A data statistics chart dynamic display system and display method

Abstract

The present invention relates to the field of visualization technology, and discloses a data statistics chart dynamic display system and display method, including: querying the source data of the data statistics chart, optimizing the display of the data statistics chart to be displayed, and obtaining the optimized display chart; acquiring the display user, analyzing the display user's perception environment, making a first adjustment to the optimized display chart, analyzing the display user's viewing state, making a second adjustment to the optimized display chart, and obtaining a second adjusted display chart; querying the display user's historical viewing mode, analyzing the display user's viewing preference, and updating the second adjusted display chart to obtain an updated display chart; identifying the display user's display demand mode; in the first mode, interactively adjusting the updated display chart to obtain a first target display chart; in the second mode, making multiple adjustments to the updated display chart to obtain a multiple adjusted display chart, and using the multiple adjusted display chart as the second target display chart. The present invention can improve the user's viewing experience of viewing data statistics charts.

Description

Technical Field

[0001] The invention relates to a data statistical graph dynamic display system and a display method, belonging to the field of visualization technology. Background Art

[0002] Dynamic display of statistical graphs plays a key role in data analysis and decision-making. An excellent dynamic display method of statistical graphs can help users intuitively understand the changing trends and distribution of data, thereby improving the efficiency and accuracy of data analysis. At the same time, it can be customized according to different needs to meet the specific needs of different users, so as to provide more personalized data analysis services and facilitate users to quickly obtain key information in different scenarios, thereby improving the scientificity and timeliness of decision-making and improving work efficiency.

[0003] At present, the display of data statistics charts is generally achieved through static chart drawing technology, which builds a chart system with fixed style and data to achieve data visualization. However, through this method, the chart cannot reflect the changes in data in real time. Since data analysis often involves a large amount of dynamically changing data, users cannot grasp the latest situation in time when the data is constantly updated. In addition, users have different display requirements for data statistics charts in different scenarios, which makes the display of data statistics charts not flexible enough, resulting in poor user experience. Summary of the invention

[0004] The present invention provides a data statistical graph dynamic display system and a display method, the main purpose of which is to improve the viewing experience of users viewing the data statistical graph.

[0005] To achieve the above object, the present invention provides a data statistics chart dynamic display system, comprising:

[0006] A display graph optimization module is used to obtain a data statistical graph to be displayed, query the source data of the data statistical graph, construct a correlation coefficient matrix and an independence test chart of the source data, analyze the data correlation of the source data according to the correlation coefficient matrix and the independence test chart, identify the distribution characteristics and data type of the source data, and optimize the display of the data statistical graph to be displayed based on the data correlation, the distribution characteristics and the data type to obtain an optimized display graph;

[0007] A display image adjustment module is used to obtain a display user corresponding to the optimized display image, analyze the perception environment between the display user and the optimized display image, and when the perception environment does not meet the preset environment, make a first adjustment to the optimized display image to obtain a first adjusted display image, and analyze the user viewing state of the display user, and when the user viewing state does not meet the preset state, make a second adjustment to the first adjusted display image to obtain a second adjusted display image;

[0008] a display graph updating module, configured to query the historical viewing mode of the display user, analyze the viewing preference of the display user based on the historical viewing mode, and perform a graph update on the second adjusted display graph based on the viewing preference to obtain an updated display graph;

[0009] A demand pattern recognition module, used to recognize the display demand pattern of the display user;

[0010] A display image interactive adjustment module, used for querying the multimodal interactive engine of the updated display image when the display demand mode is the first mode, and interactively adjusting the updated display image by using the multimodal interactive engine to obtain a first target display image;

[0011] The target display image acquisition module is used to collect multiple display plans of the display user when the display demand mode is the second mode, and based on the multiple display plans, make multiple adjustments to the updated display image to obtain multiple adjusted display images, evaluate the chart quality of the multiple adjusted display images, and when the chart quality meets the preset quality, use the multiple adjusted display images as the second target display image.

[0012] Optionally, analyzing the data correlation of the source data according to the correlation coefficient matrix and the independence test chart includes:

[0013] Calculate the correlation coefficient value of the source data according to the correlation coefficient matrix;

[0014] Analyzing the linear closeness of the source data based on the correlation coefficient value;

[0015] Querying chart information of the independence test chart;

[0016] Analyzing data independence of the source data based on the chart information;

[0017] Based on the linear closeness and the data independence, data correlation of the source data is determined.

[0018] Optionally, calculating the correlation coefficient value of the source data according to the correlation coefficient matrix includes:

[0019] Identify the number of rows and columns of the correlation coefficient matrix to determine the data variables of the source data;

[0020] Based on the data variables, the correlation coefficient value of the source data is calculated using the following formula:

[0021] ;

[0022] in, represents the correlation coefficient value, represents the number of data variables, Indicates the first variables, Indicates the first variables, express The mean of express The mean of express No. Observations, express No. Observed values.

[0023] Optionally, the optimizing the display of the statistical graph of the data to be displayed based on the data correlation, the distribution characteristics and the data type to obtain an optimized display graph includes:

[0024] Querying the correlation strength of the data correlation;

[0025] When the correlation strength is strong;

[0026] According to the data type, the statistical graph of the data to be displayed is optimized to obtain a preliminary optimized display graph;

[0027] Based on the distribution characteristics, the data distribution form of the preliminary optimized display diagram is optimized to obtain an optimized display diagram corresponding to a strong correlation strength;

[0028] When the correlation strength is not strong;

[0029] Optimizing the individual charts of the statistical charts of the data to be displayed to obtain individual optimized charts;

[0030] Performing feature enhancement on the individual optimized graph to obtain an enhanced graph;

[0031] Special attribute annotation is performed on the enhanced chart to obtain an optimized display chart corresponding to when the correlation strength is not strong.

[0032] Optionally, performing a second adjustment on the first adjustment display image to obtain a second adjustment display image includes:

[0033] Querying the display data of the first adjustment display graph;

[0034] Performing data standardization processing on the display data to obtain standardized data;

[0035] Calculating a covariance tensor of the normalized data;

[0036] Performing tensor decomposition on the covariance tensor to obtain eigenvalues ​​and eigenvectors;

[0037] Calculating the cumulative variance contribution rate of the standardized data;

[0038] Based on the eigenvalue, the eigenvector and the cumulative variance contribution rate, simplifying the standardized data to obtain simplified data;

[0039] The simplified data is used to reconstruct the first adjusted presentation image to obtain a second adjusted presentation image.

[0040] Optionally, the calculating the covariance tensor of the standardized data includes: performing tensor quantization processing on the standardized data to obtain tensor data, and calculating the tensor mean of the tensor data using the following formula:

[0041] ;

[0042] in, Represents the mean of the tensor, A represents the size of the first dimension of the tensor data, B represents the size of the second dimension of the tensor data, C represents the size of the third dimension of the tensor data, a represents the index of the tensor data in the first dimension, b represents the index of the tensor data in the second dimension, and c represents the index of the tensor data in the third dimension. Represents the index element value of the tensor data;

[0043] According to the tensor mean, the covariance tensor of the standardized data is calculated using the following formula:

[0044] ;

[0045] in, represents the covariance tensor, represents the normalization coefficient of the covariance tensor, Represents the mean of the tensor, A represents the size of the first dimension of the tensor data, B represents the size of the second dimension of the tensor data, C represents the size of the third dimension of the tensor data, a represents the index of the tensor data in the first dimension, b represents the index of the tensor data in the second dimension, and c represents the index of the tensor data in the third dimension. Represents the index element value of the tensor data, and T represents the number of samples of the standardized data.

[0046] Optionally, analyzing the viewing preference of the display user based on the historical viewing mode includes:

[0047] Based on the historical viewing pattern, calculating the chart type preference coefficient, the dwell time preference coefficient, and the interaction frequency preference coefficient of the display user for the data statistics chart;

[0048] Based on the chart type preference coefficient, the dwell time preference coefficient and the interaction frequency preference coefficient, the comprehensive viewing preference index of the display user is calculated using the following formula:

[0049] ;

[0050] in, represents the comprehensive viewing preference index, represents the chart type preference coefficient, represents the residence time preference coefficient, represents the interaction frequency preference coefficient, express The weight of express The weight of express The weight of

[0051] The viewing preference of the display user is determined according to the comprehensive viewing preference index.

[0052] Optionally, the calculating of the chart type preference coefficient, the dwell time preference coefficient, and the interaction frequency preference coefficient of the display user for the data statistics chart based on the historical viewing mode includes:

[0053] According to the historical viewing mode, query the total number of chart views, the sum of the average stay time of all chart types and the total number of chart interactions of the display user;

[0054] Based on the total number of views of the chart, the chart type preference coefficient of the display user for the data statistics chart is calculated using the following formula:

[0055] ;

[0056] in, represents the chart type preference coefficient, Indicates the total number of chart views. Indicates the display of the user's Number of chart views;

[0057] Based on the sum of the average dwell time of all chart types, the dwell time preference coefficient of the display user for the data statistics chart is calculated using the following formula:

[0058] ;

[0059] in, represents the residence time preference coefficient, represents the sum of the average dwell time of all chart types, Indicates that the user is showing Average dwell time of each chart;

[0060] Based on the total number of interactions with the chart, the interaction frequency preference coefficient of the display user for the data statistics chart is calculated using the following formula:

[0061] ;

[0062] in, represents the interaction frequency preference coefficient, Indicates the total number of chart interactions. Indicates that the user is showing The number of interactions for this chart.

[0063] Optionally, the interactively adjusting the updated display image by using the multimodal interaction engine to obtain a first target display image includes:

[0064] Acquiring a user's voice command using the multimodal interaction engine;

[0065] Performing text parsing on the voice command to obtain a voice text command;

[0066] Performing a first interactive adjustment on the update display diagram based on the voice text instruction to obtain an interactively adjusted display diagram;

[0067] Acquiring a user's gesture command using the multimodal interaction engine;

[0068] Based on the gesture instruction, gesture adjustment is performed on the interactive adjustment display image to obtain a first target display image.

[0069] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0070] at least one processor; and,

[0071] a memory communicatively connected to the at least one processor; wherein,

[0072] 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 implement the above-mentioned data statistical chart dynamic display system.

[0073] In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned data statistical chart dynamic display system.

[0074] Compared with the problems described in the background technology, the present invention first obtains the statistical graph of the data to be displayed to help users determine the source data that needs to be analyzed. For example, if the statistical graph shows that a certain data point is abnormally high or low, the analyst may need to query the detailed data related to it to understand the reasons behind it, and according to the correlation coefficient matrix and the independence test chart, the data correlation of the source data can be analyzed to more comprehensively understand the structure and characteristics of the source data, providing a strong basis for subsequent optimization; obtaining the display user corresponding to the optimized display graph can help to clarify the target audience of the graph, so as to make subsequent adjustments and optimizations in a targeted manner. Further, the present invention updates the second adjusted display graph based on the viewing preference, and the updated display graph can realize personalized chart display, enhance the interaction and resonance between users and charts, improve the quality and value of charts, better meet the information needs of users, and identify the display user's display demand mode to optimize the display form, and different demand modes may correspond to different optimal display forms. For example, for users who focus on detail analysis, high-resolution, interactive charts may need to be provided; for users who browse quickly, concise and clear charts may be more suitable. Identifying the demand pattern helps to select the most suitable display form, and by using the multimodal interaction engine to interactively adjust the updated display graph, obtaining the first target display graph can optimize the interactivity of the graph, more accurately meet the user's demand for viewing the graph, and thus improve the user experience, and when the quality of the graph meets the preset quality, using the multiple adjusted display graph as the second target display graph can determine the graph that meets the quality requirements as the final display result, providing users with high-quality display content, and achieving the high-quality display goal under a specific display demand mode, meeting the needs of users. The present invention can improve the user's viewing experience of viewing data statistics graphs. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A schematic diagram of functional modules of a data statistics chart dynamic display system provided by an embodiment of the present invention;

[0076] Figure 2 A schematic diagram of a method flow of a data statistics chart dynamic display system provided by an embodiment of the present invention;

[0077] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0079] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0080] In fact, the server-side device deployed by the computer software and hardware intelligent interaction system may be composed of one or more devices. The above-mentioned computer software and hardware intelligent interaction system can be implemented as: business instance, virtual machine, hardware device. For example, the computer software and hardware intelligent interaction system can be implemented as a business instance deployed on one or more devices in the cloud node. In simple terms, the live broadcast service system can be understood as a software deployed on the cloud node, which is used to provide computer software and hardware intelligent interaction services to each user terminal. Alternatively, the computer software and hardware intelligent interaction system can also be implemented as a virtual machine deployed on one or more devices in the cloud node. The virtual machine is installed with application software for managing each user terminal. Alternatively, the computer software and hardware intelligent interaction system can also be implemented as a server consisting of many hardware devices of the same or different types, and one or more hardware devices are set to provide computer software and hardware intelligent interaction services to each user terminal.

[0081] In terms of implementation, the computer software and hardware intelligent interaction system and the user end are adapted to each other. That is, the computer software and hardware intelligent interaction system is an application installed on the cloud service platform, and the user end is a client that establishes a communication connection with the application; or the computer software and hardware intelligent interaction system is implemented as a website, and the user end is implemented as a web page; or the computer software and hardware intelligent interaction system is implemented as a cloud service platform, and the user end is implemented as a small program in an instant messaging application.

[0082] Reference Figure 1 FIG. 1 is a functional module diagram of a dynamic display of a data statistics chart provided by an embodiment of the present invention.

[0083] The data statistics chart dynamic display system 100 of the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed on the cloud (such as a server, server cluster, etc. of a power grid information operation and maintenance support decision system), or it can also be developed as a website. According to the functions implemented, the data statistics chart dynamic display system 100 includes a display chart optimization module 101, a display chart adjustment module 102, a display chart update module 103, a demand pattern recognition module 104, a display chart interactive adjustment module 105 and a target display chart acquisition module 106.

[0084] In an embodiment of the present invention, each module of the data statistics chart dynamic display system can be independently implemented and called with other modules. The call here can be understood as a module that can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. In the data statistics chart dynamic display system provided by the embodiment of the present invention, there is no need to modify the program code. The scope of application of the acute cerebral infarction detection architecture can be adjusted by adding modules and directly calling them to achieve cluster-based horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the data statistics chart dynamic display system. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0085] In the following, in conjunction with specific embodiments, each component of the data statistics chart dynamic display system and the specific workflow are described respectively.

[0086] The display graph optimization module 101 is used to obtain a statistical graph of the data to be displayed, query the source data of the statistical graph of the data, construct a correlation coefficient matrix and an independence test chart of the source data, analyze the data correlation of the source data according to the correlation coefficient matrix and the independence test chart, identify the distribution characteristics and data type of the source data, and optimize the display of the statistical graph of the data to be displayed based on the data correlation, the distribution characteristics and the data type to obtain an optimized display graph.

[0087] The embodiment of the present invention can help users determine the source data that needs to be analyzed by obtaining the data statistics graph to be displayed. For example, if the statistics graph shows that a data point is abnormally high or low, the analyst may need to query the detailed data related to it to understand the reason behind it. The data statistics graph refers to a tool that displays data in a graphical manner. It uses various graphic elements, such as points, lines, columns, pies, etc., to intuitively present the characteristics, relationships and trends of the data, so that people can more easily understand and analyze the data.

[0088] The embodiment of the present invention can deeply understand the specific content and details of the data by querying the source data of the data statistical graph, providing a basis for subsequent analysis and optimization. Wherein, the source data refers to an unprocessed or initially generated data set.

[0089] Furthermore, the embodiment of the present invention can analyze in detail the potential relationship between each data in the source data by constructing the correlation coefficient matrix and independence test chart of the source data. The correlation coefficient matrix refers to a matrix used to measure the degree of linear correlation between multiple variables, and the independence test chart refers to a visualization tool used to test whether two or more variables are independent of each other.

[0090] The embodiment of the present invention can more comprehensively understand the structure and characteristics of the source data by analyzing the data correlation of the source data according to the correlation coefficient matrix and the independence test chart, thereby providing a strong basis for subsequent optimization.

[0091] As an embodiment of the present invention, analyzing the data correlation of the source data according to the correlation coefficient matrix and the independence test chart includes: calculating the correlation coefficient value of the source data according to the correlation coefficient matrix, analyzing the linear closeness of the source data based on the correlation coefficient value, querying the chart information of the independence test chart, analyzing the data independence of the source data based on the chart information, and determining the data correlation of the source data based on the linear closeness and the data independence.

[0092] Among them, the correlation coefficient value refers to a numerical value used to measure the degree of linear correlation between two variables, the linear closeness refers to the closeness of the linear relationship between each variable in the source data, the chart information refers to the various data and symbols contained in the independence test chart, and the data independence refers to the degree of independence between each variable in the source data.

[0093] Exemplarily, in an optional embodiment of the present invention, the calculating the correlation coefficient value of the source data according to the correlation coefficient matrix includes: identifying the number of rows and columns of the correlation coefficient matrix to determine the data variables of the source data, and based on the data variables, calculating the correlation coefficient value of the source data using the following formula:

[0094] ;

[0095] in, represents the correlation coefficient value, represents the number of data variables, Indicates the first variables, Indicates the first variables, express The mean of express The mean of express No. Observations, express No. Observed values.

[0096] Optionally, the linear closeness of the source data analyzed based on the correlation coefficient value can be obtained by identifying the calculation result of the correlation coefficient value. Assuming that the range of the correlation coefficient value is between -1 and 1, if most of the correlation coefficient values ​​are close to -1 or 1, it means that the linear closeness between the variables of the source data is relatively high (can be set to -1 to -0.6, 1 to 0.6). If most of the correlation coefficient values ​​are close to 0, it means that the linear closeness between the variables of the source data is relatively low (can be set to 0 to 0.6, -0.6 to 0). The specific setting can be based on the actual application scenario. The data independence of the source data analyzed based on the chart information can be obtained by calculating the chart. The statistical value of the information (such as the chi-square value) is obtained. If the statistical value is small and the p-value is large (usually greater than the set significance level, such as 0.05), it can be considered that the variables are independent of each other. If the statistical value is large and the p-value is small, it can be considered that the variables are not independent. The data correlation of the source data based on the linear closeness and the data independence can be determined by comprehensively considering the analysis results of the linear closeness and data independence. If the linear closeness is high and the data independence is low, it means that there is a strong linear correlation between the variables. If the linear closeness is low and the data independence is high, it means that there is almost no linear relationship between the variables and they are independent of each other.

[0097] The embodiment of the present invention can help users select the most appropriate chart by identifying the distribution characteristics and data types of the source data, so that the distribution and characteristics of the data can be clearly presented. For example, normally distributed data can be displayed using a bar chart or a histogram, while skewed distributed data may require special processing. The distribution characteristics refer to the distribution and characteristics of the data in the population, such as central tendency, degree of dispersion, and distribution form, and the data type refers to the nature and characteristics of the data, such as numerical data, categorical data, and time series data.

[0098] Optionally, the distribution characteristics of the source data can be identified by drawing charts such as histograms and box plots to observe the distribution pattern of the data, and the data type can be identified by checking the field type of the source data.

[0099] Furthermore, the embodiment of the present invention optimizes the display of the data statistical graph to be displayed based on the data correlation, the distribution characteristics and the data type, and obtains the optimized display graph, which can perform targeted optimization on the data statistical graph, so that it can convey information more accurately and clearly, and improve the effect of data visualization, thereby better meeting the needs of users and helping users understand the meaning and trends of data more quickly.

[0100] As an embodiment of the present invention, the display optimization of the statistical graph of the data to be displayed based on the data correlation, the distribution characteristics and the data type to obtain an optimized display graph includes: querying the correlation strength of the data correlation, and when the correlation strength is strong, performing graphical optimization on the statistical graph of the data to be displayed according to the data type to obtain a preliminary optimized display graph; based on the distribution characteristics, performing data distribution morphology optimization on the preliminary optimized display graph to obtain an optimized display graph corresponding to when the correlation strength is strong; when the correlation strength is not strong, performing individual chart optimization on the statistical graph of the data to be displayed to obtain an individual optimized chart; performing feature enhancement on the individual optimized chart to obtain an enhanced chart; and marking the enhanced chart with special attributes to obtain an optimized display graph corresponding to when the correlation strength is not strong.

[0101] It should be noted that the correlation strength of the data correlation can be determined based on the correlation coefficient value. If the correlation coefficient value is in the range of -1 to -0.6, 1 to 0.6, it means that the correlation strength is strong. If the correlation coefficient value is between 0 to 0.6, -0.6 to 0, it means that the correlation strength is weak.

[0102] Optionally, the process of performing graphic optimization on the statistical graph of the data to be displayed is as follows: determining the data type corresponding to the statistical graph of the data to be displayed. If it is numerical data, the width and spacing of the columns of the bar graph can be adjusted to make it more compact to highlight the correlation. For the line graph, the lines can be made thicker and more obvious, and the colors can be made brighter to emphasize the consistency of the trend. If it is categorized data, color coding can be used to highlight related category combinations, such as using the same color system to represent related categories; the process of performing data distribution morphology optimization on the preliminary optimized display graph is as follows: determining the data analysis distribution characteristics corresponding to the statistical graph of the data to be displayed, including the central tendency of the data (such as mean, median), degree of dispersion (such as standard deviation, variance), skewness, etc. If the data is normally distributed, a normal curve can be added to the graph. If the data is skewed, annotations can be added to the graph to explain the direction and degree of skewness, or appropriate transformation methods (such as logarithmic transformation) can be used to make the data The data is closer to normal distribution before being displayed; the process of optimizing the individual charts of the statistical charts to be displayed to obtain the individual optimized charts is as follows: targeted optimization is performed on different types of statistical charts. For example, for a bar chart, the color and border of the column can be adjusted to make it more beautiful. For a line chart, data point marks can be added to make the data clearer and more readable. The process of enhancing the features of the individual optimized charts to obtain the enhanced charts is as follows: if it is numerical data, a data label can be added using a script generated by java to display the specific value, or a trend line, a fitting curve, etc. can be added to highlight the characteristics of the data. If it is categorized data, the clarity of the legend can be increased, or different shapes or patterns can be used to distinguish different categories; the process of marking special attributes of the enhanced charts is as follows: identifying special attributes in the data, such as outliers, outliers, etc., marking them out using special symbols or colors, and adding annotations next to the charts to explain the situation of the outliers.

[0103] The display image adjustment module 102 is used to obtain the display user corresponding to the optimized display image, analyze the perception environment between the display user and the optimized display image, and when the perception environment does not meet the preset environment, perform a first adjustment on the optimized display image to obtain a first adjusted display image, analyze the user viewing status of the display user, and when the user viewing status does not meet the preset status, perform a second adjustment on the first adjusted display image to obtain a second adjusted display image.

[0104] The embodiment of the present invention can help clarify the target audience of the chart by obtaining the display user corresponding to the optimized display chart, so as to carry out subsequent adjustments and optimizations in a targeted manner. It can be obtained by identifying the user's query information. For example, when a user views a statistical chart, the user information can be obtained by logging in.

[0105] Furthermore, the embodiment of the present invention can understand the actual situation of the display user when viewing the chart by analyzing the perceptual environment between the display user and the optimized display chart, so as to better adapt to these situations and improve the readability and usability of the chart.

[0106] It should be noted that the perception environment in the present invention refers to a light environment, which can be obtained through a light sensor.

[0107] It should be noted that when the perception environment does not meet the preset environment, it means that the light condition does not meet the preset light condition, that is, when the user views the statistical chart, he will feel uncomfortable or have a poor viewing experience. The preset environment can be determined by setting the preset standard of the perception environment according to the needs and actual conditions of the display user. For example, the preset light intensity range, background color contrast requirements, device resolution adaptation standards, etc.

[0108] Furthermore, the embodiment of the present invention can improve the adaptability and robustness of the chart by performing the first adjustment on the optimized display chart to obtain the first adjusted display chart, so that it can effectively convey information in various possible environments without losing its value due to environmental factors, providing users with a better visual experience, so that they can easily view and understand the chart no matter what environment they are in.

[0109] As an embodiment of the present invention, the first adjustment of the optimized display image to obtain the first adjusted display image includes: querying the light intensity level in the perceived environment, and when the light intensity level does not meet the preset intensity, adjusting the color brightness and contrast of the optimized display image until the light intensity level meets the preset intensity; querying the background color contrast in the perceived environment, and when the background color contrast does not meet the preset level, adjusting the color brightness of the optimized display image until the background color contrast meets the preset level.

[0110] It should be noted that when the light intensity level does not meet the preset intensity, it means that the light intensity is higher or lower than the preset intensity. The preset intensity can be set by considering the application scenario. For example, in offices, shopping malls and other environments, you can refer to the indoor lighting standards. Generally speaking, the lighting intensity in offices is usually around 300-500 lux, and shopping malls may be higher. The preset light intensity value can be set to a value within this range based on specific display needs and human eye comfort. It can be set by considering the human eye's perception. The human eye has a limited range of adaptation to light. Too strong or too weak light will affect the visual effect and comfort. Generally speaking, the human eye is in a more comfortable environment with a light intensity of 200-1000 lux. When the background color contrast does not meet the preset level, it means that the background color contrast is higher or lower than the preset level. The preset level can be set by considering environmental factors. The background color contrast will also be affected by the ambient light. In strong light, a higher contrast is required to make the display image clearly visible; in weak light, a lower contrast may be more comfortable. The background color contrast preset value can be dynamically adjusted according to different environmental conditions.

[0111] Optionally, the process of adjusting the color brightness and contrast of the optimized display image is as follows: if the light intensity is low, the color brightness of the optimized display image can be increased; if the light intensity is high, the color brightness can be reduced; the process of adjusting the color brightness of the optimized display image is as follows: if the background color contrast is low, the color brightness of the optimized display image can be increased; if the background color is darker, the brightness of the display image can be increased.

[0112] The embodiment of the present invention can understand the user's current static and dynamic situation by analyzing the user's viewing state of the display user, and then adjust the statistical chart to make the user's viewing more comfortable. The user viewing state refers to the state of the user viewing the data statistical chart, such as walking, riding in a car, and sitting still indoors.

[0113] It should be noted that, when the viewing state of the user does not satisfy the preset state, it means that the user is in a non-static state.

[0114] Furthermore, in the embodiment of the present invention, by performing a second adjustment on the first adjustment display graph to obtain a second adjustment display graph, the user's viewing comfort of the graph can be improved.

[0115] As an embodiment of the present invention, the second adjustment is performed on the first adjusted display graph to obtain a second adjusted display graph, including: querying the display data of the first adjusted display graph, performing data standardization on the display data to obtain standardized data, calculating the covariance tensor of the standardized data, performing tensor decomposition on the covariance tensor to obtain eigenvalues ​​and eigenvectors, calculating the cumulative variance contribution rate of the standardized data, simplifying the standardized data based on the eigenvalues, the eigenvectors and the cumulative variance contribution rate to obtain simplified data, and reconstructing the display graph of the first adjusted display graph using the simplified data to obtain the second adjusted display graph.

[0116] The covariance tensor refers to a multidimensional array used to describe the covariance relationship between different dimensions of high-dimensional data, and the cumulative variance contribution rate refers to an indicator used to measure the proportion of the total variance of the original data that can be explained by these principal components after selecting several principal components.

[0117] Optionally, the data standardization processing of the displayed data can be achieved by the Z-score standardization technology, the tensor decomposition of the covariance tensor can be performed by a tensor decomposition algorithm, such as singular value decomposition (SVD), principal component analysis and other methods, the calculation of the cumulative variance contribution rate of the standardized data can be performed by a simple calculation of accumulating eigenvalues ​​and comparing them with the total variance, and can be achieved with the help of basic mathematical operation functions in a programming language (such as Python), and the process of simplifying the standardized data based on the eigenvalues, the eigenvectors and the cumulative variance contribution rate to obtain simplified data is: using principal component analysis (PCA) related technology, according to a preset threshold of the cumulative variance contribution rate, the main eigenvectors are selected for data projection to simplify the data, wherein the preset threshold can be set to 80% - 95%. For example, when analyzing the gene expression data of a large number of biological samples, if the threshold is set to 85%, it means that the user hopes to select principal components so that these principal components can explain 85% of the variance in the original gene expression data. In this way, in the subsequent analysis, although the data dimension is greatly reduced, most of the key information is still retained, which is sufficient for discovering the main difference patterns between different samples, performing cluster analysis and other operations. The use of the simplified data to reconstruct the first adjusted display graph can be performed through an image reconstruction algorithm, based on the simplified data and the original structural information of the display graph, using a drawing library (such as Python's Matplotlib, etc.) to redraw the display graph to obtain a second adjusted display graph.

[0118] Furthermore, in another optional embodiment of the present invention, the calculating the covariance tensor of the standardized data includes: performing tensor quantization processing on the standardized data to obtain tensor data, and calculating the tensor mean of the tensor data using the following formula:

[0119] ;

[0120] in, Represents the mean of the tensor, A represents the size of the first dimension of the tensor data, B represents the size of the second dimension of the tensor data, C represents the size of the third dimension of the tensor data, a represents the index of the tensor data in the first dimension, b represents the index of the tensor data in the second dimension, and c represents the index of the tensor data in the third dimension. Represents the index element value of the tensor data;

[0121] According to the tensor mean, the covariance tensor of the standardized data is calculated using the following formula:

[0122] ;

[0123] in, represents the covariance tensor, represents the normalization coefficient of the covariance tensor, Represents the mean of the tensor, A represents the size of the first dimension of the tensor data, B represents the size of the second dimension of the tensor data, C represents the size of the third dimension of the tensor data, a represents the index of the tensor data in the first dimension, b represents the index of the tensor data in the second dimension, and c represents the index of the tensor data in the third dimension. Represents the index element value of the tensor data, and T represents the number of samples of the standardized data.

[0124] The display graph updating module 103 is used to query the historical viewing mode of the display user, analyze the viewing preference of the display user based on the historical viewing mode, and update the second adjusted display graph based on the viewing preference to obtain an updated display graph.

[0125] In the embodiment of the present invention, by querying the display user's historical viewing mode, the user's needs and preferences can be better understood so as to perform more targeted chart optimization. The user's historical viewing mode can be determined by querying the user's browsing history, click behavior, dwell time and other data.

[0126] Furthermore, the embodiment of the present invention can clarify the user's preferences in terms of chart type, color, layout, etc. by analyzing the viewing preferences of the display user based on the historical viewing mode, thereby providing specific direction and focus for chart updating.

[0127] As an embodiment of the present invention, analyzing the viewing preference of the display user based on the historical viewing mode includes: calculating the display user's chart type preference coefficient, residence time preference coefficient, and interaction frequency preference coefficient for the data statistics chart based on the historical viewing mode, and calculating the display user's comprehensive viewing preference index based on the chart type preference coefficient, the residence time preference coefficient, and the interaction frequency preference coefficient using the following formula:

[0128] ;

[0129] in, represents the comprehensive viewing preference index, represents the chart type preference coefficient, represents the residence time preference coefficient, represents the interaction frequency preference coefficient, express The weight of express The weight of express The weight of

[0130] The viewing preference of the display user is determined according to the comprehensive viewing preference index.

[0131] Optionally, the viewing preference of the displayed user can be determined based on the comprehensive viewing preference index by comparing the comprehensive viewing preference index with a preset index. If the comprehensive viewing preference index is greater than the preset index, it means that the displayed user has a preference for this type of mode. If the comprehensive viewing preference index is not greater than the preset index, it means that the displayed user has a general preference for this type of mode. The preset index can be set to 0.6, or can be set according to an actual application scenario.

[0132] Among them, the chart type preference coefficient refers to the user's relative preference for different chart types, the dwell time preference coefficient refers to an indicator that measures the relative importance of the user's dwell time on different chart types, and the interaction frequency preference coefficient refers to the relative frequency of the user's interactive operations on different chart types.

[0133] Exemplarily, the calculation of the display user's chart type preference coefficient, dwell time preference coefficient, and interaction frequency preference coefficient for the data statistical chart based on the historical viewing pattern includes: querying the display user's total chart viewing times, the average dwell time sum of all chart types, and the total chart interaction times according to the historical viewing pattern, and based on the total chart viewing times, calculating the display user's chart type preference coefficient for the data statistical chart using the following formula:

[0134] ;

[0135] in, represents the chart type preference coefficient, Indicates the total number of chart views. Indicates the display of the user's Number of chart views;

[0136] Based on the sum of the average dwell time of all chart types, the dwell time preference coefficient of the display user for the data statistics chart is calculated using the following formula:

[0137] ;

[0138] in, represents the residence time preference coefficient, represents the sum of the average dwell time of all chart types, Indicates that the user is showing Average dwell time of each chart;

[0139] Based on the total number of interactions with the chart, the interaction frequency preference coefficient of the display user for the data statistics chart is calculated using the following formula:

[0140] ;

[0141] in, represents the interaction frequency preference coefficient, Indicates the total number of chart interactions. Indicates that the user is showing The number of interactions for this chart.

[0142] Furthermore, the embodiment of the present invention updates the second adjusted display chart based on the viewing preference to obtain an updated display chart, which can achieve personalized chart display, enhance the interaction and resonance between the user and the chart, improve the quality and value of the chart, and better meet the user's information needs.

[0143] Optionally, the process of updating the second adjusted display graph based on the viewing preference to obtain the updated display graph is as follows: if the user prefers bright colors, the color scheme of the graph can be adjusted to use brighter colors; if the user likes a simple layout, some unnecessary graph elements can be removed to make the graph more concise and clear; based on the user's preference for a specific graph type, consider converting the second adjusted display graph to the user's favorite graph type, or incorporating the user's preferred graph elements into the existing graph.

[0144] The demand pattern identification module 104 is used to identify the display demand pattern of the display user.

[0145] The embodiment of the present invention can optimize the display form by identifying the display demand pattern of the display user, and different demand patterns may correspond to different optimal display forms. For example, for users who focus on detail analysis, high-resolution, interactive charts may need to be provided; for users who browse quickly, concise and clear charts may be more appropriate. Identifying the demand pattern helps to select the most suitable display form. Among them, the display demand pattern refers to a single-person viewing mode and a multi-person interactive viewing mode.

[0146] Optionally, the display demand pattern may be identified by identifying the number of information logins of display users.

[0147] The display image interactive adjustment module 105 is used to query the multimodal interaction engine of the updated display image when the display demand mode is the first mode, and use the multimodal interaction engine to interactively adjust the updated display image to obtain a first target display image.

[0148] It should be noted that when the display demand mode is the first mode, it refers to a single-person viewing mode.

[0149] As an embodiment of the present invention, the multimodal interaction engine for querying the updated display graph can provide technical support and tools for subsequent interaction adjustments. The multimodal interaction engine refers to a technical component that can integrate multiple interaction modes to achieve more natural and efficient interaction between users and the system.

[0150] Optionally, the multimodal interaction engine can be obtained by querying an API interface of a data statistical graph to be displayed.

[0151] Furthermore, the embodiment of the present invention can optimize the interactivity of the chart by utilizing the multimodal interaction engine to interactively adjust the updated display chart to obtain the first target display chart, more accurately meet the user's needs for viewing the chart, and thus improve the user experience.

[0152] As an embodiment of the present invention, the method of using the multimodal interaction engine to interactively adjust the updated display image to obtain a first target display image includes: using the multimodal interaction engine to obtain a user's voice instruction, performing text parsing on the voice instruction to obtain a voice-to-text instruction, performing a first interactive adjustment on the updated display image based on the voice-to-text instruction to obtain an interactively adjusted display image, and using the multimodal interaction engine to obtain a user's gesture instruction, and performing a gesture adjustment on the interactively adjusted display image based on the gesture instruction to obtain a first target display image.

[0153] The voice command refers to an adjustment command issued by a user's voice, and the gesture command refers to an adjustment command issued by a user's gesture.

[0154] Optionally, the voice command can be obtained through the voice recognition engine in the multimodal interaction engine, and the voice text command can be obtained by text parsing the voice command through natural language processing technology. The first interactive adjustment of the updated display diagram based on the voice text command can be obtained by using a chart generation tool and a data interface to generate a corresponding statistical chart according to the instruction. For example, the user can say "enlarge the chart", "switch to a line chart", "show the next data series" and other instructions, and the system performs corresponding operations according to the instructions. It should be noted that after obtaining the interactive adjustment display diagram, speech synthesis technology can be used again, such as Google Cloud Text-to-Speech to convert data interpretation and description into voice output and feedback to the user. After the user confirms, the adjustment is completed. The gesture instruction can be obtained by identifying the user's gesture operation through a gesture sensor. The gesture adjustment of the interactive adjustment display diagram based on the gesture instruction to obtain the first target display diagram can be obtained by converting different gesture actions into corresponding interactive operation instructions through a gesture recognition algorithm. For example, a gesture recognition model based on machine learning is used to classify and recognize user gestures.

[0155] The target display image acquisition module 106 is used to collect multiple display plans of the display user when the display demand mode is the second mode, and based on the multiple display plans, make multiple adjustments to the updated display image to obtain a multiple adjusted display image, evaluate the chart quality of the multiple adjusted display image, and when the chart quality meets the preset quality, use the multiple adjusted display image as the second target display image.

[0156] The embodiment of the present invention can clarify the current specific display demand scenario by collecting multiple display plans of the display user when the display demand mode is the second mode, and provide targeted direction for subsequent operations. The second mode refers to the multi-person interactive viewing mode.

[0157] Optionally, the multiple display schemes may be collected through an online feedback platform.

[0158] Furthermore, the embodiment of the present invention performs multiple adjustments to the updated display diagram based on the multiple display schemes to obtain a multiple adjusted display diagram. The diagram can be modified and optimized in various aspects according to the collected multiple schemes to adapt to the needs and expectations of different users, thereby meeting the diverse needs of different users and improving the versatility and adaptability of the diagram.

[0159] Optionally, based on the multiple display schemes, multiple adjustments are made to the updated display graph to obtain the multiple adjusted display graph by performing color adjustments based on the color preferences proposed by the user, performing data highlighting adjustments based on certain key data that the user wishes to highlight, and performing layout adjustments based on the user's feedback on the layout adjustment of the chart, and retaining each adjustment to generate multiple adjustment results.

[0160] Furthermore, the example of the present invention can evaluate the quality of the adjusted charts through specific standards and methods through the evaluation of the chart quality of the multiple adjusted display charts, and determine whether they meet certain quality requirements, thereby ensuring that the final displayed charts have high quality and can effectively convey information, thereby avoiding low-quality displays that affect user understanding and use.

[0161] As an embodiment of the present invention, the evaluating the chart quality of the multiple adjustment display images includes: performing clarity evaluation on the multiple adjustment display images to obtain clarity evaluation results, performing accuracy evaluation on the multiple adjustment display images to obtain accuracy evaluation results, performing aesthetics evaluation on the multiple adjustment display images to obtain aesthetics evaluation results, performing practicality evaluation on the multiple adjustment display images to obtain practicality evaluation results, and determining the chart quality of the multiple adjustment display images based on the clarity evaluation results, the accuracy evaluation results, the aesthetics evaluation results and the practicality evaluation results.

[0162] Among them, the clarity assessment refers to checking whether the data in the chart is clear and readable, whether the labels are clear, and avoiding ambiguity or confusion. The accuracy assessment refers to checking whether the data in the chart is accurate and consistent with the original data. The aesthetics assessment refers to evaluating the aesthetics of the chart from aspects such as color matching, layout rationality, and visual effects. The practicality assessment refers to considering the practicality of the chart in actual use, such as whether it is easy to understand and whether it can quickly convey key information.

[0163] It should be explained that the clarity evaluation, the accuracy evaluation, the aesthetics evaluation and the practicality evaluation are all evaluated by collecting the ratings of different users in the second mode and averaging them.

[0164] The embodiment of the present invention can determine a chart that meets the quality requirements as the final display result by using the multiple adjusted display chart as the second target display chart when the quality of the chart meets the preset quality, thereby providing users with high-quality display content and achieving high-quality display goals under a specific display demand mode, thereby meeting the needs of users.

[0165] It should be noted that the preset quality refers to the scoring value obtained by combining the clarity evaluation result, the accuracy evaluation result, the aesthetics evaluation result and the practicality evaluation result. For example, the user's average clarity evaluation of Figure a is 90 points, the average accuracy evaluation is 100, the average aesthetics evaluation is 95, and the average practicality evaluation result is 95 (the full score is 100), then the average score of Figure a is 95. The preset quality means that the average score reaches 90 points (which can be set in combination with actual application). In this case, Figure a can be set as the final target figure, and if they have the same highest score, they can be displayed together.

[0166] Reference Figure 2 FIG. 1 is a flow chart of a method for dynamically displaying a data statistical graph provided by an embodiment of the present invention. In this embodiment, the computer software and hardware intelligent interaction method includes:

[0167] Obtain a data statistical graph to be displayed, query source data of the data statistical graph, construct a correlation coefficient matrix and an independence test chart of the source data, analyze the data correlation of the source data according to the correlation coefficient matrix and the independence test chart, identify the distribution characteristics and data type of the source data, and optimize the display of the data statistical graph to be displayed based on the data correlation, the distribution characteristics and the data type to obtain an optimized display graph;

[0168] Acquire a display user corresponding to the optimized display image, analyze a perception environment between the display user and the optimized display image, and when the perception environment does not satisfy a preset environment, make a first adjustment to the optimized display image to obtain a first adjusted display image, analyze a user viewing state of the display user, and when the user viewing state does not satisfy a preset state, make a second adjustment to the first adjusted display image to obtain a second adjusted display image;

[0169] querying the historical viewing mode of the display user, analyzing the viewing preference of the display user based on the historical viewing mode, and updating the second adjusted display graph based on the viewing preference to obtain an updated display graph;

[0170] Identifying the display demand pattern of the display user;

[0171] When the display demand mode is the first mode, querying the multimodal interaction engine of the updated display image, and using the multimodal interaction engine to interactively adjust the updated display image to obtain a first target display image;

[0172] When the display demand mode is the second mode, multiple display plans of the display user are collected, and based on the multiple display plans, multiple adjustments are made to the updated display graph to obtain a multiple adjusted display graph, and the chart quality of the multiple adjusted display graph is evaluated. When the chart quality meets the preset quality, the multiple adjusted display graph is used as the second target display graph.

[0173] In the several embodiments provided by the present invention, it should be understood that the provided system and method can be implemented in other ways. For example, the system embodiment described above is only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0174] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0175] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A data statistics chart dynamic display system, characterized in that: The system comprises: a display graph optimization module, a display graph adjustment module, a display graph update module, a demand pattern recognition module, a display graph interactive adjustment module, and a target display graph acquisition module; A display graph optimization module is used to obtain a data statistical graph to be displayed, query the source data of the data statistical graph, construct a correlation coefficient matrix and an independence test chart of the source data, analyze the data correlation of the source data according to the correlation coefficient matrix and the independence test chart, identify the distribution characteristics and data type of the source data, and optimize the display of the data statistical graph to be displayed based on the data correlation, the distribution characteristics and the data type to obtain an optimized display graph; A display image adjustment module is used to obtain a display user corresponding to the optimized display image, analyze the perception environment between the display user and the optimized display image, and when the perception environment does not meet the preset environment, make a first adjustment to the optimized display image to obtain a first adjusted display image, analyze the user viewing state of the display user, and when the user viewing state does not meet the preset state, make a second adjustment to the first adjusted display image to obtain a second adjusted display image, wherein the second adjustment to the first adjusted display image to obtain the second adjusted display image includes: querying display data of the first adjusted display image, performing data standardization processing on the display data to obtain standardized data, calculating the covariance tensor of the standardized data, performing tensor decomposition on the covariance tensor to obtain eigenvalues ​​and eigenvectors, calculating the cumulative variance contribution rate of the standardized data, simplifying the standardized data based on the eigenvalues, the eigenvectors and the cumulative variance contribution rate to obtain simplified data, and reconstructing the display image of the first adjusted display image using the simplified data to obtain the second adjusted display image; Further, the calculating the covariance tensor of the standardized data includes: performing tensor quantization processing on the standardized data to obtain tensor data, and calculating the tensor mean of the tensor data using the following formula: ； in, Represents the mean of the tensor, A represents the size of the first dimension of the tensor data, B represents the size of the second dimension of the tensor data, C represents the size of the third dimension of the tensor data, a represents the index of the tensor data in the first dimension, b represents the index of the tensor data in the second dimension, and c represents the index of the tensor data in the third dimension. Represents the index element value of the tensor data, According to the tensor mean, the covariance tensor of the standardized data is calculated using the following formula: ； in, represents the covariance tensor, represents the normalization coefficient of the covariance tensor, Represents the mean of the tensor, A represents the size of the first dimension of the tensor data, B represents the size of the second dimension of the tensor data, C represents the size of the third dimension of the tensor data, a represents the index of the tensor data in the first dimension, b represents the index of the tensor data in the second dimension, and c represents the index of the tensor data in the third dimension. Represents the index element value of the tensor data, and T represents the number of samples of the standardized data; a display graph updating module, configured to query the historical viewing mode of the display user, analyze the viewing preference of the display user based on the historical viewing mode, and perform a graph update on the second adjusted display graph based on the viewing preference to obtain an updated display graph; A demand pattern recognition module, used to recognize the display demand pattern of the display user; A display image interactive adjustment module, used for querying the multimodal interactive engine of the updated display image when the display demand mode is the first mode, and interactively adjusting the updated display image by using the multimodal interactive engine to obtain a first target display image; The target display image acquisition module is used to collect multiple display plans of the display user when the display demand mode is the second mode, and based on the multiple display plans, make multiple adjustments to the updated display image to obtain multiple adjusted display images, evaluate the chart quality of the multiple adjusted display images, and when the chart quality meets the preset quality, use the multiple adjusted display images as the second target display image.

2. A data statistics chart dynamic display system as claimed in claim 1, characterized in that: The step of analyzing the data correlation of the source data according to the correlation coefficient matrix and the independence test chart includes: Calculate the correlation coefficient value of the source data according to the correlation coefficient matrix; Analyzing the linear closeness of the source data based on the correlation coefficient value; Querying chart information of the independence test chart; Analyzing data independence of the source data based on the chart information; Based on the linear closeness and the data independence, data correlation of the source data is determined.

3. A data statistics chart dynamic display system as claimed in claim 2, characterized in that: The calculating the correlation coefficient value of the source data according to the correlation coefficient matrix includes: Identify the number of rows and columns of the correlation coefficient matrix to determine the data variables of the source data; Based on the data variables, the correlation coefficient value of the source data is calculated using the following formula: ； in, represents the correlation coefficient value, represents the number of data variables, represents the i-th variable in the data variable, represents the jth variable in the data variable, express The mean of express The mean of express The kth observation of express The kth observation of .

4. A data statistics chart dynamic display system as claimed in claim 1, characterized in that: The step of optimizing the data statistical graph to be displayed based on the data correlation, the distribution characteristics and the data type to obtain an optimized display graph includes: Querying the correlation strength of the data correlation; When the correlation strength is strong; According to the data type, the data statistical graph to be displayed is graphically optimized to obtain a preliminary optimized display graph; Based on the distribution characteristics, the data distribution form of the preliminary optimized display diagram is optimized to obtain an optimized display diagram corresponding to a strong correlation strength; When the correlation strength is not strong; Optimizing the individual charts of the data statistics charts to be displayed to obtain individual optimized charts; Performing feature enhancement on the individual optimized graph to obtain an enhanced graph; Special attribute annotation is performed on the enhanced chart to obtain an optimized display chart corresponding to when the correlation strength is not strong.

5. A data statistics chart dynamic display system as claimed in claim 1, characterized in that: The analyzing the viewing preference of the display user based on the historical viewing mode includes: Based on the historical viewing pattern, calculating the chart type preference coefficient, the dwell time preference coefficient, and the interaction frequency preference coefficient of the display user for the data statistics chart; Based on the chart type preference coefficient, the dwell time preference coefficient and the interaction frequency preference coefficient, the comprehensive viewing preference index of the display user is calculated using the following formula: ； in, represents the comprehensive viewing preference index, represents the chart type preference coefficient, represents the residence time preference coefficient, represents the interaction frequency preference coefficient, express The weight of express The weight of express The weight of The viewing preference of the display user is determined according to the comprehensive viewing preference index.

6. A data statistics chart dynamic display system as claimed in claim 5, characterized in that: The calculating, based on the historical viewing mode, the chart type preference coefficient, the dwell time preference coefficient, and the interaction frequency preference coefficient of the display user for the data statistics chart includes: According to the historical viewing mode, query the total number of chart views, the sum of the average stay time of all chart types and the total number of chart interactions of the display user; Based on the total number of views of the chart, the chart type preference coefficient of the display user for the data statistics chart is calculated using the following formula: ； in, represents the chart type preference coefficient, Indicates the total number of chart views. Indicates the number of times the user has viewed the i-th chart; Based on the sum of the average dwell time of all chart types, the dwell time preference coefficient of the display user for the data statistics chart is calculated using the following formula: ； in, represents the residence time preference coefficient, represents the sum of the average dwell time of all chart types, Indicates the average time users stay on the i-th chart; Based on the total number of interactions with the chart, the interaction frequency preference coefficient of the display user for the data statistics chart is calculated using the following formula: ； in, represents the interaction frequency preference coefficient, Indicates the total number of chart interactions. Indicates the number of interactions of displayed users on the i-th chart.

7. A data statistics chart dynamic display system as claimed in claim 1, characterized in that: The interactively adjusting the updated display image by using the multimodal interaction engine to obtain a first target display image includes: Acquiring a user's voice command using the multimodal interaction engine; Performing text parsing on the voice command to obtain a voice text command; Performing a first interactive adjustment on the update display diagram based on the voice text instruction to obtain an interactively adjusted display diagram; Acquiring a user's gesture command using the multimodal interaction engine; Based on the gesture instruction, gesture adjustment is performed on the interactive adjustment display image to obtain a first target display image.

8. A method for dynamically displaying a data statistical graph, characterized in that: The method comprises: Obtain a data statistical graph to be displayed, query source data of the data statistical graph, construct a correlation coefficient matrix and an independence test chart of the source data, analyze the data correlation of the source data according to the correlation coefficient matrix and the independence test chart, identify the distribution characteristics and data type of the source data, and optimize the display of the data statistical graph to be displayed based on the data correlation, the distribution characteristics and the data type to obtain an optimized display graph; Obtaining a display user corresponding to the optimized display image, analyzing a perception environment between the display user and the optimized display image, and when the perception environment does not satisfy a preset environment, performing a first adjustment on the optimized display image to obtain a first adjusted display image, analyzing a user viewing state of the display user, and when the user viewing state does not satisfy a preset state, performing a second adjustment on the first adjusted display image to obtain a second adjusted display image, wherein the second adjustment on the first adjusted display image to obtain the second adjusted display image includes: querying display data of the first adjusted display image, performing data standardization processing on the display data to obtain standardized data, calculating a covariance tensor of the standardized data, performing tensor decomposition on the covariance tensor to obtain eigenvalues ​​and eigenvectors, calculating a cumulative variance contribution rate of the standardized data, performing data simplification on the standardized data based on the eigenvalues, the eigenvectors and the cumulative variance contribution rate to obtain simplified data, and reconstructing the first adjusted display image using the simplified data to obtain a second adjusted display image; Further, the calculating the covariance tensor of the standardized data includes: performing tensor quantization processing on the standardized data to obtain tensor data, and calculating the tensor mean of the tensor data using the following formula: ； in, Represents the mean of the tensor, A represents the size of the first dimension of the tensor data, B represents the size of the second dimension of the tensor data, C represents the size of the third dimension of the tensor data, a represents the index of the tensor data in the first dimension, b represents the index of the tensor data in the second dimension, and c represents the index of the tensor data in the third dimension. Represents the index element value of the tensor data, According to the tensor mean, the covariance tensor of the standardized data is calculated using the following formula: ； in, represents the covariance tensor, represents the normalization coefficient of the covariance tensor, Represents the mean of the tensor, A represents the size of the first dimension of the tensor data, B represents the size of the second dimension of the tensor data, C represents the size of the third dimension of the tensor data, a represents the index of the tensor data in the first dimension, b represents the index of the tensor data in the second dimension, and c represents the index of the tensor data in the third dimension. Represents the index element value of the tensor data, and T represents the number of samples of the standardized data; querying the historical viewing mode of the display user, analyzing the viewing preference of the display user based on the historical viewing mode, and updating the second adjusted display graph based on the viewing preference to obtain an updated display graph; Identifying the display demand pattern of the display user; When the display demand mode is the first mode, querying the multimodal interaction engine of the updated display image, and using the multimodal interaction engine to interactively adjust the updated display image to obtain a first target display image; When the display demand mode is the second mode, multiple display plans of the display user are collected, and based on the multiple display plans, multiple adjustments are made to the updated display graph to obtain a multiple adjusted display graph, and the chart quality of the multiple adjusted display graph is evaluated. When the chart quality meets the preset quality, the multiple adjusted display graph is used as the second target display graph.

Images