Mountain slope collapse treatment scheme generation method and device and related equipment

Abstract

The application relates to the technical field of geological disaster prevention, and discloses a mountain slope collapse treatment scheme generation method and device and related equipment. The method comprises the following steps: obtaining historical visual data of a mountain slope collapse site; processing the historical visual data through a visual analysis model to obtain first collapse factor data and first collapse factor proportion data; matching a first collapse treatment scheme according to the first collapse factor data and the first collapse factor proportion data; sending the first collapse factor data, the first collapse factor proportion data and the first collapse treatment scheme to a trained mountain slope collapse treatment scheme analysis model to obtain corresponding comprehensive effect data; and setting the first collapse treatment scheme as a target mountain slope collapse treatment scheme corresponding to the mountain slope collapse site when the comprehensive effect data is greater than preset comprehensive effect threshold data. Through the above method, the efficiency and reliability of generating a mountain slope collapse treatment scheme are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of geological disaster prevention, and particularly relates to a mountain slope collapse treatment scheme generation method, device, equipment and storage medium. BACKGROUND

[0002] Mountain slope collapse refers to the phenomenon that the mountain slope or slope foot is damaged, displaced or collapsed due to the action of various factors such as geology, climate and human factors, resulting in the downward movement of soil, gravel and the like on the slope surface. This phenomenon is widespread in areas with complex geological structure and variable climate, such as mountainous areas and hilly regions. Mountain slope collapse poses a serious threat to the surrounding environment, human life and property safety. Mountain slope collapse can cause various serious hazards, and may result in casualties, especially in densely populated areas such as mountainous settlements and tourist attractions. Once a collapse accident occurs, it often results in heavy casualties. Mudslides, landslides and other phenomena caused by collapse can cause damage to infrastructure, houses, farmland and other properties, resulting in huge property losses. Mountain slope collapse can also cause soil erosion, vegetation damage, water and soil loss, and other problems, thereby disrupting the ecological balance and affecting the stability and sustainability of the ecological environment. In addition, mountain slope collapse often leads to road and railway interruptions, affecting transportation and causing inconvenience to local economic development and personnel exchanges. Moreover, the large amount of soil and rock material after the collapse will be lost with rainwater, causing soil and water loss, and further affecting the fertility and productivity of the land. In the traditional mountain slope collapse treatment scheme generation process, relevant data of the collapse site need to be collected in advance, and then the relevant data are analyzed according to the previous manual treatment experience to develop corresponding preliminary treatment measures. On the one hand, the efficiency of analyzing the relevant collapse data according to the manual treatment experience is low. On the other hand, the preliminary treatment scheme in the mountain slope collapse treatment process also usually relies on manual experience. However, due to the subjectivity of human beings, the accuracy of the treatment scheme of the slope collapse accident obtained by relying on manual experience cannot be effectively guaranteed, and therefore the effect of the treatment scheme needs to be evaluated. However, the existing technology does not have a reliable comprehensive evaluation, and therefore a treatment scheme with high reliability cannot be obtained. SUMMARY

[0003] The technical problem solved by the embodiments of the present application is that the traditional mountain slope collapse treatment scheme generation method has low efficiency in generating the treatment scheme, and the reliability of the obtained treatment scheme is low.

[0004] To solve the above technical problems, the first technical solution adopted by the embodiments of the present application is to provide a mountain slope collapse management scheme generation method, comprising: obtaining historical visual data of a mountain slope collapse site; processing the historical visual data of the mountain slope collapse site through a pre-trained visual analysis model to obtain first collapse factor data corresponding to the mountain slope collapse site and first collapse factor proportion data corresponding to the first collapse factor data; matching a corresponding first collapse management scheme according to the first collapse factor data and the first collapse factor proportion data; sending the first collapse factor data, the first collapse factor proportion data, and the first collapse management scheme to a trained mountain slope collapse management scheme analysis model to obtain comprehensive effect data corresponding to the first collapse management scheme; and setting the first collapse management scheme as a target mountain slope collapse management scheme corresponding to the mountain slope collapse site if the comprehensive effect data is greater than a preset comprehensive effect threshold data.

[0005] Optionally, the training step of the mountain slope collapse management scheme analysis model comprises: obtaining historical data of mountain slope collapse accidents, analyzing the historical data of mountain slope collapse to obtain second collapse factor data and first collapse factor correlation data corresponding to the second collapse factor data; obtaining historical data of mountain slope collapse management schemes, analyzing the historical data of mountain slope collapse management schemes to obtain first collapse management factor data and first collapse management effect data corresponding to the first collapse management factor data; obtaining first collapse management factor correlation action data corresponding to the first collapse management factor data, and establishing a management effect correlation relationship between the first collapse management factor correlation action data and the first collapse management effect data; sending the second collapse factor data, the first collapse factor correlation data, the first collapse management factor data, the first collapse management effect data, the first collapse management factor correlation action data, and the management effect correlation relationship to a pre-constructed initial mountain slope collapse management scheme analysis model for model training to obtain a trained mountain slope collapse management scheme analysis model, wherein the initial mountain slope collapse management scheme analysis model is constructed through the historical data of mountain slope collapse accidents and the historical data of mountain slope collapse management schemes.

[0006] Optionally, the step of processing the historical visual data of the mountain slope by the pre-trained visual analysis model to obtain the first collapse factor data corresponding to the collapse location of the mountain slope and the first collapse factor proportion data corresponding to the first collapse factor data comprises: obtaining historical visual data of a mountain slope collapse location, wherein the historical visual data comprises historical video data and historical picture data; analyzing the historical video data and the historical picture data to obtain different collapse factor sample data corresponding to the historical video data and the historical picture data, and different collapse factor proportion sample data corresponding to the collapse factor sample data; training a pre-created initial visual analysis model by using the collapse factor sample data and the collapse factor proportion sample data to obtain the trained visual analysis model; and inputting the historical visual data of the mountain slope into the trained visual analysis model to obtain the first collapse factor data and the first collapse factor proportion data.

[0007] Optionally, the step of sending the first collapse factor data, the first collapse factor proportion data and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model to obtain the comprehensive effect data corresponding to the first collapse treatment scheme comprises: obtaining second collapse factor correlation data of a mountain slope collapse location according to the first collapse factor data; sending the first collapse factor data, the first collapse factor proportion data, the second collapse factor correlation data and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model; and receiving the comprehensive treatment effect data returned by the mountain slope collapse treatment scheme analysis model.

[0008] Optionally, after the step of receiving the comprehensive management effect data returned by the mountain slope collapse management scheme analysis model, the method further comprises: determining whether each item of management effect data in the comprehensive management effect data is within a preset management effect data threshold range; if at least one item of target management effect data in the comprehensive management effect data is not within the corresponding management effect data threshold range, optimizing at least one first collapse factor data corresponding to the target management effect data and the first collapse factor proportion data corresponding to the first collapse factor data; updating the second collapse factor correlation data and the first collapse management scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data; re-executing the step of sending the first collapse factor data, the first collapse factor proportion data, the second collapse factor correlation data and the first collapse management scheme to the trained mountain slope collapse management scheme analysis model to the step of updating the second collapse factor correlation data and the first collapse management scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data until each item of management effect data in the comprehensive management effect data corresponding to the optimized first collapse management scheme is within the preset management effect data threshold range.

[0009] Optionally, the step of matching the corresponding first collapse management scheme according to the first collapse factor data and the first collapse factor proportion data comprises: obtaining historical mountain slope collapse management scheme data, analyzing the historical mountain slope collapse management scheme data to obtain corresponding second collapse management factor data and second collapse management effect data corresponding to the second collapse management factor data; combining the first collapse factor data and the first collapse factor proportion data into a corresponding collapse factor data pair, and combining the second collapse management factor data and the second collapse management effect data into a corresponding collapse management factor data pair; calculating a data matching degree percentage between the collapse factor data pair and the collapse management factor data pair according to a preset collapse factor data and collapse management factor correspondence table; if the data matching degree percentage is within a preset data matching degree percentage threshold range, setting the historical mountain slope collapse management scheme data corresponding to the maximum data matching degree percentage as the first collapse management scheme.

[0010] Optionally, after the step of setting the first collapse control scheme as the target mountain slope collapse control scheme corresponding to the mountain slope collapse site, the method further comprises: obtaining actual collapse control effect data after implementation of the target mountain slope collapse control scheme; and optimizing the mountain slope collapse control scheme analysis model and the corresponding relationship table of the collapse factor data and the collapse control factor based on the target mountain slope collapse control scheme and the actual collapse control effect data.

[0011] To solve the above technical problems, a second technical solution adopted by the embodiments of the present application is to provide a mountain slope collapse control scheme generation device, comprising: a historical visual data module configured to obtain mountain slope historical visual data of a mountain slope collapse site; a collapse factor data module configured to process the mountain slope historical visual data by a pre-trained visual analysis model to obtain first collapse factor data corresponding to the mountain slope collapse site and first collapse factor proportion data corresponding to the first collapse factor data; a control scheme matching module configured to match a corresponding first collapse control scheme based on the first collapse factor data and the first collapse factor proportion data; a comprehensive effect data module configured to send the first collapse factor data, the first collapse factor proportion data, and the first collapse control scheme to a trained mountain slope collapse control scheme analysis model to obtain comprehensive effect data corresponding to the first collapse control scheme; and a collapse control scheme module configured to set the first collapse control scheme as a target mountain slope collapse control scheme corresponding to the mountain slope collapse site if the comprehensive effect data is greater than preset comprehensive effect threshold data.

[0012] To solve the above technical problems, a third technical solution adopted by the embodiments of the present application is to provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the mountain slope collapse control scheme generation method as described above.

[0013] To solve the above technical problems, a third technical solution adopted by the embodiments of the present application is to provide a non-volatile computer readable storage medium, characterized in that the non-volatile computer readable storage medium stores computer executable instructions, and when the computer executable instructions are executed by an electronic device, the electronic device performs the mountain slope collapse control scheme generation method as described above.

[0014] Differently from the related art, the mountain slope collapse treatment scheme generation method provided by the present application can obtain historical visual data of a mountain slope collapse site and process the data through a pre-trained visual analysis model, so that first collapse factor data and proportion data thereof can be accurately obtained, which helps to quickly and comprehensively identify key factors leading to mountain slope collapse and relative importance thereof from an intuitive visual perspective. According to the accurate collapse factor data and proportion data, a corresponding first collapse treatment scheme is matched, compared with a traditional experience-based or general treatment scheme selection, the matching degree of the treatment scheme and the actual collapse condition is greatly improved, and the time and cost for screening and formulating the treatment scheme are saved. The collapse factor data, the proportion data and the treatment scheme are sent to the trained analysis model to obtain comprehensive effect data, so that the implementation effect of the treatment scheme can be scientifically and quantitatively predicted and evaluated, so that the decision maker can understand the possible effectiveness of the scheme before actually implementing the treatment scheme, and make preparation for adjustment in advance. A preset comprehensive effect threshold data is set, and the comprehensive effect data output by the model is compared with the threshold data. Only when the comprehensive effect data is greater than the threshold, the target treatment scheme is determined, so that the finally selected treatment scheme has high effectiveness and reliability, and can effectively solve the problem of mountain slope collapse and protect the surrounding environment and personnel safety. The whole generation method continuously accumulates data and experience, and with more historical visual data of mountain slopes being included in the analysis and continuous feedback and adjustment of the model in actual application, the collapse factor analysis, treatment scheme matching and effect evaluation and other links can be continuously optimized. BRIEF DESCRIPTION OF DRAWINGS

[0015] One or more embodiments are illustrated by way of example with reference to the accompanying drawings, which are schematic and not intended to be limiting of the embodiments, and in which like reference numerals designate similar items in the figures, in which:

[0016] Figure 1 is a schematic diagram of a running environment of a mountain slope collapse treatment scheme generation method provided by an embodiment of the present application.

[0017] Figure 2 is a schematic diagram of an execution flow of a mountain slope collapse treatment scheme generation method provided by an embodiment of the present application.

[0018] Figure 3 is a schematic diagram of an execution flow of a mountain slope collapse treatment scheme generation method provided by an embodiment of the present application.

[0019] Figure 4 is a schematic diagram of an execution flow of a mountain slope collapse treatment scheme generation method provided by an embodiment of the present application.

[0020] Figure 5is an execution flow diagram for obtaining comprehensive effect data corresponding to the first collapse treatment scheme in the mountain slope collapse treatment scheme generation method provided by the embodiment of the present application.

[0021] Figure 6 is an execution flow diagram for a training process of a mountain slope collapse treatment scheme analysis model in the mountain slope collapse treatment scheme generation method provided by the embodiment of the present application.

[0022] Figure 7 is a system structure diagram of the mountain slope collapse treatment scheme generation device provided by the embodiment of the present application.

[0023] Figure 8 is a hardware structure diagram of an electronic device for executing the mountain slope collapse treatment scheme generation method provided by the embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0025] It should be noted that, unless conflicting, each feature in the embodiments of the present application can be combined with each other, and all within the protection scope of the present application. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device schematic diagram or the order in the flowchart.

[0026] Unless otherwise defined, all technical and scientific terms used in the present application have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The term "and / or" used in the present application includes any and all combinations of one or more related listed items.

[0027] In order to facilitate the understanding of the present embodiment, first, a mountain slope collapse treatment scheme generation method disclosed by the embodiment of the present application is introduced in detail, please refer to Figure 1 , Figure 1 is a running environment diagram of the mountain slope collapse treatment scheme generation method provided by the embodiment of the present application, such as Figure 1As shown, the execution subject of the slope collapse treatment scheme generation method provided in this application embodiment is generally an electronic device with a certain computing power, such as a computer. In some possible implementations, the slope collapse treatment scheme generation method can be implemented by a processor calling computer-readable instructions stored in memory. Figure 1 The computer equipment mentioned can be a server. A server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. This can be understood as... Figure 1 The number of computer devices shown is merely illustrative and can be expanded in any number according to actual needs.

[0028] Please continue reading. Figure 2 , Figure 2 This is a schematic diagram of the execution flow of the method for generating a slope collapse treatment scheme provided in this application embodiment, as shown below. Figure 2 As shown, it includes the following steps:

[0029] S1. Obtain historical visual data of the mountain slope at the location of the landslide.

[0030] Among them, from the perspective of classification of data processing types, mountain slope history visual data can be divided into mountain slope history image data and mountain slope history video data. First, mountain slope history image and mountain slope history video data can provide intuitive geological information changes and clearly show the geomorphic change of the mountain slope in the past period of time. For example, by comparing the photos of several years ago and the recent video, it can be found that the increase and decrease of the vegetation coverage on the surface of the mountain, the change of the weathering degree of the rock, etc. These intuitive information helps to determine whether the mountain slope is in a slow natural erosion process or has changed rapidly due to recent human activities or special geological events (such as earthquakes, heavy rains, etc.). Second, mountain slope history image and mountain slope history video data can assist in analyzing the collapse reasons (such as natural factors and human factors). Historical video and image data can record the response of the mountain slope under different climate conditions. For example, by watching the video during the heavy rain period in the past years, it can be observed that the degree of rainwater erosion on the mountain slope, whether there are signs of debris flow formation, etc. Historical images may show geological structure information such as faults and folds inside the mountain. For example, a historical geological exploration image shows that there is a hidden fault under the mountain slope, and the rock around the fault gradually deforms under the action of gravity over time. The influence of human activities on the stability of the mountain slope can also be analyzed through historical data. For example, historical images and videos can record engineering construction activities near the mountain slope, such as road construction, house building, mining, etc. If new cracks and rock loosening phenomena appear in the mountain after a large-scale blasting operation near the mountain slope is observed in the video, it can be determined that the blasting is a human factor that leads to the decrease of the stability of the mountain slope.

[0031] S2, processing the mountain slope history visual data through the pre-trained visual analysis model to obtain first collapse factor data corresponding to the mountain slope collapse site and first collapse factor proportion data corresponding to the first collapse factor data.

[0032] Among them, it needs to be specially pointed out that when the above historical visual data cannot obtain corresponding collapse factors, other data forms of collapse associated data (such as collapse accident investigation report text data about the accident collapse site, conference audio data about the collapse accident, etc.) can be obtained for extracting collapse factor data.

[0033] As an optional implementation, please continue to refer to Figure 3 , Figure 3 is the execution process schematic diagram of obtaining collapse factors in the mountain slope collapse treatment scheme generation method provided by the embodiment of the application, and specifically includes the following steps S21 to S24.

[0034] S21, acquire historical visual data of mountain slope collapse sites, wherein the historical visual data comprises historical video data and historical picture data.

[0035] S22, analyze the historical video data and the historical picture data to obtain different collapse factor sample data corresponding to the historical video data and the historical picture data, and different collapse factor proportion sample data corresponding to the collapse factor sample data.

[0036] The factors affecting the collapse of various types of mountain slopes can be of various types, such as geological factors, topographical factors, meteorological factors, hydrological factors, and vegetation factors. Under various factors, there are different factors, such as rock-soil factor, geological structure factor, and earthquake activity factor under geological factor, slope and slope height factor, and slope surface form factor under topographical factor, rainfall factor and snow factor under meteorological factor, river erosion factor and groundwater activity factor under hydrological factor, and vegetation coverage factor and vegetation root factor under vegetation factor.

[0037] S23, train the pre-created initial visual analysis model by using the collapse factor sample data and the collapse factor proportion sample data to obtain a trained visual analysis model.

[0038] S24, input the historical visual data of the mountain slope into the trained visual analysis model to obtain first collapse factor data and first collapse factor proportion data.

[0039] The collapse factor data and the proportion data provide a quantitative basis for the collapse risk assessment of the mountain slope, and the collapse factor proportion data can guide the development of the management scheme, making the management measures more targeted. For the collapse factors with high proportion, appropriate management techniques are adopted, for example, if the rock-soil type factor has high proportion and the rock-soil of the mountain slope is loose sand, the management scheme can focus on using geotextile reinforcement and grouting to improve the strength and stability of the rock-soil. In addition, during the management process, the collapse factor data and the proportion data can be used to predict the effect of the management measures. By comparing the changes of the collapse factor data before and after the management and considering the adjustment of the proportion of each factor, it can be evaluated whether the management measures effectively reduce the risk of mountain slope collapse, for example, after the drainage management of a mountain slope affected by groundwater activity (high proportion), the change of the groundwater level (collapse factor data) is monitored, and the influence of the groundwater factor on the collapse is re-evaluated. If the groundwater level decreases significantly and the influence of the proportion of the collapse decreases, it can be preliminarily judged that the management measures are effective.

[0040] S3, match a corresponding first collapse management scheme according to the first collapse factor data and the first collapse factor proportion data.

[0041] As an optional implementation, please continue to refer to Figure 4 , Figure 4 is a matching corresponding first collapse control scheme execution process schematic diagram in a mountain slope collapse control scheme generation method provided by the embodiment of the application, and specifically includes the following steps S31 to S34.

[0042] S31, obtain historical mountain slope collapse control scheme data, analyze the historical mountain slope collapse control scheme data to obtain corresponding second collapse control factor data, and second collapse control effect data corresponding to the second collapse control factor data.

[0043] For example, the control factor can be an engineering measure factor, such as an anchoring factor, a retaining wall factor, etc., can also be a vegetation restoration factor, such as a plant species factor, a planting density factor, etc., and can also be a drainage factor, such as a surface drainage factor, an underground drainage factor, etc. The collapse control effect data corresponding to the collapse control factor can be stability index data, such as displacement data of the mountain slope, anti-slide stability coefficient, etc., and can also be environmental index data, such as vegetation coverage data, soil erosion amount data, etc. In a slope control project of a large hydropower engineering, a combination of multiple control measures is adopted, the displacement rate of the slope before control is fast, reaching 5-8 mm per month, and the displacement rate gradually decreases after control, and is stabilized at 0.5-1 mm per month after half a year, indicating that the slope stability has been greatly improved. For example, in some soil slope control, the anti-slide stability coefficient before control is 1.05, in a critical stable state, after implementing control measures (such as reinforced soil technology and drainage measures), the anti-slide stability coefficient is increased to 1.30, meeting the slope stability requirement, proving that the control measures effectively improve the anti-slide ability of the slope.

[0044] S32, combine the first collapse factor data and the first collapse factor proportion data to obtain a corresponding collapse factor data pair, and combine the second collapse control factor data and the second collapse control effect data to obtain a corresponding collapse control factor data pair.

[0045] In the actual implementation process, the collapse factors with different proportions need corresponding collapse management factors, because the collapse management effects of different collapse management factors are not completely the same (the implementation cost and difficulty also need to be considered). For example, in the management of a mountain slope where rainfall is the main collapse factor (accounting for 40%), it is very important to improve the drainage system. In the management of a mountain slope along a highway in a southern area, due to the large and concentrated annual rainfall, rainwater erosion and penetration are the main inducements for slope collapse, and the management scheme focuses on the construction of surface and underground drainage systems, including the installation of a water interception ditch on the slope top and drainage holes and blind trenches on the slope surface. The construction cost of the drainage system is relatively moderate, mainly including material procurement and labor costs. In terms of implementation difficulty, the surface drainage system is relatively simple to construct, but it is necessary to ensure that the drainage slope is reasonable and smooth. The underground drainage system is more difficult to construct, and it is necessary to accurately determine the position and depth of the drainage holes and blind trenches to avoid excessive disturbance to the slope rock mass. In terms of management effect, in the rainy season, the slope with a perfect drainage system has a slope surface runoff reduction of about 40%, effectively reducing the erosion of rainwater on the slope, and the slope displacement is also significantly reduced, ensuring the stability of the slope.

[0046] S33, calculating the data matching percentage between the collapse factor data pair and the collapse management factor data pair according to the preset collapse factor data and collapse management factor correspondence table.

[0047] S34, if the data matching percentage is within the preset data matching percentage threshold range, setting the historical mountain slope collapse management scheme data corresponding to the maximum data matching percentage as the first collapse management scheme.

[0048] It needs to be specially pointed out that if the corresponding first collapse management scheme cannot be obtained according to the data matching percentage threshold range, the historical mountain slope collapse management scheme data with a higher matching degree can also be used as a management scheme template, and the management factor data in the template is adjusted on the basis of the management scheme template, so that the newly generated first collapse management scheme can meet the requirements of the above-mentioned data matching percentage threshold.

[0049] For example, after evaluating the collapse risk of a certain mountain slope, it was found that the existing data matching degree could not directly correspond to the existing first collapse control scheme. After analysis, the slope gradient of the slope is 55°, the rock-soil type is silty clay, the annual rainfall is about 1000mm, and the vegetation coverage is only 15%. When referring to the historical mountain slope collapse control scheme data, a similar historical case was found, whose control scheme is as follows: the slope gradient of the historical case is 60°, the rock-soil is loose sand, the annual rainfall is 800mm, and the vegetation coverage is 10%. The control scheme mainly adopts slope cutting and load reduction (reducing the slope to 45°), grouting reinforcement for sand, and a small amount of vegetation restoration (soil spraying). On the basis of the historical mountain slope collapse control scheme, a new first collapse control scheme is generated, the slope cutting and load reduction: the slope gradient is reduced from 55° to 50°, the excavation sequence and method are reasonably planned to ensure construction safety, and the excavated earth and stone are properly handled and transported to the designated place for stacking or used for other filling engineering. Grouting reinforcement: for silty clay, cement slurry with special additives is used for grouting. The grouting pressure is controlled within a suitable range (such as 0.3-0.5MPa), and the appropriate grouting amount (about 0.2-0.3 cubic meters per cubic meter of soil) is determined according to the calculation to ensure that the slurry fully fills the soil pores and improves the cohesion and internal friction angle of the soil. Vegetation restoration: adopt soil spraying technology, select plant seeds suitable for humid environment, reduce the amount of water retaining agent, and strengthen maintenance and management after spraying, regularly water and fertilize to ensure normal growth of vegetation, and the goal is to increase the vegetation coverage to more than 50% within one year.

[0050] S4, sending the first collapse factor data, the first collapse factor proportion data, and the first collapse control scheme to the trained mountain slope collapse control scheme analysis model to obtain comprehensive effect data corresponding to the first collapse control scheme.

[0051] As a preferred embodiment, please continue to refer to Figure 5 , Figure 5 is the execution flow diagram of obtaining comprehensive effect data corresponding to the first collapse control scheme in the mountain slope collapse control scheme generation method provided by the embodiment of the present application, and specifically includes the following steps S41 to S43.

[0052] S41, obtaining second collapse factor correlation data of the mountain slope collapse site according to the first collapse factor data.

[0053] For example, in terms of geology-related collapse factors, geotechnical mechanical parameter data and geological structure data can be used as collapse factor correlation data; in terms of topography-related collapse factors, slope geometry data and topography relative position data can be used as collapse factor correlation data; in terms of meteorological and hydrological-related collapse factors, rainfall data and rainfall intensity data and vegetation-related collapse factor correlation data can be used as collapse factor correlation data. For example, in terms of geotechnical mechanical parameter data, cohesion, internal friction angle, elastic modulus and other parameters, the mechanical parameters of different rock-soil types differ greatly. The cohesion and internal friction angle of hard and complete rock are high, while the cohesion of loose sand is low and the internal friction angle is relatively small. Through indoor soil test and in-situ test, these data can be obtained to quantitatively evaluate the stability of rock-soil mass and further determine the possibility of collapse under the action of gravity and external force.

[0054] S42, sending the first collapse factor data, the first collapse factor proportion data, the second collapse factor correlation data and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model.

[0055] S43, receiving the comprehensive treatment effect data returned by the mountain slope collapse treatment scheme analysis model.

[0056] As another preferred embodiment, after the above step S43, the following steps S44 to S48 can also be included.

[0057] S44, determining whether each item of treatment effect data in the comprehensive treatment effect data is within the preset treatment effect data threshold range.

[0058] S45, if at least one target treatment effect data in the comprehensive treatment effect data is not within the corresponding treatment effect data threshold range, optimizing at least one first collapse factor data corresponding to the target treatment effect data and the first collapse factor proportion data corresponding to the first collapse factor data.

[0059] S46, updating the second collapse factor correlation data and the first collapse treatment scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data.

[0060] S47, re-executing the steps between the above S42 to S46 until each item of treatment effect data in the comprehensive treatment effect data corresponding to the optimized first collapse treatment scheme is within the preset treatment effect data threshold range.

[0061] The design of the governance effect data threshold range is to ensure that the generated slope collapse governance scheme can achieve the expected governance effect, such as indicating that the governance measures are effectively implemented, ensuring the stability of the slope, and providing a basis for long-term maintenance. Specifically, the governance effect data within the preset threshold range directly indicates that the governance measures are effectively implemented according to the plan, achieving the expected preliminary effect, meaning that there are no major mistakes in engineering construction, technical application, etc., and the execution of the governance scheme is reliable. The preset threshold is usually set based on the previous risk assessment, and when the governance effect data meets the threshold range, it verifies that the methods, models and factors considered in the previous risk assessment are reasonable and accurate, providing a reliable reference for the risk assessment of subsequent similar projects.

[0062] S5, if the comprehensive effect data is greater than the preset comprehensive effect threshold data, set the first collapse governance scheme as the target mountain slope collapse governance scheme corresponding to the mountain slope collapse site.

[0063] As a preferred embodiment, after the above step S5, actual collapse governance effect data after implementation of the target mountain slope collapse governance scheme can also be obtained; through the target mountain slope collapse governance scheme and the corresponding actual collapse governance effect data, the mountain slope collapse governance scheme analysis model and the corresponding relationship table of the collapse factor data and the collapse governance factor are optimized.

[0064] As another preferred embodiment, please continue to refer to Figure 6 , Figure 6 is the training process execution flowchart of the mountain slope collapse governance scheme analysis model in the mountain slope collapse governance scheme generation method provided by the embodiment of the present application, and specifically includes the following steps S61 to S64.

[0065] S61, obtain mountain slope collapse accident history data, analyze the mountain slope collapse history data to obtain second collapse factor data, and first collapse factor correlation data corresponding to the second collapse factor data.

[0066] S62, obtain mountain slope collapse governance scheme history data, analyze the mountain slope collapse governance scheme history data to obtain first collapse governance factor data, and first collapse governance effect data corresponding to the first collapse governance factor data.

[0067] S63, obtain first collapse governance factor correlation action data corresponding to the first collapse governance factor data, and establish a governance effect correlation relationship between the first collapse governance factor correlation action data and the first collapse governance effect data.

[0068] S64, send the second collapse factor data, the first collapse factor correlation data, the first collapse management factor data, the first collapse management effect data, the first collapse management factor correlation effect data and the management effect correlation relationship to the pre-constructed initial mountain slope collapse management scheme analysis model for model training, to obtain the trained mountain slope collapse management scheme analysis model. Wherein, the initial mountain slope collapse management scheme analysis model is constructed by mountain slope collapse accident historical data and mountain slope collapse management scheme historical data.

[0069] Wherein, the mountain slope collapse management scheme analysis model obtained through the training process of the above mountain slope collapse management scheme analysis model, not only can deeply understand the collapse cause, optimize the management scheme formulation, and clear the factor action mechanism, but also can improve the prediction accuracy of the analysis model, and promote the improvement of the management effect and technology. For example, through the analysis of a large number of historical data and model training, the shortcomings of existing management scheme and technology can be found, so as to provide direction for the innovation of management technology, and new management factor or management factor combination may be found, to promote the continuous progress of mountain slope collapse management technology. Specifically, in the process of analyzing historical data, it is found that the traditional vegetation slope protection technology is not good in some complex geological conditions. Based on this, researchers can explore innovative management methods combined with new materials or biological technology, such as using plant varieties with special root system or developing new soil conditioner to improve the effect of vegetation slope protection.

[0070] The mountain slope collapse management scheme generation method provided by the embodiment of the present application can obtain the historical visual data of the mountain slope collapse site and process the data through the pre-trained visual analysis model, so that the first collapse factor data and the proportion data thereof can be accurately obtained, which helps to quickly and comprehensively identify the key factors causing the mountain slope collapse and the relative importance thereof from the intuitive visual angle. According to the accurate collapse factor data and the proportion data thereof, the corresponding first collapse management scheme is matched, which greatly improves the matching degree of the management scheme and the actual collapse condition compared with the traditional experience type or general type management scheme selection, and saves the time and cost of screening and formulating the management scheme. The collapse factor data, the proportion data and the management scheme are sent to the trained analysis model to obtain the comprehensive effect data, so that the implementation effect of the management scheme can be scientifically and quantitatively predicted and evaluated, so that the decision maker can understand the possible effectiveness of the scheme before the actual implementation of the management scheme, and make preparation for adjustment in advance. The preset comprehensive effect threshold data is set, and the comprehensive effect data output by the model is compared with the threshold data. Only when the comprehensive effect data is greater than the threshold data, the target management scheme is determined, so that the finally selected management scheme has high effectiveness and reliability, and can effectively solve the problem of mountain slope collapse and protect the surrounding environment and personnel safety. The whole generation method process continuously accumulates data and experience. With more historical visual data of mountain slopes being included in the analysis and the continuous feedback and adjustment of the model in the actual application, the collapse factor analysis, management scheme matching and effect evaluation and other links can be continuously optimized.

[0071] Please continue to refer to Figure 7 , Figure 7 The system structure diagram of the mountain slope collapse management scheme generation device provided by the embodiment of the present application is shown in Figure 7 The mountain slope collapse management scheme generation device 70 includes a historical visual data module 71, a collapse factor data module 72, a management scheme matching module 73, a comprehensive effect data module 74 and a collapse management scheme module 75.

[0072] The historical visual data module 71 is configured to obtain the historical visual data of the mountain slope of the mountain slope collapse site.

[0073] The collapse factor data module 72 is configured to process the historical visual data of the mountain slope through the pre-trained visual analysis model, obtain the first collapse factor data corresponding to the mountain slope collapse site, and obtain the first collapse factor proportion data corresponding to the first collapse factor data.

[0074] The management scheme matching module 73 is configured to match the corresponding first collapse management scheme according to the first collapse factor data and the first collapse factor proportion data.

[0075] The comprehensive effect data module 74 is configured to send the first collapse factor data, the first collapse factor proportion data, and the first collapse management scheme to the trained mountain slope collapse management scheme analysis model to obtain the comprehensive effect data corresponding to the first collapse management scheme.

[0076] The collapse management scheme module 75 is configured to set the first collapse management scheme as the target mountain slope collapse management scheme corresponding to the mountain slope collapse site if the comprehensive effect data is greater than the preset comprehensive effect threshold data.

[0077] As an optional implementation, the mountain slope collapse management scheme generation device 70 further comprises an analysis model training module, which is specifically configured to obtain historical mountain slope collapse accident data, analyze the historical mountain slope collapse data to obtain second collapse factor data and first collapse factor correlation data corresponding to the second collapse factor data; obtain historical mountain slope collapse management scheme data, analyze the historical mountain slope collapse management scheme data to obtain first collapse management factor data and first collapse management effect data corresponding to the first collapse management factor data; obtain first collapse management factor correlation action data corresponding to the first collapse management factor data, and establish a management effect correlation relationship between the first collapse management factor correlation action data and the first collapse management effect data; send the second collapse factor data, the first collapse factor correlation data, the first collapse management factor data, the first collapse management effect data, the first collapse management factor correlation action data, and the management effect correlation relationship to a pre-created initial mountain slope collapse management scheme analysis model for model training to obtain a trained mountain slope collapse management scheme analysis model, wherein the initial mountain slope collapse management scheme analysis model is constructed by the historical mountain slope collapse accident data and the historical mountain slope collapse management scheme data.

[0078] As an optional implementation, the collapse factor data module 72 is specifically configured to obtain historical mountain slope historical visual data of a mountain slope collapse site, wherein the historical visual data comprises historical video data and historical picture data; analyze the historical video data and historical picture data to obtain different collapse factor sample data corresponding to the historical video data and historical picture data, and different collapse factor proportion sample data corresponding to the collapse factor sample data; train a pre-created initial visual analysis model by using the collapse factor sample data and the collapse factor proportion sample data to obtain a trained visual analysis model; and input the historical mountain slope visual data into the trained visual analysis model to obtain the first collapse factor data and the first collapse factor proportion data.

[0079] As an optional implementation, the comprehensive effect data module 74 is specifically configured to obtain second collapse factor correlation data of a mountain slope collapse site according to the first collapse factor data; send the first collapse factor data, the first collapse factor proportion data, the second collapse factor correlation data and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model; and receive the comprehensive treatment effect data returned by the mountain slope collapse treatment scheme analysis model.

[0080] As an optional implementation, the comprehensive effect data module 74 is further specifically configured to determine whether each item of the comprehensive treatment effect data is within a preset treatment effect data threshold range; if at least one target treatment effect data in the comprehensive treatment effect data is not within the corresponding treatment effect data threshold range, optimize at least one first collapse factor data corresponding to the target treatment effect data and the first collapse factor proportion data corresponding to the first collapse factor data; update the second collapse factor correlation data and the first collapse treatment scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data; and perform the steps from sending the first collapse factor data, the first collapse factor proportion data, the second collapse factor correlation data and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model to updating the second collapse factor correlation data and the first collapse treatment scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data again until each item of the comprehensive treatment effect data corresponding to the optimized first collapse treatment scheme is within the preset treatment effect data threshold range.

[0081] As an optional implementation, the treatment scheme matching module 73 is specifically configured to obtain historical mountain slope collapse treatment scheme data, analyze the historical mountain slope collapse treatment scheme data to obtain corresponding second collapse treatment factor data and second collapse treatment effect data corresponding to the second collapse treatment factor data; combine the first collapse factor data and the first collapse factor proportion data into a corresponding collapse factor data pair, and combine the second collapse treatment factor data and the second collapse treatment effect data into a corresponding collapse treatment factor data pair; calculate a data matching degree percentage between the collapse factor data pair and the collapse treatment factor data pair according to a preset collapse factor data and collapse treatment factor correspondence table; and if the data matching degree percentage is within a preset data matching degree percentage threshold range, set the historical mountain slope collapse treatment scheme data corresponding to the maximum data matching degree percentage as the first collapse treatment scheme.

[0082] As an optional implementation, the collapse management scheme module 75 is further configured to acquire actual collapse management effect data after implementation of the target mountain slope collapse management scheme; and optimize the mountain slope collapse management scheme analysis model and the corresponding relationship table between the collapse factor data and the collapse management factor based on the target mountain slope collapse management scheme and the actual collapse management effect data.

[0083] It should be noted that the mountain slope collapse management scheme generation apparatus can execute the mountain slope collapse management scheme generation method provided in the embodiments of the present application, and has the corresponding function modules and advantages of the execution method. Technical details not described in detail in the embodiment of the mountain slope collapse management scheme generation apparatus can be referred to the mountain slope collapse management scheme generation method provided in the embodiments of the present application.

[0084] Please continue to refer to Figure 8 , Figure 8 is a hardware structure schematic diagram of an electronic device 800 for executing the mountain slope collapse management scheme generation method provided in the embodiments of the present application, as shown in Figure 8 , the electronic device 800 comprises:

[0085] one or more processors 810 and memories 820, Figure 8 for example, taking one processor 810 as an example.

[0086] The processor 810 and the memory 820 can be connected through a bus or other means, Figure 8 for example, taking the connection through the bus as an example.

[0087] The memory 820 is a non-volatile computer readable storage medium, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the mountain slope collapse management scheme generation method in the embodiments of the present application. The processor 810 executes various function applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 820, that is, realizes the mountain slope collapse management scheme generation method of the above method embodiment.

[0088] The memory 820 can include a program storage area and a data storage area, where the program storage area can store an operating system, at least one application required by the mountain slope collapse treatment scheme generation apparatus; and the data storage area can store data created according to the use of the mountain slope collapse treatment scheme generation apparatus, and the like. In addition, the memory 820 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some embodiments, the memory 820 can optionally include a memory disposed remotely with respect to the processor 810, which can be connected to the mountain slope collapse treatment scheme generation apparatus through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0089] The one or more modules are stored in the memory 820, and when executed by the one or more processors 810, perform the mountain slope collapse treatment scheme generation method in any of the above method embodiments, for example, perform the method steps S1 to S5 in the above description of Figure 2 , the method steps S21 to S24 in Figure 3 , the method steps S31 to S34 in Figure 4 , the method steps S41 to S43 in Figure 5 , the method steps S61 to S64 in Figure 6 , to achieve the functions of the modules 71-75 in Figure 7 .

[0090] The above product can perform the method provided by the embodiments of the present application, and has the corresponding function modules and beneficial effects of performing the method. Technical details not described in detail in the embodiments can be referred to the method provided by the embodiments of the present application.

[0091] The embodiments of the present application provide a non-volatile computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are executed by one or more processors, for example, one processor 810 in Figure 8 , so that the above one or more processors can perform the mountain slope collapse treatment scheme generation method in any of the above method embodiments, for example, perform the method steps S1 to S5 in the above description of Figure 2 , the method steps S21 to S24 in Figure 3 , the method steps S31 to S34 in Figure 4 , the method steps S41 to S43 in Figure 5 , the method steps S61 to S64 in Figure 6 , to achieve the functions of the modules 71-75 in Figure 7 .

[0092] The embodiment of the present application provides a computer program product, the computer program product comprises a computer program stored on a non-volatile computer readable storage medium, the computer program comprises program instructions, when the program instructions are executed by the electronic device, the electronic device can execute the mountain slope collapse treatment scheme generation method in any method embodiment described above, for example, execute the method steps S1 to S5 in the method steps S1 to S5, Figure 2 The method steps S21 to S24 in the method steps S21 to S24, Figure 3 The method steps S31 to S34 in the method steps S31 to S34, Figure 4 The method steps S41 to S43 in the method steps S41 to S43, Figure 5 The method steps S61 to S64 in the method steps S61 to S64, and the functions of the modules 71-75 in the modules 71-75 are implemented. Figure 6 Figure 7 The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0093] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus a general hardware platform, and of course, can also be realized by hardware. Those skilled in the art can understand that all or part of the processes in the above embodiment methods can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium, and when the program is executed, the processes of the above embodiments can be included. Wherein, the storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM) and the like.

[0094] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus a general hardware platform, and of course, can also be realized by hardware. Those skilled in the art can understand that all or part of the processes in the above embodiment methods can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium, and when the program is executed, the processes of the above embodiments can be included. Wherein, the storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM) and the like.

[0095] ​Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit them; under the idea of the present application, the technical features in the above examples or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of different aspects of the present application as described above, which are not provided in details for simplicity; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating a slope collapse treatment plan, characterized in that, include: Obtain historical visual data of the mountain slope at the site of the landslide; The historical visual data of the mountain slope is processed by a pre-trained visual analysis model to obtain the first collapse factor data corresponding to the collapse location of the mountain slope, and the first collapse factor proportion data corresponding to the first collapse factor data. Match the corresponding first collapse mitigation scheme based on the first collapse factor data and the first collapse factor weight data; Send the first collapse factor data, the first collapse factor weight data, and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model to obtain the comprehensive effect data corresponding to the first collapse treatment scheme. If the comprehensive effect data is greater than the preset comprehensive effect threshold data, the first collapse treatment scheme is set as the target mountain slope collapse treatment scheme corresponding to the mountain slope collapse location; The step of sending the first collapse factor data, the first collapse factor proportion data, and the first collapse mitigation scheme to the trained slope collapse mitigation scheme analysis model to obtain the comprehensive effect data corresponding to the first collapse mitigation scheme includes: obtaining second collapse factor correlation data of the slope collapse location based on the first collapse factor data; sending the first collapse factor data, the first collapse factor proportion data, the second collapse factor correlation data, and the first collapse mitigation scheme to the trained slope collapse mitigation scheme analysis model; receiving the comprehensive mitigation effect data returned by the slope collapse mitigation scheme analysis model; determining whether each mitigation effect data in the comprehensive mitigation effect data is within a preset mitigation effect data threshold range; if at least one target mitigation effect data in the comprehensive mitigation effect data is not within the corresponding mitigation effect data threshold range, optimizing the target mitigation effect data. The process involves: obtaining at least one first collapse factor data corresponding to the standard treatment effect data, and the first collapse factor proportion data corresponding to the first collapse factor data; updating the second collapse factor association data and the first collapse treatment scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data; re-executing the steps between sending the first collapse factor data, the first collapse factor proportion data, the second collapse factor association data, and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model and updating the second collapse factor association data and the first collapse treatment scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data, until each treatment effect data in the comprehensive treatment effect data corresponding to the optimized first collapse treatment scheme is within the preset treatment effect data threshold range; The step of processing historical visual data of the mountain slope using a pre-trained visual analysis model to obtain first collapse factor data corresponding to the mountain slope collapse location and first collapse factor weight data corresponding to the first collapse factor data includes: acquiring historical visual data of the mountain slope at historical collapse locations, wherein the historical visual data includes historical video data and historical image data; parsing the historical video data and historical image data to obtain different collapse factor sample data corresponding to the historical video data and historical image data, and different collapse factor weight sample data corresponding to the collapse factor sample data; training a pre-created initial visual analysis model using the collapse factor sample data and the collapse factor weight sample data to obtain the trained visual analysis model; and inputting the historical visual data of the mountain slope into the trained visual analysis model to obtain the first collapse factor data and the first collapse factor weight data. The training steps of the analysis model for slope collapse treatment schemes include: acquiring historical data of slope collapse accidents, parsing the historical data of slope collapse accidents to obtain second collapse factor data, and first collapse factor correlation data corresponding to the second collapse factor data; acquiring historical data of slope collapse treatment schemes, parsing the historical data of slope collapse treatment schemes to obtain first collapse treatment factor data, and first collapse treatment effect data corresponding to the first collapse treatment factor data; acquiring first collapse treatment factor correlation data corresponding to the first collapse treatment factor data, and establishing the first collapse treatment factor correlation data. The correlation between the sub-correlation data and the first landslide treatment effect data is established; the second landslide factor data, the first landslide factor correlation data, the first landslide treatment factor data, the first landslide treatment effect data, the first landslide treatment factor correlation data, and the treatment effect correlation are sent to a pre-constructed initial mountain slope landslide treatment scheme analysis model for model training, thereby obtaining a trained mountain slope landslide treatment scheme analysis model. The initial mountain slope landslide treatment scheme analysis model is constructed using the historical data of mountain slope landslide accidents and the historical data of mountain slope landslide treatment schemes. The step of matching the first landslide treatment scheme according to the first landslide factor data and the first landslide factor proportion data includes: acquiring historical mountain slope landslide treatment scheme data; parsing the historical mountain slope landslide treatment scheme data to obtain corresponding second landslide treatment factor data and second landslide treatment effect data corresponding to the second landslide treatment factor data; combining the first landslide factor data and the first landslide factor proportion data into corresponding landslide factor data pairs, and combining the second landslide treatment factor data and the second landslide treatment effect data into corresponding landslide treatment factor data pairs; calculating the data matching percentage between the landslide factor data pairs and the landslide treatment factor data pairs according to a preset landslide factor data and landslide treatment factor correspondence table; if the data matching percentage is within a preset data matching percentage threshold range, then setting the historical mountain slope landslide treatment scheme data corresponding to the largest data matching percentage as the first landslide treatment scheme.

2. The method for generating a slope collapse treatment plan according to claim 1, characterized in that, After the step of setting the first landslide treatment plan as the target landslide treatment plan corresponding to the landslide location, the method further includes: Obtain data on the actual collapse control effect after the implementation of the target mountain slope collapse control scheme; Based on the target slope collapse treatment plan and the corresponding actual collapse treatment effect data, the analysis model of the slope collapse treatment plan and the correspondence table between the collapse factor data and the collapse treatment factor are optimized.

3. A device for generating a slope collapse treatment plan, characterized in that, include: The historical visual data module is used to acquire historical visual data of the mountain slopes at the locations of landslides. The collapse factor data module is used to process the historical visual data of the mountain slope through a pre-trained visual analysis model to obtain the first collapse factor data corresponding to the collapse location of the mountain slope, and the first collapse factor weight data corresponding to the first collapse factor data. The governance scheme matching module is used to match the corresponding first collapse governance scheme based on the first collapse factor data and the first collapse factor proportion data. The comprehensive effect data module is used to send the first collapse factor data, the first collapse factor proportion data and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model to obtain the comprehensive effect data corresponding to the first collapse treatment scheme. The landslide management scheme module is used to set the first landslide management scheme as the target landslide management scheme corresponding to the landslide location when the comprehensive effect data is greater than the preset comprehensive effect threshold data. The analysis model training module is specifically used to acquire historical data on slope collapse accidents, parse the historical data to obtain second collapse factor data, and corresponding first collapse factor correlation data; acquire historical data on slope collapse remediation schemes, parse the historical data to obtain first collapse remediation factor data, and corresponding first collapse remediation effect data; acquire first collapse remediation factor correlation data corresponding to the first collapse remediation factor data, and establish a remediation effect correlation between the first collapse remediation factor correlation data and the first collapse remediation effect data; The second collapse factor data, the first collapse factor correlation data, the first collapse treatment factor data, the first collapse treatment effect data, the first collapse treatment factor correlation data, and the treatment effect correlation relationship are sent to a pre-constructed initial mountain slope collapse treatment scheme analysis model for model training, thereby obtaining a trained mountain slope collapse treatment scheme analysis model. The initial mountain slope collapse treatment scheme analysis model is constructed using the historical data of mountain slope collapse accidents and the historical data of mountain slope collapse treatment schemes. Specifically, the collapse factor data module is used to acquire historical visual data of mountain slopes at historical collapse sites, including historical video data and historical image data; parse the historical video data and historical image data to obtain different collapse factor sample data and different collapse factor proportion sample data corresponding to the historical video data and historical image data; train a pre-created initial visual analysis model using the collapse factor sample data and the collapse factor proportion sample data to obtain the trained visual analysis model; input the historical visual data of the mountain slopes into the trained visual analysis model to obtain the first collapse factor data and the first collapse factor proportion data; Specifically, the comprehensive effect data module is used to obtain the second collapse factor correlation data of the mountain slope collapse site based on the first collapse factor data; send the first collapse factor data, the first collapse factor proportion data, the second collapse factor correlation data, and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model; and receive the comprehensive treatment effect data returned by the mountain slope collapse treatment scheme analysis model. Specifically, the comprehensive effect data module is further used to determine whether each treatment effect data in the comprehensive treatment effect data is within a preset treatment effect data threshold range; if at least one target treatment effect data in the comprehensive treatment effect data is not within the corresponding treatment effect data threshold range, optimize at least one first collapse factor data corresponding to the target treatment effect data and the first collapse factor proportion data corresponding to the first collapse factor data; update the second collapse factor association data and the first collapse treatment scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data; re-execute the steps between sending the first collapse factor data, the first collapse factor proportion data, the second collapse factor association data and the first collapse treatment scheme to the trained mountain slope collapse treatment scheme analysis model and updating the second collapse factor association data and the first collapse treatment scheme according to the optimized first collapse factor data and the corresponding first collapse factor proportion data, until each treatment effect data in the comprehensive treatment effect data corresponding to the optimized first collapse treatment scheme is within the preset treatment effect data threshold range; Specifically, the governance scheme matching module is used to acquire historical slope collapse governance scheme data, parse the historical slope collapse governance scheme data to obtain corresponding second collapse governance factor data, and second collapse governance effect data corresponding to the second collapse governance factor data; combine the first collapse factor data and the first collapse factor proportion data into corresponding collapse factor data pairs, and combine the second collapse governance factor data and the second collapse governance effect data into corresponding collapse governance factor data pairs; calculate the data matching percentage between the collapse factor data pairs and the collapse governance factor data pairs according to a preset collapse factor data and collapse governance factor correspondence table; if the data matching percentage is within a preset data matching percentage threshold range, then set the historical slope collapse governance scheme data corresponding to the largest data matching percentage as the first collapse governance scheme.

4. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method for generating a slope collapse control scheme according to any one of claims 1-2.

5. A non-volatile computer-readable storage medium, characterized in that, The non-volatile computer-readable storage medium stores computer-executable instructions, which, when executed by an electronic device, cause the electronic device to perform the method for generating a slope collapse control scheme as described in any one of claims 1-2.

Images