Method and system for processing two-dimensional and three-dimensional data of space-time geographic information

Abstract

The invention is suitable for the technical field of geographic information processing, and provides a processing method and system for two-dimensional and three-dimensional data of space-time geographic information, and the method comprises the steps: collecting two-dimensional and three-dimensional data from different sources, integrating position information and time information, and constructing a unified space-time grid, thereby improving the integration of the data. And setting a dynamic model, and tracking and analyzing changes of geographic features in a three-dimensional space and behaviors of the geographic features on a two-dimensional plane in real time so as to predict a future change trend. And analyzing the mutual influence of different geographic features in the space-time grid, constructing a space-time influence matrix, and quantifying the dynamic relationship between the two-dimensional and three-dimensional features. And establishing an anomaly detection model, judging potential anomaly events in combination with historical data, and generating alarm information to provide decision support. By integrating the two-dimensional data and the three-dimensional data, the capability of analyzing traffic flow, crowd dynamics and environmental changes is remarkably improved, a scientific basis is provided for city management and resource allocation, and intelligent cities and sustainable development are promoted.

Description

Technical Field

[0001] The present invention belongs to the technical field of geographic information processing, and particularly relates to a method and system for processing two-dimensional and three-dimensional data of spatio-temporal geographic information. Background Art

[0002] With the acceleration of the urbanization process and the rapid development of information technology, the acquisition and processing of spatio-temporal geographic information have become increasingly important. Traditional Geographic Information Systems (GIS) often focus on static data and lack the ability to monitor and analyze dynamic changes in real time. This results in insufficient timeliness and accuracy of data when dealing with urban management, traffic flow monitoring, environmental protection and other fields, making it difficult to meet the needs of modern society for efficient decision-making.

[0003] At present, many existing technologies still face many challenges in processing two-dimensional and three-dimensional data. Traditional methods usually process two-dimensional data (such as maps and road networks) and three-dimensional data (such as building heights and terrain information) separately, making it difficult to effectively reflect the correlation between data. This method not only reduces the analysis efficiency, but also may lead to information loss and misunderstanding, thus affecting the scientific nature of decision-making.

[0004] In addition, with the development of Internet of Things and big data technologies, real-time data collection has become possible. However, how to effectively integrate dynamic data from different sources, especially in complex urban environments, remains an urgent problem to be solved. Existing technologies often lack a unified processing framework for multi-dimensional data, resulting in a serious phenomenon of information islands and limiting the application potential of data. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for processing two-dimensional and three-dimensional data of spatio-temporal geographic information, aiming to solve the technical problems existing in the prior art identified in the background art.

[0006] The present invention is implemented as follows. A method for processing two-dimensional and three-dimensional data of spatio-temporal geographic information, the method comprising:

[0007] Collect spatio-temporal geographic information from different sources, including two-dimensional data and three-dimensional data, and integrate the collected two-dimensional data and three-dimensional data in terms of location information and time information, and place them in a unified spatio-temporal grid;

[0008] Set up dynamic modeling on the spatio-temporal grid to track and analyze in real time the changes of geographic features in three-dimensional space and the behaviors on the two-dimensional plane, and predict the future behavior trends of geographic features based on the analysis results;

[0009] Analyze the mutual influence between different geographic features in the spatio-temporal grid, capture the relationship between two-dimensional geographic features and three-dimensional geographic features, and analyze the dynamic influence relationship between them;

[0010] An anomaly detection model is established to combine dynamic influence relationships and future behavior trends, determine whether there are potential abnormal events, and generate warning messages.

[0011] As a further solution of the present invention, the collected two-dimensional data and three-dimensional data are integrated in terms of location information and time information and placed in a unified spatio-temporal grid, specifically including:

[0012] Data is collected from the identified data sources to obtain the required two-dimensional data and three-dimensional data, including real-time collection of static data and dynamic data;

[0013] Geographical features of the collected two-dimensional data and three-dimensional data are extracted, including location information and event information, and spatio-temporal attributes are constructed for each geographical feature, including spatial attributes and time attributes;

[0014] A multi-dimensional grid structure is established as the spatio-temporal grid, and the obtained two-dimensional data, three-dimensional data and corresponding spatio-temporal attributes are integrated and placed in a unified spatio-temporal grid.

[0015] As a further solution of the present invention, dynamic modeling is set on the spatio-temporal grid to continuously track and analyze the changes of geographical features in three-dimensional space and their behaviors on a two-dimensional plane, and based on the analysis results, predict the future behavior trends of geographical features, specifically including:

[0016] According to the collected two-dimensional data, three-dimensional data and spatio-temporal attributes, a dynamic model is constructed, and all the spatio-temporal attributes collected at the current moment are used as inputs;

[0017] The dynamic model is used to monitor the changes of geographical features in three-dimensional space, including position changes, morphological changes and behaviors on a two-dimensional plane, and based on the monitoring results, analyze the behavior trends of geographical features and predict future change trends and potential behavior patterns.

[0018] As a further solution of the present invention, predicting future change trends and potential behavior patterns specifically means:

[0019] Define the neighborhood of each geographical feature and capture all neighborhood features related to the geographical feature within the neighborhood;

[0020] Based on the dynamic model, combined with neighborhood features, analyze the future change trends of each geographical feature:

[0021] ;

[0022] Among them, represents the state of the geographical feature at time ; A set of neighborhood features representing geographical features, is the influence coefficient, representing the neighborhood feature on the geographical feature of the influence intensity, represents the neighborhood feature and the geographical feature the difference between states, that is, the influence effect of the neighborhood feature on the geographical feature.

[0023] As a further solution of the present invention, the mutual influence between different geographical features in the analysis spatio-temporal grid is captured, the relationship between two-dimensional geographical features and three-dimensional geographical features is analyzed, and the dynamic influence relationship between them is analyzed, specifically including:

[0024] According to all the constructed spatio-temporal attributes, a relationship model between each geographical feature is constructed, the dynamic correlation of different geographical features in the spatio-temporal grid is analyzed, and it is judged whether there are two-dimensional features that affect the three-dimensional features and recorded;

[0025] Create a spatio-temporal influence matrix to record the intensity and direction of the interaction between different geographical features in time and space, where each element of the matrix represents the influence weight between different geographical features;

[0026] Identify the periodicity of the change trend of different geographical features in the time dimension, which is defined as the dynamic influence relationship.

[0027] As a further solution of the present invention, the dynamic correlation of different geographical features in the spatio-temporal grid is analyzed, and it is judged whether there are two-dimensional features that affect the three-dimensional features, specifically:

[0028] ;

[0029] Among them, represents the mutual information amount between the two-dimensional feature and the three-dimensional feature is proportional to the dependence relationship, represents the probability that the two-dimensional feature and the three-dimensional feature occur simultaneously, is the marginal probability of the occurrence of the two-dimensional feature occurring, is the marginal probability of the occurrence of the three-dimensional feature occurring;

[0030] The identification of the periodicity of the change trend of different geographical features in the time dimension is specifically:

[0031] Based on the obtained spatio-temporal attributes, extract the information of each geographical feature in different time attributes and spatial attributes, and generate a time series by permutation;

[0032] Calculate the result correlation of each geographical feature in the time series at different time points to identify the period:

[0033] ;

[0034] Among them, represents the autocorrelation coefficient of the time series at the time delay , represents the observed value of the geographical feature at time represents the mean value of the time series, represents the total number of samples of the time series.

[0035] As a further solution of the present invention, the establishment of the anomaly detection model combines the dynamic influence relationship and the future behavior trend to determine whether there is a potential abnormal event and generate a warning message, specifically including:

[0036] Construct an anomaly detection model based on historical data and spatio-temporal attributes, and input the real-time collected spatio-temporal data into the anomaly detection model;

[0037] Use the constructed anomaly detection model to monitor the real-time data to determine whether there is an abnormal event:

[0038] ;

[0039] Among them, represents the error value, represents the actual observed value at time is the influence coefficient;

[0040] Set an error threshold. If the error value is greater than the error threshold, it is determined that there is an abnormal event.

[0041] Another object of the present invention is to provide a spatio-temporal geographical information two-dimensional and three-dimensional data processing system, the system includes:

[0042] A data integration module for collecting spatio-temporal geographical information from different sources, including two-dimensional data and three-dimensional data, and integrating the collected two-dimensional data and three-dimensional data in terms of location information and time information and placing them in a unified spatio-temporal grid;

[0043] A geographical feature change tracking and analysis module for setting up dynamic modeling on the spatio-temporal grid, real-time tracking and analyzing the changes of geographical features in the three-dimensional space and the behaviors on the two-dimensional plane, and predicting the future behavior trends of geographical features based on the analysis results;

[0044] The feature interaction analysis module is used to analyze the interactions between different geographical features in the spatio-temporal grid, capture the relationships between two-dimensional geographical features and three-dimensional geographical features, and analyze the dynamic influence relationships between them.

[0045] The anomaly detection module is used to establish an anomaly detection model, combine the dynamic influence relationships and future behavior trends, determine whether there are potential abnormal events, and generate warning messages.

[0046] The beneficial effects of the present invention are:

[0047] By integrating the dynamic characteristics of time and space, the constructed spatio-temporal grid in this method realizes comprehensive data analysis. The unified data processing framework improves data integration, enabling decision-makers to obtain rich geographical information on one platform. This enhances the understanding of complex geographical features and their interactions, and helps optimize urban planning and resource management.

[0048] The real-time tracking function of the dynamic model makes the analysis of traffic flow and crowd dynamics more accurate, can timely reflect the impacts of these dynamics on the surrounding environment, helps managers quickly identify traffic flow changes, reduce congestion, and improve urban traffic efficiency. By capturing the relationships between two-dimensional features (such as roads and rivers) and three-dimensional features (such as building heights), users can identify the linkage effects of these features, providing an important basis for scientific resource allocation and urban development strategies.

[0049] In terms of anomaly detection, the algorithm combining the spatio-temporal state transition model effectively identifies potential abnormal events, such as traffic accidents or environmental pollution. This comprehensive analysis improves the accuracy of abnormal event identification, speeds up the response speed, and ensures that managers can take timely measures to mitigate potential impacts. Description of the Drawings

[0050] Figure 1 It is a flowchart of a method for processing two-dimensional and three-dimensional spatio-temporal geographical information provided by an embodiment of the present invention.

[0051] Figure 2 It is a flowchart of integrating the collected two-dimensional data and three-dimensional data in terms of location information and time information and placing them in a unified spatio-temporal grid provided by an embodiment of the present invention.

[0052] Figure 3 It is a flowchart of real-time tracking and analyzing the changes of geographical features in three-dimensional space and the behaviors on a two-dimensional plane, and predicting the future behavior trends of geographical features based on the analysis results provided by an embodiment of the present invention.

[0053] Figure 4 It is a flowchart of capturing the relationships between two-dimensional geographical features and three-dimensional geographical features and analyzing the dynamic influence relationships between them provided by an embodiment of the present invention.

[0054] Figure 5 This is a flowchart for determining whether there are potential abnormal events provided by an embodiment of the present invention;

[0055] Figure 6 This is a structural block diagram of a processing system for two - and three - dimensional spatio - temporal geographic information provided by an embodiment of the present invention. Detailed implementation manners

[0056] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] Figure 1 This is a flowchart of a method for processing two - and three - dimensional spatio - temporal geographic information provided by an embodiment of the present invention. As Figure 1 shown, the method includes:

[0058] S100, collect spatio - temporal geographic information from different sources, including two - dimensional data and three - dimensional data, and integrate the collected two - dimensional data and three - dimensional data in terms of location information and time information, and place them in a unified spatio - temporal grid;

[0059] This step includes comprehensively collecting two - dimensional and three - dimensional data from various sources. These data are not limited to static information (such as maps, heights and shapes of buildings, etc.), but also include dynamic information (such as traffic flow, climate change, etc.). In this process, the collection of data needs to fully consider its location information and time information so that all data can be effectively integrated within the same spatio - temporal framework. Specifically, by extracting geographical features from the collected two - dimensional data and three - dimensional data, key spatial attributes, time attributes, and comprehensive spatio - temporal attributes can be identified, which provide a basis for subsequent analysis and modeling.

[0060] Next, in the process of constructing the spatio - temporal grid, by establishing a multi - dimensional grid structure, different types of data can be integrated together to form a unified spatio - temporal grid. This grid is not only a carrier for data storage, but also a basic framework for spatio - temporal data analysis. Within this framework, all spatio - temporal attributes are integrated, laying a solid foundation for subsequent dynamic modeling and impact analysis. Through this integration method, users can more intuitively obtain the overall picture of geographical features, thus achieving more efficient decision - making in fields such as urban planning and environmental monitoring.

[0061] By systematically integrating data from different sources and of different types, it not only provides rich basic information for subsequent analysis, but also improves the availability and reliability of the data. Through this comprehensive data processing method, users can more comprehensively understand the dynamic changes in the geospatial space and obtain key spatio-temporal information in a timely manner. In addition, the unified spatio-temporal framework makes the relationships between different data clearer, thus promoting the cross-analysis and comprehensive utilization of data. This method can significantly improve the accuracy and efficiency of urban management, resource allocation, and environmental monitoring in practical applications, and help achieve more scientific and forward-looking decision-making.

[0062] As Figure 2 shown, the integration of the collected two-dimensional data and three-dimensional data in terms of location information and time information and placing them in a unified spatio-temporal grid specifically includes:

[0063] S110, Collect data from the identified data sources to obtain the required two-dimensional data and three-dimensional data, including real-time collection of static data and dynamic data;

[0064] S120, Extract geographical features from the collected two-dimensional data and three-dimensional data, including location information and event information, and construct spatio-temporal attributes for each geographical feature, including spatial attributes and time attributes;

[0065] S130, Establish a multi-dimensional grid structure as the spatio-temporal grid, integrate the obtained two-dimensional data, three-dimensional data and corresponding spatio-temporal attributes, and place them in the unified spatio-temporal grid.

[0066] S200, Set up dynamic modeling on the spatio-temporal grid to track and analyze the changes of geographical features in the three-dimensional space and their behaviors on the two-dimensional plane in real time, and predict the future behavior trends of geographical features based on the analysis results;

[0067] This step can help us better understand the impact of urban expansion by monitoring the state changes of geographical features in the three-dimensional space in real time. For example, during the urban development process, the buildings in a certain area gradually increase in height, which will affect environmental factors such as light and wind direction in the surrounding area. The model can capture this change and analyze its impact on the residents, such as the reduction of sunshine time may lead to a decrease in the satisfaction of residents living in this area, thus affecting the real estate market in this area.

[0068] Secondly, in terms of behavior analysis on a two-dimensional plane, the model can track changes in traffic flow. For example, when construction occurs on a main road, the traffic flow may be forced to divert to other secondary roads. Through the dynamic model, changes in traffic flow can be monitored in real time, the causes of traffic congestion can be analyzed, and traffic conditions in the next few hours can be predicted. This will provide a basis for decision-making for traffic management departments, helping them adjust traffic lights or set up temporary traffic control during peak hours, thus alleviating congestion.

[0069] Suppose a pollution incident occurs in a certain area. The dynamic model can analyze in real time the impact of pollution sources (such as factory emissions) on the surrounding water bodies or air quality. By monitoring the relationship between different geographical features (such as rivers, vegetation coverage, etc.) and pollutant concentrations, the model can predict the trend of pollution diffusion and provide early warning information to decision-makers in a timely manner so that emergency measures can be taken.

[0070] In this step, by establishing a dynamic model, users can not only capture changes in geographical features in a timely manner but also deeply understand the impact of these changes on the surrounding environment and population, thus making more accurate decisions. This real-time monitoring and analysis ability makes the work in fields such as urban management, environmental protection, and traffic management more efficient and scientific, promoting the realization of smart cities and sustainable development.

[0071] As Figure 3 shown, the dynamic modeling set on the spatio-temporal grid to track and analyze in real time the changes of geographical features in three-dimensional space and their behaviors on a two-dimensional plane, and predict the future behavior trends of geographical features based on the analysis results, specifically including:

[0072] S210, construct a dynamic model according to the collected two-dimensional data, three-dimensional data and spatio-temporal attributes, and use all the spatio-temporal attributes collected at the current moment as the input;

[0073] S220, use the dynamic model to monitor the changes of geographical features in three-dimensional space, including position changes, morphological changes and behaviors on a two-dimensional plane, and based on the monitoring results, analyze the behavior trends of geographical features and predict future change trends and potential behavior patterns.

[0074] In this step, the prediction of future change trends and potential behavior patterns is specifically:

[0075] Define the neighborhood of each geographical feature and capture all neighborhood features related to this geographical feature within the neighborhood;

[0076] Based on the dynamic model, analyze the future change trends of each geographical feature in combination with neighborhood features:

[0077] ;

[0078] Among them, represents the state of the geographical feature at time . represents the set of neighborhood features of the geographical feature, is the influence coefficient, indicating the influence intensity of the neighborhood feature on the geographical feature . represents the difference between the neighborhood feature and the state of the geographical feature, that is, the influence effect of the neighborhood feature on the geographical feature.

[0079] S300. Analyze the mutual influence between different geographical features in the spatio-temporal grid, capture the relationship between two-dimensional geographical features and three-dimensional geographical features, and analyze the dynamic influence relationship between them;

[0080] This step can quantify the correlation between two-dimensional features and three-dimensional features through the calculation of mutual information. This provides an important quantitative basis for judging whether there is an influence of two-dimensional features on three-dimensional features. For example, in an urban environment, two-dimensional features (such as road layout) may affect three-dimensional features (such as the height and distribution of buildings). If it is found that the increase in roads is accompanied by changes in building height, the potential connection between the two can be inferred.

[0081] Furthermore, by creating a spatio-temporal influence matrix to record the intensity and direction of the interaction between different geographical features in time and space, it can help us identify which two-dimensional features have a significant impact on three-dimensional features during a specific time period. For example, when a newly built expressway is opened, the housing prices in the surrounding areas may increase significantly. Through the spatio-temporal influence matrix, the intensity of this influence can be quantified, providing a reference for future urban planning.

[0082] The analysis of the change trend in the time dimension is also very crucial. By identifying the periodic changes of different geographical features over time, their future behavior can be predicted more accurately. For example, during seasonal changes, the vegetation coverage rate in certain areas may show periodic changes, and this information can help urban managers make scientific plans when formulating greening policies.

[0083] By systematically analyzing the relationship between different geographical features, the dynamic changes in the geographical space can be understood more comprehensively. This analysis not only enhances the connectivity of data but also improves the depth of understanding of complex environmental phenomena. For example, in the field of public safety, by analyzing the dynamic relationship between geographical features, potential risk areas can be identified in advance, such as the relationship between high crime rates and specific road layouts, providing a basis for public security management.

[0084] Such as Figure 4As shown, analyze the mutual influence between different geographical features in the analysis spatio-temporal grid, capture the relationship between two-dimensional geographical features and three-dimensional geographical features, and analyze the dynamic influence relationship between them, specifically including:

[0085] S310. According to all the spatio-temporal attributes constructed, construct a relationship model between each geographical feature, analyze the dynamic correlation of different geographical features in the spatio-temporal grid, and determine whether there are two-dimensional features that affect three-dimensional features and record them;

[0086] S320. Create a spatio-temporal influence matrix to record the intensity and direction of the interaction between different geographical features in time and space, where each element of the matrix represents the influence weight between different geographical features;

[0087] S330. Identify the periodicity of the change trend of different geographical features in the time dimension, which is defined as the dynamic influence relationship.

[0088] In this step, the analysis of the dynamic correlation of different geographical features in the spatio-temporal grid and the determination of whether there are two-dimensional features that affect three-dimensional features are specifically as follows:

[0089] ;

[0090] Among them, represents the mutual information amount between the two-dimensional feature and the three-dimensional feature , which is proportional to the dependence relationship, represents the probability that the two-dimensional feature and the three-dimensional feature occur simultaneously, is the marginal probability of the occurrence of the two-dimensional feature , is the marginal probability of the occurrence of the three-dimensional feature ;

[0091] The identification of the periodicity of the change trend of different geographical features in the time dimension is specifically as follows:

[0092] Based on the obtained spatio-temporal attributes, extract the information of each geographical feature under different time attributes and spatial attributes, and generate a time series by permutation;

[0093] Calculate the result correlation of each geographical feature in the time series at different time points to identify the period:

[0094] ;

[0095] Among them, represents the autocorrelation coefficient of the time series at the time delay , Geographical feature observation values representing time Represents the mean of the time series Represents the total number of samples in the time series

[0096] S400, establish an anomaly detection model, combine dynamic influence relationships and future behavior trends, judge whether there are potential abnormal events, and generate warning information

[0097] By analyzing historical data and spatio-temporal attributes, construct a highly adaptable anomaly detection model. This model uses past observation values and collected spatio-temporal data to identify normal behavior patterns and set relevant thresholds for comparison in real-time data monitoring. For example, for traffic flow data, the model can learn the normal range of flow fluctuations, and once the real-time data shows a significant deviation from this range, an alarm will be triggered

[0098] The anomaly detection model inputs the real-time collected data into the established anomaly detection model for monitoring. By calculating the error between the current observation value and the predicted value, it can effectively judge whether there is an anomaly. For example, as mentioned in the formula Specifically reflects how to analyze by combining the current state and the historical state. If the error exceeds the set threshold, it is determined that there is an abnormal event, and alarm information will be generated in a timely manner

[0099] When the model detects an abnormal event, the system will be able to quickly generate alarm information and transmit it to relevant decision-makers. These information not only include the basic characteristics of the abnormal event (such as event type, occurrence time, influence range, etc.), but also can be accompanied by analysis results based on historical data to help decision-makers quickly understand the potential impact and response measures of the event. For example, in traffic management, if a traffic accident occurs on a certain road section, the system will not only alarm in real-time, but also be able to provide the historical traffic flow data of this road section to help decision-makers evaluate the impact of the accident on the overall traffic

[0100] By combining real-time monitoring and dynamic models, this method can quickly respond to emergencies and provide data support for decision-making. For example, in environmental monitoring, if it is detected that the air quality in a certain area suddenly deteriorates, the model can quickly identify this anomaly and send an alarm to the management personnel, prompting them to take timely measures, such as activating the emergency plan or conducting on-site investigations. This rapid response ability significantly improves the timeliness and effectiveness of event response and reduces potential hazards

[0101] In addition, the established anomaly detection model is not limited to a single data source, but can also comprehensively consider the complex relationships between multiple spatio-temporal features, which is particularly important for highly dynamic environments (such as urban traffic, environmental monitoring, etc.). By enhancing the linkage between data, users can more comprehensively understand and respond to changes, promoting the realization of intelligent decision-making

[0102] As Figure 5 shown, the establishment of the anomaly detection model combines dynamic influence relationships and future behavior trends to determine whether there are potential abnormal events and generate warning information, specifically including:

[0103] S410, construct an anomaly detection model based on historical data and spatio-temporal attributes, and input the real-time collected spatio-temporal data into the anomaly detection model;

[0104] S420, use the constructed anomaly detection model to monitor the real-time data to determine whether there are abnormal events:

[0105] ;

[0106] wherein, represents the error value, represents the actual observed value at time, is the influence coefficient;

[0107] S430, set an error threshold. If the error value is greater than the error threshold, it is determined that there is an abnormal event.

[0108] Figure 6 is the structural block diagram of a spatio-temporal geographic information two-dimensional and three-dimensional data processing system provided by an embodiment of the present invention. As Figure 6 shown, the system includes:

[0109] A data integration module 100 for collecting spatio-temporal geographic information from different sources, including two-dimensional data and three-dimensional data, and integrating the collected two-dimensional data and three-dimensional data in terms of location information and time information and placing them in a unified spatio-temporal grid;

[0110] A geographic feature change tracking and analysis module 200 for setting up dynamic modeling on the spatio-temporal grid, real-time tracking and analyzing the changes of geographic features in the three-dimensional space and the behaviors on the two-dimensional plane, and predicting the future behavior trends of geographic features based on the analysis results;

[0111] An inter-feature interaction analysis module 300 for analyzing the mutual influences between different geographic features in the spatio-temporal grid, capturing the relationships between two-dimensional geographic features and three-dimensional geographic features, and analyzing the dynamic influence relationships between them;

[0112] An anomaly detection module 400 for establishing an anomaly detection model, combining dynamic influence relationships and future behavior trends to determine whether there are potential abnormal events and generating warning information.

[0113] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0114] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0115] The above embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent of the present invention should be subject to the appended claims.

[0116] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for processing two-dimensional and three-dimensional spatio-temporal geographic information, characterized in that The method includes: Collect spatio-temporal geographical information from different sources, including two-dimensional data and three-dimensional data, and integrate the collected two-dimensional data and three-dimensional data in terms of location information and time information, and place them in a unified spatio-temporal grid; Set up dynamic modeling on the spatio-temporal grid to track and analyze the changes of geographical features in three-dimensional space and their behaviors on the two-dimensional plane in real time, and predict the future behavior trends of geographical features based on the analysis results; Analyze the mutual influences between different geographical features in the spatio-temporal grid, capture the relationships between two-dimensional geographical features and three-dimensional geographical features, and analyze the dynamic influence relationships between them; Establish an anomaly detection model, combine the dynamic influence relationships and future behavior trends to determine whether there are potential abnormal events, and generate warning information.

2. The method according to claim 1, wherein The integration of the collected two-dimensional data and three-dimensional data in terms of location information and time information and placing them in a unified spatio-temporal grid specifically includes: Conduct data collection from the identified data sources to obtain the required two-dimensional data and three-dimensional data, including real-time collection of static data and dynamic data; Extract geographical features from the collected two-dimensional data and three-dimensional data, including location information and event information, and construct spatio-temporal attributes for each geographical feature, including spatial attributes and time attributes; Establish a multi-dimensional grid structure as the spatio-temporal grid, integrate the obtained two-dimensional data, three-dimensional data and corresponding spatio-temporal attributes, and place them in a unified spatio-temporal grid.

3. The method according to claim 2, characterized in that The setting up of dynamic modeling on the spatio-temporal grid to track and analyze the changes of geographical features in three-dimensional space and their behaviors on the two-dimensional plane in real time, and predict the future behavior trends of geographical features based on the analysis results specifically includes: Construct a dynamic model according to the collected two-dimensional data, three-dimensional data and spatio-temporal attributes, and use all the spatio-temporal attributes collected at the current moment as the input; Use the dynamic model to monitor the changes of geographical features in three-dimensional space, including position changes, morphological changes and behaviors on the two-dimensional plane, and based on the monitoring results, analyze the behavior trends of geographical features and predict future change trends and potential behavior patterns.

4. The method according to claim 3, wherein The prediction of future change trends and potential behavior patterns specifically is: Define the neighborhood of each geographical feature and capture all the neighborhood features related to this geographical feature within the neighborhood; Based on the dynamic model, analyze the future change trends of each geographical feature in combination with the neighborhood features: ； Among them, represents the state of the geographical feature at time . represents the set of neighborhood features of the geographical feature, is the influence coefficient, indicating the influence intensity of the neighborhood feature on the geographical feature . represents the difference between the state of the neighborhood feature and the geographical feature , that is, the influence effect of the neighborhood feature on the geographical feature.

5. The method according to claim 3, characterized in that, The analysis of the mutual influences between different geographical features in the spatio-temporal grid, capture the relationships between two-dimensional geographical features and three-dimensional geographical features, and analyze the dynamic influence relationships between them specifically includes: According to all the constructed spatio-temporal attributes, construct a relationship model between each geographical feature, analyze the dynamic relevance of different geographical features in the spatio-temporal grid, and determine whether there are two-dimensional features that affect three-dimensional features and record them; Create a spatio-temporal influence matrix to record the intensity and direction of the interaction between different geographical features in time and space, where each element of the matrix represents the influence weight between different geographical features; Identify the periodicity of the change trends of different geographical features in the time dimension, which is defined as the dynamic influence relationship.

6. The method according to claim 5, wherein Analyze the dynamic correlation of different geographical features in the spatio-temporal grid to determine whether there are two-dimensional features that affect three-dimensional features, specifically: ； Among them, represents the mutual information between two-dimensional features and three-dimensional features, and is proportional to the dependence relationship. represents the probability of two-dimensional features and three-dimensional features occurring simultaneously. is the marginal probability of two-dimensional features occurring. is the marginal probability of three-dimensional features occurring; Identify the periodicity of the change trends of different geographical features in the time dimension, specifically: Based on the obtained spatio-temporal attributes, extract the information of each geographical feature at different time attributes and spatial attributes, and generate a time series by arranging them; Calculate the result correlation of each geographical feature in the time series at different time points to identify the period: ； Among them, represents the autocorrelation coefficient of the time series at the time delay , represents the observed value of the geographical feature of time, represents the mean value of the time series, represents the total number of samples of the time series.

7. The method according to claim 5, wherein Establish an anomaly detection model, combine the dynamic influence relationship and future behavior trend, determine whether there are potential abnormal events, and generate warning information, specifically including: Based on historical data and spatio-temporal attributes, construct an anomaly detection model, and input the real-time collected spatio-temporal data into the anomaly detection model; Use the constructed anomaly detection model to monitor the real-time data to determine whether there are abnormal events: ； Among them, represents the error value, represents the actual observed value at a certain moment, is the influence coefficient; Set an error threshold. If the error value is greater than the error threshold, it is determined that there is an abnormal event.

8. A processing system for two-dimensional and three-dimensional spatio-temporal geographic information, characterized in that, The system includes: A data integration module for collecting spatio-temporal geographical information from different sources, including two-dimensional data and three-dimensional data, and integrating the collected two-dimensional data and three-dimensional data in terms of location information and time information, and placing them in a unified spatio-temporal grid; A geographical feature change tracking and analysis module for setting up dynamic modeling on the spatio-temporal grid, real-time tracking and analyzing the changes of geographical features in three-dimensional space and the behaviors on the two-dimensional plane, and predicting the future behavior trends of geographical features based on the analysis results; A feature interaction analysis module for analyzing the mutual influence between different geographical features in the spatio-temporal grid, capturing the relationship between two-dimensional geographical features and three-dimensional geographical features, and analyzing the dynamic influence relationship between them; An anomaly detection module for establishing an anomaly detection model, combining the dynamic influence relationship and future behavior trend, determining whether there are potential abnormal events, and generating warning information.

Images