Disaster situation prediction method and system combined with iron tower monitoring data

Abstract

The invention relates to the technical field of disaster prediction, and provides a disaster prediction method and system combined with iron tower monitoring data. The method comprises the following steps: carrying out block processing on a disaster situation prediction region to obtain a plurality of local disaster situation prediction regions; interaction is carried out to obtain communication iron tower layout information of the disaster prediction area; obtaining multiple groups of communication iron towers; pre-constructing a monitoring data calling model, and obtaining a plurality of iron tower calling amount thresholds; performing communication data random calling on the multiple groups of communication iron towers to obtain multiple groups of random communication feature data; pre-constructing a disaster intensity analysis model, and synchronizing the plurality of groups of random communication feature data to the disaster intensity analysis model to obtain a plurality of disaster intensity parameters; and performing global analysis on the disaster situation prediction area, and outputting a global disaster situation prediction result. According to the method and the device, the technical problem in the prior art that an area with serious disasters cannot be accurately positioned is solved, and the technical effects of improving the positioning accuracy of the area with serious disasters and reducing the influence of the disasters are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of disaster prediction, and in particular to a disaster prediction method and system in combination with tower monitoring data. Background Art

[0002] When a major unconventional emergency occurs, the data used to analyze, judge, and predict this major event determines the scientificity, efficiency, and rationality of the final decision. When these data are converted into knowledge, they will play a huge role in predicting major unconventional emergencies. By combining tower monitoring data to predict the occurrence and development of disasters, the priority of disaster relief can be determined. In disaster prevention, mitigation, and relief, data analysis plays an increasingly important role. Disaster prediction is becoming more and more important today, and how to accurately locate the location of a disaster has become a top priority for research.

[0003] In summary, the existing technology has the problem of being unable to accurately locate the area where the disaster is severe. Summary of the invention

[0004] Based on this, it is necessary to provide a disaster prediction method and system that combines tower monitoring data to improve the accuracy of positioning in disaster-stricken areas and reduce the impact of disasters in response to the above technical problems.

[0005] In a first aspect, the present application provides a disaster prediction method combined with tower monitoring data, the method comprising: presetting a grid threshold, and based on the grid threshold, performing block processing on the disaster prediction area to obtain multiple local disaster prediction areas; interactively obtaining communication tower layout information of the disaster prediction area, wherein the communication tower layout information includes K communication towers, and the K communication towers are identified by K layout coordinates; according to the multiple local disaster prediction areas and the K layout coordinates, the K communication towers are divided into groups to obtain multiple groups of communication towers; pre-constructing a monitoring data call model, synchronizing the multiple local disaster prediction areas to the monitoring data call model, and obtaining multiple tower call volume thresholds; performing random calls on the communication data of the multiple groups of communication towers according to the multiple tower call volume thresholds to obtain multiple groups of random communication feature data; pre-constructing a disaster intensity analysis model, synchronizing the multiple groups of random communication feature data to the disaster intensity analysis model, and obtaining multiple disaster intensity parameters; performing a global analysis of the disaster prediction area according to the multiple disaster intensity parameters, and outputting a global disaster prediction result.

[0006] In a second aspect, the present application provides a disaster prediction system combined with tower monitoring data, the system comprising: a grid threshold preset module, the grid threshold preset module is used to preset a grid threshold, and based on the grid threshold, the disaster prediction area is block-processed to obtain multiple local disaster prediction areas; a communication tower layout information acquisition module, the communication tower layout information acquisition module is used to interactively obtain communication tower layout information of the disaster prediction area, wherein the communication tower layout information includes K communication towers, and the K communication towers are marked with K layout coordinates; a multiple communication tower acquisition module, the multiple communication tower acquisition module is used to group the K communication towers according to the multiple local disaster prediction areas and the K layout coordinates to obtain multiple groups of communication towers; a monitoring data call model construction module, The monitoring data call model construction module is used to pre-build a monitoring data call model, synchronize the multiple local disaster prediction areas to the monitoring data call model, and obtain multiple tower call volume thresholds; a random communication feature data acquisition module, the random communication feature data acquisition module is used to randomly call the communication data of the multiple groups of communication towers according to the multiple tower call volume thresholds, and obtain multiple groups of random communication feature data; a disaster intensity parameter acquisition module, the disaster intensity parameter acquisition module is used to pre-build a disaster intensity analysis model, synchronize the multiple groups of random communication feature data to the disaster intensity analysis model, and obtain multiple disaster intensity parameters; a global disaster prediction result output module, the global disaster prediction result output module is used to perform a global analysis of the disaster prediction area according to the multiple disaster intensity parameters, and output a global disaster prediction result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] First, a grid threshold is preset, and the disaster prediction area is block-processed based on the grid threshold to obtain multiple local disaster prediction areas; secondly, the communication tower layout information of the disaster prediction area is interactively obtained, wherein the communication tower layout information includes K communication towers, and the K communication towers are identified by K layout coordinates; next, the K communication towers are grouped according to the multiple local disaster prediction areas and the K layout coordinates to obtain multiple groups of communication towers; then a monitoring data call model is pre-constructed, and the multiple local disaster prediction areas are synchronized to the monitoring data call model to obtain multiple tower call volume thresholds; then, communication data of the multiple groups of communication towers are randomly called according to the multiple tower call volume thresholds to obtain multiple groups of random communication feature data; then a disaster intensity analysis model is pre-constructed, and the multiple groups of random communication feature data are synchronized to the disaster intensity analysis model to obtain multiple disaster intensity parameters; finally, the disaster prediction area is globally analyzed according to the multiple disaster intensity parameters, and a global disaster prediction result is output. The present application solves the technical problem in the prior art that it is impossible to accurately locate areas with severe disasters, thereby achieving the technical effect of improving the accuracy of positioning areas with severe disasters and reducing the impact of disasters.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a flow chart of a disaster prediction method in combination with tower monitoring data in one embodiment;

[0011] Figure 2 A schematic diagram of a flow chart of obtaining a tower call volume threshold value in a disaster prediction method in combination with tower monitoring data in one embodiment;

[0012] Figure 3 It is a structural block diagram of a disaster prediction system in combination with tower monitoring data in one embodiment.

[0013] Explanation of the reference numerals: grid threshold preset module 11, communication tower layout information acquisition module 12, multiple communication tower groups acquisition module 13, monitoring data call model construction module 14, random communication characteristic data acquisition module 15, disaster intensity parameter acquisition module 16, global disaster prediction result output module 17. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] like Figure 1 As shown, the present application provides a disaster prediction method combined with tower monitoring data, the method comprising:

[0016] Preset a grid threshold, and perform block processing on the disaster prediction area based on the grid threshold to obtain multiple local disaster prediction areas;

[0017] Tower monitoring refers to a monitoring tower that monitors a target area, such as a forest, wetland, grassland, etc., by using a monitoring tower to monitor the target area, obtain tower monitoring data, and use the tower monitoring data to predict the disaster situation in the target area. The present application provides a disaster prediction method that combines tower monitoring data. The monitored data can be used to predict in advance whether a disaster will occur in the target area, so that staff can issue early warning information in a timely manner to minimize losses when a natural disaster is about to occur, there is a risk of a natural disaster, or a natural disaster is occurring but has not caused serious damage.

[0018] The disaster prediction area refers to the area where disaster prediction is required. The preset grid threshold refers to the threshold of the grid boundary set by the staff. In this application, it refers to the block processing of the disaster prediction area, for example, the urban management area is divided into unit grids according to certain standards, and a form of supervision and disposal is established by strengthening the inspection of the components and events of the unit grids; the disaster prediction area is divided into multiple small grids by the grid threshold, and the small grids are multiple local disaster prediction areas. By dividing multiple local disaster prediction areas, the scope of disaster prediction can be narrowed, so as to achieve the effect of improving the accuracy of disaster prediction.

[0019] Interactively obtain communication tower layout information of the disaster prediction area, wherein the communication tower layout information includes K communication towers, and the K communication towers are marked with K layout coordinates;

[0020] The communication tower layout information of the disaster prediction area can be obtained by querying the communication tower layout map, wherein the communication tower layout information includes K communication towers, K refers to the number of communication towers in the disaster prediction area, and each communication tower has a location identifier. By obtaining the communication tower layout information of the disaster prediction area, a foundation is laid for the subsequent division of multiple groups of communication towers.

[0021] According to the multiple local disaster prediction areas and the K layout coordinate identifiers, the K communication towers are divided into groups to obtain multiple groups of communication towers;

[0022] Group division refers to dividing the K communication towers according to the multiple local disaster prediction areas and the K layout coordinate identifiers. For example, one local disaster prediction area is selected from the multiple local disaster prediction areas, and the number of communication towers in the local disaster prediction area is determined according to the K layout coordinate identifiers. The number of communication towers in the local disaster prediction area can be recorded as the first group of communication towers, and so on, multiple groups of communication towers can be obtained. Multiple groups of communication towers are obtained through the multiple local disaster prediction areas and the K layout coordinate identifiers, which contributes to the subsequent data synchronization call.

[0023] Pre-constructing a monitoring data call model, synchronizing the multiple local disaster prediction areas to the monitoring data call model, and obtaining multiple tower call volume thresholds;

[0024] The monitoring data call model includes a terrain complexity analysis module and a regional classification execution module. The multiple local disaster prediction areas are synchronized to the monitoring data call model to obtain multiple tower call thresholds, that is, the number of towers to be called is determined according to the terrain complexity of the local disaster prediction area; the number of towers called is the tower call threshold. By obtaining multiple tower call thresholds, data support is provided for the subsequent acquisition of multiple groups of random communication feature data.

[0025] The monitoring data calling model includes a terrain complexity analysis module and a regional classification execution module;

[0026] A terrain complexity calculation formula is pre-constructed, and the terrain complexity calculation formula is as follows:

[0027]

[0028] Where TCI stands for terrain complexity index, N is the number of contour lines in the topographic map, Characterizes the rate of change of height of contour line i in the x direction, Characterizes the rate of change of the height of contour line i in the y direction, The Euclidean norm that characterizes the height variation on contour line i;

[0029] Pre-constructing a multi-level sample iron tower call volume, wherein the multi-level sample iron tower call volume is mapped to multiple sample complexity thresholds;

[0030] Synchronizing the terrain complexity calculation formula to the terrain complexity analysis module;

[0031] The multi-level sample tower call volume is synchronized to the regional hierarchical execution module.

[0032] The monitoring data call model includes a terrain complexity analysis module and a regional classification execution module, wherein the terrain complexity analysis module is used to determine the terrain complexity of the local disaster prediction area, thereby determining the tower call amount. For example, the complexity of the plain is low, and only two communication towers are needed to fully record the monitoring data. The complexity of the mountain is high, and ten communication towers are needed to fully record the monitoring data. A terrain complexity calculation formula is pre-constructed, wherein TCI represents the terrain complexity index, N is the number of contour lines in the topographic map, Characterizes the rate of change of height of contour line i in the x direction, Characterizes the rate of change of the height of contour line i in the y direction, The Euclidean norm that characterizes the height change on the contour line i; pre-constructing the multi-level sample tower call volume, the multi-level sample tower call volume has a functional relationship with the multiple sample complexity thresholds; synchronizing the terrain complexity calculation formula to the terrain complexity analysis module; synchronizing the multi-level sample tower call volume to the regional grading execution module, and obtaining the monitoring data call model by constructing the terrain complexity analysis module and the regional grading execution module, which provides a basis for subsequently obtaining multiple groups of random communication feature data.

[0033] like Figure 2 As shown, interactively obtain a regional topographic map of the disaster prediction area;

[0034] Splitting the regional topographic map according to the multiple local disaster prediction areas to obtain multiple local topographic maps;

[0035] Extracting data from the plurality of local topographic maps to obtain a plurality of groups of contour line parameters;

[0036] Synchronizing the plurality of groups of contour line parameters to the terrain complexity analysis module of the monitoring data call model to obtain a plurality of local complexity indexes;

[0037] In the regional hierarchical execution module, the multiple local complexity indexes are traversed based on the multiple sample complexity thresholds to obtain the multiple tower call volume thresholds.

[0038] The regional topographic map refers to the regional topographic map of the disaster prediction area, which is obtained by horizontally projecting the objects and landforms on the ground (projecting them onto the horizontal plane along the plumb line direction) and shrinking them onto the drawing at a certain scale. In this application, it refers to the contour map; splitting the regional topographic map according to the multiple local disaster prediction areas means dividing the regional topographic map according to the multiple local disaster prediction areas to obtain multiple local topographic maps; calculating according to the horizontal projection and proportion of the objects and landforms in the local topographic map to obtain multiple groups of contour line parameters; synchronizing the multiple groups of contour line parameters to the terrain complexity analysis module of the monitoring data call model, and generating multiple local complexity indexes according to the terrain complexity calculation formula; inputting the complexity index into the regional hierarchical execution module, and obtaining multiple tower call volume thresholds corresponding to the complexity index according to the multiple sample complexity thresholds. By obtaining multiple tower call volume thresholds, support is provided for subsequent random calls of communication data and obtaining multiple groups of random communication feature data.

[0039] Randomly calling the communication data of the multiple groups of communication towers according to the multiple tower calling amount thresholds to obtain multiple groups of random communication feature data;

[0040] Random call of communication data means, for example, selecting any one of the multiple local disaster prediction areas, the total number of communication towers in the local disaster prediction area is 100, and the threshold value of the calling quantity of the multiple towers is 10, then the data of 10 communication towers are randomly selected from the 100 communication towers for random call of communication data, which is recorded as a set of random communication feature data; and so on, multiple sets of random communication feature data are obtained in a random combination manner, which lays a foundation for the subsequent acquisition of multiple disaster intensity parameters.

[0041] Pre-constructing a disaster intensity analysis model, synchronizing the multiple groups of random communication feature data to the disaster intensity analysis model, and obtaining multiple disaster intensity parameters;

[0042] The disaster intensity analysis model refers to a model for predicting the disaster intensity in the multiple local disaster prediction areas, and multiple disaster intensity parameters corresponding to the multiple random communication feature data are obtained by inputting the multiple groups of random communication feature data, wherein the disaster intensity parameter refers to the severity of the disaster. By obtaining multiple disaster severity data, it contributes to the subsequent accurate disaster prediction.

[0043] The disaster intensity analysis model includes a tower status analysis module and a local disaster calculation module;

[0044] Interactively obtain K groups of historical routine operation and maintenance data of the K communication towers;

[0045] Counting the fault frequency according to the K groups of historical routine operation and maintenance data to obtain K fault frequency parameters;

[0046] Perform disaster monitoring confidence assignment based on the K fault frequency parameters to obtain K disaster monitoring confidence levels;

[0047] Synchronize the K disaster monitoring trust levels to the local disaster calculation module;

[0048] A tower abnormality parameter function is pre-constructed, and the tower abnormality parameter function is synchronized to the tower status analysis module.

[0049] The tower abnormal parameter function is as follows:

[0050]

[0051] Among them, G is the tower abnormal parameter value, N is the number of period divisions, (On i ) and (Off i ) represent the online and offline time of the tower at the (i)th data point, respectively, and w i Assign weights to each period, is the rate of change of the online time of the communication tower over time, is the rate of change of the offline time of the communication tower over time;

[0052] A data partition threshold is preset, and the data partition threshold and the tower abnormality parameter are functionally synchronized to the tower status analysis module.

[0053] The disaster intensity analysis model includes a tower status analysis module and a local disaster calculation module, wherein the status analysis module is to analyze the operation data of the K communication towers to determine whether the K communication towers are operating normally; the local disaster calculation module is to determine the severity of the disaster in the multiple local disaster prediction areas; interactively obtain K groups of historical routine operation and maintenance data of the K communication towers, wherein the K groups of historical routine operation and maintenance data can be obtained from historical data; count the fault frequency according to the K groups of historical routine operation and maintenance data to obtain K fault frequency parameters, where the fault frequency refers to the fault frequency in The number of failures of the K communication towers within the specified time is used to obtain K failure frequency parameters, and confidence assignment for disaster monitoring is performed based on the K failure frequency parameters, wherein confidence assignment refers to the assignment of trust in the accuracy of the monitoring data of the communication towers. For example, the fewer the number of failures of the K communication towers, the more stable the communication towers are, and the higher the accuracy of the monitored data is. K disaster monitoring trusts are obtained, and the K disaster monitoring trusts are synchronized to the local disaster calculation module; a tower abnormality parameter function is constructed, and the tower abnormality parameter function is synchronized to the tower status analysis module. In the tower abnormality parameter function, G is the tower abnormality parameter value, N is the number of period divisions, (On i ) and (Off i ) represent the online and offline time of the tower at the (i)th data point, respectively, and w i Assign weights to each period, is the rate of change of the online time of the communication tower over time, The data division threshold is set by the staff, and the data division threshold and the tower abnormal parameter function are synchronized to the tower status analysis module to judge the tower status. By obtaining the tower status analysis module and the local disaster calculation module and synchronizing them to the disaster intensity analysis module, data support is provided for the accuracy of subsequent judgment of disaster intensity.

[0054] A global analysis is performed on the disaster prediction area according to the multiple disaster intensity parameters, and a global disaster prediction result is output.

[0055] Global analysis refers to analyzing the entire disaster prediction area, traversing the disaster intensity sequence through the preset disaster source tracking activation node, obtaining the global disaster prediction result, and then performing rescue work in the entire disaster prediction area based on the global disaster prediction result.

[0056] Serializing the multiple disaster intensity parameters to obtain a disaster intensity sequence;

[0057] Preset a disaster source tracing activation node, and use the disaster source tracing activation node to traverse the disaster intensity sequence to obtain the global disaster prediction result, wherein the global disaster prediction result includes M core risk areas, wherein M is a positive integer less than K;

[0058] Interactively obtaining a regional path layout of the disaster prediction area;

[0059] Generate M emergency routes according to the regional path layout and the M core risk areas;

[0060] Priority rescue is given to the M core risk areas according to the M rescue routes.

[0061] Sort the multiple disaster intensity parameters obtained to obtain a disaster intensity sequence sorted by the severity of the disaster; set a disaster source tracking activation node, the disaster source tracking activation node refers to a disaster intensity parameter set by the staff, traverse the disaster intensity sequence according to the disaster intensity parameter, and obtain the global disaster prediction result, wherein the global disaster prediction result includes M core risk areas, wherein M is a positive integer less than K, and the core risk area refers to the M local disaster prediction areas that need to be rescued and have a disaster intensity greater than the disaster source tracking activation node; obtain the regional path layout of the disaster prediction area by querying relevant data, generate M rescue routes according to the regional path layout and the M core risk areas, and then rescue the M core risk areas according to the M emergency routes. The present application solves the technical problem that the existing technology cannot accurately locate the area with severe disasters, and achieves the technical effect of improving the accuracy of positioning the area with severe disasters and reducing the impact of disasters.

[0062] like Figure 3 As shown, the embodiment of the present application also provides a disaster prediction system combined with tower monitoring data, the system comprising:

[0063] A grid threshold preset module 11, wherein the grid threshold preset module 11 is used to preset a grid threshold, and based on the grid threshold, block processing is performed on the disaster prediction area to obtain multiple local disaster prediction areas;

[0064] A communication tower layout information acquisition module 12, wherein the communication tower layout information acquisition module 12 is used to interactively obtain the communication tower layout information of the disaster prediction area, wherein the communication tower layout information includes K communication towers, and the K communication towers are identified by K layout coordinates;

[0065] A module 13 for obtaining multiple groups of communication towers, wherein the module 13 is used for grouping the K communication towers according to the multiple local disaster prediction areas and the K layout coordinate identifiers to obtain multiple groups of communication towers;

[0066] A monitoring data call model construction module 14, wherein the monitoring data call model construction module is used to pre-construct a monitoring data call model, synchronize the multiple local disaster prediction areas to the monitoring data call model, and obtain multiple tower call volume thresholds;

[0067] A random communication characteristic data acquisition module 15, wherein the random communication characteristic data acquisition module 14 is used to randomly call the communication data of the multiple groups of communication towers according to the multiple tower call amount thresholds to obtain multiple groups of random communication characteristic data;

[0068] A disaster intensity parameter acquisition module 16, wherein the disaster intensity parameter acquisition module 15 is used to pre-build a disaster intensity analysis model, synchronize the multiple groups of random communication feature data to the disaster intensity analysis model, and obtain multiple disaster intensity parameters;

[0069] The global disaster prediction result output module 17 is used to perform a global analysis on the disaster prediction area according to the multiple disaster intensity parameters and output a global disaster prediction result.

[0070] Furthermore, the embodiment of the present application also includes:

[0071] The monitoring data calling model includes a module, and the monitoring data calling model includes a module for the monitoring data calling model including a terrain complexity analysis module and a regional classification execution module;

[0072] A terrain complexity calculation formula construction module is used to pre-construct a terrain complexity calculation formula. The terrain complexity calculation formula is as follows:

[0073]

[0074] Where TCI stands for terrain complexity index, N is the number of contour lines in the topographic map, Characterizes the rate of change of height of contour line i in the x direction, Characterizes the rate of change of the height of contour line i in the y direction, The Euclidean norm that characterizes the height variation on contour line i;

[0075] A multi-level sample iron tower call volume construction module, wherein the multi-level sample iron tower call volume construction module is used to pre-construct the multi-level sample iron tower call volume, wherein the multi-level sample iron tower call volume is mapped to multiple sample complexity thresholds;

[0076] A terrain complexity calculation formula synchronization module, the terrain complexity calculation formula synchronization module is used to synchronize the terrain complexity calculation formula to the terrain complexity analysis module;

[0077] A sample tower call volume synchronization module is used to synchronize the multi-level sample tower call volume to the regional hierarchical execution module.

[0078] Furthermore, the embodiment of the present application also includes:

[0079] A regional topographic map acquisition module, the regional topographic map acquisition module is used to interactively obtain a regional topographic map of the disaster prediction area;

[0080] A local topographic map acquisition module, the local topographic map acquisition module is used to split the regional topographic map according to the multiple local disaster prediction areas to obtain multiple local topographic maps;

[0081] A contour line parameter acquisition module, which is used to extract data from the multiple local topographic maps to obtain multiple groups of contour line parameters;

[0082] A local complexity index obtaining module, the local complexity index obtaining module is used to synchronize the multiple groups of contour line parameters to the terrain complexity analysis module of the monitoring data calling model to obtain multiple local complexity indexes;

[0083] The tower call volume threshold acquisition module is used to traverse the multiple local complexity indexes in the regional hierarchical execution module based on the multiple sample complexity thresholds to obtain the multiple tower call volume thresholds.

[0084] Furthermore, the embodiment of the present application also includes:

[0085] The disaster intensity analysis model includes a module, and the disaster intensity analysis model includes a module for the disaster intensity analysis model, including a tower state analysis module and a local disaster calculation module;

[0086] A historical conventional operation and maintenance data acquisition module, wherein the historical conventional operation and maintenance data activity module is used to interactively obtain K groups of historical conventional operation and maintenance data of the K communication towers;

[0087] A fault frequency parameter acquisition module, the fault frequency parameter acquisition module is used to count the fault frequency according to the K groups of historical routine operation and maintenance data to obtain K fault frequency parameters;

[0088] A disaster monitoring confidence obtaining module, the disaster monitoring confidence obtaining module is used to perform disaster monitoring confidence assignment based on the K fault frequency parameters to obtain K disaster monitoring confidences;

[0089] A disaster monitoring trust degree synchronization module, the disaster monitoring trust degree synchronization module is used to synchronize the K disaster monitoring trust degrees to the local disaster calculation module;

[0090] The tower abnormal parameter functional formula construction module is used to pre-construct the tower abnormal parameter functional formula and synchronize the tower abnormal parameter functional formula to the tower status analysis module.

[0091] Furthermore, the embodiment of the present application also includes:

[0092] The tower abnormal parameter functional module is used for the tower abnormal parameter functional formula as follows:

[0093]

[0094] Among them, G is the tower abnormal parameter value, N is the number of period divisions, (On i ) and (Off i ) represent the online and offline time of the tower at the (i)th data point, respectively, and w i Assign weights to each period, is the rate of change of the online time of the communication tower over time, is the rate of change of the offline time of the communication tower over time;

[0095] A data partition threshold preset module is used to preset a data partition threshold, and functionally synchronize the data partition threshold and the tower abnormality parameter to the tower status analysis module.

[0096] Furthermore, the embodiment of the present application also includes:

[0097] A disaster intensity sequence acquisition module, wherein the disaster intensity sequence acquisition module is used to sequence the multiple disaster intensity parameters to obtain a disaster intensity sequence;

[0098] A global disaster prediction result acquisition module, the global disaster prediction result acquisition module is used to preset a disaster source tracing activation node, and use the disaster source tracing activation node to traverse the disaster intensity sequence to obtain the global disaster prediction result, wherein the global disaster prediction result includes M core risk areas, wherein M is a positive integer less than K;

[0099] A regional path layout acquisition module, the regional path layout acquisition module is used to interactively obtain the regional path layout of the disaster prediction area;

[0100] A rescue route generation module, the rescue route generation module is used to generate M rescue routes according to the regional path layout and the M core risk areas;

[0101] A priority rescue module is used to perform priority rescue on the M core risk areas according to the M rescue routes.

[0102] For the specific embodiment of the disaster prediction method system combined with tower monitoring data, please refer to the embodiment of the disaster prediction method combined with tower monitoring data above, which will not be repeated here. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0103] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0104] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A disaster prediction method combining tower monitoring data, characterized in that: The method comprises: Preset a grid threshold, and perform block processing on the disaster prediction area based on the grid threshold to obtain multiple local disaster prediction areas; Interactively obtain communication tower layout information of the disaster prediction area, wherein the communication tower layout information includes K communication towers, and the K communication towers are marked with K layout coordinates; According to the multiple local disaster prediction areas and the K layout coordinate identifiers, the K communication towers are divided into groups to obtain multiple groups of communication towers; Pre-constructing a monitoring data call model, synchronizing the multiple local disaster prediction areas to the monitoring data call model, and obtaining multiple tower call volume thresholds; Randomly calling the communication data of the multiple groups of communication towers according to the multiple tower calling amount thresholds to obtain multiple groups of random communication feature data; Pre-constructing a disaster intensity analysis model, synchronizing the multiple groups of random communication feature data to the disaster intensity analysis model, and obtaining multiple disaster intensity parameters; A global analysis is performed on the disaster prediction area according to the multiple disaster intensity parameters, and a global disaster prediction result is output.

2. The method according to claim 1, characterized in that Pre-constructing a monitoring data calling model, the method further includes: The monitoring data calling model includes a terrain complexity analysis module and a regional classification execution module; A terrain complexity calculation formula is pre-constructed, and the terrain complexity calculation formula is as follows: Among them, represents the terrain complexity index, N is the number of contour lines in the topographic map, represents the height change rate of contour line i in the x direction, represents the height change rate of contour line i in the y direction, and represents the Euclidean norm of the height change on contour line i; Pre-constructing a multi-level sample iron tower call volume, wherein the multi-level sample iron tower call volume is mapped to multiple sample complexity thresholds; Synchronizing the terrain complexity calculation formula to the terrain complexity analysis module; The multi-level sample tower call volume is synchronized to the regional hierarchical execution module.

3. The method according to claim 2, characterized in that The plurality of local disaster prediction areas are synchronized to the monitoring data call model to obtain a plurality of tower call volume thresholds, and the method further includes: interactively obtaining a regional topographic map of the disaster prediction area; Splitting the regional topographic map according to the multiple local disaster prediction areas to obtain multiple local topographic maps; Extracting data from the plurality of local topographic maps to obtain a plurality of groups of contour line parameters; Synchronizing the plurality of groups of contour line parameters to the terrain complexity analysis module of the monitoring data call model to obtain a plurality of local complexity indexes; In the regional hierarchical execution module, the multiple local complexity indexes are traversed based on the multiple sample complexity thresholds to obtain the multiple tower call volume thresholds.

4. The method according to claim 1, characterized in that Pre-constructing a disaster intensity analysis model, the method further includes: The disaster intensity analysis model includes a tower status analysis module and a local disaster calculation module; Interactively obtain K groups of historical routine operation and maintenance data of the K communication towers; Counting the fault frequency according to the K groups of historical routine operation and maintenance data to obtain K fault frequency parameters; Perform disaster monitoring confidence assignment based on the K fault frequency parameters to obtain K disaster monitoring confidence levels; Synchronize the K disaster monitoring trust levels to the local disaster calculation module; A tower abnormality parameter function is pre-constructed, and the tower abnormality parameter function is synchronized to the tower status analysis module.

5. The method according to claim 4, characterized in that Pre-constructing a tower abnormal parameter function formula, and synchronizing the tower abnormal parameter function formula to the tower status analysis module, the method further includes: The tower abnormal parameter function is as follows: Among them, G is the tower abnormal parameter value, N is the number of period divisions, (On i ) and (Off i ) represent the online and offline time of the tower at the (i)th data point, respectively, and w i Assign weights to each period, is the rate of change of the online time of the communication tower over time, is the rate of change of the offline time of the communication tower over time; A data partition threshold is preset, and the data partition threshold and the tower abnormality parameter are functionally synchronized to the tower status analysis module.

6. The method according to claim 5, characterized in that Performing a global analysis on the disaster prediction area according to the multiple disaster intensity parameters and outputting a global disaster prediction result, the method further includes: Serializing the multiple disaster intensity parameters to obtain a disaster intensity sequence; Preset a disaster source tracing activation node, and use the disaster source tracing activation node to traverse the disaster intensity sequence to obtain the global disaster prediction result, wherein the global disaster prediction result includes M core risk areas, wherein M is a positive integer less than K; Interactively obtaining a regional path layout of the disaster prediction area; Generate M emergency routes according to the regional path layout and the M core risk areas; Priority rescue is given to the M core risk areas according to the M rescue routes.

7. The disaster prediction system combined with tower monitoring data is characterized by: The system comprises: A grid threshold preset module, which is used to preset a grid threshold and perform block processing on the disaster prediction area based on the grid threshold to obtain multiple local disaster prediction areas; A communication tower layout information acquisition module, the communication tower layout information acquisition module is used to interactively obtain the communication tower layout information of the disaster prediction area, wherein the communication tower layout information includes K communication towers, and the K communication towers are marked with K layout coordinates; A module for obtaining multiple groups of communication towers, wherein the module is used to divide the K communication towers into groups according to the multiple local disaster prediction areas and the K layout coordinate identifiers to obtain multiple groups of communication towers; A monitoring data call model construction module, wherein the monitoring data call model construction module is used to pre-construct a monitoring data call model, synchronize the multiple local disaster prediction areas to the monitoring data call model, and obtain multiple tower call volume thresholds; A random communication characteristic data acquisition module, wherein the random communication characteristic data acquisition module is used to randomly call the communication data of the multiple groups of communication towers according to the multiple tower call amount thresholds to obtain multiple groups of random communication characteristic data; A disaster intensity parameter acquisition module, wherein the disaster intensity parameter acquisition module is used to pre-build a disaster intensity analysis model, synchronize the multiple groups of random communication feature data to the disaster intensity analysis model, and obtain multiple disaster intensity parameters; A global disaster prediction result output module is used to perform a global analysis on the disaster prediction area according to the multiple disaster intensity parameters and output a global disaster prediction result.

Images