57 results about "Pheromone matrix" patented technology

The invention discloses a mobile robot path planning method based on an ant colony algorithm under a dynamic environment. The method comprises the following steps of 1, modeling the environment by using a grating method; 2, building local diffusion information pheromone tau''rs; 4, computing a transition probability; 5, adding a feasible node S into a tabu table; 6, completing paths; 7, acquiringthe shortest path via path information recorded in the tabu table; 8, updating pheromone matrix elements; and 9, finding the optimal path via iteration, that is to say an algorithm ending condition ismet, and outputting a final result. According to the ant colony algorithm based on a potential field method provided by the invention, the faster convergence speed and optimizing ability are provided, the local diffusion information pheromone has relative good smoothness, the collaboration ability of individual ants is further enhanced, the local cross paths are reduced, the quantity of lost antsis reduced, and thus the ant colony algorithm is converged to the global optimum with the faster speed, and meanwhile also achieves the diversity of learning, and the defect that an artificial potential field method is easy to trap in the local optimum is overcome.

The invention discloses a container goods placing method based on an improved ant colony algorithm and a heuristic algorithm. The method comprises the following steps that information of goods to be loaded and container space information are initialized; an ant colony, goods loading chain information of each ant and pheromone information are initialized; goods selection probability is generated by a current ant according to the iterations of a current ant colony algorithm and the maximum iteration, and a heuristic goods selection mode or an ant colony goods selection mode is chosen according to a roulette mode; if the heuristic mode is chosen, goods loaded on the left and the rear of the current space and the current space to be loaded are taken into consideration, and proper goods are selected from selected goods to be loaded and are loaded in a recursion mode; if the ant colony goods selection mode is chosen, a pheromone matrix is inquired, and goods are loaded in the roulette mode; the optimal placing posture of the chosen goods is chosen in a backtracking mode.

The invention discloses a search method for relevance feedback images based on an ant colony algorithm and a probability hypergraph, which comprises a training stage and a search stage. The training stage comprises the following steps of extracting low-level features of images, studying a dictionary and performing the high level representation of the images in a library image. The search stage comprises the following steps of extracting low-level features of sample images; performing the high level representation of the sample images; constructing an affinity matrix; initializing or updating a pheromone matrix; labeling positive correlation images and negative collation images for search results of all sample images in the image library; calculating a semantic pheromone matrix; calculating an affinity enhancing probability; enhancing the affinity matrix by using the ant colony algorithm; constructing a hypergraph; and returning the search result and finishing search, or updating the pheromone matrix for the next search. According to the method, an efficient and accurate image search technology is provided for image search and a higher use value is realized.

The invention provides a genetic locus excavation method based on a multi-target ant colony optimization algorithm. The ant colony optimization is used as a foundation design packaging type feature selection algorithm; in each type of iteration, one manual ant selects one SNPs feature subset, one feature subset and corresponding complicated property states to construct a multi-target model; a logistic regression model and a Bayesian network model are used for modeling the selected SNPs feature subset and the corresponding property states respectively; then an AIC (Akaike Information Criterion) and K2 are used as evaluation criteria of the corresponding models, and scores are used as solutions of a multi-target function; a non-dominated ranking method is adopted and all the solutions of the multi-target model in the step 2 are screened into non-dominated solutions and dominated solutions; the iteration of an pheromone matrix Tau is carried out according to advantageous and disadvantageous degrees of the solutions, and one SNPs locus subset selected by the feature selection algorithm is obtained after the iteration is finished. An endless hypothesis test is carried out on Chi-square analysis in the SNPs locus subset; finally, SNPs locus related to complicated properties is screened according to a P value set by a user.

The invention provides an elastic optical network based resource distribution method in virtual network mapping and mainly solves a problem of resource distribution based on an electric optical network in virtual network mapping. The specific steps include: 1, forming a virtual network; 2, performing general initiation; 3, performing local initiation; 4, mapping virtual network nodes; 5, calculating virtual network node fitness; 6, recording a mapping result; 7, judging whether the number of ants of each generation is 0 or not; 8, updating an information prime matrix; 9, judging whether the ant generation number is 0 or not; 10, obtaining a final mapping result of the virtual network nodes; 11, mapping a virtual network link. According to the invention, by adopting an adaptive method and a continuous contiguity method, influence on physical network nodes by the virtual network link is evaluated comprehensively, network mapping jam rate and the amount of physical network link resource occupied by the virtual network are reduced, and physical network link load balance is improved.

The invention discloses a hybrid ant colony algorithm for a VRP problem and an implementation system thereof. The algorithm comprises the steps of (S1) allowing all ants in an ant colony to independently construct a solution of the VRP problem and optimizing the solution by using a local search operation, (S2) performing a pheromone perturbation strategy to adjust a pheromone matrix if an iterative optimal solution remains unchanged in successive iterations, wherein the iterative optimal solution is an optimal solution in solutions constructed by all ants in a single time of iteration, (S3) starting a simulated annealing algorithm to search for a better solution if the optimal solution remains unchanged in the successive iterations so far and taking an optimal solution so far of the ant colony algorithm as an initial solution, (S4) updating the pheromone matrix according to the quality of an ant solution and updating the optimal solution so far, (S5) repeating the steps (S1), (S2), (S3) and (S4) until an obtained optimal solution satisfies a termination condition. According to the hybrid ant colony algorithm for a VRP problem and the implementation system thereof, the purposes of high-quality solution and strong robustness for the VRP problem can be achieved.

The invention discloses a cloudsim platform based virtual machine batch deployment method. The method includes extending a hybrid ant colony algorithm and taking the extended hybrid ant colony algorithm as a virtual machine batch deployment strategy. The hybrid ant colony algorithm performs global pheromone updating by adopting the following formula of pheromone [j][i]=pheromone [j][i]*rho, wherein the rho is a pheromone residual factor, the formula II is a pheromone matrix from a virtual machine i to a physical machine j, wherein ants[k].pheromoneDeltaMatrix represents a pheromone variation matrix of a kth ant, and antNum represent of the quantity of ants. Compared with a greedy strategy, the deployment method has the advantage that load balance and resource utilization rate of a system can be heightened obviously.

The invention discloses a hybrid multi-aircraft conflict resolution method based on an artificial potential field method and an ant colony algorithm. The hybrid multi-aircraft conflict resolution method comprises the following steps of: S1, performing charge conversion between an aircraft and a destination, and obtaining an initial path by the artificial potential field method; S2, adjusting the initial path which is obtained by the artificial potential field method, and encoding the adjusted path to obtain foraging paths of authority ants; S3, deriving an authority ant colony from the authority ants, and initializing a pheromone matrix by using the authority ant colony; S4, according the initialized pheromone matrix, carrying out iterative optimization by the ant colony algorithm to obtain a final conflict resolution scheme. The method of the invention avoids pure pursuit of time effectiveness of the artificial potential field method which may cause the problem of angular deflection incapability of resolution schemes. At the same time, the method solves the time effectiveness problem, i.e., the problem that simulation of the biological self-organization process by the ant colony algorithm leads to heavy calculation burden and cannot be applied to conflict resolution scenes in real time, so that requirements from reality scenes on time effectiveness and feasibility are satisfied.

The invention discloses an ant colony algorithm-based multi-objective workpiece scheduling method and device. The method includes the following steps that: in current iteration, a first preset numberof ants are established, and an empty batch is established; a pheromone matrix and an objective preference vector are acquired, and current processing equipment is obtained; the empty batch is adoptedas the first current batch of the current processing equipment; first workpieces to be processed are scheduled into the first current batch; second workpieces to be processed are added to a current candidate list until all the second workpieces to be processed are scheduled; a pheromone matrix of the next iteration of the current iteration is updated; whether the number of the times of iterationcorresponding to the current iteration is equal to a second preset threshold is judged; if the number of the times of iteration corresponding to the current iteration is not equal to the second presetthreshold, the number of the times of iteration is updated, and the method returns to the step of executing the establishment of the empty batch; and if the number of the times of iteration corresponding to the current iteration is equal to the second preset threshold, a scheduling scheme corresponding to a global optimal completion duration and a global optimal energy consumption in the currentiteration process is used as a target scheduling method. With the method and device provided by the embodiments of the invention adopted, multi-objective scheduling of workpieces can be realized.

The present invention relates to a path optimizing method of an intelligent voice guide robot. The method comprises the following steps: inputting coordinate information of all scenic spots in a scenic region into the control system of an intelligent guide robot, performing map modeling, and performing coordinate processing of the environment information; calculating the mutual distance among the scenic spots through adoption of the coordinate information of the scenic spots, and initializing a information prime matrix according to the distance information; arranging initial parameters; placing ants at different scenic spots, selecting the next scenic spot to be accessed at will according to the probability P<k>ij until all the scenic spots are accessed; allowing the information prime on the connection paths among the scenic spots to gradually disappear while the ants release the information prime, and therefore, after all the ants complete one-time circulation, requiring to perform real-time updating of the information prime concentration on the connection paths among the scenic spots; if the maximum iterations are not reached, going on updating; and or else, ending the iterations, and outputting the optimal solution, namely outputting an optimal line L.

The invention discloses a workpiece scheduling method and device based on an ant colony algorithm, and the method comprises the steps: 1), creating a workpiece scheduling scheme corresponding to antsfor the ants corresponding to a to-be-scheduled workpiece set in the current iteration; 2) judging whether the number of iterations corresponding to the current iteration reaches the maximum number ofiterations or not; 3) if yes, updating the non-dominated solution set to obtain a target non-dominated solution set, and taking a solution in the target non-dominated solution set as a target scheduling method; (4) if not, judging whether to carry out detection or not;, taking the globally updated pheromone matrix for the completion time as a first initial pheromone matrix of the next iteration;taking the globally updated pheromone matrix for the rejection cost as a second initial pheromone matrix of the next iteration, and returning to execute the step 1) until the number of iterations corresponding to the current iteration reaches the maximum number of iterations. By applying the method and the device, the batch processing scheduling problem containing the rejection condition can be processed.

The invention discloses a database multi-connection query optimization method based on an evolutionary algorithm. According to the method, first, a data preprocessing technology and a bidirectional semi-connection technology are introduced into an SDD-1 algorithm, projection and other unary operation are adopted to simplify data, meanwhile, data of all nodes is ordered by merging, and row data and column data can be reduced at the same time through the bidirectional semi-connection technology; second, all beneficial bidirectional semi-connections are calculated and added into a set BS, a parallel genetic algorithm is adopted to solve a connection query strategy of the SDD-1 algorithm, a group initialization method, a fitness function and a relevant genetic operator suitable for the problem are constructed, and a protocol optimal query path for solving the problem is obtained; and last, the query path is used to initialize a pheromone matrix of an ant colony algorithm, a multi-ant-colony optimization method is utilized to solve an optimal query path again, and the problem that the parallel genetic algorithm has a weak local search ability is solved.

The invention relates to an edge detection method based on the combination of region growth and an ant colony optimization algorithm, the method comprising the following steps: S1, processing an imageby adopting a region growth method to extract a region of interest; S2, adopting ant colony optimization method to generate pheromone matrix for the extracted region of interest; S3, for the extracted ROI, using the pheromone matrix generated by ant colony optimization method to calculate the threshold value and determine the image edge. The invention overcomes the technical defects of the priorart such as unclear edge, discontinuous edge and large noise influence, improves the prior ant colony algorithm which is easy to converge prematurely, and provides an edge detection method based on the combination of the region growth and the ant colony optimization algorithm.

The present invention discloses a workpiece scheduling method and a device based on an ant colony algorithm. The workpiece scheduling method comprises the following steps of: establishing a first preset number of ants at the current iteration, and establishing an empty batch for the current number of ants; taking the empty batch as a first current batch of the ants, and scheduling a first workpiece to be machine into the first current batch; adding a second workpiece to be machine into a candidate list corresponding to the first current batch; scheduling the second workpiece to be machine intothe first current batch according to the probability; until all the workpieces to be machine are scheduled to a batch corresponding to the current ant; taking the next ant as the current ant, and establishing an empty batch for the ant; updating a pheromone matrix; judging whether the number of iterations corresponding to the current iteration is equal to the maximum number of iterations or not;if the number of iterations corresponding to the current iteration is equal to the maximum number of iterations, taking the corresponding relationship between the machining equipment and the workpieceto be machine corresponding to the ants with the smallest target value in the current iteration as a target scheduling method. By applying the embodiments of the workpiece scheduling method and the device based on the ant colony algorithm, workpieces with higher importance can be scheduled into corresponding batches.

The invention discloses an optical network multi-fault tolerant method which relates to the technical field of optical network survivability. Each optical network node i maintains an information prime matrix Ti and a local node model Mi. The method comprises the following steps of: S1. a positive ant in each node of an optical network selects a target node d according to flow distribution at a preset time interval, asynchronously moves to the target node d and records the physical connectivity of the passed path and a path node identifier; S2. after the positive ant arrives at the target node, a reverse ant is generated at the target node, and the positive ant transfers all memories to the reverse ant; and S3. the reverse ant returns along the passed path of the positive ant and adjusts the local node model in a network state and the information prime matrix of each accessed node on the way according to the final connectivity of the path. Through the invention, the damaged business can be rapidly turned to a normal network resource and the arrival business can be selected to a path with higher connectivity.

The embodiment of the invention discloses a multi-path planning method and system. The method comprises the steps: setting array parameters of path planning, calculating array similarity, confirming the array parameters as ant colony parameters, and confirming the array similarity as ant colony similarity; dividing the ant colony into a plurality of populations according to the ant colony similarity, and initializing a pheromone matrix of each population; starting total iteration, constructing a plurality of solutions according to the pheromone matrix of each population, and calculating an optimal path in each solution; judging whether the ant colony is re-divided or not according to the total iteration times, if so, re-dividing the whole ant colony, and executing a global updating rule; if not, executing a global updating rule; and adding one to the total number of iterations, and ending the iteration when an end condition is satisfied to obtain the optimal path and path length of theplurality of populations. A plurality of different distribution paths can be planned.

The embodiment of the invention discloses an image segmentation method, a device, equipment and a computer-readable storage medium. The method comprises the following steps: ROI region growth processing is performed on the image to be segmented to extract a region of interest from the image to be segmented as a target detection region image; using a chaotic ant colony algorithm, the edge of the target detection region image is detected to obtain the edge image of the image to be segmented; before extracting the image edge by using the chaotic ant colony algorithm, the application extracts theregion of interest from the image to be segmented instead of the whole image to be segmented for subsequent processing, thereby effectively reducing the image processing and the searching workload ofthe midpoint in the real environment, thereby improving the running speed of the image segmentation method and satisfying the real-time requirement. Because the chaotic ant colony algorithm calculatesthe image threshold value by updating the pheromone matrix so as to obtain the image edge information, which can find the image edge more comprehensively and quickly, thus improving the speed and accuracy of image segmentation.

The invention belongs to the technical field of communication and particularly relates to a node topology control method and a node topology control system; the node topology control method comprisesthe following steps: initializing a network, establishing an initialization pheromone matrix and randomly selecting transmission power for each node; judging whether each node is provided with at least one neighbor node; calculating pheromone, an energy heuristic value and node transmission power selection probability for each node with the neighbor node; and judging whether a topological graph formed by each node in the steps meets the connectivity of the nodes at least between a source point and an end point and obtaining an optimal transmission power combination path for each node. According to the node topology control method and the node topology control system, the topology can be reconstructed on the basis of the existing remaining nodes, so that the energy expenditure of the nodesis reduced, the life cycle of the network is prolonged, the interference of the network is reduced, the throughput of the network is improved; meanwhile, the network has certain robustness so as to effectively achieve the aims of energy conservation and energy balance.

The invention provides a side-cloud collaborative multi-task scheduling method and system for guaranteeing a side-cloud load ratio, and the method comprises the steps: calculating the score of each task scheduled to any node based on the remaining available amount of CPU resources and the remaining available amount of memory resources of each node, and the CPU resource request amount and the memory resource request amount of each task, establishing a score matrix; initializing a pheromone matrix; obtaining all element values based on each task, and calculating a random factor of each task; establishing a scheduling strategy boundary, and enabling ants to adopt a pheromone concentration scheduling strategy or a random scheduling strategy; obtaining a scheduling strategy of each ant, and obtaining a scheduling scheme of each ant; calculating an edge cloud load ratio, and calculating a target score of the scheduling scheme; obtaining the size of the random factor of each task, and if the size of the random factor is greater than a preset first threshold value, taking the scheduling scheme of the ant with the maximum target score as an optimal strategy; and if the information is smaller than or equal to the preset first threshold value, updating the pheromone matrix.

The invention discloses a method for studying and judging a power distribution network power failure. The method comprises the steps that power failure and decompression users are screened, and powerdistribution network topology of the power failure and decompression users is acquired; an ant colony is set up for the power failure and decompression users, and an overall path matrix is set up according to the power distribution network topology; ant colony distribution is judged to determine a subpath matrix of ant colony search and serves as a sub-information prime matrix; fault search is carried out through an ant colony algorithm, all ants in the ant colony are subjected to path search, and element values of the sub-information prime matrix are updated synchronously; it is adopted as aterminal condition that all the ants are judged, and the largest element value in the sub-information prime matrix is the power failure point. According to the method, under the condition of not increasing hardware investment cost, the speed of failure locating is increased, the accuracy of failure locating is improved, the response time is shortened, the cost is reduced, and the customer satisfaction degree and the system operation index are improved.

The invention belongs to the technical field of aircraft route planning, and particularly relates to an aircraft route planning method which comprises the following steps: step 1, discretizing a situation space to obtain a plurality of discrete points; step 2, generating a heuristic factor matrix of each discrete point; step 3, taking the discrete point at a planning starting point as a current planning point; step 4, selecting discrete points meeting the safe flight condition of the aircraft in the current planning point range to form a set of next planning points of the discrete points; step5, judging whether the set is empty or not; step 6, if the set is not empty, selecting a next planning point from the set based on the heuristic factor matrix and the pheromone matrix thereof to update the current planning point; judging whether the current planning point is a discrete point at the planning end point or not, and if not, returning to the step 4; if so, searching to obtain and store a planned route; and step 7, if the set is empty, searching to obtain and store the planned route.

The invention discloses a method for researching and judging a power outage fault in a distribution network. Overall path matrix; judge the distribution of ant colony to determine the sub-path matrix of ant colony search, and use it as a sub-pheromone matrix; use ant colony algorithm to search for faults, search for paths for all ants in the ant colony, and update them synchronously The element value of the sub-pheromone matrix; all ants have been judged as the termination condition, and the maximum value of the element in the sub-pheromone matrix is ​​the power failure point. The invention improves the speed and accuracy of fault location, shortens the response time, reduces the cost, and improves customer satisfaction and system operation indicators without increasing hardware investment cost.

The invention discloses a power failure fault location method of a distribution network based on an improved ant colony algorithm, which comprises the following steps: establishing an overall path matrix according to a distribution network topology; dividing the normal power supply user group into a negative ant colony and dividing the normal power supply user group into a negative ant colony; determining the forward information element matrix and the negative information element matrix are respectively determined according to the differentiated ant colony, driving a positive ant colony algorithm for the forward information element matrix, and driving a negative ant colony algorithm for the negative information element matrix, performing the target search separately and calculating the element values in each information element. All the ants have been judged as the termination condition, and the forward pheromone matrix and the negative pheromone matrix are added and combined to obtainthe total pheromone matrix. The maximum value of the elements in the total pheromone matrix is the power failure fault point. The power failure fault location method improves the speed and the accuracy of the fault location without increasing the hardware input cost, shortens the response time, reducing the cost, and improves the customer satisfaction and the system operation index.

The invention relates to an indoor activity detection and identification method and a system based on multi-sensor network wherein the method comprises: recording the position information and triggering information of all the triggering type sensors in a targeted indoor environment; prior to the identification of the activity type, training and processing the k-nearest neighbor algorithm to obtain identification bases; in the practical application, according to the processing of the triggering information, the heterogeneous pheromone residual mask and the single frame picture change to obtain a corresponding a pheromone matrix; and finally, based on the identification bases, realizing the identification of the human body activity type. According to the invention, a plurality of triggering type sensors are arranged in an indoors environment and the triggering information and the position information of each triggering type sensor are recorded, which increases the accuracy and the reliability of the identification result considerably.

The invention discloses an adaptive adjustment method for teaching video playing speed. The adaptive adjustment method comprises the following steps: constructing a general pheromone matrix, a classification pheromone matrix and a speed migration parameter matrix of a video by utilizing T time periods of the video and m preset playing speeds; collecting preview feedback of the viewers to classifythe viewers; calculating an initial playing speed according to the viewer type; in the watching process, according to the speed migration parameter matrix, the playing speed of the current time period, and the general pheromone matrix and the classification pheromone matrix which are updated after the previous watcher watches, calculating the probability that the playing speed is changed into eachspeed of m speeds when the current watcher watches the next time period; adjusting the playing speed of the current viewer in the next time period according to the probability; after playing, generating a playing speed path of the video watched by the current viewer; and collecting after-class feedback of the viewer and updating the general pheromone matrix and the classification pheromone matrixaccording to the after-class feedback and the playing speed path.

The invention provides a sparse ant system supporting a large-scale combination optimization problem. The system comprises an initial solution construction module, an iterative solving module, a sparse pheromone matrix update module and an optimal solution calculation module. The invention furthermore provides a method for calculating an optimal solution of the large-scale combination optimizationproblem by using the sparse ant system. The method comprises the steps of 1, constructing an initial solution; 2, calculating optimal solutions by multi-time iteration, calculating global iterative optimal solutions in M ants, circulating each ant for N times, obtaining a sub-step solution node j during each calculation, finally obtaining feasible solutions of current iteration, selecting the global optimal solution in the feasible solutions of the M ants, and performing comparison and update on the global optimal solution of the current iteration and the iterative optimal solution so far; 3,after each iteration is finished, updating a sparse pheromone matrix according to the global iterative optimal solution; and 4, performing loop iteration according to rules of the steps 2 and 3, until the defined iterative frequency or total cost of the feasible solutions is smaller than or equal to a target optimal solution.

The invention relates to an OD flow direction clustering method based on a multi-path graph cutting criterion and ant colony optimization, and the method comprises the steps: constructing a theme distribution model through a flow direction end point POI, calculating the flow direction space-time semantic similarity, constructing an undirected graph complex network and an initial pheromone matrix, extracting all connected components of the network, and recognizing connected components to be clustered; and adopting multi-process parallel mode for connected components to be clustered based on a multi-path graph cutting criterion and ant colony optimization, wherein one process clusters one connected component. Clustering results of all the processes of the steps are summarized, and a final clustering result is obtained. According to the method, an undirected graph complex network thought and a clustering algorithm are organically combined, complex network simplification is performed by adopting a Gaussian kernel function, and automatic noise identification is realized by utilizing graph connected components. According to the method, a heuristic function is improved based on a multi-path graph cutting criterion, and the initial node of the ant colony is screened by utilizing betweenness centrality based on a complex network idea, so that the clustering effect is effectively improved.

The invention provides a mobile robot path planning method based on an improved ant colony algorithm. The method comprises the following steps: establishing a grid map; all parameters of the ant colony algorithm are initialized, an initial path is generated according to an artificial potential field method, an initial pheromone matrix of the path is updated, and a tabu table is initialized; a selectable node is constructed according to the tabu table and the obstacle information, a candidate solution is constructed according to an improved state transition rule, and a next node is selected according to a roulette principle; updating the taboo table and recording path nodes and path lengths of the ants; judging whether the ants arrive at a target node or not, if the ants arrive at the target node, performing node optimization on the complete path according to a node optimization strategy to obtain an optimal path of current iteration, and performing pheromone global updating; and performing iteration according to a preset maximum number of iterations to obtain an optimal path. According to the invention, the traditional ant colony algorithm is optimized and improved to achieve the effects of accelerating the convergence speed of the algorithm and avoiding the local optimal solution.

The invention discloses a traveling salesman problem solving method based on an improved ant colony algorithm. The method comprises the following steps: step 1, assigning an initial pheromone concentration; 2, ants are distributed to all nodes; 3, completing one time of iteration; 4, updating each path pheromone; 5, judging whether the optimal path is still unchanged or not in a period of time after the pheromone divergence point, and if so, executing the step 6; if not, executing the step 7; 6, resetting the pheromone matrix, and executing the step 2; 7, judging whether the algorithm reachesthe maximum number of iterations or not, and if so, finishing solving; and if not, executing the step 2. By improving the ant colony algorithm, the ant colony algorithm can more effectively avoid thesituation that the algorithm is caught in local convergence in the process of solving the TSP problem, the global search ability of the algorithm is improved, and therefore the accuracy of result solving is improved.

The invention discloses a multi-target route planning method and device, electronic equipment and a storage medium, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: determining access priority indexes of a plurality of to-be-accessed points and access distances among the plurality of to-be-accessed points; constructing ant routes according to the initialized pheromone matrix and the initialized ant information, determining an optimal route from the constructed ant routes according to the access priority index and the access distance, and updating the pheromone matrix based on the optimal route; reconstructing an ant route according to the updated pheromone matrix and the re-initialized ant information until the number of times of constructing the ant route reaches a preset number of times; and screening out a target route from the constructed ant routes according to the access priority index and the access distance. According to the embodiment, the problem that multi-target route planning cannot be carried out by a single-target route planning method can be solved.