A forest and grassland fire factor monitoring method, monitoring system, medium and product

Abstract

The present application relates to the technical field of forest and grassland fire factor monitoring, and in particular to a forest and grassland fire factor monitoring method, monitoring system, medium and product, the method comprising obtaining sensor monitoring data corresponding to the monitored area, and performing data similarity aggregation on the sensor monitoring data to obtain at least one aggregated feature information; performing word segmentation processing on each aggregated feature information, and determining the aggregated keyword dictionary corresponding to each aggregated feature information based on the word segmentation processing result; determining the corresponding supplementary information based on each aggregated keyword dictionary and historical monitoring data; determining the corresponding aggregated feature value based on each aggregated feature information and the supplementary information, and determining the corresponding fire factor characteristic map based on each aggregated feature value; determining the fire factor index based on the fire factor characteristic map, and generating hidden danger prompt information when the fire factor index is higher than the preset index threshold. The present application facilitates improving the accuracy of monitoring and analyzing forest and grassland fire factors.

Description

Technical Field

[0001] The present application relates to the technical field of forest and grassland fire factor monitoring, and in particular to a forest and grassland fire factor monitoring method, monitoring system, medium and product. Background Art

[0002] Since a large amount of combustibles such as dead branches and leaves have accumulated in forests or grasslands, once these combustibles encounter open flames, the fire will spread rapidly, especially in hot and dry seasons, the speed of fire spread will become faster, increasing the difficulty of rescue. Fire is extremely destructive to forest or grassland ecosystems. It will not only burn vegetation and destroy biological habitats, but may also cause water and soil loss and soil erosion. Therefore, actively monitoring forest and grassland fire factors is conducive to timely discovery of some hidden dangers or abnormal conditions in forests or grasslands, so as to provide important information for timely firefighting.

[0003] In the relevant technology, it is generally possible to determine whether there are fire hazards in the forest or grassland by analyzing the fire monitoring data collected by sensor equipment, and to generate early warning signals in time after the fire hazard is discovered. However, since the relevant monitoring equipment may have problems such as low sensitivity and poor anti-interference ability, when the fire factor monitoring and analysis of Senlian grassland is carried out only based on the data collected by the sensor, the accuracy of the analysis results may be low, which may affect the accuracy of the fire hazard warning. Summary of the invention

[0004] In order to improve the accuracy of monitoring and analyzing forest and grassland fire factors, thereby improving the accuracy of fire hazard warnings, the present application provides a forest and grassland fire factor monitoring method, monitoring system, medium and product.

[0005] In the first aspect, the present application provides a method for monitoring forest and grassland fire factors, which adopts the following technical solution:

[0006] A method for monitoring forest and grassland fire factors, comprising:

[0007] Acquire sensor monitoring data corresponding to the area to be monitored, and perform data similarity aggregation on the sensor monitoring data to obtain at least one aggregated feature information corresponding to the sensor monitoring data, wherein the sensor monitoring data includes rainfall, temperature, humidity, wind speed, wind direction, and moisture content of litter;

[0008] Performing word segmentation processing on each aggregated feature information, and determining an aggregated keyword dictionary corresponding to each aggregated feature information based on the word segmentation processing result corresponding to each aggregated feature information;

[0009] Acquire historical monitoring data, and determine supplementary information corresponding to each aggregate feature information based on each aggregate keyword dictionary and the historical monitoring data;

[0010] Determine, according to each aggregated feature information and the supplementary information corresponding to each aggregated feature information, an aggregated feature value corresponding to each aggregated feature information, and determine, based on each aggregated feature value, a fire factor feature graph corresponding to the sensor monitoring data;

[0011] A corresponding fire factor index is determined based on the fire factor characteristic diagram, and when the fire factor index is higher than a preset index threshold, hidden danger prompt information is generated based on the sensor monitoring data.

[0012] By adopting the above technical scheme, the redundancy of sensor monitoring data is reduced by performing data similarity aggregation on sensor monitoring data, thereby improving the effectiveness of sensor monitoring data. An aggregated keyword dictionary is obtained after word segmentation and keyword extraction on aggregated feature information. Based on the aggregated keyword dictionary, corresponding supplementary information is determined from historical monitoring data to supplement monitoring and analysis information that may be omitted by the aggregated feature information, thereby improving the comprehensiveness of the monitoring and analysis process of fire factors, and then facilitating the improvement of the accuracy of monitoring and analysis of forest and grassland fire factors. Finally, the fire risk in the monitored area is quantified by the fire factor index, so as to timely discover fire hazards in forests or grasslands, thereby facilitating the improvement of the accuracy of fire hazard warnings.

[0013] In a possible implementation, the aggregate feature information is segmented, and based on the segmentation result corresponding to the aggregate feature information, an aggregate keyword dictionary corresponding to the aggregate feature vector is determined, including:

[0014] Performing word segmentation processing on the aggregated feature information based on a preset word segmentation algorithm to obtain a word segmentation text;

[0015] Identify at least one keyword contained in the segmented text, and determine a weight value of each keyword based on the frequency and position of occurrence of each keyword in the aggregated feature information;

[0016] The aggregate keyword dictionary is determined based on each keyword and a weight value corresponding to each keyword.

[0017] By adopting the above technical solution, the aggregated feature information is segmented through a preset segmentation algorithm, so that longer text information can be decomposed into smaller, meaningful segmented texts, so as to facilitate subsequent keyword recognition and weight calculation, thereby improving the accuracy and processing efficiency of the information extraction process. In addition, the aggregated keyword dictionary is determined based on the keywords and the weight values ​​corresponding to the keywords, so that when the supplementary information is subsequently determined based on the aggregated keyword dictionary, the effectiveness of the supplementary information can be improved.

[0018] In one possible implementation, the method further includes:

[0019] If the hidden danger elimination instruction is not received within the preset time period, the target simulation model corresponding to the monitored area is obtained, and a simulated hidden danger image is determined based on the target simulation model and each aggregated feature information and the supplementary information corresponding to each aggregated feature information;

[0020] Identify an impact area from the simulated hidden danger image, and determine a first impact value corresponding to the impact area based on an impact area of ​​the impact area and a preset first impact value mapping relationship, wherein the preset first impact value mapping relationship is a corresponding relationship between the impact area and the first impact value;

[0021] Determine the regional value grade of the affected area according to the simulated hidden danger image, and determine the second impact value corresponding to the regional value grade based on the regional value grade and a preset second impact value mapping relationship, wherein the preset second impact value mapping relationship is a corresponding relationship between the regional value grade and the second impact value;

[0022] A target warning level of the hidden danger prompt information is determined based on the first impact value and the second impact value, a target feedback method is determined based on the target warning level, and the hidden danger prompt information is fed back based on the target feedback method.

[0023] By adopting the above technical solution, when it is detected that hidden dangers are not eliminated in time, the affected area and regional value of the affected area are analyzed, so as to predict and evaluate the risks that the detected area may face in the future, and adjust the warning level based on the possible risks, so as to ensure that important hidden dangers receive timely and efficient responses while avoiding excessive reactions to unimportant hidden dangers, so as to improve the efficiency and pertinence of emergency response.

[0024] In a possible implementation manner, determining the regional value level of the affected area according to the simulated hidden danger image includes:

[0025] Determine biological characteristics and biological species of the affected area based on the simulated hidden danger image, and determine the ecological value corresponding to the affected area based on the biological characteristics and biological species;

[0026] Determine the area type of the impact area based on the biological features and biological species contained in the impact area, and determine the economic value based on the area type, the area types include agriculture, forestry, and tourism, and different area types correspond to different economic values;

[0027] Determine the number of associated roads corresponding to the affected area based on the simulated hidden danger image, and determine the corresponding traffic value based on the number of associated roads, wherein the associated roads are roads passing through the affected area;

[0028] The regional value level of the impact area is determined based on the ecological value, the economic value, and the traffic value.

[0029] By adopting the above technical solution, a multi-dimensional assessment of the regional value of the affected area is conducted from aspects such as ecological value, economic value and traffic value, which makes it easier to improve the accuracy of determining the regional value level of the affected area, thereby facilitating the improvement of the accuracy and effectiveness of early warning feedback.

[0030] In a possible implementation manner, determining the corresponding fire factor index based on the fire factor vector graph includes:

[0031] Identify the feature point coordinates corresponding to each aggregated feature information in the fire factor vector graph;

[0032] Determine the characteristic region corresponding to the fire factor vector diagram and the area value corresponding to the characteristic region based on the coordinates of each characteristic point, wherein the characteristic region is the region formed by connecting all characteristic points;

[0033] The corresponding fire factor index is determined based on the regional area value and the preset index mapping relationship, and the preset index mapping relationship is the corresponding relationship between the regional area value and the fire factor index.

[0034] By adopting the above technical solution, by converting the aggregated feature information into feature point coordinates, and then determining the feature area corresponding to the aggregated feature information based on the feature point coordinates, it is easy to quantify the aggregated feature information. Through quantification, it is easy to intuitively view the fire risk reflected by the aggregated feature information, which helps to achieve rapid classification and response of fire situations.

[0035] In one possible implementation, the method further includes:

[0036] When a fire factor index of concern is detected, the stage monitoring data corresponding to the fire factor index of concern is obtained, wherein the fire factor index of concern is a fire factor index within a preset range of the fire factor index, and the stage monitoring data is the sensor monitoring data corresponding to the preset period of concern;

[0037] Determining an abnormal change monitoring feature from the stage monitoring data, wherein a corresponding change rate of the abnormal change monitoring feature within the preset time period of interest is higher than a corresponding preset standard change rate;

[0038] Generate preventive reminder information based on the abnormal change monitoring characteristics.

[0039] By adopting the above technical scheme, when there is no fire risk, the stage monitoring data corresponding to the fire factor index is analyzed to determine the monitoring features that may be abnormal in the stage monitoring data, and then the prevention prompt information generated based on the abnormal change monitoring features is convenient for timely sending prompt information to relevant staff to remind them to pay attention to the abnormal change monitoring features and take measures to eliminate the abnormalities in time. Through this timely prevention and intervention of individual monitoring features, it is helpful to control the fire risk in the initial stage, thereby reducing the probability of fire risk occurrence.

[0040] In a second aspect, the present application provides a monitoring system, which adopts the following technical solution:

[0041] A monitoring system, comprising:

[0042] at least one processor;

[0043] Memory;

[0044] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned forest and grassland fire factor monitoring method.

[0045] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0046] A computer-readable storage medium, comprising: storing a computer program that can be loaded by a processor and execute the above-mentioned forest and grassland fire factor monitoring method.

[0047] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution:

[0048] A computer program product includes a computer program, which implements the above-mentioned forest and grassland fire factor monitoring method when executed by a processor.

[0049] In summary, the present application includes at least one of the following beneficial technical effects:

[0050] By performing data similarity aggregation on sensor monitoring data, it is convenient to reduce the redundancy of sensor monitoring data, thereby improving the effectiveness of sensor monitoring data. By performing word segmentation and keyword extraction on the aggregated feature information, an aggregated keyword dictionary is obtained, and then the corresponding supplementary information is determined from the historical monitoring data based on the aggregated keyword dictionary, so as to supplement the monitoring and analysis information that may be missed by the aggregated feature information, thereby improving the comprehensiveness of the monitoring and analysis process of fire factors, and then facilitating the improvement of the accuracy of monitoring and analysis of forest and grassland fire factors. Finally, the fire risk in the monitored area is quantified through the fire factor index, so as to timely discover the fire hazards in the forest or grassland, thereby facilitating the improvement of the accuracy of fire hazard warning.

[0051] By analyzing the affected area and regional value of the affected area when hidden dangers are detected and not eliminated in time, it is possible to predict and evaluate the risks that the detected area may face in the future, and adjust the warning level based on the possible risks, so as to ensure that important hidden dangers receive timely and efficient response while avoiding overreaction to unimportant hidden dangers, so as to improve the efficiency and pertinence of emergency response. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart of a forest and grassland fire factor monitoring method in an embodiment of the present application;

[0053] Figure 2 It is a flowchart of a method for determining target feedback in an embodiment of the present application;

[0054] Figure 3 It is a structural schematic diagram of a monitoring system in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following is combined with Figures 1 to 3 This application is described in further detail.

[0056] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0059] Specifically, the embodiment of the present application provides a forest and grassland fire factor monitoring method, which is executed by a monitoring system, and the monitoring system can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this.

[0060] refer to Figure 1 , Figure 1 : is a flow chart of a forest and grassland fire factor monitoring method in an embodiment of the present application, the method includes steps S110-S150, wherein:

[0061] Step S110: Obtain sensor monitoring data corresponding to the monitored area, and perform data similarity aggregation on the sensor monitoring data to obtain at least one aggregated feature information corresponding to the sensor monitoring data, wherein the sensor monitoring data includes rainfall, temperature, humidity, wind speed, wind direction, and moisture content of litter.

[0062] Specifically, the area to be monitored is an area where fire factor monitoring is required, which may be a forest, grassland, woodland, etc. The specific scene is not specifically limited in the embodiment of the present application. The fire factors corresponding to areas such as forests or grasslands include weather factors, vegetation factors, and terrain factors, etc. The sensor monitoring data corresponding to different fire factors may be different or the same. For example, when determining the impact of weather factors on fire hazards, it is necessary to analyze data such as temperature, humidity, wind speed, and rainfall. When determining the impact of vegetation factors on fire hazards, it is necessary to analyze vegetation type, vegetation density, rainfall, and moisture content of litter, etc.

[0063] The sensor monitoring data includes but is not limited to rainfall, temperature, humidity, wind speed, wind direction and moisture content of litter, etc., which can be collected by the sensor monitoring equipment installed in the monitored area and uploaded to the monitoring system. The sensor monitoring equipment can include surface humidity sensors, temperature sensors, wind direction sensors, wind speed sensors, rainfall sensors, etc. After the monitored sensors complete the collection, the sensor monitoring data can be uploaded to the monitoring system through the Beidou fusion gateway device. The Beidou fusion gateway device is used to connect the Beidou system's positioning, navigation, timing and short message communication data with the ground monitoring system. The specific transmission method is not specifically limited in the embodiment of the present application, as long as the collected sensor monitoring data can be uploaded to the monitoring system.

[0064] Since multiple measurements are usually performed when collecting sensor monitoring data in order to improve the accuracy and reliability of the monitoring data, the sensor monitoring data generally contains a large number of observations, and these observations may be highly redundant. By performing data similarity aggregation on the sensor monitoring data, relatively similar data points can be merged, thereby reducing the redundancy of the sensor monitoring data. In addition, by performing similarity aggregation on the sensor monitoring data, it is helpful to identify environmental conditions or development trends from the sensor monitoring data, thereby facilitating the improvement of the accuracy of assessing fire hazards based on sensor monitoring data.

[0065] When performing data similarity aggregation on sensor monitoring data, sensor monitoring data of different dimensions can be first summoned into a unified dimension. For example, physical quantities such as temperature and humidity can be converted into standard units or relative values, and then a preset clustering algorithm is used to cluster the normalized sensor monitoring data, and the sensor monitoring data is divided into multiple classes or clusters. The monitoring data in the same class or cluster has a high similarity. Among them, the preset clustering algorithm can include K-means, DBSCAN, and hierarchical clustering, etc. The specific clustering method is not specifically limited in the embodiment of the present application and can be set by relevant technical personnel. Finally, aggregation is performed based on all classes or clusters to obtain aggregated feature information. Since different data classes or clusters are a set of similar data, the data similarity aggregation process refers to summarizing, analyzing or processing these data classes or clusters in order to identify environmental status or trends therefrom. Therefore, the data contained in the aggregated feature information may come from one class or cluster, or from multiple classes or clusters, and the amount of aggregated feature information is not specifically limited in the embodiment of the present application.

[0066] Step S120: performing word segmentation processing on each piece of aggregated feature information, and determining an aggregated keyword dictionary corresponding to each piece of aggregated feature information based on the word segmentation processing result corresponding to each piece of aggregated feature information.

[0067] Specifically, the aggregated feature information is split into smaller units through word segmentation processing, which facilitates the analysis and understanding of the aggregated feature information, thereby improving the accuracy of information retrieval using the aggregated feature information. Each piece of aggregated feature information can be subjected to word segmentation processing through a word segmentation tool or algorithm, and the specific word segmentation tool or algorithm is not specifically limited in the embodiments of the present application. In the fields of text processing, natural language processing, search engine optimization, or information retrieval, the aggregated keyword dictionary plays an important role. Based on the word segmentation processing results, the corresponding aggregated keyword dictionary is determined to facilitate the intuitive analysis of the keywords in the aggregated feature information and the relevant information of each keyword.

[0068] Further, for any piece of aggregated feature information, word segmentation processing is performed on the aggregated feature information, and based on the word segmentation processing results corresponding to the aggregated feature information, the aggregated keyword dictionary corresponding to the aggregated feature vector is determined, which specifically may include:

[0069] Word segmentation processing is performed on the aggregated feature information based on a preset word segmentation algorithm to obtain a segmented text; at least one keyword included in the segmented text is identified, and based on the occurrence frequency and occurrence position of each keyword in the aggregated feature information, the weight value of each keyword is determined; the aggregated keyword dictionary is determined based on each keyword and the weight value corresponding to each keyword.

[0070] Specifically, the preset word segmentation algorithm can be the jieba library algorithm. Word segmentation processing is performed on the aggregated feature information based on the jieba library algorithm to split the aggregated feature information into multiple segmented texts. During the splitting process, the word segmentation mode can also be selected according to actual needs. The word segmentation mode includes the full mode, the accurate mode, and the search engine mode. The specific word segmentation mode is not specifically limited in the embodiments of the present application. The recall rates corresponding to different word segmentation modes are different. For example, the search engine mode performs secondary segmentation on the long-word text on the basis of the accurate mode. Before identifying the keywords included in the segmented text, a stop word removal operation can be performed on the segmented text. Among them, words with high usage frequencies but low effectiveness, such as "de" (of) and "shi" (is), in the segmented text can be removed to improve the effectiveness of the segmented text.

[0071] After the stop words are removed, a preset keyword extraction algorithm can be used to extract keywords from each segmented text, where the preset keyword extraction algorithm can be Word2Vec, TextRank, LDA, etc., where Word2Vec is a method of expressing vocabulary as vectors using neural networks; TextRank is a graph-based sorting algorithm used for text processing, especially in keyword extraction and abstract generation; LDA is a topic model algorithm that can be used to identify topics in large-scale text data. The specific preset keyword extraction algorithm is not specifically limited in the embodiments of this application. Based on the above method, at least one keyword corresponding to each segmented text can be obtained.

[0072] After determining the keywords corresponding to all the segmented texts, the frequency and position of each keyword in the corresponding segmented text can be identified. Different frequencies and positions correspond to different importance, that is, the corresponding weight values ​​are different. The higher the frequency, the higher the corresponding weight value. The more concentrated the position is in the preset key position, the higher the corresponding weight value. The preset key position can be the beginning of a paragraph, the beginning of a sentence, the title, etc. The specific preset key position is not specifically limited in the embodiment of the present application, and can be determined by relevant staff according to historical experimental data and uploaded to the monitoring system. In order to improve the standardization of determining the weight value corresponding to the keyword, the corresponding weight value can be determined based on the preset weight value mapping relationship after the frequency and position of the keyword in the corresponding segmented text are determined. The preset weight mapping relationship is the corresponding relationship between the combination of the frequency and position of the occurrence and the weight value. The specific content of the preset weight mapping relationship is not specifically limited in the embodiment of the present application, and can be determined by relevant staff according to historical experimental data and uploaded to the monitoring system. The aggregated keyword dictionary contains all the keywords corresponding to the aggregated feature information and the weight value of each keyword, and each keyword is sorted from high to low according to the corresponding weight value. According to the above method, the bureau and keyword dictionary corresponding to each aggregated feature information can be determined.

[0073] Step S130: Acquire historical monitoring data, and determine supplementary information corresponding to each aggregate feature information based on each aggregate keyword dictionary and the historical monitoring data.

[0074] Specifically, the historical monitoring data is the sensor collection data acquired within the historical time period. In order to improve the accuracy of determining the supplementary information based on the historical monitoring data, the historical sensor collection data is generally subjected to sedimentation preprocessing, and the historical monitoring data is obtained only after the island data or incomplete data contained in the historical sensor collection data is eliminated. The historical monitoring data is usually time-sensitive, that is, the historical monitoring data is usually updated after each preset time period, where the preset time period can be 30 days or 25 days. The specific duration is not specifically limited in the embodiments of the present application.

[0075] For any aggregate keyword dictionary, the corresponding related content is extracted from the historical monitoring data according to the arrangement order of each keyword in the aggregate keyword dictionary, and the related content corresponding to all aggregate feature information is integrated to obtain the supplementary information corresponding to the aggregate feature information. When determining the supplementary information corresponding to the aggregate feature information, the extraction is performed based on the aggregate keyword dictionary, which is convenient for improving the relevance between the supplementary information and the aggregate feature information, thereby facilitating improving the accuracy and quality of the supplementary information.

[0076] Step S140: Determine the aggregated feature value corresponding to each aggregated feature information according to each aggregated feature information and the supplementary information corresponding to each aggregated feature information, and determine the fire factor characteristic graph corresponding to the sensor monitoring data based on each aggregated feature value.

[0077] Specifically, the aggregated feature information is obtained after being collected by the current sensor monitoring equipment and can reflect the current environmental status. However, the effectiveness of the aggregated feature information often depends on the accuracy of the sensor monitoring equipment. Once the sensor monitoring equipment has an accuracy deviation, it is easy to cause the collected sensor monitoring data to be inaccurate. Therefore, in the embodiment of the present application, not only the sensor monitoring data is analyzed, but after the sensor monitoring data is aggregated for data similarity, the fire hazards faced by the monitored area are analyzed or predicted based on the sensor monitoring data and the supplementary information corresponding to the sensor monitoring data.

[0078] For any aggregated feature information, the aggregated feature information is integrated with the corresponding supplementary information to obtain multiple integrated data. The focus direction corresponding to each integrated data may be different. For example, the focus direction corresponding to integrated data a may be the impact of weather factors on fire hazards in the monitored area, and the focus direction corresponding to integrated data b may be the impact of biological factors on fire hazards in the monitored area. The aggregated feature value is a quantitative expression of the corresponding integrated data, which can be the fire hazard impact value determined after analyzing the integrated data. The higher the fire hazard impact value, the greater the threat posed by the current status of the fire factors contained in the corresponding aggregated feature information to the fire hazard.

[0079] When analyzing the integrated data, at least one observation feature contained in the integrated data can be identified. Since the data contained in the aggregated feature information may come from one class or cluster, or from multiple classes or clusters, and the integrated data is obtained by integrating the aggregated feature information and the corresponding supplementary information, the integrated data may contain at least one observation feature. For example, when the focus direction corresponding to the integrated data is weather factors, the observation features may be temperature, humidity, wind speed, light, and rainfall, wherein light may be the observation feature corresponding to the supplementary information. Since the aggregated feature information is normalized information, the corresponding aggregated feature value can be determined based on the preset observation weight and the observation value corresponding to each observation feature, wherein the specific preset observation weight is not specifically limited in the embodiment of the present application, and can be determined by relevant staff based on historical experimental data and uploaded to the monitoring system.

[0080] Based on the above method, the aggregated characteristic value corresponding to each aggregated characteristic information can be determined. Each aggregated characteristic value corresponds to a different fire factor. All aggregated characteristic values ​​and the corresponding fire factors are imported into a preset multidimensional coordinate system to obtain a fire factor characteristic diagram. Different coordinate axes correspond to different fire factors. When importing the aggregated characteristic values ​​and the corresponding fire factors, it is necessary to first determine the corresponding write coordinate axis, and then determine the characteristic coordinate value corresponding to each aggregated characteristic value based on the preset coordinate value conversion algorithm. Finally, the characteristic point of each fire factor is determined based on the write coordinate axis and the characteristic coordinate value, wherein the preset coordinate value conversion algorithm is used to convert the aggregated characteristic value into a coordinate value.

[0081] Step S150: Determine the corresponding fire factor index based on the fire factor characteristic diagram, and when the fire factor index is higher than a preset index threshold, generate hidden danger prompt information based on the sensor monitoring data.

[0082] Specifically, when the fire factor index is higher than the preset index threshold, it indicates that under the influence of all fire factors, the monitored area has fire hazards. At this time, it is necessary to generate hidden danger prompt information in time to prompt relevant staff to pay attention to or solve the hidden danger. Further, determining the corresponding fire factor index based on the fire factor vector diagram can specifically include:

[0083] Identify the coordinates of the feature points corresponding to each aggregated feature information in the fire factor vector map; determine the feature region corresponding to the fire factor vector map and the regional area value corresponding to the feature region based on the coordinates of each feature point, and the feature region is the region formed by connecting all feature points; determine the corresponding fire factor index based on the regional area value and the preset index mapping relationship, and the preset index mapping relationship is the correspondence between the regional area value and the fire factor index.

[0084] Specifically, all the characteristic points of each characteristic coordinate in the fire factor characteristic map are first connected to obtain a characteristic area, and then the area value of the characteristic area is calculated based on the characteristic point coordinates corresponding to each characteristic point. The specific calculation method is not specifically limited in the embodiment of the present application. Finally, the fire factor index corresponding to the area value is determined based on the preset index mapping relationship, wherein the preset index mapping relationship contains fire factor indices corresponding to different area values. The specific content of the preset index mapping relationship and the specific preset index threshold are not specifically limited in the embodiment of the present application, and can be determined by relevant staff based on historical experimental data and uploaded to the monitoring system.

[0085] For the embodiments of the present application, by performing data similarity aggregation on sensor monitoring data, it is convenient to reduce the redundancy of sensor monitoring data, thereby improving the effectiveness of sensor monitoring data, and obtaining an aggregated keyword dictionary after performing word segmentation processing, keyword extraction and other operations on the aggregated feature information, and then determining the corresponding supplementary information from the historical monitoring data based on the aggregated keyword dictionary, so as to supplement the monitoring and analysis information that may be missed by the aggregated feature information, thereby improving the comprehensiveness of the monitoring and analysis process of fire factors, and then facilitating the improvement of the accuracy of monitoring and analysis of forest and grassland fire factors. Finally, the fire risk in the monitored area is quantified by the fire factor index, so as to facilitate the timely discovery of fire hazards in forests or grasslands, thereby facilitating the improvement of the accuracy of fire hazard warnings.

[0086] Further, in order to improve the efficiency and pertinence of emergency response, the method provided in the embodiment of the present application further includes steps S1 to S4, such as Figure 2 As shown, where:

[0087] Step S1: If the hidden danger elimination instruction is not received within the preset time period, the target simulation model corresponding to the monitored area is obtained, and a simulated hidden danger image is determined based on the target simulation model and each aggregated feature information and the supplementary information corresponding to each aggregated feature information.

[0088] Specifically, the preset time period is a period of time after the hidden danger prompt information is generated. The duration corresponding to the preset time period can be 60 minutes or 80 minutes. The specific duration is not specifically limited in the embodiment of the present application and can be set by relevant technical personnel. If the relevant staff receives the hidden danger prompt information and solves the hidden danger situation, they can upload the hidden danger elimination instruction to the monitoring equipment through the terminal device they carry. Since the workload required to solve the hidden danger situation is large and the number of staff required is large, if the hidden danger elimination instruction is not received within the preset time period, it can be characterized that the hidden danger prompt information may be in a waiting state. At this time, in order to ensure that important hidden dangers are responded to in a timely and efficient manner, the changes in the monitored area in the future period of time can be simulated and predicted, and the simulation and prediction results can be intuitively viewed through the simulated hidden danger image.

[0089] The target simulation model corresponding to the area to be monitored can be uploaded to the monitoring system in advance by relevant staff. The target simulation model has an environment and ecosystem consistent with the area to be monitored. Therefore, when the target simulation model is driven based on the aggregated feature information and each aggregated feature information, the development of fire hazards that the monitored area may face in the future can be predicted.

[0090] Step S2: Identify the affected area from the simulated hidden danger image, and determine the first impact value corresponding to the affected area based on the impact area of ​​the affected area and the preset first impact value mapping relationship, where the preset first impact value mapping relationship is the corresponding relationship between the affected area and the first impact value.

[0091] Specifically, since the simulated hidden danger image is the development of fire hazards that the monitored area may face in the future, a fire may have already occurred in the simulated hidden danger image. The affected area is the area where the fire occurs. When identifying the affected area from the simulated hidden danger image, it can be identified through a feature recognition algorithm. When it is identified that the simulated hidden danger image contains preset fire features, it can be determined that the simulated hidden danger image contains the affected area. The preset fire features can be smoke, ignition points, etc. The specific preset fire features are not specifically limited in the embodiments of the present application, as long as they can characterize the fire.

[0092] After identifying the affected area, the affected area corresponding to the affected area can be determined according to the edge detection algorithm, wherein the larger the affected area, the higher the corresponding first impact value. The preset first impact value mapping relationship includes first impact values ​​corresponding to different impact areas, and the specific content is not specifically limited in the embodiment of the present application.

[0093] Step S3: Determine the regional value level of the affected area according to the simulated hidden danger image, and determine the second impact value corresponding to the regional value level based on the regional value level and the preset second impact value mapping relationship. The preset second impact value mapping relationship is the corresponding relationship between the regional value level and the second impact value.

[0094] Specifically, since different areas have different land uses, for example, whether they are planned as protected areas, whether they are developed as tourist areas, etc., and different areas have different ecological values, for example, areas with high biodiversity richness may be protected and restricted from development, thereby affecting market value, etc., it is necessary to analyze the regional value level of the affected area after determining the affected area, so as to be able to respond promptly to hidden dangers or abnormalities in the affected area with a higher regional value level. Among them, the regional value level of the affected area can be analyzed from the aspects of ecological value, economic value, and traffic value. After determining the regional value level, the second impact value corresponding to the regional value level is determined based on the preset second impact value mapping relationship. The preset second impact value mapping relationship contains second impact values ​​corresponding to different regional value levels. The specific content is not specifically limited in the embodiment of this application. Further, the regional value level of the affected area is determined according to the simulated hidden danger image, which can specifically include:

[0095] Based on the simulated hidden danger image, the biological characteristics and biological species of the affected area are determined, and the ecological value corresponding to the affected area is determined based on the biological characteristics and biological species; the regional type of the affected area is determined based on the biological characteristics and biological species contained in the affected area, and the economic value is determined based on the regional type. The regional types include agriculture, forestry, and tourism, and different regional types have different corresponding economic values; based on the simulated hidden danger image, the number of associated roads corresponding to the affected area is determined, and the corresponding traffic value is determined based on the number of associated roads. The associated roads are roads passing through the affected area; the regional value level of the affected area is determined based on the ecological value, economic value and traffic value.

[0096] Specifically, the ecological value assessment of the affected area focuses more on the natural environment and biodiversity in the affected area. The biological characteristics corresponding to the affected area include plant characteristics and animal characteristics, such as first-class protected animals and second-class protected animals. Different biological characteristics correspond to different ecological values. In addition, different biological species correspond to different ecological values. The more biological species, the higher the corresponding ecological value. The biological characteristics and biological species of the affected area can be obtained from the monitoring system. The monitoring system stores the ecological characteristics and biological species corresponding to the area to be monitored, which can be uploaded to the monitoring system in advance by relevant staff. The ecological value corresponding to the biological characteristics and biological species of the affected area can be determined based on the first mapping relationship, and the first mapping relationship contains the ecological values ​​corresponding to different biological characteristics and different biological species.

[0097] The economic value of the affected area is evaluated, with more emphasis on the economic output, land use efficiency, etc. of the affected area. The area type corresponding to the affected area can be first identified through feature recognition. The area types include agriculture, forestry, tourism, etc. Different area types have corresponding economic values, which can be specifically determined based on the second mapping relationship. The second mapping relationship contains specific economic values ​​corresponding to different area types.

[0098] Traffic value assessment is conducted on the impacted area, with more emphasis on traffic accessibility in the impacted area. Roads in the impacted area can be identified from the simulated hidden danger image, and the roads in the impacted area can be determined as associated roads. The more associated roads there are, the higher the corresponding traffic value. Specifically, the traffic value corresponding to different numbers of associated roads can be determined based on the third mapping relationship, and the third mapping relationship contains specific traffic values ​​corresponding to different numbers.

[0099] Among them, the specific contents of the first mapping relationship, the second mapping relationship and the third mapping relationship are not specifically limited in the embodiments of this application, and can be determined by relevant staff based on historical experimental data and uploaded to the monitoring system. Finally, the total value is obtained by summarizing the ecological value, economic value and traffic value, and then the regional value level corresponding to the total value is determined based on the preset value level mapping relationship. The preset value level mapping relationship contains different regional value levels corresponding to the total value. The specific content of the preset value level mapping relationship is not limited in the embodiments of this application.

[0100] Step S4: determining a target warning level of the hidden danger prompt information based on the first impact value and the second impact value, determining a target feedback method based on the target warning level, and feeding back the hidden danger prompt information based on the target feedback method.

[0101] Specifically, after determining the first impact value and the second impact value, the first impact value and the second impact value can be aggregated to obtain a total impact value, and finally the corresponding target warning level can be determined based on the total impact value. The higher the target warning level, the more complex the corresponding target feedback method. For example, when the target warning level is level one, the corresponding target feedback method is SMS feedback; when the target warning level is level two, the corresponding target feedback method is SMS feedback and broadcast feedback; when the target warning level is level three, the corresponding target feedback method is SMS feedback, broadcast feedback, and buzzer feedback. The target feedback methods corresponding to different target warning levels are not specifically limited in the embodiments of the present application and can be set by relevant technical personnel.

[0102] By analyzing the affected area and regional value of the affected area when hidden dangers are detected and not eliminated in time, it is possible to predict and evaluate the risks that the detected area may face in the future, and adjust the warning level based on the possible risks, so as to ensure that important hidden dangers receive timely and efficient response while avoiding overreaction to unimportant hidden dangers, so as to improve the efficiency and pertinence of emergency response.

[0103] Furthermore, in order to control the fire risk in the initial stage, the method provided by the present application also includes:

[0104] When a fire factor index of concern is detected, the stage monitoring data corresponding to the fire factor index of concern is obtained, the fire factor index of concern is a fire factor index within a preset range of the fire factor index, and the stage monitoring data is the sensor monitoring data corresponding to the preset time period of concern; the abnormal change monitoring feature is determined from the stage monitoring data, and the corresponding change rate of the abnormal change monitoring feature within the preset time period of concern is higher than the corresponding preset standard change rate; and prevention prompt information is generated based on the abnormal change monitoring feature.

[0105] Specifically, after determining the fire factor index of the area to be monitored, if the fire factor index is higher than the preset index threshold, hidden danger warning information is generated; if the fire factor index is not higher than the preset index threshold and is within the preset attention factor index range, no hidden danger warning information will be generated at this time, but the area to be monitored can be set as the attention area, and the fire factor index corresponding to the attention area can be determined as the attention fire factor index, wherein the specific preset attention factor index range is not specifically limited in the embodiment of the present application, as long as the preset index threshold can be ensured to be higher than the preset attention factor index range.

[0106] The preset time period of concern is a period of time before the fire factor index of concern is detected. The duration corresponding to the preset time period of concern can be 60 minutes or 80 minutes. The specific duration is not specifically limited in the embodiment of the present application and can be set by relevant technical personnel. By analyzing the sensor monitoring data corresponding to the preset time period of concern, abnormal change monitoring features with large changes are determined. For example, the light intensity continues to rise within the preset time period of concern, or the temperature continues to rise within the preset time period. If the abnormal change monitoring features are not intervened in time, the abnormal change monitoring features may affect the fire factor index corresponding to the area of ​​concern, which may cause fire hazards in the area of ​​concern.

[0107] By analyzing the stage monitoring data corresponding to the fire factor index when there is no fire risk, the monitoring features that may be abnormal in the stage monitoring data are determined, and then the prevention prompt information generated based on the abnormal change monitoring features is convenient for timely sending prompt information to relevant staff to remind them to pay attention to the abnormal change monitoring features and take measures to eliminate the abnormalities in time. Through this timely prevention and intervention of individual monitoring features, it is helpful to control the fire risk in the initial stage, thereby reducing the probability of fire risk occurrence.

[0108] The present application provides a monitoring system, such as Figure 3 As shown, Figure 3 The monitoring system 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the monitoring system 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the monitoring system 300 does not constitute a limitation on the embodiments of the present application.

[0109] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0110] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The fact that only one line is used in the diagram does not mean that there is only one bus or only one type of bus.

[0111] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0112] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0113] The monitoring system includes, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The monitoring system shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0114] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0115] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in any of the above embodiments is implemented.

[0116] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0117] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for monitoring forest and grassland fire factors, characterized in that: include: Acquire sensor monitoring data corresponding to the area to be monitored, and perform data similarity aggregation on the sensor monitoring data to obtain at least one aggregated feature information corresponding to the sensor monitoring data, wherein the sensor monitoring data includes rainfall, temperature, humidity, wind speed, wind direction, and moisture content of litter; Performing word segmentation processing on each aggregated feature information, and determining an aggregated keyword dictionary corresponding to each aggregated feature information based on the word segmentation processing result corresponding to each aggregated feature information; Acquire historical monitoring data, and determine supplementary information corresponding to each aggregate feature information based on each aggregate keyword dictionary and the historical monitoring data; Determine, according to each aggregated feature information and the supplementary information corresponding to each aggregated feature information, an aggregated feature value corresponding to each aggregated feature information, and determine, based on each aggregated feature value, a fire factor feature graph corresponding to the sensor monitoring data; Determining a corresponding fire factor index based on the fire factor characteristic graph, and generating hidden danger prompt information based on the sensor monitoring data when the fire factor index is higher than a preset index threshold; The aggregation feature information is segmented, and based on the segmentation result corresponding to the aggregation feature information, an aggregation keyword dictionary corresponding to the aggregation feature vector is determined, including: Performing word segmentation processing on the aggregated feature information based on a preset word segmentation algorithm to obtain a word segmentation text; Identify at least one keyword contained in the segmented text, and determine a weight value of each keyword based on the frequency and position of occurrence of each keyword in the aggregated feature information; Determine the aggregate keyword dictionary based on each keyword and a weight value corresponding to each keyword; Wherein, determining the corresponding fire factor index based on the fire factor characteristic graph includes: Identify the coordinates of the feature points corresponding to each aggregated feature information in the fire factor feature map; Determine the characteristic region corresponding to the fire factor characteristic map and the area value corresponding to the characteristic region based on the coordinates of each characteristic point, wherein the characteristic region is the region formed by connecting all characteristic points; The corresponding fire factor index is determined based on the regional area value and the preset index mapping relationship, and the preset index mapping relationship is the corresponding relationship between the regional area value and the fire factor index.

2. A forest-grassland fire factor monitoring method according to claim 1, characterized in that: Also includes: If the hidden danger elimination instruction is not received within the preset time period, the target simulation model corresponding to the monitored area is obtained, and a simulated hidden danger image is determined based on the target simulation model and each aggregated feature information and the supplementary information corresponding to each aggregated feature information; Identify an impact area from the simulated hidden danger image, and determine a first impact value corresponding to the impact area based on an impact area of ​​the impact area and a preset first impact value mapping relationship, wherein the preset first impact value mapping relationship is a corresponding relationship between the impact area and the first impact value; Determine the regional value grade of the affected area according to the simulated hidden danger image, and determine the second impact value corresponding to the regional value grade based on the regional value grade and a preset second impact value mapping relationship, wherein the preset second impact value mapping relationship is a corresponding relationship between the regional value grade and the second impact value; A target warning level of the hidden danger prompt information is determined based on the first impact value and the second impact value, a target feedback method is determined based on the target warning level, and the hidden danger prompt information is fed back based on the target feedback method.

3. A forest-grassland fire factor monitoring method according to claim 2, characterized in that: The step of determining the regional value level of the affected area according to the simulated hidden danger image comprises: Determine biological characteristics and biological species of the affected area based on the simulated hidden danger image, and determine the ecological value corresponding to the affected area based on the biological characteristics and biological species; Determine the area type of the impact area based on the biological features and biological species contained in the impact area, and determine the economic value based on the area type, the area types include agriculture, forestry, and tourism, and different area types correspond to different economic values; Determine the number of associated roads corresponding to the affected area based on the simulated hidden danger image, and determine the corresponding traffic value based on the number of associated roads, wherein the associated roads are roads passing through the affected area; The regional value level of the impact area is determined based on the ecological value, the economic value, and the traffic value.

4. A forest-grassland fire factor monitoring method according to claim 1, characterized in that: Also includes: When a fire factor index of concern is detected, the stage monitoring data corresponding to the fire factor index of concern is obtained, wherein the fire factor index of concern is a fire factor index within a preset range of the fire factor index, and the stage monitoring data is the sensor monitoring data corresponding to the preset period of concern; Determining an abnormal change monitoring feature from the stage monitoring data, wherein a corresponding change rate of the abnormal change monitoring feature within the preset time period of interest is higher than a corresponding preset standard change rate; Generate preventive reminder information based on the abnormal change monitoring characteristics.

5. A monitoring system, characterized in that: The monitoring system includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a forest and grassland fire factor monitoring method as described in any one of claims 1-4.

6. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and execute a method for monitoring forest and grassland fire factors as described in any one of claims 1-4.

7. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the steps of a forest and grassland fire factor monitoring method described in any one of claims 1 to 4.

Images