Dynamic updating method and system of spatiotemporal data elements based on GIS

Abstract

The embodiment of the present invention provides a method and system for dynamically updating spatiotemporal data elements based on GIS support, belonging to the field of data processing technology. The method includes: obtaining the first spatiotemporal data of a target object under a target sensor at a target time, the corresponding second spatiotemporal data under a target remote sensing technology, and the corresponding third spatiotemporal data under a real-time detection system; aligning the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to obtain initial conflict data corresponding to the target object; using the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to perform abnormal identification on the initial conflict data to obtain target conflict data corresponding to the target object; performing data fusion on the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data according to the target conflict data to obtain target spatiotemporal data corresponding to the target object at the target time; dynamically updating the spatiotemporal data elements of the target object according to the target spatiotemporal data to obtain a target update result.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for dynamically updating spatiotemporal data elements supported by GIS. Background Art

[0002] Traditional geographic information system (GIS) data usually exists in a static form, and its update cycle is long, often taking several months or even years to be fully updated. The lag of this static data is particularly prominent in many key application scenarios, especially in the fields of emergency response, traffic management, and urban planning. In these fields, real-time or near real-time data updates are crucial because they directly affect the timeliness and accuracy of decision-making. In emergency response, such as natural disasters (such as earthquakes, floods, forest fires), public health emergencies, etc., real-time updated GIS data can provide the latest geographic information of the disaster area, helping emergency management departments to quickly formulate rescue plans and resource allocation strategies. Although dynamic update technology has significant advantages in improving the timeliness and accuracy of decision-making, in practical applications, related technologies still face some challenges when dynamically updating GIS data, especially in ensuring the accuracy of updated data. Dynamic update of GIS data usually relies on multiple data sources, including sensors, remote sensing data, drone images, social media information, etc. The diversity and complexity of these data sources increase the difficulty of data processing, which may lead to inconsistency and uncertainty in data quality, resulting in a decrease in data accuracy, which in turn affects the subsequent use of GIS data. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a method and system for dynamically updating spatiotemporal data elements based on GIS support, aiming to solve the problem in the related technology that when dynamically updating GIS data, the diversity and complexity of data sources increase the difficulty of data processing, resulting in inconsistency and uncertainty in data quality, thereby causing a decrease in data accuracy and affecting the subsequent use of GIS data.

[0004] In a first aspect, an embodiment of the present invention provides a method for dynamically updating spatiotemporal data elements based on GIS support, comprising:

[0005] Obtaining first spatiotemporal data corresponding to the target object under the target sensor at the target time, second spatiotemporal data corresponding to the target remote sensing technology, and third spatiotemporal data corresponding to the real-time detection system;

[0006] Performing data alignment on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to obtain initial conflict data corresponding to the target object;

[0007] Using the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to perform abnormal identification on the initial conflict data to obtain target conflict data corresponding to the target object;

[0008] According to the target conflict data, data fusion is performed on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to obtain target spatiotemporal data corresponding to the target object at the target time;

[0009] The spatiotemporal data elements of the target object are dynamically updated according to the target spatiotemporal data to obtain a target update result.

[0010] In a second aspect, an embodiment of the present invention provides a system for dynamically updating spatiotemporal data elements based on GIS support, including:

[0011] A data acquisition module, used to obtain first spatiotemporal data corresponding to the target object under the target sensor at the target time, second spatiotemporal data corresponding to the target remote sensing technology, and third spatiotemporal data corresponding to the real-time detection system;

[0012] A data alignment module, used for performing data alignment on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to obtain initial conflicting data corresponding to the target object;

[0013] an anomaly identification module, configured to perform anomaly identification on the initial conflict data using the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to obtain target conflict data corresponding to the target object;

[0014] A data fusion module, configured to fuse the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data according to the target conflict data, so as to obtain target spatiotemporal data corresponding to the target object at the target time;

[0015] The data updating module is used to dynamically update the spatiotemporal data elements of the target object according to the target spatiotemporal data to obtain a target update result.

[0016] The embodiment of the present invention provides a method and system for dynamically updating spatiotemporal data elements based on GIS support. The method comprises: obtaining first spatiotemporal data corresponding to a target object under a target sensor at a target time, second spatiotemporal data corresponding to a target remote sensing technology, and third spatiotemporal data corresponding to a real-time detection system, thereby aligning the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to obtain initial conflict data corresponding to the target object, thereby providing support for subsequently eliminating deviations and errors between different data sources and improving data consistency, and then using the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to further identify anomalies in the initial conflict data to obtain target conflict data, thereby providing support for subsequently effectively detecting and correcting errors and anomalies in the data to further improve data accuracy. Therefore, the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data are fused according to the target conflict data, and then the target spatiotemporal data corresponding to the target object at the target time is obtained. Therefore, the fusion of multi-source data can improve the reliability of the data, reduce the error and uncertainty of a single data source, and thus significantly improve the accuracy, real-time and comprehensiveness of GIS data. Finally, the spatiotemporal data elements of the target object are dynamically updated according to the target spatiotemporal data to obtain the target update result, thereby ensuring the real-time nature of GIS data while also ensuring the reliability and accuracy of the dynamic update of GIS data, thereby providing good support for subsequent data decision-making and analysis. It also solves the problem in the related technology that the diversity and complexity of data sources when dynamically updating GIS data increases the difficulty of data processing, leading to inconsistency and uncertainty in data quality, thereby causing a decrease in data accuracy, and thus affecting the subsequent use of GIS data. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic diagram of a flow chart of a method for dynamically updating spatiotemporal data elements supported by GIS provided in an embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the module structure of a dynamic updating system for spatiotemporal data elements supported by GIS provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0021] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0022] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0023] The embodiment of the present invention provides a method and system for dynamically updating spatiotemporal data elements based on GIS support. The method for dynamically updating spatiotemporal data elements based on GIS support can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0024] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0025] Please refer to Figure 1 , Figure 1 A flowchart of a method for dynamically updating spatiotemporal data elements based on GIS support is provided in an embodiment of the present invention.

[0026] like Figure 1 As shown, the method for dynamically updating spatiotemporal data elements based on GIS support includes steps S101 to S105.

[0027] Step S101, obtaining first spatiotemporal data corresponding to a target object under a target sensor at a target time, second spatiotemporal data corresponding to a target remote sensing technology, and third spatiotemporal data corresponding to a real-time detection system.

[0028] For example, the target time can be a fixed time point or a dynamic time period such as within the last hour). In the data analysis of the Geographic Information System (GIS), the target object mainly refers to a specific area that needs to be analyzed in detail and supported by decision-making based on GIS data. These areas can be various types of geographic units, such as the road network, transportation hubs, public transportation stations and other transportation areas related to transportation in cities or regions, or disaster-stricken areas affected by natural disasters, public emergencies, etc. That is, the target object is the area that needs to be analyzed based on GIS data.

[0029] Exemplarily, according to the characteristics of the target object (such as environmental monitoring, traffic flow, etc.), the sensor type such as GPS sensor, lidar, etc. is determined, and then the target sensor is deployed at an appropriate location to cover the activity range of the target object, thereby collecting the first spatiotemporal data of the target object under the target sensor in real time.

[0030] Exemplarily, according to the characteristics of the target object, a suitable target remote sensing technology (such as satellite remote sensing, aerial remote sensing, etc.) is selected, so as to obtain image data or other remote sensing data of the target object at the target time through a remote sensing platform (such as satellite, drone, etc.) to obtain the second spatiotemporal data.

[0031] Exemplarily, a real-time detection system (such as a traffic monitoring system, an environmental monitoring system, etc.) is selected or built that can monitor the target object in real time, ensuring that the real-time detection system can access the data stream of the target object and obtain the third-party spatiotemporal data of the target object at the target time in real time.

[0032] Step S102: align the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to obtain initial conflict data corresponding to the target object.

[0033] Exemplarily, a common time window or time interval is determined, the first space-time data, the second space-time data and the third space-time data are aligned within the time window, and then the time-aligned first space-time data, the second space-time data and the third space-time data are converted into the same coordinate system, thereby obtaining first conversion data corresponding to the first space-time data, second conversion data corresponding to the second space-time data, and third conversion data corresponding to the third space-time data.

[0034] Exemplarily, the first conversion data is respectively calculated with the second conversion data and the third conversion data to obtain the first total distance between the first conversion distance and the second conversion data and the third conversion data, and the second total distance between the second conversion distance and the first conversion data and the third conversion data is obtained, and the third total distance between the third conversion distance and the first conversion data and the second conversion data is obtained, and then the first total distance, the second total distance, and the third total distance are compared with a preset threshold. When the first total distance is greater than the preset threshold, it means that the first spatiotemporal data corresponding to the first conversion distance is one of the initial conflicting data. When the first total distance is less than or equal to the preset threshold, the first spatiotemporal data corresponding to the first conversion distance is normal data. Similarly, when any one of the first total distance, the second total distance, and the third total distance at the target time is greater than the preset threshold, it means that there is a conflict between the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data at the time, and then the initial conflicting data corresponding to the target object is obtained.

[0035] In some embodiments, the data alignment of the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to obtain the initial conflict data corresponding to the target object includes: determining a target reference system, and converting the first spatiotemporal data to the target reference system to obtain first conversion data, converting the second spatiotemporal data to the target reference system to obtain second conversion data, and converting the third spatiotemporal data to the target reference system to obtain third conversion data; obtaining historical conversion data corresponding to the target reference system, and performing data fitting based on the historical conversion data to obtain a target regression model; obtaining the fitted spatiotemporal data corresponding to the target object at the target time based on the target regression model; calculating a first difference sequence between the fitted spatiotemporal data and the first conversion data, calculating a second difference sequence between the fitted spatiotemporal data and the second conversion data, and calculating a third difference sequence between the fitted spatiotemporal data and the third conversion data; performing data fusion based on the first difference sequence, the second difference sequence, and the third difference sequence to obtain a target difference sequence; performing data clustering on the target difference sequence to obtain a target clustering result, and obtaining the initial conflict data corresponding to the target object based on the target clustering result.

[0036] Exemplarily, the target reference system may be a global coordinate system (WGS84), a projection coordinate system of a specific area, etc. Thus, the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data are converted to the target reference system to ensure their spatial and semantic consistency, thereby obtaining the first conversion data corresponding to the target reference system converted from the first spatiotemporal data, the second conversion data corresponding to the target reference system converted from the second spatiotemporal data, and the third conversion data corresponding to the target reference system converted from the third spatiotemporal data.

[0037] Exemplarily, historical conversion data within a historical time period is collected and then a regression analysis method (such as linear regression, polynomial regression, time series analysis, etc.) is used to fit the historical conversion data to obtain a target regression model. Then, according to the target regression model, the fitting spatiotemporal data of the target object at the target time is predicted.

[0038] Exemplarily, the differences between the fitted spatiotemporal data and the first conversion data, the second conversion data and the third conversion data are calculated respectively to obtain a first difference sequence between the fitted spatiotemporal data and the first conversion data, a second difference sequence between the fitted spatiotemporal data and the second conversion data, and a third difference sequence between the fitted spatiotemporal data and the first conversion data.

[0039] Exemplarily, the first difference sequence, the second difference sequence and the third difference sequence are bitwise added to obtain a target difference sequence.

[0040] Exemplarily, a clustering method (such as K-means clustering, DBSCAN clustering, etc.) is used to perform data clustering on the target difference sequence to obtain a target clustering result, and based on the target clustering result, a target cluster corresponding to a smaller number of clusters is obtained, thereby determining the spatiotemporal data of the corresponding position of the difference in the target cluster as the initial conflict data.

[0041] In some embodiments, the target difference sequence is clustered to obtain a target clustering result, including: determining an initial mean parameter and an initial covariance parameter corresponding to an initial Gaussian kernel function, and determining, based on the initial mean parameter and the initial covariance parameter, first probability information that each sub-difference in the target difference sequence belongs to the initial Gaussian kernel function; updating the initial mean parameter and the initial covariance parameter based on the sub-difference and the first probability information to obtain updated target mean parameter and target covariance parameter; updating the initial Gaussian kernel function based on the target mean parameter and the target covariance parameter to obtain a target Gaussian kernel function; calculating second probability information that each sub-difference in the target difference sequence belongs to the target Gaussian kernel function; determining, based on the first probability information and the second probability information, an associated Gaussian kernel function corresponding to each sub-difference in the target difference sequence in the initial Gaussian kernel function and the target Gaussian kernel function; and performing data clustering on the target difference sequence based on the associated Gaussian kernel function to obtain the target clustering result.

[0042] Exemplarily, the mean of the target difference sequence is used as the initial mean parameter corresponding to the initial Gaussian kernel function, and the covariance of the target difference sequence is calculated according to the initial mean parameter to obtain the initial covariance parameter.

[0043] Exemplarily, an initial Gaussian kernel function is determined according to an initial mean parameter and an initial covariance parameter, and then a corresponding initial probability density function is determined according to the initial Gaussian kernel function, so that each sub-difference in the target difference sequence is substituted into the initial probability density function to obtain the corresponding first probability information.

[0044] Exemplarily, the first probability information corresponding to each sub-difference in the target difference sequence is obtained, and then the first probability information and the sub-difference are multiplied and summed to obtain a first value, and all the first probability information are summed to obtain a second value, and then the ratio between the first value and the second value is used to update the initial mean parameter to obtain the target mean parameter.

[0045] Exemplarily, the square of the difference between the sub-difference value and the target mean parameter is obtained and multiplied with the first probability information and then summed to obtain a third value, and then the ratio between the third value and the second value is used to update the initial covariance parameter to obtain the target covariance parameter.

[0046] Exemplarily, the initial Gaussian kernel function is updated according to the target mean parameter and the target covariance parameter to obtain the target Gaussian kernel function, and then the corresponding target probability density function is determined according to the target Gaussian kernel function, so that each sub-difference in the target difference sequence is substituted into the target probability density function to obtain the corresponding second probability information. Similarly, the target mean parameter and the target covariance parameter are updated according to the second probability information until the target mean parameter and the target covariance parameter no longer change significantly.

[0047] Exemplarily, the associated Gaussian kernel function of each sub-difference in the target difference sequence is determined as the Gaussian kernel function with a higher probability between the initial Gaussian kernel function and the target Gaussian kernel function according to the first probability information and the second probability information. Thus, the associated Gaussian kernel function of each sub-difference is obtained, and then data statistics are performed on the associated Gaussian kernel function, so that the spatiotemporal data corresponding to the data when the number of sub-differences is small under the associated Gaussian kernel function is determined as the initial conflict data.

[0048] Step S103: using the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to perform abnormality identification on the initial conflict data to obtain target conflict data corresponding to the target object.

[0049] Exemplarily, an abnormality recognition model is determined, such as a statistical method (such as Z-score, Grubbs' test), a machine learning algorithm (such as isolation forest, One-Class SVM), a deep learning algorithm (such as Autoencoder), etc., and the parameters of the abnormality recognition model are set according to the application scenario and data characteristics to ensure the effectiveness and applicability of the model, so as to use multi-source data sets and historical conflict data for model training, optimize model parameters, and improve the accuracy and stability of the model. Thus, the constructed abnormality recognition model is used to use the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to perform abnormality recognition on the initial conflict data, and obtain the target conflict data corresponding to the target object.

[0050] In some embodiments, the use of the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to identify anomalies in the initial conflict data to obtain target conflict data corresponding to the target object includes: determining a target reference system, and converting the first spatiotemporal data to the target reference system to obtain first conversion data, converting the second spatiotemporal data to the target reference system to obtain second conversion data, and converting the third spatiotemporal data to the target reference system to obtain third conversion data; obtaining a target position corresponding to the initial conflict data, and obtaining first neighborhood data corresponding to the initial conflict data from the first conversion data according to the target position; obtaining second neighborhood data corresponding to the initial conflict data from the second conversion data according to the target position; obtaining third neighborhood data corresponding to the initial conflict data from the third conversion data according to the target position; calculating a first correlation value between the first neighborhood data and the second neighborhood data, calculating a second correlation value between the second neighborhood data and the third neighborhood data, and calculating a third correlation value between the first neighborhood data and the third neighborhood data; identifying anomalies in the initial conflict data according to the first correlation value, the second correlation value, and the third correlation value to obtain the target conflict data corresponding to the target object.

[0051] Exemplarily, the target reference system may be a global coordinate system (WGS84), a projection coordinate system of a specific area, etc. Thus, the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data are converted to the target reference system to ensure their spatial and semantic consistency, thereby obtaining the first conversion data corresponding to the target reference system converted from the first spatiotemporal data, the second conversion data corresponding to the target reference system converted from the second spatiotemporal data, and the third conversion data corresponding to the target reference system converted from the third spatiotemporal data.

[0052] Exemplarily, the target position of the initial conflict data corresponding to the first space-time data, the second space-time data, or the third space-time data is obtained, and then according to the target position, the first neighborhood data, the second neighborhood data, and the third neighborhood data corresponding to the initial conflict data are respectively obtained from the first conversion data, the second conversion data, and the third conversion data.

[0053] Exemplarily, the first correlation value between the first neighborhood data and the second neighborhood data, the second correlation value between the second neighborhood data and the third neighborhood data, and the third correlation value between the first neighborhood data and the third neighborhood data are calculated using methods such as the Pearson correlation coefficient, the Spearman correlation coefficient, and the mutual information.

[0054] Exemplarily, a first target correlation value between the first neighborhood data and the second neighborhood data and the third neighborhood data is obtained by adding the first correlation value and the third correlation value, and a second target correlation value between the second neighborhood data and the first neighborhood data and the third neighborhood data is obtained by adding the first correlation value and the second correlation value, and a third target correlation value between the third neighborhood data and the first neighborhood data and the second neighborhood data is obtained by adding the second correlation value and the third correlation value.

[0055] Exemplarily, the first target correlation value is compared with a preset threshold value, and when the first target correlation value is less than the preset threshold value, the corresponding data of the initial conflict data under the first neighborhood data in the first spatiotemporal data is determined as the target conflict data. The second target correlation value is compared with the preset threshold value, and when the second target correlation value is less than the preset threshold value, the corresponding data of the initial conflict data under the second neighborhood data in the second spatiotemporal data is determined as the target conflict data. The third target correlation value is compared with the preset threshold value, and when the third target correlation value is less than the preset threshold value, the corresponding data of the initial conflict data under the third neighborhood data in the third spatiotemporal data is determined as the target conflict data.

[0056] In some embodiments, the calculation of the first correlation value between the first neighborhood data and the second neighborhood data includes: obtaining a first distance between the first neighborhood data and the second neighborhood data; calculating a first correlation matrix corresponding to the first neighborhood data and a second correlation matrix corresponding to the second neighborhood data; calculating the degree of association and the degree of difference between the first correlation matrix and the second correlation matrix; determining a first correlation factor between the first neighborhood data and the second neighborhood data using the degree of association and the degree of difference in combination with the first distance, the first correlation matrix, and the second correlation matrix; determining a first support and a first confidence corresponding to the first neighborhood data and the second neighborhood data according to the first conversion data and the second conversion data; obtaining a first occurrence frequency corresponding to the first neighborhood data from the first conversion data and a second occurrence frequency corresponding to the second neighborhood data from the second conversion data; determining the first correlation value between the first neighborhood data and the second neighborhood data by fusing the first occurrence frequency, the second occurrence frequency, the first support and the first confidence according to the first correlation factor; wherein the first correlation factor and the first correlation value are obtained according to the following formula:

[0057]

[0058]

[0059] in, represents the degree of correlation between the first correlation matrix and the second correlation matrix, represents the degree of difference between the first correlation matrix and the second correlation matrix, represents the amount of data corresponding to the first neighborhood data or the second neighborhood data, ln represents taking the natural logarithm, represents the first correlation value between the first neighborhood data and the second neighborhood data, represents the first support between the first neighborhood data and the second neighborhood data; represents the first occurrence frequency corresponding to the first neighborhood data, represents the second occurrence frequency corresponding to the second neighborhood data, abs represents the absolute value, represents the first correlation factor between the first neighborhood data and the second neighborhood data, represents the first distance between the first neighborhood data and the second neighborhood data, represents the first correlation matrix corresponding to the first neighborhood data, represents the second correlation matrix corresponding to the second neighborhood data, represents the first confidence between the first neighborhood data and the second neighborhood data, and e represents a natural constant.

[0060] Exemplarily, a first distance between the first neighborhood data and the second neighborhood data is calculated using a distance measurement method, such as Euclidean distance, Manhattan distance, cosine distance, etc. Next, a first correlation matrix corresponding to the first neighborhood data and a second correlation matrix corresponding to the second neighborhood data are calculated using a correlation calculation method, such as Pearson correlation coefficient, Spearman correlation coefficient, etc.

[0061] Exemplarily, the degree of association and degree of difference between the first correlation matrix and the second correlation matrix are calculated using a similarity measurement method, such as matrix similarity measurement, KL divergence, etc. The degree of association can reflect the similarity between the first neighborhood data and the second neighborhood data, and the degree of difference can reflect the difference between the first neighborhood data and the second neighborhood data.

[0062] Exemplarily, the first correlation factor between the first neighborhood data and the second neighborhood data is determined by using the correlation degree and the difference degree in combination with the first distance, the first correlation matrix, and the second correlation matrix according to the following formula:

[0063]

[0064] in, represents the degree of association between the first correlation matrix and the second correlation matrix, represents the difference between the first correlation matrix and the second correlation matrix, represents the amount of data corresponding to the first neighborhood data or the second neighborhood data, ln represents taking the natural logarithm, represents the first correlation factor between the first neighborhood data and the second neighborhood data, represents the first distance between the first neighborhood data and the second neighborhood data, represents the first correlation matrix corresponding to the first neighborhood data, Represents the second correlation matrix corresponding to the second neighborhood data.

[0065] Exemplarily, the calculation of the first correlation factor integrates multiple dimensions such as the degree of correlation, degree of difference, first distance, and correlation matrix of the data, and can more comprehensively and accurately evaluate the relationship between the first neighborhood data and the second neighborhood data. By using the degree of correlation and degree of difference in combination with the first distance, the first correlation matrix, and the second correlation matrix to determine the first correlation factor between the first neighborhood data and the second neighborhood data, the data relationship can be comprehensively evaluated.

[0066] Exemplarily, a first support and a first confidence between the first neighborhood data and the second neighborhood data are determined based on the first conversion data and the second conversion data. The first support and the first confidence can reflect the strength and stability of the relationship between the data sets. For example, the first support refers to the frequency of the first neighborhood data and the second neighborhood data appearing simultaneously in the first conversion data and the second conversion data. The first confidence represents the conditional probability of the second neighborhood data appearing when the first neighborhood data is included. The first confidence reflects the degree of dependence between the first neighborhood data and the second neighborhood data.

[0067] Exemplarily, a first occurrence frequency corresponding to the first neighborhood data is obtained from the first conversion data, and a second occurrence frequency corresponding to the second neighborhood data is obtained from the second conversion data. The first occurrence frequency, the second occurrence frequency, the first support and the first confidence are fused according to the first correlation factor using the following formula to determine a first correlation value between the first neighborhood data and the second neighborhood data.

[0068]

[0069] in, represents the first correlation value between the first neighborhood data and the second neighborhood data, represents the first support between the first neighborhood data and the second neighborhood data; represents the first occurrence frequency corresponding to the first neighborhood data, represents the second occurrence frequency corresponding to the second neighborhood data, abs represents the absolute value, represents the first correlation factor between the first neighborhood data and the second neighborhood data, represents the first distance between the first neighborhood data and the second neighborhood data, represents the first correlation matrix corresponding to the first neighborhood data, represents the second correlation matrix corresponding to the second neighborhood data, represents the first confidence between the first neighborhood data and the second neighborhood data, and e represents a natural constant.

[0070] Exemplarily, in combination with the first support, the first confidence and the first correlation factor, the first correlation value between the first neighborhood data and the second neighborhood data can be more accurately calculated. This calculation method comprehensively considers the frequency, support, confidence and correlation factor of the data, so that the calculation of the correlation value is more comprehensive and accurate. This step not only considers the frequency of occurrence of the data, but also introduces multiple dimensions such as support, confidence and correlation factor for comprehensive analysis. This multi-dimensional analysis method can more deeply explore the relationship and potential association between the data, thereby improving the depth and breadth of data analysis. Thus, by calculating the first correlation value between the first neighborhood data and the second neighborhood data, more accurate data association information can be provided for the subsequent decision support system. By introducing indicators such as support and confidence, a more intuitive basis can be provided for the interpretation of data association. This makes the results of the model not only more accurate, but also easier to understand and explain, thereby enhancing the interpretability of data analysis.

[0071] It should be noted that the present application can also calculate the second correlation value between the second neighborhood data and the second neighborhood data and calculate the third correlation value between the first neighborhood data and the third neighborhood data according to the above steps, which will not be repeated in this application.

[0072] In some embodiments, the abnormality identification of the initial conflict data according to the first correlation value, the second correlation value and the third correlation value to obtain the target conflict data corresponding to the target object includes: obtaining a first similarity between the first neighborhood data and the second neighborhood data, obtaining a second similarity between the first neighborhood data and the third neighborhood data, and obtaining a third similarity between the second neighborhood data and the third neighborhood data; fusing the first similarity, the second similarity and the third similarity to determine the target similarity; comparing the first correlation value, the second correlation value and the third correlation value according to the target similarity to obtain a target comparison result corresponding to the initial conflict data; and determining the target conflict data corresponding to the target object according to the target comparison result.

[0073] Exemplarily, a similarity calculation method (such as cosine similarity, Euclidean distance, etc.) is selected to calculate the similarity between the first neighborhood data and the second neighborhood data to obtain a first similarity, and the same similarity calculation method is used to calculate the similarity between the first neighborhood data and the third neighborhood data to obtain a second similarity. The same similarity calculation method is used to calculate the similarity between the second neighborhood data and the third neighborhood data to obtain a third similarity.

[0074] Exemplarily, the first similarity, the second similarity and the third similarity are weightedly fused to obtain the target similarity, so as to obtain the first target correlation value between the first neighborhood data and the second neighborhood data and the third neighborhood data by adding the first correlation value and the third correlation value, and obtain the second target correlation value between the second neighborhood data and the first neighborhood data and the third neighborhood data by adding the first correlation value and the second correlation value, and obtain the third target correlation value between the third neighborhood data and the first neighborhood data and the second neighborhood data by adding the second correlation value and the third correlation value.

[0075] Exemplarily, the first target correlation value, the second target correlation value, and the third target correlation value are compared with the target similarity in sequence to obtain the target comparison result. When the target comparison results are all greater than or equal to the target similarity, the initial conflict data is determined as normal data, and when any one of the target comparison results is less than the target similarity, the spatiotemporal data corresponding to the time when it is less than the target similarity is determined as the target conflict data.

[0076] For example, if the target similarity is 0.755, the first target correlation value is 0.8, the second target correlation value is 0.72, and the third target correlation value is 0.68, then in the target comparison result, the first target correlation value is greater than the target similarity, the second target correlation value is less than the target similarity, and the third target correlation value is less than the target similarity. Then, the second spatiotemporal data at the target position in the second neighborhood data corresponding to the second target correlation value is the target conflict data, and the third spatiotemporal data at the target position in the third neighborhood data corresponding to the third target correlation value is the target conflict data.

[0077] Step S104: performing data fusion on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data according to the target conflict data to obtain target spatiotemporal data corresponding to the target object at the target time.

[0078] Exemplarily, after the target conflict data is eliminated from the corresponding first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data, the remaining data is converted to the target reference system and then averaged bit by bit to obtain the target spatiotemporal data corresponding to the target object at the target time.

[0079] In some embodiments, the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data are fused according to the target conflict data to obtain the target spatiotemporal data corresponding to the target object at the target time, including: filtering out fourth spatiotemporal data and fifth spatiotemporal data from the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data according to the target conflict data; determining a first probability distribution corresponding to the fourth spatiotemporal data and a second probability distribution corresponding to the fifth spatiotemporal data; determining a first weight corresponding to the fourth spatiotemporal data and a second weight corresponding to the fifth spatiotemporal data according to the first probability distribution and the second probability distribution; and fusing the fourth spatiotemporal data and the fifth spatiotemporal data according to the first weight and the second weight to obtain the target spatiotemporal data corresponding to the target object at the target time.

[0080] Exemplarily, the fourth and fifth spatiotemporal data are obtained by removing the data in the corresponding time and space according to the target conflict data, that is, the data related to the target conflict data are filtered out from the first, second and third spatiotemporal data, and marked as the fourth and fifth spatiotemporal data, respectively.

[0081] For example, the second spatiotemporal data at the target position in the second neighborhood data corresponding to the second target related value is target conflict data, and the third spatiotemporal data at the target position in the third neighborhood data corresponding to the third target related value is target conflict data. Then, after deleting the second spatiotemporal data and the third spatiotemporal data corresponding to the target position, only the first spatiotemporal data corresponding to the target position remains, and then the first spatiotemporal data corresponding to the target position is determined as the fourth spatiotemporal data and the fifth spatiotemporal data, that is, the fourth spatiotemporal data and the fifth spatiotemporal data are the same. If the second spatiotemporal data at the target position in the second neighborhood data corresponding to the second target related value is target conflict data, after deleting the second spatiotemporal data corresponding to the target position, only the first spatiotemporal data corresponding to the target position and the third spatiotemporal data corresponding to the target position remain, and then the first spatiotemporal data corresponding to the target position is determined as the fourth spatiotemporal data and the third spatiotemporal data corresponding to the target position is determined as the fifth spatiotemporal data.

[0082] Exemplarily, a Gaussian kernel function that the fourth spatiotemporal data conforms to is determined based on the distribution of the fourth spatiotemporal data and data surrounding the fourth spatiotemporal data, and then the first probability distribution of the fourth spatiotemporal data is determined based on the Gaussian kernel function. And a Gaussian kernel function that the fifth spatiotemporal data conforms to is determined based on the distribution of the fifth spatiotemporal data and data surrounding the fifth spatiotemporal data, and then the second probability distribution of the fifth spatiotemporal data is determined based on the Gaussian kernel function.

[0083] Exemplarily, the first weight corresponding to the fourth spatiotemporal data and the second weight corresponding to the fifth spatiotemporal data are obtained by normalization based on the first probability distribution and the second probability distribution, and then the fourth spatiotemporal data and the fifth spatiotemporal data are converted to the target reference system and weighted summed using the first weight and the second weight to obtain the target spatiotemporal data corresponding to the target object at the target time.

[0084] Step S105: dynamically update the spatiotemporal data elements of the target object according to the target spatiotemporal data to obtain a target update result.

[0085] Exemplarily, the spatiotemporal data elements of the target object are dynamically updated according to the target spatiotemporal data to obtain a target update result.

[0086] In some embodiments, after obtaining the target update result, the method further includes: storing the target spatiotemporal data in a target database to obtain a target storage result, and visually displaying the target spatiotemporal data in real time on a GIS platform to obtain a target display result.

[0087] Exemplarily, a NoSQL database that supports spatiotemporal data storage, such as MongoDB (with geospatial index), is selected as the target database, the target spatiotemporal data is inserted into the target database according to the defined storage structure, and the target storage results (such as storage time, storage location, storage status, etc.) are recorded.

[0088] For example, select a suitable GIS platform (such as ArcGIS, QGIS, Google Earth Engine, etc.) to ensure that it supports the visualization of real-time data. Configure and connect the target database on the GIS platform to ensure that the stored target spatiotemporal data can be obtained in real time. Design the layers and styles of the visualization, and select appropriate symbols, colors, transparency, etc. to clearly display the target spatiotemporal data. Configure the real-time data update mechanism so that when the target spatiotemporal data changes, the GIS platform can update the display results in real time. Start the real-time visualization function on the GIS platform to obtain the target display results.

[0089] In some implementations, the method further includes: performing real-time analysis on the target object according to the target update result to obtain a target analysis result.

[0090] Exemplarily, the target update result is obtained from the target database in real time. The obtained target update result is input into the defined analysis model. According to the analysis method and algorithm of the model, the target object is calculated and analyzed in real time. This may include operations such as data aggregation, trend analysis, anomaly detection, etc., so as to obtain the target analysis result.

[0091] For example, the latest target spatiotemporal data can be obtained from the target database (such as MongoDB) in real time. Define an analysis model to monitor key indicators such as the position change and speed change of the target object in real time, and design analysis methods, such as using sliding window technology for trend analysis, or using statistical methods for anomaly detection. The acquired target spatiotemporal data is input into the defined analysis model to obtain the position change, speed trend, and anomaly detection results of the target object, so that the target object can be analyzed in real time according to the target update results to obtain the target analysis results. Ensure that the analysis process is efficient and accurate, and can generate reliable analysis results in a timely manner to support real-time decision-making and monitoring.

[0092] See also Figure 2 , Figure 2 A system 200 for dynamically updating spatiotemporal data elements based on GIS support is provided in an embodiment of the present application. The system 200 for dynamically updating spatiotemporal data elements based on GIS support includes a data acquisition module 201, a data alignment module 202, an anomaly recognition module 203, a data fusion module 204, and a data update module 205. The data acquisition module 201 is used to obtain the first spatiotemporal data corresponding to the target object under the target sensor at the target time, the second spatiotemporal data corresponding to the target remote sensing technology, and the third spatiotemporal data corresponding to the real-time detection system; the data alignment module 202 is used to align the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data. The first spatiotemporal data is aligned with the second spatiotemporal data to obtain the initial conflict data corresponding to the target object; an anomaly identification module 203 is used to use the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to perform anomaly identification on the initial conflict data to obtain the target conflict data corresponding to the target object; a data fusion module 204 is used to perform data fusion on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data according to the target conflict data to obtain the target spatiotemporal data corresponding to the target object at the target time; a data update module 205 is used to dynamically update the spatiotemporal data elements of the target object according to the target spatiotemporal data to obtain a target update result.

[0093] In some implementations, the data alignment module 202 performs, during the process of aligning the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to obtain the initial conflicting data corresponding to the target object:

[0094] Determine a target reference system, and convert the first spatiotemporal data into the target reference system to obtain first converted data, convert the second spatiotemporal data into the target reference system to obtain second converted data, and convert the third spatiotemporal data into the target reference system to obtain third converted data;

[0095] Obtaining historical conversion data corresponding to the target reference system, and performing data fitting according to the historical conversion data to obtain a target regression model;

[0096] Obtaining fitting spatiotemporal data corresponding to the target object at the target time according to the target regression model;

[0097] Calculating a first difference sequence between the fitting spatiotemporal data and the first converted data, calculating a second difference sequence between the fitting spatiotemporal data and the second converted data, and calculating a third difference sequence between the fitting spatiotemporal data and the third converted data;

[0098] Performing data fusion according to the first difference sequence, the second difference sequence and the third difference sequence to obtain a target difference sequence;

[0099] Data clustering is performed on the target difference sequence to obtain a target clustering result, and the initial conflict data corresponding to the target object is obtained according to the target clustering result.

[0100] In some implementations, the data alignment module 202 performs, during the process of performing data clustering on the target difference sequence to obtain a target clustering result:

[0101] Determine an initial mean parameter and an initial covariance parameter corresponding to an initial Gaussian kernel function, and determine, according to the initial mean parameter and the initial covariance parameter, first probability information that each sub-difference in the target difference sequence belongs to the initial Gaussian kernel function;

[0102] updating the initial mean parameter and the initial covariance parameter according to the sub-difference value and the first probability information to obtain updated target mean parameter and target covariance parameter;

[0103] The initial Gaussian kernel function is updated according to the target mean parameter and the target covariance parameter to obtain a target Gaussian kernel function;

[0104] Calculate second probability information corresponding to each of the sub-differences in the target difference sequence belonging to the target Gaussian kernel function;

[0105] Determine, according to the first probability information and the second probability information, the associated Gaussian kernel function corresponding to each of the sub-difference values ​​in the target difference value sequence in the initial Gaussian kernel function and the target Gaussian kernel function;

[0106] The target difference sequence is clustered according to the associated Gaussian kernel function to obtain the target clustering result.

[0107] In some implementations, the anomaly identification module 203 performs, during the process of using the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data to identify anomalies on the initial conflict data to obtain target conflict data corresponding to the target object:

[0108] Determine a target reference system, and convert the first spatiotemporal data into the target reference system to obtain first converted data, convert the second spatiotemporal data into the target reference system to obtain second converted data, and convert the third spatiotemporal data into the target reference system to obtain third converted data;

[0109] Obtaining a target position corresponding to the initial conflicting data, and obtaining first neighborhood data corresponding to the initial conflicting data from the first conversion data according to the target position;

[0110] Obtaining second neighborhood data corresponding to the initial conflicting data from the second converted data according to the target position;

[0111] Obtaining third neighborhood data corresponding to the initial conflicting data from the third converted data according to the target position;

[0112] Calculating a first correlation value between the first neighborhood data and the second neighborhood data, calculating a second correlation value between the second neighborhood data and the third neighborhood data, and calculating a third correlation value between the first neighborhood data and the third neighborhood data;

[0113] The target conflict data corresponding to the target object is obtained by performing abnormal identification on the initial conflict data according to the first correlation value, the second correlation value and the third correlation value.

[0114] In some implementations, the abnormality identification module 203, during the process of calculating the first correlation value between the first neighborhood data and the second neighborhood data, performs:

[0115] Obtaining a first distance between the first neighborhood data and the second neighborhood data;

[0116] Calculating a first correlation matrix corresponding to the first neighborhood data and a second correlation matrix corresponding to the second neighborhood data;

[0117] Calculating the degree of association and the degree of difference between the first correlation matrix and the second correlation matrix;

[0118] Determine a first correlation factor between the first neighborhood data and the second neighborhood data by using the correlation degree and the difference degree in combination with the first distance, the first correlation matrix, and the second correlation matrix;

[0119] Determine a first support and a first confidence corresponding to the first neighborhood data and the second neighborhood data according to the first conversion data and the second conversion data;

[0120] Obtaining a first occurrence frequency corresponding to the first neighborhood data from the first conversion data and obtaining a second occurrence frequency corresponding to the second neighborhood data from the second conversion data;

[0121] Determine the first correlation value between the first neighborhood data and the second neighborhood data by fusing the first occurrence frequency, the second occurrence frequency, the first support and the first confidence according to the first association factor;

[0122] The first correlation factor and the first correlation value are obtained according to the following formula:

[0123]

[0124]

[0125] in, represents the degree of correlation between the first correlation matrix and the second correlation matrix, represents the degree of difference between the first correlation matrix and the second correlation matrix, represents the amount of data corresponding to the first neighborhood data or the second neighborhood data, ln represents taking the natural logarithm, represents the first correlation value between the first neighborhood data and the second neighborhood data, represents the first support between the first neighborhood data and the second neighborhood data; represents the first occurrence frequency corresponding to the first neighborhood data, represents the second occurrence frequency corresponding to the second neighborhood data, abs represents the absolute value, represents the first correlation factor between the first neighborhood data and the second neighborhood data, represents the first distance between the first neighborhood data and the second neighborhood data, represents the first correlation matrix corresponding to the first neighborhood data, represents the second correlation matrix corresponding to the second neighborhood data, represents the first confidence between the first neighborhood data and the second neighborhood data, and e represents a natural constant.

[0126] In some implementations, the abnormality identification module 203, in the process of performing abnormality identification on the initial conflict data according to the first correlation value, the second correlation value, and the third correlation value to obtain the target conflict data corresponding to the target object, performs:

[0127] Obtaining a first similarity between the first neighborhood data and the second neighborhood data, obtaining a second similarity between the first neighborhood data and the third neighborhood data, and obtaining a third similarity between the second neighborhood data and the third neighborhood data;

[0128] fusing the first similarity, the second similarity and the third similarity to determine a target similarity;

[0129] Comparing the first correlation value, the second correlation value and the third correlation value according to the target similarity to obtain a target comparison result corresponding to the initial conflict data;

[0130] The target conflict data corresponding to the target object is determined according to the target comparison result.

[0131] In some implementations, the data fusion module 204 performs, during the process of fusing the first spatiotemporal data, the second spatiotemporal data, and the third spatiotemporal data according to the target conflict data to obtain the target spatiotemporal data corresponding to the target object at the target time:

[0132] Filter out fourth space-time data and fifth space-time data from the first space-time data, the second space-time data and the third space-time data according to the target conflict data;

[0133] Determine a first probability distribution corresponding to the fourth spatiotemporal data and a second probability distribution corresponding to the fifth spatiotemporal data;

[0134] Determine a first weight corresponding to the fourth spatiotemporal data and a second weight corresponding to the fifth spatiotemporal data according to the first probability distribution and the second probability distribution;

[0135] The target spatiotemporal data corresponding to the target object at the target time is obtained by fusing the fourth spatiotemporal data and the fifth spatiotemporal data according to the first weight and the second weight.

[0136] In some implementations, after obtaining the target update result, the spatiotemporal data element dynamic update system 200 based on GIS further executes:

[0137] The target spatiotemporal data are stored in a target database to obtain a target storage result, and the target spatiotemporal data are visualized in real time on a GIS platform to obtain a target display result.

[0138] In some implementations, the spatiotemporal data element dynamic update system 200 supported by GIS further executes: performing real-time analysis on the target object according to the target update result to obtain a target analysis result.

[0139] In some implementations, the spatiotemporal data element dynamic update system 200 supported by GIS can be applied to terminal devices.

[0140] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the dynamic update system 200 of spatiotemporal data elements supported by GIS described above can refer to the corresponding process in the aforementioned embodiment of the dynamic update method of spatiotemporal data elements supported by GIS, and will not be repeated here.

[0141] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of the method for dynamically updating spatiotemporal data elements based on GIS support as provided in the description of the embodiment of the present invention.

[0142] The storage medium may be an internal storage unit of the terminal device in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device.

[0143] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0144] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0145] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for dynamically updating spatiotemporal data elements based on GIS, characterized in that: The method comprises: Obtaining first spatiotemporal data corresponding to the target object under the target sensor at the target time, second spatiotemporal data corresponding to the target remote sensing technology, and third spatiotemporal data corresponding to the real-time detection system; Performing data alignment on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to obtain initial conflict data corresponding to the target object; Determine a target reference system, and convert the first spatiotemporal data to the target reference system to obtain first conversion data, convert the second spatiotemporal data to the target reference system to obtain second conversion data, and convert the third spatiotemporal data to the target reference system to obtain third conversion data; obtain a target position corresponding to the initial conflict data, and obtain first neighborhood data corresponding to the initial conflict data from the first conversion data according to the target position; obtain second neighborhood data corresponding to the initial conflict data from the second conversion data according to the target position; obtain third neighborhood data corresponding to the initial conflict data from the third conversion data according to the target position; calculate a first correlation value between the first neighborhood data and the second neighborhood data, calculate a second correlation value between the second neighborhood data and the third neighborhood data, and calculate a third correlation value between the first neighborhood data and the third neighborhood data; perform abnormal identification on the initial conflict data according to the first correlation value, the second correlation value, and the third correlation value to obtain target conflict data corresponding to the target object; According to the target conflict data, data fusion is performed on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to obtain target spatiotemporal data corresponding to the target object at the target time; Dynamically updating the spatiotemporal data elements of the target object according to the target spatiotemporal data to obtain a target update result; The step of calculating a first correlation value between the first neighborhood data and the second neighborhood data includes: Obtaining a first distance between the first neighborhood data and the second neighborhood data; Calculating a first correlation matrix corresponding to the first neighborhood data and a second correlation matrix corresponding to the second neighborhood data; Calculating the degree of association and the degree of difference between the first correlation matrix and the second correlation matrix; Determine a first correlation factor between the first neighborhood data and the second neighborhood data by using the correlation degree and the difference degree in combination with the first distance, the first correlation matrix, and the second correlation matrix; Determine a first support and a first confidence corresponding to the first neighborhood data and the second neighborhood data according to the first conversion data and the second conversion data; Obtaining a first occurrence frequency corresponding to the first neighborhood data from the first conversion data and obtaining a second occurrence frequency corresponding to the second neighborhood data from the second conversion data; Determine the first correlation value between the first neighborhood data and the second neighborhood data by fusing the first occurrence frequency, the second occurrence frequency, the first support and the first confidence according to the first association factor; The first correlation factor and the first correlation value are obtained according to the following formula: Among them, corr 12 represents the degree of correlation between the first correlation matrix and the second correlation matrix, con 12 represents the difference between the first correlation matrix and the second correlation matrix, num represents the amount of data corresponding to the first neighborhood data or the second neighborhood data, ln represents taking the natural logarithm, rel 12 represents the first correlation value between the first neighborhood data and the second neighborhood data, support 12 represents the first support between the first neighborhood data and the second neighborhood data; f1 represents the first occurrence frequency corresponding to the first neighborhood data, f2 represents the second occurrence frequency corresponding to the second neighborhood data, abs represents the absolute value, ass 12 represents the first correlation factor between the first neighborhood data and the second neighborhood data, dis 12 represents the first distance between the first neighborhood data and the second neighborhood data, R1 represents the first correlation matrix corresponding to the first neighborhood data, R2 represents the second correlation matrix corresponding to the second neighborhood data, conf 12 represents the first confidence between the first neighborhood data and the second neighborhood data, and e represents a natural constant.

2. The method according to claim 1, characterized in that The step of performing data alignment on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to obtain initial conflict data corresponding to the target object includes: Determine a target reference system, and convert the first spatiotemporal data into the target reference system to obtain first converted data, convert the second spatiotemporal data into the target reference system to obtain second converted data, and convert the third spatiotemporal data into the target reference system to obtain third converted data; Obtaining historical conversion data corresponding to the target reference system, and performing data fitting according to the historical conversion data to obtain a target regression model; Obtaining fitting spatiotemporal data corresponding to the target object at the target time according to the target regression model; Calculating a first difference sequence between the fitting spatiotemporal data and the first converted data, calculating a second difference sequence between the fitting spatiotemporal data and the second converted data, and calculating a third difference sequence between the fitting spatiotemporal data and the third converted data; Performing data fusion according to the first difference sequence, the second difference sequence and the third difference sequence to obtain a target difference sequence; Data clustering is performed on the target difference sequence to obtain a target clustering result, and the initial conflict data corresponding to the target object is obtained according to the target clustering result.

3. The method according to claim 2, characterized in that The step of performing data clustering on the target difference sequence to obtain a target clustering result includes: Determine an initial mean parameter and an initial covariance parameter corresponding to an initial Gaussian kernel function, and determine, according to the initial mean parameter and the initial covariance parameter, first probability information that each sub-difference in the target difference sequence belongs to the initial Gaussian kernel function; updating the initial mean parameter and the initial covariance parameter according to the sub-difference value and the first probability information to obtain updated target mean parameter and target covariance parameter; The initial Gaussian kernel function is updated according to the target mean parameter and the target covariance parameter to obtain a target Gaussian kernel function; Calculate second probability information corresponding to each of the sub-differences in the target difference sequence belonging to the target Gaussian kernel function; Determine, according to the first probability information and the second probability information, the associated Gaussian kernel function corresponding to each of the sub-difference values ​​in the target difference value sequence in the initial Gaussian kernel function and the target Gaussian kernel function; The target difference sequence is clustered according to the associated Gaussian kernel function to obtain the target clustering result.

4. The method according to claim 1, characterized in that The performing abnormal identification on the initial conflict data according to the first correlation value, the second correlation value, and the third correlation value to obtain the target conflict data corresponding to the target object includes: Obtaining a first similarity between the first neighborhood data and the second neighborhood data, obtaining a second similarity between the first neighborhood data and the third neighborhood data, and obtaining a third similarity between the second neighborhood data and the third neighborhood data; fusing the first similarity, the second similarity and the third similarity to determine a target similarity; Comparing the first correlation value, the second correlation value and the third correlation value according to the target similarity to obtain a target comparison result corresponding to the initial conflict data; The target conflict data corresponding to the target object is determined according to the target comparison result.

5. The method according to claim 1, characterized in that The step of fusing the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data according to the target conflict data to obtain target spatiotemporal data corresponding to the target object at the target time includes: Filter out fourth space-time data and fifth space-time data from the first space-time data, the second space-time data and the third space-time data according to the target conflict data; Determine a first probability distribution corresponding to the fourth spatiotemporal data and a second probability distribution corresponding to the fifth spatiotemporal data; Determine a first weight corresponding to the fourth spatiotemporal data and a second weight corresponding to the fifth spatiotemporal data according to the first probability distribution and the second probability distribution; The target spatiotemporal data corresponding to the target object at the target time is obtained by fusing the fourth spatiotemporal data and the fifth spatiotemporal data according to the first weight and the second weight.

6. The method according to any one of claims 1 to 5, characterized in that After obtaining the target update result, the method further includes: The target spatiotemporal data are stored in a target database to obtain a target storage result, and the target spatiotemporal data are visualized in real time on a GIS platform to obtain a target display result.

7. The method according to any one of claims 1 to 5, characterized in that The method further includes: performing real-time analysis on the target object according to the target update result to obtain a target analysis result.

8. A dynamic updating system of spatiotemporal data elements based on GIS, characterized in that: include: A data acquisition module, used to obtain first spatiotemporal data corresponding to the target object under the target sensor at the target time, second spatiotemporal data corresponding to the target remote sensing technology, and third spatiotemporal data corresponding to the real-time detection system; A data alignment module, used for performing data alignment on the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data to obtain initial conflicting data corresponding to the target object; an abnormality identification module, used to determine a target reference system, and convert the first spatiotemporal data to the target reference system to obtain first conversion data, convert the second spatiotemporal data to the target reference system to obtain second conversion data, and convert the third spatiotemporal data to the target reference system to obtain third conversion data; obtain a target position corresponding to the initial conflict data, and obtain first neighborhood data corresponding to the initial conflict data from the first conversion data according to the target position; According to the target position, second neighborhood data corresponding to the initial conflict data is obtained from the second conversion data; according to the target position, third neighborhood data corresponding to the initial conflict data is obtained from the third conversion data; a first correlation value between the first neighborhood data and the second neighborhood data is calculated, a second correlation value between the second neighborhood data and the third neighborhood data is calculated, and a third correlation value between the first neighborhood data and the third neighborhood data is calculated; according to the first correlation value, the second correlation value and the third correlation value, an abnormality is identified on the initial conflict data to obtain the target conflict data corresponding to the target object; wherein, the calculation of the first correlation value between the first neighborhood data and the second neighborhood data includes: obtaining a first distance between the first neighborhood data and the second neighborhood data; calculating a first correlation matrix corresponding to the first neighborhood data and a second correlation matrix corresponding to the second neighborhood data; Calculate the degree of association and the degree of difference between the first correlation matrix and the second correlation matrix; determine the first correlation factor between the first neighborhood data and the second neighborhood data using the degree of association and the degree of difference in combination with the first distance, the first correlation matrix, and the second correlation matrix; determine the first support and the first confidence corresponding to the first neighborhood data and the second neighborhood data according to the first conversion data and the second conversion data; obtain the first occurrence frequency corresponding to the first neighborhood data from the first conversion data and the second occurrence frequency corresponding to the second neighborhood data from the second conversion data; determine the first correlation value between the first neighborhood data and the second neighborhood data by fusing the first occurrence frequency, the second occurrence frequency, the first support and the first confidence according to the first correlation factor; wherein the first correlation factor and the first correlation value are obtained according to the following formula: Among them, corr 12 represents the degree of correlation between the first correlation matrix and the second correlation matrix, con 12 represents the difference between the first correlation matrix and the second correlation matrix, num represents the amount of data corresponding to the first neighborhood data or the second neighborhood data, ln represents taking the natural logarithm, rel 12 represents the first correlation value between the first neighborhood data and the second neighborhood data, support 12 represents the first support between the first neighborhood data and the second neighborhood data; f1 represents the first occurrence frequency corresponding to the first neighborhood data, f2 represents the second occurrence frequency corresponding to the second neighborhood data, abs represents the absolute value, ass 12 represents the first correlation factor between the first neighborhood data and the second neighborhood data, dis 12 represents the first distance between the first neighborhood data and the second neighborhood data, R1 represents the first correlation matrix corresponding to the first neighborhood data, R2 represents the second correlation matrix corresponding to the second neighborhood data, conf 12 represents the first confidence between the first neighborhood data and the second neighborhood data, and e represents a natural constant; A data fusion module, configured to fuse the first spatiotemporal data, the second spatiotemporal data and the third spatiotemporal data according to the target conflict data, so as to obtain target spatiotemporal data corresponding to the target object at the target time; The data updating module is used to dynamically update the spatiotemporal data elements of the target object according to the target spatiotemporal data to obtain a target update result.

Images