Debris flow disaster-pregnancy condition analysis method and system based on big data

Abstract

According to the big data-based debris flow disaster-pregnancy condition analysis method and system provided by the invention, the debris flow potential description event information set in the current debris flow hidden danger element information is obtained through analysis according to the important attribute of the important description content of each debris flow gully object in the hidden danger point directory data; and carrying out anomaly analysis on the debris flow potential description event information set of the current debris flow hidden danger factor information and the debris flow potential description event information set of the previous group of debris flow hidden danger factor information of the current debris flow hidden danger factor information, and determining a debris flow disaster-pregnant condition analysis set of the current debris flow hidden danger factor information. Therefore, the debris flow disaster-gestational condition analysis set of the current debris flow hidden danger element information can be accurately positioned, so that the debris flow disaster-gestational condition analysis set can be subsequently utilized to perform efficient analysis, each hidden danger can be accurately prevented and treated, and the possibility of debris flow occurrence is reduced.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and more specifically, to a method and system for analyzing debris flow disaster conditions based on big data. Background Art

[0002] A debris flow ditch is a basic condition for the occurrence of debris flow. Each hidden danger indicator in the debris flow ditch needs to be analyzed to avoid the occurrence of debris flow. However, at present, there are various interference factors in the analysis of debris flow disaster conditions, resulting in inaccurate analysis. Therefore, a technical solution is urgently needed to overcome the above technical problems. Summary of the invention

[0003] In view of this, the present application provides a method and system for analyzing debris flow disaster conditions based on big data.

[0004] In a first aspect, a method for analyzing debris flow disaster conditions based on big data is provided, the method comprising: Input the current debris flow hidden danger factor information currently obtained by the big data acquisition terminal into the preset hidden danger factor mining network for mining, and obtain the hidden danger point directory data corresponding to the current debris flow hidden danger factor information; Obtaining a debris flow potential description event information set in the current debris flow hazard element information based on important attribute analysis of important description contents of each debris flow ditch object in the hazard point directory data; Anomaly analysis is performed on the debris flow potential description event information set of the current debris flow hazard element information and the debris flow potential description event information set of the previous group of debris flow hazard element information of the current debris flow hazard element information to determine the debris flow disaster-pregnant condition analysis set of the current debris flow hazard element information; and the debris flow disaster-pregnant condition analysis set of the current debris flow hazard element information is transmitted to the hazard warning terminal.

[0005] In the present application, the hidden danger factor mining network is obtained by training an artificial intelligence network based on reference information carrying project task information obtained online.

[0006] In the present application, the hidden danger factor mining network includes a first local analysis network, a second local analysis network, a third local analysis network and a fourth local analysis network; the step of inputting the current debris flow hidden danger factor information currently acquired by the big data acquisition terminal into the preset hidden danger factor mining network for mining to obtain the hidden danger point directory data corresponding to the current debris flow hidden danger factor information includes: Respectively performing important content identification processing on the current debris flow hazard factor information through the first local analysis network and the second local analysis network to obtain important description content of the current debris flow hazard factor information; Performing content mining and content fusion processing on the important description content through the third local analysis network to obtain content fusion information of the current debris flow hazard factor information; The content fusion information is processed by the fourth local analysis network to perform important content identification and feature derivation processing to obtain the hazard point directory data corresponding to the current debris flow hazard element information.

[0007] In the present application, the first local analysis network includes a plurality of first local feature extraction layers and a plurality of second local feature extraction layers, the first local feature extraction layer and the second local feature extraction layer are cyclically trained, there is at least one second local feature extraction layer between two consecutive first local feature extraction layers, and the second local analysis network includes a plurality of third local feature extraction layers connected one by one; the steps of performing important content recognition processing on the current debris flow hazard element information through the first local analysis network and the second local analysis network respectively to obtain the important description content of the current debris flow hazard element information include: Inputting the information of the current debris flow hazard factor information into the first local feature extraction layer and the second local feature extraction layer in the first local analysis network one by one to perform important content recognition processing to obtain description data with a first high importance; The first description data with high importance is input one by one into multiple third local feature extraction layers in the second local analysis network for depolarization processing to obtain important description content of the current debris flow hazard factor information; wherein each of the first local feature extraction layers performs important content recognition processing on the input information to obtain corresponding first depolarized important description content, and outputs the first depolarized important description content to the next local feature extraction layer of the first local feature extraction layer; each of the second local feature extraction layers performs content mining on the input information to obtain second depolarized important description content, and outputs the second depolarized important description content and the information input to the second local feature extraction layer to the next local feature extraction layer; each of the third local feature extraction layers performs important content recognition processing on the input information to obtain corresponding third depolarized important description content, and outputs the third depolarized important description content to the next local feature extraction layer of the third local feature extraction layer.

[0008] In the present application, the third local analysis network includes a plurality of fourth local feature extraction layers and a fifth local feature extraction layer; the step of performing content mining and content fusion processing on the important description content of the current debris flow hazard element information through the third local analysis network to obtain the content fusion information of the current debris flow hazard element information includes: The important description contents of the current debris flow hazard factor information are input into each of the fourth local feature extraction layers for content mining processing to obtain multiple fourth depolarized important description contents, and the obtained fourth depolarized important description contents are output to the fifth local feature extraction layer; the fifth local feature extraction layer performs content fusion processing on each of the fourth depolarized important description contents to obtain content fusion information of the current debris flow hazard factor information.

[0009] In the present application, the fourth local analysis network includes a feature derivation unit and a sixth local feature extraction layer, and the sixth local feature extraction layer is respectively connected to the feature derivation unit and one of the first local feature extraction layers or one of the second local feature extraction layers in the first local analysis network; the step of performing important content recognition processing and feature derivation processing on the content fusion information of the current debris flow hazard element information through the fourth local analysis network to obtain the hazard point directory data corresponding to the current debris flow hazard element information includes: The content fusion information of the current debris flow hazard factor information is input into the feature derivation unit for feature derivation processing to obtain target information and output it to the sixth local feature extraction layer; the sixth local feature extraction layer receives the first depolarized important description content output by the connected first local feature extraction layer or the second depolarized important description content output by the second local feature extraction layer and the target information output by the feature derivation unit, performs global processing on the acquired information to obtain global data, and performs important content recognition processing on the global data to obtain the hazard point directory data corresponding to the current debris flow hazard factor information.

[0010] In the present application, the step of obtaining the debris flow potential description event information set of the current debris flow hazard element information based on the important attribute analysis of the important description content of each debris flow ditch object in the hazard point directory data includes: Using the target restriction condition to mark the important description contents of all debris flow ditch objects whose important attributes in the hidden danger point directory data are the first value; Based on the percentage of important description contents of debris flow ditch objects whose important attributes are the first value in the target constraint conditions in all important description contents of debris flow ditch objects in the target constraint conditions, determining whether the potential description event information set of debris flow is carried in the hidden danger point directory data; If the debris flow potential description event information set is carried, the debris flow potential description event information set of the current debris flow potential description event information is obtained based on the debris flow potential description event information set in the hidden danger point directory data.

[0011] In the present application, the step of marking the important description contents of all debris flow ditch objects whose important attributes in the hazard point directory data are the first value by using the target restriction condition includes: Obtain important description contents of debris flow ditch objects having significant abnormality in the first direction and the second direction respectively from among all important description contents of debris flow ditch objects whose important attribute is the first value in the hidden danger point catalog data, wherein the significant abnormality includes the maximum significant abnormality and the minimum significant abnormality; The target restriction condition is determined based on the distribution of the important description content of the debris flow ditch object with significant abnormality in the hidden danger point catalog data, and each condition feature of the target restriction condition is associated with one of the important description content of the debris flow ditch object with significant abnormality.

[0012] In the present application, the step of judging whether the potential description event information set of debris flow is carried in the hazard point directory data based on the percentage of the important description content of the debris flow ditch object whose important attribute is the first value in the target constraint condition in all the important description content of the debris flow ditch object in the target constraint condition includes: Determine a first data scale of a data set consisting of important description contents of a debris flow ditch object whose important attribute is a first value within the target constraint condition, and determine a second data scale of the target constraint condition; determining a quantitative comparison result between the first data scale and the second data scale; When the quantitative comparison result is greater than a preset standard value, it is determined that the data set formed by the important description content of the debris flow ditch object whose important attribute in the hidden danger point directory data is the first value is the debris flow potential description event information set.

[0013] In the present application, the step of performing an abnormal analysis on the debris flow potential description event information set of the current debris flow hazard element information and the debris flow potential description event information set of the previous group of debris flow hazard element information of the current debris flow hazard element information to determine the debris flow disaster-pregnant condition analysis set of the current debris flow hazard element information includes: Determine a quantitative evaluation of debris flow gully movement changes between a debris flow potential description event information set of the current debris flow hazard factor information and a debris flow potential description event information set of a previous set of debris flow hazard factor information of the current debris flow hazard factor information; When the quantified evaluation of the debris flow gully movement change is not greater than the set quantified evaluation, the debris flow gully movement information of the debris flow potential description event information set based on the previous set of debris flow hazard element information is analyzed in the current debris flow hazard element information to obtain a debris flow disaster-pregnancy condition analysis set; When the quantitative evaluation of the debris flow gully movement change is greater than the set quantitative evaluation, the debris flow potential description event information set of the current debris flow hazard element information is used as the debris flow disaster-pregnancy condition analysis set.

[0014] In the present application, the step of determining the quantitative evaluation of debris flow gully movement changes between the debris flow potential description event information set of the current debris flow hazard element information and the debris flow potential description event information set of the previous group of debris flow hazard element information of the current debris flow hazard element information includes: Using the same classification thread, the debris flow potential description event information set of the current debris flow hazard factor information is divided into a plurality of first local information sets, and the debris flow potential description event information set of the previous group of debris flow hazard factor information is divided into a plurality of second local information sets; For each of the first local information sets, a quantitative evaluation of the movement change of the debris flow gully between important points of the first local information set and corresponding important points of the second local information set is determined.

[0015] In a second aspect, a debris flow disaster condition analysis system based on big data is provided, comprising a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute it to implement the above method.

[0016] The debris flow disaster condition analysis method and system based on big data provided by the embodiment of the present application, by inputting the current debris flow hidden danger element information currently obtained by the big data acquisition end into the preset hidden danger element mining network for mining, so as to obtain the hidden danger point directory data corresponding to the current debris flow hidden danger element information. And according to the important attribute analysis of the important description content of each debris flow ditch object in the hidden danger point directory data, the debris flow potential description event information set in the current debris flow hidden danger element information is obtained, and then the debris flow potential description event information set of the current debris flow hidden danger element information and the debris flow potential description event information set of the previous group of debris flow hidden danger element information of the current debris flow hidden danger element information are analyzed abnormally to determine the debris flow disaster condition analysis set of the current debris flow hidden danger element information. In this way, the debris flow disaster condition analysis set of the current debris flow hidden danger element information can be accurately located, so that the debris flow disaster condition analysis set can be used for efficient analysis in the future, and each hidden danger can be accurately prevented and controlled to reduce the possibility of debris flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a method for analyzing debris flow disaster conditions based on big data provided in an embodiment of the present application.

[0019] Figure 2 A block diagram of a debris flow disaster condition analysis device based on big data provided in an embodiment of the present application.

[0020] Figure 3 An architecture diagram of a debris flow disaster condition analysis system based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0022] See also Figure 1 , showing a method for analyzing debris flow disaster conditions based on big data, which may include the technical solutions described in the following steps 210-240.

[0023] Step 210, input the current debris flow hazard factor information currently obtained by the big data acquisition terminal into the preset hazard factor mining network for mining, and obtain the hazard point directory data corresponding to the current debris flow hazard factor information.

[0024] Exemplarily, the hidden danger factor mining network can be understood as an AI artificial intelligence network. Further, the hidden danger point directory data is used to characterize the types of debris flow hidden danger data obtained in real time.

[0025] Step 220, based on the important attribute analysis of the important description content of each debris flow ditch object in the hidden danger point directory data, obtain the debris flow potential description event information set in the current debris flow hidden danger element information.

[0026] Exemplarily, the important attributes are used to characterize the key features in the important description content of the debris flow ditch object. Further, the debris flow potential description event information is used to characterize the important topics in the debris flow hidden danger element information.

[0027] Step 230, performing an anomaly analysis on the debris flow potential description event information set of the current debris flow hazard element information and the debris flow potential description event information set of the previous group of debris flow hazard element information of the current debris flow hazard element information, to determine the debris flow disaster-pregnancy condition analysis set of the current debris flow hazard element information.

[0028] Exemplarily, anomaly analysis can be understood as comparing information sets of potential description events of debris flow.

[0029] Step 240: transmitting the debris flow disaster-pregnancy condition analysis set of the current debris flow hazard element information to the hazard warning terminal.

[0030] In this embodiment, in step 210, the current debris flow hazard factor information of the project task currently being processed can be received by the big data acquisition terminal, and the current debris flow hazard factor information may carry the project task information. The acquired current debris flow hazard factor information can be input into the preset hazard factor mining network for mining to obtain the hazard point directory data corresponding to the current debris flow hazard factor information. Among them, the hazard factor mining network is obtained by training the artificial intelligence network according to the reference information carrying the project task information obtained online.

[0031] Furthermore, before the current debris flow hazard factor information is input into the hazard factor mining network for mining, the current debris flow hazard factor information can be preliminarily processed. In this embodiment, the hazard factor mining network obtained by artificial intelligence network training includes a first local analysis network, a second local analysis network, a third local analysis network, and a fourth local analysis network. The local analysis network can be understood as a sub-model or a network layer. In combination with the content described in the above step 210, the hazard point directory data corresponding to the current debris flow hazard factor information can be obtained through the following steps.

[0032] Step 211 , performing important content identification processing on the current debris flow hazard factor information through the first local analysis network and the second local analysis network respectively, to obtain important description content of the current debris flow hazard factor information.

[0033] Step 212: performing content mining and content fusion processing on the important description content through the third local analysis network to obtain content fusion information of the current debris flow hazard element information.

[0034] Step 213, performing important content recognition processing and feature derivation processing on the content fusion information through the fourth local analysis network to obtain the hazard point directory data corresponding to the current debris flow hazard element information.

[0035] In this embodiment, the first local analysis network includes multiple first local feature extraction layers (which can be understood as convolutional neural models / convolutional layers) and multiple second local feature extraction layers, and the first local feature extraction layers and the second local feature extraction layers are trained in a loop. There is at least one second local feature extraction layer between two consecutive first local feature extraction layers, and the second local analysis network includes multiple third local feature extraction layers connected one by one.

[0036] In the above step 211, when the important content identification processing of the current debris flow hazard factor information is performed using the first local analysis network and the second local analysis network respectively to obtain the important description content of the current debris flow hazard factor information, the information of the current debris flow hazard factor information can be input one by one into the first local feature extraction layer and the second local feature extraction layer in the first local analysis network for important content identification processing to obtain the description data with a first high importance. Then, the description data with a first high importance are input one by one into the multiple third local feature extraction layers in the second local analysis network for depolarization processing to obtain the important description content of the current debris flow hazard factor information.

[0037] Each first local feature extraction layer performs important content recognition processing on the input information to obtain the corresponding first depolarized important description content, and outputs the first depolarized important description content to the next local feature extraction layer of the first local feature extraction layer. The next local feature extraction layer can be the second local feature extraction layer connected to the first local feature extraction layer, or the third local feature extraction layer in the second local analysis network connected to the first local feature extraction layer.

[0038] In this embodiment, each first local feature extraction layer is described in such a way that the first local feature extraction layer first performs important content recognition processing on the input information using a depolarization value, and then performs a refinement processing (which can be understood as an optimization processing).

[0039] Furthermore, each second local feature extraction layer obtains a second depolarized important description content after performing content mining on the input information, and outputs the second depolarized important description content and the information input to the second local feature extraction layer to the next local feature extraction layer. The next local feature extraction layer may be the first local feature extraction layer connected to the second local feature extraction layer, or may be another second local feature extraction layer.

[0040] In this embodiment, the description method of each second depolarization value (which can be understood as a convolution eigenvalue) is that the second local feature extraction layer first performs important content recognition processing on the input information with the depolarization value, and performs refinement processing. Then, the important content recognition processing is performed with the depolarization value, and the refinement processing is performed again. Finally, the important content recognition processing is performed with the depolarization value again to obtain the second depolarization important description content. The obtained second depolarization important description content and the information input to this layer are then output to the next local feature extraction layer together.

[0041] Each third local feature extraction layer performs important content recognition processing on the input information to obtain the corresponding third depolarized important description content, and outputs the third depolarized important description content to the next local feature extraction layer of the third local feature extraction layer. The next local feature extraction layer can be another third local feature extraction layer connected after the third local feature extraction layer, or it can be a local feature extraction layer in the fourth local analysis network connected thereto.

[0042] In this embodiment, the description method of each third local feature extraction layer is that the third local feature extraction layer first performs important content recognition processing on the input information with a depolarization value, and performs a refinement processing. Then, the important content recognition processing is performed with a depolarization value, and finally, a refinement processing is performed to obtain the third depolarization important description content and output it.

[0043] In this embodiment, the third local analysis network includes a plurality of fourth local feature extraction layers and a fifth local feature extraction layer. In the above step 212, the content fusion information of the current debris flow hazard element information can be obtained according to the fourth local analysis network through the following steps: The important description contents of the current debris flow hazard factor information are input to each fourth local feature extraction layer for content mining processing to obtain multiple fourth depolarized important description contents, and each fourth depolarized important description content is output to the fifth local feature extraction layer. The fifth local feature extraction layer performs content fusion processing on each fourth depolarized important description content to obtain content fusion information of the current debris flow hazard factor information.

[0044] In this embodiment, the description method of the fourth local feature extraction layer is the same as the unit training of the third local feature extraction layer, and the unit training of the fifth local feature extraction layer is the same as the description method of the second local feature extraction layer, and no further limitation is made here.

[0045] Further, in the present embodiment, the fourth local analysis network includes a feature derivation unit and a sixth local feature extraction layer, and the sixth local feature extraction layer is respectively connected to the feature derivation unit and one of the first local feature extraction layers or one of the second local feature extraction layers in the first local analysis network. Exemplarily, the sixth local feature extraction layer is respectively connected to the feature derivation unit and the second local feature extraction layer in the first local analysis network, and it should be understood that this is not limited here. In the above step 213, the hidden danger point directory data corresponding to the current debris flow hidden danger element information can be obtained by the following steps: the content fusion information of the current debris flow hidden danger element information is input to the feature derivation unit for feature derivation processing to obtain the target information and output it to the sixth local feature extraction layer. The sixth local feature extraction layer receives the first depolarized important description content output by the connected first local feature extraction layer or the second depolarized important description content output by the second local feature extraction layer and the target information output by the feature derivation unit. For example, it can be receiving the first depolarized important description content and the target information, or it can be receiving the second depolarized important description content and the target information. The sixth local feature extraction layer performs global processing on the acquired information to obtain global data, and performs important content recognition processing on the global data to obtain the hidden danger point directory data corresponding to the current debris flow hidden danger element information.

[0046] In this embodiment, the description method of the sixth local feature extraction layer is the same as the description method of the second local feature extraction layer, and no further limitation is made here. In addition, the fourth local analysis network may also include a feature derivation unit and a sixth local feature extraction layer, wherein the feature derivation unit and the feature derivation unit, the sixth local feature extraction layer and the sixth local feature extraction layer are processed in the same manner, and no further limitation is made here. By globally combining the target information output by the feature derivation unit with the first depolarized important description content or the second depolarized important description content, the new important description content obtained in the information expansion process can be combined with the features with high similarity obtained in the previous depolarization process, so as to retain some high-importance description data obtained in the previous depolarization process to a certain extent, thereby improving the final mining effect.

[0047] The hidden danger factor mining network provided in this embodiment is more convenient than the existing conventional artificial intelligence network, and its structure does not carry classification units, which can minimize the scale of variables that need to be trained and improve processing efficiency.

[0048] The current debris flow hidden danger element information obtained by the big data acquisition terminal is associated with the above processing to obtain the corresponding hidden danger point directory data, which includes multiple important description contents of debris flow ditch objects, and the important attribute of each important description content of the debris flow ditch object is -2 or 2. Among them, the important description content of the debris flow ditch object with the important attribute of the first value may be the important description content of the debris flow ditch object in the foreground information, and the important description content of the debris flow ditch object with the important attribute of -2 may be the important description content of the debris flow ditch object in the background information. In this embodiment, when executing the above step 220, the debris flow potential description event information set in the current debris flow hidden danger element information can be determined specifically through the following steps.

[0049] Step 221, using the target restriction condition to mark the important description contents of all debris flow ditch objects whose important attributes in the hidden danger point directory data are the first value.

[0050] Step 222, based on the percentage of the important description content of the debris flow ditch object with the first value of the important attribute in the target constraint condition in the important description content of all the debris flow ditch objects in the target constraint condition, it is determined whether the potential description event information set of the debris flow is carried in the hidden danger point directory data. If the potential description event information set of the debris flow is carried, the following step 223 is executed; if the potential description event information set of the debris flow is not carried, the following step 224 is executed.

[0051] Step 223, based on the debris flow potential description event information set in the hidden danger point directory data, the debris flow potential description event information set of the current debris flow hidden danger element information is obtained.

[0052] Step 224, directly transmit the current debris flow hazard factor information to the hazard warning terminal.

[0053] In order to detect whether the current debris flow hidden danger element information carries the project theme information, in this embodiment, firstly, the target restriction condition can be used to mark the important description content of all debris flow ditch objects whose important attributes are the first value in the hidden danger point directory data. Then, according to the percentage of the important description content of the debris flow ditch objects whose important attributes are the first value in the target restriction condition in the important description content of all debris flow ditch objects in the target restriction condition, it is judged whether the hidden danger point directory data carries the debris flow potential description event information set. If it is determined that the hidden danger point directory data carries the debris flow potential description event information set, the debris flow potential description event information set of the current debris flow hidden danger element information can be obtained according to the debris flow potential description event information set in the hidden danger point directory data. If the debris flow potential description event information set is not carried, there is no need to obtain the subsequent debris flow disaster-pregnant condition analysis set, and the current debris flow hidden danger element information can be directly transmitted to the hidden danger warning terminal.

[0054] Optionally, when using the target constraint to mark all the important description contents of debris flow ditch objects whose important attributes are the first value in the hidden danger point directory data, the important description contents of debris flow ditch objects with significant abnormality in the first direction and the second direction can be obtained from all the important description contents of debris flow ditch objects whose important attributes are the first value in the hidden danger point directory data, including the maximum significant abnormality and the minimum significant abnormality. That is, for the hidden danger point directory data, the important description contents of debris flow ditch objects with the first value in multiple directions of the hidden danger point directory data can be obtained respectively. Then, based on the distribution of the important description contents of debris flow ditch objects with significant abnormality in the hidden danger point directory data obtained, the target constraint is determined, and each conditional feature of the target constraint is associated with one of the important description contents of the debris flow ditch objects with significant abnormality. In this way, the target constraint is the minimum standard value that can mark all the important description contents of debris flow ditch objects with the first value in the hidden danger point directory data.

[0055] It should be understood that, in addition to the important description content of the debris flow ditch object with the important attribute (which can be understood as the significant abnormality in the important direction) as the first value, the target constraint condition also includes the important description content of the debris flow ditch object (abnormality label) with the important attribute as 1. In this embodiment, it can be judged whether the potential description event information set of debris flow (which can be understood as the type information in the hidden danger point directory data) is carried in the hidden danger point directory data by the percentage of the important description content of the debris flow ditch object with the important attribute as the first value in the target constraint condition to the important description content of all the debris flow ditch objects in the target constraint condition.

[0056] Alternatively, as another independently implemented embodiment, the number of important description contents of debris flow ditch objects with an important attribute of the first value within the target constraint and the number of important description contents of all debris flow ditch objects within the target constraint can also be determined. Then, it is determined whether the quantitative comparison result between the number of important description contents of debris flow ditch objects with the first value and the number of important description contents of all debris flow ditch objects within the target constraint is greater than a pre-set standard value. When it is greater than the pre-set standard value, it can be determined that the data set formed by the important description contents of the debris flow ditch objects with the first value as the important attribute is the debris flow potential description event information set.

[0057] On the basis of determining the debris flow potential description event information set in the hazard point directory data, the data set of the debris flow potential description event information set corresponding to the hazard point directory data in the current debris flow hazard element information is the debris flow potential description event information set of the current debris flow hazard element information.

[0058] In this embodiment, taking into account that there may be mining disorder in the hidden danger factor mining network in some cases, in order to ensure the accuracy of the mining results, after determining the debris flow potential description event information set in the current debris flow hidden danger factor information, the debris flow potential description event information set of the current debris flow hidden danger factor information and the debris flow potential description event information set of the previous group of debris flow hidden danger factor information of the current debris flow hidden danger factor information will be analyzed by abnormal analysis to determine the final debris flow disaster-pregnancy condition analysis set of the current debris flow hidden danger factor information.

[0059] In this embodiment, when executing the above step 230, the debris flow disaster-predisposing condition analysis set of the current debris flow hazard factor information can be determined specifically through the following steps.

[0060] Step 231, determine the quantitative evaluation of debris flow gully movement changes between the debris flow potential description event information set of the current debris flow hazard element information and the debris flow potential description event information set of the previous group of debris flow hazard element information of the current debris flow hazard element information, and detect whether the quantitative evaluation of the debris flow gully movement changes is not greater than the set quantitative evaluation. If it is not greater than the set quantitative evaluation, execute the following step 232, otherwise, execute the following step 233.

[0061] Step 232, based on the debris flow potential description event information set of the previous set of debris flow hazard element information, the debris flow gully movement information is analyzed in the current debris flow hazard element information to obtain a debris flow disaster-pregnancy condition analysis set.

[0062] Step 233, using the debris flow potential description event information set of the current debris flow hazard element information as the debris flow disaster-pregnancy condition analysis set.

[0063] Furthermore, if the obtained quantitative evaluation of the movement change of the debris flow gully is greater than the set quantitative evaluation, it can be determined that the project theme mining results for the current debris flow hazard element information are complete, and the debris flow potential description event information set of the current debris flow hazard element information can be used as the final debris flow disaster condition analysis set.

[0064] Based on the above important description content, in this embodiment, the same classification thread can be used to divide the debris flow potential description event information set of the current debris flow hazard element information into multiple first local information sets, and the previous set of debris flow hazard element information can be divided into multiple second local information sets. Among them, the same classification thread can be to divide the debris flow potential description event information set into 2 groups, or to divide the debris flow potential description event information set into 3 groups, which will not be repeated here.

[0065] For each first local information set in the current debris flow hazard element information, determine the quantitative evaluation of the debris flow gully movement change between the important points of the first local information set and the important points of the corresponding second local information set of the previous set of debris flow hazard element information. When the quantitative evaluation of the debris flow gully movement change between the important points of one of the first local information sets and the important points of the corresponding second local information set is greater than the set quantitative evaluation, it can be determined that the mining result of the current debris flow hazard element information is accurate, and the debris flow potential description event information set of the current debris flow hazard element information can be used as the debris flow disaster condition analysis set. If the quantitative evaluation of the debris flow gully movement change between the important points of any first local information set and the important points of the corresponding second local information set is not greater than the set quantitative evaluation, the debris flow potential description event information set of the previous set of debris flow hazard element information is used as the debris flow disaster condition analysis set of the current debris flow hazard element information.

[0066] After determining the debris flow disaster condition analysis set of the current debris flow hazard element information, the debris flow disaster condition analysis set of the current debris flow hazard element information can be transmitted to the hazard warning terminal. In this application, the debris flow disaster condition analysis set can be carried in a data queue and transmitted to the hazard warning terminal together with the data queue.

[0067] Based on the above, please refer to Figure 2 , a device 200 for analyzing debris flow disaster conditions based on big data is provided, the device comprising: The directory mining module 1210 is used to input the current debris flow hidden danger element information currently obtained by the big data acquisition terminal into the preset hidden danger element mining network for mining, so as to obtain the hidden danger point directory data corresponding to the current debris flow hidden danger element information; The information obtaining module 1220 is used to obtain a debris flow potential description event information set in the current debris flow hazard element information based on important attribute analysis of important description contents of each debris flow ditch object in the hazard point directory data; The data analysis module 1230 is used to perform anomaly analysis on the debris flow potential description event information set of the current debris flow hazard element information and the debris flow potential description event information set of the previous group of debris flow hazard element information of the current debris flow hazard element information, to determine the debris flow disaster condition analysis set of the current debris flow hazard element information; and transmit the debris flow disaster condition analysis set of the current debris flow hazard element information to the hazard warning terminal.

[0068] Based on the above, please refer to Figure 3, shows a debris flow disaster condition analysis system 300 based on big data, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.

[0069] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0070] In summary, based on the above scheme, the current debris flow hidden danger element information currently obtained by the big data acquisition end is input into the preset hidden danger element mining network for mining, so as to obtain the hidden danger point directory data corresponding to the current debris flow hidden danger element information. And according to the important attribute analysis of the important description content of each debris flow ditch object in the hidden danger point directory data, the debris flow potential description event information set in the current debris flow hidden danger element information is obtained, and then the debris flow potential description event information set of the current debris flow hidden danger element information and the debris flow potential description event information set of the previous group of debris flow hidden danger element information of the current debris flow hidden danger element information are analyzed abnormally to determine the debris flow disaster condition analysis set of the current debris flow hidden danger element information. In this way, the debris flow disaster condition analysis set of the current debris flow hidden danger element information can be accurately located, so that the debris flow disaster condition analysis set can be used for efficient analysis in the future, and each hidden danger can be accurately prevented and controlled to reduce the possibility of debris flow.

[0071] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art can understand that the above methods and systems can be implemented using computer executable instructions and / or included in processor control codes, such as on a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided. The system and its modules of the present application can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0072] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0073] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0074] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0075] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a plurality of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, the product including computer-readable program code.

[0076] A computer storage medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or equipment to communicate, propagate or transmit the program for use. The program code located on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0077] The computer program codes required for the operation of each part of the present application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partly on the user's computer and partly on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0078] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0079] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0080] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used for the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0081] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0082] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of this application. Other variations may also fall within the scope of this application. Therefore, as an example and not a limitation, the alternative training of the embodiments of this application can be considered to be consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly introduced and described in this application.

[0083] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for analyzing debris flow disaster conditions based on big data, characterized in that: The method comprises: Input the current debris flow hidden danger factor information currently obtained by the big data acquisition terminal into the preset hidden danger factor mining network for mining, and obtain the hidden danger point directory data corresponding to the current debris flow hidden danger factor information; Obtaining a debris flow potential description event information set in the current debris flow hazard element information based on important attribute analysis of important description contents of each debris flow ditch object in the hazard point directory data; Anomaly analysis is performed on the debris flow potential description event information set of the current debris flow hazard element information and the debris flow potential description event information set of the previous group of debris flow hazard element information of the current debris flow hazard element information to determine the debris flow disaster-pregnant condition analysis set of the current debris flow hazard element information; and the debris flow disaster-pregnant condition analysis set of the current debris flow hazard element information is transmitted to the hazard warning terminal.

2. The method for analyzing debris flow disaster conditions based on big data according to claim 1 is characterized in that: The hidden danger factor mining network is obtained by training an artificial intelligence network based on reference information carrying project task information obtained online.

3. The method for analyzing debris flow disaster conditions based on big data according to claim 1 is characterized in that: The hidden danger factor mining network includes a first local analysis network, a second local analysis network, a third local analysis network and a fourth local analysis network; the step of inputting the current debris flow hidden danger factor information currently acquired by the big data acquisition terminal into the preset hidden danger factor mining network for mining to obtain the hidden danger point directory data corresponding to the current debris flow hidden danger factor information includes: Respectively performing important content identification processing on the current debris flow hazard factor information through the first local analysis network and the second local analysis network to obtain important description content of the current debris flow hazard factor information; Performing content mining and content fusion processing on the important description content through the third local analysis network to obtain content fusion information of the current debris flow hazard factor information; The content fusion information is processed by the fourth local analysis network to perform important content identification and feature derivation processing to obtain the hazard point directory data corresponding to the current debris flow hazard element information.

4. The method for analyzing debris flow disaster conditions based on big data according to claim 3 is characterized in that: The first local analysis network includes a plurality of first local feature extraction layers and a plurality of second local feature extraction layers, the first local feature extraction layer and the second local feature extraction layer are cyclically trained, there is at least one second local feature extraction layer between two consecutive first local feature extraction layers, and the second local analysis network includes a plurality of third local feature extraction layers connected one by one; the steps of performing important content recognition processing on the current debris flow hazard factor information through the first local analysis network and the second local analysis network respectively to obtain the important description content of the current debris flow hazard factor information include: Inputting the information of the current debris flow hazard factor information into the first local feature extraction layer and the second local feature extraction layer in the first local analysis network one by one to perform important content recognition processing to obtain description data with a first high importance; The first description data with high importance is input one by one into multiple third local feature extraction layers in the second local analysis network for depolarization processing to obtain important description content of the current debris flow hazard factor information; wherein each of the first local feature extraction layers performs important content recognition processing on the input information to obtain corresponding first depolarized important description content, and outputs the first depolarized important description content to the next local feature extraction layer of the first local feature extraction layer; each of the second local feature extraction layers performs content mining on the input information to obtain second depolarized important description content, and outputs the second depolarized important description content and the information input to the second local feature extraction layer to the next local feature extraction layer; each of the third local feature extraction layers performs important content recognition processing on the input information to obtain corresponding third depolarized important description content, and outputs the third depolarized important description content to the next local feature extraction layer of the third local feature extraction layer.

5. The method for analyzing debris flow disaster conditions based on big data according to claim 3 is characterized in that: The third local analysis network includes a plurality of fourth local feature extraction layers and a fifth local feature extraction layer; the step of performing content mining and content fusion processing on the important description content of the current debris flow hazard factor information through the third local analysis network to obtain content fusion information of the current debris flow hazard factor information includes: The important description contents of the current debris flow hazard factor information are input into each of the fourth local feature extraction layers for content mining processing to obtain multiple fourth depolarized important description contents, and the obtained fourth depolarized important description contents are output to the fifth local feature extraction layer; the fifth local feature extraction layer performs content fusion processing on each of the fourth depolarized important description contents to obtain content fusion information of the current debris flow hazard factor information.

6. The method for analyzing debris flow disaster conditions based on big data according to claim 4 is characterized in that: The fourth local analysis network includes a feature derivation unit and a sixth local feature extraction layer, and the sixth local feature extraction layer is respectively connected to the feature derivation unit and one of the first local feature extraction layers or one of the second local feature extraction layers in the first local analysis network; the step of performing important content recognition processing and feature derivation processing on the content fusion information of the current debris flow hazard element information through the fourth local analysis network to obtain the hazard point directory data corresponding to the current debris flow hazard element information includes: The content fusion information of the current debris flow hazard factor information is input into the feature derivation unit for feature derivation processing to obtain target information and output it to the sixth local feature extraction layer; the sixth local feature extraction layer receives the first depolarized important description content output by the connected first local feature extraction layer or the second depolarized important description content output by the second local feature extraction layer and the target information output by the feature derivation unit, performs global processing on the acquired information to obtain global data, and performs important content recognition processing on the global data to obtain the hazard point directory data corresponding to the current debris flow hazard factor information.

7. The method for analyzing debris flow disaster conditions based on big data according to any one of claims 1 to 6, characterized in that: The step of obtaining the debris flow potential description event information set of the current debris flow hazard element information based on the important attribute analysis of the important description content of each debris flow ditch object in the hazard point directory data comprises: Using the target restriction condition to mark the important description contents of all debris flow ditch objects whose important attributes in the hidden danger point directory data are the first value; Based on the percentage of important description contents of debris flow ditch objects whose important attributes are the first value in the target constraint conditions in all important description contents of debris flow ditch objects in the target constraint conditions, determining whether the potential description event information set of debris flow is carried in the hidden danger point directory data; If the debris flow potential description event information set is carried, the debris flow potential description event information set of the current debris flow potential description event information is obtained based on the debris flow potential description event information set in the hidden danger point directory data.

8. The method for analyzing debris flow disaster conditions based on big data according to claim 7 is characterized in that: The step of marking important description contents of all debris flow ditch objects whose important attributes in the hidden danger point directory data are the first value by using the target restriction condition comprises: Obtain important description contents of debris flow ditch objects having significant abnormality in the first direction and the second direction respectively from among all important description contents of debris flow ditch objects whose important attribute is the first value in the hidden danger point catalog data, wherein the significant abnormality includes the maximum significant abnormality and the minimum significant abnormality; Determine a target restriction condition based on the distribution of the obtained important description content of the debris flow ditch object with significant abnormality in the hidden danger point catalog data, wherein each condition feature of the target restriction condition is associated with one of the important description content of the debris flow ditch object with significant abnormality; The step of judging whether the potential description event information set of debris flow is carried in the hazard point directory data based on the percentage of the important description content of the debris flow ditch object whose important attribute is the first value in the target constraint condition in all the important description content of the debris flow ditch object in the target constraint condition includes: Determine a first data scale of a data set consisting of important description contents of a debris flow ditch object whose important attribute is a first value within the target constraint condition, and determine a second data scale of the target constraint condition; determining a quantitative comparison result between the first data scale and the second data scale; When the quantitative comparison result is greater than a preset standard value, it is determined that the data set formed by the important description content of the debris flow ditch object whose important attribute in the hidden danger point directory data is the first value is the debris flow potential description event information set.

9. The method for analyzing debris flow disaster conditions based on big data according to any one of claims 1 to 6, characterized in that: The step of performing an abnormal analysis on the debris flow potential description event information set of the current debris flow hazard factor information and the debris flow potential description event information set of the previous group of debris flow hazard factor information of the current debris flow hazard factor information to determine the debris flow disaster-pregnant condition analysis set of the current debris flow hazard factor information comprises: Determine a quantitative evaluation of debris flow gully movement changes between a debris flow potential description event information set of the current debris flow hazard factor information and a debris flow potential description event information set of a previous set of debris flow hazard factor information of the current debris flow hazard factor information; When the quantified evaluation of the debris flow gully movement change is not greater than the set quantified evaluation, the debris flow gully movement information of the debris flow potential description event information set based on the previous set of debris flow hazard element information is analyzed in the current debris flow hazard element information to obtain a debris flow disaster-pregnancy condition analysis set; When the quantified evaluation of the movement change of the debris flow gully is greater than the set quantified evaluation, the debris flow potential description event information set of the current debris flow hidden danger element information is used as the debris flow disaster-pregnancy condition analysis set; The step of determining the quantitative evaluation of debris flow gully movement changes between the debris flow potential description event information set of the current debris flow hazard element information and the debris flow potential description event information set of the previous set of debris flow hazard element information of the current debris flow hazard element information comprises: Using the same classification thread, the debris flow potential description event information set of the current debris flow hazard factor information is divided into a plurality of first local information sets, and the debris flow potential description event information set of the previous group of debris flow hazard factor information is divided into a plurality of second local information sets; For each of the first local information sets, a quantitative evaluation of the movement change of the debris flow gully between important points of the first local information set and corresponding important points of the second local information set is determined.

10. A debris flow disaster condition analysis system based on big data, characterized in that: The invention comprises a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute the computer program to implement the method according to any one of claims 1 to 9.

Images