Multi-source data fusion analysis method and system based on parallel coordinate graph

Abstract

The invention discloses a multi-source data fusion analysis method and system based on a parallel coordinate graph, and the method comprises the steps: obtaining multi-source data in a bridge construction process, carrying out the preprocessing operation of the multi-source data, and carrying out the time synchronization operation of the multi-source data, identifying abnormal values and missing data in the multi-source data; mapping the pre-processed multi-source data to a parallel coordinate graph, and distributing corresponding colors to the multi-source data according to a time dimension so as to distinguish each piece of source data in the multi-source data; and displaying the parallel coordinate graph for a user, and performing operation on the parallel coordinate graph by the user to search required data so as to complete multi-source data fusion analysis.

Description

Technical Field

[0001] The present invention belongs to the technical field of multi-source data fusion analysis in a bridge construction process, and more specifically, relates to a multi-source data fusion analysis method and system based on a parallel coordinate graph. Background Art

[0002] Traditional structural monitoring data analysis methods have many limitations. First, these methods can usually only process a single or a small number of types of data, and it is difficult to effectively integrate multi-source heterogeneous data. Second, the analysis results obtained by traditional methods often lack intuitiveness, making it difficult for engineers to clearly understand the relationship and differences between different monitoring indicators. In addition, in multidimensional data exploration and analysis, traditional methods are difficult to achieve dynamic and effective multidimensional attribute interaction and analysis. This makes it impossible for engineers to quickly identify key factors or potential risks.

[0003] More importantly, traditional methods often ignore the temporal and spatial characteristics of data when processing structural monitoring data. They cannot effectively show the distribution pattern of multidimensional attribute characteristics in time and space, and it is difficult to reveal the complex correlation between various monitoring indicators. For example, the mutual influence and coupling effects that may exist between different types of monitoring data such as stress, displacement, and temperature are difficult to be intuitively presented and deeply analyzed in traditional analysis methods.

[0004] These limitations seriously affect engineers' comprehensive assessment and accurate judgment of the health status of bridge structures, and increase the possibility of potential risks being ignored. Therefore, there is an urgent need for a new analysis method that can comprehensively process multi-source heterogeneous data, realize dynamic interactive analysis, and intuitively display the spatiotemporal characteristics and correlation of data.

[0005] Parallel Coordinates Plots is a technique used to visualize high-dimensional data. Parallel Coordinates Plots maps multiple dimensions of high-dimensional data to multiple parallel coordinate axes, and displays the high-dimensional data set as a set of broken lines that intersect with the parallel coordinate axes. Usually, between adjacent coordinate axes, the broken lines formed by the data overlap. From the overall distribution characteristics of the broken lines, the data correlation on adjacent dimensions of the data set can be observed. Specifically, if there are parallel broken lines between two coordinate axes, it means that the dimensions represented by the two coordinate axes are positively correlated; on the contrary, if the broken lines between the coordinate axes intersect, it means that the dimensions are negatively correlated. Compared with scatter plots and heat maps, parallel coordinate plots can more clearly present the relationship between dimension pairs and are an important tool for high-dimensional data analysis.

[0006] However, parallel coordinates also have some application problems. The coordinate axes of parallel coordinates are arranged in sequence and in parallel. Therefore, if the dimension of the data set is very large, the parallel coordinates will be very long. In this way, even a parallel coordinates plot with a small number of dimensions may require a large horizontal display space to display the visualization results, resulting in a waste of space. Secondly, in this horizontal display space, the order of each coordinate axis corresponding to the dimension also affects the performance of the pairwise correlation between the dimensions, and it is difficult to intuitively represent the relationship between a specific dimension and three or more different dimensions. This situation can be illustrated by a simple example. Suppose a data set has four dimensions a, b, c, and d, which are visualized by a parallel coordinates plot. If arranged in the order of a, b, c, and d, it is easy to observe the relationship between a and b, or the relationship between b and c. However, in this visualization, due to the arrangement order of the coordinate axes, the correlation between b and d is not easy to observe. Finally, since the parallel coordinate graph maps each piece of data into a broken line between the coordinate axes, when the amount of data is too large or the data scale is too large, it will cause the broken lines to cross and overlap, causing visual confusion, hindering the expression of information, and reducing the comprehensibility of the graph itself, which seriously affects the progress of data analysis. Summary of the invention

[0007] In order to solve the above technical problems, the present invention proposes a multi-source data fusion analysis method based on parallel coordinate graph, comprising:

[0008] Acquire multi-source data during the bridge construction process, and perform preprocessing operations on the multi-source data, wherein the preprocessing operations include: performing time synchronization operations on the multi-source data, and identifying abnormal values ​​and missing data in the multi-source data;

[0009] Mapping the multi-source data after the preprocessing operation onto a parallel coordinate graph, and assigning corresponding colors to the multi-source data according to the time dimension, so as to distinguish each source data in the multi-source data;

[0010] The parallel coordinate graph is displayed to the user, and the user operates on the parallel coordinate graph to find required data, thereby completing multi-source data fusion analysis.

[0011] Furthermore, the user performs operations on the parallel coordinate graph including:

[0012] The user places the lines of required data in parallel by dragging the lines of each source data in the multi-source data on the parallel coordinate graph.

[0013] Furthermore, the user performs operations on the parallel coordinate graph including:

[0014] When a user selects a desired value range on the coordinate axis of the parallel coordinate graph, the parallel coordinate graph only displays lines of source data in the desired value range.

[0015] Furthermore, it also includes:

[0016] Automatically generate corresponding time series scatter plots based on the indicators selected by the user to enhance the ability to analyze abnormal indicators.

[0017] Furthermore, assigning corresponding colors to the multi-source data according to the time dimension includes: the closer the time is, the lighter the color of the line corresponding to the source data in the multi-source data is, and vice versa, the darker the color is.

[0018] The present invention also proposes a multi-source data fusion analysis system based on parallel coordinate graph, comprising:

[0019] A data processing module, used to obtain multi-source data in the bridge construction process, and perform preprocessing operations on the multi-source data, wherein the preprocessing operations include: performing time synchronization operations on the multi-source data, and identifying abnormal values ​​and missing data in the multi-source data;

[0020] A mapping module, used to map the multi-source data after the preprocessing operation onto a parallel coordinate graph, and assign corresponding colors to the multi-source data according to the time dimension, so as to distinguish each source data in the multi-source data;

[0021] The display module is used to display the parallel coordinate graph to the user, and the user operates on the parallel coordinate graph to find the required data, thereby completing the multi-source data fusion analysis.

[0022] Furthermore, the user performs operations on the parallel coordinate graph including:

[0023] The user places the lines of required data in parallel by dragging the lines of each source data in the multi-source data on the parallel coordinate graph.

[0024] Furthermore, the user performs operations on the parallel coordinate graph including:

[0025] When a user selects a desired value range on the coordinate axis of the parallel coordinate graph, the parallel coordinate graph only displays lines of source data in the desired value range.

[0026] Furthermore, it also includes:

[0027] Automatically generate corresponding time series scatter plots based on the indicators selected by the user to enhance the ability to analyze abnormal indicators.

[0028] Furthermore, assigning corresponding colors to the multi-source data according to the time dimension includes: the closer the time is, the lighter the color of the line corresponding to the source data in the multi-source data is, and vice versa, the darker the color is.

[0029] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:

[0030] The technical solution of the present invention can solve the technical problems that the existing exploration and analysis of multi-dimensional monitoring data of bridge structures cannot realize dynamic and effective interactive linkage and analysis of multi-dimensional attributes, and cannot effectively display the spatial distribution pattern of multi-dimensional attribute characteristics and the correlation between each attribute dimension. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;

[0032] Figure 2 is a structural diagram of a system in Embodiment 2 of the present invention;

[0033] Figure 3 is an effect diagram of a parallel coordinate graph of Embodiment 1 of the present invention;

[0034] Figure 4 is an effect diagram of a parallel coordinate graph of an example of embodiment 1 of the present invention;

[0035] Figure 5 It is an effect diagram of the time series scatter diagram of Example 1 of the present invention. DETAILED DESCRIPTION

[0036] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0037] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.

[0038] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0039] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.

[0040] The display screen is used to display the user interface of each application.

[0041] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.

[0042] Example 1

[0043] like Figure 1 As shown, an embodiment of the present invention provides a multi-source data fusion analysis method based on a parallel coordinate graph, comprising:

[0044] Step 101, acquiring multi-source data in a bridge construction process, and performing a preprocessing operation on the multi-source data, wherein the preprocessing operation includes: performing a time synchronization operation on the multi-source data, and identifying abnormal values ​​and missing data in the multi-source data;

[0045] Step 102, mapping the multi-source data after the preprocessing operation onto a parallel coordinate graph, and assigning corresponding colors to the multi-source data according to the time dimension, so as to distinguish each source data in the multi-source data;

[0046] Specifically, the user performs operations on the parallel coordinate graph including:

[0047] The user places the lines of required data in parallel by dragging the lines of each source data in the multi-source data on the parallel coordinate graph.

[0048] Specifically, the user performs operations on the parallel coordinate graph including:

[0049] When a user selects a desired value range on the coordinate axis of the parallel coordinate graph, the parallel coordinate graph only displays lines of source data in the desired value range.

[0050] Specifically, assigning corresponding colors to the multi-source data according to the time dimension includes: the closer the time is, the lighter the color of the line corresponding to the source data in the multi-source data is, and vice versa.

[0051] Step 103, displaying the parallel coordinate graph to the user, and the user operates on the parallel coordinate graph to search for required data, thereby completing multi-source data fusion analysis.

[0052] Specifically, it also includes:

[0053] Automatically generate corresponding time series scatter plots based on the indicators selected by the user to enhance the ability to analyze abnormal indicators.

[0054] In order to make this embodiment clearer, this embodiment is supplemented with examples, as shown below:

[0055] 1. Monitoring data collection:

[0056] The present invention adopts advanced monitoring technology to comprehensively collect multi-source data during the bridge construction process. In terms of structural response data, a high-precision, distributed monitoring network is used to accurately capture the stress and strain of key parts of the bridge. The network sampling frequency is as high as 100Hz, which can accurately record the dynamic response of the bridge and provide key data support for fatigue analysis and vibration control. In terms of environmental parameter data, a new generation of meteorological stations are deployed to comprehensively collect environmental data such as temperature, humidity, wind speed, and rainfall. It is particularly worth mentioning that the ultrasonic anemometer equipped with the system can capture complex wind field changes in real time, providing a reliable basis for the wind-resistant design of bridges.

[0057] In order to meet the challenges of heterogeneous data fusion, innovative data processing methods are adopted. For example, for special signals such as vibration acceleration, the original data is not directly used as the dimension of the parallel coordinate diagram, but the spectrum or extreme value information of vibration acceleration is extracted first. For video signals, the focus is on key information such as personnel activities, equipment status or structural displacement reflected by the signal. In addition, various types of unstructured data can be processed intelligently: weather conditions can be classified into categories such as sunny and light rain, the evaluation of the supervision engineer can be converted into digital scores, and even the finite element simulation results can be associated with the actual time nodes to achieve effective fusion of multi-source data.

[0058] To ensure data quality and consistency, strict data preprocessing and synchronization mechanisms were implemented. In terms of time synchronization, a high-precision time synchronization mechanism was developed based on the Network Time Protocol (NTP) to ensure that the timestamp accuracy of all data sources reaches the millisecond level, which is crucial for subsequent data fusion analysis, especially transient dynamic response analysis. In terms of data cleaning, machine learning-based anomaly detection algorithms such as Isolation Forest and Autoencoder were used to automatically identify and process outliers and missing data. These algorithms effectively identify abnormal data caused by sensor failure or environmental interference by learning the normal patterns of the data, ensuring the data quality of subsequent analysis.

[0059] 2. Parallel coordinates plot design

[0060] like Figure 3As shown in the figure, the present invention uses the D3.js library to develop a powerful and highly interactive parallel coordinate graph visualization tool. This tool has made many innovations based on the traditional parallel coordinate graph, greatly improving the efficiency and intuitiveness of multidimensional data analysis. The main features are as follows:

[0061] The time dimension is cleverly introduced into the parallel coordinates chart and combined with color coding. Specifically, the time information is mapped to the color of the line, using a gradient color scheme from light to dark. This design allows users to intuitively observe the changing trend of data over time. For example, light lines represent the latest data, and dark lines represent long-term data. The combination of time dimension and color coding greatly enhances the ability of parallel coordinates charts to display time series data, making time patterns and trends clear at a glance.

[0062] In order to facilitate users to explore the correlation between different dimensions, the dragging function of the coordinate axis is implemented. Users can freely adjust the position of each dimension (coordinate axis) and place the dimensions of interest side by side by dragging, which greatly facilitates users to observe and analyze the relationship between specific pairs of dimensions. For example, when users suspect that there may be a correlation between two dimensions, they can drag the coordinate axes of the two dimensions to adjacent positions and visually judge the relationship between them by observing the pattern of the connecting lines (such as parallel, cross, etc.). The flexible interaction method makes complex multidimensional relationship analysis simple and intuitive.

[0063] A unique "brush" tool has been designed to greatly enhance the ability to filter and explore data. Users can select a numerical range of interest on any axis, and the system will respond in real time, displaying only the data lines that meet the conditions, while updating the data distribution on other axes. This feature makes dynamic filtering and real-time exploration of multidimensional data possible. For example, users can select a specific time period or a specific numerical range of a dimension, and the system will update the display in real time, retaining only the data lines that meet the conditions, which helps users quickly locate the data subset of interest and can also help discover potential correlation patterns between different dimensions.

[0064] like Figure 4 As shown in the figure, taking the typical sensor data during anchor excavation as an example, the typical sensor data of the entire excavation period is aligned and sampled to draw a parallel coordinate graph. The time axis on the left represents the passage of time from bottom to top, and each color line represents the maximum value of each indicator within a day. The specific advantages of the parallel coordinate graph are reflected in the following aspects:

[0065] (1) Multidimensional data display: Parallel coordinate graphs can simultaneously display multiple sensor data, such as time, horizontal displacement of the deep layer of the ground-connected wall, vertical displacement of the cap beam, weather, precipitation, finite element calculation results, etc., allowing engineers to comprehensively analyze complex data sets in graphs.

[0066] (2) Correlation mining: By observing the cross-pattern of lines, engineers can intuitively identify the correlation and trend between variables. For example, the time axis is basically parallel to the deep horizontal displacement of the ground-connected wall, indicating that the two are positively correlated; while the deep horizontal displacement of the ground-connected wall and the horizontal displacement of the cap beam turn into an inverse relationship after a certain time point. This correlation can be intuitively presented through the parallel coordinate diagram.

[0067] (3) Outlier detection: Parallel coordinates can help quickly identify abnormal data points. When a data point deviates from the main trend, it indicates that there may be an abnormal situation. Engineers can further check the abnormal data and take timely countermeasures.

[0068] (4) Data clustering: Similar data points form similar line patterns in parallel coordinate graphs, which helps identify data clusters. In the anchor excavation case, data points at similar construction stages or under similar environmental conditions will show similar line trends in the graph, helping engineers discover common patterns in the construction process.

[0069] (5) Interactivity: Combined with interactive technology, parallel coordinate graphs can realize dynamic filtering, reordering and other functions, further enhancing data exploration capabilities. Engineers can focus on the time period of interest or specific sensor data by clicking or dragging specific coordinate axes, thereby improving the efficiency and accuracy of data analysis. For example, the data of cap beam horizontal displacement and embankment settlement can be displayed adjacently by adjusting the coordinate axes, making the development trend and correlation of the two more intuitive and visible.

[0070] 3. Multi-view linkage display

[0071] like Figure 5 As shown in the figure, the present invention introduces a time series scatter plot as a supplementary analysis tool for the parallel coordinates plot, further enhancing the ability to analyze possible abnormal indicators and providing strong support for engineers to judge the structural development trend. This multi-view linkage design greatly improves the depth and breadth of data analysis.

[0072] In practical applications, the corresponding time series scatter plots can be automatically generated according to the indicators selected by the user. For example, the relationship between the water level drop (sensor number: SW-04) and the deep horizontal displacement of the ground-connected wall (sensor number: ZQT14-19) and the levee settlement (sensor number: DBC11-02) was analyzed in detail. Through these time series scatter plots, some important correlations were found: the water level drop in the surrounding soil and the deep horizontal displacement of the ground-connected wall showed a significant negative correlation, especially in the middle of the construction period, when the horizontal displacement of the ground-connected wall structure developed rapidly. This correlation was more significant. Similarly, a certain degree of positive correlation was observed between the water level drop and the levee settlement.

[0073] However, this paper emphasizes the importance of maintaining a cautious attitude when interpreting these correlations. The changes in various elements during the construction process are a complex coupling process, and the observed correlations do not necessarily mean causality. Some correlations may only apply to specific construction stages and cannot be simply extended to the entire construction cycle. Therefore, it is recommended that users need to comprehensively consider the impact of various factors during analysis, continuously monitor and evaluate changes at different stages, and combine engineering experience and expertise to accurately grasp the changing laws of the project status.

[0074] Through this multi-view linkage analysis, especially the combination of time series scatter plots and parallel coordinate plots, engineers are provided with a powerful tool that can provide in-depth insights into complex structural behavior patterns, effectively identify potential risks, and provide reliable data support for decision making.

[0075] This embodiment also includes setting a multi-source data dynamic response evaluation model to analyze the multi-dimensional data on the parallel coordinate graph. The multi-source data dynamic response evaluation model is specifically:

[0076]

[0077] Where P(t) is the dynamic response evaluation value of multi-source data at time t, n is the type of source data in the multi-source data, and w i is the weight of the i-th source data, a i is the first adjustment factor of the i-th source data, b i is the second adjustment factor of the i-th source data, x i is the characteristic value of the i-th source data, c i is the third adjustment factor of the i-th source data, d i is the fourth adjustment factor of the i-th source data, w′ is the first adjustment factor of time, α is the second adjustment factor of time, β is the third adjustment factor of time, c ij is the i-th source data x i With the j-th source data x j The adjustment factor for the interaction between i , x j , t) is the i-th source data x at time t i With the j-th source data x j The interaction function between j is the characteristic value of the jth source data, k is the adjustment factor of dynamic influence, h t (t) is the dynamic influence function at time t, λ is the adjustment factor of global interaction, φ(x i , x j , t) is the i-th source data x at time t i With the j-th source data x jThe global interaction function between .

[0078] According to the dynamic response evaluation value P(t) of the multi-source data at time t, the dynamic response capability of the multi-source data at different time points is evaluated, and the data in the bridge construction process is adjusted so that the dynamic response evaluation value P(t) of the multi-source data at time t reaches the preset value to complete the parameter optimization of the bridge construction.

[0079] The i-th source data x at time t i With the j-th source data x j The interaction function h(x i , x j , t) is:

[0080]

[0081] Among them, γ is the first adjustment factor of interaction, δ is the second adjustment factor of interaction, k is the third adjustment factor of interaction, and μ is the fourth adjustment factor of interaction.

[0082] Dynamic influence function h at time t t (t) is:

[0083] h t (t) = tan -1 (∈·t)+η·sin(ζ·t 2 )

[0084] Among them, ∈ is the first adjustment factor of the dynamic impact of time, η is the second adjustment factor of the dynamic impact of time, and ζ is the third adjustment factor of the dynamic impact of time.

[0085] The i-th source data x at time t i With the j-th source data x j The global interaction function φ(x i , x j , t) is:

[0086]

[0087] Among them, ρ is the weight of the global interaction, μ′ is used to adjust the i-th source data x i and the jth source data x j The first adjustment of the position in the overall result, V is used to adjust the i-th source data x i and the jth source data x j The second adjustment of the position in the overall result, λ′ is the weight of time, and τ is the center point of time.

[0088] Example 2

[0089] like Figure 2 As shown, the embodiment of the present invention also provides a multi-source data fusion analysis system based on a parallel coordinate graph, comprising:

[0090] A data processing module, used to obtain multi-source data in the bridge construction process, and perform preprocessing operations on the multi-source data, wherein the preprocessing operations include: performing time synchronization operations on the multi-source data, and identifying abnormal values ​​and missing data in the multi-source data;

[0091] A mapping module, used to map the multi-source data after the preprocessing operation onto a parallel coordinate graph, and assign corresponding colors to the multi-source data according to the time dimension, so as to distinguish each source data in the multi-source data;

[0092] Specifically, the user performs operations on the parallel coordinate graph including:

[0093] The user places the lines of required data in parallel by dragging the lines of each source data in the multi-source data on the parallel coordinate graph.

[0094] Specifically, the user performs operations on the parallel coordinate graph including:

[0095] When a user selects a desired value range on the coordinate axis of the parallel coordinate graph, the parallel coordinate graph only displays lines of source data in the desired value range.

[0096] Specifically, assigning corresponding colors to the multi-source data according to the time dimension includes: the closer the time is, the lighter the color of the line corresponding to the source data in the multi-source data is, and vice versa.

[0097] The display module is used to display the parallel coordinate graph to the user, and the user operates on the parallel coordinate graph to find the required data, thereby completing the multi-source data fusion analysis.

[0098] Specifically, it also includes:

[0099] Automatically generate corresponding time series scatter plots based on the indicators selected by the user to enhance the ability to analyze abnormal indicators.

[0100] Example 3

[0101] The embodiment of the present invention further provides a storage medium storing a plurality of instructions, wherein the instructions are used to implement the multi-source data fusion analysis method based on a parallel coordinate graph.

[0102] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0103] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, acquiring multi-source data in a bridge construction process, and performing a preprocessing operation on the multi-source data, wherein the preprocessing operation includes: performing a time synchronization operation on the multi-source data, and identifying abnormal values ​​and missing data in the multi-source data;

[0104] Step 102, mapping the multi-source data after the preprocessing operation onto a parallel coordinate graph, and assigning corresponding colors to the multi-source data according to the time dimension, so as to distinguish each source data in the multi-source data;

[0105] Specifically, the user performs operations on the parallel coordinate graph including:

[0106] The user places the lines of required data in parallel by dragging the lines of each source data in the multi-source data on the parallel coordinate graph.

[0107] Specifically, the user performs operations on the parallel coordinate graph including:

[0108] When a user selects a desired value range on the coordinate axis of the parallel coordinate graph, the parallel coordinate graph only displays lines of source data in the desired value range.

[0109] Specifically, assigning corresponding colors to the multi-source data according to the time dimension includes: the closer the time is, the lighter the color of the line corresponding to the source data in the multi-source data is, and vice versa.

[0110] Step 103, displaying the parallel coordinate graph to the user, and the user operates on the parallel coordinate graph to search for required data, thereby completing multi-source data fusion analysis.

[0111] Specifically, it also includes:

[0112] Automatically generate corresponding time series scatter plots based on the indicators selected by the user to enhance the ability to analyze abnormal indicators.

[0113] Example 4

[0114] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores multiple instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the multi-source data fusion analysis method based on parallel coordinate graphs.

[0115] Specifically, the electronic device of this embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.

[0116] Among them, the storage medium can be used to store software programs and modules, such as a multi-source data fusion analysis method based on a parallel coordinate graph in an embodiment of the present invention, and the corresponding program instructions / modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the above-mentioned multi-source data fusion analysis method based on a parallel coordinate graph. The storage medium may include a high-speed random storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include a storage medium remotely arranged relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0117] The processor can call the information and application stored in the storage medium through the transmission system to perform the following steps: Step 101, obtain multi-source data in the bridge construction process, and perform preprocessing operations on the multi-source data, wherein the preprocessing operations include: performing time synchronization operations on the multi-source data, and identifying abnormal values ​​and missing data in the multi-source data;

[0118] Step 102, mapping the multi-source data after the preprocessing operation onto a parallel coordinate graph, and assigning corresponding colors to the multi-source data according to the time dimension, so as to distinguish each source data in the multi-source data;

[0119] Specifically, the user performs operations on the parallel coordinate graph including:

[0120] The user places the lines of required data in parallel by dragging the lines of each source data in the multi-source data on the parallel coordinate graph.

[0121] Specifically, the user performs operations on the parallel coordinate graph including:

[0122] When a user selects a desired value range on the coordinate axis of the parallel coordinate graph, the parallel coordinate graph only displays lines of source data in the desired value range.

[0123] Specifically, assigning corresponding colors to the multi-source data according to the time dimension includes: the closer the time is, the lighter the color of the line corresponding to the source data in the multi-source data is, and vice versa.

[0124] Step 103, displaying the parallel coordinate graph to the user, and the user operates on the parallel coordinate graph to search for required data, thereby completing multi-source data fusion analysis.

[0125] Specifically, it also includes:

[0126] Automatically generate corresponding time series scatter plots based on the indicators selected by the user to enhance the ability to analyze abnormal indicators.

[0127] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0128] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or 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 software functional units.

[0132] If the integrated unit is implemented 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 solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0133] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A multi-source data fusion analysis method based on parallel coordinates, characterized in that: include: Acquire multi-source data during the bridge construction process, and perform preprocessing operations on the multi-source data, wherein the preprocessing operations include: performing time synchronization operations on the multi-source data, and identifying abnormal values ​​and missing data in the multi-source data; Mapping the multi-source data after the preprocessing operation onto a parallel coordinate graph, and assigning corresponding colors to the multi-source data according to the time dimension, so as to distinguish each source data in the multi-source data; The parallel coordinate graph is displayed to the user, and the user operates on the parallel coordinate graph to find required data, thereby completing multi-source data fusion analysis.

2. The multi-source data fusion analysis method based on parallel coordinate graph according to claim 1, characterized in that: The operations performed by the user on the parallel coordinate graph include: The user places the lines of required data in parallel by dragging the lines of each source data in the multi-source data on the parallel coordinate graph.

3. The multi-source data fusion analysis method based on parallel coordinate graph according to claim 1, characterized in that: The operations performed by the user on the parallel coordinate graph include: When a user selects a desired value range on the coordinate axis of the parallel coordinate graph, the parallel coordinate graph only displays lines of source data in the desired value range.

4. The multi-source data fusion analysis method based on parallel coordinate graph according to claim 1, characterized in that: Also includes: Automatically generate corresponding time series scatter plots based on the indicators selected by the user to enhance the ability to analyze abnormal indicators.

5. The multi-source data fusion analysis method based on parallel coordinate graph according to claim 1, characterized in that: Assigning corresponding colors to the multi-source data according to the time dimension includes: the closer the time is, the lighter the color of the line corresponding to the source data in the multi-source data is, and vice versa.

6. A multi-source data fusion analysis system based on parallel coordinate graph, characterized in that: include: A data processing module, used to obtain multi-source data in the bridge construction process, and perform preprocessing operations on the multi-source data, wherein the preprocessing operations include: performing time synchronization operations on the multi-source data, and identifying abnormal values ​​and missing data in the multi-source data; A mapping module, used to map the multi-source data after the preprocessing operation onto a parallel coordinate graph, and assign corresponding colors to the multi-source data according to the time dimension, so as to distinguish each source data in the multi-source data; The display module is used to display the parallel coordinate graph to the user, and the user operates on the parallel coordinate graph to find the required data, thereby completing the multi-source data fusion analysis.

7. The multi-source data fusion analysis system based on parallel coordinate graph according to claim 6, characterized in that: The operations performed by the user on the parallel coordinate graph include: The user places the lines of required data in parallel by dragging the lines of each source data in the multi-source data on the parallel coordinate graph.

8. The multi-source data fusion analysis system based on parallel coordinate graph according to claim 6, characterized in that: The operations performed by the user on the parallel coordinate graph include: When a user selects a desired value range on the coordinate axis of the parallel coordinate graph, the parallel coordinate graph only displays lines of source data in the desired value range.

9. The multi-source data fusion analysis system based on parallel coordinate graph according to claim 6, characterized in that: Also includes: Automatically generate corresponding time series scatter plots based on the indicators selected by the user to enhance the ability to analyze abnormal indicators.

10. The multi-source data fusion analysis system based on parallel coordinate graph according to claim 6, characterized in that: Assigning corresponding colors to the multi-source data according to the time dimension includes: the closer the time is, the lighter the color of the line corresponding to the source data in the multi-source data is, and vice versa.

Images