Bus network optimization method, device and equipment

Abstract

The invention discloses a public transit network optimization method, device and equipment, and relates to the technical field of traffic scheduling. Constructing a network optimization model based on an ant colony algorithm, inputting the public transit network diagram and the OD matrix into the network optimization model for iteration until a preset number of iterations is reached, and obtaining an optimal path; the optimization target module is used for defining an optimization target function of a network optimization model according to the public transit network diagram and the OD matrix, and initializing ant colony parameters and importance factors; the path selection module is used for constructing a path selection strategy for path selection according to the ant colony parameters to obtain a first path; and the crossover and variation module is used for performing crossover and variation processing on the first path subjected to punishment processing to obtain a second path, and evaluating the second path to determine a first optimized path. According to the method, the network optimization model can be dynamically adjusted, the convergence speed is increased, and the global search capability is improved. The operation efficiency of the public transit network diagram is optimized, and the operation requirements of urban buses are better met.

Description

Technical Field

[0001] This application relates to the technical field of traffic scheduling, and particularly to an optimization method, device, and equipment for a bus network. Background Art

[0002] With the continuous acceleration of the urbanization process and the continuous growth of the urban population, the urban public transportation system plays an important role in alleviating traffic congestion and improving the travel efficiency of residents. As the basis of the urban public transportation system, the optimization degree of the bus network is directly related to the operation efficiency and service quality of the public transportation system. Therefore, the optimization algorithm for the public transportation system has emerged as the times require.

[0003] In this development context, in the optimization problem of the bus network, the existing technology usually adopts the ant colony algorithm to construct a solution space in practical problems, and guides the search direction of ants through the accumulation and evaporation of pheromones. In practical applications, the performance of the ant colony algorithm is sensitive to parameter settings, and the adjustment of parameters has a great impact on the performance of the algorithm. Therefore, there is a problem of difficulty in adjusting parameters, which increases the processing cost.

[0004] In addition, the current optimization method for the bus network also includes the method of collecting mobile phone signaling data to determine the mobile phone point trajectory, constructing an OD matrix based on this, combining it with the shortest path algorithm to generate alternative bus routes, and then using the genetic algorithm to screen out the optimal solution. Although it makes full use of the spatial distribution characteristics of spatio-temporal big data and the exploration ability of the genetic algorithm in complex path spaces, improving the efficiency in dealing with large-scale path optimization problems. However, the traditional genetic algorithm may converge prematurely to a local optimal solution, resulting in the inability to find the global optimal solution, making the optimization result prone to falling into the local optimum and lacking solution diversity. At the same time, it cannot guarantee the convergence speed and quality of the solution in a complex traffic network environment. Summary of the Invention

[0005] By providing an optimization method, device, and equipment for a bus network, the embodiments of this application solve the problems of low accuracy in optimizing bus routes and not meeting the operating requirements of urban buses in the prior art. By constructing a bus network graph and an OD matrix, using the ant colony algorithm to construct an optimization objective function, selecting paths that meet the constraints of the optimization objective function with the help of a path selection strategy, and combining the crossover and mutation processing of the genetic algorithm to dynamically adjust the importance factor, the optimal path is obtained. It realizes the ability to obtain a globally optimal bus network solution, makes the optimal path, that is, the optimized bus route, more in line with the requirements of the efficient operation of urban buses, and improves the accuracy, applicability, and efficiency of the operation of the bus network.

[0006] In a first aspect, an embodiment of the present application provides an optimization method for a bus network, including: obtaining bus stop data, GPS operation data of buses, and passenger card-swipe data; constructing a bus network graph according to the bus stop data and the GPS operation data of buses; constructing an OD matrix according to the bus network graph and the passenger card-swipe data; constructing a network optimization model based on the ant colony algorithm, and inputting the bus network graph and the OD matrix into the network optimization model for iteration until a preset number of iterations is reached to obtain an optimal path; wherein the network optimization model includes an optimization objective module, a path selection module, a penalty module, a crossover and mutation module, and an adjustment module; the optimization objective module is configured to define an optimization objective function of the network optimization model according to the bus network graph and the OD matrix, and initialize ant colony parameters and importance factors; the path selection module is configured to construct a path selection strategy for path selection according to the ant colony parameters to obtain a first path; the penalty module is configured to perform penalty processing on the first path that meets the restriction conditions to update the pheromone on the first path; the crossover and mutation module is configured to perform crossover and mutation processing on the first path after penalty processing to obtain a second path, and evaluate the second path to determine a first optimized path; the adjustment module is configured to adjust the importance factor of the first optimized path according to the number of iterations until the preset number of iterations is reached to obtain the optimal path.

[0007] In a possible implementation manner, the constructing a bus network graph according to the bus stop data and the GPS operation data of buses includes: making the GPS operation data of the buses correspond to the bus stop data one by one to determine a bus stop sequence and an actual driving path; constructing nodes according to the bus stop sequence; taking the actual driving path between each two bus stops as an edge; and constructing the bus network graph according to the nodes and the edges.

[0008] In a possible implementation manner, the constructing an OD matrix according to the bus network graph and the passenger card-swipe data includes: performing time matching on the GPS operation data of the buses and the passenger card-swipe data to determine card-swipe location information; extracting geographical location information of each node in the bus network graph; performing spatial matching on the geographical location information and the card-swipe location information to determine a passenger boarding node; defining a distance function according to the geographical location information, constructing a passenger travel chain, and determining a passenger alighting node; and determining the passenger flow between the starting and ending points of each bus line according to the passenger boarding node and the passenger alighting node to construct the OD matrix.

[0009] In a possible implementation, the optimization objective function of the network optimization model is defined according to the bus network map and the OD matrix, and the ant colony parameters and importance factors are initialized, including: determining the constraint conditions according to the bus network map and the OD matrix; wherein, the optimization objective function of the network optimization model is defined according to the bus network map and the OD matrix, and the ant colony parameters and importance factors are initialized, including: determining the constraint conditions according to the bus network map and the OD matrix; wherein, the constraint conditions include node spacing, line length, and line non - straightness coefficient; based on the constraint conditions, the optimization objective function is defined; pheromone is set on each bus line, and based on the optimization objective function, the starting point of each bus line in the bus network map is used as the initial position of the ant colony; the initial values of the ant colony parameters and the initial values and extreme values of the importance factors are set; wherein, the importance factors include pheromone importance factor and heuristic importance factor, and the ant colony parameters include the number of ants, pheromone concentration, pheromone evaporation rate, and number of iterations; wherein, the optimization objective function is as follows: ; where, ; ; ; In the formula, represents the value of the optimization objective function of the network optimization model, represents the th bus line in the bus network map, represents the set of the number of bus lines in the bus network map, , represents the current node, represents the total number of nodes in the bus network map, represents the th node in the bus network map, and ≠ , represents the direct passenger flow from the current node to the th node, represents the minimum value of the preset line length of the bus line, represents the actual value of the line length of the th bus line, represents the maximum value of the preset line length of the bus line, respectively represent the line non - straightness coefficient of the currently traveled bus line and the preset maximum line non - straightness coefficient, and respectively represent the minimum and maximum values of the preset distance between two adjacent nodes in the bus line, represents the current node in the bus network graph to the next node of the node distance, represents the straight-line distance between the starting point and the ending point of the th bus line in the bus network graph.

[0010] In a possible implementation manner, the constructing a path selection strategy according to the ant colony parameters to perform path selection to obtain a first path includes: iteratively executing a judgment step until the end point of the current bus line is traversed to obtain the first path; the judgment step is as follows: calculating the transfer probability of an ant at the current node based on the ant colony parameters to determine the next node to obtain a first node; after obtaining the first node, randomly generating a probability value, if the probability value is less than a preset decision value, randomly exploring unvisited nodes to obtain a second node; if the probability value is greater than or equal to the preset decision value, calculating the transfer probability of the first node and taking its next node as the second node; judging whether the second node is the same as the end point of the current bus line where it is located; if the second node is different from the end point of the current bus line, taking the next node of the current second node as the first node to execute the judgment step; if the second node is the same as the end point of the current bus line, taking the current second node as the first node to execute the judgment step.

[0011] In a possible implementation manner, the performing penalty processing on the first path that meets the constraint conditions to update the pheromone on the first path includes: the constraint conditions include: nodes that the line network optimization model detects that the ants have passed through during the exploration of the first path; and / or, the first path does not meet the preset length; and / or, the first path does not meet the non-linear coefficient constraint.

[0012] In a possible implementation manner, performing crossover and mutation processing on the first path that has undergone penalty processing to obtain a second path, and evaluating the second path to determine a first optimized path, includes: selecting two bus lines with intersection points in the first path that has undergone penalty processing, and using the intersection point as a common node; performing single-point crossover processing on the section between the common node and the end point of the current bus line to obtain a crossover line; randomly replacing one node in the crossover line with a preset node to obtain the second path; determining the optimization objective function value of the second path, and if it is better than the optimization objective function value of the first path that has undergone penalty processing, updating the pheromone on the second path to obtain the first optimized path; otherwise, using the first path that has undergone penalty processing as the first optimized path.

[0013] In a possible implementation manner, adjusting the importance factor of the first optimized path according to the number of iterations until a preset number of iterations is reached to obtain the optimal path, includes: dynamically adjusting the pheromone importance factor and the heuristic importance factor according to an adjustment formula to obtain the optimal path; where the adjustment formula is as follows: ; ; In the formula, and represent the pheromone importance factor and the heuristic importance factor at the -th iteration, and respectively represent the initial value and the maximum value of the pheromone importance factor, and respectively represent the initial value and the minimum value of the heuristic importance factor, and represent control parameters, represents the number of iterations of the line network optimization model, represents a mathematical constant.

[0014] Second aspect, an optimization device for a bus network provided by an embodiment of the present application includes: a data acquisition module, configured to acquire bus stop data, GPS operation data of buses, and passenger card-swipe data; a network construction module, configured to construct a bus network diagram according to the bus stop data and the GPS operation data of buses; construct an OD matrix according to the bus network diagram and the passenger card-swipe data; a model construction module, configured to construct a network optimization model based on an ant colony algorithm, input the bus network diagram and the OD matrix into the network optimization model for iteration until a preset number of iterations is reached to obtain an optimal path; wherein, the network optimization model includes an optimization objective module, a path selection module, a penalty module, a crossover and mutation module, and an adjustment module; the optimization objective module is configured to define an optimization objective function of the network optimization model according to the bus network diagram and the OD matrix, and initialize ant colony parameters and importance factors; the path selection module is configured to construct a path selection strategy for path selection according to the ant colony parameters to obtain a first path; the penalty module is configured to perform penalty processing on the first path that meets the constraint conditions to update the pheromone on the first path; the crossover and mutation module is configured to perform crossover and mutation processing on the first path after penalty processing to obtain a second path, and evaluate the second path to determine a first optimized path; the adjustment module is configured to adjust the importance factor of the first optimized path according to the number of iterations until a preset number of iterations is reached to obtain the optimal path.

[0015] Third aspect, an apparatus for executing an optimization method of a bus network provided by an embodiment of the present application includes: a processor; a memory for storing processor-executable instructions; when the processor executes the executable instructions, the method described in the first aspect or any possible implementation manner of the first aspect is implemented.

[0016] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: The embodiments of the present application adopt an optimization method, device, and equipment for a bus network. By constructing a bus network graph and an OD matrix, the utilization efficiency of bus network data is improved, making it more in line with the actual passenger flow. A network optimization model is constructed and an optimization objective function is defined. Based on the path selection strategy, paths are selected, which improves the diversity of solutions and avoids the problems of falling into local optima and premature convergence of the network optimization model. Combining penalty processing and crossover mutation processing, the parameters of the network optimization model are dynamically adjusted, and the optimization objective function is used as a guide for path evaluation to obtain the optimal path. This speeds up the convergence rate of the network optimization model, enhances the global search ability and the feasibility of solutions, and effectively solves the problems of low accuracy in optimizing bus routes and not meeting the operation requirements of urban buses in the prior art. It can dynamically adjust the network optimization model, speed up the convergence rate and global search ability, improve the accuracy of exploring paths by the optimization objective function, optimize the operation efficiency of the bus network, and better meet the operation requirements of urban buses, with stronger universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for describing the embodiments of the present application or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of an optimization method for a bus network provided by an embodiment of the present application; Figure 2 It is a flowchart of a method for identifying passenger boarding nodes provided by an embodiment of the present application; Figure 3 It is a flowchart of a method for identifying passenger alighting nodes provided by an embodiment of the present application; Figure 4 It is a flowchart of a network optimization model provided by an embodiment of the present application; Figure 5 It is an experimental comparison diagram of bus route 268 provided by an embodiment of the present application; Figure 6 It is an experimental comparison diagram of bus route 311 provided by an embodiment of the present application; Figure 7 It is an experimental comparison diagram of bus route 600 provided by an embodiment of the present application; Figure 8 It is an experimental comparison diagram of bus route 616 provided by an embodiment of the present application; Figure 9 It is an experimental comparison diagram of bus route 734 provided by an embodiment of the present application; Figure 10It is a schematic structural diagram of an optimization device for a bus network provided by an embodiment of the present application. Specific embodiments

[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0020] The following explanations are made for some technologies involved in the embodiments of the present application to facilitate understanding. It should be considered that they are merely illustrative. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, some descriptions of well-known functions and structures are omitted in the following description.

[0021] Figure 1 It is a flowchart of an optimization method for a bus network provided by an embodiment of the present application, including steps 101 to 111. Figure 1 It is only an execution order shown in the embodiment of the present application and does not represent the only execution order of an optimization method for a bus network. Under the condition that the final result can be achieved, Figure 1 The steps shown can be executed in parallel or reversed, as follows.

[0022] Step 101: Obtain bus stop data, GPS operation data of buses, and passenger card swiping data.

[0023] In the embodiment of the present application, obtain bus stop data, GPS operation data of buses, and passenger card swiping data of bus lines from the traffic management department. Among them, the passenger card swiping data includes the ID (CARDID) and swiping time (CREATETIME) of the bus IC card. Preprocess the obtained data, where the preprocessing includes removing duplicate data, missing data, invalid data, performing data consistency verification, and abnormal data processing.

[0024] Step 102: Construct a bus network map according to the bus stop data and the GPS operation data of the buses. Correlate the GPS operation data of the buses with the bus stop data one by one to determine the bus stop sequence and the actual driving path. According to the bus stop sequence, construct nodes; use the actual driving path between each bus stop as an edge; construct a bus network map according to the nodes and edges.

[0025] Specifically, the GPS operation data of the bus includes longitude and latitude, bus driving speed, bus ID, and collection time. The bus stop data includes stop name, longitude and latitude, and bus line. Based on the longitude and latitude, the GPS operation data of the bus can be corresponding to the bus stop data, anchoring the actual stop of the bus vehicle, and determining the driving direction of the bus, that is, the bus stop sequence and the actual driving path. The GPS operation data of the bus can obtain the specific real-time information of the bus vehicle. Using a map matching algorithm, such as the Hidden Markov Model, the GPS operation data of the bus is converted into a geographic coordinate system (such as WGS84) for matching with the bus stop data. Mapping the GPS operation data of the bus to the actual road can verify the accuracy of the stop location and generate a bus network map including bus lines, stop locations, and connection relationships between lines.

[0026] Step 103: Construct an OD matrix based on the bus network map and passenger card swiping data.

[0027] Perform time matching on the GPS operation data of the bus and the passenger card swiping data to determine the card swiping location information; extract the geographical location information of each node in the bus network map, perform spatial matching on the geographical location information and the card swiping location information to determine the passenger boarding node; define a distance function based on the geographical location information, construct a passenger travel chain, and determine the passenger alighting node.

[0028] In the embodiment of the present application, the bus network map is used to describe the supply capacity of the bus network system and the road connection relationship. Especially when the bus line is adjusted, the travel choices of passengers may also change accordingly. Extracting the geographical location information of the nodes, that is, the bus stops, can correspond more precisely to the actual road. As Figure 2 shown, it is a flowchart of the passenger boarding node recognition method. Perform time matching on the preprocessed GPS operation data of the bus and the passenger card swiping data, and infer the position of the bus vehicle corresponding to the passenger card swiping moment, then the current card swiping location information of the passenger can be determined. The node coordinates can be standardized by adopting a unified time reference and a geocoding method.

[0029] Exemplarily, UTC (Coordinated Universal Time) timestamp and Geocoding (an address standardization tool) can be used for time matching.

[0030] Specifically, according to the bus node data, extract the geographical location information of each node, use a spatial matching algorithm to calculate the spatial distance between the card swiping location information and the geographical location information of the node, and select the node with the closest distance as the passenger boarding node. The spatial matching algorithm is such as the Best-First Search (BFS) algorithm.

[0031] As Figure 3As shown in the figure, it is a flowchart of a method for identifying passenger alighting nodes. Exemplarily, bus stop data and passenger card - swiping data with passenger boarding node data are input. The distance between two adjacent nodes is calculated based on longitude and latitude, a distance function is defined, and a passenger travel chain is constructed.

[0032] Among them, the distance function is specifically as follows: ; In the formula, represents the distance between two nodes in the bus network graph, and represent the sine function and cosine function respectively, and respectively represent and the latitudes and longitudes of the nodes, and represent any two nodes respectively.

[0033] In the embodiment of the present application, a temporary list A is established, and all IC records with the same ID are stored in table A. Since the last record in the IC record has no next adjacent node, the records in table A except the last record in each IC record are studied. Select passenger card - swiping data of passengers who swipe the card more than twice a day, and define the current record as the th record. The card - swiping processing steps are iteratively executed until the final passenger alighting nodes are determined. Among them, the card - swiping processing steps include: Judge whether the th record is the last passenger card - swiping data of the day. If it is the last passenger card - swiping data, it is matched with the passenger card - swiping data record of the first trip of the day, that is, the corresponding bus line. If it is the same bus line, the first passenger card - swiping data is defined as the passenger alighting node of the current record; if it is not the last passenger card - swiping data, check whether the bus lines of the passenger card - swiping data records adjacent to the th record (the th record) are the same. If they are the same, the boarding node in the passenger card - swiping data of the adjacent subsequent bus line is marked as the passenger alighting node of the current record; if the bus lines of the passenger card - swiping data records adjacent to the th record are not the same, based on a preset spatial threshold, select the node with the closest distance between the boarding node of the th record and the subsequent node of the boarding node of the current th record as the passenger alighting node; until all passenger alighting nodes are determined.

[0034] Judging the transfer steps according to the passenger getting-off node. If the time difference of the passenger card-swipe data between the passenger getting-off node and the next getting-on node meets the preset time threshold, it is determined as a transfer trip, and the invalid intermediate passenger card-swipe data during the transfer is deleted, only keeping the th record and the getting-off node data of the last card-swipe; if the time difference of the passenger card-swipe data between the getting-off node and the next getting-on node is not within the preset time threshold range, it is determined as an independent trip, and the getting-off node of the th record is set as the passenger getting-off node that meets the spatial judgment requirements.

[0035] Among them, the preset time threshold is obtained by calculating the walking time required for the passenger to walk from the current node to the getting-on node corresponding to the next bus ride card-swipe data, and 10 minutes can be taken. Then search for the th bus ride card-swipe data record's getting-off time and the th bus ride card-swipe data record's getting-on time, and calculate the consumption time of the passenger during the transfer. The preset spatial threshold can be taken as 1 kilometer.

[0036] According to the passenger getting-on node and the passenger getting-off node, determine the passenger flow between the starting and ending points of each bus line to construct an OD matrix. As shown in Table 1, it is the OD matrix result table of some bus lines. The rows in the OD matrix represent the end points, and the columns represent the starting points.

[0037] Exemplarily, such as , it means that the passenger flow from the 7th location to the 7th location is 110 people, that is, this is a closed trip chain, and the starting point and the ending point of the passenger are the same.

[0038] Table 1 OD matrix result table of some bus lines

[0039] Step 104: Construct a line network optimization model based on the ant colony algorithm, and input the bus line network graph and the OD matrix into the line network optimization model for iteration until the preset number of iterations is reached. Among them, the line network optimization model includes an optimization objective module, a path selection module, a penalty module, a crossover and mutation module, and an adjustment module.

[0040] Such as Figure 4 shown, it is the flow chart of the line network optimization model. This application obtains an optimized ant colony algorithm based on the ant colony algorithm and the genetic algorithm, and constructs a line network optimization model based on the optimized ant colony algorithm.

[0041] Step 105: The optimization objective module is used to define the optimization objective function of the line network optimization model according to the bus line network graph and the OD matrix, and initialize the ant colony parameters and the importance factors.

[0042] According to the bus network map and the OD matrix, determine the constraint conditions; among them, the constraint conditions include the node spacing, the line length, and the line non - straightness coefficient.

[0043] Specifically, according to the distance function, determine the straight - line distance between each node of the bus line, and then determine the line non - straightness coefficient. Take the line length, the line non - straightness coefficient, and the inter - station distance as the constraint conditions for constructing the network optimization model.

[0044] Based on the constraint conditions, define the optimization objective function. Among them, the optimization objective function is specifically as follows: ; where, ; ; ; In the formula, represents the optimization objective function value of the network optimization model, represents the th bus line in the bus network map, represents the set of the number of bus lines in the bus network map, , represents the current node, represents the total number of nodes in the bus network map, represents the th node in the bus network map, and ≠ , represents the direct passenger flow from the current node to the th node, represents the minimum value of the preset line length of the bus line, represents the actual value of the line length of the th bus line, represents the maximum value of the preset line length of the bus line, respectively represent the line non - straightness coefficient of the currently traveled bus line and the preset maximum line non - straightness coefficient, and respectively represent the minimum and maximum values of the preset distance between adjacent two nodes in the bus line, represents the node spacing from the current node to the next node in the bus network map, represents the straight - line distance between the starting point and the ending point of the th bus line in the bus network map.

[0045] Exemplarily, the preset The route length of each bus line ranges from 15 to 25 kilometers (total length). The distance between adjacent nodes in the preset bus lines ranges from 1 to 3 kilometers, and the non - straight - line coefficient of the preset line is not greater than 1.4. The maximization objective optimization function is to find a bus line with the largest direct passenger flow, a relatively low non - straight - line coefficient, and a route length within the range of the constraint conditions, so as to improve the passenger flow of the bus line and further achieve the purpose of optimizing the entire bus network map.

[0046] Set pheromone on each bus line, and based on the optimization objective function, take the starting point of each bus line in the bus network map as the initial position of the ant colony.

[0047] Set the initial values and the maximum and minimum values of the importance factors of the ant - colony parameters; among them, the importance factors include the pheromone importance factor and the heuristic importance factor, and the ant - colony parameters include the number of ants, pheromone concentration, pheromone evaporation rate, and the number of iterations.

[0048] Exemplarily, the number of ants is , which represents the total number of nodes in the bus network map. The pheromone concentration can be taken as 1, the pheromone evaporation rate can be taken as 20% - 50%, and the number of iterations is 200 times.

[0049] In the embodiment of the present application, setting a certain amount of pheromone on the bus line can avoid the deviation caused by too large a difference in pheromone during subsequent selection. Initialize the pheromone set on each bus line according to the pheromone setting formula.

[0050] The pheromone setting formula is as follows: ; In the formula, represents the pheromone concentration from the current node to the th node, represents a constant value, which can be taken as 1, represents the optimization objective function value of the network optimization model.

[0051] Step 106: The path - selection module is used to construct a path - selection strategy for path selection according to the ant - colony parameters to obtain the first path.

[0052] Iteratively execute the judgment step until the end of the current bus line is traversed to obtain the first path; the judgment step is as follows: Calculate the transition probability of the ant at the current node based on the ant colony parameters to determine the next node and obtain the first node; after obtaining the first node, randomly generate a probability value. If the probability value is less than the preset decision value, randomly explore unvisited nodes to obtain the second node; if the probability value is greater than or equal to the preset decision value, calculate the transition probability of the first node and use its next node as the second node; judge whether the second node is the same as the end of the current bus line where it is located; if the second node is different from the end of the current bus line, use the next node of the current second node as the first node to execute the judgment step; if the second node is the same as the end of the current bus line, use the current second node as the first node to execute the judgment step.

[0053] Specifically, the total number of nodes of the bus lines in the bus network graph is , denoted as . Traditionally, the ant colony algorithm is usually used for path selection in bus line optimization. However, the pheromone in the initial stage of the ant colony algorithm is usually evenly distributed, and the path selection of ants is close to random, requiring a large number of iterations to form a significant difference in pheromone concentration. Although its positive feedback mechanism can accelerate convergence, in large-scale problems, the pheromone accumulation process is slow, resulting in low solution efficiency and slow convergence speed. This application conducts path-guided selection according to the path selection strategy, which can accelerate the convergence speed and improve the global search ability.

[0054] Traditionally, the heuristic information is usually defined as the reciprocal of the distance between two points, while this application adds multiple parameters to define the heuristic information. Specifically, the multiple parameters include the direct passenger flow, line length, and line non-straightness coefficient.

[0055] Construct a transfer strategy based on the ant colony parameters, calculate the transition probability of the ant through the transfer formula, and select the transfer path. Then construct a random strategy to guide the ant to explore more different paths through the random formula, avoid falling into the local optimum problem, and increase the possibility of finding the global optimum solution.

[0056] Among them, the transfer formula is specifically as follows: ; where ; In the formula, represents the transfer probability of the th ant transferring from the current node to the nd node, represents the current node, represents the unvisited candidate node, represents the th node in the bus network graph, represents the pheromone concentration, represents the heuristic information, represents from the current node to the pheromone concentration on the path between the represents from the current node to the unvisited candidate node pheromone concentration on the path between them, represents from the current node to the heuristic information of the represents from the current node to the unvisited candidate node heuristic information, represents the set of nodes that have been visited by the current ant, represents the pheromone importance factor, represents the heuristic importance factor, and represents the direct passenger flow from the next candidate node to the nodes that have been traveled and the direct passenger flow from the nodes that have been traveled to the next candidate node, represents the length of the current route when the ant reaches the next candidate node, represents the non - straight - line coefficient of the current bus route that has been traveled.

[0057] Random formula, specifically as follows: ; In the formula, represents the second node determined by the random strategy, represents the next node determined by the transfer strategy, represents the unvisited candidate node, represents a random probability value, represents the probability of randomly selecting other nodes, which is a preset decision value and is a fixed value between 0 and 1.

[0058] Among them, based on the search result of the ant, that is, the first path, the pheromone concentration on the first path is updated to prompt the ant to explore other possible paths subsequently. When the random strategy selects a path, although it depends on the pheromone concentration and heuristic information, after each selection of the next node using the pheromone concentration and heuristic information, a certain randomness is introduced through the probability selection mechanism. According to the preset decision value judging whether to execute the random strategy can avoid the premature convergence of the optimized ant colony algorithm.

[0059] Step 107: Penalty module, which is used to perform penalty processing on the first path that meets the restriction conditions, so as to update the pheromone on the first path. The restriction conditions include: The node that the ant has passed through is detected by the line network optimization model during the exploration of the first path; and / or, The first path does not meet the preset length; and / or, The first path does not meet the non-straight line coefficient constraint.

[0060] Specifically, for the first path that meets the restriction conditions, perform pheromone update processing. There may be some infeasible solutions in the first path determined according to the path selection strategy. Since the infeasible solutions will affect the overall solution quality, the pheromone on the first path that does not meet the constraint conditions is evaporated additionally as penalty processing. The preset length is 15 - 25 kilometers, and the non-straight line coefficient constraint is 1 - 1.4.

[0061] Step 108: Crossover and mutation module, which is used to perform crossover and mutation processing on the first path after penalty processing to obtain a second path, and evaluate the second path to determine the first optimized path.

[0062] Select two bus lines with crossover points from the first path after penalty processing, and use the crossover point as a common node; perform single-point crossover processing on the section between the common node and the end point of the current bus line to obtain a crossover line; randomly replace one node in the crossover line with a preset node to obtain the second path.

[0063] Exemplarily, based on the genetic algorithm, perform crossover and mutation processing on the first path after penalty processing. Two bus lines with crossover points that need to be optimized can be selected and , and define the station sequence of bus line as , and define the station sequence of bus line as .

[0064] Select an appropriate crossover point on these two bus lines for crossover processing. Exemplarily, the crossover point is and , where . At the crossover point , perform single-point crossover processing. Specifically, it is manifested as exchanging the sections of the two bus lines after the crossover point . For bus line , keep the bus stop sequence from the starting point to the crossover point unchanged, and then continue with bus line from The sequence of bus stops to the end point, i.e., For the bus line , keep the sequence of bus stops from the starting point to the intersection point unchanged, and then follow it with the sequence of bus stops of the bus line from to the end point, i.e., .

[0065] The specific method for generating a new crossover line is as follows: , ; Randomly select a node in the new crossover line , and perform mutation processing at its position. Exemplarily, replace with an alternative node . The alternative node can be selected from the nodes in the bus network diagram other than the starting and ending points, and is adjacent to , and the distance is within 1 kilometer, i.e., and are connected by an edge to . Similarly, perform similar mutation processing on the new bus line to obtain the second path.

[0066] Determine the optimal objective function value of the second path. If it is better than the optimal objective function value of the first path after penalty processing, update the pheromone on the second path to obtain the first optimized path.

[0067] Specifically, calculate the optimal objective function value on the second path after crossover and mutation processing, and evaluate it. If it is better than the optimal objective function value on the first path after penalty processing, replace the first path with the second path, and at the same time update the pheromone concentration to obtain the first optimized path; otherwise, use the first path after penalty processing as the first optimized path.

[0068] Step 109: Adjustment module, used to adjust the importance factor of the first optimized path according to the number of iterations until the preset number of iterations is reached to obtain the optimal path.

[0069] Dynamically adjust the pheromone importance factor and the heuristic importance factor according to the adjustment formula to obtain the optimal path.

[0070] Among them, the adjustment formula is as follows: ; ; In the formula, and represent the pheromone importance factor and the heuristic importance factor at the th iteration, and represent the initial value and the maximum value of the pheromone importance factor respectively, and represent the initial value and the minimum value of the heuristic importance factor respectively, and represent control parameters, represents the number of iterations of the network optimization model, represents a mathematical constant.

[0071] Among them, and are used to control and to gradually approximate the maximum and minimum values of the preset importance factors, and make the change graph of iterative convergence smoother, improving the global search ability and convergence speed of the optimized ant colony algorithm. Define an optimization objective function based on the optimized ant colony algorithm, and iteratively execute the update steps until the preset number of iterations is reached. Among them, the update steps include: updating the pheromone on the first optimized path, and adjusting the pheromone importance factor and the heuristic factor. Determine whether the preset number of iterations is reached. As the number of iterations increases, gradually increases, gradually decreases until reaching the minimum value. Dynamically adjust and at different stages of the optimized ant colony algorithm through adjustment formulas, so that it enhances the influence of pheromone in the initial stage, increases the exploration intensity, searches for more possible solutions, strengthens development in the later stage, weakens the influence of heuristic information, and makes full use of the existing first optimized path to achieve a more effective balance between exploration and development.

[0072] Step 110: Determine whether the preset number of iterations is reached. If the preset number of iterations is not reached, continue to execute Steps 106 to 109 until the preset number of iterations is reached. Among them, the number of iterations is 200 times.

[0073] Step 111: Obtain the optimal path. If the preset number of iterations has been reached, end the iteration and obtain the optimal path, that is, obtain the optimized bus network diagram.

[0074] In the embodiments of the present application, by comparing the optimization objective function with the direct passenger flow, the effects of the optimized ant colony algorithm, the traditional ant colony algorithm, and the genetic algorithm are verified. The present application evaluates the ability of the optimized ant colony algorithm to meet the global optimal objective. The direct passenger flow, as a key evaluation index for bus line design, is directly related to the travel experience of passengers and the effectiveness of bus lines. Optimizing the passenger flow can significantly reduce the number of transfers and improve the travel experience and convenience of passengers.

[0075] Among them, the calculation of the direct passenger flow is specifically as follows: ; In the formula, represents the direct passenger flow, represents the total number of nodes in the bus network graph, represents the current node, represents the th node in the bus network graph, represents the direct passenger flow from the current node to the th node.

[0076] As Figures 5-9 shown, it is an experimental comparison graph on the bus line, which is the experimental result of the convergence change obtained by comparing the optimization objective function of the optimized ant colony algorithm with the traditional ant colony algorithm and the genetic algorithm with the number of iterations. Figures 5-9 In it, the abscissa represents the number of iterations, the ordinate represents the value of the optimization objective function of the network optimization model, GA represents the genetic algorithm, ACO represents the traditional ant colony algorithm, and OURS-ACO represents the optimized ant colony algorithm in the present application.

[0077] Exemplarily, five representative bus lines 268, 311, 600, 616, and 734 within Xi'an City were selected as the experimental objects. The number of iterations was set to 200 times. Optimization solutions were carried out respectively under the traditional ant colony algorithm and the optimized ant colony algorithm, and the obtained results were systematically compared and analyzed. Compared with the traditional algorithm, the optimized ant colony algorithm can improve the optimization objective function value faster, and the optimization objective function value rises steadily during the convergence process, showing better performance and consistency, and can continuously discover better solutions, further verifying its effectiveness and practicality in bus network optimization. For each bus line, the optimal values, worst values, and average values of the optimization objective function and the direct passenger flow in the results of 10 experiments were respectively recorded to evaluate the comprehensive performance of the optimized ant colony algorithm in terms of global optimal ability and result stability. In addition, as shown in Table 2 below, it is the comparison result table of the objective function values of the optimized ant colony algorithm and other algorithms, and Table 3 is the comparison result table of the direct passenger flow of the optimized ant colony algorithm and other algorithms. In order to further quantify the advantages of the optimized ant colony algorithm in this application, the average optimization result was calculated using the improvement rate formula to intuitively reflect the optimization gain in the actual application scenario.

[0078] Among them, the calculation of the improvement rate formula is specifically as follows: ; In the formula, represents the improvement rate, represents the average value of the optimization objective function values of the optimized ant colony algorithm in this application, represents the average value of the objective function values of the compared genetic algorithm and the traditional ant colony algorithm.

[0079] Table 2 Comparison result table of the objective function values of the optimized ant colony algorithm and other algorithms

[0080] Table 3 Comparison result table of the direct passenger flow of the optimized ant colony algorithm and other algorithms

[0081] In Table 2, , and respectively represent the optimal value, the worst value, and the average value of the objective function values of the genetic algorithm, the traditional ant colony algorithm, and the optimized ant colony algorithm in this application (the objective function value of the optimized ant colony algorithm is the optimized objective function value). GA represents the genetic algorithm, ACO represents the traditional ant colony algorithm, and OURS-ACO represents the optimized ant colony algorithm in this application. It can be seen from Table 2 that in terms of the overall objective function value, that is, the optimized ant colony algorithm shows better performance in terms of the optimal value, the worst value, and the average value. During the optimization process of complex line networks, it can converge to the global optimal solution more quickly and effectively avoid falling into local optima. In addition, the experiment also shows that the optimized ant colony algorithm has strong robustness when dealing with traffic networks of different scales and types, further demonstrating its wide applicability and advantages in practical applications.

[0082] In Table 3, 、 and respectively represent the direct passenger flow volume in the optimal case, the worst case, and the average case. It can be seen from Table 3 that in terms of the direct passenger flow volume of bus lines, compared with the traditional ant colony algorithm and the genetic algorithm, although the optimized ant colony algorithm does not always outperform the above two algorithms in terms of the optimal value and the worst value, from the average value of the overall performance, the optimized ant colony algorithm shows obvious advantages, with varying degrees of improvement on each bus line, intuitively reflecting that the optimized ant colony algorithm in this application has been significantly improved in terms of stability and overall efficiency, especially having stronger adaptability in dealing with complex passenger flow situations.

[0083] Although this application provides method operation steps as described in the embodiments or flowcharts, based on routine or non-creative labor, there may be more or fewer operation steps. The step order listed in this embodiment is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual device or client product executes, it can be executed in the order of the method shown in this embodiment or the drawings or executed in parallel (such as in an environment with parallel processors or multi-threaded processing).

[0084] As Figure 10 shown, the embodiment of this application also provides an optimization device 1000 for a bus line network. The device includes: a data acquisition module 1001, a line network construction module 1002, a model construction module 1003, an optimization objective module 1004, a path selection module 1005, a penalty module 1006, a crossover and mutation module 1007, and an adjustment module 1008, as follows.

[0085] The data acquisition module 1001 is used to acquire bus stop data, GPS operation data of buses, and passenger card swiping data; The network construction module 1002 is configured to construct a bus network diagram based on bus stop data and the GPS operation data of buses; and construct an OD matrix based on the bus network diagram and passenger card-swipe data. The model construction module 1003 is configured to construct a network optimization model based on the ant colony algorithm, input the bus network diagram and the OD matrix into the network optimization model for iteration until a preset number of iterations is reached, and obtain an optimal path; wherein, the network optimization model includes an optimization objective module, a path selection module, a penalty module, a crossover and mutation module, and an adjustment module. The optimization objective module 1004 is configured to define an optimization objective function of the network optimization model according to the bus network diagram and the OD matrix, and initialize ant colony parameters and importance factors. The path selection module 1005 is configured to construct a path selection strategy for path selection according to the ant colony parameters, and obtain a first path. The penalty module 1006 is configured to perform penalty processing on the first path that meets the restriction conditions, so as to update the pheromone on the first path. The crossover and mutation module 1007 is configured to perform crossover and mutation processing on the first path after penalty processing, obtain a second path, and evaluate the second path to determine a first optimized path. The adjustment module 1008 is configured to adjust the importance factor of the first optimized path according to the number of iterations until a preset number of iterations is reached, and obtain an optimal path.

[0086] Some modules in the device described in this application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment, where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0087] The device or module illustrated in the above application embodiments can be specifically implemented by a computer chip or entity, or by a product with certain functions. For the convenience of description, the above device is described by dividing it into various modules according to functions. When implementing the embodiments of this application, the functions of each module can be implemented in the same or multiple software and / or hardware. Of course, the module that implements a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0088] The methods, devices or modules described in this application can be implemented in the form of computer-readable program codes. The controller can be implemented in any appropriate manner. For example, the controller can take the form of, for example, a microprocessor or a processor, a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor, logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program codes, the method steps can be logically programmed to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers to achieve the same functions. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0089] The embodiments of this application also provide a device for executing the optimization method of a bus network. The device includes: a processor; a memory for storing instructions executable by the processor; when the processor executes the executable instructions, the method described in the embodiments of this application is implemented.

[0090] The embodiments of this application also provide a non-volatile computer-readable storage medium, on which a computer program or instructions are stored. When the computer program or instructions are executed, the method described in the embodiments of this application is implemented.

[0091] In addition, in each embodiment of this application, the various functional modules can be integrated in one processing module, or each module can exist alone, or two or more modules can be integrated in one module.

[0092] The above storage medium includes, but is not limited to, random access memory (English: Random Access Memory; abbreviation: RAM), read-only memory (English: Read-Only Memory; abbreviation: ROM), cache (English: Cache), hard disk drive (English: Hard Disk Drive; abbreviation: HDD), or memory card (English: Memory Card). The memory can be used to store computer program instructions.

[0093] From the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary hardware. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, or can also be reflected in the implementation process of data migration. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, mobile terminal, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0094] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. All or part of this application can be used in many general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, mobile communication terminals, multi-processor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on.

[0095] The above embodiments are only used to illustrate the technical solution of this application, rather than to limit this application; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solution recorded in the foregoing embodiments, or perform equivalent replacement on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of this application.

Claims

1. An optimization method for a bus network, characterized in that, Including: Obtaining bus stop data, GPS operation data of buses, and passenger card - swiping data; Constructing a bus network graph according to the bus stop data and the GPS operation data of buses; Constructing an OD matrix according to the bus network graph and the passenger card - swiping data; Constructing a network optimization model based on the ant colony algorithm, inputting the bus network graph and the OD matrix into the network optimization model for iteration until a preset number of iterations is reached to obtain the optimal path; wherein, the network optimization model includes an optimization objective module, a path selection module, a penalty module, a crossover and mutation module, and an adjustment module; The optimization objective module is used to define the optimization objective function of the network optimization model according to the bus network graph and the OD matrix, and initialize the ant colony parameters and importance factors; The path selection module is used to construct a path selection strategy according to the ant colony parameters for path selection to obtain a first path; The penalty module is used to perform penalty processing on the first path that meets the constraint conditions to update the pheromone on the first path; The crossover and mutation module is used to perform crossover and mutation processing on the first path after penalty processing to obtain a second path, and evaluate the second path to determine a first optimized path; The adjustment module is used to adjust the importance factor of the first optimized path according to the number of iterations until a preset number of iterations is reached to obtain the optimal path.

2. The method according to claim 1, characterized in that, The constructing a bus network graph according to the bus stop data and the GPS operation data of buses includes: One - to - one corresponding the GPS operation data of buses and the bus stop data to determine the bus stop sequence and the actual driving path; Constructing nodes according to the bus stop sequence; Taking the actual driving path between each two bus stops as an edge; Constructing the bus network graph according to the nodes and edges.

3. The method according to claim 2, characterized in that The constructing an OD matrix according to the bus network graph and the passenger card - swiping data includes: Performing time matching on the GPS operation data of buses and the passenger card - swiping data to determine the card - swiping location information; Extracting the geographical location information of each node in the bus network graph; Performing spatial matching on the geographical location information and the card - swiping location information to determine the passenger boarding nodes; Defining a distance function according to the geographical location information, constructing a passenger travel chain, and determining the passenger alighting nodes; Determining the passenger flow between the starting and ending points of each bus line according to the passenger boarding nodes and the passenger alighting nodes to construct the OD matrix.

4. The method according to claim 3, characterized in that The defining the optimization objective function of the network optimization model, initializing the ant colony parameters and importance factors according to the bus network graph and the OD matrix includes: Determining the constraint conditions according to the bus network graph and the OD matrix; wherein, the constraint conditions include node spacing, line length, and line non - straightness coefficient; Defining the optimization objective function based on the constraint conditions; Setting pheromone on each bus line, and based on the optimization objective function, taking the starting point of each bus line in the bus network graph as the initial position of the ant colony; Set the initial values and extreme values of the ant colony parameters and the importance factors; wherein, the importance factors include a pheromone importance factor and a heuristic importance factor, and the ant colony parameters include the number of ants, the pheromone concentration, the pheromone evaporation rate, and the number of iterations; Among them, the optimization objective function is as follows: ; wherein, ； ； ； Wherein, represents the optimization objective function value of the line network optimization model, represents the th bus line in the bus line network diagram, represents the set of the number of bus lines in the bus line network diagram, , represents the current node, represents the total number of nodes in the bus line network diagram, represents the th node in the bus line network diagram, and ≠ , represents the direct passenger flow from the current node to the th node, represents the minimum value of the line length of the preset bus line, represents the actual value of the line length of the th bus line, represents the maximum value of the line length of the preset bus line, respectively represent the line non - straightness coefficient of the currently traveled bus line and the preset maximum line non - straightness coefficient, and respectively represent the minimum and maximum values of the preset distance between adjacent two nodes in the bus line, represents the node distance from the current node to the next node in the bus line network diagram, represents the straight - line distance between the starting point and the ending point of the th bus line in the bus line network diagram.

5. The method according to claim 2, wherein Construct a path selection strategy according to the ant colony parameters to select a path, and obtain a first path, including: Iteratively execute the judgment step until the end of the current bus line is traversed to obtain the first path; The judgment step is as follows: Calculate the transfer probability of the ant at the current node based on the ant colony parameters to determine the next node and obtain a first node; After obtaining the first node, randomly generate a probability value. If the probability value is less than a preset decision value, randomly explore unvisited nodes to obtain a second node; if the probability value is greater than or equal to the preset decision value, calculate the transfer probability of the first node and use its next node as the second node; Judge whether the second node is the same as the end of the current bus line where it is located; If the second node is different from the end of the current bus line, use the next node of the current second node as the first node to execute the judgment step; If the second node is the same as the end of the current bus line, use the current second node as the first node to execute the judgment step.

6. The method according to claim 1, wherein Perform penalty processing on the first path that meets the constraint conditions to update the pheromone on the first path, including: The constraint conditions include: The line network optimization model detects nodes that the ant has passed through during the exploration of the first path; and / or, The first path does not meet the preset length; and / or, The first path does not meet the non-linear coefficient constraint.

7. The method according to claim 1, characterized in that Perform crossover and mutation processing on the first path after penalty processing to obtain a second path, and evaluate the second path to determine a first optimized path, including: Select two bus lines with intersection points in the first path after penalty processing, and use the intersection point as a common node; Perform single-point crossover processing on the section between the common node and the end of the current bus line to obtain a crossover line; Randomly replace one node in the crossover line with a preset node to obtain the second path; Determine the optimization objective function value of the second path. If it is better than the optimization objective function value of the first path after penalty processing, update the pheromone on the second path to obtain the first optimized path; otherwise, use the first path after penalty processing as the first optimized path.

8. The method according to claim 4, characterized in that, Adjust the importance factors of the first optimized path according to the number of iterations until the preset number of iterations is reached to obtain the optimal path, including: Dynamically adjust the pheromone importance factor and the heuristic importance factor according to the adjustment formula to obtain the optimal path; wherein, the adjustment formula is as follows: ； ； In the formula, and represent the pheromone importance factor and the heuristic importance factor at the -th iteration, and represent the initial value and the maximum value of the pheromone importance factor respectively, and represent the initial value and the minimum value of the heuristic importance factor respectively, and represent control parameters, represents the number of iterations of the line network optimization model, represents a mathematical constant.

9. An optimization device for a bus network, characterized in that, Include: A data acquisition module for acquiring bus stop data, GPS operation data of buses, and passenger card swiping data; A line network construction module, configured to construct a bus line network diagram according to the bus stop data and the GPS operation data of buses; Construct an OD matrix according to the bus line network diagram and the passenger card swiping data; A model construction module, configured to construct a line network optimization model based on the ant colony algorithm, input the bus line network diagram and the OD matrix into the line network optimization model for iteration until a preset number of iterations is reached, and obtain an optimal path; wherein, the line network optimization model includes an optimization objective module, a path selection module, a penalty module, a crossover and mutation module, and an adjustment module; The optimization objective module is configured to define an optimization objective function of the line network optimization model according to the bus line network diagram and the OD matrix, and initialize ant colony parameters and importance factors; The path selection module is configured to construct a path selection strategy for path selection according to the ant colony parameters, and obtain a first path; The penalty module is configured to perform penalty processing on the first path that meets the restriction conditions, so as to update the pheromone on the first path; The crossover and mutation module is configured to perform crossover and mutation processing on the first path after penalty processing, obtain a second path, and evaluate the second path to determine a first optimized path; The adjustment module is configured to adjust the importance factor of the first optimized path according to the number of iterations until a preset number of iterations is reached, and obtain the optimal path.

10. An apparatus for performing an optimization method of a bus network, characterized in that, It includes: A processor; A memory for storing instructions executable by the processor; When the processor executes the executable instructions, the method described in any one of claims 1 to 8 is implemented.

Images