WO2024011864A1

WO2024011864A1 - Bus route scheduling processing method and apparatus, device, and readable storage medium

Info

Publication number: WO2024011864A1
Application number: PCT/CN2022/142235
Authority: WO
Inventors: 蚁韩羚; 田贤材; 唐锲; 余晓填; 王孝宇
Original assignee: 深圳云天励飞技术股份有限公司
Priority date: 2022-07-14
Filing date: 2022-12-27
Publication date: 2024-01-18
Also published as: CN115293519A

Abstract

The present application relates to the technical field of intelligent transportation, and provides a bus route scheduling processing method and apparatus, a computer device, and a computer-readable storage medium. In order to solve the problem of a poor scheduling effect of bus routes, different types of bus factors are obtained, and the bus factors are combined to obtain initial bus genes; degrees of fitness of the initial bus genes are evaluated, and survival-of-the-fittest screening is performed on the initial bus genes according to the magnitude of the degrees of fitness so as to obtain natural selection bus genes; a bus gene variation iteration variable is obtained and whether the variable meets a preset bus gene variation termination condition is determined; if the variable meets a preset bus gene variation termination condition, natural selection bus genes that meet a preset first degree of fitness condition are selected; and a bus route scheduling table is obtained according to departure shifts corresponding to the selected natural selection bus genes. The objectivity of scheduling on the basis of a variety of bus factors can be improved, and operating costs of the bus routes can be reduced without increasing the average waiting time of passengers.

Description

Bus route scheduling processing method, device, equipment and readable storage medium

This application requests the priority of the Chinese patent application submitted to the China Patent Office on July 14, 2022, with the application number 202210827674.3 and the invention title "Method, device, equipment and readable storage medium for processing bus line scheduling", which The entire contents are incorporated herein by reference.

Technical field

The present application relates to the field of smart transportation technology, and in particular to a bus route scheduling processing method, device, computer equipment and computer-readable storage medium.

Background technique

At present, bus line scheduling is mainly based on schedules pre-designed by manual experience. When designing the schedule, it relies too much on the subjective feelings of the dispatcher. In addition to considering the departure time, other factors will also be considered when dispatching buses. For example, in order to adapt to different public transportation situations, various factors such as different departure types and departure models will be configured on the same line. In terms of departure type, in addition to mainline trains on the same line, in order to adapt to the more concentrated passenger flow in different situations such as short-distance passenger flow and long-distance passenger flow, there will also be large station express trains or section line trains. In terms of departure types, in order to adapt to the different passenger flow conditions between peak and off-peak periods of public transportation, on the same line, in addition to arranging large vehicles during peak periods, various types such as medium-sized vehicles or small vehicles will also be arranged during off-peak periods. car model.

The above-mentioned factors of bus routes bring difficulty to the design of bus schedule. Therefore, according to the bus schedule designed in traditional technology, the dispatching of bus lines is often less effective in actual operations, resulting in either crowded passenger flow or a waste of bus resources.

Contents of the invention

This application provides a bus line scheduling processing method, device, computer equipment and computer-readable storage medium, which can solve the technical problem of poor bus line scheduling in traditional technology.

In the first aspect, this application provides a bus route scheduling processing method, including: obtaining different types of bus factors and combining the bus factors to obtain an initial bus gene, wherein the bus factors describe the bus routes The factors involved in the scheduling, the initial bus gene describes the initial departure frequency; calculate the fitness of each of the initial bus genes, and based on the size of the fitness, the initial bus genes are screened for survival of the fittest. , obtain the naturally selected bus gene, where the fitness describes the degree of excellence of the initial bus gene; obtain the bus gene mutation iteration variable, and determine whether the bus gene mutation iteration variable meets the preset bus gene mutation termination condition; If the bus gene mutation iteration variable satisfies the preset bus gene variation termination condition, the naturally selected bus gene that meets the preset first fitness condition is screened out as the first target bus gene; according to the first target bus gene According to the corresponding departure frequency, the schedule of the bus line is obtained.

In the second aspect, this application also provides a bus line scheduling processing device, including: a first acquisition unit, used to acquire different types of bus factors, and combine the bus factors to obtain an initial bus gene, where , the bus factors describe the factors involved in the scheduling of bus lines, and the initial bus genes describe the initial departure frequency; the first screening unit is used to calculate the fitness of each of the initial bus genes, and according to the The size of the fitness, the initial bus gene is screened for survival of the fittest, and the natural selection bus gene is obtained, wherein the fitness describes the degree of excellence of the initial bus gene; the first judgment unit is used to obtain the variation of the bus gene iterate variables, and determine whether the bus gene mutation iteration variable satisfies the preset bus gene variation termination condition; the second screening unit is used to filter out the bus gene variation iteration variable if it satisfies the preset bus gene variation termination condition. The naturally selected bus gene that meets the preset first fitness condition is used as the first target bus gene; the first acquisition unit is used to obtain the bus line schedule according to the departure frequency corresponding to the first target bus gene. surface.

In a third aspect, this application also provides a computer device, which includes a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program, it implements the bus line scheduling processing method. A step of.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor causes the processor to perform the bus route scheduling. steps of the processing method.

This application provides a bus line scheduling processing method, device, computer equipment and computer-readable storage medium. The processing method obtains the initial bus genes by obtaining different types of bus factors and combining the bus factors, and then evaluates the fitness of the initial bus genes, and selects the initial bus genes according to the size of the fitness, and obtains Naturally select the bus gene, then obtain the bus gene variation iteration variable, and determine whether the bus gene variation iteration variable meets the preset bus gene variation termination condition. If the bus gene variation iteration variable satisfies the preset bus gene variation termination condition, filter Naturally selected bus genes that meet the preset first fitness conditions are selected, and based on the departure times corresponding to the selected naturally selected bus genes, the bus line schedule is obtained, thereby combining the various factors involved in the bus line schedule. Different types of public transportation factors are combined to construct an initial public transportation gene, and based on the adaptability screening of the genetic algorithm, the initial public transportation gene is subjected to natural selection of survival of the fittest through fitness, and then a combination that meets the preset first fitness condition is obtained. type bus gene, and obtain the bus line schedule according to the departure frequency corresponding to the bus gene, so that the bus line schedule is more in line with the actual needs that require a combination of multiple bus factors, and can improve the efficiency of bus routes based on multiple bus factors. The objectivity of bus scheduling can reduce the operating costs of bus lines without increasing the average waiting time of passengers.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, which are of great significance to this field. Ordinary technicians can also obtain other drawings based on these drawings without exerting creative work.

Figure 1 is a schematic flow chart of a bus line scheduling processing method provided by an embodiment of the present application;

Figure 2 is a schematic diagram of the first sub-flow of the bus line scheduling processing method provided by the embodiment of the present application;

Figure 3 is a schematic diagram of the second sub-flow of the bus line scheduling processing method provided by the embodiment of the present application;

Figure 4 is a schematic diagram of the third sub-flow of the bus line scheduling processing method provided by the embodiment of the present application;

Figure 5 is a schematic diagram of the fourth sub-flow of the bus route scheduling processing method provided by the embodiment of the present application;

Figure 6 is a schematic block diagram of a bus line scheduling processing device provided by an embodiment of the present application;

Figure 7 is a schematic block diagram of a computer device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

It should be understood that, when used in this specification and the appended claims, the terms "comprises" and "comprises" indicate the presence of described features, integers, steps, operations, elements and/or components but do not exclude the presence of one or The presence or addition of multiple other features, integers, steps, operations, elements, components and/or collections thereof.

The embodiment of the present application provides a bus route scheduling processing method. The processing method can be applied to computer equipment such as desktops or servers, and can be used in smart buses to schedule bus routes based on multiple bus factors. For example, when scheduling bus line departures based on various bus factors such as departure time, departure type, and departure model, the bus line scheduling processing method provided by the embodiment of the present application can be used.

For example, in smart public transportation, when scheduling bus lines based on the simulation system of the bus system, different types of bus factors can be pre-configured manually on the configuration page of the simulation system. The configured bus factors can include at least any two of the following: Types: departure time, departure type and departure model. The simulation system performs the following operations: obtains departure time, departure type, departure model and other bus factors, and combines different types of bus factors to obtain an initial bus gene. The initial bus gene Describe the initial bus schedule; calculate the fitness of each of the initial bus genes, and select the initial bus genes according to the size of the fitness to obtain the natural selection bus genes, where the fitness Describe the quality of the initial bus gene; obtain the bus gene variation iteration variable, and determine whether the bus gene variation iteration variable satisfies the preset bus gene variation termination condition; if the bus gene variation iteration variable satisfies the preset Based on the bus gene mutation termination condition, the naturally selected bus genes that meet the preset first fitness condition are selected as the first target bus genes; according to the departure frequency corresponding to the first target bus gene, the bus route arrangement is obtained Schedule. Among them, the simulation system of the bus system is a system that uses a simulation model to simulate the map routes, bus stops, departure vehicles, passenger flow and other bus traffic scenarios involved in the bus lines.

Please refer to Figure 1 , which is a schematic flowchart of a bus route scheduling processing method provided by an embodiment of the present application. As shown in Figure 1, the method includes the following steps S11-S16:

S11. Obtain different types of bus factors, and combine the bus factors to obtain an initial bus gene. The bus factors describe the factors involved in the scheduling of bus lines, and the initial bus genes describe the generated initial bus genes. Departure schedule.

Specifically, with the development of bus transportation, when scheduling bus vehicles on bus lines, in addition to considering the departure time of the bus vehicles, various types of bus factors such as departure type and departure model will also be considered. Among them, the departure time Types include main line trains, station express trains and regional line trains, and the departure models include large cars, medium cars, small cars, etc. When scheduling bus vehicles on bus lines, it is necessary to combine and optimize multiple types of bus factors to obtain the departure frequency corresponding to each combination. All departures within the operating day are sorted according to departure time to realize the optimization of bus lines. Scheduling, so as to reduce the transportation cost of bus lines as much as possible without increasing the average waiting time of passengers.

In the embodiment of this application, multiple types of public transportation factors are considered. When scheduling bus lines, each type of public transportation factor can be set as a corresponding preset public transportation factor set. Each of the preset public transportation factor sets includes the same Different factor objects of class Transit Factors. For example, the departure time of bus vehicles can be combined into a preset bus departure time set with a granularity of 1 minute, and the departure times within the operating time period of the bus vehicles can be described as {t ₁ , t ₂ ,...t _n }, Among them, t ₁ , t ₂ ,...t _n are departure times, and the value range is any integer between 0 and 1440. They are used to describe the minute count in 24 hours of operation of a bus line. For example, the 395th minute is equivalent to 06:30, t ₁ describes the departure time of the first bus, and t _n describes the departure time of the last bus. Of course, the departure time of the bus can also be divided into 2 minutes or other preset time units as a granularity, and it can also be divided. The time within 24 hours is combined into a preset bus departure time set, and only the time within the longest operating time range of the bus line within the operating day is combined into a preset bus departure time set. For example, for a bus line, if the bus The first bus time of the line is 6:00, and the last bus time is 23:00 in the evening. The departure time included in the preset bus departure time set can be between 6:00 and 23:00 on operating days. As for the departure type, the departure types of the bus vehicles used by the bus lines can be combined into a preset set of bus vehicle types, which can be described as {main line bus (Normal in English), interval line bus (Shuttle in English)}, also It can be described as {main line train (Normal in English), Dazhan Express train (Express in English), and section line train (Shuttle in English)}, among which, main line train, Dazhan Express train, and section line train are The specific type object of the departure type. In addition, with the development of public transportation, if other departure types are generated, they can also be included in the preset bus vehicle type set. For the departure model, the vehicle models of the bus vehicles used in the bus lines can be combined into a preset bus vehicle departure model set, which can be described as {large vehicle (Big in English), small vehicle (Small in English)}, or The description is {large car (Big in English), medium car (Medium in English), small car (Small in English)}, where large car, medium car, and small car are the specific vehicle models of public transportation vehicles. In addition, as If the development of public transportation vehicles produces other departure models, they can also be included in the set of preset bus departure models. In addition, the preset bus vehicle power type set {fuel vehicle, electric vehicle}, or construct different collections such as preset bus vehicle power type collection {fuel vehicle, gasoline-electric hybrid vehicle, electric vehicle}. It should be noted that the above examples of each type of preset public transportation factor collection are only used to explain the different collection situations that may exist for multiple types of public transportation factors, and are not used to limit the collection form of public transportation factors. With the development of public transportation, , it is completely possible to combine more types of public transportation factors into corresponding preset public transportation factor sets and apply them to the embodiments of the present application.

Then, from each preset public transportation factor set, extract specific public transportation factors included in each preset public transportation factor set, and combine the extracted public transportation factors to obtain different types of public transportation factors, and combine the public transportation factors The factors are combined to obtain the initial bus gene. In order to facilitate the subsequent genetic mutation of the initial bus gene, the initial bus gene can also be used to initialize the preset bus population, thereby initializing the preset bus population. The preset bus population includes The number of initial bus genes may be a preset first number, and the preset first number may be a hyperparameter. Wherein, the bus factors describe the factors involved in the scheduling of bus lines. In addition to the departure time, the bus factors may also include at least one of the departure type and departure model of the bus vehicle. The departure type includes the main line. At least one of a train, a station express train and a regional train, and the departure model includes at least one of a large car, a medium-sized car and a small car. The initial bus gene describes the initial departure frequency generated in the process of obtaining the bus line schedule. For example, based on the above-mentioned preset bus departure time set, preset bus vehicle type set and preset bus vehicle departure model set, the bus factors corresponding to 390, mainline buses and medium-sized buses are respectively extracted and combined into the initial bus gene (390 , main line car, medium-sized car), used to describe a main line train using a medium-sized car at 06:30. Especially when the bus line scheduling is combined with the departure time, departure type and departure model described above, the bus line scheduling can fully describe the actual factors of bus vehicle scheduling, and improve the efficiency of bus line scheduling based on departure time, departure type and departure model. The objectivity of bus line scheduling corresponding to comprehensive factors can reduce the operating costs of bus lines without increasing the average waiting time of passengers.

Further, in order to more accurately reflect the randomness of the genetic algorithm, specific factor objects contained in each of the preset public transportation factor sets can be randomly extracted, thereby randomly obtaining different types of public transportation factors, and combining the public transportation factors, Then the initial bus gene is obtained randomly.

By obtaining different types of bus factors and combining multiple bus factors, when optimizing bus line scheduling, multiple bus factors can be comprehensively considered to improve the objectivity and effectiveness of bus line scheduling. This will reduce the bus company's costs without increasing the average waiting time for passengers.

Further, after obtaining the initial bus gene, it also includes:

Determine whether the initial bus gene meets the preset bus business rules;

If the initial bus gene satisfies the preset bus business rules, retain the initial bus gene;

If the initial bus gene does not meet the preset bus business rules, the initial bus gene is not retained.

Specifically, after obtaining the initial bus gene, in order to make the generated bus gene meet the needs of the actual bus line, it is determined whether the initial bus gene satisfies the preset bus business rules. The preset bus business rules may include the following content One or more of the following: 1) The first and last train must be a main line; 2) At least one of the two adjacent trains must be a main line; 3) The number of sub-line types on the same line cannot exceed 3; 4) Two adjacent trains must be a main line The departure time interval of the line cannot exceed the specified maximum departure interval; 5) Each vehicle model has corresponding quantity constraints. If the initial bus gene satisfies the preset bus business rules, the initial bus gene is retained, and the retained initial bus gene can be added to the preset bus population, thereby initializing the preset bus population. If If the initial bus gene does not meet the preset bus business rules, the initial bus gene is not retained, the initial bus gene is not added to the preset bus population, the initial bus gene can be discarded or eliminated, In this way, the generated bus genes that do not comply with the preset bus business rules are filtered out, and until the preset first number of initial bus genes corresponding to the hyperparameters is obtained, as the basis for the mutation of bus genes based on the genetic algorithm, it can improve the efficiency of bus genes based on the initial The feasibility of progeny bus genes obtained from genetic variation of bus genes will further improve the objectivity of bus route scheduling based on departure time, departure type and departure model. Among them, hyperparameters are parameters preset by machine learning before learning.

S12. Calculate the fitness of each initial bus gene, and select the initial bus genes according to the size of the fitness to obtain the natural selection bus gene. The fitness describes the initial bus gene. The degree of pros and cons of bus genes.

Specifically, for the multiple initial bus genes obtained, the fitness of each initial bus gene is evaluated. The fitness describes the quality of the initial bus genes, that is, the fitness is used to describe the quality of the initial bus genes. The degree to which the initial bus gene meets the preset target requirements. The higher the degree of the fitness meets the preset target requirements, the more worthy of retaining the initial bus gene is. The lower the degree of the fitness meets the preset target requirements. It shows that the less worth retaining the initial bus gene, the greater the probability that the initial bus gene will be eliminated, and all the initial bus genes can be sorted according to the fitness from large to small to obtain the bus genes Sort the sequence, and select several naturally selected bus genes with the highest fitness from the bus gene sorting sequence, so that the initial bus genes are screened for survival of the fittest according to the fitness, and the initial bus genes are completed. Natural selection retains excellent initial bus genes (i.e. elite genes) and eliminates unsuitable initial bus genes, thereby obtaining several naturally selected bus genes. For example, the number of naturally selected bus genes can be a preset second number , wherein the preset second number is smaller than the preset first number, and the preset second number may also be a hyperparameter. Among them, the calculation formula of the fitness can adopt the following calculation method:

The fitness of the bus gene = - (bus vehicle cost + average waiting time of passengers * penalty coefficient);

Among them, the negative number is taken to facilitate understanding, because generally the higher the fitness of the bus gene, the better the bus gene is and the more worthy it is to retain. The bus vehicle cost is the cost incurred by the operation of the bus vehicle. The bus vehicle cost includes the purchase cost of the bus vehicle, the cost of the driver and passengers, vehicle fuel consumption and vehicle losses and other costs incurred during the operation of the bus vehicle. For different vehicle models, it can be Calculate the cost of public transportation vehicles. The passenger waiting time is the time difference between the arrival time of the passenger at the bus stop and the arrival time of the next train at the bus stop. The average waiting time of passengers is the average waiting time of all passengers on the bus line. For the average waiting time of passengers at a single bus stop on the bus line, the following process can be used to obtain it:

1) For each OD pair of the bus line, within a preset time, based on the camera installed on the bus vehicle, collect the number of people who boarded the bus at the departure station of the OD pair, and obtain the number of boarding passengers of the OD pair. The bus time, and the boarding time can be the arrival time of the bus vehicle at the departure station, where the OD pair is the bus station pair consisting of the departure station and the destination station of the passenger's trip on the bus line;

2) Based on the boarding time, randomly generate the passenger arrival time of each boarding passenger. The passenger arrival time is the time when the boarding passenger arrives at the departure station. The passenger arrival time is early. At the stated boarding time;

3) According to the preset departure time of the bus vehicle contained in the initial bus gene and the running time of the bus vehicle between each two adjacent bus stops, calculate the estimated arrival time of the bus vehicle at the departure stop;

4) Subtract the passenger's arrival time from the estimated arrival time of the vehicle to obtain the waiting time of the passenger who boarded the bus. Add the waiting time of all passengers who boarded the bus and average it to obtain the departure time. The average waiting time of all passengers at the station is the average waiting time of passengers.

For example, if bus stop A is an OD-centered departure station, within the preset time, if the boarding passengers at bus stop A are A1, A2, A3, A4 and A5, the boarding time is t, and the boarding time is t. Using t as the benchmark, the arrival time of each passenger on the bus is randomly generated. We can use t1 to describe the arrival time of A1, t2 to describe the arrival time of A2, t3 to describe the arrival time of A3, and t4 to describe the arrival time of A4. t5 describes the arrival time of A5, where t1, t2, t3, t4 and t5 are all earlier than t. If based on the preset departure time of the bus vehicle contained in the initial bus gene and the running time of the bus vehicle between each two adjacent bus stops, the estimated arrival time of the bus vehicle at the departure stop is obtained as T, then The waiting time of A1 is T-t1, the waiting time of A2 is T-t2, the waiting time of A3 is T-t3, the waiting time of A4 is T-t4, and the waiting time of A5 is T-t5. The average waiting time of passengers can be calculated using the following formula: T _v = {(T-t1)+(T-t2)+(T-t3)+(T-t4)+(T-t5)}/5, T _v That is the average waiting time for boarding passengers A1, A2, A3, A4 and A5.

Further, based on the average waiting time of passengers at the above single departure station, the average waiting time of passengers at their respective departure stations for all ODs in the bus line can be obtained, and the average waiting time of passengers at all departure stations is averaged, Get the average waiting time of passengers on this bus line. The above process can be processed based on the simulation system of the public transportation system.

In another embodiment, the arrival time of each passenger on the bus can also be counted in the following way: for a bus line, set up a site camera at each bus stop, and calculate the arrival time of each passenger through the video Collect and monitor, obtain the arrival video of passengers arriving at the departure station, perform face recognition on the arrival video to identify each initial passenger, and record the arrival time of the initial passenger at the bus stop based on the collected arrival video . In addition, for each passenger boarding the bus, the vehicle camera in the bus collects the boarding video of the boarding passenger, and performs face recognition on the boarding video to obtain the target passenger who boarded the bus and assign the target passenger to the boarding video. Compare the face recognition results of each of the initial passengers to match the target passenger with the initial passenger, and determine the arrival time of the target passenger based on the arrival time of the initial passenger, which is the arrival time of the passenger who boarded the bus. . Compared with the above-mentioned boarding time as the basis, the passenger arrival time of each boarding passenger is randomly generated, which can more accurately reflect the arrival time of passengers arriving at the departure station.

The penalty coefficient is a hyperparameter, and the penalty coefficient can be:

Among them, the total bus vehicle cost of the bus line is the sum of the costs of all bus vehicles in the operating day, the average waiting time of the bus line is the average waiting time of passengers in the operating day of the bus line, and the constant coefficient is a preset fixed value, which is Empirical value, constant coefficient initialization can be 0.5.

The above statistical method of fitness of bus genes and the setting of penalty coefficient fully take into account the two main purposes that need to be considered in the bus line scheduling process, that is, the average waiting time of passengers is as short as possible and the cost of bus vehicles is as low as possible, so that Reduce the operating costs of bus lines without increasing the average waiting time for passengers.

S13. Obtain the bus gene variation iteration variable, and determine whether the bus gene variation iteration variable meets the preset bus gene variation termination condition;

S14. If the bus gene mutation iteration variable does not meet the preset bus gene variation termination condition, do not screen out the naturally selected bus genes that meet the preset first fitness condition;

S15. If the bus gene mutation iteration variable meets the preset bus gene variation termination condition, select the naturally selected bus gene that meets the preset first fitness condition as the first target bus gene;

S16. Obtain the bus schedule according to the departure frequency corresponding to the first target bus gene.

Specifically, the bus gene mutation iteration variable is set in advance. The bus gene mutation iteration variable is used to describe the variation of the initial bus gene. The bus gene variation iteration variable is used to count the variation of the initial bus gene. The bus gene variation is Iteration variables can be accessed through variable names. The bus gene mutation iteration variables can be described in the form of key-value pairs. The keywords of the key-value pairs (ie, variable names) are used to describe the bus gene mutation iteration variables. The key-value pairs The value (the value of the variable, that is, the value corresponding to the variable name) is used to describe the specific value of the mutation of the initial bus gene. The value of the key-value pair can be accessed through the keyword of the key-value pair. The bus gene mutation iteration variable It may be the number of mutation iterations of the initial bus gene, or the bus gene mutation iteration variable may be the number of population generations (that is, the number of bus gene iterations) in which the average population fitness of the bus population remains unchanged continuously.

Based on the bus gene variation iteration variable, for each iteration of the initial bus gene, the bus gene variation iteration variable is obtained, and it is judged whether the bus gene variation iteration variable satisfies the preset bus gene variation termination condition, and the preset bus gene variation terminates Condition description: The bus gene is based on the termination condition of gene mutation and natural selection of the genetic algorithm (i.e., the completion condition of gene mutation and natural selection). The preset bus gene mutation termination condition can be the maximum number of mutation iterations of the bus gene, or all The average population fitness of the bus population composed of bus genes remains unchanged for S consecutive rounds (S is a preset constant), where the average population fitness is the average of the fitness of all bus genes in the bus population. If the bus gene mutation iteration variable does not meet the preset bus gene mutation termination condition, the naturally selected bus gene that meets the preset first fitness condition will not be screened out. If the bus gene mutation iteration variable satisfies the preset The bus gene mutation termination condition is to select the naturally selected bus genes that meet the preset first fitness condition as the first target bus gene, where the preset first fitness condition can be several buses with larger fitness Gene, or for multiple bus genes with the same departure time, a selective method is used to determine a bus gene, such as randomly selecting one of the bus genes, or selecting the bus gene ranked first. For example, since different bus genes correspond to different departure times, it is impossible to send out more than one bus at the same minute during actual departure. Therefore, although the departure times of two or more adjacent bus genes can be the same , but when there are multiple bus genes with the same departure time, you can only consider one of the bus genes and ignore other bus genes with the same departure time. For example, for bus genes [(390,normal,medium),(395,normal,big),(395,express,medium)] with the same departure time, it can be equivalent to [(390,normal,medium),( 395,normal,big)].

Since the bus gene corresponds to the departure frequency, therefore, after determining the first target bus gene, the departure frequency corresponding to the first target bus gene can be determined, and the departure frequency corresponding to the first target bus gene can be determined The shifts are sorted according to the chronological order of departure time, thereby obtaining the schedule of the bus lines. If the preset bus gene mutation termination conditions are not met, the naturally selected bus genes that meet the preset first fitness condition will not be screened out, and the bus gene mutation and natural selection will continue until the preset bus gene mutation termination conditions are met. No more mutation and natural selection of bus genes.

In the embodiment of this application, the initial bus genes are obtained by obtaining different types of bus factors and combining the bus factors, and then the fitness of the initial bus genes is evaluated, and the initial bus genes are screened for survival of the fittest based on the fitness. Obtain the natural selection bus gene, then obtain the bus gene variation iteration variable, and determine whether the bus gene variation iteration variable meets the preset bus gene variation termination condition. If the bus gene variation iteration variable satisfies the preset bus gene variation termination condition, The naturally selected bus genes that meet the preset first fitness condition are screened out, and based on the departure frequency corresponding to the selected naturally selected bus gene, the bus line schedule is obtained, so that the bus line schedule involves many factors. Different types of public transportation factors are combined to construct the initial public transportation gene, and based on the adaptive screening of the genetic algorithm, the initial public transportation gene is subjected to natural selection of survival of the fittest through fitness, and then the first public transportation gene that meets the preset fitness conditions is obtained. Combined bus genes, and based on the departure frequency corresponding to the bus gene, the bus line scheduling is obtained, so that the bus line scheduling is more in line with the actual needs that require a combination of multiple bus factors, and can improve the efficiency of bus routes based on a variety of bus The objectivity of factor scheduling can reduce the operating costs of bus lines without increasing the average waiting time of passengers.

Please refer to Figure 2. Figure 2 is a schematic diagram of the first sub-flow of the bus route scheduling processing method provided by the embodiment of the present application. As shown in Figure 2, after obtaining the initial bus gene, it also includes:

Add the initial bus gene to the preset bus population;

After determining whether the preset bus gene mutation termination conditions are met, it also includes:

S21. If the preset bus gene mutation termination condition is not met, obtain the bus gene that meets the preset second fitness condition from the preset bus population as the second target bus gene;

S22. Genetically mutate the second target bus gene to obtain the offspring bus gene, and add the offspring bus gene to the preset bus population;

S23. Calculate the fitness of the bus genes of the offspring, and select the bus genes included in the preset bus population for survival of the fittest based on the fitness of each bus gene included in the preset bus population;

S24. Determine again whether the preset bus gene mutation termination conditions are met;

S25. If the preset bus gene mutation termination condition is still not satisfied, iteratively obtain the bus gene that satisfies the preset second fitness condition from the preset bus population as the bus corresponding to the second target bus gene. The genetic mutation process of the gene until the preset bus gene mutation termination conditions are met;

S26. If the preset bus gene mutation termination condition is met, perform the step of screening out naturally selected bus genes that meet the preset first fitness condition.

Specifically, the initial bus gene is added to a preset bus population, which describes a group of bus genes that undergo genetic mutation, and the bus gene mutation iteration is performed based on the preset bus population, and the bus gene is added to the preset bus population. The preset bus population contains bus genes for natural selection of survival of the fittest.

If the preset bus gene mutation termination conditions are not met, and the naturally selected bus genes that meet the preset first fitness condition are not screened out, buses that meet the preset second fitness condition are obtained from the preset bus population. Genes, the bus genes with the preset second fitness condition can be the preset third number of bus genes with greater fitness, as the second target bus genes, and the second target bus genes are genetically mutated, Obtain the offspring bus genes, and then add the offspring bus genes to the preset bus population to update the preset bus population.

Since each iteration of the initial bus gene changes, the bus genes are screened for survival of the fittest based on the fitness of the bus gene, so that the preset bus population retains the elite buses corresponding to the feasible solutions with higher fitness. Genes, in particular, the preset second fitness condition is to obtain bus genes from the preset bus population with a preset sampling probability, and the preset sampling probability is consistent with the bus genes included in the preset bus population. The corresponding bus vehicle cost is inversely proportional, so that the preset bus population maintains a certain proportion of feasible solutions and prevents the preset bus population from deviating too far from the feasible area.

Calculate the fitness of the bus genes of the offspring to obtain the fitness of each bus gene included in the preset bus population, and convert the preset bus gene according to the fitness of each bus gene included in the preset bus population. The bus genes contained in the bus population are again subjected to natural selection of survival of the fittest, and it is again determined whether the preset bus gene mutation termination conditions are met. If the preset bus gene mutation termination conditions are still not met, the iteration continues from the preset bus gene mutation termination conditions. Obtain bus genes that meet the preset second fitness condition from the population, and genetically mutate the acquired bus genes until the preset bus gene mutation termination conditions are met. If the preset bus gene mutation termination conditions are met, filter Naturally selected bus genes that meet the preset first fitness condition are selected, and the selected naturally selected bus genes are converted into bus line schedules to obtain the bus line schedule. Based on the genetic algorithm, the fitness Through iterative gene mutation of larger bus genes, a bus schedule that integrates multiple bus factors is finally obtained, which can improve the objectivity of bus schedules based on multiple bus factors, thereby reducing the average waiting time of passengers without increasing the bus schedule. Bus line operating costs.

In one embodiment, please refer to FIG. 3 , which is a second sub-flow schematic diagram of a bus route scheduling processing method provided by an embodiment of the present application. As shown in Figure 3, a group of bus genes is described by a bus gene array. The bus gene array contains bus gene elements. Each of the bus gene elements describes the departure frequency corresponding to a bus gene. The bus gene elements include bus Gene node, the bus gene node stores one type of bus factors. In this embodiment, the second target bus gene is genetically mutated to obtain the offspring bus gene, including:

S31. Obtain two bus gene elements, and intercept them at the same position of the two bus gene elements to obtain a pair of sub-gene elements at the corresponding position;

S32. Replace the two sub-gene elements contained in the sub-gene element with each other in a crossover manner to obtain the offspring bus gene.

Specifically, all departures of a bus line are described using an array, that is, a bus gene array is used to describe a group of bus genes. The bus gene array contains bus gene elements, and each of the bus gene elements describes the departure corresponding to a bus gene. The bus gene element includes a bus gene node, and each bus gene node stores a type of bus factor. In particular, the bus gene element may include multiple bus gene nodes, and one bus gene element describes multiple types. public transportation factors, thereby combining multiple factors involved in the scheduling of bus lines to achieve comprehensive scheduling of bus lines based on multiple factors.

When performing gene mutation, two bus gene elements are obtained. The two bus gene elements contain the same number of bus gene nodes. That is, the structures of the bus gene nodes contained in the two bus gene elements are the same. Intercept at several identical positions of the public transportation gene elements, that is, intercept at the position of the nth public transportation gene node of the two public transportation gene elements to obtain a pair of sub-transit gene elements at the corresponding position, and then add the sub-transit gene elements to The bus gene element replaces the two sub-bus gene elements contained in it in a crossover manner to obtain the offspring bus gene. For example, if there are two bus gene elements a and b, among which, the bus gene element a is [a ₁ , a ₂ , a ₃ ,... _an ], and the bus gene element b is [b ₁ , b ₂ , b ₃ , ...b _n ], where a _n describes the n-th bus gene node of bus gene element a, b _n describes the n-th bus gene node of bus gene element b, and each bus gene node description of bus gene elements a and b A type of transit factor. At least the following methods can be used to carry out genetic mutation and obtain offspring genes:

1) Single point crossover. For example, for the above two bus gene elements a and b, the third bus gene node a ₃ of the bus gene element a can be selected, and the bus gene element a can be [a ₁ , a ₂ , a ₃ ,...a _n ] Intercept into two parts: sub-gene elements [a ₁ , a ₂ , a ₃ ] and [a ₄ ,...a _n ], select the third bus gene node b ₃ of the bus gene element b, and the bus gene element b can be [ b ₁ , b ₂ , b ₃ ,…b _n ] are intercepted into two parts: sub-gene element [b ₁ , b ₂ , b ₃ ] and [b ₄ ,…b _n ], among which the sub-gene element at the corresponding position [ a ₁ , a ₂ , a ₃ ] and [b ₁ , b ₂ , b ₃ ] are pairs of sub-gene elements, and the corresponding position sub-gene elements [a ₄ ,... _an ] and [b ₄ ,...b _n ] is a sub-gene element pair, and you can select the sub-gene element pair [a ₄ ,... _an ] and [b ₄ ,...b _n ], and select [a ₄ ,... _an ] and [b ₄ ,...b _n ] By replacing each other in the crossover method, the offspring bus genes [a ₁ , a ₂ , a ₃ , b ₄ ,...b _n ] and [b ₁ , b ₂ , b ₃ , a ₄ ,...a _n ] can be obtained, thereby converting the bus genes Genetic elements mutate to produce offspring genes.

2) Double point intersection. For example, for the above two bus gene elements a and b, the third bus gene node a ₃ and the fifth bus gene node a ₅ of the bus gene element a can be selected, and the bus gene element a can be [a ₁ , a ₂ , a ₃ ,... _an ] are intercepted into three parts: sub-gene elements [a ₁ , a ₂ , a ₃ ], [a ₄ , a ₅ ] and [a ₆ ,... _an ], and select the bus gene element b For the third bus gene node b ₃ and the fifth bus gene node b ₅ , the bus gene elements b can be intercepted as [b ₁ , b ₂ , b ₃ ,...b _n ] into sub-gene elements [b ₁ , b ₂ , b ₃ ], [b ₄ , b ₅ ] and [b ₆ ,...b _n ]. Among them, the sub-gene element pairs at the corresponding positions include: [a ₁ , a ₂ , a ₃ ] and [b ₁ , b ₂ , b ₃ ], [a ₄ , a ₅ ] and [b ₄ , b ₅ ], and [a ₆ ,...a _n ] and [b ₆ ,...b _n ], and sub-gene elements can be selected For [a ₁ , a ₂ , a ₃ ] and [b ₁ , b ₂ , b ₃ ], [a ₄ , a ₅ ] and [b ₄ , b ₅ ], or [a ₆ ,...a _n ] and [ b ₆ ,...b _n ] adopt a crossover method to replace each other. For example, the offspring bus genes [a ₁ , a ₂ , a ₃ , a ₄ , a ₅ , b ₆ ,...b _n ] and [b ₁ , b ₂ can be obtained , b ₃ , b ₄ , b ₅ , a ₆ ,…a _n ], thereby mutating the bus gene elements to produce offspring bus genes.

3) Multi-point crossover. Similar to the above-mentioned single-point crossover and double-point crossover, especially when multiple bus gene nodes are included, only bus gene nodes with 3 or more bus gene elements are selected, and the two bus gene elements are intercepted into four parts. Or four or more segments of sub-gene elements, and four or more pairs of sub-gene elements are obtained, and then the pairs of sub-gene elements are selected to replace each other in a crossover manner, thereby mutating the bus genes and producing offspring bus genes.

The above-mentioned way of mutating bus genes can fully reflect the randomness and diversity of bus gene mutations based on genetic algorithms, making the resulting bus genes more diverse, thereby further improving the objectivity of scheduling based on multiple bus factors as much as possible , reducing the operating costs of bus lines without increasing the average waiting time of passengers.

In one embodiment, please refer to FIG. 4 , which is a schematic diagram of the third sub-flow of the bus route scheduling processing method provided by the embodiment of the present application. A group of bus genes is described by a bus gene array. The bus gene array contains bus gene elements. Each of the bus gene elements describes a bus schedule corresponding to a bus gene. The bus gene elements include bus gene nodes. The bus gene elements The gene node stores a type of public transportation factor, as shown in Figure 4. In this embodiment, the second target public transportation gene is genetically mutated to obtain a descendant public transportation gene, including:

S41. Obtain the bus gene element and select the bus gene node contained in the bus gene element;

S42. Replace the bus factors of the bus gene node with other bus factors of the same type to obtain the offspring bus genes.

Specifically, when performing gene mutation, a bus gene element is obtained, and the bus gene node contained in the bus gene element is selected. In particular, the bus gene node contained in the bus gene element can be randomly selected, so that the genetic variation can be better described. randomness, and replace the bus factors of the bus gene node with other bus factors of the same type to obtain the offspring bus genes. For example, if there is a bus gene element a as [a ₁ , a ₂ , a ₃ ,... _an ], the mth bus gene node a _m contained in the bus gene element a can be randomly selected, where 1＜m＜n, And replace a _m with other bus factors of the same type. For example, if a _m is a large vehicle in the starting model, you can randomly replace the large vehicle with a medium-sized car or a small car in the starting model, so as to obtain the bus genes of future generations. The way the bus gene mutates can be called a single point mutation. The above-mentioned bus gene mutation method enriches the bus gene mutation method, can fully reflect the randomness and diversity of bus gene mutation based on genetic algorithms, and makes the generated bus genes more diverse, thereby further improving the efficiency of bus gene mutation as much as possible. The objectivity of bus schedules based on various bus factors can reduce the operating costs of bus lines without increasing the average waiting time of passengers.

Further, when the second target bus gene is genetically mutated to obtain the bus gene of the offspring, the genetic mutation methods of Figure 3 and Figure 4 described above can be combined to genetically mutate the second target bus gene, For example, randomly selecting the single-point crossover, double-point crossover, multi-point crossover or single-point mutation described above to genetically mutate the specific second target bus gene can more prominently reflect the randomness of gene mutation based on genetic algorithms. The resulting bus genes will be richer and more diverse, thereby further improving the objectivity of bus schedules based on a variety of bus factors, and reducing the operating costs of bus lines without increasing the average waiting time of passengers.

In one embodiment, please refer to FIG. 5 , which is a schematic diagram of the fourth sub-flow of a bus route scheduling processing method provided by an embodiment of the present application. As shown in Figure 5, in this embodiment, after obtaining the schedule of the bus line, it also includes:

S51. Iterate the genetic mutation of the initial bus gene n times, and calculate the estimated average waiting time corresponding to the bus line schedule obtained in each iteration, where n≥2, n is an integer;

S52. Obtain the historical average waiting time of the bus line based on the single historical schedule of the bus line;

S53. Determine whether the estimated average waiting time is less than or equal to the historical average waiting time;

S54. If the estimated average waiting time is greater than the historical average waiting time, do not use the estimated average waiting time as the target estimated average waiting time;

S55. If the estimated average waiting time is less than or equal to the historical average waiting time, use the estimated average waiting time as the target estimated average waiting time;

S56. Calculate the proportion of the number of all the target estimated average waiting times to the number of all the estimated average waiting times;

S57. Determine whether the ratio is less than or equal to the preset first ratio threshold;

S58. If the ratio is less than or equal to the preset first ratio threshold, increase the penalty coefficient;

S59. If the proportion is greater than the preset first proportion threshold, determine whether the proportion is greater than or equal to the preset second proportion threshold;

S60. If the ratio is greater than or equal to the preset second ratio threshold, reduce the penalty coefficient, wherein the preset first ratio threshold is smaller than the preset second ratio threshold;

S61. If the ratio is smaller than the preset second ratio threshold, do not reduce the penalty coefficient.

Specifically, since the fitness of the bus gene is - (bus vehicle cost + average passenger waiting time * penalty coefficient), and the higher the bus cost, it means that more bus vehicles need to be used to arrange more departures. The corresponding waiting time for passengers is lower. On the contrary, the lower the cost of bus vehicles, which means that fewer buses need to be used to arrange fewer departures, and the waiting time for passengers is relatively higher. Therefore, based on the fitness of the above-mentioned bus genes, when the penalty coefficient is high, the fitness of the bus genes focuses more on the average waiting time of passengers, resulting in more bus schedules with low passenger waiting times but high bus vehicle costs. , when the penalty coefficient is low, the fitness of bus genes focuses more on bus vehicle costs, resulting in more bus schedules with low bus vehicle costs but high passenger waiting times. Therefore, using a high penalty coefficient can obtain a passenger waiting time that is no higher than the average waiting time of passengers under the original schedule. By reducing the penalty coefficient, a bus schedule with lower bus vehicle cost can be obtained, so that the bus schedule can be obtained through dynamic Adjust the penalty coefficient to achieve an ideal balance between the average waiting time of passengers and the cost of bus vehicles, thereby reducing the cost of the bus company without increasing the average waiting time of passengers.

The initial bus gene is genetically mutated. Each time the initial bus gene is mutated for one generation, that is, the initial bus gene undergoes gene mutation iteration once, the corresponding generation of bus population can be obtained, and the characteristics of the bus population of this generation can be obtained. Corresponding schedule, according to the obtained schedule, obtain the estimated average waiting time corresponding to the schedule, and the estimated average waiting time is the schedule of the bus line obtained in each iteration The average waiting time for a bus is obtained, and then the historical average waiting time for the bus line is obtained based on the single historical schedule of the bus line. The single historical schedule can be the schedule currently being used by the bus line. surface.

Determine whether the estimated average waiting time is less than or equal to the historical average waiting time, that is, compare the estimated average waiting time with the historical average waiting time. If the estimated average waiting time The time is less than or equal to the historical average waiting time, indicating that the schedule corresponding to the estimated average waiting time is better than the schedule corresponding to the historical average waiting time, and the estimated average waiting time is equal to The bus time is used as the target to estimate the average waiting time, and the schedule corresponding to the estimated average waiting time is used as a feasible solution for the bus line scheduling.

Calculate the proportion of all the target estimated average waiting times in the number of all estimated average waiting times, and determine whether the proportion is less than or equal to the preset first proportion threshold. If the If the proportion is less than the preset first proportion threshold, the penalty coefficient is increased. If the proportion is greater than the preset first proportion threshold, then it is determined whether the proportion is greater than or equal to the preset second proportion threshold. If If the ratio is greater than or equal to the preset second ratio threshold, the penalty coefficient is reduced, wherein the preset first ratio threshold is smaller than the preset second ratio threshold. If the ratio is smaller than the The second proportion threshold is preset and the penalty coefficient is not reduced. The amount by which the penalty coefficient is increased or decreased may be a preset value, and the value may be an empirical value. For example, count the proportion of feasible solutions in the bus population of the last five generations. If the proportion is less than 0.2, it indicates that there are many infeasible solutions in the bus population. At this time, the penalty coefficient can be increased to 1.2 times the original value, so as to be more focused. Compared with the waiting time, we can find as many feasible solutions as possible. If the proportion is greater than 0.8, it indicates that there are many feasible solutions in the bus population. At this time, the penalty coefficient is reduced to 0.8 times of the original, so as to make it more feasible. Focus on cost and try to find as many feasible solutions to lower-cost shift scheduling as possible. Through the dynamic adjustment of the penalty coefficient, it is possible to dynamically achieve a better trade-off between the cost of bus vehicles and the average waiting time of passengers, find as many feasible solutions to lower-cost scheduling as possible, and further improve the efficiency of bus schedules based on multiple The objectivity of bus factor scheduling can reduce the operating costs of bus lines without increasing the average waiting time of passengers.

It should be noted that in the embodiment shown in FIG. 5 , steps S57 to S59 are just an example to describe the processing flow of this embodiment, and are not intended to limit the order of step S57 and step S59. In another implementation, In this example, the content of step S59 can also be determined first, and then the content of step S57 can be determined as needed, which does not affect the implementation result of this embodiment.

It should be noted that the bus line scheduling processing methods described in the above embodiments can recombine the technical features contained in different embodiments as needed to obtain a combined implementation solution, but all of them are required in this application. within the scope of protection.

Please refer to FIG. 6 , which is a schematic block diagram of a bus route scheduling processing device provided by an embodiment of the present application. Corresponding to the above-mentioned bus line scheduling processing method, embodiments of the present application also provide a bus line scheduling processing device. As shown in FIG. 6 , the bus line scheduling processing device includes a unit for executing the above-mentioned bus line scheduling processing method, and the bus line scheduling processing device can be configured in a computer device. Specifically, please refer to FIG. 6 . The bus line scheduling processing device 60 includes a first acquisition unit 61 , a first screening unit 62 , a first judgment unit 63 , a second screening unit 64 and a first acquisition unit 65 .

Among them, the first acquisition unit 61 is used to acquire different types of bus factors, and combine the bus factors to obtain an initial bus gene, where the bus factors describe the factors involved in the scheduling of bus lines, and the The initial bus gene describes the initial departure frequency;

The first screening unit 62 is used to calculate the fitness of each of the initial bus genes, and according to the size of the fitness, screen the initial bus genes for survival of the fittest to obtain the naturally selected bus genes, wherein: Fitness describes the quality of the initial bus gene;

The first judgment unit 63 is used to obtain the bus gene mutation iteration variable and determine whether the bus gene mutation iteration variable meets the preset bus gene mutation termination condition;

The second screening unit 64 is used to screen out the naturally selected bus genes that meet the preset first fitness condition as the first target bus gene if the bus gene mutation iterative variable satisfies the preset bus gene mutation termination condition;

The first obtaining unit 65 is configured to obtain the schedule of the bus line according to the departure frequency corresponding to the first target bus gene.

In one embodiment, the fitness is calculated as follows:

Among them, the bus vehicle cost is the cost incurred by the operation of the bus vehicle, the average waiting time of passengers is the average waiting time of all passengers on the bus line, and the penalty coefficient is a hyperparameter.

In one embodiment, the bus route scheduling processing device 60 further includes:

An adding unit for adding the initial bus gene to a preset bus population, wherein the preset bus population describes a bus gene group that undergoes genetic mutation;

A second acquisition unit, configured to acquire a bus gene that satisfies the preset second fitness condition from the preset bus population as the second target bus gene if the preset bus gene mutation termination condition is not met;

A gene mutation unit, used to genetically mutate the second target bus gene to obtain a descendant bus gene, and add the descendant bus gene to the preset bus population;

The third screening unit is used to calculate the fitness of the bus genes of the offspring, and select the bus genes included in the preset bus population for survival of the fittest based on the fitness of each bus gene included in the preset bus population. ;

The second judgment unit is used to judge again whether the preset bus gene mutation termination condition is met;

an iterative unit, configured to iterate the bus genes that satisfy the preset second fitness condition from the preset bus population as the second target bus gene if the preset bus gene mutation termination condition is still not satisfied; The genetic mutation process of the corresponding bus gene until the preset bus gene mutation termination condition is met;

An execution unit, configured to execute the step of screening out naturally selected bus genes that meet the preset first fitness condition if the preset bus gene mutation termination condition is met.

In one embodiment, a group of bus genes is described by a bus gene array. The bus gene array contains bus gene elements. Each of the bus gene elements describes the departure frequency corresponding to a bus gene. The bus gene elements include bus genes. Gene node, the bus gene node stores a type of bus factor, and the gene variation unit includes:

Intercepting sub-units is used to obtain two bus gene elements, and intercept the two bus gene elements at the same position to obtain a pair of sub-gene elements at the corresponding position;

The cross-exchange subunit is used to replace the two sub-gene elements contained in the sub-gene element with each other in a cross-over manner to obtain the offspring bus gene.

In one embodiment, a group of bus genes is described by a bus gene array. The bus gene array contains bus gene elements. Each of the bus gene elements describes the departure frequency corresponding to a bus gene. The bus gene elements include bus genes. Gene node, the gene variation unit includes:

The first acquisition subunit is used to obtain the bus gene element and select the bus gene node contained in the bus gene element;

The replacement subunit is used to replace the public transportation factors of the public transportation gene node with other public transportation factors of the same type to obtain the descendant public transportation genes.

The first statistical unit is used to perform gene mutation iterations on the initial bus gene n times, and count the estimated average waiting time corresponding to the bus line schedule obtained in each iteration, where n ≥ 2 , n is an integer;

The third acquisition unit is used to obtain the historical average waiting time of the bus line based on the single historical schedule of the bus line;

The third judgment unit is used to judge whether the estimated average waiting time is less than or equal to the historical average waiting time;

A determination unit configured to use the estimated average waiting time as the target estimated average waiting time if the estimated average waiting time is less than or equal to the historical average waiting time;

A calculation unit configured to calculate the proportion of the number of all the target estimated average waiting times to the number of all the estimated average waiting times;

A fourth judgment unit, used to judge whether the ratio is less than or equal to a preset first ratio threshold;

An increasing unit configured to increase the penalty coefficient if the proportion is less than or equal to the preset first proportion threshold;

The fifth judgment unit is used to judge whether the ratio is greater than or equal to the preset second ratio threshold.

A reducing unit configured to reduce the penalty coefficient if the ratio is greater than or equal to the preset second ratio threshold, wherein the preset first ratio threshold is smaller than the preset second ratio threshold.

In one embodiment, the bus factors include departure time, departure type and departure model.

It should be noted that those skilled in the art can clearly understand that the above-mentioned bus line scheduling processing device and the specific implementation process of each unit can refer to the corresponding descriptions in the foregoing method embodiments. For the convenience and simplicity of description, I won’t go into details here.

At the same time, the division and connection of each unit in the above bus line scheduling processing device are only for illustration. In other embodiments, the bus line scheduling processing device can be divided into different units according to needs, and can also be divided into different units according to needs. Each unit in the bus line scheduling processing device adopts different connection sequences and methods to complete all or part of the functions of the bus line scheduling processing device.

The above bus line scheduling processing device can be implemented in the form of a computer program, and the computer program can be run on the computer device as shown in Figure 7.

Please refer to FIG. 7 , which is a schematic block diagram of a computer device provided by an embodiment of the present application. The computer device 500 may be a computer device such as a desktop computer or a server, or may be a component or component in other devices.

Referring to Figure 7, the computer device 500 includes a processor 502, a memory and a network interface 505 connected through a system bus 501. The memory may include a non-volatile storage medium 503 and an internal memory 504, and the memory may also be volatile. storage media.

The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it can cause the processor 502 to execute the above-mentioned bus route scheduling processing method.

The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

The internal memory 504 provides an environment for the execution of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, it can cause the processor 502 to perform the above-mentioned bus line scheduling processing method.

The network interface 505 is used for network communication with other devices. Those skilled in the art can understand that the structure shown in Figure 7 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than shown, some combinations of components, or a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and processor are consistent with the embodiment shown in FIG. 7 and will not be described again.

Wherein, the processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps: obtain different types of bus factors and combine the bus factors to obtain an initial bus gene, wherein the bus The factors describe the factors involved in bus line scheduling, and the initial bus genes describe the initial departure frequency; the fitness of each initial bus gene is calculated, and according to the size of the fitness, the initial bus genes are Carry out the screening of survival of the fittest to obtain the natural selection bus gene, where the fitness describes the degree of excellence of the initial bus gene; obtain the bus gene mutation iteration variable, and determine whether the bus gene mutation iteration variable satisfies the preset bus gene Mutation termination condition; if the bus gene mutation iteration variable satisfies the preset bus gene mutation termination condition, select the naturally selected bus gene that meets the preset first fitness condition as the first target bus gene; according to the first According to the departure frequency corresponding to a target bus gene, the schedule of the bus line is obtained.

In one embodiment, when the processor 502 implements the calculation of the fitness of each of the initial bus genes, the fitness is calculated as follows:

In one embodiment, after obtaining the initial bus genes, the processor 502 also implements the following steps:

Add the initial bus gene to a preset bus population, wherein the preset bus population describes a bus gene group that undergoes genetic mutation;

If the preset bus gene mutation termination condition is not met, the bus gene that meets the preset second fitness condition is obtained from the preset bus population as the second target bus gene; the second target bus gene is Gene mutation, obtain offspring bus genes, and add the offspring bus genes to the preset bus population; calculate the fitness of the offspring bus genes, and calculate the fitness of each bus gene included in the preset bus population according to the degree, the bus genes included in the preset bus population are screened for survival of the fittest; it is again determined whether the preset bus gene mutation termination conditions are met; if the preset bus gene mutation termination conditions are still not met, iterate the The bus gene that satisfies the preset second fitness condition is obtained from the preset bus population and is used as the gene mutation process of the bus gene corresponding to the second target bus gene until the preset bus gene mutation termination condition is met; if The preset bus gene mutation termination condition is used to perform the step of screening out naturally selected bus genes that meet the preset first fitness condition.

In one embodiment, a group of bus genes is described by a bus gene array. The bus gene array contains bus gene elements. Each of the bus gene elements describes the departure frequency corresponding to a bus gene. The bus gene elements include bus genes. Gene node. The bus gene node stores one type of bus factors. When the processor 502 implements the genetic mutation of the second target bus gene to obtain the offspring bus gene, the processor 502 specifically implements the following steps:

Obtain two bus gene elements and intercept them at the same position of the two bus gene elements to obtain a pair of sub-gene elements at the corresponding position;

The two sub-gene elements contained in the sub-gene element are replaced with each other in a crossover manner to obtain a descendant bus gene.

Obtain the bus gene element and select the bus gene node contained in the bus gene element;

The bus factors of the bus gene node are replaced with other bus factors of the same type to obtain the offspring bus genes.

In one embodiment, after obtaining the bus schedule, the processor 502 also performs the following steps:

The initial bus gene is genetically mutated and iterated n times, and the estimated average waiting time corresponding to the bus line schedule obtained in each iteration is calculated, where n≥2, n is an integer; according to the Based on the single historical schedule of the bus line, obtain the historical average waiting time of the bus line; determine whether the estimated average waiting time is less than or equal to the historical average waiting time; if the estimated average waiting time If the bus time is less than or equal to the historical average waiting time, use the estimated average waiting time as the target estimated average waiting time; calculate the number of all target estimated average waiting times in all the estimated The proportion of the average waiting time; determine whether the proportion is less than or equal to the preset first proportion threshold; if the proportion is less than or equal to the preset first proportion threshold, increase the penalty coefficient ; Or, determine whether the proportion is greater than or equal to the preset second proportion threshold. If the proportion is greater than or equal to the preset second proportion threshold, reduce the penalty coefficient, wherein the preset first proportion The threshold is smaller than the preset second ratio threshold.

In one embodiment, when the processor 502 implements the acquisition of different types of bus factors, the bus factors include departure time, departure type and departure model.

It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (Central Processing Unit, CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), Application Specific Integrated Circuit (ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general processor may be a microprocessor or the processor may be any conventional processor.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above method.

Therefore, the present application also provides a computer-readable storage medium. The computer-readable storage medium can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program is executed by the processor. When the processor performs the following steps:

A computer program product, when run on a computer, causes the computer to execute the steps of the bus line scheduling processing method described in the above embodiments.

The computer-readable storage medium may be an internal storage unit of the aforementioned device, such as a hard disk or memory of the device. The computer-readable storage medium may also be an external storage device of the device, such as a plug-in hard disk, a smart memory card (SMC), or a secure digital (SD) card equipped on the device. , Flash Card, etc. Further, the computer-readable storage medium may also include both an internal storage unit of the device and an external storage device.

Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described equipment, devices and units can be referred to the corresponding processes in the foregoing method embodiments, and will not be described again here.

The storage medium is a physical, non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk, which can store computer programs. medium.

Those of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of both. In order to clearly illustrate the relationship between hardware and software Interchangeability, in the above description, the composition and steps of each example have been generally described according to functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each specific application, but such implementations should not be considered beyond the scope of this application.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only a logical function division, and there may be other division methods during actual implementation. For example multiple units or components may be combined or integrated into another system, or some features may be omitted, or not implemented.

The steps in the methods of the embodiments of this application can be sequence adjusted, combined, and deleted according to actual needs. The units in the device of the embodiment of the present application can be merged, divided, and deleted according to actual needs. In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present application is essentially or contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to cause an electronic device (which may be a personal computer, terminal, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person familiar with the technical field can easily think of various equivalents within the technical scope disclosed in the present application. modifications or substitutions, these modifications or substitutions shall be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

A bus line scheduling processing method, which is characterized by including:

Obtain different types of bus factors, and combine the bus factors to obtain an initial bus gene, where the bus factors describe factors involved in bus line scheduling, and the initial bus gene describes the initial departure frequency;

The fitness of each initial bus gene is calculated, and based on the size of the fitness, the initial bus genes are screened for survival of the fittest to obtain natural selection bus genes, where the fitness describes the initial bus gene degree of excellence;

Obtain the bus gene variation iteration variable, and determine whether the bus gene variation iteration variable meets the preset bus gene variation termination condition;

If the bus gene mutation iteration variable satisfies the preset bus gene mutation termination condition, select the naturally selected bus gene that meets the preset first fitness condition as the first target bus gene;

According to the departure frequency corresponding to the first target bus gene, a schedule of the bus line is obtained.
The bus route scheduling processing method according to claim 1, characterized in that the bus factors include departure time, departure type and departure model.
The bus line scheduling processing method according to claim 1, characterized in that the fitness adopts the following calculation method:

The fitness of the bus gene = - (bus vehicle cost + average waiting time of passengers * penalty coefficient);

Among them, the bus vehicle cost is the cost incurred by the operation of the bus vehicle, the average waiting time of passengers is the average waiting time of all passengers on the bus line, and the penalty coefficient is a hyperparameter.
The bus route scheduling processing method according to claim 1, characterized in that after obtaining the initial bus gene, it further includes:

Add the initial bus gene to a preset bus population, wherein the preset bus population describes a bus gene group that undergoes genetic mutation;

After determining whether the preset bus gene mutation termination conditions are met, it also includes:

If the preset bus gene mutation termination condition is not met, obtain the bus gene that meets the preset second fitness condition from the preset bus population as the second target bus gene;

Genetically mutate the second target bus gene to obtain a progeny bus gene, and add the progeny bus gene to the preset bus population;

Calculate the fitness of the bus genes of the offspring, and select the bus genes included in the preset bus population for survival of the fittest based on the fitness of each bus gene included in the preset bus population;

Determine again whether the preset bus gene mutation termination conditions are met;

If the preset bus gene mutation termination condition is still not satisfied, iterate and obtain the bus gene that satisfies the preset second fitness condition from the preset bus population as the bus gene corresponding to the second target bus gene. Gene mutation process until the preset bus gene mutation termination conditions are met;

If the preset bus gene mutation termination condition is met, the step of screening out naturally selected bus genes that meet the preset first fitness condition is performed.
The bus route scheduling processing method according to claim 4, characterized in that a group of bus genes is described by a bus gene array, the bus gene array contains bus gene elements, and each of the bus gene elements describes a bus gene. Corresponding to the departure schedule, the bus gene element includes a bus gene node, and the bus gene node stores a type of bus factor. The second target bus gene is genetically mutated to obtain a descendant bus gene, including:

Obtain two bus gene elements and intercept them at the same position of the two bus gene elements to obtain a pair of sub-gene elements at the corresponding position;

The two sub-gene elements contained in the sub-gene element are replaced with each other in a crossover manner to obtain a descendant bus gene.
The bus route scheduling processing method according to claim 4, characterized in that a group of bus genes is described by a bus gene array, the bus gene array contains bus gene elements, and each of the bus gene elements describes a bus gene. Corresponding to the departure schedule, the bus gene element includes a bus gene node, and the bus gene node stores a type of bus factor. The second target bus gene is genetically mutated to obtain a descendant bus gene, including:

Obtain the bus gene element and select the bus gene node contained in the bus gene element;

The bus factors of the bus gene node are replaced with other bus factors of the same type to obtain the offspring bus genes.
The bus line scheduling processing method according to claim 1, characterized in that after obtaining the bus line schedule, it further includes:

Iterate the gene mutation of the initial bus gene n times, and calculate the estimated average waiting time corresponding to the bus line schedule obtained in each iteration, where n≥2, n is an integer;

Obtain the historical average waiting time of the bus line based on the single historical schedule of the bus line;

Determine whether the estimated average waiting time is less than or equal to the historical average waiting time;

If the estimated average waiting time is less than or equal to the historical average waiting time, use the estimated average waiting time as the target estimated average waiting time;

Calculate the proportion of the number of all said target estimated average waiting times to the number of all said estimated average waiting times;

Determine whether the ratio is less than or equal to a preset first ratio threshold;

If the ratio is less than or equal to the preset first ratio threshold, increase the penalty coefficient;

Or, determine whether the ratio is greater than or equal to a preset second ratio threshold

If the ratio is greater than or equal to the preset second ratio threshold, the penalty coefficient is reduced, wherein the preset first ratio threshold is smaller than the preset second ratio threshold.
A bus line scheduling processing device, which is characterized by including:

The first acquisition unit is used to obtain different types of bus factors, and combine the bus factors to obtain an initial bus gene, where the bus factors describe factors involved in bus line scheduling, and the initial bus gene Describe the initial departure schedule;

The first screening unit is used to calculate the fitness of each of the initial bus genes, and according to the size of the fitness, the initial bus genes are screened for survival of the fittest to obtain natural selection bus genes, wherein the adaptation Degree describes the quality of the initial bus gene;

The first judgment unit is used to obtain the bus gene variation iteration variable and determine whether the bus gene variation iteration variable meets the preset bus gene variation termination condition;

The second screening unit is used to screen out the naturally selected bus genes that meet the preset first fitness condition as the first target bus gene if the bus gene variation iteration variable satisfies the preset bus gene variation termination condition;

The first acquisition unit is used to obtain the schedule of the bus line according to the departure frequency corresponding to the first target bus gene.
A computer device, characterized in that the computer device includes a memory and a processor connected to the memory; the memory is used to store a computer program; the processor is used to run the computer program to execute the claims Steps of the method described in any one of 1-7.
A computer-readable storage medium, characterized in that the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1-7 can be implemented.