Scheduling method, system and equipment for slope monitoring resources and storage medium

Abstract

The invention relates to a side slope monitoring resource scheduling method, system and device and a storage medium, and the scheduling method comprises the steps: firstly constructing a graph structure through a sensor, a monitoring device, a professional and an auxiliary tool based on a space-time condition, then converting a side slope monitoring resource structure graph into a tree structure, and carrying out the scheduling of the side slope monitoring resource. A resource combination scheme is more hierarchical and clearer, a plurality of initial resource combination sequences are obtained, and the initial resource combination sequences are subjected to crossover, variation and fitness learning processing, so that the resource combination sequences are evolved towards targets of stable monitoring quality, strong correlation among resources and low total cost of the resources; a plurality of optimized resource combination sequences are obtained, and the monitoring stability, rationality and economical efficiency of a resource combination scheme are improved; and finally, based on the characteristic information of the slope to be monitored, selecting the optimized resource combination sequence with the maximum matching degree value from the plurality of optimized resource combination sequences, and taking the optimized resource combination sequence as a recommended monitoring scheme of the slope to be monitored, which is high in reasonability and scientificity.

Description

Technical Field

[0001] The present invention relates to the technical field of slope monitoring, and in particular to a method, system, equipment and storage medium for scheduling slope monitoring resources. Background Art

[0002] Slope monitoring is of great significance to engineering construction and operation maintenance, personnel safety protection, property safety protection and environmental protection. The selection of slope monitoring resources directly affects the accuracy of slope monitoring results and affects slope safety. Reasonable scheduling of various slope monitoring resources is a prerequisite for completing high-quality slope monitoring.

[0003] At present, when conducting slope resource scheduling, it is often determined based on manual experience, but manual experience is overly dependent on past experience. When the slope problem is complex or the slope area is large, the manual experience method is often inefficient and the scheduling plan quality is low. Machine learning algorithms can quickly improve computing efficiency, but they require a large amount of training data. When faced with new slope problems, they are prone to lack of explainability and controllability, poor rationality and scientificity, and poor stability in generating scheduling plans. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system, device and storage medium for scheduling slope monitoring resources.

[0005] The technical solution of the present invention is as follows:

[0006] A method for scheduling slope monitoring resources includes the following operations:

[0007] S1. Based on sensors, monitoring equipment, professionals and auxiliary tools, a slope monitoring resource structure diagram is constructed; the nodes in the slope monitoring resource structure diagram are sensors, monitoring equipment, professionals and auxiliary tools. If there is overlap in available time between nodes, the nodes are connected by edges. The edge strength between nodes is obtained based on the spatial distance and the overlap duration of available time;

[0008] S2. Convert the slope monitoring resource structure diagram into a tree structure to obtain a slope monitoring resource structure tree; specifically: treat sensors, monitoring equipment, professionals and auxiliary tools as primary resources, secondary resources, tertiary resources and quaternary resources respectively; randomly combine the nodes in the primary resources to obtain a number of combined nodes; the several combined nodes and the nodes in the primary resources are all used as root nodes, and are connected to the nodes with edge relationships in the secondary resources, tertiary resources and quaternary resources in turn to obtain a slope monitoring resource structure tree; based on the slope monitoring resource structure tree, obtain a number of optimized resource combination sequences; specifically: obtain the nodes from the root node in the slope monitoring resource structure tree; The path from the point to the tail node is obtained to obtain several initial resource combination sequences; the initial resource combination sequence with a fitness greater than the first fitness threshold is used as the initial preferred sequence; all initial preferred sequences form an initial sequence preferred set; the initial resource combination sequence with a fitness not greater than the first fitness threshold is cross-processed to obtain several cross-resource combination sequences; based on the initial sequence preferred set, several cross-resource combination sequences are mutated to obtain several mutated resource combination sequences; the mutated resource combination sequence and the initial sequence preferred set are subjected to fitness learning to obtain several optimized resource combination sequences; the fitness is obtained based on the node cost and the edge strength between nodes;

[0009] S3. Based on the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored, obtain the characteristic vector of the slope to be monitored; obtain the product of the characteristic vectors corresponding to several optimized resource combination sequences and the characteristic vector of the slope to be monitored to obtain several matching degrees; and use the optimized resource combination sequence corresponding to the maximum matching degree as the recommended monitoring plan for the slope to be monitored.

[0010] The edge strength of the corresponding edges between sensor nodes in S1, or / and the edge strength of the corresponding edges between sensor nodes and monitoring device nodes, or / and the edge strength of the corresponding edges between monitoring device nodes, is obtained based on spatial distance, available time overlap duration, functional relevance and historical co-occurrence times; the edge strength of the corresponding edges between sensor nodes or / and monitoring device nodes and professional nodes is obtained based on spatial distance, available time overlap duration, and the dependence of sensors or / and monitoring devices on professionals; the edge strength of the corresponding edges between sensor nodes or / and monitoring device nodes and auxiliary tool nodes is obtained based on spatial distance, available time overlap duration, and the degree of necessity of auxiliary tools to sensors or / and monitoring devices; the edge strength of the corresponding edges between professional nodes is obtained based on spatial distance, available time overlap duration, and historical co-occurrence times; the edge strength of the corresponding edges between professional nodes and auxiliary tool nodes is obtained based on spatial distance, available time overlap duration, and historical co-occurrence times; the edge strength of the corresponding edges between auxiliary tool nodes is obtained based on spatial distance, available time overlap duration, and historical co-occurrence times.

[0011] The specific operations of the crossover processing in S2 are as follows: taking the initial resource combination sequence whose fitness is not greater than the first fitness threshold as the sequence to be crossed; obtaining the maximum fitness value and the minimum fitness value among all the sequences to be crossed; obtaining the crossover probability of each sequence to be crossed based on the maximum fitness value and the minimum fitness value; sorting all the sequences to be crossed in the order of crossover probability from small to large and from large to large to obtain a forward sorted sequence set and a reverse sorted sequence set; exchanging parts of the sequences to be crossed with the same sort number in the forward sorted sequence set and the reverse sorted sequence set to obtain several crossover resource combination sequences.

[0012] The mutation processing operations in S2 are as follows: based on the sensor failure probability, monitoring equipment failure probability, professional error probability and auxiliary tool damage probability, obtain the mutation probability of each cross-resource combination sequence; determine whether the mutation probability of the current cross-resource combination sequence is greater than the mutation probability threshold; if greater, replace the resources at the corresponding position of the non-root node in the current cross-resource combination sequence with the resources in any initial resource combination sequence in the initial sequence optimization set to obtain the current initial mutation sequence; determine whether the weighted difference between the fitness of the initial mutation sequence and the mutation probability is greater than the comprehensive mutation probability threshold; if greater, use the current initial mutation sequence as the current mutation resource combination sequence; if not greater , the current initial mutation sequence performs resource replacement and size judgment operations with the comprehensive mutation probability threshold until the weighted difference between fitness and mutation probability is greater than the comprehensive mutation probability threshold, and the current mutation resource combination sequence is obtained; if not, randomly select an initial resource combination sequence with a fitness greater than the second fitness threshold from the initial sequence optimization set as the target sequence; replace the resources at the corresponding positions of the non-root nodes in the current cross resource combination sequence with any resource in the target sequence to obtain the current mutation resource combination sequence; the second fitness threshold is greater than the first fitness threshold; after all cross resource combination sequences have completed the mutation probability judgment operation, several mutation resource combination sequences are obtained.

[0013] The operations of fitness learning processing in S2 are specifically as follows: the mutated resource combination sequence and the initial sequence optimization set form a sequence set to be learned; the fitness of each sequence to be learned in the sequence set to be learned is obtained, and the sequence to be learned with a fitness greater than the third fitness threshold is used as the target learning sequence, and all target learning sequences form a target learning sequence set; each target learning sequence in the target learning sequence set is processed by a combination of resources of a first fixed length to obtain a number of resource combination fragments; the resource combination fragment corresponding to the maximum fitness value at the same position in the number of resource combination fragments is selected as the target learning resource combination fragment at the corresponding position; each sequence to be learned in the sequence set to be learned is traversed with a sliding window of a first fixed length, and the resource combination fragment corresponding to the minimum fitness value in each sequence to be learned is replaced with the target learning resource combination fragment at the same position to obtain a number of optimized resource combination sequences.

[0014] The fitness in S2 is obtained by the following formula:

[0015]

[0016] F is fitness, E is ij is the edge strength between node i and node j, node i and node j are resources, resources include sensors, monitoring equipment, professionals and auxiliary tools, C s , C m , C p , C a are the sth sensor cost, the mth monitoring equipment cost, the pth professional cost and the ath auxiliary tool cost respectively. S, M, P and A are the total number of sensors, monitoring equipment, professionals and auxiliary tools in the current resource sequence respectively. ε is the compensation amount.

[0017] In S3, if the slope risk value of the slope to be monitored is greater than the risk threshold, the optimized resource combination sequence with a matching degree greater than the matching degree threshold and the smallest duplication with the recommended monitoring scheme is used as a supplementary monitoring scheme for the slope to be monitored, and is used to form an optimal monitoring scheme with the recommended monitoring scheme for the slope to be monitored.

[0018] A scheduling system for slope monitoring resources, used to implement the above-mentioned scheduling method for slope monitoring resources, comprising:

[0019] The slope monitoring resource structure diagram generation module is used to construct a slope monitoring resource structure diagram based on sensors, monitoring equipment, professionals and auxiliary tools. The nodes in the slope monitoring resource structure diagram are sensors, monitoring equipment, professionals and auxiliary tools. If there is overlap in available time between nodes, the nodes are connected by edges. The edge strength between nodes is obtained based on the spatial distance and the overlap duration of available time.

[0020] The optimized resource combination sequence generation module is used to convert the slope monitoring resource structure diagram into a tree structure to obtain a slope monitoring resource structure tree; specifically: sensors, monitoring equipment, professionals and auxiliary tools are respectively used as primary resources, secondary resources, tertiary resources and quaternary resources; after randomly combining the nodes in the primary resources, a number of combination nodes are obtained; a number of combination nodes and nodes in the primary resources are used as root nodes, and are respectively connected to the nodes with edge relationships in the secondary resources, tertiary resources and quaternary resources in turn to obtain a slope monitoring resource structure tree; based on the slope monitoring resource structure tree, a number of optimized resource combination sequences are obtained; specifically: obtain the slope monitoring resource structure tree The path from the root node to the tail node in the paper mulberry tree is used to obtain several initial resource combination sequences; the initial resource combination sequence with a fitness greater than the first fitness threshold is used as the initial preferred sequence; all initial preferred sequences form an initial sequence preferred set; the initial resource combination sequence with a fitness not greater than the first fitness threshold is cross-processed to obtain several cross-resource combination sequences; based on the initial sequence preferred set, several cross-resource combination sequences are mutated to obtain several mutated resource combination sequences; the mutated resource combination sequence and the initial sequence preferred set are subjected to fitness learning to obtain several optimized resource combination sequences; the fitness is obtained based on the node cost and the edge strength between nodes;

[0021] The recommended monitoring scheme generation module is used to obtain the characteristic vector of the slope to be monitored based on the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored; obtain the product of the characteristic vectors corresponding to several optimized resource combination sequences and the characteristic vector of the slope to be monitored to obtain several matching degrees; and use the optimized resource combination sequence corresponding to the maximum matching degree as the recommended monitoring scheme for the slope to be monitored.

[0022] A scheduling device for slope monitoring resources comprises a processor and a memory, wherein the processor implements the above-mentioned scheduling method for slope monitoring resources when executing a computer program stored in the memory.

[0023] A computer-readable storage medium is used to store a computer program, wherein the computer program implements the above-mentioned method for scheduling slope monitoring resources when executed by a processor.

[0024] The beneficial effects of the present invention are:

[0025] The present invention provides a scheduling method for slope monitoring resources. Firstly, based on time and space conditions, currently available sensors, monitoring equipment, professionals and auxiliary tools are constructed into a graph structure to intuitively reflect the distribution of currently available monitoring resources and the correlation between resources; then the slope monitoring resource structure graph is converted into a tree structure, so that the resource combination scheme is more hierarchical and clearer, and a plurality of initial resource combination sequences are obtained. The initial resource combination sequences are subjected to crossover, mutation and fitness learning processing, so that the resource combination sequences evolve toward the goals of stable monitoring quality, strong correlation between resources and low total resource cost, and a plurality of optimized resource combination sequences are obtained, thereby improving the monitoring stability, rationality and economy of the resource combination scheme; finally, based on the characteristic information of the slope to be monitored itself, the optimized resource combination sequence with the largest matching value is selected from a plurality of optimized resource combination sequences as a recommended monitoring scheme for the slope to be monitored with strong rationality and scientificity. DETAILED DESCRIPTION

[0026] This embodiment provides a method for scheduling slope monitoring resources, including the following operations:

[0027] S1. Based on sensors, monitoring equipment, professionals and auxiliary tools, a slope monitoring resource structure diagram is constructed; the nodes in the slope monitoring resource structure diagram are sensors, monitoring equipment, professionals and auxiliary tools. If there is overlap in available time between nodes, the nodes are connected by edges. The edge strength between nodes is obtained based on the spatial distance and the overlap duration of available time;

[0028] S2. Convert the slope monitoring resource structure diagram into a tree structure to obtain a slope monitoring resource structure tree; specifically: treat sensors, monitoring equipment, professionals and auxiliary tools as primary resources, secondary resources, tertiary resources and quaternary resources respectively; randomly combine the nodes in the primary resources to obtain a number of combined nodes; the several combined nodes and the nodes in the primary resources are all used as root nodes, and are connected to the nodes with edge relationships in the secondary resources, tertiary resources and quaternary resources in turn to obtain a slope monitoring resource structure tree; based on the slope monitoring resource structure tree, obtain a number of optimized resource combination sequences; specifically: obtain the nodes from the root node in the slope monitoring resource structure tree; The path from the point to the tail node is obtained to obtain several initial resource combination sequences; the initial resource combination sequence with a fitness greater than the first fitness threshold is used as the initial preferred sequence; all initial preferred sequences form an initial sequence preferred set; the initial resource combination sequence with a fitness not greater than the first fitness threshold is cross-processed to obtain several cross-resource combination sequences; based on the initial sequence preferred set, several cross-resource combination sequences are mutated to obtain several mutated resource combination sequences; the mutated resource combination sequence and the initial sequence preferred set are subjected to fitness learning to obtain several optimized resource combination sequences; the fitness is obtained based on the node cost and the edge strength between nodes;

[0029] S3. Based on the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored, obtain the characteristic vector of the slope to be monitored; obtain the product of the characteristic vectors corresponding to several optimized resource combination sequences and the characteristic vector of the slope to be monitored to obtain several matching degrees; and use the optimized resource combination sequence corresponding to the maximum matching degree as the recommended monitoring plan for the slope to be monitored.

[0030] S1. Based on sensors, monitoring equipment, professionals and auxiliary tools, a slope monitoring resource structure diagram is constructed; the nodes in the slope monitoring resource structure diagram are sensors, monitoring equipment, professionals and auxiliary tools. If there is overlap in the available time between nodes, the nodes are connected by edges. The edge strength between nodes is obtained based on the spatial distance and the overlap duration of the available time.

[0031] Based on the time and space conditions, the currently available sensors, monitoring equipment, professionals and auxiliary tools are constructed into a graph structure to intuitively reflect the distribution of currently available monitoring resources and the correlation between resources (the ease with which resources can be obtained at the same time and the degree of functional connection between resources).

[0032] A slope monitoring resource structure diagram is constructed based on currently available sensors with time and space attributes (sensors that are directly set inside the slope and can directly obtain slope conditions, such as fiber optic displacement sensors, stress sensors, pore water pressure sensors, etc.), monitoring equipment (set outside the slope to obtain slope conditions such as drones, cameras, ground monitoring stations, etc.), professionals (such as geotechnical engineers, surveying engineers, and geological engineers), and auxiliary tools (such as mounting brackets, drilling equipment, anchoring tools, etc.).

[0033] The nodes in the slope monitoring resource structure diagram are sensors, monitoring equipment, professionals and auxiliary tools. If the available time between nodes overlaps, it means that the corresponding resources of the two nodes can be obtained at the same time. In this way, the nodes are connected with edges. In this way, the slope monitoring resources are regarded as a system, which clearly shows the time correlation of different resources and helps to quickly and comprehensively understand the distribution of currently available resources.

[0034] Among them, the edge strength between nodes is obtained based on the spatial distance and the overlap duration of available time. The greater the edge strength, the shorter the edge length, which can intuitively show the difficulty of simultaneously obtaining resources in time and space. The edge strength between resources is defined as follows.

[0035] The edge strength of the corresponding edge between sensor nodes, or / and the edge strength of the corresponding edge between sensor nodes and monitoring device nodes, or / and the edge strength of the corresponding edge between monitoring device nodes, is obtained based on the spatial distance, the length of available time overlap, the functional relevance, and the number of historical co-occurrences. The smaller the spatial distance, the longer the length of available time overlap, the greater the functional relevance, and the greater the number of historical co-occurrences, the greater the edge strength, the greater the correlation between resources, and the less difficult it is to be scheduled simultaneously. The functional relevance is obtained based on the number of overlapping functional keywords between sensors, or / and between sensors and monitoring devices, or / and between monitoring device nodes.

[0036] The edge strength of the corresponding edge between the sensor node or / and monitoring device node and the professional node is obtained based on the spatial distance, the length of the available time overlap, and the dependence of the sensor or / and monitoring device on the professional. The dependence of the sensor or / and monitoring device on the professional is obtained based on the number of historical co-occurrences of the sensor or / and monitoring device and the professional.

[0037] The edge strength of the corresponding edge between the sensor node or / and monitoring device node and the auxiliary tool node is obtained based on the spatial distance, the length of the available time overlap, and the degree of necessity of the auxiliary tool for the sensor or / and monitoring device. The degree of necessity of the auxiliary tool for the sensor or / and monitoring device is obtained based on the number of historical co-occurrences of the auxiliary tool and the sensor or / and monitoring device.

[0038] The edge strength of the corresponding edges between professional nodes is obtained based on the spatial distance, the length of overlap in available time, and the number of historical co-occurrences.

[0039] The edge strength of the corresponding edge between the professional node and the auxiliary tool node is obtained based on the spatial distance, the length of overlap in available time, and the number of historical co-occurrences.

[0040] The edge strength of the corresponding edges between auxiliary tool nodes is obtained based on the spatial distance, the length of available time overlap, and the number of historical co-occurrences.

[0041] S2. Convert the slope monitoring resource structure diagram into a tree structure to obtain a slope monitoring resource structure tree; based on the slope monitoring resource structure tree, obtain a number of optimized resource combination sequences.

[0042] The slope monitoring resource structure diagram is converted into a tree structure, so that the resource combination scheme appears more hierarchical and clearer, and several initial resource combination sequences are obtained; the initial resource combination sequence is processed by crossover, mutation and fitness learning, so that the resource combination sequence evolves towards the goals of stable monitoring quality, strong correlation between resources and low total resource cost, and several optimized resource combination sequences are obtained, which improves the monitoring stability, rationality and economy of the resource combination scheme.

[0043] First, the slope monitoring resource structure diagram is converted into a tree structure to obtain a slope monitoring resource structure tree. In the slope monitoring resource structure tree, the position of each tree node (node / resource) in the tree can reasonably reflect its role in the slope monitoring resource solution system.

[0044] The operation of obtaining the structure tree of slope monitoring resources is as follows: based on the ability of resources to directly and quickly obtain the data of the slope itself, the resources are divided into levels from large to small, and the sensors buried in the slope for monitoring, the monitoring equipment for monitoring the overall situation of the slope at a distance from the slope, the professionals for placing instruments and performing data analysis, and the auxiliary tools for installing or fixing instruments are respectively (divided into) as primary resources, secondary resources, tertiary resources and quaternary resources; the nodes in the primary resources are randomly combined to obtain several combined nodes; the number of nodes (resources) in the combined nodes is different, and can be The number of nodes in the first-level resource is 2 or more, thereby ensuring the richness of resource combination; several combination nodes and nodes in the first-level resource are all used as root nodes, and those resources (secondary resources, tertiary resources and quaternary resources) that indirectly affect the judgment of slope data through other intermediate data can be used as child nodes, and then the root node is connected with the nodes with edge relationships in the second-level resource, the third-level resource and the fourth-level resource in turn, to obtain the slope monitoring resource structure tree; that is, after the root node is connected with several nodes in the second-level resource with which it has an edge relationship, it is connected with several nodes in the third-level resource and the fourth-level resource in turn. When the nodes in the upper-level resource are connected with several nodes in the lower-level resource, they are connected sequentially, that is, the number of inbound and outbound edges of a node is 1. When the nodes in the upper-level resource are connected with several nodes in the lower-level resource, they can randomly not connect with the nodes in the lower-level resource, so as to reduce the number of resources in the resource combination scheme, form a low-cost resource combination scheme, and enrich the resource combination scheme.

[0045] Then, the path from the root node to the tail node in the slope monitoring resource structure tree is obtained to obtain several initial resource combination sequences. The initial resource combination sequence consists of several nodes / resources and edges.

[0046] Subsequently, the initial resource combination sequence with a fitness greater than the first fitness threshold, that is, the initial resource combination sequence with advantages in both cost and correlation between resources, is used as the initial preferred sequence; all initial preferred sequences form an initial sequence preferred set. The fitness is obtained based on the node cost and the edge strength between nodes.

[0047] The above fitness is obtained by the following formula:

[0048]

[0049] F is fitness, E is ij is the edge strength between node i and node j. Node i and node j are resources. Node i and node j can be different resources of different levels or different resources of the same level. Resources include sensors, monitoring equipment, professionals and auxiliary tools. s , C m , C p , C a are the sth sensor cost, the mth monitoring equipment cost, the pth professional cost and the ath auxiliary tool cost respectively. S, M, P and A are the total number of sensors, monitoring equipment, professionals and auxiliary tools in the current resource sequence (including the initial resource combination sequence), respectively. ε is the compensation amount.

[0050] Then, based on the slope monitoring resource structure tree, several optimized resource combination sequences are obtained.

[0051] One method is to obtain the path from the root node to the tail node in the slope monitoring resource structure tree to obtain several initial resource combination sequences; among the several initial resource combination sequences, the initial resource combination sequences whose fitness is greater than the initial fitness threshold are used as optimized resource combination sequences to obtain several optimized resource combination sequences.

[0052] Another method is to obtain the path from the root node to the tail node in the slope monitoring resource structure tree to obtain several initial resource combination sequences in order to obtain a resource combination scheme with stable monitoring quality, strong correlation between resources and low total resource cost.

[0053] In order to improve the diversity of resource combination sequences, the initial resource combination sequences whose fitness is not greater than the first fitness threshold are cross-processed to obtain a plurality of cross-resource combination sequences.

[0054] The specific operation of the crossover processing is as follows: taking the initial resource combination sequence whose fitness is not greater than the first fitness threshold as the sequence to be crossed; obtaining the maximum fitness value and the minimum fitness value among all the sequences to be crossed; obtaining the crossover probability of each sequence to be crossed based on the maximum fitness value and the minimum fitness value; sorting all the sequences to be crossed twice according to the order of crossover probability from small to large and from large to large, to obtain a forward sorted sequence set and a reverse sorted sequence set; exchanging parts of the sequences to be crossed with the same sorting number in the forward sorted sequence set and the reverse sorted sequence set (exchanging the resource combinations after the resources in the same position), so that the two sequences to be crossed with larger and smaller crossover probabilities exchange parts of their resource combinations with each other, balancing the fitness while enriching the diversity of the resource combination sequences, and obtaining several crossover resource combination sequences.

[0055] The above partial sequence exchange is achieved by exchanging the resource combinations at the same positions of the two sequences to be crossed. For example, the sequence to be crossed 1 is sensor a-sensor b-monitoring equipment a-professional a-assistant tool a, and the sequence to be crossed 2 is sensor b-monitoring equipment b-professional b-assistant tool b. After partial sequence exchange (with the third position point as the exchange point), the initial cross resource combination sequence 1 is sensor a-sensor b-professional b-assistant tool b, and the initial cross resource combination sequence 2 is sensor b-monitoring equipment b-monitoring equipment a-professional a-assistant tool a. If there is a situation where there is no edge between resources in the resource sequence after the partial sequence exchange, that is, the resources cannot be used at the same time, then the resources that have not been exchanged will be deleted to obtain a cross-screening resource sequence as a cross-resource combination sequence. For example, in the resource sequence of the above-mentioned initial cross-resource combination sequence 2 sensor b-monitoring device b-monitoring device a-professional a-auxiliary tool a, there is no edge between monitoring device b and monitoring device a, but there is an edge relationship between sensor b and monitoring device a, then the monitoring device b will be deleted, and sensor b will be connected to monitoring device a to obtain the cross-resource combination sequence of sensor b-monitoring device a-professional a-auxiliary tool a.

[0056] The crossover probability of the current sequence to be crossed is the ratio of the difference between the maximum fitness and the fitness of the current sequence to be crossed to the difference between the maximum fitness and the minimum fitness.

[0057] Next, in order to maximize the monitoring quality of resources in the resource combination sequence, make the resource combination in the resource combination sequence not only of high quality but also of strong correlation between resources, and improve the rationality and scientificity of the resource combination sequence, based on the initial sequence optimization set with relatively large fitness, several cross-resource combination sequences are mutated to obtain several mutated resource combination sequences.

[0058] The operation of mutation processing is as follows.

[0059] Based on the probability of sensor failure, monitoring equipment failure, professional error and auxiliary tool damage, the variation probability of each cross-resource combination sequence is obtained. The greater the probability of sensor failure, monitoring equipment failure, professional error and auxiliary tool damage, the more likely the resource combination scheme in the cross-resource combination sequence is to fail during implementation, the monitoring quality is unstable, and the more quality optimization of resource combination is needed, the greater the variation probability. The probability of sensor failure, monitoring equipment failure, professional error and auxiliary tool damage are obtained based on the historical sensor failure frequency and maintenance times, monitoring equipment failure frequency and maintenance times, professional error frequency and length of service, auxiliary tool damage frequency and maintenance times, respectively.

[0060] The mutation probability can be the weighted sum of the sensor failure probability, monitoring equipment failure probability, professional error probability, and auxiliary tool damage probability. It can also be the weighted sum of the monitoring equipment failure probability, professional error probability, auxiliary tool damage probability, and sensor failure probability, considering that the probabilities are independent of each other and use an "or" logical relationship. For example, the sensor failure probability is p 1 , the probability of monitoring equipment failure is p 2 , the probability of professional error is p 3 , the probability of auxiliary tool damage is p 4 , then the mutation probability P = w 1 p 1 +w 2 p 2 +w 3 p 3 +w 4 p 4 , or mutation probability P = w 1 p 1 +w 2 p 2 +w 3 p 3 +w 4 p 4 -w 5 (p 1 p 2 -p 1 p 3 -p 1 p 4 -p 2 p 3 -p 2 p 4 -p 3 p 4 )+w 6 (p 1 p 2 p 3 +p 1 p 2 p 4 +p 2 p 3 p 4 ), w 1 、w 2 、w 3 、w 4 、w 5 、w 6 They are the first weight, the second weight, the third weight, the fourth weight, the fifth weight, and the sixth weight respectively.

[0061] Determine whether the mutation probability of the current cross-resource combination sequence is greater than the mutation probability threshold.

[0062] If it is greater than, it proves that the resource combination scheme in the current cross-resource combination sequence has low monitoring quality and relatively unstable monitoring results when it is subsequently implemented. In order to improve the quality of the resource combination scheme and ensure strong correlation between resources and low total resource cost, the resources at the corresponding positions of the non-root nodes in the current cross-resource combination sequence are replaced with resources in any initial resource combination sequence in the initial sequence optimization set to obtain the current initial mutation sequence; and then the weighted difference between the fitness and mutation probability of the initial mutation sequence is used as the mutation quality after the preliminary mutation; it is judged whether the weighted difference between the fitness and mutation probability of the initial mutation sequence is greater than the comprehensive mutation probability threshold; if it is greater than, it proves that the mutation operation has reached the target state, and the current initial mutation sequence is used as the current mutation resource combination sequence; if it is not greater than, the current initial mutation sequence performs resource replacement at the corresponding position of the non-root node, and performs size judgment operations with the comprehensive mutation probability threshold until the weighted difference between the fitness and mutation probability is greater than the comprehensive mutation probability threshold, the mutation operation reaches the target state, and the resource combination scheme corresponding to the resource sequence satisfies both high combination scheme quality and strong correlation between resources and low total resource cost, and the current mutation resource combination sequence is obtained.

[0063] If it is not greater than, it proves that the resource combination scheme in the current cross-resource combination sequence has higher monitoring quality and more stable monitoring results in subsequent implementation. In order to further improve the correlation between resources and further reduce the total resource cost on the basis of high quality of resource combination schemes, an initial resource combination sequence with a fitness greater than the second fitness threshold is randomly selected from the initial sequence preferred set as the target sequence; the resource at the corresponding position of the non-root node in the current cross-resource combination sequence is replaced by any resource in the target sequence to obtain the current variant resource combination sequence.

[0064] The second fitness threshold is greater than the first fitness threshold.

[0065] After all cross-resource combination sequences have completed the operation of mutation probability judgment, several mutation resource combination sequences are obtained.

[0066] Finally, in order to further improve the fitness of the resource combination scheme in the resource sequence and further reduce the total resource cost on the basis of improving the correlation between resources in the resource sequence, the variant resource combination sequence and the initial sequence optimization set are subjected to fitness learning to obtain several optimized resource combination sequences.

[0067] The operations of fitness learning processing are specifically as follows: the mutated resource combination sequence and the initial sequence optimization set form a sequence set to be learned; the fitness of each sequence to be learned in the sequence set to be learned is obtained, and the sequence to be learned with a fitness greater than a third fitness threshold is used as a target learning sequence, and all target learning sequences form a target learning sequence set; each target learning sequence in the target learning sequence set is subjected to a first fixed-length combined resource segmentation process, and each target learning sequence is segmented into a plurality of resource combination fragments to obtain a plurality of resource combination fragments; the resource combination fragment corresponding to the maximum fitness value at the same position in the plurality of resource combination fragments is selected as the target learning resource combination fragment at the corresponding position; at the same time, each sequence to be learned in the sequence set to be learned is traversed with a first fixed-length sliding window, and the resource combination fragment corresponding to the minimum fitness value in each sequence to be learned is replaced with the target learning resource combination fragment at the same position, and the fitness of each sequence to be learned is further optimized from a local position to obtain a plurality of optimized resource combination sequences.

[0068] S3. Based on the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored, obtain the characteristic vector of the slope to be monitored; obtain the product of the characteristic vectors corresponding to several optimized resource combination sequences and the characteristic vector of the slope to be monitored to obtain several matching degrees; and use the optimized resource combination sequence corresponding to the maximum matching degree as the recommended monitoring plan for the slope to be monitored.

[0069] Based on the characteristic information of the slope to be monitored, the optimized resource combination sequence with the largest matching value is selected from several optimized resource combination sequences as the recommended monitoring scheme for the slope to be monitored, so as to achieve the correspondence, rationality and scientificity of the recommended monitoring scheme.

[0070] Firstly, the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored are spliced ​​and embedded to obtain the characteristic vector of the slope to be monitored.

[0071] At the same time, each optimized resource combination sequence is embedded respectively to obtain an optimized resource combination sequence feature vector of each optimized resource combination sequence.

[0072] Next, the products of the corresponding feature vectors of several optimized resource combination sequences and the feature vector of the slope to be monitored are obtained, that is, the products of the feature vectors of each optimized resource combination sequence and the feature vector of the slope to be monitored are obtained respectively to obtain several matching degrees.

[0073] Finally, the optimized resource combination sequence corresponding to the maximum matching degree is taken as the recommended monitoring plan for the slope to be monitored.

[0074] In addition, if the slope risk value of the slope to be monitored is greater than the risk threshold, the optimized resource combination sequence with a matching degree greater than the matching degree threshold and the smallest duplication with the optimal monitoring scheme will be used as a supplementary monitoring scheme for the slope to be monitored to achieve complementarity with the recommended monitoring scheme, and to form an optimal monitoring scheme with the recommended monitoring scheme for the slope to be monitored, so as to ensure the slope monitoring quality of the slope to be monitored with a larger slope risk value.

[0075] The above slope risk value can be obtained based on the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored; the above repeatability can be obtained based on the number of resource category repetitions and the number of resource repetitions of the two resource combination sequences.

[0076] This embodiment further provides a scheduling system for slope monitoring resources, which is used to implement the above-mentioned scheduling method for slope monitoring resources, including:

[0077] The slope monitoring resource structure diagram generation module is used to construct a slope monitoring resource structure diagram based on sensors, monitoring equipment, professionals and auxiliary tools. The nodes in the slope monitoring resource structure diagram are sensors, monitoring equipment, professionals and auxiliary tools. If there is overlap in available time between nodes, the nodes are connected by edges. The edge strength between nodes is obtained based on the spatial distance and the overlap duration of available time.

[0078] The optimized resource combination sequence generation module is used to convert the slope monitoring resource structure diagram into a tree structure to obtain a slope monitoring resource structure tree; specifically: sensors, monitoring equipment, professionals and auxiliary tools are respectively used as primary resources, secondary resources, tertiary resources and quaternary resources; after randomly combining the nodes in the primary resources, a number of combination nodes are obtained; a number of combination nodes and nodes in the primary resources are used as root nodes, and are respectively connected to the nodes with edge relationships in the secondary resources, tertiary resources and quaternary resources in turn to obtain a slope monitoring resource structure tree; based on the slope monitoring resource structure tree, a number of optimized resource combination sequences are obtained; specifically: obtain the slope monitoring resource structure tree The path from the root node to the tail node in the paper mulberry tree is used to obtain several initial resource combination sequences; the initial resource combination sequence with a fitness greater than the first fitness threshold is used as the initial preferred sequence; all initial preferred sequences form an initial sequence preferred set; the initial resource combination sequence with a fitness not greater than the first fitness threshold is cross-processed to obtain several cross-resource combination sequences; based on the initial sequence preferred set, several cross-resource combination sequences are mutated to obtain several mutated resource combination sequences; the mutated resource combination sequence and the initial sequence preferred set are subjected to fitness learning to obtain several optimized resource combination sequences; the fitness is obtained based on the node cost and the edge strength between nodes;

[0079] The recommended monitoring scheme generation module is used to obtain the characteristic vector of the slope to be monitored based on the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored; obtain the product of the characteristic vectors corresponding to several optimized resource combination sequences and the characteristic vector of the slope to be monitored to obtain several matching degrees; and use the optimized resource combination sequence corresponding to the maximum matching degree as the recommended monitoring scheme for the slope to be monitored.

[0080] This embodiment further provides a scheduling device for slope monitoring resources, including a processor and a memory, wherein the processor implements the above-mentioned scheduling method for slope monitoring resources when executing a computer program stored in the memory.

[0081] This embodiment further provides a computer-readable storage medium for storing a computer program, wherein the computer program implements the above-mentioned method for scheduling slope monitoring resources when executed by a processor.

[0082] The present embodiment provides a method for scheduling slope monitoring resources. First, based on time and space conditions, currently available sensors, monitoring equipment, professionals and auxiliary tools are constructed into a graph structure to intuitively reflect the distribution of currently available monitoring resources and the correlation between resources; then the slope monitoring resource structure graph is converted into a tree structure, so that the resource combination scheme is more hierarchical and clearer, and a number of initial resource combination sequences are obtained. The initial resource combination sequences are crossover, mutation and fitness learning processes are performed to make the resource combination sequences evolve toward the goals of stable monitoring quality, strong correlation between resources and low total resource cost, and a number of optimized resource combination sequences are obtained, thereby improving the monitoring stability, rationality and economy of the resource combination scheme; finally, based on the characteristic information of the slope to be monitored itself, the optimized resource combination sequence with the largest matching value is selected from a number of optimized resource combination sequences as a recommended monitoring scheme for the slope to be monitored with strong rationality and scientificity. The method is applied to slope resource scheduling, and the generated scheme has high quality and good scheme generation stability.

Claims

1. A method for dispatching slope monitoring resources, characterized in that: The following operations are included: S1. Based on sensors, monitoring equipment, professionals and auxiliary tools, a slope monitoring resource structure diagram is constructed; the nodes in the slope monitoring resource structure diagram are sensors, monitoring equipment, professionals and auxiliary tools. If there is overlap in available time between nodes, the nodes are connected by edges. The edge strength between nodes is obtained based on the spatial distance and the overlap duration of available time; S2. Convert the slope monitoring resource structure diagram into a tree structure to obtain a slope monitoring resource structure tree; specifically: treat sensors, monitoring equipment, professionals and auxiliary tools as primary resources, secondary resources, tertiary resources and quaternary resources respectively; randomly combine the nodes in the primary resources to obtain a number of combined nodes; the several combined nodes and the nodes in the primary resources are all used as root nodes, and are connected to the nodes with edge relationships in the secondary resources, tertiary resources and quaternary resources in turn to obtain a slope monitoring resource structure tree; Based on the slope monitoring resource structure tree, several optimized resource combination sequences are obtained; specifically: the path from the root node to the tail node in the slope monitoring resource structure tree is obtained to obtain several initial resource combination sequences; the initial resource combination sequence with a fitness greater than the first fitness threshold is used as the initial preferred sequence; all initial preferred sequences form an initial sequence preferred set; the initial resource combination sequence with a fitness not greater than the first fitness threshold is cross-processed to obtain several cross-resource combination sequences; based on the initial sequence preferred set, several cross-resource combination sequences are mutated to obtain several mutated resource combination sequences; the mutated resource combination sequence and the initial sequence preferred set are subjected to fitness learning to obtain several optimized resource combination sequences; the fitness is obtained based on the node cost and the edge strength between nodes; S3. Based on the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored, obtain the characteristic vector of the slope to be monitored; obtain the product of the characteristic vectors corresponding to several optimized resource combination sequences and the characteristic vector of the slope to be monitored to obtain several matching degrees; and use the optimized resource combination sequence corresponding to the maximum matching degree as the recommended monitoring plan for the slope to be monitored.

2. A method for dispatching slope monitoring resources according to claim 1, characterized in that: In S1, The edge strength of the corresponding edges between sensor nodes, or / and the edge strength of the corresponding edges between sensor nodes and monitoring device nodes, or / and the edge strength of the corresponding edges between monitoring device nodes are obtained based on spatial distance, available time overlap duration, functional relevance, and historical co-occurrence times; The edge strength of the corresponding edge between the sensor node or / and the monitoring device node and the professional node is obtained based on the spatial distance, the length of the available time overlap, and the dependence of the sensor or / and the monitoring device on the professional; The edge strength of the corresponding edge between the sensor node or / and the monitoring device node and the auxiliary tool node is obtained based on the spatial distance, the length of the available time overlap, and the degree of necessity of the auxiliary tool for the sensor or / and the monitoring device; The edge strength of the corresponding edges between professional nodes is obtained based on spatial distance, length of overlap in available time, and number of historical co-occurrences; The edge strength of the corresponding edge between the professional node and the auxiliary tool node is obtained based on the spatial distance, the length of the available time overlap, and the number of historical co-occurrences; The edge strength of the corresponding edges between auxiliary tool nodes is obtained based on the spatial distance, the length of available time overlap, and the number of historical co-occurrences.

3. A method for dispatching slope monitoring resources according to claim 1, characterized in that: In S2, the cross processing operation is specifically as follows: The initial resource combination sequence whose fitness is not greater than the first fitness threshold is used as the sequence to be crossed; the maximum fitness value and the minimum fitness value of all the sequences to be crossed are obtained; Based on the maximum fitness value and the minimum fitness value, the crossover probability of each sequence to be crossed is obtained respectively; according to the order of crossover probability from small to large and from large to large, all the sequences to be crossed are sorted to obtain a forward sorting sequence set and a reverse sorting sequence set; Partial sequence exchange is performed on two to-be-crossed sequences with the same sequence number in the forward sorting sequence set and the reverse sorting sequence set to obtain a plurality of cross-resource combination sequences.

4. A method for dispatching slope monitoring resources according to claim 1, characterized in that: In S2, the operations of the mutation processing are specifically as follows: Based on the probability of sensor failure, monitoring equipment failure, professional error, and auxiliary tool damage, the mutation probability of each cross-resource combination sequence is obtained; Determine whether the mutation probability of the current cross-resource combination sequence is greater than the mutation probability threshold; If it is greater than, replace the resource at the corresponding position of the non-root node in the current cross resource combination sequence with the resource in any initial resource combination sequence in the initial sequence optimization set to obtain the current initial mutation sequence; determine whether the weighted difference between the fitness and mutation probability of the initial mutation sequence is greater than the comprehensive mutation probability threshold; if it is greater than, use the current initial mutation sequence as the current mutation resource combination sequence; if it is not greater than, perform resource replacement and size judgment with the comprehensive mutation probability threshold on the current initial mutation sequence until the weighted difference between the fitness and mutation probability is greater than the comprehensive mutation probability threshold to obtain the current mutation resource combination sequence; If not, randomly select an initial resource combination sequence with a fitness greater than the second fitness threshold from the initial sequence optimization set as the target sequence; replace the resource at the corresponding position of the non-root node in the current cross resource combination sequence with any resource in the target sequence to obtain the current variant resource combination sequence; the second fitness threshold is greater than the first fitness threshold; After all cross-resource combination sequences have completed the operation of mutation probability judgment, several mutation resource combination sequences are obtained.

5. The method for dispatching slope monitoring resources according to claim 1, characterized in that: In S2, the operations of the fitness learning process are specifically as follows: The mutated resource combination sequence and the initial sequence optimization set form a sequence set to be learned; the fitness of each sequence to be learned in the sequence set to be learned is obtained, and the sequence to be learned whose fitness is greater than the third fitness threshold is used as the target learning sequence, and all target learning sequences form a target learning sequence set; Each target learning sequence in the target learning sequence set is processed by the combined resource segmentation of the first fixed length to obtain a plurality of resource combination fragments; the resource combination fragment corresponding to the maximum fitness value at the same position in the plurality of resource combination fragments is selected as the target learning resource combination fragment at the corresponding position; Each sequence to be learned in the sequence set to be learned is traversed with a sliding window of a first fixed length, and the resource combination fragment corresponding to the minimum fitness value in each sequence to be learned is replaced with the target learning resource combination fragment at the same position to obtain several optimized resource combination sequences.

6. A method for dispatching slope monitoring resources according to claim 1, characterized in that: In S2, the fitness is obtained by the following formula: F is fitness, E is ij is the edge strength between node i and node j, node i and node j are resources, resources include sensors, monitoring equipment, professionals and auxiliary tools, C s , C m , C p , C a are the sth sensor cost, the mth monitoring equipment cost, the pth professional cost and the ath auxiliary tool cost respectively. S, M, P and A are the total number of sensors, monitoring equipment, professionals and auxiliary tools in the current resource sequence respectively. ε is the compensation amount.

7. The method for dispatching slope monitoring resources according to claim 1, characterized in that: In S3, if the slope risk value of the slope to be monitored is greater than the risk threshold, the optimized resource combination sequence with a matching degree greater than the matching degree threshold and the smallest repetition with the recommended monitoring plan is used as a supplementary monitoring plan for the slope to be monitored, to form an optimal monitoring plan with the recommended monitoring plan for the slope to be monitored.

8. A scheduling system for slope monitoring resources, used to implement the scheduling method for slope monitoring resources according to claim 1, characterized in that: include: The slope monitoring resource structure diagram generation module is used to construct the slope monitoring resource structure diagram based on sensors, monitoring equipment, professionals and auxiliary tools; The nodes in the slope monitoring resource structure diagram are sensors, monitoring equipment, professionals and auxiliary tools. If there is overlap in available time between nodes, the nodes are connected by edges. The edge strength between nodes is obtained based on the spatial distance and the overlap duration of available time. The optimized resource combination sequence generation module is used to convert the slope monitoring resource structure diagram into a tree structure to obtain a slope monitoring resource structure tree; specifically: sensors, monitoring equipment, professionals and auxiliary tools are respectively used as primary resources, secondary resources, tertiary resources and quaternary resources; after randomly combining the nodes in the primary resources, a number of combination nodes are obtained; a number of combination nodes and nodes in the primary resources are used as root nodes, and are respectively connected to the nodes with edge relationships in the secondary resources, tertiary resources and quaternary resources in turn to obtain a slope monitoring resource structure tree; based on the slope monitoring resource structure tree, a number of optimized resource combination sequences are obtained; specifically: obtain the slope monitoring resource structure tree The path from the root node to the tail node in the paper mulberry tree is used to obtain several initial resource combination sequences; the initial resource combination sequence with a fitness greater than the first fitness threshold is used as the initial preferred sequence; all initial preferred sequences form an initial sequence preferred set; the initial resource combination sequence with a fitness not greater than the first fitness threshold is cross-processed to obtain several cross-resource combination sequences; based on the initial sequence preferred set, several cross-resource combination sequences are mutated to obtain several mutated resource combination sequences; the mutated resource combination sequence and the initial sequence preferred set are subjected to fitness learning to obtain several optimized resource combination sequences; the fitness is obtained based on the node cost and the edge strength between nodes; The recommended monitoring scheme generation module is used to obtain the characteristic vector of the slope to be monitored based on the slope height, slope angle, rock and soil properties, groundwater information, and crack development information of the slope to be monitored; obtain the product of the characteristic vectors corresponding to several optimized resource combination sequences and the characteristic vector of the slope to be monitored to obtain several matching degrees; and use the optimized resource combination sequence corresponding to the maximum matching degree as the recommended monitoring scheme for the slope to be monitored.

9. A dispatching device for slope monitoring resources, characterized in that: The method comprises a processor and a memory, wherein the processor implements the method for scheduling slope monitoring resources as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the scheduling method for slope monitoring resources according to any one of claims 1 to 7 is implemented.

Images