False fire point data identification method and device, equipment and storage medium

Abstract

The invention relates to a false fire point data identification method and device, equipment and a storage medium. The method comprises the following steps: acquiring target fire point monitoring data of a target area within a preset historical duration; performing spatial clustering on multiple pieces of fire point data in the target fire point monitoring data based on a preset clustering mode to obtain multiple clustering objects of the target fire point monitoring data; performing time spectrum analysis on each clustering object to obtain power spectrum density distribution of each clustering object; based on the power spectral density distribution of the clustering objects, identifying fire point types of the clustering objects, and determining the clustering objects of which the fire point types are false fire points as target clustering objects; and determining the fire point data in the target clustering object as the false fire point data of the target area in the preset historical duration, so that the false fire point data in the fire point monitoring data can be quickly identified by effectively utilizing the spatial distribution rule and the time spectrum characteristics of the historical fire point data. The identification efficiency and the identification accuracy of the false fire point data can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data processing, and particularly to a method, apparatus, device, and storage medium for identifying false fire point data. Background Art

[0002] Fire is one of the important disasters threatening safety and the ecological environment. In order to detect and control fires in a timely manner, it is necessary to monitor fire point hotspots, and satellite remote sensing is an important means for fire point monitoring. However, due to the influence of sensors and environmental factors, there are often a large number of false fire points in remote sensing images, such as traditional industrial heat source factories, scattered bare lands, photovoltaic power stations, etc. Although these false fire points have relatively low temperatures and are not clearly marked on the map, their thermal radiation characteristics are similar to those of small fire points, and it is easy to confuse them with real small fire points. Small fire points are the important objects of concern in fire point monitoring. These false fire points will interfere with the monitoring of real fire points, affect the accuracy of fire point monitoring data, and cause unnecessary waste of resources.

[0003] Currently, it mainly relies on manual identification of false fire point data in fire point monitoring data, with low efficiency and low identification accuracy. Therefore, there is an urgent need for a method for identifying false fire point data to quickly and accurately identify false fire point data in fire point monitoring data. Summary of the Invention

[0004] To solve the above technical problems, the present disclosure provides a method, apparatus, device, and storage medium for identifying false fire point data.

[0005] The first aspect of the present disclosure provides a method for identifying false fire point data, including:

[0006] Obtaining target fire point monitoring data of a target area within a preset historical duration;

[0007] Performing spatial clustering on multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple clustering objects of the target fire point monitoring data;

[0008] Performing time-frequency spectrum analysis on each clustering object to obtain the power spectral density distribution of each clustering object;

[0009] For each clustering object, based on the power spectral density distribution of the clustering object, identifying the fire point type of the clustering object, and determining the clustering object with the fire point type of false fire point as the target clustering object;

[0010] Determining the fire point data in the target clustering object as the false fire point data of the target area within the preset historical duration.

[0011] Optionally, the above obtaining target fire point monitoring data of a target area within a preset historical duration includes:

[0012] Obtain the original fire point monitoring data of the target area within a preset historical time period;

[0013] Based on a preset data cleaning method, clean the original fire point monitoring data to obtain the target fire point monitoring data of the target area within a preset historical time period. The preset data cleaning method includes at least one of removing abnormal data, removing duplicate data, and removing invalid data.

[0014] Optionally, the above preset clustering method includes a density clustering algorithm;

[0015] Perform spatial clustering on multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple clustering objects of the target fire point monitoring data, including:

[0016] Based on the preset neighborhood radius and preset minimum number of points included in the density clustering algorithm, through the density clustering algorithm, cluster the fire point data adjacent in space in the target fire point monitoring data into one category to obtain multiple clustering objects of the target fire point monitoring data.

[0017] Optionally, the above based on the preset neighborhood radius and preset minimum number of points included in the density clustering algorithm, through the density clustering algorithm, cluster the fire point data adjacent in space in the target fire point monitoring data into one category to obtain multiple clustering objects of the target fire point monitoring data, including:

[0018] For each fire point data to be clustered in the target fire point monitoring data, find the target fire points whose distance from the fire point position of the fire point data to be clustered is less than or equal to the preset neighborhood radius, and obtain the fire point data of the target fire points;

[0019] When the number of target fire points is greater than or equal to the preset minimum number of points included, cluster the fire point data to be clustered and the fire point data of the target fire points to obtain a clustering object, and determine the fire point data in the clustering object as the fire point data that has been to be clustered;

[0020] Determine the fire point data outside the clustering object as the fire point data to be clustered, and perform the steps of finding the target fire points whose distance from the fire point position of the fire point data to be clustered is less than or equal to the preset neighborhood radius and the subsequent steps on the fire point data to be clustered until the number of fire point data to be clustered in the target fire point monitoring data is 0, to obtain multiple clustering objects of the target fire point monitoring data.

[0021] Optionally, the above perform time-frequency spectrum analysis on each clustering object to obtain the power spectral density distribution of each clustering object, including:

[0022] For each clustering object, perform a fast Fourier transform on the time series of the clustering object to obtain the power spectral density distribution of the clustering object.

[0023] Optionally, for each clustering object, based on the power spectral density distribution of the clustering object, identify the fire point type of the clustering object, and determine the clustering object with the fire point type of false fire point as the target clustering object, including:

[0024] For each clustering object, extract the maximum power spectral density in the power spectral density distribution of the clustering object;

[0025] When the maximum power spectral density of the clustering object is greater than the preset density threshold, determine that the fire point type of the clustering object is a real fire point;

[0026] When the maximum power spectral density of the clustering object is less than or equal to the preset density threshold, determine that the fire point type of the clustering object is a false fire point.

[0027] Optionally, the above determination of the fire point data in the target clustering object as the false fire point data in the target area within the preset historical duration includes:

[0028] Determine the map position of the fire point position of the fire point data in the target clustering object in the preset non-fire point map, where the preset non-fire point map includes multiple non-fire point positions;

[0029] Identify the target positions that coincide with the non-fire point positions in the preset non-fire point map among the map positions;

[0030] Calculate the ratio between the number of target positions and the total number of map positions corresponding to the fire point positions in the target clustering object to obtain the recognition accuracy rate of false fire points in the target fire point monitoring data;

[0031] When the recognition accuracy rate is greater than the preset accuracy rate threshold, determine the fire point data in the target clustering object as the false fire point data in the target area within the preset historical duration;

[0032] When the recognition accuracy rate is less than or equal to the preset accuracy rate threshold, adjust the clustering parameters of the preset clustering method, and re-execute the steps of spatially clustering the multiple fire point data in the target fire point monitoring data based on the preset clustering method and subsequent steps.

[0033] The second aspect of the present disclosure provides an apparatus for identifying false fire point data, including:

[0034] An acquisition module, configured to acquire target fire point monitoring data in a target area within a preset historical duration;

[0035] A clustering module, configured to spatially cluster multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple clustering objects of the target fire point monitoring data;

[0036] An analysis module for performing time-frequency spectrum analysis on each clustering object to obtain the power spectral density distribution of each clustering object;

[0037] An identification module for identifying the type of hot spot of each clustering object based on the power spectral density distribution of the clustering object, and determining the clustering object with the hot spot type of false hot spot as the target clustering object;

[0038] A determination module for determining the hot spot data in the target clustering object as the false hot spot data of the target area within a preset historical duration.

[0039] Optionally, the above acquisition module includes:

[0040] An acquisition sub-module for acquiring the original hot spot monitoring data of the target area within a preset historical duration;

[0041] A data cleaning sub-module for cleaning the original hot spot monitoring data based on a preset data cleaning method to obtain the target hot spot monitoring data of the target area within a preset historical duration, and the preset data cleaning method includes at least one of removing abnormal data, removing duplicate data, and removing invalid data.

[0042] Optionally, the above preset clustering method includes a density clustering algorithm;

[0043] The above clustering module includes:

[0044] A clustering sub-module for clustering the hot spot data adjacent in space in the target hot spot monitoring data into one category through a density clustering algorithm based on a preset neighborhood radius and a preset minimum inclusion point number in the density clustering algorithm to obtain multiple clustering objects of the target hot spot monitoring data.

[0045] Optionally, the above clustering sub-module includes:

[0046] A search unit for searching for a target hot spot whose distance from the hot spot position of the hot spot data to be clustered in the target hot spot monitoring data is less than or equal to a preset neighborhood radius for each hot spot data to be clustered in the target hot spot monitoring data, and acquiring the hot spot data of the target hot spot;

[0047] A clustering unit for clustering the hot spot data of the hot spot data to be clustered and the target hot spot when the number of target hot spots is greater than or equal to a preset minimum inclusion point number to obtain a clustering object, and determining the hot spot data in the clustering object as the hot spot data to be clustered;

[0048] An execution unit is used to determine the fire point data outside the clustering object as the fire point data to be clustered, and perform steps such as finding the target fire points whose distances from the fire point positions of the fire point data to be clustered are less than or equal to the preset neighborhood radius and subsequent steps on the fire point data to be clustered until the number of fire point data to be clustered in the target fire point monitoring data is 0, so as to obtain multiple clustering objects of the target fire point monitoring data.

[0049] Optionally, the above analysis module includes:

[0050] A transformation sub-module is used to perform a fast Fourier transform on the time series of each clustering object to obtain the power spectral density distribution of the clustering object.

[0051] Optionally, the above recognition module includes:

[0052] An extraction sub-module is used to extract the maximum power spectral density in the power spectral density distribution of each clustering object;

[0053] A first determination sub-module is used to determine that the fire point type of the clustering object is a real fire point when the maximum power spectral density of the clustering object is greater than the preset density threshold;

[0054] A second determination sub-module is used to determine that the fire point type of the clustering object is a false fire point when the maximum power spectral density of the clustering object is less than or equal to the preset density threshold.

[0055] Optionally, the above determination module includes:

[0056] A third determination sub-module is used to determine the map position of the fire point position of the fire point data in the target clustering object in the preset non-fire point map, and the preset non-fire point map includes multiple non-fire point positions;

[0057] A recognition sub-module is used to recognize the target positions that coincide with the non-fire point positions in the preset non-fire point map in the map position;

[0058] A calculation sub-module is used to calculate the ratio between the number of target positions and the total number of map positions corresponding to the fire point positions in the target clustering object to obtain the recognition accuracy rate of false fire points in the target fire point monitoring data;

[0059] A fourth determination sub-module is used to determine the fire point data in the target clustering object as the false fire point data of the target area within the preset historical duration when the recognition accuracy rate is greater than the preset accuracy rate threshold;

[0060] An adjustment sub-module is used to adjust the clustering parameters of the preset clustering method and re-execute the steps such as spatial clustering of multiple fire point data in the target fire point monitoring data based on the preset clustering method and subsequent steps when the recognition accuracy rate is less than or equal to the preset accuracy rate threshold.

[0061] The third aspect of the present disclosure provides a computer device, including a memory and a processor. Among them, a computer program is stored in the memory. When the computer program is executed by the processor, the method for identifying false fire point data in the first aspect above can be implemented.

[0062] The fourth aspect of the present disclosure provides a computer-readable storage medium. A computer program is stored in the storage medium. When the computer program is executed by the processor, the method for identifying false fire point data in the first aspect above can be implemented.

[0063] The technical solution provided by the present disclosure has the following advantages compared with the prior art:

[0064] The present disclosure obtains target fire point monitoring data of a target area within a preset historical duration; performs spatial clustering on multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple clustering objects of the target fire point monitoring data; performs time-frequency spectrum analysis on each clustering object to obtain the power spectral density distribution of each clustering object; for each clustering object, based on the power spectral density distribution of the clustering object, identifies the fire point type of the clustering object, and determines the clustering object with the fire point type of false fire point as the target clustering object; determines the fire point data in the target clustering object as the false fire point data of the target area within the preset historical duration. The present disclosure can effectively utilize the spatial distribution law and time-frequency spectrum characteristics of historical fire point data, quickly identify false fire point data in fire point monitoring data, and can improve the identification efficiency and accuracy of false fire point data. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0067] Figure 1 is a flowchart of a method for identifying false fire point data provided by an embodiment of the present disclosure;

[0068] Figure 2 is a flowchart of a method for identifying false fire point data provided by an embodiment of the present disclosure;

[0069] Figure 3 is a flowchart of a method for identifying false fire point data provided by an embodiment of the present disclosure;

[0070] Figure 4 It is a schematic structural diagram of an identification device for false fire point data provided by an embodiment of the present disclosure;

[0071] Figure 5 It is a schematic structural diagram of a computer device provided by an embodiment of the present disclosure. Specific embodiments

[0072] In order to more clearly understand the above-mentioned objects, features, and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0073] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0074] It should be understood that the various steps recorded in the method embodiments of the present disclosure may be executed in different orders and / or executed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0075] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, the element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0076] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless expressly specified otherwise in the context, it should be understood as "one or more".

[0077] The method for identifying false fire point data provided by the embodiments of the present disclosure can be executed by a computer device, which can be understood as any device with processing and computing capabilities, including but not limited to mobile terminals such as smart phones, laptops, personal digital assistants (PDAs), tablet computers (PADs), and fixed electronic devices such as digital TVs and desktop computers.

[0078] To better understand the inventive concept of the embodiments of the present disclosure, the technical solutions of the embodiments of the present disclosure will be described below in conjunction with exemplary embodiments.

[0079] Figure 1 is a flowchart of a method for identifying false fire point data provided by the embodiments of the present disclosure. The method can be executed by a computer device, which can be understood as any device with computing and processing capabilities, such as Figure 1 As shown, the method for identifying false fire point data provided in this embodiment includes the following steps:

[0080] Step 110: Obtain the target fire point monitoring data of the target area within a preset historical period.

[0081] In the embodiments of the present disclosure, the preset historical period can be set as needed. For example, the past year is not limited here.

[0082] The target fire point monitoring data can be understood as multiple fire point data obtained through monitoring.

[0083] The fire point data can include data such as the location data of the fire point (e.g., longitude and latitude of the fire point) and the discovery time of the fire point.

[0084] The computer device can obtain the target fire point monitoring data of the target area within a preset historical period from the fire information resource management system.

[0085] In some embodiments, the computer device can obtain the original fire point monitoring data of the target area within a preset historical period; based on a preset data cleaning method, perform data cleaning on the original fire point monitoring data to obtain the target fire point monitoring data of the target area within a preset historical period.

[0086] Among them, the preset data cleaning method can include at least one of removing abnormal data, removing duplicate data, and removing invalid data.

[0087] Step 120: Perform spatial clustering on the multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple clustering objects of the target fire point monitoring data.

[0088] In the embodiments of the present disclosure, the computer device may perform spatial clustering on multiple fire point data in the target fire point monitoring data based on a preset clustering method, that is, cluster the fire point data adjacent in space in the target fire point monitoring data into one category, and obtain multiple clustering objects of the target fire point monitoring data. Each clustering object includes at least one fire point data.

[0089] The preset clustering method can be set as needed and is not limited here. For example, the preset clustering method can be the Density-Based Spatial Clustering of Applications with Noise (DBSCAN), also known as the density-based clustering algorithm.

[0090] Step 130: Perform time-frequency analysis on each clustering object to obtain the power spectral density distribution of each clustering object.

[0091] In the embodiments of the present disclosure, the computer device may perform time-frequency analysis on each clustering object of the target fire point monitoring data to obtain the power spectral density distribution of each clustering object.

[0092] Time-frequency analysis is a signal processing technique used to comprehensively analyze and extract features of a signal from two dimensions of the time domain and the frequency domain. It reveals the energy distribution of the signal at different frequencies by converting the signal from the time domain to the frequency domain.

[0093] The Power Spectral Density (PSD) is a statistic used to describe how the power of a signal changes with frequency, mainly used to analyze the spectral characteristics of a signal and help understand the energy distribution of the signal. The power spectral density is defined as the power value of the signal at different frequencies and can be understood as the energy distribution of the signal in different frequency bands.

[0094] Specifically, for each clustering object, the computer device may perform a Fast Fourier Transform (FFT) on the time series of the clustering object to obtain the power spectral density distribution of the clustering object.

[0095] The time series of the clustering object can be understood as a sequence formed by arranging multiple fire point data in the clustering object in the order of their discovery time.

[0096] Step 140: For each clustering object, based on the power spectral density distribution of the clustering object, identify the fire point type of the clustering object, and determine the clustering object with the fire point type of false fire point as the target clustering object.

[0097] In the embodiments of the present disclosure, for each clustering object, based on the power spectral density distribution of the clustering object, the computer device can identify the fire point type of the clustering object, and determine the clustering object with the fire point type of false fire point as the target clustering object.

[0098] Among them, the fire point type can be a false fire point or a real fire point.

[0099] A false fire point can be understood as a fire point that is not really burning. For example, it can include traditional industrial heat source factories, scattered bare lands, photovoltaic power stations, etc.

[0100] A real fire point can be understood as a fire point that is really burning.

[0101] Step 150: Determine the fire point data in the target clustering object as the false fire point data of the target area within the preset historical duration.

[0102] Thus, the spatial distribution law and time-frequency spectrum characteristics of historical fire point data can be effectively utilized to quickly identify the false fire point data in the fire point monitoring data, and the identification efficiency and accuracy of the false fire point data can be improved.

[0103] Figure 2 It is a flowchart of a method for identifying false fire point data provided by the embodiments of the present disclosure. This method can be executed by a computer device, which can be understood as any device with computing functions and processing capabilities, such as Figure 2 As shown, the method for identifying false fire point data provided in this embodiment includes the following steps:

[0104] Step 210: Obtain the target fire point monitoring data of the target area within the preset historical duration.

[0105] Step 220: Based on the preset neighborhood radius and the preset minimum number of points included in the density clustering algorithm, through the density clustering algorithm, cluster the fire point data adjacent in space in the target fire point monitoring data into one category to obtain multiple clustering objects of the target fire point monitoring data.

[0106] The preset neighborhood radius can be set as needed. For example, 0.005, which is not limited here.

[0107] The preset minimum number of points included can be set as needed. For example, 10, which is not limited here.

[0108] Specifically, it can include steps 2201-2203:

[0109] Step 2201: For each fire point data to be clustered in the target fire point monitoring data, find the target fire point whose distance from the fire point position of the fire point data to be clustered is less than or equal to the preset neighborhood radius, and obtain the fire point data of the target fire point.

[0110] Step 2202: When the number of target fire points is greater than or equal to the preset minimum inclusion points, cluster the to-be-clustered fire point data and the target fire point data to obtain a clustering object, and determine the fire point data in the clustering object as the to-be-clustered fire point data that has been processed.

[0111] Step 2203: Determine the fire point data outside the clustering object as the to-be-clustered fire point data, and execute the content of Steps 2201 - 2202 for the to-be-clustered fire point data until the number of to-be-clustered fire point data in the target fire point monitoring data is 0, to obtain multiple clustering objects of the target fire point monitoring data.

[0112] Step 230: Perform time-frequency spectrum analysis on each clustering object to obtain the power spectral density distribution of each clustering object.

[0113] Step 240: For each clustering object, extract the maximum power spectral density in the power spectral density distribution of the clustering object.

[0114] In the embodiments of the present disclosure, the power spectral density distribution of each clustering object includes multiple power spectral densities.

[0115] For each clustering object, the computer device can extract the maximum power spectral density in the power spectral density distribution of the clustering object.

[0116] Step 250: When the maximum power spectral density of the clustering object is greater than the preset density threshold, determine that the fire point type of the clustering object is a real fire point.

[0117] The preset density threshold can be set as needed and is not limited here.

[0118] Step 260: When the maximum power spectral density of the clustering object is less than or equal to the preset density threshold, determine that the fire point type of the clustering object is a false fire point, and determine the clustering object with the fire point type of false fire point as the target clustering object.

[0119] Step 270: Determine the fire point data in the target clustering object as the false fire point data in the target area within the preset historical duration.

[0120] Thus, the spatial distribution law and time-frequency spectrum characteristics of historical fire point data can be effectively utilized, and false fire point data in the fire point monitoring data can be identified by the maximum power spectral density of the fire point data clustering object, which can improve the identification efficiency and accuracy of false fire point data.

[0121] Figure 3It is a flowchart of a method for identifying false fire point data provided by an embodiment of the present disclosure. This method can be executed by a computer device, which can be understood as any device with computing and processing capabilities, such as Figure 3 As shown, the method for identifying false fire point data provided in this embodiment includes the following steps:

[0122] Step 310: Obtain the target fire point monitoring data of the target area within a preset historical duration.

[0123] Step 320: Based on a preset clustering method, perform spatial clustering on multiple fire point data in the target fire point monitoring data to obtain multiple clustering objects of the target fire point monitoring data.

[0124] Step 330: Perform time-frequency spectrum analysis on each clustering object to obtain the power spectral density distribution of each clustering object.

[0125] Step 340: For each clustering object, based on the power spectral density distribution of the clustering object, identify the fire point type of the clustering object, and determine the clustering object with the fire point type of false fire point as the target clustering object.

[0126] Step 350: Determine the map position of the fire point location of the fire point data in the target clustering object in a preset non-fire point map, where the preset non-fire point map includes multiple non-fire point positions.

[0127] In the embodiment of the present disclosure, the preset non-fire point map includes the positions of multiple non-fire points.

[0128] The non-fire point position can be understood as a position that is not a real fire point. For example, the non-fire point position can be the position of a traditional industrial heat source factory, the position of scattered bare land, the position of a photovoltaic power station, etc. in the preset non-fire point map.

[0129] The computer device can determine the map position of the fire point location of the fire point data in the target clustering object in the preset non-fire point map.

[0130] Step 360: Identify the target positions that coincide with the non-fire point positions in the preset non-fire point map among the map positions.

[0131] In the embodiment of the present disclosure, the computer device can identify the target positions that coincide with the non-fire point positions in the preset non-fire point map among the map positions of the fire point location of the fire point data in the target clustering object.

[0132] Step 370: Calculate the ratio between the number of target positions and the total number of map positions corresponding to the fire point locations in the target clustering object to obtain the identification accuracy rate of false fire points in the target fire point monitoring data.

[0133] Specifically, calculate the ratio between the number of target positions and the total number of map positions corresponding to the fire point positions in the target clustering object, and then calculate the percentage of this ratio to obtain the recognition accuracy rate of false fire points in the target fire point monitoring data.

[0134] Step 380: When the recognition accuracy rate is greater than the preset accuracy rate threshold, determine the fire point data in the target clustering object as the false fire point data in the target area within the preset historical duration.

[0135] The preset accuracy rate threshold can be set as needed, for example, 90%, which is not limited here.

[0136] Step 390: When the recognition accuracy rate is less than or equal to the preset accuracy rate threshold, adjust the clustering parameters of the preset clustering method, and re-execute the steps of spatial clustering of multiple fire point data in the target fire point monitoring data based on the preset clustering method and subsequent steps.

[0137] Thus, the authenticity of the false fire point data in the initially obtained target fire point monitoring data can be verified. When the recognition accuracy rate of the false fire point data reaches a certain requirement, the false fire point data in the target area within the preset historical duration will be output, which can further improve the accuracy of false fire point data recognition.

[0138] In some embodiments of the present disclosure, after obtaining the false fire point data in the target area within the preset historical duration, the computer device can also organize the obtained false fire point data and its corresponding spectral features into a data set. The data set can include the following information:

[0139] Spatial information: the longitude and latitude coordinates of each fire point in the false fire point data, the vectorized information of the clustering boundary;

[0140] Time information: the time series of each fire point data in the clustering object of the false fire point data;

[0141] Spectral features: the power spectral density distribution of the clustering object of the false fire point data, its maximum power spectral density, and the frequency corresponding to the maximum power spectral density;

[0142] Label: false fire point label.

[0143] Figure 4 It is a schematic structural diagram of an identification device for false fire point data provided by an embodiment of the present disclosure. This device can be understood as the above computer device or some functional modules in the above computer device. As Figure 4 shown, the identification device 400 for false fire point data includes:

[0144] An acquisition module 410, configured to acquire target fire point monitoring data in a target area within a preset historical duration;

[0145] A clustering module 420, configured to perform spatial clustering on multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple clustering objects of the target fire point monitoring data;

[0146] An analysis module 430, configured to perform time-frequency spectrum analysis on each of the clustering objects to obtain the power spectral density distribution of each of the clustering objects;

[0147] An identification module 440, configured to, for each clustering object, identify the fire point type of the clustering object based on the power spectral density distribution of the clustering object, and determine the clustering object with the fire point type of false fire point as the target clustering object;

[0148] A determination module 450, configured to determine the fire point data in the target clustering object as the false fire point data of the target area within a preset historical duration.

[0149] Optionally, the above-mentioned acquisition module includes:

[0150] An acquisition sub-module, configured to acquire the original fire point monitoring data of the target area within a preset historical duration;

[0151] A data cleaning sub-module, configured to perform data cleaning on the original fire point monitoring data based on a preset data cleaning method to obtain the target fire point monitoring data of the target area within the preset historical duration, where the preset data cleaning method includes at least one of eliminating abnormal data, removing duplicate data, and eliminating invalid data.

[0152] Optionally, the above-mentioned preset clustering method includes a density clustering algorithm;

[0153] The above-mentioned clustering module includes:

[0154] A clustering sub-module, configured to cluster the fire point data adjacent in space in the target fire point monitoring data into one category based on a preset neighborhood radius and a preset minimum inclusion point number in the density clustering algorithm to obtain multiple clustering objects of the target fire point monitoring data.

[0155] Optionally, the above-mentioned clustering sub-module includes:

[0156] A search unit, configured to, for each fire point data to be clustered in the target fire point monitoring data, search for a target fire point whose distance from the fire point position of the fire point data to be clustered is less than or equal to a preset neighborhood radius, and acquire the fire point data of the target fire point;

[0157] A clustering unit, configured to cluster the fire point data to be clustered and the fire point data of the target fire points when the number of the target fire points is greater than or equal to a preset minimum inclusion point number, obtain a clustering object, and determine the fire point data in the clustering object as the fire point data to be clustered that has been processed;

[0158] An execution unit, configured to determine the fire point data outside the clustering object as the fire point data to be clustered, and execute the steps of finding the target fire points whose distances from the fire point positions of the fire point data to be clustered are less than or equal to a preset neighborhood radius and subsequent steps for the fire point data to be clustered until the number of the fire point data to be clustered in the target fire point monitoring data is 0, so as to obtain multiple clustering objects of the target fire point monitoring data.

[0159] Optionally, the above analysis module includes:

[0160] A transformation sub-module, configured to perform a fast Fourier transform on the time series of each clustering object to obtain the power spectral density distribution of the clustering object.

[0161] Optionally, the above recognition module includes:

[0162] An extraction sub-module, configured to extract the maximum power spectral density in the power spectral density distribution of each clustering object.

[0163] A first determination sub-module, configured to determine that the fire point type of the clustering object is a real fire point when the maximum power spectral density of the clustering object is greater than a preset density threshold.

[0164] A second determination sub-module, configured to determine that the fire point type of the clustering object is a false fire point when the maximum power spectral density of the clustering object is less than or equal to the preset density threshold.

[0165] Optionally, the above determination module includes:

[0166] A third determination sub-module, configured to determine the map position of the fire point position of the fire point data in the target clustering object in a preset non-fire point map, where the preset non-fire point map includes multiple non-fire point positions;

[0167] An identification sub-module, configured to identify a target position that coincides with a non-fire point position in the preset non-fire point map among the map positions;

[0168] A calculation sub-module, configured to calculate the ratio between the number of the target positions and the total number of the map positions corresponding to the fire point positions in the target clustering object, so as to obtain the identification accuracy rate of false fire points in the target fire point monitoring data.

[0169] A fourth determination sub-module, configured to determine the fire point data in the target clustering object as the false fire point data of the target area within a preset historical duration when the recognition accuracy rate is greater than a preset accuracy rate threshold;

[0170] An adjustment sub-module, configured to adjust the clustering parameters of the preset clustering method and re-execute the steps of spatially clustering multiple fire point data in the target fire point monitoring data based on the preset clustering method and subsequent steps when the recognition accuracy rate is less than or equal to the preset accuracy rate threshold.

[0171] The false fire point data recognition device provided by the embodiments of the present disclosure can implement the method of any of the above embodiments, and its execution manner and beneficial effects are similar, which will not be elaborated here.

[0172] The embodiments of the present disclosure further provide a computer device, which includes a processor and a memory. Among them, a computer program is stored in the memory, and when the computer program is executed by the processor, the method of any of the above embodiments can be implemented, and its execution manner and beneficial effects are similar, which will not be elaborated here.

[0173] Figure 5 is a schematic structural diagram of a computer device provided by the embodiments of the present disclosure. As Figure 5 shown, the computer device 500 may include a processor 510 and a memory 520. Among them, a computer program 521 is stored in the memory 520, and when the computer program 521 is executed by the processor 510, the method provided by any of the above embodiments can be implemented, and its execution manner and beneficial effects are similar, which will not be elaborated here.

[0174] Of course, for simplicity, Figure 5 only some of the components related to the present invention in the computer device 500 are shown, and components such as a bus, an input / output interface, an input device, and an output device are omitted. In addition, according to specific application scenarios, the computer device 500 may further include any other appropriate components.

[0175] The embodiments of the present disclosure provide a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method of any of the above embodiments can be implemented, and its execution manner and beneficial effects are similar, which will not be elaborated here.

[0176] The above computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, a system, device, or component of electricity, magnetism, optics, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of the readable storage medium (an exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0177] The above computer program may be written in any combination of one or more programming languages to write program code for performing the operations of the embodiments of the present disclosure. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer device, partially on the user device, executed as an independent software package, partially on the user's computer device and partially on a remote computer device, or entirely on a remote computer device or server.

[0178] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0179] In addition, although the operations are depicted in a specific order, this should not be construed as requiring that the operations be performed in the specific order shown or in a sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0180] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying false fire point data, characterized in that: include: Obtain the target fire point monitoring data of the target area within a preset historical period; Performing spatial clustering on the multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple clustering objects of the target fire point monitoring data; Performing time spectrum analysis on each of the cluster objects to obtain a power spectrum density distribution of each of the cluster objects; For each of the cluster objects, based on the power spectrum density distribution of the cluster object, the fire point type of the cluster object is identified, and the cluster object whose fire point type is a false fire point is determined as a target cluster object; The fire point data in the target cluster object is determined as the false fire point data of the target area within a preset historical time period.

2. The method according to claim 1, characterized in that The step of obtaining target fire point monitoring data of a target area within a preset historical time period includes: Obtain the original fire point monitoring data of the target area within a preset historical period; Based on a preset data cleaning method, the original fire point monitoring data is cleaned to obtain the target fire point monitoring data of the target area within the preset historical time period, and the preset data cleaning method includes at least one of eliminating abnormal data, removing duplicate data, and eliminating invalid data.

3. The method according to claim 1, characterized in that The preset clustering method includes a density clustering algorithm; The spatially clustering the multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple cluster objects of the target fire point monitoring data includes: Based on the preset neighborhood radius and the preset minimum number of included points in the density clustering algorithm, the spatially adjacent fire point data in the target fire point monitoring data are clustered into one category through the density clustering algorithm to obtain multiple clustering objects of the target fire point monitoring data.

4. The method according to claim 3, characterized in that The preset neighborhood radius and the preset minimum number of included points in the density clustering algorithm are used to cluster the spatially adjacent fire point data in the target fire point monitoring data into one category through the density clustering algorithm to obtain multiple clustering objects of the target fire point monitoring data, including: For each fire point data to be clustered in the target fire point monitoring data, searching for a target fire point whose distance from the fire point position of the fire point data to be clustered is less than or equal to a preset neighborhood radius, and acquiring the fire point data of the target fire point; When the number of the target fire points is greater than or equal to the preset minimum number of included points, clustering the fire point data to be clustered and the fire point data of the target fire points to obtain a clustering object, and determining the fire point data in the clustering object as the fire point data to be clustered; The fire point data outside the clustering objects are determined as the fire point data to be clustered, and the steps of searching for target fire points whose distance from the fire point positions of the fire point data to be clustered is less than or equal to the preset neighborhood radius and subsequent steps are performed on the fire point data to be clustered, until the number of fire point data to be clustered in the target fire point monitoring data is 0, thereby obtaining multiple clustering objects of the target fire point monitoring data.

5. The method according to claim 1, characterized in that The performing time spectrum analysis on each of the cluster objects to obtain the power spectrum density distribution of each of the cluster objects includes: For each of the cluster objects, a fast Fourier transform is performed on the time series of the cluster object to obtain a power spectrum density distribution of the cluster object.

6. The method according to claim 1, characterized in that The step of identifying the fire point type of each cluster object based on the power spectrum density distribution of the cluster object, and determining the cluster object whose fire point type is a false fire point as a target cluster object includes: For each of the cluster objects, extracting the maximum power spectrum density in the power spectrum density distribution of the cluster object; When the maximum power spectrum density of the cluster object is greater than a preset density threshold, determining that the fire point type of the cluster object is a real fire point; When the maximum power spectrum density of the cluster object is less than or equal to a preset density threshold, it is determined that the fire point type of the cluster object is a false fire point.

7. The method according to claim 1, characterized in that The step of determining the fire point data in the target cluster object as false fire point data of the target area within a preset historical time period includes: Determine a map position of a fire point location of the fire point data in the target cluster object in a preset non-fire point map, wherein the preset non-fire point map includes a plurality of non-fire point locations; Identifying a target position in the map position that coincides with a non-fire point position in the preset non-fire point map; Calculating the ratio between the number of the target positions and the total number of map positions corresponding to the fire point positions in the target cluster object, and obtaining the recognition accuracy rate of the false fire points in the target fire point monitoring data; When the recognition accuracy is greater than a preset accuracy threshold, the fire point data in the target cluster object is determined as false fire point data of the target area within a preset historical time length; When the recognition accuracy is less than or equal to a preset accuracy threshold, the clustering parameters of the preset clustering method are adjusted, and the steps of spatially clustering the multiple fire point data in the target fire point monitoring data based on the preset clustering method and subsequent steps are re-executed.

8. A device for identifying false fire point data, characterized in that: include: An acquisition module is used to acquire the target fire point monitoring data of the target area within a preset historical time period; A clustering module, used for spatially clustering the multiple fire point data in the target fire point monitoring data based on a preset clustering method to obtain multiple clustering objects of the target fire point monitoring data; An analysis module, used for performing time spectrum analysis on each of the cluster objects to obtain a power spectrum density distribution of each of the cluster objects; an identification module, for identifying, for each of the cluster objects, the fire point type of the cluster object based on the power spectrum density distribution of the cluster object, and determining the cluster object whose fire point type is a false fire point as a target cluster object; A determination module is used to determine the fire point data in the target cluster object as false fire point data in the target area within a preset historical time period.

9. The device according to claim 8, characterized in that The acquisition module comprises: The acquisition submodule is used to obtain the original fire point monitoring data of the target area within a preset historical time period; The data cleaning submodule is used to clean the original fire point monitoring data based on a preset data cleaning method to obtain the target fire point monitoring data of the target area within the preset historical time period. The preset data cleaning method includes at least one of eliminating abnormal data, removing duplicate data, and eliminating invalid data.

10. The device according to claim 8, characterized in that The preset clustering method includes a density clustering algorithm; The clustering module comprises: The clustering submodule is used to cluster the spatially adjacent fire point data in the target fire point monitoring data into one category based on the preset neighborhood radius and the preset minimum number of included points in the density clustering algorithm, and obtain multiple clustering objects of the target fire point monitoring data.

11. The device according to claim 10, characterized in that The clustering submodule includes: A search unit, for searching, for each fire point data to be clustered in the target fire point monitoring data, a target fire point whose distance from the fire point position of the fire point data to be clustered is less than or equal to a preset neighborhood radius, and acquiring the fire point data of the target fire point; A clustering unit, for clustering the fire point data to be clustered and the fire point data of the target fire points to obtain a clustering object when the number of the target fire points is greater than or equal to a preset minimum number of included points, and determining the fire point data in the clustering object as the fire point data to be clustered; An execution unit is used to determine the fire point data outside the clustering objects as the fire point data to be clustered, and execute the steps of searching for target fire points whose distance from the fire point positions of the fire point data to be clustered is less than or equal to a preset neighborhood radius and subsequent steps on the fire point data to be clustered, until the number of fire point data to be clustered in the target fire point monitoring data is 0, thereby obtaining multiple clustering objects of the target fire point monitoring data.

12. The device according to claim 8, characterized in that The analysis module comprises: The transformation submodule is used to perform a fast Fourier transform on the time series of each cluster object to obtain the power spectrum density distribution of the cluster object.

13. The device according to claim 8, characterized in that The identification module comprises: An extraction submodule, configured to extract, for each of the cluster objects, a maximum power spectrum density in the power spectrum density distribution of the cluster object; A first determination submodule, configured to determine that the fire point type of the cluster object is a real fire point when the maximum power spectrum density of the cluster object is greater than a preset density threshold; The second determination submodule is used to determine that the fire point type of the cluster object is a false fire point when the maximum power spectrum density of the cluster object is less than or equal to a preset density threshold.

14. The device according to claim 8, characterized in that The determination module comprises: A third determination submodule is used to determine the map position of the fire point position of the fire point data in the target cluster object in a preset non-fire point map, wherein the preset non-fire point map includes a plurality of non-fire point positions; An identification submodule, used to identify a target position in the map position that coincides with a non-fire point position in the preset non-fire point map; A calculation submodule, used to calculate the ratio between the number of the target positions and the total number of map positions corresponding to the fire point positions in the target cluster object, and obtain the recognition accuracy rate of false fire points in the target fire point monitoring data; A fourth determination submodule is used to determine the fire point data in the target cluster object as false fire point data of the target area within a preset historical time period when the recognition accuracy is greater than a preset accuracy threshold; The adjustment submodule is used to adjust the clustering parameters of the preset clustering method when the recognition accuracy is less than or equal to the preset accuracy threshold, and re-execute the spatial clustering of multiple fire point data in the target fire point monitoring data based on the preset clustering method and subsequent steps.

15. A computer device, characterized in that: include: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method for identifying false fire point data as described in any one of claims 1-7 is implemented.

16. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for identifying false fire point data according to any one of claims 1 to 7 is implemented.

Images