Variable route bus to-be-selected station optimization method and device and storage medium
By building a simulation optimization model and a Kriging model global optimization algorithm, optimizing the to-selected stations for variable line buses has solved the problem of insufficient optimization of to-selected stations in the existing technology, improving the level of operational services and efficiency, and reducing costs.
Patent Information
- Application Number
- CN202310619530.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-29
- Publication Date
- 2024-11-29
AI Technical Summary
In the prior art, there is a lack of a mature system for optimizing stations for variable line buses, resulting in insufficient operational service levels, high costs and low efficiency.
By obtaining passenger reservation travel needs, building a simulation optimization model, using the Kriging model global optimization algorithm, determine the optimal site selection to minimize the value of the passenger service quality function, and optimize the driving path and stopping site of variable line buses.
It effectively improves the service level of variable line buses, reduces operating costs, improves service efficiency, and optimizes passengers' travel experience.
Smart Images

Figure CN119047669A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of transportation technology, and in particular to a method, device and storage medium for optimizing candidate stops for variable route buses. Background Art
[0002] like Figure 1 As shown in the figure, the working process of the variable route bus can be simply summarized as follows: a baseline route is laid out in a pre-set service area, and a series of fixed stations are assigned to the baseline route. The vehicle travels along the baseline route, following the scheduled time of each fixed station and arriving at each fixed station in turn. If there is a boarding and / or alighting demand that deviates from the baseline route between two adjacent fixed stations, the vehicle can choose whether to serve the passenger based on whether the maximum travel time can be met, that is, whether to pass through the candidate station requested by the passenger, that is, Figure 1 The circle shown in .
[0003] Although variable route buses have been in practice for many years, there is still no mature system for optimizing the candidate stops for variable route buses, and it is still under research.
[0004] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the invention
[0005] In response to the above technical problems, the present application provides a method, device and storage medium for optimizing candidate stops for variable route buses, which can effectively improve the service level of variable route bus operations, reduce operating costs and improve service efficiency.
[0006] To achieve the above object, the technical solution of the present invention is achieved as follows:
[0007] In a first aspect, an embodiment of the present invention provides a method for optimizing candidate bus stops on a variable route, the method comprising:
[0008] S1. Obtaining a reserved travel demand of at least one passenger for a bus with a variable route, wherein the reserved travel demand includes a reserved boarding station and a disembarking station;
[0009] S2, determining a simulation optimization problem with the candidate site as a decision variable and minimizing the value of the passenger service quality function as an optimization goal, and constructing a simulation optimization model for calculating the value of the passenger service quality function;
[0010] S3. According to the simulation optimization model, the Kriging model global optimization algorithm based on the multi-point filling sampling criterion is used to solve the simulation optimization problem, and the target candidate site selected for the travel reservation demand of the at least one passenger for the variable route bus is obtained.
[0011] In one embodiment, the constraint condition of the simulation optimization model includes a rejection rate threshold of a variable route bus, and the construction of the simulation optimization model for calculating the value of the passenger service quality function includes:
[0012] According to the reservation travel demand of the at least one passenger for the variable route bus, an initial travel path of the variable route bus is obtained based on a heuristic insertion algorithm;
[0013] The rejection rate of the variable route bus corresponding to the initial driving path is obtained, and a rejection rate threshold of the variable route bus is determined according to the rejection rate of the variable route bus corresponding to the initial driving path.
[0014] In one embodiment, the step of obtaining the initial travel path of the variable-route bus based on a heuristic insertion algorithm according to the reserved travel demand of the at least one passenger for the variable-route bus includes:
[0015] Determine the type of each passenger according to a preset classification rule based on the boarding station and the alighting station reserved by the at least one passenger for the variable route bus;
[0016] According to the type of each passenger and the preset relaxation time constraint, the initial travel path of the variable route bus is obtained based on the heuristic insertion algorithm.
[0017] In one embodiment, the calculation formula of the passenger service quality function is F=w1K+w2W+w3R+w4I, wherein w1, w2, w3, w4 are proportional coefficients, K is the average time on board the passenger, W is the average time waiting for the passenger, R is the average walking time of the passenger, and I is the average waiting time of the passenger.
[0018] In one embodiment, the step S3 comprises:
[0019] S30, based on the Latin hypercube experimental design method, randomly select N from the site collection s Initial combinations of candidate sites are brought into the simulation optimization model to calculate the value of the passenger service quality function corresponding to each of the initial combinations of candidate sites, and a sample set is established; the site set includes all random combinations of all candidate sites in the variable route bus;
[0020] S31, establishing a Kriging model according to the sample set;
[0021] S32, performing secondary sampling in the site set based on the multi-point filling sampling criterion to obtain a maximum value candidate site combination, and bringing it into the simulation optimization model to calculate the value of the passenger service quality function corresponding to the maximum value candidate site combination;
[0022] S33, updating the sample set according to the maximum value candidate site combination and the value of the passenger service quality function corresponding to the maximum value candidate site combination;
[0023] S34, determine whether the preset number of iterations has been reached, if not, return to step S31, if yes, end and determine the target candidate site based on the candidate site combination corresponding to the value of the minimum passenger service quality function in the sample set.
[0024] In one embodiment, N s =11×M-1, where M is the number of all candidate stops for variable bus routes.
[0025] In one embodiment, the method of performing secondary sampling within the site set based on the multi-point filling sampling criterion to obtain the maximum value candidate site combination includes:
[0026] Perform secondary sampling within the site set based on a multi-point filling sampling criterion to obtain at least one site combination to be selected for sampling;
[0027] A prediction result of the Kriging model on the at least one candidate site combination is obtained, and a maximum value candidate site combination is determined from the at least one candidate site combination according to the prediction result.
[0028] In a second aspect, an embodiment of the present invention provides a device for optimizing candidate bus stops on a variable route, the device comprising:
[0029] An acquisition module, used to acquire a reserved travel demand of at least one passenger for a bus with a variable route, wherein the reserved travel demand includes a reserved boarding station and a disembarking station;
[0030] A processing module, used for determining a simulation optimization problem with the candidate station as a decision variable and minimizing the value of the passenger service quality function as an optimization target, and constructing a simulation optimization model for calculating the value of the passenger service quality function;
[0031] The optimization module is used to solve the simulation optimization problem according to the simulation optimization model and the Kriging model global optimization algorithm based on the multi-point filling sampling criterion, and obtain the target candidate site selected for the reservation travel demand of at least one passenger for the variable route bus.
[0032] The present application also provides a device for optimizing candidate bus stops on a variable route, comprising: a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the above method are implemented.
[0033] The present application also provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0034] As described above, the variable route bus candidate site optimization method of the present application includes the steps of: obtaining at least one passenger's scheduled travel demand for the variable route bus, the scheduled travel demand including the scheduled boarding site and the alighting site; determining a simulation optimization problem with the candidate site as the decision variable and minimizing the value of the passenger service quality function as the optimization target, and constructing a simulation optimization model for calculating the value of the passenger service quality function; according to the simulation optimization model, solving the simulation optimization problem with the Kriging model global optimization algorithm based on the multi-point filling sampling criterion, and obtaining the target candidate site selected for the at least one passenger's scheduled travel demand for the variable route bus. Based on the above technical solution, by simulating the service performance of the variable route bus operation, the stop sites of the variable route bus are determined based on the passenger's scheduled travel demand for the variable route bus, which can effectively improve the service level of the variable route bus operation, reduce operating costs, and improve service efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.
[0036] Figure 1 It is a schematic diagram of the working process of the existing variable route bus;
[0037] Figure 2 It is a flow chart of a method for optimizing candidate bus stops on a variable route provided by an embodiment of the present invention;
[0038] Figure 3 It is a schematic diagram of the working process of a variable route bus based on a candidate site strategy in an embodiment of the present invention;
[0039] Figure 4 It is a structural schematic diagram of a device for optimizing candidate bus stops on a variable route provided by an embodiment of the present invention.
[0040] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0041] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0042] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.
[0043] See also Figure 2 , is a method for optimizing a bus station to be selected on a variable route provided by an embodiment of the present invention. The method can be applied to the situation of selecting a bus station to be selected on a variable route. The method can be executed by a device for optimizing a bus station to be selected on a variable route provided by an embodiment of the present invention. The device can be implemented in software and / or hardware. In a specific application, the device can be a desktop computer, a laptop computer, a smart phone, a personal digital assistant, a tablet computer, a server, and the like. The method for optimizing a bus station to be selected on a variable route includes the following steps:
[0044] Step S1: obtaining a reserved travel demand of at least one passenger for a bus with a variable route, wherein the reserved travel demand includes a reserved boarding point and a disembarking point.
[0045] Optionally, passengers can install tools such as a variable route bus applet in electronic devices such as smart phones, so as to select boarding and alighting stations from all the candidate stations and fixed stations in the variable route bus through the above tools, thereby generating a travel reservation demand for the variable route bus, and can send the corresponding travel reservation demand to the management end of the variable route bus, such as a server. Optionally, the boarding station and / or the alighting station can be a fixed station or a candidate station.
[0046] Step S102: determine a simulation optimization problem with the candidate site as a decision variable and minimizing the value of the passenger service quality function as an optimization target, and construct a simulation optimization model for calculating the value of the passenger service quality function.
[0047] It can be understood that variable route buses need to plan their travel routes before each operation. In addition to fixed stations, the planned travel routes may also include candidate stations. In this embodiment, a simulation optimization model construction method for variable route buses based on candidate stations is proposed, which mainly includes the following processes: (1) determining the variable route bus operation service area and maximum travel time; (2) simulating the generation of variable route bus passenger demand; (3) introducing the candidate station strategy; (4) using the heuristic insertion algorithm to obtain the travel route; (5) obtaining the specific travel data of each passenger and calculating the evaluation index. The following briefly describes the variable route bus operation service area and maximum travel time, passenger demand generation, variable route buses based on the candidate station strategy, and model performance evaluation.
[0048] (I) Variable route bus operation service area and maximum travel time
[0049] Here, an existing fixed bus route can be selected as the base route of the variable route bus. Through field investigation, stations with large passenger flow can be selected as fixed stations for the variable route bus, thereby determining the length L of the service area of the variable route bus and the location of the fixed stations on the base route. At the same time, the width W / 2 of the service area of the variable route bus can be selected as 1.5 miles as a reference.
[0050] Maximum travel time T S It is the maximum time that a vehicle is allowed to travel from the starting station to the terminal station. The general value can be referred to the following formula:
[0051]
[0052] Where C is the number of fixed sites, T d is the waiting time at each fixed station, T r is the waiting time for each non-fixed station, V bis the vehicle speed. L is the length of the variable bus service area, W is the width of the variable bus service area, and M is the fleet size of the variable bus system. θ is the expected passenger flow density, which can generally be set according to actual conditions. p1, p2, and p3 are the proportions of people getting on and off outside the station, getting on at a fixed station and getting off outside the station, and getting off at a fixed station and getting on outside the station.
[0053] 2. Generation of passenger demand
[0054] Passengers served by variable route buses can be divided into four categories:
[0055] Category 1: Get on and off the bus at fixed stops;
[0056] The second type: board the bus at a fixed station and get off outside the station;
[0057] The third category: get off at a fixed station and get on outside the station;
[0058] Category 4: getting on and off the bus outside the station.
[0059] Passengers' travel needs are generally simulated based on actual passenger flow data.
[0060] (III) Variable bus routes based on candidate station strategy
[0061] like Figure 3 As shown in Figure 1, in this strategy, bus operators deploy some fixed and suitable meeting points, namely candidate stations, to the service area based on land use, questionnaire surveys or operation planning methods before actual application. Passengers can then get on or off the bus at their scheduled locations or at meeting points within their acceptable walking distance. Therefore, selecting appropriate candidate stations is crucial to the implementation of the candidate station strategy.
[0062] 4. Model performance evaluation
[0063] In this embodiment, the passenger service quality function is used as the service performance evaluation index of the variable route bus, wherein the calculation formula of the passenger service quality function F is F=w1K+w2W+w3R+w4I, wherein w1, w2, w3, w4 are proportional coefficients, K is the average time on the bus of the passenger, W is the average waiting time of the passenger, R is the average walking time of the passenger, and I is the average waiting time of the passenger. Here, the proportional coefficient can be set based on actual needs. After determining a driving path of the variable route bus, combined with the travel reservation demand of at least one passenger for the variable route bus, the value of the passenger service quality function corresponding to the driving path can be obtained.
[0064] In this embodiment, the parameters of the simulation optimization model are optimized by a simulation optimization method, that is, the locations of the selected stations are optimized by a simulation optimization method, so as to further improve the service level of the variable route bus. Simulation optimization means that the objective function or constraint function value of the optimization model is calculated by a simulation model. The simulation optimization method can better reflect the actual situation and help decision makers plan and control the variable route bus before the service operation. The simulation optimization model constructed in this embodiment is:
[0065] min:average(F)
[0066] Subject to:RE≤ε
[0067] y i ∈{0, 1}
[0068] Among them, F is the value of the variable route bus service quality function under multiple operation cycles, RE is the value of the variable route bus rejection rate, and ε is the preset variable route bus rejection rate threshold. i A variable ranging from 0 to 1, which is 1 if the candidate site is selected and 0 otherwise.
[0069] In one embodiment, the constraint condition of the simulation optimization model includes a rejection rate threshold of a variable route bus, and the construction of the simulation optimization model for calculating the value of the passenger service quality function includes:
[0070] According to the reservation travel demand of the at least one passenger for the variable route bus, an initial travel path of the variable route bus is obtained based on a heuristic insertion algorithm;
[0071] The rejection rate of the variable route bus corresponding to the initial driving path is obtained, and a rejection rate threshold of the variable route bus is determined according to the rejection rate of the variable route bus corresponding to the initial driving path.
[0072] Among them, the heuristic insertion algorithm based on the first-come-first-served reservation principle in this embodiment is used to quickly construct the driving path. This heuristic insertion algorithm is a type of efficient vehicle planning method. Its core idea is that each insertion places the coordinates at the position with the lowest rejection rate of the variable route bus system. Assuming there are n passengers and the reservation time is t1<t2<....<tn, the insertion algorithm for variable route bus driving can be established:
[0073] Passenger 1: If the passenger is a first-class passenger, he / she must be accepted by the system. If the passenger is a second-class, third-class or fourth-class passenger, the passenger's off-station demand coordinates are assigned to the fixed station interval where he / she is located. The driving path is obtained by the insertion method. If the relaxation time constraint is met, the passenger demand is accepted and the driving path is updated; if the relaxation time constraint is not met, the passenger demand is rejected and the driving path before the insertion is retained.
[0074] Passenger 2: If the passenger is a first-class passenger, he / she must be accepted by the system. If the passenger is a second-class, third-class or fourth-class passenger, the passenger's off-station demand coordinates are assigned to the fixed station interval where he / she is located. The driving path is obtained by the insertion method. If the relaxation time constraint is met, the passenger demand is accepted and the driving path is updated; if the relaxation time constraint is not met, the passenger demand is rejected and the driving path before the insertion is retained.
[0075] Passenger n: If the passenger is a first-class passenger, he / she must be accepted by the system. If the passenger is a second-class, third-class or fourth-class passenger, the passenger's off-station demand coordinates are assigned to the fixed station interval where he / she is located. The driving path is obtained by the insertion method. If the relaxation time constraint is met, the passenger demand is accepted and the driving path is updated; if the relaxation time constraint is not met, the passenger demand is rejected and the driving path before the insertion is retained.
[0076] Optionally, according to the reserved travel demand of at least one passenger for the variable route bus, the initial travel path of the variable route bus generated for the reserved travel demand can be obtained based on the heuristic insertion algorithm; based on the initial travel path and the reserved travel demand, the rejection rate of the variable route bus corresponding to the initial travel path can be obtained, and the rejection rate threshold of the variable route bus can be determined according to the rejection rate of the variable route bus corresponding to the initial travel path. For example, assuming that there are 10 reserved travel demands, that is, 10 passengers reserve variable route buses, if it is determined based on the initial travel path that only 8 passengers' reserved travel demands are accepted, then the rejection rate of the variable route bus corresponding to the initial travel path is 20%, and the preset rejection rate threshold of the variable route bus can be set to 20%.
[0077] In one embodiment, the step of obtaining the initial travel path of the variable-route bus based on a heuristic insertion algorithm according to the reserved travel demand of the at least one passenger for the variable-route bus includes:
[0078] Determine the type of each passenger according to a preset classification rule based on the boarding station and the alighting station reserved by the at least one passenger for the variable route bus;
[0079] According to the type of each passenger and the preset relaxation time constraint, the initial travel path of the variable route bus is obtained based on the heuristic insertion algorithm.
[0080] Here, according to the boarding and alighting stations reserved by the at least one passenger for the variable route bus, the type of each passenger can be determined according to the preset classification rules, that is, the first type is boarding and alighting at a fixed station, the second type is boarding at a fixed station and alighting outside the station, the third type is alighting at a fixed station and boarding outside the station, and the fourth type is boarding and alighting outside the station; then, according to the type of each passenger and the preset relaxation time constraint, the initial travel path of the variable route bus is obtained based on the heuristic insertion algorithm. Among them, the preset relaxation time constraint can be set according to the longest time interval between two adjacent fixed stations, etc.
[0081] Step S3: according to the simulation optimization model, the Kriging model global optimization algorithm based on the multi-point filling sampling criterion is used to solve the simulation optimization problem, and the target candidate site selected for the travel demand of the at least one passenger for the variable route bus reservation is obtained.
[0082] Among them, the best way to deal with simulation optimization problems is to use a global optimization algorithm based on a proxy model. The proxy model is a simplified model used in engineering to replace complex models with long calculation time and solve quickly, including response surface model, neural network model, Kriging model and support vector machine model. Among many proxy models, Kriging has good approximation ability for multi-peak and nonlinear problems. Therefore, the Kriging model is often used for modeling simulation optimization problems. In this embodiment, a Kriging model global optimization algorithm based on a multi-point filling sampling criterion is proposed to solve the simulation optimization problem. The main principle or process includes: step (1), using the experimental design method to select initial sampling points and calculate their corresponding response values to form a training set; step (2), judging whether the termination condition is met, if it is met, outputting the current optimal solution; if it is not met, executing step (3); step (3), constructing a Kriging model based on the training set; step (4), using the multi-point filling sampling criterion to find new sampling points and calculate their corresponding response values; step (5), updating the training set of the Kriging model, and returning to step (2).
[0083] The following is a brief description of the principles of the experimental design method, termination conditions, Kriging model and multi-point sampling method.
[0084] 1. Experimental design method
[0085] The first step of the Kriging global optimization method is initial sampling. Initial sampling requires the use of experimental design methods, the most commonly used of which is Latin hypercube sampling.
[0086] Assuming that N sample points need to be generated for an M-dimensional problem, N sample points can be generated by dividing each dimension of the design space into N subspaces and randomly generating a sample point in each subspace. The specific mathematical expression is:
[0087]
[0088] Where j is the jth design variable, i is the i-th level of the design variable, 1≤i≤N, 1≤j≤M. U is a random uniform distribution in [0, 1], and π is a random integer distribution in [0, N].
[0089] Among them, the number of initial sampling points of the Kriging global optimization method should be N s =11×M-1, where N S is the number of initial sampling points, and M is the dimension of the problem (ie, the number of all candidate stations for variable route buses in this embodiment).
[0090] (II) Termination conditions
[0091] The termination condition is the basis for judging whether the algorithm stops. Since there is no explicit analytical expression for simulation optimization problems, it is difficult to derive the exact termination condition through mathematical methods. In engineering applications, the termination condition is generally when the number of simulation calculations exceeds the maximum predetermined value, that is, NFE>NFE max , where NFE is the number of simulation calculations, NEE is max It is the maximum number of simulation calculations that is preset.
[0092] (III) Kriging model
[0093] Assume there are m sample points X = [x1, x2, ...., x m ] T , and its corresponding response value Y=[y1,y2,....,y m ] T The Kriging model interpolates the objective function based on the Gaussian process and known points. Its basic prediction value expression is:
[0094] y(x)=f T (x)β+z(x)
[0095] Where β is the regression coefficient matrix, f(x) is the polynomial matrix containing the p regression values of x. z(x) is the spatially correlated random distribution error, which can be considered as a realization of the Gaussian process Z(x) with mean 0 and variance σ 2 The covariance formula between design points is:
[0096] E(Z(xi , x j )=σ 2 R(θ,x i , x j )
[0097] Here, the variance σ 2 is a scalar, R(θ, x i , x j ) is the spatial correlation function.
[0098] The optimal linear unbiased estimate of y(x) is:
[0099]
[0100] The least squares estimate of the regression coefficient matrix β is:
[0101]
[0102] The variance of y(x) is s 2 can be calculated as:
[0103]
[0104] (IV) Multi-point sampling method
[0105] The sampling method is the core of the Kriging global optimization method, which determines which points will be used as new sampling points to update the Kriging model. In this embodiment, a multi-point filling sampling criterion is proposed to achieve multi-point sampling through multi-objective optimization. The constructed multi-objective problem is as follows:
[0106] Where q is the control parameter, q = 10 n , n is generally between 3 and 7. P is a positive integer. min is the minimum value of the objective function among all known sampling points, Y max is the maximum value of the objective function among all known sampling points. y(x) is the predicted value of the Kriging model, and s(x) is the predicted standard deviation of the Kriging model. Φ and They are the cumulative distribution function and probability density function of the standard normal distribution respectively.
[0107] After constructing the multi-objective problem, the multi-objective optimization algorithm is used to solve it and the optimal Pareto frontier can be obtained. Finally, the required new sampling points are selected according to the size of the Kriging model probability improvement function corresponding to each point in the Pareto frontier. Among them, the probability improvement function is
[0108]
[0109] In one embodiment, the step S3 comprises:
[0110] S30, based on the Latin hypercube experimental design method, randomly select N from the site collection s Initial combinations of candidate sites are brought into the simulation optimization model to calculate the value of the passenger service quality function corresponding to each of the initial combinations of candidate sites, and a sample set is established; the site set includes all random combinations of all candidate sites in the variable route bus;
[0111] S31, establishing a Kriging model according to the sample set;
[0112] S32, performing secondary sampling in the site set based on the multi-point filling sampling criterion to obtain a maximum value candidate site combination, and bringing it into the simulation optimization model to calculate the value of the passenger service quality function corresponding to the maximum value candidate site combination;
[0113] S33, updating the sample set according to the maximum value candidate site combination and the value of the passenger service quality function corresponding to the maximum value candidate site combination;
[0114] S34, determine whether the preset number of iterations has been reached, if not, return to step S31, if yes, end and determine the target candidate site based on the candidate site combination corresponding to the value of the minimum passenger service quality function in the sample set.
[0115] Among them, N s =11×M-1, where M is the number of all candidate stops for the variable route bus. It can be understood that if the number of all candidate stops for the variable route bus is M, then the number of all random combinations of all candidate stops is 2 M .
[0116] Specifically, after establishing a sample set according to an initial candidate site combination and the value of the passenger service quality function corresponding to the initial candidate site combination, the candidate site combination is taken as input, and the value of the passenger service quality function corresponding to the candidate site combination is taken as output to establish a Kriging model; then, secondary sampling is performed in the site set based on the multi-point filling sampling criterion to obtain the maximum value candidate site combination and the value of the passenger service quality function corresponding to the maximum value candidate site combination, and the sample set is added to update the sample set, and the number of iterations is updated at the same time, that is, the number of iterations is increased by 1; then, when it is determined that the number of iterations is less than the preset number of iterations, the Kriging model is re-established using the updated sample set to repeat the above operation until the number of iterations is equal to the preset number of iterations, that is, the preset number of iterations is reached, and then the target candidate site is determined according to the candidate site combination corresponding to the minimum passenger service quality function value in the sample set, and the candidate site combination corresponding to the minimum passenger service quality function value in the sample set can be used as the target candidate site.
[0117] In one embodiment, the method of performing secondary sampling within the site set based on the multi-point filling sampling criterion to obtain the maximum value candidate site combination includes:
[0118] Perform secondary sampling within the site set based on a multi-point filling sampling criterion to obtain at least one site combination to be selected for sampling;
[0119] A prediction result of the Kriging model on the at least one candidate site combination is obtained, and a maximum value candidate site combination is determined from the at least one candidate site combination according to the prediction result.
[0120] Among them, secondary sampling can be performed in the site set based on the multi-point filling sampling criterion, so that the remaining candidate site combinations in the site set except the initial candidate site combination are used as at least one candidate site combination for sampling, and input into the Kriging model to obtain the prediction result of the Kriging model for each candidate site combination in the at least one candidate site combination, and the prediction result can be used to determine whether the corresponding candidate site combination is better than the candidate site combination in the sample set, that is, whether the value is greater. According to the prediction result of the Kriging model for each candidate site combination in the at least one candidate site combination, the maximum value candidate site combination can be determined.
[0121] In summary, in the method for optimizing the candidate stations for variable route buses provided in the above embodiment, by simulating the service performance of the variable route bus operation, the stop stations of the variable route bus are determined based on the passengers' reservation travel demand for the variable route bus, which can effectively improve the service level of the variable route bus operation, reduce operating costs, and improve service efficiency.
[0122] Based on the same inventive concept as the above embodiments, see Figure 4 , which shows the composition of a variable route bus candidate station optimization device provided by an embodiment of the present invention, which may include:
[0123] An acquisition module, used to acquire a reserved travel demand of at least one passenger for a bus with a variable route, wherein the reserved travel demand includes a reserved boarding station and a disembarking station;
[0124] A processing module, used for determining a simulation optimization problem with the candidate station as a decision variable and minimizing the value of the passenger service quality function as an optimization target, and constructing a simulation optimization model for calculating the value of the passenger service quality function;
[0125] The optimization module is used to solve the simulation optimization problem according to the simulation optimization model and the Kriging model global optimization algorithm based on the multi-point filling sampling criterion, and obtain the target candidate site selected for the reservation travel demand of at least one passenger for the variable route bus.
[0126] In summary, in the variable route bus candidate station optimization device provided in the above embodiment, by simulating the service performance of the variable route bus operation, the stop stations of the variable route bus are determined based on the passengers' scheduled travel needs for the variable route bus, which can effectively improve the service level of the variable route bus operation, reduce operating costs, and improve service efficiency.
[0127] In one embodiment, the processing module is specifically used to:
[0128] According to the reservation travel demand of the at least one passenger for the variable route bus, an initial travel path of the variable route bus is obtained based on a heuristic insertion algorithm:
[0129] The rejection rate of the variable route bus corresponding to the initial driving path is obtained, and a rejection rate threshold of the variable route bus is determined according to the rejection rate of the variable route bus corresponding to the initial driving path.
[0130] In one embodiment, the processing module is specifically used to:
[0131] Determine the type of each passenger according to a preset classification rule based on the boarding station and the alighting station reserved by the at least one passenger for the variable route bus;
[0132] According to the type of each passenger and the preset relaxation time constraint, the initial travel path of the variable route bus is obtained based on the heuristic insertion algorithm.
[0133] In one embodiment, the calculation formula of the passenger service quality function is F=w1K+w2W+w3R+w4I, wherein w1, w2, w3, w4 are proportional coefficients, K is the average time on board the passenger, W is the average time waiting for the passenger, R is the average walking time of the passenger, and I is the average waiting time of the passenger.
[0134] In one embodiment, the optimization module is specifically used to:
[0135] S30, based on the Latin hypercube experimental design method, randomly select N from the site collection s Initial combinations of candidate sites are brought into the simulation optimization model to calculate the value of the passenger service quality function corresponding to each of the initial combinations of candidate sites, and a sample set is established; the site set includes all random combinations of all candidate sites in the variable route bus;
[0136] S31, establishing a Kriging model according to the sample set;
[0137] S32, performing secondary sampling in the site set based on the multi-point filling sampling criterion to obtain a maximum value candidate site combination, and bringing it into the simulation optimization model to calculate the value of the passenger service quality function corresponding to the maximum value candidate site combination;
[0138] S33, updating the sample set according to the maximum value candidate site combination and the value of the passenger service quality function corresponding to the maximum value candidate site combination;
[0139] S34, determine whether the preset number of iterations has been reached, if not, return to step S31, if yes, end and determine the target candidate site based on the candidate site combination corresponding to the value of the minimum passenger service quality function in the sample set.
[0140] In one embodiment, N s =11×M-1, where M is the number of all candidate stops for variable bus routes.
[0141] In one embodiment, the optimization module is specifically used to:
[0142] Perform secondary sampling within the site set based on a multi-point filling sampling criterion to obtain at least one site combination to be selected for sampling;
[0143] A prediction result of the Kriging model on the at least one candidate site combination is obtained, and a maximum value candidate site combination is determined from the at least one candidate site combination according to the prediction result.
[0144] It should be noted that: the variable route bus station optimization device provided in the above embodiment only uses the division of the above program modules as an example to illustrate when implementing the variable route bus station optimization method. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the vehicle identification device is divided into different program modules to complete all or part of the processing described above. In addition, the variable route bus station optimization device provided in the above embodiment and the corresponding variable route bus station optimization method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0145] An embodiment of the present application also provides a device for optimizing candidate bus stops on a variable route, comprising: a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the above method are implemented.
[0146] An embodiment of the present application further provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0147] In the embodiments of the variable route bus candidate station optimization device and storage medium provided in the present application, all technical features of any of the above-mentioned variable route bus candidate station optimization method embodiments may be included, and the expanded and explained contents of the specification are basically the same as those of the embodiments of the above-mentioned methods, and will not be repeated here.
[0148] The embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer executes the methods in the above various possible implementation modes.
[0149] An embodiment of the present application also provides a chip, including a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device equipped with the chip executes the methods in various possible implementation modes as described above.
[0150] It is understood that the above scenarios are only examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of the present application. The technical solutions of the present application can also be applied to other scenarios. For example, it is known to those skilled in the art that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0151] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0152] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.
[0153] The units in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.
[0154] In the present application, the same or similar terminology concepts, technical solutions and / or application scenario descriptions are generally described in detail only the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of the present application, for the same or similar terminology concepts, technical solutions and / or application scenario descriptions that are not described in detail later, reference can be made to the previous related detailed descriptions.
[0155] In the present application, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0156] The various technical features of the technical solution of the present application can be arbitrarily combined. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.
[0157] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to execute the method of each embodiment of the present application.
[0158] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. Computer instructions can be stored in a storage medium, or transmitted from one storage medium to another storage medium. For example, computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. Available media can be magnetic media, (e.g., floppy disk, storage disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state storage disk Solid State Disk (SSD)), etc.
[0159] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A method for optimizing candidate bus stops on variable routes. It is characterized in that The method comprises the following steps: S1. Obtaining a reserved travel demand of at least one passenger for a bus with a variable route, wherein the reserved travel demand includes a reserved boarding station and a disembarking station; S2, determining a simulation optimization problem with the candidate site as a decision variable and minimizing the value of the passenger service quality function as an optimization goal, and constructing a simulation optimization model for calculating the value of the passenger service quality function; S3. According to the simulation optimization model, the Kriging model global optimization algorithm based on the multi-point filling sampling criterion is used to solve the simulation optimization problem, and the target candidate site selected for the travel reservation demand of the at least one passenger for the variable route bus is obtained.
2. The method according to claim 1, It is characterized in that The constraint conditions of the simulation optimization model include a rejection rate threshold of a variable route bus, and the simulation optimization model constructed for calculating the value of the passenger service quality function includes: According to the reservation travel demand of the at least one passenger for the variable route bus, an initial travel path of the variable route bus is obtained based on a heuristic insertion algorithm; The rejection rate of the variable route bus corresponding to the initial driving path is obtained, and a rejection rate threshold of the variable route bus is determined according to the rejection rate of the variable route bus corresponding to the initial driving path.
3. The method according to claim 2, It is characterized in that The method of obtaining the initial travel path of the variable route bus based on a heuristic insertion algorithm according to the reserved travel demand of the at least one passenger for the variable route bus includes: Determine the type of each passenger according to a preset classification rule based on the boarding station and the alighting station reserved by the at least one passenger for the variable route bus; According to the type of each passenger and the preset relaxation time constraint, the initial travel path of the variable route bus is obtained based on the heuristic insertion algorithm.
4. The method according to claim 1, It is characterized in that The calculation formula of the passenger service quality function F is F = w 1 K+w 2 W+w 3 R+w 4 I, where w 1 , w 2 , w 3 , w 4 is the proportionality coefficient, K is the average time passengers spend on the bus, W is the average time passengers spend waiting for the bus, R is the average walking time of passengers, and I is the average waiting time of passengers.
5. The method according to claim 1, It is characterized in that The step S3 comprises: S30, based on the Latin hypercube experimental design method, randomly select N from the site collection s Initial combinations of candidate sites are brought into the simulation optimization model to calculate the value of the passenger service quality function corresponding to each of the initial combinations of candidate sites, and a sample set is established; the site set includes all random combinations of all candidate sites in the variable route bus; S31, establishing a Kriging model according to the sample set; S32, performing secondary sampling in the site set based on the multi-point filling sampling criterion to obtain a maximum value candidate site combination, and bringing it into the simulation optimization model to calculate the value of the passenger service quality function corresponding to the maximum value candidate site combination; S33, updating the sample set according to the maximum value candidate site combination and the value of the passenger service quality function corresponding to the maximum value candidate site combination; S34, determine whether the preset number of iterations has been reached, if not, return to step S31, if yes, end and determine the target candidate site based on the candidate site combination corresponding to the value of the minimum passenger service quality function in the sample set.
6. The method according to claim 5, It is characterized in that N s =11×M-1, where M is the number of all candidate stops for variable bus routes.
7. The method according to claim 5, It is characterized in that The method of performing secondary sampling within the site set based on the multi-point filling sampling criterion to obtain a maximum value candidate site combination includes: Perform secondary sampling within the site set based on a multi-point filling sampling criterion to obtain at least one site combination to be selected for sampling; A prediction result of the Kriging model on the at least one candidate site combination is obtained, and a maximum value candidate site combination is determined from the at least one candidate site combination according to the prediction result.
8. A device for optimizing the candidate bus stops on a variable bus route. It is characterized in that The device comprises: An acquisition module, used to acquire a reserved travel demand of at least one passenger for a bus with a variable route, wherein the reserved travel demand includes a reserved boarding station and a disembarking station; A processing module, used for determining a simulation optimization problem with the candidate station as a decision variable and minimizing the value of the passenger service quality function as an optimization target, and constructing a simulation optimization model for calculating the value of the passenger service quality function; The optimization module is used to solve the simulation optimization problem according to the simulation optimization model and the Kriging model global optimization algorithm based on the multi-point filling sampling criterion, and obtain the target candidate site selected for the reservation travel demand of at least one passenger for the variable route bus.
9. A device for optimizing the candidate bus stops on a variable bus route. It is characterized in that include: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the method for optimizing candidate stations for a variable route bus as described in any one of claims 1 to 7 are implemented.
10. A storage medium, It is characterized in that The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for optimizing candidate bus stops on a variable route as claimed in any one of claims 1 to 7.
