.

[0116] An electronic device readable storage medium stores instructions. When executed by one or more processors, the instructions cause the electronic device to perform the method of one or more of the above embodiments.

[0117] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the application is not limited by the described action sequence, because according to the application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the application.

[0118] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0119] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments is merely illustrative, and the units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0120] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0121] In addition, the functional units in each embodiment of the present application can be integrated into a processing unit, or each unit can be physically present separately, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0122] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for making a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, magnetic disk or optical disk, and various program codes that can be stored.

[0123] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practicing the true principles of the present disclosure. The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional techniques in the art that are not described in the present disclosure.

Claims

1. A data visualization processing method, characterized by, The method comprises: a plurality of original data input by a user; determining a data partition corresponding to each of the original data according to a data label corresponding to each of the original data; the determining of the data partition corresponding to each of the original data according to the data label corresponding to each of the original data comprises: labeling each of the original data to obtain a data label corresponding to each of the original data; comparing the data label with a preset initial label of the data partition to obtain a label comparison result; and if the label comparison result meets a preset condition, determining the data partition corresponding to the original data; constructing a knowledge graph between the initial labels according to the preset initial labels of each of the data partitions; establishing a training data set and a test data set according to the correlation in the knowledge graph; training a preset model using the training data set and the test data set to obtain a correlation analysis model; inputting the original data into the correlation analysis model corresponding to the data partition corresponding to the original data to determine key visual data and auxiliary visual data in the original data; the inputting of the original data into the correlation analysis model corresponding to the data partition corresponding to the original data to determine the key visual data and the auxiliary visual data in the original data comprises: inputting the original data into the correlation analysis model corresponding to the data partition corresponding to the original data to obtain a correlation score corresponding to the original data; determining the original data with a correlation score greater than a preset threshold as key visual data, and determining the original data with a correlation score not greater than the preset threshold as auxiliary visual data; visualizing the auxiliary visual data according to a standard visual parameter corresponding to the auxiliary visual data to obtain a first visual result corresponding to the auxiliary visual data; visualizing the key visual data according to a target visual parameter corresponding to the key visual data to obtain a second visual result corresponding to the key visual data; combining the first visual result and the second visual result to obtain a target visual result corresponding to the original data.

2. The method of claim 1, wherein, after the determining of the original data with the correlation score greater than the preset threshold as the key visual data and the determining of the original data with the correlation score not greater than the preset threshold as the auxiliary visual data, the method further comprises: adjusting the standard visual parameter according to a difference between the correlation score and the preset threshold to obtain a target visual parameter corresponding to the key visual data.

3. The method of claim 1, wherein, before the visualizing of the auxiliary visual data according to the standard visual parameter corresponding to the auxiliary visual data to obtain the first visual result corresponding to the auxiliary visual data, the method further comprises: de-duplicating the auxiliary visual data according to the standard visual parameter corresponding to the auxiliary visual data.

4. The method of claim 1, wherein, After the combination of the first visualization result and the second visualization result, the target visualization result corresponding to the plurality of original data is obtained, and the method further includes: extracting keywords of the first visualization result, and labeling the keywords in the target visualization result.

5. A data visualization processing system, characterized by, The system includes: an input module configured to input a plurality of original data in response to a user input; a data labeling module configured to determine a data partition corresponding to each of the original data according to a data label corresponding to each of the original data; the determination of the data partition corresponding to each of the original data according to the data label corresponding to each of the original data includes: labeling each of the original data to obtain a data label corresponding to each of the original data; comparing the data label with an initial label preset for the data partition to obtain a label comparison result; and determining the data partition corresponding to the original data if the label comparison result meets a preset condition; a data division module configured to construct a knowledge graph among the initial labels according to the initial labels preset for each of the data partitions; establish a training data set and a test data set according to a correlation in the knowledge graph; train a preset model using the training data set and the test data set to obtain a correlation analysis model; and input the original data into the correlation analysis model corresponding to the data partition corresponding to the original data to determine key visualization data and auxiliary visualization data in the original data; the input of the original data into the correlation analysis model corresponding to the data partition corresponding to the original data to determine the key visualization data and the auxiliary visualization data in the original data includes: inputting the original data into the correlation analysis model corresponding to the data partition corresponding to the original data to obtain a correlation score corresponding to the original data; determining the original data with a correlation score greater than a preset threshold as the key visualization data, and determining the original data with a correlation score not greater than the preset threshold as the auxiliary visualization data; a first visualization processing module configured to perform visualization processing on the auxiliary visualization data according to a standard visualization parameter corresponding to the auxiliary visualization data to obtain a first visualization result corresponding to the auxiliary visualization data; a second visualization processing module configured to perform visualization processing on the key visualization data according to a target visualization parameter corresponding to the key visualization data to obtain a second visualization result corresponding to the key visualization data; an output module configured to combine the first visualization result and the second visualization result to obtain a target visualization result corresponding to the plurality of original data, with the first visualization result as a base background layer and the second visualization result as a foreground focus layer.

6. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, and the instructions are adapted to be loaded and executed by the processor to perform the method of any one of claims 1-4.

7. An electronic device, comprising: An electronic device comprising a processor, a memory for storing instructions, and a transceiver for communicating with other devices, the processor configured to execute the instructions stored in the memory to cause the electronic device to perform the method of any one of claims 1-4.

Images