Disaster monitoring data identification method and device, storage medium and electronic equipment

Abstract

The invention relates to a disaster monitoring data identification method and device, a storage medium and electronic equipment, and relates to the technical field of disaster monitoring, and the method comprises the steps: carrying out the fitting of a monitoring data fluctuation curve and a corresponding normal fluctuation curve, and obtaining a fitting rate; if the fitting rate is smaller than a preset fitting rate threshold value, determining the corresponding monitoring dimension as a suspected abnormal fluctuation dimension, and determining a first risk coefficient of monitoring data abnormal fluctuation of the suspected abnormal fluctuation dimension influenced by an actual interference event; when the first risk coefficient does not exceed a preset first threshold value, determining that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is abnormal fluctuation; and when the first risk coefficient exceeds a first threshold value, determining whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is abnormal fluctuation or not based on other suspected abnormal fluctuation dimensions. The method has the effect of improving the accuracy of identifying the disaster monitoring data.

Description

Technical Field

[0001] The present application relates to the field of disaster monitoring technology, and specifically to a disaster monitoring data identification method, device, storage medium and electronic equipment. Background Art

[0002] Disaster monitoring data refers to quantitative information on natural phenomena related to disasters, acquired through various technical means (such as sensors, satellites, radar, and ground-based observations). This data reflects environmental changes before, during, and after a disaster, and serves as a core basis for disaster early warning, risk assessment, and emergency decision-making. Therefore, identifying anomalies in disaster monitoring data is crucial for disaster early warning. Disaster early warning, in particular, involves monitoring, analyzing, and assessing disaster risks, issuing advance warnings, and providing individuals, communities, and governments with time to prepare. It is a critical component of disaster management, aiming to reduce disaster losses and casualties.

[0003] Currently, the common method for identifying disaster monitoring data involves collecting data and then identifying whether it exhibits abnormal fluctuations. If so, the data is considered abnormal, indicating a risk of disaster. However, if data collection is disrupted by interference, such as equipment failure or extreme weather conditions, the data may also exhibit abnormal fluctuations. Because these fluctuations are not caused by disaster risk, this method of identifying disaster monitoring data is inaccurate, leading to false triggering of disaster warnings. Summary of the Invention

[0004] In order to improve the accuracy of disaster monitoring data identification, the present application provides a disaster monitoring data identification method, device, storage medium and electronic equipment.

[0005] In a first aspect of the present application, a method for identifying disaster monitoring data is provided, which specifically includes: Acquire monitoring data within a preset time period of at least one monitoring dimension corresponding to the target disaster; Fitting the monitoring data within a preset time period of a single monitoring dimension to obtain a corresponding monitoring data fluctuation curve, and fitting the monitoring data fluctuation curve with a corresponding normal fluctuation curve to obtain a fitting rate; If the fitting rate is less than a preset fitting rate threshold, the corresponding monitoring dimension is determined as a suspected abnormal fluctuation dimension, and based on at least one actual interference event, a key interference event, and a corresponding key dimension occurring within the preset time, a first risk coefficient of abnormal fluctuation of the monitoring data of the suspected abnormal fluctuation dimension due to the influence of the actual interference event is determined, wherein the key interference event is an interference event that is likely to interfere with abnormal fluctuation of the monitoring data of the monitoring dimension, and the key dimension is a monitoring dimension that is likely to generate abnormal fluctuation of the monitoring data when the corresponding key interference event occurs; When the first risk coefficient does not exceed a preset first threshold, determining that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation; When the first risk coefficient exceeds the first threshold, based on other suspected abnormal fluctuation dimensions, determine whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation, and the other suspected abnormal fluctuation dimensions are other suspected abnormal fluctuation dimensions in each of the monitoring dimensions.

[0006] By adopting the above technical solution, the monitoring data within the preset time of a single monitoring dimension is fitted. If the fitting rate is less than the fitting rate threshold, it means that the similarity between the monitoring data fluctuation curve and the corresponding normal fluctuation curve is low, and the corresponding monitoring dimension may have abnormal fluctuations in the monitoring data, which may be abnormal fluctuations before the disaster occurs, or normal fluctuations caused by interference during the collection of monitoring data. Further verification is required, and the corresponding monitoring dimension is determined as a suspected abnormal fluctuation dimension. Furthermore, based on key interference events and corresponding key dimensions, the possibility of abnormal fluctuations in monitoring data caused by the actual interference events in the suspected abnormal fluctuation dimension is analyzed. If the first risk coefficient does not exceed the preset first threshold, it means that the possibility of abnormal fluctuations in the suspected abnormal fluctuation dimension caused by the actual interference event is small, which further indicates that the abnormal fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is due to the risk of the target disaster. Finally, the fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is determined to be abnormal fluctuation. On the contrary, if the first risk coefficient exceeds the first threshold, it means that the suspected abnormal fluctuation dimension is more likely to be affected by the actual interference event and experience abnormal fluctuations, but it cannot be ruled out that the fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is an abnormal fluctuation before the disaster occurs. In this case, a comprehensive analysis is performed in combination with other suspected abnormal fluctuation dimensions to re-determine whether the fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is an abnormal fluctuation, thereby improving the accuracy of disaster monitoring data identification and avoiding false triggering of disaster warnings.

[0007] In one embodiment, the determining of a first risk coefficient of abnormal fluctuation of monitoring data in the suspected abnormal fluctuation dimension due to the influence of the actual interference event, the key interference event, and the corresponding key dimension occurring within the preset time specifically includes: Obtain historical interference events that have induced abnormal fluctuations in monitoring data of the monitoring dimension during historical monitoring of the target disaster, count the number of occurrences of individual historical interference events among all historical interference events, and sort the historical interference events. Select the first number of historical interference events in order from the beginning to the end to determine them as key interference events. The greater the number of occurrences, the higher the corresponding historical interference event is ranked. Obtaining historical monitoring dimensions of abnormal fluctuations in monitoring data when a single key interference event occurs, counting the occurrence frequency of a single historical monitoring dimension among all historical monitoring dimensions, sorting the historical monitoring dimensions, and selecting a second number of historical monitoring dimensions in order from front to back to determine them as key dimensions corresponding to the single key interference event, where a higher occurrence frequency results in a higher ranking of the corresponding historical monitoring dimension; Determine a first weight for each of the key interference events, and determine a second weight for the key dimension corresponding to each of the key interference events, wherein the first weight is the ratio of the number of occurrences of each key interference event to the sum of the number of occurrences of all key interference events, and the second weight is the ratio of the frequency of occurrence of a single key dimension corresponding to the key interference event to the sum of the frequency of occurrence of all corresponding key dimensions; A first risk coefficient of abnormal fluctuation of the monitoring data caused by the suspected abnormal fluctuation dimension due to the influence of the actual interference event is determined based on at least one actual interference event occurring within the preset time, the first weight, and the second weight.

[0008] In one embodiment, determining, based on at least one actual interference event occurring within the preset time, the first weight, and the second weight, a first risk coefficient for abnormal fluctuations in monitoring data caused by the suspected abnormal fluctuation dimension due to the actual interference event specifically includes: If the key dimensions corresponding to the actual interference event include the suspected abnormal fluctuation dimension, the corresponding actual interference event is determined as the target interference event; Calculating a first product of a first weight of each target interference event and a second weight of a corresponding suspected abnormal fluctuation dimension; The first products are summed to obtain a first risk coefficient for abnormal fluctuation of the monitoring data caused by the actual interference event in the suspected abnormal fluctuation dimension.

[0009] In one embodiment, after determining that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation when the first risk coefficient does not exceed a preset first threshold, the method further includes: Obtaining first historical dimensions in which abnormal fluctuations in monitoring data occur when the target disaster occurs in historical disaster monitoring, counting the number of recurrences of each first historical dimension in all first historical dimensions, and selecting a third number of first historical dimensions from each of the first historical dimensions in descending order of the number of recurrences to determine as target dimensions; Obtaining a second historical dimension in which abnormal monitoring data fluctuations co-occur with a single target dimension when the target disaster occurs in historical disaster monitoring, and counting the number of times each second historical dimension co-occurs with the single target dimension; Selecting a fourth number of second historical dimensions from each of the second historical dimensions in descending order of the number of common occurrences as associated dimensions corresponding to the single target dimension; Determine a third weight for each target dimension, and determine a fourth weight for each associated dimension corresponding to the target dimension, wherein the third weight is the ratio of the number of repeated occurrences of each target dimension to the sum of the number of repeated occurrences of all target dimensions, and the fourth weight is the ratio of the number of common occurrences of a single associated dimension corresponding to the target dimension to the sum of the number of common occurrences of all corresponding associated dimensions; The suspected abnormal fluctuation dimension is verified according to the third weight and the fourth weight.

[0010] In one embodiment, verifying the suspected abnormal fluctuation dimension based on the third weight and the fourth weight specifically includes: Calculating a second risk coefficient for each other suspected abnormal fluctuation dimension to cause abnormal fluctuation of the monitoring data due to the actual interference event; if the second risk coefficient does not exceed the first threshold, determining the corresponding other suspected abnormal fluctuation dimension as the first reference dimension; When the suspected abnormal fluctuation dimension is the target dimension, determining the first reference dimension included in each associated dimension corresponding to the suspected abnormal fluctuation dimension as the first important dimension, and calculating the second product of the third weight of the suspected abnormal fluctuation dimension and the fourth weight of each corresponding first important dimension; The second products are summed to obtain the sum of the first products. If the sum of the first products exceeds the preset second threshold, the monitoring data fluctuation of the suspected abnormal fluctuation dimension is verified to be an abnormal fluctuation, and the monitoring data of each of the first important dimensions is verified to be an abnormal fluctuation.

[0011] In one embodiment, after verifying that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation, the method further includes: If the second risk coefficient exceeds the first threshold, determining the corresponding other suspected abnormal fluctuation dimension as the second reference dimension, and determining the second reference dimension included in each associated dimension corresponding to the suspected abnormal fluctuation dimension as the second important dimension; Calculating a third product of the third weight of the suspected abnormal fluctuation dimension and the fourth weights of the corresponding second important dimensions; If the third product exceeds a preset third threshold, determining that the corresponding monitoring data fluctuation of the second important dimension is an abnormal fluctuation; If the third product does not exceed the third threshold, it is determined that the corresponding fluctuation of the monitoring data of the second important dimension is a normal fluctuation.

[0012] In one embodiment, determining whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation based on other suspected abnormal fluctuation dimensions specifically includes: Calculating a second risk coefficient for each other suspected abnormal fluctuation dimension to cause abnormal fluctuation of the monitoring data due to the actual interference event; if the second risk coefficient does not exceed the first threshold, determining the corresponding other suspected abnormal fluctuation dimension as the first reference dimension; If the first reference dimension is included in each associated dimension corresponding to the target dimension, the corresponding target dimension is determined as the key focus dimension, and the first reference dimension included in each associated dimension corresponding to the key focus dimension is determined as the key associated dimension; Calculating a fourth product of the third weight of each of the key focus dimensions and the fourth weight of each corresponding key associated dimension, and summing the fourth products to obtain the sum of the second products of the corresponding key focus dimensions; Selecting the maximum sum of the second products from the sums of the second products, and if the key focus dimension corresponding to the maximum sum of the second products is not the suspected abnormal fluctuation dimension, determining that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is not an abnormal fluctuation; If the key focus dimension corresponding to the sum of the maximum second products is the suspected abnormal fluctuation dimension, the monitoring data fluctuation of the suspected abnormal fluctuation dimension is determined to be an abnormal fluctuation.

[0013] In a second aspect of the present application, a disaster monitoring data identification device is provided, specifically comprising: A data acquisition module, configured to acquire monitoring data of at least one monitoring dimension corresponding to a target disaster within a preset time period; A curve fitting module is used to fit the monitoring data within a preset time of a single monitoring dimension to obtain a corresponding monitoring data fluctuation curve, and to fit the monitoring data fluctuation curve with a corresponding normal fluctuation curve to obtain a fitting rate; a coefficient determination module for determining the corresponding monitoring dimension as a suspected abnormal fluctuation dimension if the fitting rate is less than a preset fitting rate threshold, and determining a first risk coefficient for abnormal fluctuations in monitoring data of the suspected abnormal fluctuation dimension due to the influence of the actual interference event based on at least one actual interference event, a key interference event, and a corresponding key dimension that occur within the preset time, wherein the key interference event is an interference event that is likely to interfere with abnormal fluctuations in the monitoring data of the monitoring dimension, and the key dimension is a monitoring dimension that is likely to generate abnormal fluctuations in monitoring data when the corresponding key interference event occurs; a first identification module, configured to determine that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation when the first risk coefficient does not exceed a preset first threshold; The second identification module is used to determine whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation based on other suspected abnormal fluctuation dimensions when the first risk coefficient exceeds the first threshold, and the other suspected abnormal fluctuation dimensions are other suspected abnormal fluctuation dimensions in each of the monitoring dimensions.

[0014] By adopting the above technical solution, the data acquisition module obtains the monitoring data within the preset time of the monitoring dimension, the curve fitting module determines the fitting rate of the monitoring data fluctuation curve and the corresponding normal fluctuation curve, and the coefficient determination module determines the first risk coefficient of the suspected abnormal fluctuation dimension being affected by the actual interference event to cause abnormal fluctuation of the monitoring data when the fitting rate is less than the preset fitting rate threshold. Then, the first identification module determines that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation when the first risk coefficient does not exceed the preset first threshold. Finally, the second identification module determines whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation when the first risk coefficient exceeds the first threshold.

[0015] In a third aspect of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is loaded and executed by a processor, the method steps as described in any one of the first aspects are performed.

[0016] In a fourth aspect of the present application, an electronic device is provided, specifically comprising: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the processor is used to load and execute the computer program stored in the memory so that the electronic device performs the method as described in any one of the first aspects.

[0017] In summary, the present application includes at least one of the following beneficial technical effects: if the fitting rate is less than the fitting rate threshold, it means that the similarity between the monitoring data fluctuation curve and the corresponding normal fluctuation curve is low, and the corresponding monitoring dimension may have abnormal fluctuations in the monitoring data, which may be abnormal fluctuations before the disaster occurs, or it may be normal fluctuations caused by interference during monitoring data collection, which requires further verification, and then the corresponding monitoring dimension is determined as a suspected abnormal fluctuation dimension. Furthermore, based on key interference events and corresponding key dimensions, the possibility of abnormal fluctuations in monitoring data caused by the influence of actual interference events in the suspected abnormal fluctuation dimension is analyzed. If the first risk coefficient does not exceed the preset first threshold, it means that the possibility of abnormal fluctuations in the suspected abnormal fluctuation dimension caused by the influence of actual interference events is small, and further indicates that the abnormal fluctuation of the monitoring data of this suspected abnormal fluctuation dimension is due to the risk of target disaster occurrence, and then the monitoring data fluctuation of the suspected abnormal fluctuation dimension is finally determined to be an abnormal fluctuation. On the contrary, if the first risk coefficient exceeds the first threshold, it means that the suspected abnormal fluctuation dimension is more likely to be affected by the actual interference event and experience abnormal fluctuations, but it cannot be ruled out that the fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is an abnormal fluctuation before the disaster occurs. In this case, a comprehensive analysis is performed in combination with other suspected abnormal fluctuation dimensions to re-determine whether the fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is an abnormal fluctuation, thereby improving the accuracy of disaster monitoring data identification and avoiding false triggering of disaster warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a disaster monitoring data identification method provided by an embodiment of the present application; Figure 2 This is a schematic structural diagram of a disaster monitoring data identification device provided in an embodiment of the present application; Figure 3 It is a structural diagram of another disaster monitoring data identification device provided in an embodiment of the present application.

[0019] Explanation of the accompanying drawings: 11. Data acquisition module; 12. Curve fitting module; 13. Coefficient determination module; 14. First identification module; 15. Second identification module; 16. First verification module; 17. Second verification module. DETAILED DESCRIPTION

[0020] In order to enable people skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0021] In the description of the embodiments of this application, words such as "exemplarily," "for example," or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplarily," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0022] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0023] See also Figure 1 The present application discloses a flowchart of a method for identifying disaster monitoring data. This method can be implemented using a computer program or run on a von Neumann-based disaster monitoring data identification device. The computer program can be integrated into an application or run as a standalone tool application, specifically including: S101: Acquire monitoring data of at least one monitoring dimension corresponding to a target disaster within a preset time period.

[0024] Specifically, in an embodiment of the present application, the target disaster is the type of disaster that is monitored and warned in the disaster monitoring area. The target disaster may be an earthquake disaster. In other embodiments, the target disaster may also be a debris flow disaster, etc. For example, if the disaster monitoring area is mountainous area A, then the target disaster is a debris flow disaster. Monitoring dimensions refer to indicators for observing, analyzing and warning target disasters from different levels and angles. Monitoring data is the specific monitoring result of a single monitoring dimension within a preset time. For example, if the target disaster is an earthquake disaster, then the corresponding monitoring dimensions include but are not limited to seismic wave dimensions, geomagnetic field dimensions, and groundwater level dimensions.

[0025] Furthermore, the execution subject of a method for identifying disaster monitoring data disclosed in the implementation of the present application is a server, and the terminals of the disaster monitoring personnel and various sensors for collecting monitoring data are all wirelessly connected to the server. The terminal can be a personal computer or a smart phone. A client related to disaster monitoring data identification is installed in the terminal, and the server is the background server of the client, specifically an independent physical server, or a cluster composed of multiple physical servers. When it is necessary to carry out disaster monitoring and early warning for the disaster monitoring area, the disaster monitoring personnel send an instruction to start monitoring to the server through the client in the terminal. Based on the instruction, the server obtains the monitoring data within the preset time of at least one monitoring dimension corresponding to the target disaster through various sensors preset in the disaster monitoring area. For example, when the target disaster is an earthquake disaster, the geomagnetic field intensity data within the preset time is obtained through the preset geomagnetometer, and the seismic wave data within the preset time is obtained through the preset geological sensor, and so on. It should be noted that there are multiple groups of monitoring data within the preset time of a single monitoring dimension.

[0026] S102: Fitting the monitoring data within a preset time of a single monitoring dimension to obtain a corresponding monitoring data fluctuation curve, and fitting the monitoring data fluctuation curve with the corresponding normal fluctuation curve to obtain a fitting rate.

[0027] Specifically, a preset MATLAB tool is used to fit multiple sets of monitoring data within a preset time period for a single monitoring dimension to obtain a monitoring data fluctuation curve corresponding to the monitoring dimension, that is, a curve showing how the monitoring data changes over time. The monitoring data fluctuation curve is then fitted to a preset normal fluctuation curve for the monitoring dimension using the MATLAB tool to obtain a fitting ratio. The greater the fitting ratio, the more similar the monitoring data fluctuation curve is to the corresponding normal fluctuation curve, and the less likely the monitoring data for the monitoring dimension will experience abnormal fluctuations. The normal fluctuation curve is the curve showing normal fluctuations of the monitoring data when no abnormalities occur in the monitoring dimension.

[0028] S103: If the fitting rate is less than the preset fitting rate threshold, the corresponding monitoring dimension is determined as a suspected abnormal fluctuation dimension, and based on at least one actual interference event, key interference event and corresponding key dimension that occur within the preset time, the first risk coefficient of abnormal fluctuation of the monitoring data caused by the suspected abnormal fluctuation dimension due to the influence of the actual interference event is determined.

[0029] Specifically, the key interference event is an interference event that is easy to interfere with the abnormal fluctuation of the monitoring data of the monitoring dimension, and the key dimension is the monitoring dimension that is easy to produce abnormal fluctuation of the monitoring data when the corresponding key interference event occurs. Among them, the interference event is an event that will affect the monitoring data of the monitoring dimension corresponding to the target disaster. For example, the target disaster is an earthquake disaster, and the interference event can be the existence of engineering construction in the disaster monitoring area, which interferes with the monitoring of seismic wave data and may cause abnormal fluctuations in seismic wave data. The interference event can also be a sensor failure, which may also cause abnormal fluctuations in the collected seismic wave data. Further, the fitting rate is compared with the preset fitting rate threshold. If the fitting rate is less than the fitting rate threshold, it means that the similarity between the monitoring data fluctuation curve and the corresponding normal fluctuation curve is low, and the corresponding monitoring dimension may have abnormal fluctuations in monitoring data. Then the corresponding monitoring dimension is determined as a suspected abnormal fluctuation dimension, and it is necessary to further determine whether the monitoring data of this suspected abnormal fluctuation dimension is an abnormal fluctuation reflecting the disaster risk. In an embodiment of the present application, a feasible implementation method is: based on the statistical records of historical interference events, historical interference events that have induced abnormal fluctuations in the monitoring data of the monitoring dimension in the historical monitoring of the target disaster are obtained, wherein there are historical interference events that have occurred multiple times in all the historical interference events obtained, and then the number of occurrences of a single historical interference event in all the historical interference events is counted. The more the number of occurrences, the more likely the corresponding historical interference event is to cause abnormal fluctuations in the monitoring data. According to the number of occurrences, each historical interference event is sorted. The more the number of occurrences, the higher the corresponding historical interference event is ranked. After the sorting is completed, the first number of historical interference events is selected in order from front to back to be determined as the key interference event, that is, the interference event with a large number of occurrences that is likely to cause abnormal fluctuations in the monitoring data. Among them, the statistical records of historical interference events include interference events that have interfered with the monitoring data in the historical monitoring of the target disaster and the monitoring dimensions that have caused abnormal fluctuations in the monitoring data.

[0030] Furthermore, the historical monitoring dimensions of abnormal fluctuations in monitoring data when a single key interference event occurs are obtained, and the frequency of occurrence of a single historical monitoring dimension among all historical monitoring dimensions is counted. The higher the frequency of occurrence, the more likely the corresponding historical monitoring dimension is to be disturbed by the key interference event and to experience abnormal fluctuations. Then, the historical monitoring dimensions are sorted according to the frequency of occurrence. The higher the frequency of occurrence, the higher the ranking of the corresponding historical monitoring dimension. Then, the second number of historical monitoring dimensions are selected in order from front to back to determine as the key dimensions corresponding to a single key interference event, that is, the monitoring dimensions that are easily disturbed by the key interference event and experience abnormal fluctuations.

[0031] Furthermore, a first weight of each key interference event is determined, and a second weight of the key dimension corresponding to each key interference event is determined. The first weight is the ratio of the number of occurrences of each key interference event to the sum of the number of occurrences of all key interference events. The second weight is the ratio of the frequency of occurrence of a single key dimension corresponding to a key interference event to the sum of the frequency of occurrence of all corresponding key dimensions. Then, based on the occurrence of at least one actual interference event within a preset time, the first weight and the second weight, the first risk coefficient of the suspected abnormal fluctuation dimension being affected by the actual interference event to produce abnormal fluctuations in the monitoring data is determined. The larger the first risk coefficient, the greater the possibility of abnormal fluctuations due to the influence of the actual interference event. The specific determination process is as follows: If the key dimensions corresponding to the key interference event include a suspected abnormal fluctuation dimension, then the key interference event is determined to be an important interference event. The product of the first weight of each important interference event and the second weight of the corresponding suspected abnormal fluctuation dimension is calculated. The larger the product, the greater the possibility that the suspected abnormal fluctuation dimension will be disturbed when the important interference event occurs, and the monitoring data will fluctuate abnormally. Based on the product, the inspection order of the corresponding important interference events is determined. The larger the product, the higher the inspection order. Furthermore, based on the inspection order, the current corresponding important interference event is checked in turn. After the important interference event is checked, the key interference events other than the important interference event are checked, and finally the actual interference event (actual interference event) is determined, thereby timely and efficiently determining the actual interference event.

[0032] After an actual interference event is identified, if any of the key dimensions corresponding to the actual interference event include a suspected abnormal fluctuation dimension, the corresponding actual interference event is identified as a target interference event. Next, the first product of each target interference event's first weight and the second weight of the corresponding suspected abnormal fluctuation dimension is calculated. The larger the first product, the greater the likelihood that the suspected abnormal fluctuation dimension will be affected by abnormal fluctuations in the interference monitoring data when the corresponding target interference event occurs. The sum of these first products yields the first risk coefficient.

[0033] S104: When the first risk coefficient does not exceed a preset first threshold, determining that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation.

[0034] Specifically, after the first risk coefficient is determined, if the first risk coefficient does not exceed the preset first threshold, it means that the possibility of abnormal fluctuations in this suspected abnormal fluctuation dimension due to the influence of actual interference events is small, and further indicates that the abnormal fluctuation of the monitoring data of this suspected abnormal fluctuation dimension is due to the risk of target disasters. Then, it is finally determined that the fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is abnormal fluctuation.

[0035] In other embodiments, based on historical disaster monitoring records of the target disaster, first historical dimensions in which abnormal fluctuations in monitoring data occur when the target disaster occurs are obtained, and the number of recurrences of a single first historical dimension among all first historical dimensions is counted. The greater the number of recurrences, the greater the likelihood of the target disaster occurring when abnormal fluctuations in monitoring data occur in the corresponding first historical dimension. Then, in descending order of the number of recurrences, a third number of first historical dimensions are selected from each first historical dimension to determine as target dimensions, i.e., monitoring dimensions in which abnormal fluctuations in monitoring data are likely to occur when the target disaster occurs. The historical disaster monitoring records include, but are not limited to, monitoring dimensions in which abnormal fluctuations in monitoring data occur when the target disaster occurs in historical time.

[0036] Furthermore, based on the above-mentioned historical disaster monitoring records, a second historical dimension in which abnormal monitoring data fluctuations occur together with a single target dimension when a target disaster occurs is obtained, that is, a monitoring dimension in which abnormal monitoring data fluctuations occur simultaneously with a single target dimension. The number of times each second historical dimension co-occurs with a single target dimension is counted. The greater the number of co-occurrences, the more likely the corresponding second historical dimension is to fluctuate abnormally when a target disaster occurs, when a single target dimension fluctuates abnormally. Then, in descending order of the number of co-occurrences, a fourth number of second historical dimensions are selected from each second historical dimension to be determined as the associated dimensions corresponding to the target dimension, which are monitoring dimensions that are likely to fluctuate abnormally simultaneously with the target dimension.

[0037] Furthermore, a third weight is determined for each target dimension, and a fourth weight is determined for each associated dimension corresponding to each target dimension. The third weight is the ratio of the number of recurrences of each target dimension to the sum of the number of recurrences of all target dimensions, and the fourth weight is the ratio of the number of co-occurrences of a single associated dimension corresponding to the target dimension to the sum of the number of co-occurrences of all associated dimensions. Finally, based on the third and fourth weights, the fluctuations in the monitoring data of the suspected abnormal fluctuation dimension are verified to be abnormal fluctuations. One feasible verification method is: Calculate the second risk coefficient of each other suspected abnormal fluctuation dimension that is affected by the actual interference event and has abnormal fluctuations in the monitoring data. The specific calculation method can be found in the calculation of the first risk coefficient in step S103, which will not be repeated here. If the second risk coefficient does not exceed the first threshold, it means that the possibility of the corresponding other suspected abnormal fluctuation dimensions being affected by the actual interference event and having abnormal fluctuations in the monitoring data is small, and it is likely to be a real abnormal fluctuation, then the corresponding other suspected abnormal fluctuation dimensions are determined as the first reference dimension. Then, when the suspected abnormal fluctuation dimension is the target dimension, the first reference dimension contained in each associated dimension corresponding to the suspected abnormal fluctuation dimension is determined as the first important dimension, and the second product of the third weight of the suspected abnormal fluctuation dimension and the fourth weight of each corresponding first important dimension is calculated. The larger the second product is, the greater the possibility of abnormal fluctuations in the corresponding first important dimension when there is abnormal fluctuation in the monitoring data of the suspected abnormal fluctuation dimension, and the higher the risk of the target disaster. Furthermore, the second products are summed to obtain the sum of the first products. If the sum of the first products exceeds a preset second threshold, it indicates not only a high risk of the target disaster, but also a high probability of abnormal fluctuations in the monitoring data of the suspected abnormal fluctuation dimension and the monitoring data of each first important dimension. The monitoring data fluctuations of the suspected abnormal fluctuation dimension are verified as abnormal fluctuations, and the monitoring data of each first important dimension are verified as abnormal fluctuations, thereby more accurately identifying the monitoring dimensions with abnormal fluctuations. Simultaneously, a warning message indicating the occurrence of the target disaster is sent to the terminal.

[0038] In one embodiment, if the second risk coefficient exceeds the first threshold, it means that the corresponding other suspected abnormal fluctuation dimensions are more likely to be affected by the actual interference event and the monitoring data will fluctuate abnormally, but there is still the possibility of abnormal fluctuations. Then, the corresponding other suspected abnormal fluctuation dimensions are determined as the second reference dimensions, and the second reference dimensions contained in each associated dimension corresponding to the suspected abnormal fluctuation dimension are determined as the second important dimension. The third product of the third weight of the suspected abnormal fluctuation dimension and the fourth weight of each corresponding second important dimension is calculated. The larger the third product is, the greater the possibility of abnormal fluctuation of the monitoring data of the corresponding second important dimension under the premise of determining abnormal fluctuation of the monitoring data of the suspected abnormal fluctuation dimension. Then, each third product is compared with the preset third threshold. If the third product exceeds the third threshold, it means that the monitoring data of the corresponding second important dimension is more likely to fluctuate abnormally, and the monitoring data fluctuation of the corresponding second important dimension is determined to be abnormal fluctuation. On the contrary, if the third product does not exceed the third threshold, it means that the monitoring data of the corresponding second important dimension is less likely to fluctuate abnormally, and the monitoring data fluctuation of the corresponding second important dimension is determined to be normal fluctuation.

[0039] S105: When the first risk coefficient exceeds the first threshold, based on other suspected abnormal fluctuation dimensions, determine whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation.

[0040] Specifically, other suspected abnormal fluctuation dimensions are other suspected abnormal fluctuation dimensions in each monitoring dimension, excluding the suspected abnormal fluctuation dimension currently determined to be an abnormal fluctuation. If the first risk coefficient exceeds the first threshold, it indicates that the suspected abnormal fluctuation dimension is likely to have been affected by an actual interference event and to have experienced abnormal fluctuations. However, it cannot be ruled out that the fluctuations in the monitoring data of the suspected abnormal fluctuation dimension are abnormal fluctuations before a disaster occurs, and further verification is required. In this case, when the first reference dimension is included in each associated dimension corresponding to the target dimension, the corresponding target dimension is determined as a key focus dimension, and the first reference dimension included in each associated dimension corresponding to this key focus dimension is determined as a key associated dimension.

[0041] Calculate the fourth product of the third weight of each key focus dimension and the fourth weight of the corresponding key associated dimension, sum each fourth product, and obtain the sum of the second products of the corresponding key focus dimensions. The larger the sum of the second products, the higher the risk of the target disaster, and the greater the possibility of abnormal fluctuations in the monitoring data of the corresponding key focus dimensions. Then, select the maximum sum of the second products from the sums of the second products. If the key focus dimension corresponding to the maximum sum of the second products is not the suspected abnormal fluctuation dimension, then determine that the monitoring data fluctuations of the suspected abnormal fluctuation dimension are not abnormal fluctuations; conversely, if the key focus dimension corresponding to the maximum sum of the second products is the suspected abnormal fluctuation dimension, then determine that the monitoring data fluctuations of the suspected abnormal fluctuation dimension are abnormal fluctuations.

[0042] The implementation principle of a disaster monitoring data identification method in an embodiment of the present application is as follows: if the first risk coefficient does not exceed the preset first threshold value, it indicates that the possibility of abnormal fluctuations in the suspected abnormal fluctuation dimension due to the influence of actual interference events is small, and further indicates that the abnormal fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is due to the risk of target disasters, and then the monitoring data fluctuation of the suspected abnormal fluctuation dimension is finally determined to be abnormal fluctuation. On the contrary, if the first risk coefficient exceeds the first threshold value, it indicates that the possibility of abnormal fluctuations in the suspected abnormal fluctuation dimension due to the influence of actual interference events is large, but it cannot be ruled out that the fluctuation of the monitoring data of the suspected abnormal fluctuation dimension is an abnormal fluctuation before the disaster occurs, then a comprehensive analysis is performed in combination with other suspected abnormal fluctuation dimensions to re-determine whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation, thereby improving the accuracy of disaster monitoring data identification and avoiding the false triggering of disaster warnings.

[0043] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0044] See Figure 2 , which is a schematic diagram of the structure of a disaster monitoring data identification device provided in an embodiment of the present application. This device for disaster monitoring data identification can be implemented as all or part of the device through software, hardware, or a combination of both. The device includes a data acquisition module 11, a curve fitting module 12, a coefficient determination module 13, a first identification module 14, and a second identification module 15.

[0045] The data acquisition module 11 is used to acquire monitoring data of at least one monitoring dimension corresponding to the target disaster within a preset time period; The curve fitting module 12 is used to fit the monitoring data within a preset time of a single monitoring dimension to obtain a corresponding monitoring data fluctuation curve, and fit the monitoring data fluctuation curve with the corresponding normal fluctuation curve to obtain a fitting rate; The coefficient determination module 13 is configured to determine the corresponding monitoring dimension as a suspected abnormal fluctuation dimension if the fitting rate is less than a preset fitting rate threshold, and determine a first risk coefficient of abnormal fluctuation of the monitoring data of the suspected abnormal fluctuation dimension due to the influence of the actual interference event based on at least one actual interference event, a key interference event, and a corresponding key dimension that occur within a preset time. The key interference event is an interference event that is likely to interfere with abnormal fluctuation of the monitoring data of the monitoring dimension, and the key dimension is a monitoring dimension that is likely to produce abnormal fluctuation of the monitoring data when the corresponding key interference event occurs. A first identification module 14 is configured to determine that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation when the first risk coefficient does not exceed a preset first threshold; The second identification module 15 is used to determine whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation based on other suspected abnormal fluctuation dimensions when the first risk coefficient exceeds the first threshold, and the other suspected abnormal fluctuation dimensions are other suspected abnormal fluctuation dimensions in each monitoring dimension.

[0046] Optionally, the coefficient determination module 13 is specifically configured to: Obtain historical interference events that have induced abnormal fluctuations in monitoring data of the monitoring dimension during historical monitoring of the target disaster, count the number of occurrences of individual historical interference events among all historical interference events, and sort each historical interference event. Select the historical interference event with the largest number in order from the beginning to the end to determine it as the key interference event. The larger the number of occurrences, the higher the corresponding historical interference event is ranked. Obtain historical monitoring dimensions of abnormal fluctuations in monitoring data when a single key interference event occurs, count the occurrence frequency of a single historical monitoring dimension among all historical monitoring dimensions, sort the historical monitoring dimensions, and select the second number of historical monitoring dimensions in order from front to back to determine them as the key dimensions corresponding to the single key interference event. The higher the occurrence frequency, the higher the corresponding historical monitoring dimension is ranked. Determine a first weight for each key interference event and a second weight for the key dimension corresponding to each key interference event, wherein the first weight is the ratio of the number of occurrences of each key interference event to the sum of the number of occurrences of all key interference events, and the second weight is the ratio of the frequency of occurrence of a single key dimension corresponding to the key interference event to the sum of the frequency of occurrence of all corresponding key dimensions; According to at least one actual interference event occurring within a preset time, a first weight and a second weight, a first risk coefficient of abnormal fluctuation of monitoring data caused by the suspected abnormal fluctuation dimension due to the influence of the actual interference event is determined.

[0047] Optionally, the coefficient determination module 13 is specifically configured to: If the key dimensions corresponding to the actual interference event contain suspected abnormal fluctuation dimensions, the corresponding actual interference event will be determined as the target interference event; Calculate a first product of a first weight of each target interference event and a second weight of the corresponding suspected abnormal fluctuation dimension; The first products are summed to obtain a first risk coefficient of abnormal fluctuation of the monitoring data caused by the suspected abnormal fluctuation dimension due to the influence of the actual interference event.

[0048] Optional, such as Figure 3 As shown, the device further includes a first verification module 16, which is specifically configured to: Obtaining first historical dimensions in which abnormal fluctuations in monitoring data occur when a target disaster occurs in historical disaster monitoring, counting the number of recurrences of each first historical dimension in all first historical dimensions, and selecting a third number of first historical dimensions from each first historical dimension in descending order of the number of recurrences as target dimensions; Obtain the second historical dimension in which abnormal monitoring data fluctuations co-occur with the single target dimension when the target disaster occurs in historical disaster monitoring, and count the number of times each second historical dimension co-occurs with the single target dimension; Selecting a fourth number of second historical dimensions from each second historical dimension in descending order of the number of co-occurrences as associated dimensions corresponding to the single target dimension; Determine a third weight for each target dimension and a fourth weight for each associated dimension corresponding to each target dimension, where the third weight is the ratio of the number of recurrences of each target dimension to the sum of the number of recurrences of all target dimensions, and the fourth weight is the ratio of the number of co-occurrences of a single associated dimension corresponding to the target dimension to the sum of the number of co-occurrences of all corresponding associated dimensions; Based on the third and fourth weights, the suspected abnormal fluctuation dimensions are verified.

[0049] Optionally, the first verification module 16 is specifically configured to: Calculate a second risk coefficient for each other suspected abnormal fluctuation dimension to indicate abnormal fluctuation of the monitoring data due to the actual interference event; if the second risk coefficient does not exceed the first threshold, determine the corresponding other suspected abnormal fluctuation dimension as the first reference dimension; When the suspected abnormal fluctuation dimension is the target dimension, the first reference dimension included in each associated dimension corresponding to the suspected abnormal fluctuation dimension is determined as the first important dimension, and the second product of the third weight of the suspected abnormal fluctuation dimension and the fourth weight of each corresponding first important dimension is calculated; The second products are summed to obtain the sum of the first products. If the sum of the first products exceeds the preset second threshold, the monitoring data fluctuation of the suspected abnormal fluctuation dimension is verified to be an abnormal fluctuation, and the monitoring data of each first important dimension is verified to be an abnormal fluctuation.

[0050] Optionally, the device further includes a second verification module 17, specifically configured to: If the second risk coefficient exceeds the first threshold, the corresponding other suspected abnormal fluctuation dimension is determined as the second reference dimension, and the second reference dimension included in each associated dimension corresponding to the suspected abnormal fluctuation dimension is determined as the second important dimension; Calculating the third product of the third weight of the suspected abnormal fluctuation dimension and the fourth weight of each corresponding second important dimension; If the third product exceeds a preset third threshold, determining that the corresponding monitoring data fluctuation of the second important dimension is an abnormal fluctuation; If the third product does not exceed the third threshold, it is determined that the corresponding fluctuation of the monitoring data of the second important dimension is a normal fluctuation.

[0051] Optionally, the second identification module 15 is specifically configured to: Calculate a second risk coefficient for each other suspected abnormal fluctuation dimension to indicate abnormal fluctuation of the monitoring data due to the actual interference event; if the second risk coefficient does not exceed the first threshold, determine the corresponding other suspected abnormal fluctuation dimension as the first reference dimension; If the first reference dimension is included in each associated dimension corresponding to the target dimension, the corresponding target dimension is determined as the key focus dimension, and the first reference dimension included in each associated dimension corresponding to the key focus dimension is determined as the key associated dimension; Calculate the fourth product of the third weight of each key focus dimension and the fourth weight of each corresponding key associated dimension, and sum each fourth product to obtain the sum of the second products of the corresponding key focus dimensions; The maximum sum of the second products is selected from the sums of the second products. If the key focus dimension corresponding to the maximum sum of the second products is not a suspected abnormal fluctuation dimension, then the monitoring data fluctuation of the suspected abnormal fluctuation dimension is determined not to be an abnormal fluctuation. If the key focus dimension corresponding to the sum of the largest second products is a suspected abnormal fluctuation dimension, the monitoring data fluctuation of the suspected abnormal fluctuation dimension is determined to be an abnormal fluctuation.

[0052] It should be noted that the above-described embodiment of a disaster monitoring data identification device, when executing a disaster monitoring data identification method, only uses the division of the above-described functional modules as an example. In actual applications, the above-described functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the above-described embodiment of a disaster monitoring data identification device and a disaster monitoring data identification method embodiment are based on the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0053] An embodiment of the present application further discloses a computer-readable storage medium, and the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, a disaster monitoring data identification method of the above embodiment is implemented.

[0054] Among them, the computer program can be stored in a computer-readable medium, the computer program includes computer program code, the computer program code can be in the form of source code, object code, executable file or certain middleware, etc. The computer-readable medium includes any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that computer-readable medium includes but is not limited to the above-mentioned components.

[0055] Among them, through this computer-readable storage medium, a disaster monitoring data identification method of the above embodiment is stored in a computer-readable storage medium, and is loaded and executed on a processor to facilitate the storage and application of the above method.

[0056] An embodiment of the present application also discloses an electronic device, in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, the above-mentioned disaster monitoring data identification method is implemented.

[0057] Among them, the electronic device can be an electronic device such as a desktop computer, a laptop computer or a cloud server, and the electronic device includes but is not limited to a processor and a memory. For example, the electronic device can also include input and output devices, network access devices and buses, etc.

[0058] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0059] Among them, the memory can be an internal storage unit of the electronic device, such as the hard disk or memory of the electronic device, or it can be an external storage device of the electronic device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD) or flash memory card (FC) equipped on the electronic device. In addition, the memory can also be a combination of an internal storage unit and an external storage device of the electronic device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or is to be output. This application does not impose any restrictions on this.

[0060] Among them, through this electronic device, a disaster monitoring data identification method of the above embodiment is stored in the memory of the electronic device, and is loaded and executed on the processor of the electronic device for easy use.

[0061] The above description is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A disaster monitoring data identification method, characterized in that: The method comprises: Acquire monitoring data within a preset time period of at least one monitoring dimension corresponding to the target disaster; Fitting the monitoring data within a preset time period of a single monitoring dimension to obtain a corresponding monitoring data fluctuation curve, and fitting the monitoring data fluctuation curve with a corresponding normal fluctuation curve to obtain a fitting rate; If the fitting rate is less than a preset fitting rate threshold, the corresponding monitoring dimension is determined as a suspected abnormal fluctuation dimension, and based on at least one actual interference event, a key interference event, and a corresponding key dimension occurring within the preset time, a first risk coefficient of abnormal fluctuation of the monitoring data of the suspected abnormal fluctuation dimension due to the influence of the actual interference event is determined, wherein the key interference event is an interference event that is likely to interfere with abnormal fluctuation of the monitoring data of the monitoring dimension, and the key dimension is a monitoring dimension that is likely to generate abnormal fluctuation of the monitoring data when the corresponding key interference event occurs; When the first risk coefficient does not exceed a preset first threshold, determining that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation; When the first risk coefficient exceeds the first threshold, based on other suspected abnormal fluctuation dimensions, determine whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation, and the other suspected abnormal fluctuation dimensions are other suspected abnormal fluctuation dimensions in each of the monitoring dimensions.

2. The disaster monitoring data identification method according to claim 1, characterized in that: The determining, based on the actual interference events, key interference events, and corresponding key dimensions occurring within the preset time, of a first risk coefficient for abnormal fluctuations in monitoring data caused by the suspected abnormal fluctuation dimension due to the actual interference event specifically includes: Obtain historical interference events that have induced abnormal fluctuations in monitoring data of the monitoring dimension during historical monitoring of the target disaster, count the number of occurrences of individual historical interference events among all historical interference events, and sort the historical interference events. Select the first number of historical interference events in order from the beginning to the end to determine them as key interference events. The greater the number of occurrences, the higher the corresponding historical interference event is ranked. Obtaining historical monitoring dimensions of abnormal fluctuations in monitoring data when a single key interference event occurs, counting the occurrence frequency of a single historical monitoring dimension among all historical monitoring dimensions, sorting the historical monitoring dimensions, and selecting a second number of historical monitoring dimensions in order from front to back to determine them as key dimensions corresponding to the single key interference event, where a higher occurrence frequency results in a higher ranking of the corresponding historical monitoring dimension; Determine a first weight for each of the key interference events, and determine a second weight for the key dimension corresponding to each of the key interference events, wherein the first weight is the ratio of the number of occurrences of each key interference event to the sum of the number of occurrences of all key interference events, and the second weight is the ratio of the frequency of occurrence of a single key dimension corresponding to the key interference event to the sum of the frequency of occurrence of all corresponding key dimensions; A first risk coefficient of abnormal fluctuation of the monitoring data caused by the suspected abnormal fluctuation dimension due to the influence of the actual interference event is determined based on at least one actual interference event occurring within the preset time, the first weight, and the second weight.

3. The disaster monitoring data identification method according to claim 2, characterized in that: The determining, based on the at least one actual interference event occurring within the preset time, the first weight, and the second weight, of a first risk coefficient for abnormal fluctuation of the monitoring data caused by the suspected abnormal fluctuation dimension due to the actual interference event specifically includes: If the key dimensions corresponding to the actual interference event include the suspected abnormal fluctuation dimension, the corresponding actual interference event is determined as the target interference event; Calculating a first product of a first weight of each target interference event and a second weight of a corresponding suspected abnormal fluctuation dimension; The first products are summed to obtain a first risk coefficient for abnormal fluctuation of the monitoring data caused by the actual interference event in the suspected abnormal fluctuation dimension.

4. The disaster monitoring data identification method according to claim 2, characterized in that: After determining that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation when the first risk coefficient does not exceed a preset first threshold, the method further includes: Obtaining first historical dimensions in which abnormal fluctuations in monitoring data occur when the target disaster occurs in historical disaster monitoring, counting the number of recurrences of each first historical dimension in all first historical dimensions, and selecting a third number of first historical dimensions from each of the first historical dimensions in descending order of the number of recurrences to determine as target dimensions; Obtaining a second historical dimension in which abnormal monitoring data fluctuations co-occur with a single target dimension when the target disaster occurs in historical disaster monitoring, and counting the number of times each second historical dimension co-occurs with the single target dimension; Selecting a fourth number of second historical dimensions from each of the second historical dimensions in descending order of the number of common occurrences as associated dimensions corresponding to the single target dimension; Determine a third weight for each target dimension, and determine a fourth weight for each associated dimension corresponding to the target dimension, wherein the third weight is the ratio of the number of repeated occurrences of each target dimension to the sum of the number of repeated occurrences of all target dimensions, and the fourth weight is the ratio of the number of common occurrences of a single associated dimension corresponding to the target dimension to the sum of the number of common occurrences of all corresponding associated dimensions; The suspected abnormal fluctuation dimension is verified according to the third weight and the fourth weight.

5. The disaster monitoring data identification method according to claim 4, characterized in that: The verifying the suspected abnormal fluctuation dimension according to the third weight and the fourth weight specifically includes: Calculating a second risk coefficient for each other suspected abnormal fluctuation dimension to cause abnormal fluctuation of the monitoring data due to the actual interference event; if the second risk coefficient does not exceed the first threshold, determining the corresponding other suspected abnormal fluctuation dimension as the first reference dimension; When the suspected abnormal fluctuation dimension is the target dimension, determining the first reference dimension included in each associated dimension corresponding to the suspected abnormal fluctuation dimension as the first important dimension, and calculating the second product of the third weight of the suspected abnormal fluctuation dimension and the fourth weight of each corresponding first important dimension; The second products are summed to obtain the sum of the first products. If the sum of the first products exceeds the preset second threshold, the monitoring data fluctuation of the suspected abnormal fluctuation dimension is verified to be an abnormal fluctuation, and the monitoring data of each of the first important dimensions is verified to be an abnormal fluctuation.

6. The disaster monitoring data identification method according to claim 5, characterized in that: After verifying that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is abnormal fluctuation, the method further includes: If the second risk coefficient exceeds the first threshold, determining the corresponding other suspected abnormal fluctuation dimension as the second reference dimension, and determining the second reference dimension included in each associated dimension corresponding to the suspected abnormal fluctuation dimension as the second important dimension; Calculating a third product of the third weight of the suspected abnormal fluctuation dimension and the fourth weights of the corresponding second important dimensions; If the third product exceeds a preset third threshold, determining that the corresponding monitoring data fluctuation of the second important dimension is an abnormal fluctuation; If the third product does not exceed the third threshold, it is determined that the corresponding fluctuation of the monitoring data of the second important dimension is a normal fluctuation.

7. The disaster monitoring data identification method according to claim 4, characterized in that: Determining whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation based on other suspected abnormal fluctuation dimensions specifically includes: Calculating a second risk coefficient for each other suspected abnormal fluctuation dimension to cause abnormal fluctuation of the monitoring data due to the actual interference event; if the second risk coefficient does not exceed the first threshold, determining the corresponding other suspected abnormal fluctuation dimension as the first reference dimension; If the first reference dimension is included in each associated dimension corresponding to the target dimension, the corresponding target dimension is determined as the key focus dimension, and the first reference dimension included in each associated dimension corresponding to the key focus dimension is determined as the key associated dimension; Calculating a fourth product of the third weight of each of the key focus dimensions and the fourth weight of each corresponding key associated dimension, and summing the fourth products to obtain the sum of the second products of the corresponding key focus dimensions; Selecting the maximum sum of the second products from the sums of the second products, and if the key focus dimension corresponding to the maximum sum of the second products is not the suspected abnormal fluctuation dimension, determining that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is not an abnormal fluctuation; If the key focus dimension corresponding to the sum of the maximum second products is the suspected abnormal fluctuation dimension, the monitoring data fluctuation of the suspected abnormal fluctuation dimension is determined to be an abnormal fluctuation.

8. A disaster monitoring data identification device, characterized in that: include: A data acquisition module (11) is used to acquire monitoring data of at least one monitoring dimension corresponding to a target disaster within a preset time period; A curve fitting module (12) is used to fit the monitoring data within a preset time of a single monitoring dimension to obtain a corresponding monitoring data fluctuation curve, and to fit the monitoring data fluctuation curve with a corresponding normal fluctuation curve to obtain a fitting rate; A coefficient determination module (13) is configured to determine the corresponding monitoring dimension as a suspected abnormal fluctuation dimension if the fitting rate is less than a preset fitting rate threshold, and determine a first risk coefficient of abnormal fluctuation of monitoring data caused by the suspected abnormal fluctuation dimension due to the influence of the actual interference event based on at least one actual interference event, a key interference event, and a corresponding key dimension that occurs within the preset time, wherein the key interference event is an interference event that is likely to interfere with abnormal fluctuation of monitoring data of the monitoring dimension, and the key dimension is a monitoring dimension that is likely to generate abnormal fluctuation of monitoring data when the corresponding key interference event occurs; A first identification module (14) is configured to determine that the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation when the first risk coefficient does not exceed a preset first threshold; A second identification module (15) is used to determine whether the monitoring data fluctuation of the suspected abnormal fluctuation dimension is an abnormal fluctuation based on other suspected abnormal fluctuation dimensions when the first risk coefficient exceeds the first threshold value, and the other suspected abnormal fluctuation dimensions are other suspected abnormal fluctuation dimensions in each of the monitoring dimensions.

9. A computer-readable storage medium storing a computer program, wherein: When the computer program is loaded and executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor loads and executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images