A landslide risk intelligent assessment method and system

Abstract

The present application provides a method and system for intelligent landslide risk assessment, which can obtain some key landslide risk coefficients from a key landslide risk coefficient set as a first pending landslide risk coefficient, and obtain some non-landslide risk coefficients from a non-key landslide risk coefficient set as a second pending landslide risk coefficient. Subsequently, based on the numerical difference relationship between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, the landslide risk intelligent assessment result of the target landslide risk description information can be obtained without calculating the loss values ​​belonging to all landslide risk coefficients in the key landslide risk coefficient set and the non-key landslide risk coefficient set. Therefore, the accuracy and reliability of the landslide risk intelligent assessment result are improved.

Description

Technical Field

[0001] The present application relates to the technical field of hidden danger warning, and specifically, to a landslide risk intelligent assessment method and system. Background Art

[0002] Landslide is a common geological disaster, which not only endangers people's lives and safety, but also poses a major threat to infrastructure and people's property. Therefore, it is urgent to evaluate each landslide risk point. The existing technology uses relevant technical personnel to conduct on-site surveys, which not only takes a lot of time, but also requires a large number of relevant technical personnel to conduct surveys, and the data processing efficiency is slow. With the rapid development of artificial intelligence technology, artificial intelligence technology is combined with intelligent evaluation of landslide risks. However, the current evaluation accuracy is biased. How to improve the accuracy of the evaluation is a technical problem that is difficult to solve at present. Summary of the invention

[0003] In order to improve the technical problems existing in the related technologies, the present application provides a landslide risk intelligent assessment method and system.

[0004] In a first aspect, a landslide risk intelligent assessment method is provided, the method comprising:

[0005] Obtain target landslide risk description information;

[0006] Obtain a first undetermined landslide risk coefficient from a set of key landslide risk coefficients, and obtain a second undetermined landslide risk coefficient from a set of non-key landslide risk coefficients;

[0007] Obtaining a loss value of the target landslide risk description information under the first undetermined landslide risk coefficient, and obtaining a loss value of the target landslide risk description information under the second undetermined landslide risk coefficient; a loss function of the loss value of the target landslide risk description information under a critical landslide risk coefficient in the critical landslide risk coefficient set is greater than a loss function of the loss value of the target landslide risk description information under a non-critical landslide risk coefficient in the non-critical landslide risk coefficient set;

[0008] The numerical difference between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient is compared, and according to the comparison result, the landslide risk intelligent evaluation result for the target landslide risk description information is determined from the key landslide risk coefficient set or the non-key landslide risk coefficient set.

[0009] It can be understood that some key landslide risk coefficients can be obtained from the key landslide risk coefficient set to be determined as the first pending landslide risk coefficient, and some non-landslide risk coefficients can be obtained from the non-key landslide risk coefficient set to be determined as the second pending landslide risk coefficient. Subsequently, based on the numerical difference relationship between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, the landslide risk intelligent evaluation result of the target landslide risk description information can be obtained without calculating the loss values ​​belonging to all landslide risk coefficients in the key landslide risk coefficient set and the non-key landslide risk coefficient set. Therefore, the accuracy and reliability of the landslide risk intelligent evaluation result are improved.

[0010] In the present application, the step of obtaining a first undetermined landslide risk coefficient from a set of key landslide risk coefficients and obtaining a second undetermined landslide risk coefficient from a set of non-key landslide risk coefficients includes:

[0011] A key landslide risk coefficient is extracted from the key landslide risk coefficient set and determined as the first pending landslide risk coefficient, and all non-key landslide risk coefficients in the non-key landslide risk coefficient set are determined as the second pending landslide risk coefficients.

[0012] It can be understood that the first undetermined landslide risk coefficient can be accurately obtained from the key landslide risk coefficient set, and the second undetermined landslide risk coefficient can be accurately obtained from the non-key landslide risk coefficient set.

[0013] In the present application, the comparison result includes a first comparison result; the comparison is a numerical difference between the loss value to which the first pending landslide risk coefficient belongs and the loss value to which the second pending landslide risk coefficient belongs, and according to the comparison result, a landslide risk intelligent evaluation result for the target landslide risk description information is determined from the key landslide risk coefficient set or the non-key landslide risk coefficient set, including:

[0014] Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, when it is found that the loss value to which the first undetermined landslide risk coefficient belongs is less than the loss value to which the second undetermined landslide risk coefficient belongs, obtaining the first comparison result;

[0015] According to the first comparison result, the first undetermined landslide risk coefficient in the key landslide risk coefficient set is determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

[0016] It can be understood that by comparing the numerical difference between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, according to the comparison result, from the key landslide risk coefficient set or the non-key landslide risk coefficient set, the problem of inaccurate first comparison result is improved, so that the landslide risk intelligent evaluation result for the target landslide risk description information can be accurately determined.

[0017] In the present application, the comparison result includes a second comparison result; the comparison is performed by comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, and according to the comparison result, determining the landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set, including:

[0018] Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, when it is found that the loss value to which the first undetermined landslide risk coefficient belongs is greater than the loss value to which the second undetermined landslide risk coefficient belongs, obtaining the second comparison result;

[0019] According to the second comparison result, the non-critical landslide risk coefficient with the smallest loss value in the non-critical landslide risk coefficient set is determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

[0020] It can be understood that by comparing the numerical difference between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, according to the comparison result, from the key landslide risk coefficient set or the non-key landslide risk coefficient set, the problem of inaccurate second comparison result is improved, so that the landslide risk intelligent evaluation result for the target landslide risk description information can be accurately determined.

[0021] In the present application, the step of obtaining a first undetermined landslide risk coefficient from a set of key landslide risk coefficients and obtaining a second undetermined landslide risk coefficient from a set of non-key landslide risk coefficients includes:

[0022] A key landslide risk coefficient is extracted from the key landslide risk coefficient set and determined as the first pending landslide risk coefficient, and a non-key landslide risk coefficient is extracted from the non-key landslide risk coefficient set and determined as the second pending landslide risk coefficient.

[0023] It can be understood that the first undetermined landslide risk coefficient and the second undetermined landslide risk coefficient can be accurately obtained through the key landslide risk coefficient.

[0024] In the present application, the comparison result includes a first comparison result; the comparison is a numerical difference between the loss value to which the first pending landslide risk coefficient belongs and the loss value to which the second pending landslide risk coefficient belongs, and according to the comparison result, a landslide risk intelligent evaluation result for the target landslide risk description information is determined from the key landslide risk coefficient set or the non-key landslide risk coefficient set, including:

[0025] Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, when it is found that the loss value to which the first undetermined landslide risk coefficient belongs is less than the loss value to which the second undetermined landslide risk coefficient belongs, obtaining the first comparison result;

[0026] According to the first comparison result, obtaining the loss value of the target landslide risk description information under the key landslide risk coefficients in the key landslide risk coefficient set except the first undetermined landslide risk coefficient;

[0027] The key landslide risk coefficient with the smallest loss value in the key landslide risk coefficient set is determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

[0028] It can be understood that by comparing the numerical difference between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, according to the comparison result, from the key landslide risk coefficient set or the non-key landslide risk coefficient set, the problem of inaccurate numerical difference is improved, so that the landslide risk intelligent evaluation result for the target landslide risk description information can be accurately determined.

[0029] In the present application, the comparison result includes a second comparison result; the comparison is performed by comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, and according to the comparison result, determining the landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set, including:

[0030] Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, when it is found that the loss value to which the first undetermined landslide risk coefficient belongs is greater than the loss value to which the second undetermined landslide risk coefficient belongs, obtaining the second comparison result;

[0031] According to the second comparison result, obtaining the loss value of the target landslide risk description information under the key landslide risk coefficients in the non-key landslide risk coefficient set except the second undetermined landslide risk coefficient;

[0032] The non-critical landslide risk coefficient with the smallest loss value in the non-critical landslide risk coefficient set is determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

[0033] It can be understood that by comparing the numerical difference between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, according to the comparison result, the problem of inaccurate loss value is improved when selecting from the key landslide risk coefficient set or the non-key landslide risk coefficient set, so that the landslide risk intelligent evaluation result for the target landslide risk description information can be accurately determined.

[0034] In the present application, the step of obtaining the loss value of the target landslide risk description information under the first undetermined landslide risk coefficient includes:

[0035] Obtaining a first landslide risk safety value and a first abnormal value of the target landslide risk description information under the first undetermined landslide risk coefficient;

[0036] obtaining a landslide risk safety value percentage for the first landslide risk safety value and an abnormality percentage for the first abnormal value;

[0037] Performing function processing on the first landslide risk safety value according to the landslide risk safety value percentage to obtain a first function-processed landslide risk safety value, and performing function processing on the first abnormal value according to the abnormal percentage to obtain a first function-processed abnormal value;

[0038] According to the landslide risk safety value processed by the first function and the abnormal value processed by the first function, the loss value to which the first undetermined landslide risk coefficient belongs is determined.

[0039] It can be understood that when the target landslide risk description information is obtained, the problem of inaccurate function processing of abnormal values ​​is improved, so that the loss value under the first undetermined landslide risk coefficient can be accurately calculated.

[0040] In the present application, the step of obtaining the loss value of the target landslide risk description information under the second undetermined landslide risk coefficient includes:

[0041] Obtaining a second landslide risk safety value and a second abnormal value of the target landslide risk description information under the second undetermined landslide risk coefficient;

[0042] obtaining a landslide risk safety value percentage for the second landslide risk safety value and an abnormality percentage for the second abnormal value;

[0043] Performing function processing on the second landslide risk safety value according to the landslide risk safety value percentage to obtain a second function-processed landslide risk safety value, and performing function processing on the second abnormal value according to the abnormal percentage to obtain a second function-processed abnormal value;

[0044] According to the second function processing landslide risk safety value and the second function processing abnormal value, the loss value to which the second undetermined landslide risk coefficient belongs is determined.

[0045] It can be understood that when obtaining the target landslide risk description information, the problem of inaccurate abnormal percentage is avoided, so that the loss value under the second undetermined landslide risk coefficient can be accurately determined.

[0046] This application also includes:

[0047] Based on the landslide risk intelligent evaluation result, the target landslide risk description information is compressed to obtain compressed data of the target landslide risk description information;

[0048] The compressed data is sent to a data processing terminal, so that the data processing terminal derives the compressed data to obtain derived landslide risk description information corresponding to the target landslide risk description information, and then outputs the derived landslide risk description information in a data display terminal.

[0049] It can be understood that by accurately obtaining the compressed data, the derived landslide risk description information can be accurately output.

[0050] In the present application, the target landslide risk description information has no less than two landslide risk description information attributes; the target landslide risk description information is compressed based on the landslide risk intelligent evaluation result to obtain compressed data of the target landslide risk description information, including:

[0051] Searching for the crustal movement vector data of the target landslide risk description information under the landslide risk intelligent evaluation result;

[0052] Determining the difference between the at least two landslide risk description information attributes according to the crust movement vector data;

[0053] According to the difference between the at least two landslide risk description information attributes, the target landslide risk description information is compressed to obtain the compressed data of the target landslide risk description information.

[0054] It can be understood that when the target landslide risk description information is compressed based on the landslide risk intelligent evaluation result, the problem of inaccurate determination of differences is avoided, so that the compressed data of the target landslide risk description information can be accurately obtained.

[0055] In a second aspect, a landslide risk intelligent assessment system 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 the computer program to implement the above method.

[0056] A landslide risk intelligent assessment method and system provided in an embodiment of the present application can obtain some key landslide risk coefficients from a key landslide risk coefficient set to be determined as a first pending landslide risk coefficient, and obtain some non-landslide risk coefficients from a non-key landslide risk coefficient set to be determined as a second pending landslide risk coefficient. Subsequently, based on the numerical difference relationship between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, the landslide risk intelligent assessment result of the target landslide risk description information can be obtained without calculating the loss values ​​belonging to all landslide risk coefficients in the key landslide risk coefficient set and the non-key landslide risk coefficient set. Therefore, the accuracy and reliability of the landslide risk intelligent assessment result are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] 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.

[0058] Figure 1 A flow chart of a landslide risk intelligent assessment method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] 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.

[0060] See also Figure 1 , shows a method for intelligent landslide risk assessment, which may include the technical solutions described in the following steps S101-S104.

[0061] Step S101, obtaining target landslide risk description information;

[0062] Exemplarily, the landslide risk description information includes: soil looseness information, microseismic information and other information.

[0063] Among them, soil looseness information, microseismic information and other information are factors that trigger landslides.

[0064] For example, target landslide risk description information can be obtained, and the target landslide risk description information can be any landslide risk description information that needs to be compressed. For example, the target landslide risk description information can be an uploaded landslide risk description information, or a landslide risk description information downloaded from a database, or a remaining landslide risk description information sent by the server to the target landslide risk description information.

[0065] Step S102, obtaining a first undetermined landslide risk coefficient from a set of key landslide risk coefficients, and obtaining a second undetermined landslide risk coefficient from a set of non-key landslide risk coefficients;

[0066] For example, the key landslide risk coefficient set can be understood as a data set with large factors affecting landslide occurrence. The non-key landslide risk coefficient set can be understood as a data set with small factors affecting landslide occurrence. Among them, the undetermined landslide risk coefficient can be understood as a candidate landslide risk coefficient.

[0067] For example, the landslide risk coefficient included in the critical landslide risk coefficient set is the critical landslide risk coefficient, and the landslide risk coefficient included in the non-critical landslide risk coefficient set is the non-critical landslide risk coefficient. Among them, the critical landslide risk coefficient refers to a landslide risk coefficient less than 1, for example, the critical landslide risk coefficient in the critical landslide risk coefficient set may include a 1 / 16 landslide risk coefficient, a 1 / 4 landslide risk coefficient, and a 1 / 2 landslide risk coefficient. The non-critical landslide risk coefficient refers to a landslide risk coefficient greater than or equal to 1, for example, the non-critical landslide risk coefficient in the non-critical landslide risk coefficient set may include a 1-time landslide risk coefficient, a 2-time landslide risk coefficient, and a 4-time landslide risk coefficient. Among them, the 1-time landslide risk coefficient, the 2-time landslide risk coefficient, and the 4-time landslide risk coefficient may be referred to as a 1-time landslide risk coefficient, a 2-time landslide risk coefficient, and a 4-time landslide risk coefficient, respectively. From the above, we can see that all landslide risk coefficients can include 1 / 16 landslide risk coefficient, 1 / 4 landslide risk coefficient, 1 / 2 landslide risk coefficient, 1 landslide risk coefficient, 2 landslide risk coefficient and 4 landslide risk coefficient, etc. It can be seen that the numerical difference between two adjacent landslide risk coefficients is a 2-fold relationship.

[0068] There are two ways to extract the first pending landslide risk coefficient from the key landslide risk coefficient set and the second pending landslide risk coefficient from the non-key landslide risk coefficient set, as shown below:

[0069] The first extraction method: a key landslide risk factor can be extracted from the key landslide risk factor set and determined as the first pending landslide risk factor. The first pending landslide risk factor can be any key landslide risk factor in the key landslide risk factor set, or the first pending landslide risk factor can also be a key landslide risk factor in the specified key landslide risk factor set, for example, specifying 1 / 4 landslide risk factors as the first pending landslide risk factor. In addition, all non-key landslide risk factors in the non-key landslide risk factor set can be determined as the second pending landslide risk factor.

[0070] The second extraction method: one key landslide risk factor can be extracted from the key landslide risk factor set and determined as the first pending landslide risk factor. The first pending landslide risk factor can be any key landslide risk factor in the key landslide risk factor set, or the first pending landslide risk factor can also be a key landslide risk factor in the specified key landslide risk factor set, for example, specifying 1 / 4 landslide risk factor as the first pending landslide risk factor. One key landslide risk factor can be extracted from the non-key landslide risk factor set and determined as the second pending landslide risk factor. The second pending landslide risk factor can be any non-key landslide risk factor in the non-key landslide risk factor set, or the second pending landslide risk factor can also be a non-key landslide risk factor in the specified non-key landslide risk factor set, for example, specifying 2 times the landslide risk factor as the second pending landslide risk factor.

[0071] Step S103, obtaining the loss value of the target landslide risk description information under the first pending landslide risk coefficient, obtaining the loss value of the target landslide risk description information under the second pending landslide risk coefficient; the loss function of the loss value of the target landslide risk description information under the key landslide risk coefficient in the key landslide risk coefficient set is greater than the loss function of the loss value of the target landslide risk description information under the non-key landslide risk coefficient in the non-key landslide risk coefficient set;

[0072] Exemplarily, the loss value may be understood as a rate-distortion cost.

[0073] For example, the loss value of the target landslide risk description information under the first pending landslide risk coefficient and the loss value of the target landslide risk description information under the second pending landslide risk coefficient can be obtained. The loss value of the target landslide risk description information under a certain landslide risk coefficient can be referred to as the loss value to which the landslide risk coefficient belongs, or the landslide risk coefficient can be referred to as the landslide risk coefficient to which the loss value belongs.

[0074] Among them, since the critical landslide risk coefficient is a landslide risk coefficient less than 1, when calculating the loss value of the target landslide risk description information under the critical landslide risk coefficient, it is necessary to use the difference method to calculate it. The non-critical landslide risk coefficient is a landslide risk coefficient greater than or equal to 1. The loss function when using the difference method to calculate the loss value is greater than the loss function when not using the difference method to calculate the loss value. Therefore, the loss function when calculating the loss value of the target landslide risk description information under the critical landslide risk coefficient is greater than the loss function when calculating the loss value of the target landslide risk description information under the non-critical landslide risk coefficient.

[0075] The following describes how to calculate the loss value of the target landslide risk description information under the first pending landslide risk coefficient: wherein, the loss value to which a certain landslide risk coefficient belongs is calculated based on the landslide risk safety value and the abnormal value of the target landslide risk description information under the landslide risk coefficient, and one landslide risk coefficient corresponds to one loss value, and one landslide risk coefficient corresponds to one landslide risk safety value and one abnormal value. The above-mentioned landslide risk safety value refers to the data flow per second. The higher the landslide risk safety value, the more detailed the description of the data, the smaller the loss of the data, and the closer the compressed data obtained is to the original data. However, the higher the landslide risk safety value, the larger the storage space is required to store the compressed data. It can be understood that the landslide risk safety value can be used to indicate the degree of compression of the landslide risk description information. The smaller the landslide risk safety value, the greater the degree of compression of the landslide risk description information, indicating that the landslide risk description information is compressed smaller, and the landslide risk description information is compressed smaller, indicating that the amount of data of the compressed landslide risk description information is smaller. The larger the landslide risk safety value is, the smaller the degree of compression of the landslide risk description information is, indicating that the greater the compression of the landslide risk description information is, the greater the data volume of the compressed landslide risk description information is.

[0076] As can be seen from the above, the smaller the landslide risk safety value of the target landslide risk description information is, the larger the abnormal value of the target landslide risk description information is. The larger the landslide risk safety value of the target landslide risk description information is, the smaller the abnormal value of the target landslide risk description information is. The standard for extracting the landslide risk intelligent evaluation result for the target landslide risk description information is to comprehensively measure the landslide risk safety value and abnormal value of the target landslide risk description information under the landslide risk intelligent evaluation result. It is hoped that the landslide risk safety value of the landslide risk description information under the landslide risk intelligent evaluation result is smaller and the abnormal value is smaller. Since the loss value is calculated by the landslide risk safety value and the abnormal value, the landslide risk intelligent evaluation result for the target landslide risk description information is extracted by the loss value to which the landslide risk coefficient belongs, so that the landslide risk intelligent evaluation result for the target landslide risk description information can be extracted by comprehensively considering the landslide risk safety value and the abnormal value.

[0077] Therefore, the landslide risk safety value and abnormal value of the target landslide risk description information under the first pending landslide risk coefficient can be obtained, and the landslide risk safety value of the target landslide risk description information under the first pending landslide risk coefficient can be referred to as the first landslide risk safety value, and the abnormal value of the target landslide risk description information under the first pending landslide risk coefficient can be referred to as the first abnormal value. Among them, the above-mentioned first landslide risk safety value and the first abnormal value are calculated based on the crustal movement vector data of the target landslide risk description information under the first pending landslide risk coefficient. The crustal movement vector data of the target landslide risk description information under the first pending landslide risk coefficient can be referred to as the crustal movement vector data belonging to the first pending landslide risk coefficient.

[0078] Among them, the target landslide risk description information may include several (no less than two) landslide risk description information attributes.

[0079] More, the landslide risk safety value percentage and the abnormal percentage can also be obtained. The landslide risk safety value percentage is used to perform function processing on the landslide risk safety value, and the abnormal percentage is used to perform function processing on the abnormal value. The landslide risk safety value percentage and the abnormal percentage can be set by themselves. Therefore, the landslide risk safety value percentage can be used to perform function processing on the first landslide risk safety value of the above-mentioned target landslide risk description information under the first pending landslide risk coefficient, and a function processing value (i.e., the first landslide risk safety value after function processing, that is, the product between the first landslide risk safety value and the landslide risk safety value percentage) can be obtained. The function processing value can be referred to as the first function processing landslide risk safety value. The abnormal percentage can also be used to perform function processing on the first abnormal value of the above-mentioned target landslide risk description information under the first pending pixel speed, and a function processing value (i.e., the first abnormal value after function processing, that is, the product between the abnormal percentage and the first abnormal value) can be obtained. The function processing value can be referred to as the first function processing abnormal value. The sum of the landslide risk safety value processed by the first function and the abnormal value processed by the first function can be determined as the loss value to which the first undetermined landslide risk coefficient belongs.

[0080] Similarly, the landslide risk safety value of the target landslide risk description information under the second pending landslide risk coefficient and the abnormal value of the target landslide risk description information under the second pending landslide risk coefficient can also be obtained. The landslide risk safety value of the target landslide risk description information under the second pending landslide risk coefficient can be referred to as the second landslide risk safety value, and the abnormal value of the target landslide risk description information under the second pending landslide risk coefficient can be referred to as the second abnormal value. Similarly, the second landslide risk safety value can be processed by function using the above-mentioned landslide risk safety value percentage to obtain a function-processed value (i.e., the second landslide risk safety value after function processing, that is, the product between the second landslide risk safety value and the landslide risk safety value percentage), and the function-processed value can be referred to as the second function-processed landslide risk safety value. The above-mentioned abnormal percentage can also be used to process the second abnormal value to function, and a function-processed value (i.e., the second abnormal value after function processing, that is, the product between the abnormal percentage and the second abnormal value) can be obtained, and the function-processed value can be referred to as the second function-processed abnormal value. The sum of the landslide risk safety value processed by the second function and the abnormal value processed by the second function can be determined as the loss value to which the second pending landslide risk coefficient belongs. If there are several second pending landslide risk coefficients, each pending landslide risk coefficient corresponds to a second landslide risk safety value, a second abnormal value and a loss value.

[0081] Step S104, comparing the numerical difference between the loss value to which the first pending landslide risk coefficient belongs and the loss value to which the second pending landslide risk coefficient belongs, and determining the landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set according to the comparison result;

[0082] Exemplarily, the numerical difference is understood as the difference between the loss values. The difference can describe the corresponding information.

[0083] For example, the numerical difference between the loss value to which the first pending landslide risk coefficient belongs and the loss value to which the second pending landslide risk coefficient belongs can be compared, and a comparison result can be obtained. The comparison result includes a first comparison result and a second comparison result. If the loss value to which the first pending landslide risk coefficient belongs is smaller than the loss value to which the second pending landslide risk coefficient belongs, the first comparison result is obtained. On the contrary, if the loss value to which the first pending landslide risk coefficient belongs is larger than the loss value to which the second pending landslide risk coefficient belongs, the second comparison result is obtained.

[0084] Among them, when the first undetermined landslide risk coefficient and the second undetermined landslide risk coefficient are extracted by the first extraction method in the above step S102, and the comparison result is the above first comparison result, the first undetermined landslide risk coefficient in the key landslide risk coefficient set can be determined as the landslide risk intelligent evaluation result for the target landslide risk description information. When the first undetermined landslide risk coefficient and the second undetermined landslide risk coefficient are extracted by the first extraction method in the above step S102, and the comparison result is the above second comparison result, the non-key landslide risk coefficient with the smallest loss value in the non-key landslide risk coefficient set can be determined as the landslide risk intelligent evaluation result for the target landslide risk description information. In other words, when the first undetermined landslide risk coefficient and the second undetermined landslide risk coefficient are extracted by the first extraction method in the above step S102, the landslide risk coefficient with the smallest loss value in the first undetermined landslide risk coefficient and the second undetermined landslide risk coefficient can be determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

[0085] When the first undetermined landslide risk coefficient and the second undetermined landslide risk coefficient are extracted by the second extraction method in the above step S102, and the comparison result is the above first comparison result, the loss values ​​to which the remaining key landslide risk coefficients in the key landslide risk coefficient set except the first undetermined landslide risk coefficient belong respectively can be calculated. The key landslide risk coefficient with the smallest loss value in the key landslide risk coefficient set can be determined as the landslide risk intelligent evaluation result for the target landslide risk description information. When the first undetermined landslide risk coefficient and the second undetermined landslide risk coefficient are extracted by the second extraction method in the above step S102, and the comparison result is the above second comparison result, the loss values ​​to which the remaining non-key landslide risk coefficients in the non-key landslide risk coefficient set except the second undetermined landslide risk coefficient belong respectively can be calculated. The non-key landslide risk coefficient with the smallest loss value in the non-key landslide risk coefficient set can be determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

[0086] Furthermore, after obtaining the landslide risk intelligent evaluation result for the target landslide risk description information, the target landslide risk description information can be compressed according to the landslide risk intelligent evaluation result. Wherein, the process of the terminal compressing the target landslide risk description information through the landslide risk intelligent evaluation result can be: the crustal movement vector data of the target landslide risk description information under the landslide risk intelligent evaluation result can be obtained. Wherein, the target landslide risk description information can include several (not less than two) landslide risk description information attributes, and the difference between multiple landslide risk description information attributes of the target landslide risk description information can be obtained according to the crustal movement vector data of the target landslide risk description information. The compression of the target landslide risk description information can be achieved according to the difference between multiple landslide risk description information attributes of the target landslide risk description information. The data obtained after compressing the target landslide risk description information can be called compressed data of the target landslide risk description information.

[0087] Furthermore, the compressed data of the target landslide risk description information can be sent to a data processing terminal (can be any one), and the data processing terminal can derive the compressed data after receiving the compressed data of the target landslide risk description information. The data obtained after the data processing terminal derives the compressed data of the target landslide risk description information can be called the derived landslide risk description information of the target landslide risk description information. The data processing terminal can output the derived landslide risk description information in the data display terminal to display the target landslide risk description information to the user. Among them, the derived landslide risk description information has a certain degree of loss compared to the target landslide risk description information, but the degree of loss is guaranteed to be within a reasonable range.

[0088] The present application obtains target landslide risk description information; obtains a first pending landslide risk coefficient from a key landslide risk coefficient set, and obtains a second pending landslide risk coefficient from a non-key landslide risk coefficient set; obtains a loss value of the target landslide risk description information under the first pending landslide risk coefficient, and obtains a loss value of the target landslide risk description information under the second pending landslide risk coefficient; compares the numerical difference between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, and according to the comparison result, determines a landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set. It can be seen that the method proposed in the present application can obtain some key landslide risk coefficients from the key landslide risk coefficient set to be determined as the first pending landslide risk coefficient, and obtain some non-landslide risk coefficients from the non-key landslide risk coefficient set to be determined as the second pending landslide risk coefficient. Subsequently, according to the numerical difference relationship between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, the landslide risk intelligent evaluation result of the target landslide risk description information can be obtained without calculating the loss values ​​belonging to all landslide risk coefficients in the key landslide risk coefficient set and the non-key landslide risk coefficient set. Therefore, the accuracy and reliability of the landslide risk intelligent evaluation result are improved.

[0089] The present application provides a method for extracting a landslide risk coefficient. It describes a method for determining a landslide risk intelligent evaluation result when the first pending landslide risk coefficient and the second pending landslide risk coefficient are extracted by the second extraction method in the above step S102. The method includes:

[0090] Step S301, selecting a key landslide risk coefficient and a non-key landslide risk coefficient, and calculating their loss values;

[0091] For example, any key landslide risk coefficient (i.e., the first pending landslide risk coefficient) and any non-key landslide risk coefficient (i.e., the second pending landslide risk coefficient) can be extracted, and the loss value belonging to the selected key landslide risk coefficient and the loss value belonging to the selected non-key landslide risk coefficient can be calculated.

[0092] Step S302, the loss value of the critical landslide risk coefficient is less than the loss value of the non-critical landslide risk coefficient;

[0093] For example, it can be determined whether the loss value of the selected critical landslide risk coefficient is less than the loss value of the selected non-critical landslide risk coefficient. If so, the following step S303 is executed; if so, the following step S305 is executed.

[0094] Step S303, calculating the loss value of the remaining key landslide risk coefficient;

[0095] For example, the loss values ​​to which the remaining key landslide risk factors except the key landslide risk factor selected in step S301 belong may be calculated.

[0096] Step S304, selecting the accuracy with the smallest loss value from the key landslide risk coefficients and determining it as the final accuracy;

[0097] For example, among all the key landslide risk coefficients, the key landslide risk coefficient with the smallest loss value can be determined as the final accuracy, and the final accuracy is the above-mentioned landslide risk intelligent evaluation result.

[0098] Step S305, calculating the loss value of the remaining non-critical landslide risk coefficient;

[0099] For example, the loss values ​​to which the remaining non-critical landslide risk factors except the non-critical landslide risk factor selected in step S301 belong may be calculated.

[0100] Step S306, selecting the accuracy with the smallest loss value from the non-critical landslide risk coefficients and determining it as the final accuracy;

[0101] For example, among all non-critical landslide risk coefficients, the non-critical landslide risk coefficient with the smallest loss value can be determined as the final accuracy, and the final accuracy is the above-mentioned landslide risk intelligent evaluation result.

[0102] The present application provides a landslide risk intelligent assessment method, which may include:

[0103] Step S201, obtaining target landslide risk description information and a landslide risk coefficient extraction method; the landslide risk coefficient extraction method is a method determined based on the numerical difference relationship between the loss value of the target landslide risk description information under the first pending landslide risk coefficient and the loss value of the target landslide risk description information under the second pending landslide risk coefficient; the first pending landslide risk coefficient is obtained from a critical landslide risk coefficient set; the second pending landslide risk coefficient is obtained from a non-critical landslide risk coefficient set; the loss function of the loss value of the target landslide risk description information under the critical landslide risk coefficient in the critical landslide risk coefficient set is greater than the loss function of the loss value of the target landslide risk description information under the non-critical landslide risk coefficient in the non-critical landslide risk coefficient set;

[0104] Step S202, based on the landslide risk coefficient extraction method, determine the landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set;

[0105] In step S201-step S202, the description of the target landslide risk description information can refer to the description of the target landslide risk description information in the above step S101. The landslide risk coefficient extraction method specifically refers to how to obtain the landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or from the non-key landslide risk coefficient set based on the numerical difference between the loss value to which the first pending landslide risk coefficient belongs and the loss value to which the second pending landslide risk coefficient belongs.

[0106] The general principle of the landslide risk coefficient extraction method is as follows: if the first pending landslide risk coefficient and the second pending landslide risk coefficient are extracted according to the first extraction method in the above step S102, then the landslide risk intelligent evaluation result of the target landslide risk description information is the landslide risk coefficient with the smallest loss value among the first pending landslide risk coefficient and the second pending landslide risk coefficient. If the first pending landslide risk coefficient and the second pending landslide risk coefficient are extracted according to the second extraction method in the above step S102, and the loss value of the first pending landslide risk coefficient is less than the loss value of the second pending landslide risk coefficient, then the landslide risk intelligent evaluation result of the target landslide risk description information is the key landslide risk coefficient with the smallest loss value in the key landslide risk coefficient set. If the first pending landslide risk coefficient and the second pending landslide risk coefficient are extracted according to the second extraction method in the above step S102, and the loss value belonging to the first pending landslide risk coefficient is greater than the loss value belonging to the second pending landslide risk coefficient, then the landslide risk intelligent evaluation result of the target landslide risk description information is the non-critical landslide risk coefficient with the smallest loss value in the non-critical landslide risk coefficient set.

[0107] The present application can obtain a landslide risk intelligent evaluation result for target landslide risk description information according to a landslide risk coefficient extraction method, and during this process, some key landslide risk coefficients can be obtained from a key landslide risk coefficient set to be determined as a first pending landslide risk coefficient, and some non-landslide risk coefficients can be obtained from a non-key landslide risk coefficient set to be determined as a second pending landslide risk coefficient. Subsequently, based on the numerical difference relationship between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, the landslide risk intelligent evaluation result for the target landslide risk description information can be obtained without calculating the loss values ​​belonging to all landslide risk coefficients in the key landslide risk coefficient set and the non-key landslide risk coefficient set, thereby improving the accuracy and reliability of the landslide risk intelligent evaluation result.

[0108] Based on the above, a landslide risk intelligent assessment device is provided, the device comprising:

[0109] An information acquisition module is used to obtain target landslide risk description information;

[0110] A coefficient obtaining module, used for obtaining a first undetermined landslide risk coefficient from a set of key landslide risk coefficients, and obtaining a second undetermined landslide risk coefficient from a set of non-key landslide risk coefficients;

[0111] A loss value module, used to obtain the loss value of the target landslide risk description information under the first pending landslide risk coefficient, and obtain the loss value of the target landslide risk description information under the second pending landslide risk coefficient; the loss function of the loss value of the target landslide risk description information under the key landslide risk coefficient in the key landslide risk coefficient set is greater than the loss function of the loss value of the target landslide risk description information under the non-key landslide risk coefficient in the non-key landslide risk coefficient set;

[0112] The result evaluation module is used to compare the numerical difference between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, and according to the comparison result, determine the landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set.

[0113] On the basis of the above, a landslide risk intelligent assessment system is shown, which includes a processor and a memory communicating with each other, and the processor is used to read a computer program from the memory and execute it to implement the above method.

[0114] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0115] In summary, based on the above scheme, some key landslide risk coefficients can be obtained from the key landslide risk coefficient set to be determined as the first pending landslide risk coefficient, and some non-landslide risk coefficients can be obtained from the non-key landslide risk coefficient set to be determined as the second pending landslide risk coefficient. Subsequently, according to the numerical difference relationship between the loss value belonging to the first pending landslide risk coefficient and the loss value belonging to the second pending landslide risk coefficient, the landslide risk intelligent evaluation result of the target landslide risk description information can be obtained without calculating the loss values ​​belonging to all landslide risk coefficients in the key landslide risk coefficient set and the non-key landslide risk coefficient set. Therefore, the accuracy and reliability of the landslide risk intelligent evaluation result are improved.

[0116] 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 will understand that the above methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as 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 on the 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. 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).

[0117] 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.

Claims

1. A landslide risk intelligent assessment method, characterized in that: The method comprises: Obtain target landslide risk description information; Obtain a first undetermined landslide risk coefficient from a set of key landslide risk coefficients, and obtain a second undetermined landslide risk coefficient from a set of non-key landslide risk coefficients; Obtaining a loss value of the target landslide risk description information under the first undetermined landslide risk coefficient, and obtaining a loss value of the target landslide risk description information under the second undetermined landslide risk coefficient; a loss function of the loss value of the target landslide risk description information under a critical landslide risk coefficient in the critical landslide risk coefficient set is greater than a loss function of the loss value of the target landslide risk description information under a non-critical landslide risk coefficient in the non-critical landslide risk coefficient set; Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, and determining, according to the comparison result, a landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set; The comparison result includes a first comparison result; the comparison is performed by comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, and determining, according to the comparison result, a landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set, including: Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, when it is found that the loss value to which the first undetermined landslide risk coefficient belongs is less than the loss value to which the second undetermined landslide risk coefficient belongs, obtaining the first comparison result; According to the first comparison result, determining the first undetermined landslide risk coefficient in the key landslide risk coefficient set as the landslide risk intelligent evaluation result for the target landslide risk description information; The comparison result includes a second comparison result; the comparison is performed by comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, and determining, according to the comparison result, a landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set, including: Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, when it is found that the loss value to which the first undetermined landslide risk coefficient belongs is greater than the loss value to which the second undetermined landslide risk coefficient belongs, obtaining the second comparison result; According to the second comparison result, the non-critical landslide risk coefficient with the smallest loss value in the non-critical landslide risk coefficient set is determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

2. The method according to claim 1, characterized in that The step of obtaining a first undetermined landslide risk coefficient from a set of key landslide risk coefficients and obtaining a second undetermined landslide risk coefficient from a set of non-key landslide risk coefficients includes: A key landslide risk coefficient is extracted from the key landslide risk coefficient set and determined as the first pending landslide risk coefficient, and all non-key landslide risk coefficients in the non-key landslide risk coefficient set are determined as the second pending landslide risk coefficients.

3. The method according to claim 1, characterized in that: The step of obtaining a first undetermined landslide risk coefficient from a set of key landslide risk coefficients and obtaining a second undetermined landslide risk coefficient from a set of non-key landslide risk coefficients includes: A key landslide risk coefficient is extracted from the key landslide risk coefficient set and determined as the first pending landslide risk coefficient, and a non-key landslide risk coefficient is extracted from the non-key landslide risk coefficient set and determined as the second pending landslide risk coefficient.

4. The method according to claim 3, characterized in that The comparison result includes a first comparison result; the comparison compares the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, and determines, according to the comparison result, a landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set, including: Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, when it is found that the loss value to which the first undetermined landslide risk coefficient belongs is less than the loss value to which the second undetermined landslide risk coefficient belongs, obtaining the first comparison result; According to the first comparison result, obtaining the loss value of the target landslide risk description information under the key landslide risk coefficients in the key landslide risk coefficient set except the first undetermined landslide risk coefficient; The key landslide risk coefficient with the smallest loss value in the key landslide risk coefficient set is determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

5. The method according to claim 3, characterized in that: The comparison result includes a second comparison result; the comparison compares the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, and determines, according to the comparison result, a landslide risk intelligent evaluation result for the target landslide risk description information from the key landslide risk coefficient set or the non-key landslide risk coefficient set, including: Comparing the numerical difference between the loss value to which the first undetermined landslide risk coefficient belongs and the loss value to which the second undetermined landslide risk coefficient belongs, when it is found that the loss value to which the first undetermined landslide risk coefficient belongs is greater than the loss value to which the second undetermined landslide risk coefficient belongs, obtaining the second comparison result; According to the second comparison result, obtaining the loss value of the target landslide risk description information under the key landslide risk coefficients in the non-key landslide risk coefficient set except the second undetermined landslide risk coefficient; The non-critical landslide risk coefficient with the smallest loss value in the non-critical landslide risk coefficient set is determined as the landslide risk intelligent evaluation result for the target landslide risk description information.

6. The method according to claim 1, characterized in that The obtaining of the loss value of the target landslide risk description information under the first undetermined landslide risk coefficient includes: Obtaining a first landslide risk safety value and a first abnormal value of the target landslide risk description information under the first undetermined landslide risk coefficient; obtaining a landslide risk safety value percentage for the first landslide risk safety value and an abnormality percentage for the first abnormal value; Performing function processing on the first landslide risk safety value according to the landslide risk safety value percentage to obtain a first function-processed landslide risk safety value, and performing function processing on the first abnormal value according to the abnormal percentage to obtain a first function-processed abnormal value; According to the landslide risk safety value processed by the first function and the abnormal value processed by the first function, the loss value to which the first undetermined landslide risk coefficient belongs is determined.

7. The method according to claim 1, characterized in that The obtaining of the loss value of the target landslide risk description information under the second undetermined landslide risk coefficient includes: Obtaining a second landslide risk safety value and a second abnormal value of the target landslide risk description information under the second undetermined landslide risk coefficient; obtaining a landslide risk safety value percentage for the second landslide risk safety value and an abnormality percentage for the second abnormal value; Performing function processing on the second landslide risk safety value according to the landslide risk safety value percentage to obtain a second function-processed landslide risk safety value, and performing function processing on the second abnormal value according to the abnormal percentage to obtain a second function-processed abnormal value; Determine the loss value to which the second undetermined landslide risk coefficient belongs according to the second function processing landslide risk safety value and the second function processing abnormal value; Among them, it also includes: Based on the landslide risk intelligent evaluation result, the target landslide risk description information is compressed to obtain compressed data of the target landslide risk description information; sending the compressed data to a data processing terminal, so that the data processing terminal derives the compressed data to obtain derived landslide risk description information corresponding to the target landslide risk description information, and then outputs the derived landslide risk description information in a data display terminal; The target landslide risk description information has no less than two landslide risk description information attributes; the target landslide risk description information is compressed based on the landslide risk intelligent evaluation result to obtain compressed data of the target landslide risk description information, including: Searching for the crustal movement vector data of the target landslide risk description information under the landslide risk intelligent evaluation result; Determining the difference between the at least two landslide risk description information attributes according to the crust movement vector data; According to the difference between the at least two landslide risk description information attributes, the target landslide risk description information is compressed to obtain the compressed data of the target landslide risk description information.

8. A landslide risk intelligent assessment system, 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 7.

Images