Bus route optimization methods, devices, systems and electronic equipment

Abstract

This invention provides a method for optimizing bus routes. The method includes: acquiring a bus route map and bus stop data in a target area; determining a path network map based on the bus route map and bus stop data; identifying round-trip stops with concentrated bus demand in the target area based on the path network map and bus stop data; using these round-trip stops as slime mold foraging nodes; simulating foraging using bus stop data to determine the weight values ​​corresponding to the slime mold foraging nodes; performing road retrieval using the weight values ​​and bus stop data to obtain target stops; and optimizing bus routes in the target area based on the weight values ​​and target stops. By utilizing slime mold foraging behavior for road retrieval, the method fully considers the correlation between bus stop data and bus route accessibility, and optimizes bus routes in the target area based on weight values ​​and target stops, thus improving the scientific rigor, accuracy, and efficiency of bus route optimization.

Description

Technical Field

[0001] This invention relates to the field of road planning, and more particularly to a method, apparatus, system, electronic device, and storage medium for optimizing bus routes. Background Technology

[0002] With the acceleration of urbanization, public transportation is playing an increasingly important role in urban transportation. As a crucial component of public transportation, the optimization of bus routes is of great significance for improving service quality, alleviating traffic congestion, and promoting urban development. However, current bus route optimization relies primarily on experience and manual planning, lacking scientific rigor and accuracy, and is inefficient. Therefore, providing a method for optimizing bus routes that addresses the current shortcomings in scientific rigor, accuracy, and efficiency has become an urgent problem to be solved. Summary of the Invention

[0003] This invention provides a method for optimizing bus routes, aiming to address the problems of insufficient scientific rigor, accuracy, and low efficiency in existing bus route optimization methods. By utilizing slime mold foraging behavior for road retrieval, it can fully consider the correlation between bus stop passenger flow data, bus stop arrival and departure data, bus stop route data, passenger flow data between bus stops and destinations, bus stop location data, and bus route accessibility. This allows for more scientific and accurate determination of target stops, and bus route optimization of the target area is performed based on weight values ​​and target stops, thereby improving the scientific rigor, accuracy, and efficiency of bus route optimization.

[0004] In a first aspect, embodiments of the present invention provide a method for optimizing bus routes, characterized in that the method includes the following steps:

[0005] Obtain bus route maps and bus stop data for the target area;

[0006] Based on the bus route map and the bus stop data, a route network diagram is determined;

[0007] Based on the route network diagram and the bus stop data, determine the round-trip stops with concentrated bus demand in the target area;

[0008] The round-trip stations are used as slime mold foraging nodes. Foraging simulation is performed using the bus stop data to determine the weight value corresponding to the slime mold foraging node. Road search is performed using the weight value and the bus stop data to obtain the target station.

[0009] Based on the weight values ​​and the target stations, bus routes in the target area are optimized.

[0010] Optionally, before obtaining the bus route map and bus stop data in the target area, the method further includes:

[0011] Acquire internal image sequences of buses, bus GPS data, and bus card swipe data within the target area;

[0012] The bus interior image sequence is processed by a preset bus head and shoulder vision algorithm to obtain bus passenger recognition results.

[0013] Based on the bus passenger recognition results, the bus GPS data, and the bus card swipe data, the bus stop data is determined.

[0014] Optionally, determining the round-trip stops with concentrated bus demand in the target area based on the route network map and the bus stop data includes:

[0015] Based on the path network diagram and the bus stop data, the characteristics of overlapping bus routes in the target area are determined.

[0016] Based on the characteristics of the overlapping areas of the bus routes, the round-trip stops with concentrated bus demand in the target area are identified.

[0017] Optionally, the step of using the round-trip stations as slime mold foraging nodes, and performing foraging simulation using the bus stop data to determine the weight value corresponding to the slime mold foraging node includes:

[0018] Based on the bus stop data and the round-trip stops, the fitness function of the foraging simulation is determined;

[0019] Based on the fitness function, the weight of the position of the slime mold individual during the foraging simulation is determined;

[0020] The round-trip stations are used as slime mold foraging nodes. Foraging simulation is performed based on the weight of the slime mold individual's location during the foraging simulation, and the weight value corresponding to the slime mold foraging node is determined.

[0021] Optionally, the step of performing foraging simulation based on the weight of the position of the slime mold individual during the foraging simulation, and determining the weight value corresponding to the slime mold foraging node, includes:

[0022] Based on the biological behavior of slime molds, the foraging rules of the foraging simulation were determined;

[0023] Based on the foraging rules and the weight of the position of the slime mold individual during the foraging simulation, a foraging simulation is performed to determine the weight value corresponding to the slime mold foraging node.

[0024] Optionally, the step of performing road retrieval using the weight value and the bus stop data to obtain the target station includes:

[0025] The weight of the location of the slime mold individual is updated using the weight value and the bus stop data;

[0026] A weight threshold is set based on the weight of the location of the slime mold individual;

[0027] When the weight of the location of the slime mold individual is lower than the weight threshold, the foraging speed of the slime mold individual is reduced, and global road search is performed;

[0028] When the weight of the location of the slime mold individual is higher than the weight threshold, the foraging speed of the slime mold individual is increased, local road retrieval is performed, and the target station is obtained.

[0029] Optionally, the step of optimizing bus routes in the target area based on the weight values ​​and the target stations includes:

[0030] Based on the weight values, the weight ranking of the target sites is determined;

[0031] Based on the weight ranking of the target stations, determine the route combination ranking among the target stations;

[0032] Based on the route combination sorting, the initial path between the target stations is determined;

[0033] Based on the initial path between the target sites and the weight value, the vein width of slime mold in the initial path is determined;

[0034] Based on the vein width and the initial path, determine the optimized bus route for the target area;

[0035] Based on the optimized bus routes and the bus stop data, bus routes in the target area are optimized.

[0036] Optionally, the step of optimizing bus routes in the target area based on the optimized bus routes and the bus stop data includes:

[0037] Based on the bus stop data, the bus route optimization target for the target area is determined;

[0038] Calculate the fitness value of the bus route optimization path. If the fitness value satisfies the bus route optimization objective of the target area, then optimize the bus routes in the target area based on the bus route optimization path.

[0039] If the fitness value does not meet the bus route optimization target of the target area, the foraging simulation is repeated, and the bus optimization path with the fitness value closest to the bus route optimization target is selected.

[0040] Optionally, optimizing bus routes in the target area based on the optimized bus route includes:

[0041] Obtain a real-time map of the target area;

[0042] The latitude and longitude of the optimized bus route are compared with the latitude and longitude of the real-time map and the latitude and longitude of the bus stops in the real-time map to obtain the optimized bus stops of the optimized bus route.

[0043] Based on the optimized bus routes and optimized bus stops, bus routes in the target area are optimized.

[0044] Secondly, embodiments of the present invention also provide a bus route optimization device, the bus route optimization device comprising:

[0045] The first acquisition module is used to acquire bus route maps and bus stop data in the target area;

[0046] The first determining module is used to determine a route network diagram based on the bus route map and the bus stop data;

[0047] The second determining module is used to determine the round-trip stations with concentrated bus demand in the target area based on the path network map and the bus stop data.

[0048] The first foraging simulation module is used to take the round-trip stations as slime mold foraging nodes, perform foraging simulation using the bus station data, determine the weight value corresponding to the slime mold foraging node, and perform road retrieval using the weight value and the bus station data to obtain the target station.

[0049] The first optimization module is used to optimize bus routes in the target area based on the weight values ​​and the target stations.

[0050] Thirdly, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the bus route optimization method provided in embodiments of the present invention.

[0051] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the bus route optimization method provided in the embodiments of the present invention.

[0052] In this embodiment of the invention, a bus route map and bus stop data in the target area are acquired. Based on the bus route map and bus stop data, a path network map is determined. Based on the path network map and bus stop data, the round-trip stops with concentrated bus demand in the target area are identified. These round-trip stops are used as slime mold foraging nodes. Foraging simulation is performed using bus stop data to determine the weight values ​​corresponding to the slime mold foraging nodes. Road retrieval is performed using the weight values ​​and bus stop data to obtain the target stops. Based on the weight values ​​and target stops, bus routes in the target area are optimized. By utilizing slime mold foraging behavior for road retrieval, the correlation between bus stop passenger flow data, bus stop gathering and dispersal data, bus stop route data, passenger flow data between bus round-trip stops, bus stop location data, and bus route accessibility can be fully considered. This allows for a more scientific and accurate determination of target stops. Furthermore, by optimizing bus routes in the target area based on the weight values ​​and target stops, the scientific rigor, accuracy, and efficiency of bus route optimization are improved. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a flowchart of a bus route optimization method provided in an embodiment of the present invention;

[0055] Figure 2 This is a schematic diagram of a bus route provided in an embodiment of the present invention;

[0056] Figure 3 This is a schematic diagram of bus stop data provided in an embodiment of the present invention;

[0057] Figure 4 This is a schematic diagram illustrating the overlapping area features of a bus route according to an embodiment of the present invention;

[0058] Figure 5 This is a schematic diagram of a public transport route optimization provided by an embodiment of the present invention;

[0059] Figure 6 This is a schematic diagram of the structure of a bus route optimization device provided in an embodiment of the present invention;

[0060] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0062] like Figure 1 As shown, Figure 1 This is a flowchart of a bus route optimization method provided in an embodiment of the present invention, including:

[0063] 101. Obtain bus route maps and bus stop data for the target area.

[0064] In this embodiment of the invention, the above-mentioned bus route optimization method can be deployed in a traffic management platform. The traffic management platform can be a server or server cluster with functions such as image recognition, data processing, data storage, and data transmission. The traffic management platform can store a route map of the target area. The route map of the target area includes all roads in the target area. All roads can be rural dirt roads, urban roads, provincial highways, national highways, and other roads in the target area that are passable by vehicles.

[0065] The target area mentioned above can be any area requiring bus route optimization. The bus route map includes bus routes within the target area, and each bus route includes the corresponding bus stops and their latitude and longitude data. It should be noted that these bus routes are not exclusively for buses; they can be understood as pre-defined routes for buses, which can be used by buses or other vehicles. The bus route map also includes the latitude and longitude coordinates of these bus routes.

[0066] The aforementioned bus stop data includes bus stop passenger flow data, bus stop arrival and departure volume data, bus stop route data, passenger flow data between bus stops, and bus stop location data. The aforementioned bus stop passenger flow data refers to the number of passengers boarding at the aforementioned bus stop, which can include the number of passengers boarding each bus at the aforementioned bus stop. The aforementioned bus stop location data can be represented by latitude and longitude coordinates, UTM coordinates, MGRS coordinates, etc. The aforementioned bus stops can represent two or more bus stops, with interconnected bus routes between the two bus stops. The aforementioned passenger flow data between bus stops can be understood as the passenger volume between the two bus stops. Specifically, if the aforementioned two bus stops include a first bus stop and a second bus stop, then the passenger volume between the two bus stops can include the passenger volume from the first bus stop to the second bus stop within a certain period of time, or the passenger volume from the second bus stop to the second bus stop within a certain period of time. The aforementioned first time can be a unit of time such as a day or a week, or it can also be a fixed time period within a day, such as the morning peak period or the evening peak period.

[0067] The aforementioned bus stop passenger flow data can be understood as the number of passengers boarding and alighting at each of the aforementioned bus stops when all bus routes pass through those stops. The bus route data can include information such as the routes passing through the aforementioned bus stops, their origin, destination, route number, surrounding landmarks, departure and arrival times, bus frequency, and route trajectory.

[0068] The aforementioned passenger flow data for bus stops can also be expressed using OD passenger flow data. The aforementioned OD passenger flow data is determined based on OD data, which includes the passenger boarding and alighting locations and passenger volume. The aforementioned OD passenger flow data is determined by the aforementioned passenger boarding and alighting locations and passenger volume.

[0069] In one possible embodiment, if the traffic management platform only obtains the passenger flow data and bus stop location data of the bus stops, it can determine the bus stops with connecting roads in the target area based on the bus stop location data, and determine them as inter-bus stops. Based on the inter-bus stops and the passenger flow data of the bus stops, it can determine the passenger flow data between the inter-bus stops.

[0070] In one possible embodiment, when the above-mentioned bus route optimization method is deployed in the above-mentioned traffic management platform, the traffic management platform obtains the bus route map and bus stop data of the target area uploaded by the user through the above-mentioned data transmission function.

[0071] In another possible embodiment, cameras and GPS positioning devices can be deployed inside buses in the target area. The cameras can capture images of the interior of the buses. When the bus route optimization method is deployed in the traffic management platform, the traffic management platform acquires images captured by the cameras deployed inside all buses in the target area through the data transmission function. Based on the images, image recognition is performed to determine the bus stop data. Based on the GPS positioning device, the location of the buses is located in real time. Based on the real-time location of all buses in the target area, the bus route map in the target area is determined.

[0072] 102. Based on the bus route map and bus stop data, determine the route network diagram.

[0073] In this embodiment of the invention, the aforementioned path network diagram is a planar diagram. The aforementioned bus route map and the aforementioned bus stop data are proportionally superimposed onto the route map of the target area to obtain the aforementioned path network diagram, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of the above bus routes superimposed on the above route map, where light-colored routes are bus routes and dark-colored routes are non-bus routes.

[0074] like Figure 3 As shown, Figure 3 This is a schematic diagram of the bus stop data overlaid on the route map. The dots of different sizes in the diagram represent bus stops. Based on the location data of the bus stops, the location of the bus stops on the route map is determined. Based on the passenger flow data of the bus stops, the radius of the bus stops is determined. Specifically, the larger the passenger flow data of the bus stops, the larger the radius of the corresponding bus stops; the smaller the passenger flow data of the bus stops, the smaller the radius of the corresponding bus stops.

[0075] For example, Figure 3It includes six station radius types: a first radius type, a second radius type, a third radius type, a fourth radius type, a fifth radius type, and a sixth radius type. The radius of the bus stop corresponding to the first radius type is smaller than the radius of the bus stop corresponding to the second radius type; the radius of the bus stop corresponding to the second radius type is smaller than the radius of the bus stop corresponding to the third radius type; the radius of the bus stop corresponding to the third radius type is smaller than the radius of the bus stop corresponding to the fourth radius type; and the radius of the bus stop corresponding to the fifth radius type is smaller than the radius of the bus stop corresponding to the sixth radius type. The radius of the bus stop is defined as follows: when the passenger flow data of the bus stop is less than 30, it is the first radius type; when the passenger flow data of the bus stop is 30-59, it is the second radius type; when the passenger flow data of the bus stop is 60-89, it is the third radius type; when the passenger flow data of the bus stop is 90-119, it is the fourth radius type; when the passenger flow data of the bus stop is 120-150, it is the fifth radius type; and when the passenger flow data of the bus stop is greater than 150, it is the sixth radius type.

[0076] In one possible embodiment, after the traffic management platform obtains the bus route map and bus stop data in the target area, it maps the bus route map and bus stop data to the route map of the target area within the traffic management platform to obtain the path network map.

[0077] 103. Based on the route network diagram and bus stop data, identify the round-trip stops in the target area where bus demand is concentrated.

[0078] In this embodiment of the invention, the aforementioned bus demand concentration stations can be understood as stations with large bus station gathering and dispersal data and large passenger flow data between the corresponding bus stations. Specifically, stations with large numbers of passengers boarding and alighting at the bus station and large passenger flow data between the corresponding bus stations can be identified as the aforementioned bus demand concentration stations. If the number of passengers boarding at the bus station is large and the number of passengers alighting at the bus station is small, or the number of passengers boarding at the bus station is small and the number of passengers alighting at the bus station is large, and the passenger flow data between the corresponding bus stations is small, then the corresponding bus station cannot be used as the aforementioned bus demand concentration station.

[0079] In one possible embodiment, after the traffic management platform determines the route network map based on the bus route map and bus stop data, it determines the bus stops in the route network map that have both a large number of passengers boarding and alighting and have corresponding large passenger flow data between the aforementioned bus stops, based on the bus stop location data, bus stop passenger flow data, passenger flow data between bus stops, and bus stop arrival and departure volume data in the bus stop data. The bus stops with both a large number of passengers boarding and alighting and corresponding large passenger flow data between the aforementioned bus stops are designated as the aforementioned bus demand concentration stations.

[0080] In another possible embodiment, when the traffic management platform identifies bus stops with both large numbers of passengers boarding and alighting, and correspondingly larger passenger flow data between the aforementioned bus stops, as the round-trip stops of the aforementioned bus demand cluster, the platform then designates the straight-line route between two round-trip stops of the bus demand cluster with similar passenger flow data as the round-trip route between the two bus demand clusters. Specifically, if the number of passengers boarding at one of the bus demand clusters is 152 and the number of passengers alighting at that bus stop is 88 within a certain period, and the number of passengers boarding at another bus demand cluster is 85 and the number of passengers alighting at that bus stop is 150 within a certain period, and these two bus stops are round-trip stops to each other, then the straight-line route between the two round-trip stops of the aforementioned bus demand clusters can be designated as the round-trip route of the bus demand cluster.

[0081] 104. Using the stations to and from the destination as slime mold foraging nodes, foraging simulation is performed using bus stop data to determine the weight values ​​corresponding to the slime mold foraging nodes. Road search is then performed using the weight values ​​and bus stop data to obtain the target stations.

[0082] In this embodiment of the invention, the foraging simulation is based on the biological behavior of slime molds. The slime molds may contain biological oscillators, which are used to sense the passenger flow data of the bus stops corresponding to the round-trip stations. Specifically, when the passenger flow data of the bus stops is higher, the vibration frequency of the biological oscillator is higher and the propagation wave generated is stronger. When the passenger flow data of the bus stops is lower, the vibration frequency of the biological oscillator is lower and the propagation wave generated is weaker.

[0083] Based on the biological behavior of the slime mold described above, the simulation rules for the foraging simulation are abstracted. These simulation rules include a first simulation rule, a second simulation rule, and a third simulation rule. The first simulation rule simulates the slime mold initially approaching a bus stop, moving in a circular or fan-shaped structure using the bus stop data. The second simulation rule states that when the slime mold finds the bus stop, the higher the bus stop traffic data corresponding to that stop, the stronger the propagation wave generated by the biological vibrator within the slime mold, and the faster the slime mold's path flow. The third simulation rule states that during the foraging simulation, when the slime mold diffuses to find the bus stop, it senses the bus stop passenger flow data in all directions based on the biological vibrator. The direction with higher bus stop passenger flow data has a higher weight value for the bus stop in that direction, and the direction with lower bus stop passenger flow data has a lower weight value for the bus stop in that direction.

[0084] The aforementioned road retrieval can be performed using the aforementioned slime mold. This road retrieval includes global road retrieval and local road retrieval. Global road retrieval can be understood as follows: when the foraging simulation is in its initial state, and the biological oscillator has not found a retrieval direction where the passenger flow data at a bus stop exceeds the preset road retrieval threshold, the diffusion speed in all directions is consistent. Local road retrieval can be understood as follows: when the biological oscillator finds a retrieval direction where the passenger flow data at a bus stop exceeds the preset road retrieval threshold, the diffusion speed in that direction is accelerated. Specifically, the diffusion speed can also be determined based on the aforementioned weight values. Higher weight values ​​result in faster diffusion speeds in the corresponding direction, while lower weight values ​​result in slower diffusion speeds in the corresponding direction.

[0085] Specifically, the above foraging simulation can also be expressed by the following foraging simulation formula:

[0086]

[0087] Among them, the above The location of the slime mold mentioned above is given by t, which represents the current iteration number. This represents the optimal position at the t-th iteration. Represented as a random number [-a, a]. Expressed as slime mold weight, as well as Let t represent two slime mold individuals randomly selected in the t-th iteration. Represents a random number [-b, b]. Let r represent the position of the slime mold at the t-th iteration, and r represent a random number [0,1].

[0088] The above p can be expressed by the following formula:

[0089] p=tanh(|S(i)-DF|)i=1,2…,N

[0090] The above tanh is a function for calculating the position weight of slime mold individuals, S(i) represents the fitness value of the i-th slime mold individual, and DF represents the optimal fitness value in all iterations.

[0091] It should be noted that the above This is expressed as slime mold weight. The slime mold weight is directly proportional to the weight value. A search direction with a heavier slime mold weight has a higher weight value, and a search direction with a lighter slime mold weight has a lower weight value. This can be expressed using the following weighting formula:

[0092]

[0093] The above r represents a random number [0,1], the above S(i) represents the fitness value of the i-th slime mold individual, bF represents the best fitness value in the current iteration, and ωF represents the worst fitness value in the current iteration.

[0094] In one possible embodiment, after the traffic management platform determines the round-trip stations with concentrated public transportation demand in the target area, it determines the foraging rules of the foraging simulation based on the biological behavior of slime molds, uses the round-trip stations as slime mold foraging nodes, performs foraging simulation through the public transportation station data and the foraging rules, determines the weight values ​​of each direction, determines the weight values ​​of the round-trip stations located in each direction based on the weight values ​​of the round-trip stations in each direction, and performs global and local simulations based on the weight values ​​of the round-trip stations in each direction and the public transportation station data to determine the target station.

[0095] 105. Optimize bus routes in the target area based on weight values ​​and target stations.

[0096] In this embodiment of the invention, generally, the target stations are multiple target stations. The weight values ​​of the multiple target stations can be determined based on the weight values. Based on the weight values ​​of the multiple target stations, the weights are sorted to determine the priority of each target station. Based on the priority of each target station, the paths between each target station are sorted to determine the priority of the paths between each target station. Based on the path priority and the priority of the target stations, the optimized paths and optimized stations are determined. Based on the optimized paths and optimized stations, the bus routes in the target area are optimized.

[0097] For example, if there are three target sites, then the target sites can be identified as a first target site, a second target site, and a third target site. The first target site has a higher priority than the second target site, and the second target site has a higher priority than the third target site. Based on the priorities of the three target sites, the paths between the three target sites are sorted. If the path connecting the first target site and the second target site needs to pass through the third target site, then the path from the first target site to the third target site has a higher priority than the path from the third target site to the second target site.

[0098] In one possible embodiment, after the traffic management platform performs road retrieval using the weight values ​​and bus stop data to obtain target stations, it determines the priority of the target stations and the priority of the paths between the target stations based on the weight values. Based on the priority of the target stations and the priority of the paths between the target stations, it determines an optimized path and overlays the optimized path onto the path network graph in the target area to obtain a new bus route map. Based on the new bus route map, it performs processes such as adding or deleting bus routes in the target area to obtain optimized bus routes.

[0099] In this embodiment of the invention, a bus route map and bus stop data in the target area are acquired. Based on the bus route map and bus stop data, a path network map is determined. Based on the path network map and bus stop data, the round-trip stops with concentrated bus demand in the target area are identified. These round-trip stops are used as slime mold foraging nodes. Foraging simulation is performed using bus stop data to determine the weight values ​​corresponding to the slime mold foraging nodes. Road retrieval is performed using the weight values ​​and bus stop data to obtain the target stops. Based on the weight values ​​and target stops, bus routes in the target area are optimized. By utilizing slime mold foraging behavior for road retrieval, the correlation between bus stop passenger flow data, bus stop gathering and dispersal data, bus stop route data, passenger flow data between bus round-trip stops, bus stop location data, and bus route accessibility can be fully considered. This allows for a more scientific and accurate determination of target stops. Furthermore, by optimizing bus routes in the target area based on the weight values ​​and target stops, the scientific rigor, accuracy, and efficiency of bus route optimization are improved.

[0100] Optionally, before obtaining the bus route map and bus stop data in the target area, the system can also obtain the bus interior image sequence, bus GPS data, and bus card swiping data in the target area; the bus interior image sequence is processed by a preset bus head and shoulder vision algorithm to obtain the bus passenger recognition result; and the bus stop data is determined based on the bus passenger recognition result, bus GPS data, and bus card swiping data.

[0101] In this embodiment of the invention, the aforementioned bus interior image sequence can be acquired using an image acquisition device deployed inside the bus; the aforementioned bus GPS data can be obtained using a GPS positioning device and GPS satellites deployed inside the bus; and the aforementioned bus card swiping data can be obtained using a card swiping payment device deployed inside the bus. It should be noted that the aforementioned card swiping payment device can have functions such as recognizing bus cards and recognizing bus ride QR codes, and can collect payment by recognizing the bus card or the bus ride QR code. The aforementioned bus card swiping data includes the bus card ID, the bus ride QR code ID, the recognition time, the recognition location, and other data. The aforementioned preset bus head and shoulder vision algorithm can be a deep learning-based bus head and shoulder vision algorithm, which achieves rapid and accurate recognition of key areas such as the head and shoulders by training a bus head and shoulder vision model to be trained; or it can be a bus head and shoulder vision algorithm based on gradient calculation or a bus head and shoulder vision algorithm based on constructing a direction histogram.

[0102] In one possible embodiment, the traffic management platform acquires bus interior image sequences, bus GPS data, and bus card swiping data in the target area through the data transmission function. It then performs recognition processing on the bus interior image sequences using a preset bus head-and-shoulder vision algorithm to determine the bus passenger identification result, which includes the number of bus passengers. Based on the bus passenger identification result and the bus GPS data, it determines the number of passengers alighting at the bus stop. Based on the bus card swiping data, it determines the passenger flow data at the bus stop. Based on the passenger flow data and the number of passengers alighting at the bus stop, it determines the bus stop arrival and departure volume data. It then determines the bus stop route data using the bus GPS data and bus route map. Based on the bus stop arrival and departure volume data and the bus stop passenger flow data, it determines the passenger flow data between the bus stops and departure points. Based on the bus GPS data, it determines the bus stop location data. Finally, it integrates the bus stop passenger flow data, bus stop arrival and departure volume data, bus stop route data, passenger flow data between the bus stops and departure points, and bus stop location data to obtain the bus stop data.

[0103] Optionally, in the step of determining the round-trip stations with concentrated bus demand in the target area based on the route network map and bus stop data, the characteristics of overlapping bus routes in the target area can be determined based on the route network map and bus stop data; and the round-trip stations with concentrated bus demand in the target area can be determined based on the characteristics of overlapping bus routes.

[0104] In this embodiment of the invention, the characteristics of the overlapping areas of the aforementioned bus routes can be determined by the round-trip routes and the number of round trips between stations in the target area, such as... Figure 4 The diagram illustrating the overlapping areas of bus routes shows that it includes multiple round-trip stops, the number of round trips between these stops, and the routes themselves. The more round trips between stops, the denser the lines; conversely, the fewer round trips, the sparser the lines. In the diagram, the number of round trips from stops near Shenzhen Station to stops east of Shenzhen East Station is high, resulting in denser lines. Conversely, the number of round trips from stops near the "Luohu District" label to stops east of Luohu District is low, resulting in sparser lines. These densely packed round-trip stops are considered to be the points of high public transport demand in the target area.

[0105] In one possible embodiment, after the traffic management platform determines the route network map based on the bus route map and the bus stop data, it determines the characteristics of the overlapping areas of bus routes in the route network map based on the bus stop data, and takes the densely packed round-trip stops in the overlapping areas of bus routes as the round-trip stops where the bus demand is concentrated.

[0106] Optionally, in the step of using the round-trip stations as slime mold foraging nodes, conducting foraging simulations using bus stop data, and determining the weight values ​​corresponding to the slime mold foraging nodes, the fitness function for the foraging simulation can be determined based on the bus stop data and the round-trip stations; the weight of the slime mold individual's position during the foraging simulation can be determined based on the fitness function; and the weight values ​​corresponding to the slime mold foraging nodes can be determined by using the round-trip stations as slime mold foraging nodes and conducting foraging simulations based on the weight of the slime mold individual's position during the foraging simulation.

[0107] In this embodiment of the invention, the fitness function is used to calculate the weight of the position of the slime mold individual. Specifically, it can be determined based on parameters such as the distance between the current position of the slime mold individual and the slime mold foraging node, the time it takes for the slime mold individual to travel from its current position to the slime mold foraging node, and the energy consumption required for the slime mold individual to travel from its current position to the slime mold foraging node.

[0108] In one possible embodiment, after the traffic management platform determines the round-trip stations with concentrated bus demand in the target area based on the aforementioned path network map and bus stop data, it determines the fitness function for the slime mold to conduct foraging simulation based on parameters such as the distance between the current location of the slime mold individual and the slime mold foraging node, the time it takes for the slime mold individual to travel from its current location to the slime mold foraging node, and the energy consumption for the slime mold individual to travel from its current location to the slime mold foraging node. Based on the fitness function, it determines the weight of the current location of each slime mold individual during the foraging simulation. Based on the weight of the current location of each slime mold individual, it conducts foraging simulation to determine the weight value corresponding to the slime mold foraging node.

[0109] Optionally, in the step of performing foraging simulation based on the weight of the position of the slime mold individual during foraging simulation and determining the weight value corresponding to the slime mold foraging node, the foraging rules of the foraging simulation can be determined based on the biological behavior of the slime mold; and the foraging simulation can be performed based on the foraging rules and the weight of the position of the slime mold individual during foraging simulation to determine the weight value corresponding to the slime mold foraging node.

[0110] In this embodiment of the invention, the foraging rules for the foraging simulation include the first simulation rule, the second simulation rule, and the third simulation rule. Foraging simulation is performed based on the first simulation rule, the second simulation rule, and the third simulation rule, as well as the weight of the position of the slime mold individual during the foraging simulation, to determine the weight value corresponding to the slime mold foraging node.

[0111] In one possible embodiment, after the traffic management platform determines the round-trip stations with concentrated bus demand in the target area based on the above-mentioned path network map and bus stop data, it can determine the above-mentioned first simulation rule, second simulation rule and third simulation rule based on the biological behavior of slime molds, and perform foraging simulation according to the above-mentioned simulation rules and the weight of the position of slime mold individuals during foraging simulation, and determine the weight value corresponding to the above-mentioned slime mold foraging node.

[0112] Optionally, in the step of obtaining the target station by performing road retrieval using weight values ​​and bus stop data, the weight of the location of the slime mold individual can be updated using weight values ​​and bus stop data; a weight threshold can be set based on the weight of the location of the slime mold individual; when the weight of the location of the slime mold individual is lower than the weight threshold, the foraging speed of the slime mold individual is reduced, and a global road retrieval is performed; when the weight of the location of the slime mold individual is higher than the weight threshold, the foraging speed of the slime mold individual is increased, and a local road retrieval is performed to obtain the target station.

[0113] In an embodiment of the present invention, the above weight threshold can be determined according to the overall proportion of the above slime mold individuals in the slime mold individuals. When the above foraging simulation is in the global road retrieval, the foraging speed of the above slime mold individuals is reduced, and the foraging speeds of each slime mold individual are the same. When the above foraging simulation is in the local road retrieval, the foraging speed of the corresponding slime mold individual is increased, and the foraging speeds of the remaining slime mold individuals remain unchanged.

[0114] Specifically, the above global road retrieval and the above local road retrieval can be expressed by the following retrieval formula:

[0115]

[0116] The above is the position of the above slime mold, r represents a random number [0, 1], ub represents the upper bound of the above path network diagram, lb represents the lower bound of the above path network diagram, z can also be understood as the proportion of the above randomly distributed slime mold individuals in the total number of slime mold individuals, represents the best position at the t-th iteration, represents a random number [-a, a], represents the slime mold weight, and represents two slime mold individuals randomly selected at the t-th iteration, represents a random number [-b, b], represents the position of the slime mold at the t-th iteration, and p can be expressed by the above formula "p = tanh(|S(i) - DF|) i = 1, 2…, N".

[0117] It should be noted that when the above r < z, global road retrieval can be performed through "r·(ub - lb) + lb". When z ≤ r < p, local road retrieval can be performed. When p ≤ r, the optimal weight value corresponding to the above slime mold individual converges to 0.

[0118] Optionally, in the step of optimizing the bus line of the target area based on the weight value and the target site, the weight ranking of the target site can be determined based on the weight value; the route combination ranking between the target sites can be determined based on the weight ranking of the target site; the initial path between the target sites can be determined based on the route combination ranking; the vein width of the slime mold in the initial path can be determined based on the initial path between the target sites and the weight value; the bus optimization path of the target area can be determined based on the vein width and the initial path; and the bus line of the target area can be optimized based on the bus optimization path and the bus stop data.

[0119] In this embodiment of the invention, the weight ranking of the target stations can be determined based on the aforementioned weight values. For example, routes are combined between the top-ranked target stations. If the combination is successful, the route combination corresponding to the top-ranked target station will also be ranked higher. If the combination fails, a route is combined between one of the top-ranked target stations and one of the bottom-ranked target stations. If the combination is successful, the route combination corresponding to one of the top-ranked target stations and one of the bottom-ranked target stations will be ranked lower. Based on the aforementioned route combination ranking, an initial path is determined between the target stations. Based on the initial path between the target stations, the aforementioned VB and VC values ​​and the aforementioned weight values ​​corresponding to the initial path are determined. The vein width of the slime mold in the initial path is determined. Based on the vein width and the initial path, a public transport optimization path in the target area is determined. Public transport route optimization is performed in the target area based on the aforementioned public transport optimization path and public transport station data.

[0120] Specifically, the above-mentioned optimized bus routes can be achieved through methods such as... Figure 5 The diagram illustrates a type of optimized bus route. The optimal stop location and S1, S2, and S3 in the diagram can be understood as the target stops mentioned above. The route between the optimal stop location and S1, S2, and S3 is the route with the highest route combination ranking. The remaining route between the optimal stop location and S1, S2, and S3 is the route with the lower route combination ranking. Apart from the optimal stop location and S1, S2, and S3, the remaining roads are bus routes and non-bus routes in the route network mentioned above.

[0121] Optionally, in the step of optimizing bus routes in the target area based on bus route optimization and bus stop data, the bus route optimization target for the target area can be determined based on the bus stop data; the fitness value of the bus route optimization path can be calculated; if the fitness value meets the bus route optimization target for the target area, then the bus route optimization for the target area can be performed based on the bus route optimization path; if the fitness value does not meet the bus route optimization target for the target area, then the foraging simulation is repeated, and the bus route optimization path with the fitness value closest to the bus route optimization target is selected.

[0122] In this embodiment of the invention, the optimization objective can be determined based on the bus stop data in the target area. Specifically, the bus route problems in the target area can be determined based on the bus stop data. If the bus route problems include low frequency of departures, low accessibility, high repetition of routes on major routes, congestion, and long waiting times for passengers, then the optimization objective is to combine the bus stop data and appropriately use methods such as truncation, addition, cancellation, or segmentation to optimize the bus routes, increase the frequency of departures, increase the transfer coefficient, reduce the repetition of routes on major routes, alleviate congestion, and reduce passenger waiting times, thereby achieving the optimization objective of forming a high-frequency and high-accessibility network.

[0123] The fitness value can be calculated using the fitness function. The fitness value of the optimized bus route is compared with the bus route optimization target of the target area. If the fitness value of the optimized bus route meets the bus route optimization target of the target area, the bus route in the target area can be optimized based on the optimized bus route. If the fitness value of the optimized bus route does not meet the bus route optimization target of the target area, the foraging simulation is repeated, and the optimized bus route with the fitness value closest to the bus route optimization target is selected.

[0124] Specifically, if the fitness value of the optimized bus route obtained in the t-th foraging simulation does not meet the bus route optimization objective of the target area, then the optimal bus stop (the optimal bus stop is the stop with the highest weight value in the optimized route obtained in the t-th iteration) is selected from the bus stop data obtained in the t-th foraging simulation as the parameter in the (t+1)-th foraging simulation formula. Two bus stops are randomly selected from the bus stop data obtained in the t-th foraging simulation as parameters in the formula for the (t+1)-th foraging simulation. and parameters Foraging simulation is performed using the (t+1)th foraging simulation formula to obtain the weight values ​​of the (t+1)th foraging simulation. Based on the weight values ​​obtained from the (t+1)th foraging simulation, the (t+1)th weight ranking of the target stations is determined. Based on the (t+1)th weight ranking of the target stations, the (t+1)th route combination ranking between the target stations is determined. Based on the (t+1)th route combination ranking, the (t+1)th initial path between the target stations is determined. Based on the (t+1)th initial path between the target stations and the weight values ​​obtained from the (t+1)th foraging simulation, the vein width of the slime mold in the (t+1)th initial path is determined. Based on the vein width obtained from the (t+1)th foraging simulation and the (t+1)th initial path, the (t+1)th optimized bus route for the target area is determined. Based on the above foraging simulation formula, with the optimization objective of minimizing the fitness value, the weight values ​​corresponding to the slime mold foraging nodes are iterated until the fitness value satisfies the bus route optimization objective or the number of iterations reaches a preset value. At this point, the iteration process stops, and the bus route optimization for the target area is performed based on the updated bus route.

[0125] It should be noted that the closer the fitness value is to 0, the closer the result of the foraging simulation is to the optimization goal of the bus route. As the number of iterations in the above iterative process increases, the parameters vb and vc in the above foraging simulation formula eventually approach 0, and the fitness value also approaches 0.

[0126] Optionally, in the step of optimizing bus routes in the target area based on the optimized bus route, a real-time map of the target area can be obtained; the latitude and longitude of the optimized bus route can be compared with the latitude and longitude of the real-time map and the latitude and longitude of the bus stops in the real-time map to obtain the optimized bus stops of the optimized bus route; and the optimized bus routes in the target area can be optimized based on the optimized bus route and the optimized bus stops.

[0127] In this embodiment of the invention, the real-time map of the target area can be a real-scene map obtained by satellite photography. The real-time map includes the latitude and longitude of the real-time map and the latitude and longitude of the bus stops in the real-time map. The optimized bus route also includes the corresponding latitude and longitude. Based on the latitude and longitude of the real-time map, the latitude and longitude of the real-time route in the real-time map are determined. The latitude and longitude of the real-time route and the latitude and longitude of the bus stops in the real-time map are compared with the optimized bus route to obtain the optimized bus stops of the optimized bus route. By combining the optimized bus route and the optimized bus stops, a new bus route can be obtained. The new bus route is added to the route network, and the bus route optimization is performed on the target area based on the new bus route.

[0128] In one possible embodiment, after the traffic management platform determines the optimized bus route for the target area based on the vein width and the initial path, it acquires the real-scene map obtained by the satellite using the data transmission function. Based on the real-scene map and the optimized bus route, it determines the optimized bus stops, combines the optimized bus stops and the optimized bus route to obtain a new bus route, adds the new bus route to the path network diagram, determines the departure frequency of the new bus route, determines the passenger carrying capacity coefficient of the new bus route based on the departure frequency, and acquires the departure frequency of the bus routes in the path network diagram based on the departure frequency of the bus routes in the path network diagram. If the sum of the passenger carrying capacity coefficient of the new bus route and the passenger carrying capacity coefficient of the bus routes in the path network diagram is greater than the passenger carrying capacity coefficient required for the target area, then the bus routes in the path network diagram can be appropriately reduced to complete the optimization of the bus routes in the target area.

[0129] like Figure 6 As shown, this embodiment of the invention also provides a bus route optimization device, comprising:

[0130] The first acquisition module 601 is used to acquire bus route maps and bus stop data in the target area;

[0131] The first determining module 602 is used to determine a route network diagram based on the bus route map and the bus stop data;

[0132] The second determining module 603 is used to determine the round-trip stations with concentrated bus demand in the target area based on the path network map and the bus stop data.

[0133] The first foraging simulation module 604 is used to take the round-trip stations as slime mold foraging nodes, perform foraging simulation through the bus station data, determine the weight value corresponding to the slime mold foraging node, and perform road retrieval through the weight value and the bus station data to obtain the target station.

[0134] The first optimization module 605 is used to optimize bus routes in the target area based on the weight values ​​and the target stations.

[0135] Optionally, the bus route optimization device further includes:

[0136] The second acquisition module is used to acquire the bus interior image sequence, bus GPS data, and bus card swiping data in the target area;

[0137] The first recognition module is used to perform recognition processing on the internal image sequence of the bus according to a preset bus head and shoulder vision algorithm to obtain the bus riding recognition result;

[0138] The third determining module is used to determine the bus stop data based on the bus passenger recognition result, the bus GPS data, and the bus card swiping data.

[0139] Optionally, the second determining module 603 includes:

[0140] The first determining submodule is used to determine the characteristics of overlapping bus routes in the target area based on the path network diagram and the bus stop data.

[0141] The second determining submodule is used to determine the round-trip stops with concentrated bus demand in the target area based on the characteristics of the overlapping areas of the bus routes.

[0142] Optionally, the first foraging simulation module 604 includes:

[0143] The third determining submodule is used to determine the fitness function of the foraging simulation based on the bus stop data and the round-trip stations;

[0144] The fourth determination submodule is used to determine the weight of the position of the slime mold individual during the foraging simulation based on the fitness function;

[0145] The first foraging simulation submodule is used to take the round-trip stations as slime mold foraging nodes, perform foraging simulation based on the weight of the slime mold individual's location during the foraging simulation, and determine the weight value corresponding to the slime mold foraging node.

[0146] Optionally, the first foraging simulation submodule includes:

[0147] The first determining unit is used to determine the foraging rules of the foraging simulation based on the biological behavior of slime molds;

[0148] The second determining unit is used to perform foraging simulation based on the foraging rules and the weight of the position of the slime mold individual during the foraging simulation, and to determine the weight value corresponding to the slime mold foraging node.

[0149] Optionally, the first foraging simulation module 604 further includes:

[0150] The first update submodule updates the weight of the location of the slime mold individual using the weight value and the bus stop data;

[0151] The first setting submodule is used to set a weight threshold based on the weight of the location of the slime mold individual;

[0152] The global retrieval submodule is used to reduce the foraging speed of the slime mold individual and perform global road retrieval when the weight of the location of the slime mold individual is lower than the weight threshold.

[0153] The local retrieval submodule is used to increase the foraging speed of the slime mold individual and perform local road retrieval to obtain the target station when the weight of the location of the slime mold individual is higher than the weight threshold.

[0154] Optionally, the first optimization module 605 includes:

[0155] The fifth determining submodule is used to determine the weight ranking of the target sites based on the weight values;

[0156] The sixth determining submodule is used to determine the route combination order between the target stations based on the weight order of the target stations;

[0157] The seventh determining submodule is used to determine the initial path between the target stations based on the route combination sorting;

[0158] The eighth determining submodule is used to determine the vein width of slime mold in the initial path based on the initial path between the target sites and the weight value;

[0159] The ninth determining submodule is used to determine the optimized bus route for the target area based on the vein width and the initial path;

[0160] The first optimization submodule is used to optimize bus routes in the target area based on the optimized bus routes and the bus stop data.

[0161] Optionally, the first optimization submodule includes:

[0162] The first determining unit is used to determine the bus route optimization target for the target area based on the bus stop data.

[0163] The first optimization unit calculates the fitness value of the bus optimization path. If the fitness value satisfies the bus route optimization target of the target area, then the bus route in the target area is optimized based on the bus optimization path.

[0164] The second optimization unit is used to re-perform the foraging simulation if the fitness value does not meet the bus route optimization target of the target area, and select the bus optimization path with the fitness value closest to the bus route optimization target.

[0165] Optionally, the first optimization unit includes:

[0166] The first acquisition subunit is used to acquire a real-time map of the target area;

[0167] The first comparison subunit is used to compare the latitude and longitude of the optimized bus route with the latitude and longitude of the real-time map and the latitude and longitude of the bus stops in the real-time map, respectively, to obtain the optimized bus stops of the optimized bus route.

[0168] The first optimization subunit is used to optimize bus routes in the target area based on the optimized bus routes and the optimized bus stops.

[0169] like Figure 7 As shown, this embodiment of the invention also provides an electronic device, characterized in that it includes a processor, which can execute any of the above-described bus route optimization methods.

[0170] Specifically, it includes a processor 701 and a memory 702, as well as a computer program stored in the memory 702 and capable of running on the processor 701 to execute the bus route optimization method, wherein:

[0171] The processor 701 executes the calculator program containing the bus route optimization method stored in memory 702, and performs the following steps:

[0172] Obtain bus route maps and bus stop data for the target area;

[0173] Based on the bus route map and the bus stop data, a route network diagram is determined;

[0174] Based on the route network diagram and the bus stop data, determine the round-trip stops with concentrated bus demand in the target area;

[0175] The round-trip stations are used as slime mold foraging nodes. Foraging simulation is performed using the bus stop data to determine the weight value corresponding to the slime mold foraging node. Road search is performed using the weight value and the bus stop data to obtain the target station.

[0176] Based on the weight values ​​and the target stations, bus routes in the target area are optimized.

[0177] Optionally, before acquiring the bus route map and bus stop data in the target area, the method executed by the processor 701 further includes:

[0178] Acquire internal image sequences of buses, bus GPS data, and bus card swipe data within the target area;

[0179] The bus interior image sequence is processed by a preset bus head and shoulder vision algorithm to obtain bus passenger recognition results.

[0180] Based on the bus passenger recognition results, the bus GPS data, and the bus card swipe data, the bus stop data is determined.

[0181] Optionally, the processor 701's execution of determining the round-trip stops with concentrated bus demand in the target area based on the path network map and the bus stop data includes:

[0182] Based on the path network diagram and the bus stop data, the characteristics of overlapping bus routes in the target area are determined.

[0183] Based on the characteristics of the overlapping areas of the bus routes, the round-trip stops with concentrated bus demand in the target area are identified.

[0184] Optionally, the step executed by processor 701, which uses the round-trip stations as slime mold foraging nodes and performs foraging simulation using the bus stop data to determine the weight value corresponding to the slime mold foraging node, includes:

[0185] Based on the bus stop data and the round-trip stops, the fitness function of the foraging simulation is determined;

[0186] Based on the fitness function, the weight of the position of the slime mold individual during the foraging simulation is determined;

[0187] The round-trip stations are used as slime mold foraging nodes. Foraging simulation is performed based on the weight of the slime mold individual's location during the foraging simulation, and the weight value corresponding to the slime mold foraging node is determined.

[0188] Optionally, the processor 701 performs foraging simulation based on the weights of the slime mold individuals' positions during the foraging simulation, and determines the weight values ​​corresponding to the slime mold foraging nodes, including:

[0189] Based on the biological behavior of slime molds, the foraging rules of the foraging simulation were determined;

[0190] Based on the foraging rules and the weight of the position of the slime mold individual during the foraging simulation, a foraging simulation is performed to determine the weight value corresponding to the slime mold foraging node.

[0191] Optionally, the process executed by processor 701 to perform road retrieval using the weight value and the bus stop data to obtain the target station includes:

[0192] The weight of the location of the slime mold individual is updated using the weight value and the bus stop data;

[0193] A weight threshold is set based on the weight of the location of the slime mold individual;

[0194] When the weight of the location of the slime mold individual is lower than the weight threshold, the foraging speed of the slime mold individual is reduced, and global road search is performed;

[0195] When the weight of the location of the slime mold individual is higher than the weight threshold, the foraging speed of the slime mold individual is increased, local road retrieval is performed, and the target station is obtained.

[0196] Optionally, the optimization of bus routes in the target area based on the weight values ​​and the target stations, performed by the processor 701, includes:

[0197] Based on the weight values, the weight ranking of the target sites is determined;

[0198] Based on the weight ranking of the target stations, determine the route combination ranking among the target stations;

[0199] Based on the route combination sorting, the initial path between the target stations is determined;

[0200] Based on the initial path between the target sites and the weight value, the vein width of slime mold in the initial path is determined;

[0201] Based on the vein width and the initial path, determine the optimized bus route for the target area;

[0202] Based on the optimized bus routes and the bus stop data, bus routes in the target area are optimized.

[0203] Optionally, the process of optimizing bus routes in the target area based on the optimized bus routes and the bus stop data, executed by the processor 701, includes:

[0204] Based on the bus stop data, the bus route optimization target for the target area is determined;

[0205] Calculate the fitness value of the bus route optimization path. If the fitness value satisfies the bus route optimization objective of the target area, then optimize the bus routes in the target area based on the bus route optimization path.

[0206] If the fitness value does not meet the bus route optimization target of the target area, the foraging simulation is repeated, and the bus optimization path with the fitness value closest to the bus route optimization target is selected.

[0207] Optionally, the optimization of bus routes in the target area based on the optimized bus route, performed by the processor 701, includes:

[0208] Obtain a real-time map of the target area;

[0209] The latitude and longitude of the optimized bus route are compared with the latitude and longitude of the real-time map and the latitude and longitude of the bus stops in the real-time map to obtain the optimized bus stops of the optimized bus route.

[0210] Based on the optimized bus routes and optimized bus stops, bus routes in the target area are optimized.

[0211] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the bus route optimization method or the application-side bus route optimization method provided in this invention, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0212] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0213] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for optimizing bus routes, characterized in that, The method includes the following steps: Obtain bus route maps and bus stop data for the target area; Based on the bus route map and the bus stop data, a route network diagram is determined; Based on the route network diagram and the bus stop data, determine the round-trip stops with concentrated bus demand in the target area; The round-trip stations are used as slime mold foraging nodes. Foraging simulation is performed using the bus stop data to determine the weight value corresponding to the slime mold foraging node. Road search is performed using the weight value and the bus stop data to obtain the target station. Based on the weight values ​​and the target stations, bus routes in the target area are optimized. The step of determining the round-trip stops with concentrated public transportation demand in the target area based on the route network map and the bus stop data includes: Based on the path network diagram and the bus stop data, the characteristics of overlapping bus routes in the target area are determined. Based on the characteristics of the overlapping areas of the bus routes, the round-trip stops with concentrated bus demand in the target area are identified. The optimization of bus routes in the target area based on the weight values ​​and the target stations includes: Based on the weight values, the weight ranking of the target sites is determined; Based on the weighted ranking of the target stations, determine the route combination ranking among the target stations; Based on the route combination sorting, the initial path between the target stations is determined; Based on the initial path between the target sites and the weight value, the vein width of slime mold in the initial path is determined; Based on the vein width and the initial path, determine the optimized bus route for the target area; Based on the optimized bus routes and the bus stop data, bus routes in the target area are optimized.

2. The bus route optimization method as described in claim 1, characterized in that, Before acquiring the bus route map and bus stop data in the target area, the method further includes: Acquire internal image sequences of buses, bus GPS data, and bus card swipe data within the target area; The bus interior image sequence is processed by a preset bus head and shoulder vision algorithm to obtain bus passenger recognition results. Based on the bus passenger recognition results, the bus GPS data, and the bus card swipe data, the bus stop data is determined.

3. The bus route optimization method as described in any one of claims 1, characterized in that, The step of using the round-trip stations as slime mold foraging nodes, and conducting foraging simulations using the bus stop data to determine the weight values ​​corresponding to the slime mold foraging nodes includes: Based on the bus stop data and the round-trip stops, the fitness function of the foraging simulation is determined; Based on the fitness function, the weight of the position of the slime mold individual during the foraging simulation is determined; The round-trip stations are used as slime mold foraging nodes. Foraging simulation is performed based on the weight of the slime mold individual's location during the foraging simulation, and the weight value corresponding to the slime mold foraging node is determined.

4. The bus route optimization method as described in claim 3, characterized in that, The step of performing foraging simulation based on the weight of the location of the slime mold individual during the foraging simulation, and determining the weight value corresponding to the slime mold foraging node, includes: Based on the biological behavior of slime molds, the foraging rules of the foraging simulation were determined; Based on the foraging rules and the weight of the position of the slime mold individual during the foraging simulation, a foraging simulation is performed to determine the weight value corresponding to the slime mold foraging node.

5. The bus route optimization method as described in claim 4, characterized in that, The process of obtaining the target station by performing road retrieval using the weight value and the bus stop data includes: The weight of the location of the slime mold individual is updated using the weight value and the bus stop data; A weight threshold is set based on the weight of the location of the slime mold individual; When the weight of the location of the slime mold individual is lower than the weight threshold, the foraging speed of the slime mold individual is reduced, and global road search is performed; When the weight of the location of the slime mold individual is higher than the weight threshold, the foraging speed of the slime mold individual is increased, local road retrieval is performed, and the target station is obtained.

6. The bus route optimization method as described in claim 1, characterized in that, The optimization of bus routes in the target area based on the optimized bus routes and the bus stop data includes: Based on the bus stop data, the bus route optimization target for the target area is determined; Calculate the fitness value of the bus route optimization path. If the fitness value satisfies the bus route optimization objective of the target area, then optimize the bus routes in the target area based on the bus route optimization path. If the fitness value does not meet the bus route optimization target of the target area, the foraging simulation is repeated, and the bus optimization path with the fitness value closest to the bus route optimization target is selected.

7. The bus route optimization method as described in claim 6, characterized in that, The optimization of bus routes in the target area based on the optimized bus routes includes: Obtain a real-time map of the target area; The latitude and longitude of the optimized bus route are compared with the latitude and longitude of the real-time map and the latitude and longitude of the bus stops in the real-time map to obtain the optimized bus stops of the optimized bus route. Based on the optimized bus routes and optimized bus stops, bus routes in the target area are optimized.

8. An electronic device, characterized in that, include: The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the bus route optimization method as described in any one of claims 1 to 7.

Images