A method and system for scheduling shuttle transport tasks based on cloud management

Abstract

The present invention discloses a method and system for scheduling shuttle bus transportation tasks based on cloud management, and belongs to the technical field of general control or regulation systems. The present invention receives temporary ride applications from employees at a receiving end, screens shuttle buses that meet passenger carrying conditions, constructs a neural network prediction model for traffic congestion time under the influence of weather and a neural network prediction model for traffic congestion time under the influence of vehicle flow, outputs the traffic congestion time of each road section at a historical corresponding time point, calculates the comprehensive traffic congestion time of each road section according to a comprehensive traffic congestion calculation strategy, and estimates the time when the screened shuttle bus arrives at a destination station, and assigns scheduling tasks to the optimal shuttle bus, thereby improving the efficiency of shuttle bus transportation and the accuracy of shuttle bus scheduling.

Description

Technical Field

[0001] The present invention belongs to the general field of control or regulation system technology, and specifically relates to a method and system for scheduling shuttle transportation tasks based on cloud management. Background Art

[0002] Enterprise shuttle bus dispatching refers to the company providing shuttle bus services for employees so that they can arrive at work or return home from work on time. Enterprise shuttle bus dispatching involves many aspects, including route planning, vehicle management, shift scheduling, employee information management, etc. Through scientific and reasonable dispatching plans, the efficiency and punctuality of shuttle buses can be improved, while improving the comfort and satisfaction of employees at work.

[0003] The shuttle bus dispatching systems currently available on the market are mostly fixed shifts and fixed stops, which meet the regular commuting needs. However, in the face of flexible shuttle bus applications, it is impossible to dispatch the shortest shuttle bus to the employee's boarding stop in a short time to meet the needs in a timely manner. For example, the Chinese patent application with the publication number CN115034522A discloses a dynamic dispatching method for commuter buses based on employees' off-get off work time and alighting stops, including the following steps: S1: Collect employee riding demand data; S2: Determine the list of empty vehicles that can be dispatched for each shift; S3: Determine the list of employees who can take the bus for each shift; S4: Optimize the alighting stops of the same shift; S5: Adjust and optimize the positions of each stop in the stop set; S6: Use the ant colony algorithm to allocate vehicles and plan routes for passengers; S7: Report the return time of the vehicle and make scheduling arrangements for the next shift.

[0004] In order to solve the above problems, the present invention designs a shuttle bus transportation task scheduling method and system based on cloud management. Summary of the invention

[0005] The purpose of the present invention is: a receiving end receives an employee's temporary ride application, screens shuttle buses that meet the passenger carrying conditions, constructs a neural network prediction model for traffic congestion time under the influence of weather and a neural network prediction model for traffic congestion time under the influence of traffic flow, outputs the traffic congestion time of each road section at a corresponding historical time point, calculates the comprehensive traffic congestion time of each road section according to a comprehensive traffic congestion calculation strategy, and estimates the time for the selected shuttle bus to arrive at the destination station, assigns the scheduling task to the optimal shuttle bus, and improves the efficiency of shuttle bus transportation and the accuracy of shuttle bus scheduling.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for scheduling shuttle transport tasks based on cloud management includes the following specific steps:

[0008] S1. Extract employee information and shuttle bus information and store them in the information storage module, and plan the number of shuttle bus departures, departure time and travel route according to the employee information;

[0009] S2. Receive temporary passenger-carrying tasks issued by the message notification module, obtain employee boarding and alighting points, and filter out buses with empty seats that contain employee boarding and alighting points on their routes;

[0010] S3, obtaining historical weather information and traffic congestion conditions of each road section under historical weather conditions, constructing a neural network prediction model for traffic congestion time under weather influence, substituting the weather at the corresponding historical time point into the constructed neural network prediction model for traffic congestion time under weather influence, and outputting the traffic congestion time of each road section under the weather influence at the corresponding historical time point. It should be noted that the definition of congestion time is the time of passing through a certain road section minus the time of passing through the road section at a safe speed;

[0011] S4, obtaining historical traffic flow information and traffic congestion conditions of each road section under historical traffic flow, constructing a neural network prediction model for traffic congestion time under the influence of traffic flow, substituting the traffic flow at the corresponding historical time point into the constructed neural network prediction model for traffic congestion time under the influence of traffic flow, and outputting the traffic congestion time of each road section under the influence of the traffic flow at the corresponding historical time point;

[0012] S5. Substitute the outputted traffic congestion time of each road section under the influence of the weather at the corresponding time point in history and the traffic congestion time of each road section under the influence of the traffic volume at the corresponding time point in history into the calculation formula of the comprehensive traffic congestion time to calculate the comprehensive traffic congestion time of each road section, estimate the time for the selected shuttle buses to arrive at the destination station based on the calculated comprehensive traffic congestion time of each road section, and assign the scheduling task to the shuttle bus with the shortest arrival time at the destination station.

[0013] Specifically, S1 includes the following specific steps:

[0014] Employee information includes employee name, boarding point, alighting point and shift information. Shuttle bus information includes the approved passenger capacity, real-time passenger capacity, real-time location and real-time speed of the shuttle bus. Employee information and shuttle bus information are extracted and stored in the information storage module. The shuttle bus departure time is determined according to the employee shift information, the shuttle bus route is determined according to the station location, and the number of shuttle buses is determined according to the number of people at the boarding and alighting points.

[0015] Specifically, S2 includes the following specific steps:

[0016] When an employee applies to take a shuttle bus temporarily, the message notification module publishes a temporary passenger-carrying task, obtains the employee's boarding and alighting points, and selects the buses that have routes that include the employee's boarding and alighting points and have vacancies from the dispatched buses.

[0017] Specifically, S3 includes the following specific steps:

[0018] S31. Obtain historical weather information and traffic congestion conditions of each road section under historical weather conditions and divide the data into two subsets, wherein the first 80% is a training data set and the second 20% is a test data set. The first 80% of the training data set is input into a neural network prediction model for traffic congestion time under weather influence for training to obtain an initial neural network prediction model for traffic congestion time under weather influence. The second 20% of the test data set is used to test the initial neural network prediction model for traffic congestion time under weather influence, and output a neural network prediction model for traffic congestion time under weather influence with the highest accuracy in judging traffic congestion time. The calculation formula for the accuracy of the neural network prediction model for traffic congestion time under weather influence is: in, is the traffic congestion time output by the neural network model of the traffic congestion time in the i-th area under the influence of weather, x i is the traffic congestion time of the ith area under the influence of actual weather conditions, k is the number of congested areas for each road section, and · is the dot product between the vectors;

[0019] S32. The calculation formula of the neural network prediction model for traffic congestion time under the influence of weather is: Among them, w i is the connection weight between the neurons in the hidden layer and the output layer, w0 is the deviation, which is generally 0, and p i is the input data of the ith region, e1 is the center of the neuron basis function, σ1 is the basis function width, and ||·|| is the norm;

[0020] S33, substituting the weather at the corresponding time point in history into the constructed neural network prediction model for traffic congestion time under the influence of weather to output the traffic congestion time of each road section under the influence of the weather at the corresponding time point in history;

[0021] Specifically, S4 includes the following specific steps:

[0022] S41, obtaining historical traffic flow information and traffic congestion conditions of each road section under historical traffic flow and dividing the data into two subsets, wherein the first 80% is a training data set and the second 20% is a test data set, inputting the first 80% of the training data set into the traffic congestion time neural network prediction model under the influence of traffic flow for training, and obtaining an initial traffic congestion time neural network prediction model under the influence of traffic flow, and then using the second 20% of the test data set to test the initial traffic congestion time neural network prediction model under the influence of traffic flow, and outputting a traffic congestion time neural network prediction model under the influence of traffic flow with the smallest judgment error for traffic congestion time, wherein the calculation formula for the traffic congestion time judgment error of the traffic congestion time neural network prediction model under the influence of traffic flow is: in, is the traffic congestion time output by the neural network model of the traffic congestion time in the jth area under the influence of traffic flow, y j is the traffic congestion time of the jth area under the influence of actual traffic flow, l is the number of congested areas for each road section;

[0023] S42. The calculation formula of the neural network prediction model for traffic congestion time under the influence of the traffic flow is: Among them, t j is the connection weight between the neurons in the hidden layer and the output layer, m0 is the deviation, which is generally taken as 0, t j is the input data of the jth region, e2 is the center of the neuron basis function, σ2 is the basis function width, and ||·|| is the norm;

[0024] S43, substituting the traffic volume at the corresponding time point in history into the constructed traffic congestion time neural network prediction model under the influence of traffic volume to output the traffic congestion time of each road section under the influence of the traffic volume at the corresponding time point in history;

[0025] Specifically, S5 includes the following specific steps:

[0026] S51, substituting the outputted traffic congestion time of each road section under the influence of the weather at the corresponding time point in history and the traffic congestion time of each road section under the influence of the traffic volume at the corresponding time point in history into the traffic comprehensive congestion time calculation formula to calculate the traffic comprehensive congestion time of each road section, the traffic comprehensive congestion time calculation formula is: , where α1 is the coefficient of weather affecting traffic, α2 is the coefficient of vehicle flow affecting traffic, α1>0, α2>0 and α1+α2=1. It should be noted that the values ​​of the coefficient of weather affecting traffic and the coefficient of vehicle flow affecting traffic are obtained as follows: 5000 sets of historical data on traffic congestion time under weather influence and traffic congestion time under vehicle flow influence are taken, 50 traffic practitioners are selected to evaluate the data on traffic congestion time under weather influence and traffic congestion time under vehicle flow influence, and 5 sets of weather affecting traffic coefficient and vehicle flow affecting traffic coefficient are selected, and the set of weather affecting traffic coefficient and vehicle flow affecting traffic coefficient with the highest similarity to the actual traffic congestion is selected;

[0027] S52, based on the calculated comprehensive traffic congestion time of each road section, the estimated arrival time of the selected shuttle buses at the destination station, and assigning the dispatching task to the shuttle bus with the shortest arrival time at the destination station. After receiving the dispatching task, the shuttle bus will go to the destination station to pick up employees according to the on-board navigation.

[0028] A cloud-based shuttle transport task scheduling system, which is implemented based on the above-mentioned cloud-based shuttle transport task scheduling method, includes an information storage module, a message notification module, a weather impact module, a traffic flow impact module, a comprehensive traffic congestion calculation module and a control module;

[0029] Specifically, the information storage module is used to store employee information and shuttle bus information, the message notification module is used to publish temporary passenger carrying tasks and allocate scheduling tasks, and the weather impact module is used to input the weather at the corresponding historical time point into the constructed traffic congestion time neural network prediction model under the influence of weather, and output the traffic congestion time of each road section under the influence of the weather at the corresponding historical time point.

[0030] Specifically, the traffic flow impact module is used to input the traffic flow at the corresponding historical time point into the constructed traffic congestion time neural network prediction model under the influence of traffic flow, and output the traffic congestion time of each road section under the influence of traffic flow at the corresponding historical time point. The comprehensive traffic congestion calculation module is used to calculate the comprehensive traffic congestion time of each road section according to the traffic congestion time of each road section under the influence of weather and the traffic congestion time of each road section under the influence of traffic flow, and estimate the time when the selected shuttle bus arrives at the destination station.

[0031] Specifically, the control module is used to control the operation of the information storage module, the message notification module, the weather impact module, the vehicle flow impact module and the comprehensive traffic congestion calculation module.

[0032] An electronic device includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned cloud-management-based shuttle transportation task scheduling method by calling the computer program stored in the memory.

[0033] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for scheduling shuttle transport tasks based on cloud management.

[0034] The beneficial effects of the present invention are as follows: the receiving end of the present invention receives temporary ride applications from employees, screens shuttle buses that meet the passenger carrying conditions, constructs a neural network prediction model for traffic congestion time under the influence of weather and a neural network prediction model for traffic congestion time under the influence of traffic volume, outputs the traffic congestion time of each road section at the corresponding historical time point, calculates the comprehensive traffic congestion time of each road section according to the comprehensive traffic congestion calculation strategy, estimates the time for the selected shuttle bus to arrive at the destination station, assigns the scheduling task to the optimal shuttle bus, and improves the efficiency of shuttle bus transportation and the accuracy of shuttle bus scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of a process flow of a shuttle transport task scheduling method based on cloud management according to the present invention;

[0036] Figure 2 It is a schematic diagram of the overall framework of a shuttle transportation task scheduling system based on cloud management of the present invention. DETAILED DESCRIPTION

[0037] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the present invention equally.

[0038] Example 1

[0039] See also Figure 1 , an embodiment provided by the present invention: a shuttle transportation task scheduling method based on cloud management, which comprises the following specific steps:

[0040] S1. Extract employee information and shuttle bus information and store them in the information storage module, and plan the number of shuttle bus departures, departure time and travel route according to the employee information;

[0041] In this embodiment, S1 includes the following specific steps:

[0042] Employee information includes employee name, boarding point, alighting point and scheduling information. Shuttle bus information includes the approved passenger capacity, real-time passenger capacity, real-time location and real-time speed of the shuttle bus. Employee information and shuttle bus information are extracted and stored in the information storage module. The shuttle bus departure time is determined according to the employee scheduling information, the shuttle bus route is determined according to the station location, and the number of shuttle buses is determined according to the number of people at the boarding and alighting points.

[0043] It should be noted here that employee information can be obtained through devices such as smart bracelets or smart watches worn by employees, including employee names, boarding points, alighting points and shift information. These devices usually have GPS positioning functions, which can record the employee's location in real time and connect to the company's information system to obtain employee travel data; shuttle bus information can be obtained through on-board equipment installed on the shuttle bus, including the shuttle bus's approved passenger capacity, real-time passenger capacity, real-time positioning and real-time vehicle speed. These devices usually have functions such as GPS positioning, video monitoring, and sensors, which can monitor the shuttle bus's operating status and passenger capacity in real time, and connect to the company's information system for scheduling and management.

[0044] S2. Receive temporary passenger-carrying tasks issued by the message notification module, obtain employee boarding and alighting points, and filter out buses with empty seats that contain employee boarding and alighting points on their routes;

[0045] In this embodiment, S2 includes the following specific steps:

[0046] When an employee temporarily applies to take a shuttle bus, the message notification module publishes a temporary passenger-carrying task, obtains the employee's boarding and alighting points, and selects the buses that have routes that include the employee's boarding and alighting points and have vacancies from the dispatched buses.

[0047] S3, obtaining historical weather information and traffic congestion conditions of each road section under historical weather conditions, constructing a neural network prediction model for traffic congestion time under weather influence, substituting the weather at the corresponding historical time point into the constructed neural network prediction model for traffic congestion time under weather influence, and outputting the traffic congestion time of each road section under the weather influence at the corresponding historical time point. It should be noted that the definition of congestion time is the time of passing through a certain road section minus the time of passing through the road section at a safe speed;

[0048] In this embodiment, S3 includes the following specific steps:

[0049] S31. Obtain historical weather information and traffic congestion conditions of each road section under historical weather conditions and divide the data into two subsets, wherein the first 80% is a training data set and the second 20% is a test data set. The first 80% of the training data set is input into a neural network prediction model for traffic congestion time under weather influence for training to obtain an initial neural network prediction model for traffic congestion time under weather influence. The second 20% of the test data set is used to test the initial neural network prediction model for traffic congestion time under weather influence, and output a neural network prediction model for traffic congestion time under weather influence with the highest accuracy in judging traffic congestion time. The calculation formula for the accuracy of the neural network prediction model for traffic congestion time under weather influence is: in, is the traffic congestion time output by the neural network model of the traffic congestion time in the i-th area under the influence of weather, x i is the traffic congestion time of the ith area under the influence of actual weather conditions, k is the number of areas where congestion occurs on each road section, and · is the dot product between vectors. The area division method is as follows: obtain the road surface of the road section that needs to be congested, and divide the road surface into several areas evenly according to the length;

[0050] S32. The calculation formula of the neural network prediction model for traffic congestion time under the influence of weather is: Among them, w i is the connection weight between the neurons in the hidden layer and the output layer, w0 is the deviation, which is generally 0, and p i is the input data of the ith region, e1 is the center of the neuron basis function, σ1 is the basis function width, and ||·|| is the norm;

[0051] S33, substituting the weather at the corresponding time point in history into the constructed neural network prediction model for traffic congestion time under the influence of weather, and outputting the traffic congestion time of each road section under the influence of the weather at the corresponding time point in history.

[0052] It should be noted that the historical weather information obtained includes rainfall, snowfall, visibility, etc. Rainfall may make the road slippery, increase the risk of vehicle skidding, and thus affect traffic. Snow accumulation and reduced visibility will hinder the driver's sight distance, which may lead to road closures and increased traffic accidents. In cold weather, icy roads after rain and snow may pose a danger to moving vehicles and cause traffic accidents. Fog, haze and air pollution reduce visibility and increase the risk of traffic accidents.

[0053] Taking rainfall information as an example, historical rainfall and traffic congestion conditions of each road section under historical rainfall are obtained and the data are divided into two subsets, of which the first 80% is a training data set and the second 20% is a test data set. The first 80% of the training data set is input into the neural network prediction model of traffic congestion time under the influence of rainfall for training to obtain an initial neural network prediction model of traffic congestion time under the influence of rainfall. The second 20% of the test data set is used to test the initial neural network prediction model of traffic congestion time under the influence of rainfall, and the neural network prediction model of traffic congestion time under the influence of rainfall with the highest accuracy in judging traffic congestion time is output.

[0054] S4, obtaining historical traffic flow information and traffic congestion conditions of each road section under historical traffic flow, constructing a neural network prediction model for traffic congestion time under the influence of traffic flow, substituting the traffic flow at the corresponding historical time point into the constructed neural network prediction model for traffic congestion time under the influence of traffic flow, and outputting the traffic congestion time of each road section under the influence of the traffic flow at the corresponding historical time point;

[0055] In this embodiment, S4 includes the following specific steps:

[0056] S41, obtaining historical traffic flow information and traffic congestion conditions of each road section under historical traffic flow and dividing the data into two subsets, wherein the first 80% is a training data set and the second 20% is a test data set, inputting the first 80% of the training data set into the traffic congestion time neural network prediction model under the influence of traffic flow for training, and obtaining an initial traffic congestion time neural network prediction model under the influence of traffic flow, and then using the second 20% of the test data set to test the initial traffic congestion time neural network prediction model under the influence of traffic flow, and outputting a traffic congestion time neural network prediction model under the influence of traffic flow with the smallest judgment error for traffic congestion time, wherein the calculation formula for the traffic congestion time judgment error of the traffic congestion time neural network prediction model under the influence of traffic flow is: in, is the traffic congestion time output by the neural network model of the traffic congestion time in the jth area under the influence of traffic flow, y j is the traffic congestion time of the jth area under the influence of actual traffic flow, l is the number of congested areas for each road section;

[0057] S42. The calculation formula of the neural network prediction model for traffic congestion time under the influence of traffic flow is: Among them, t j is the connection weight between the neurons in the hidden layer and the output layer, m0 is the deviation, which is generally 0, t j is the input data of the jth region, e2 is the center of the neuron basis function, σ2 is the basis function width, and ||·|| is the norm;

[0058] S43, substituting the traffic volume at the corresponding time point in history into the constructed neural network prediction model of traffic congestion time under the influence of traffic volume, and outputting the traffic congestion time of each road section under the influence of the traffic volume at the corresponding time point in history.

[0059] It should be noted here that traffic flow has a great impact on traffic congestion. The more vehicles there are, the higher the probability of traffic accidents. In high traffic conditions, drivers usually drive more carefully to avoid collisions, which may lead to a decrease in speed. The reduced speed will reduce the road's capacity, thereby increasing traffic congestion.

[0060] S5. Substitute the outputted traffic congestion time of each road section under the influence of the weather at the corresponding time point in history and the traffic congestion time of each road section under the influence of the traffic volume at the corresponding time point in history into the calculation formula of the comprehensive traffic congestion time to calculate the comprehensive traffic congestion time of each road section, estimate the time for the selected shuttle buses to arrive at the destination station based on the calculated comprehensive traffic congestion time of each road section, and assign the scheduling task to the shuttle bus with the shortest arrival time at the destination station.

[0061] In this embodiment, S5 includes the following specific steps:

[0062] S51, substituting the outputted traffic congestion time of each road section under the influence of the weather at the corresponding time point in history and the traffic congestion time of each road section under the influence of the traffic volume at the corresponding time point in history into the traffic comprehensive congestion time calculation formula to calculate the traffic comprehensive congestion time of each road section, the traffic comprehensive congestion time calculation formula is: , where α1 is the coefficient of weather affecting traffic, α2 is the coefficient of vehicle flow affecting traffic, α1>0, α2>0 and α1+α2=1. It should be noted that the values ​​of the coefficient of weather affecting traffic and the coefficient of vehicle flow affecting traffic are obtained as follows: 5000 sets of historical data on traffic congestion time under weather influence and traffic congestion time under vehicle flow influence are taken, 50 traffic practitioners are selected to evaluate the data on traffic congestion time under weather influence and traffic congestion time under vehicle flow influence, and 5 sets of weather affecting traffic coefficient and vehicle flow affecting traffic coefficient are selected, and the set of weather affecting traffic coefficient and vehicle flow affecting traffic coefficient with the highest similarity to the actual traffic congestion is selected;

[0063] S52, based on the calculated comprehensive traffic congestion time of each road section, the estimated arrival time of the selected shuttle buses at the destination station, and assigning the dispatching task to the shuttle bus with the shortest arrival time at the destination station. After receiving the dispatching task, the shuttle bus will go to the destination station to pick up employees according to the on-board navigation.

[0064] It should be noted here that the calculation of traffic congestion time by combining weather and traffic flow has a higher accuracy. Traffic congestion is a dynamic process, which is affected by many factors, such as traffic flow, road conditions, accident rate, etc. By comprehensively considering the two dynamic factors of weather and traffic flow, the actual situation of traffic congestion can be more comprehensively reflected, and the traffic congestion situation can be calculated more conveniently, providing a decision-making basis for traffic management departments.

[0065] Example 2

[0066] See also Figure 2 A cloud-based shuttle transport task scheduling system is implemented based on the above-mentioned cloud-based shuttle transport task scheduling method, including an information storage module, a message notification module, a weather impact module, a traffic flow impact module, a comprehensive traffic congestion calculation module and a control module.

[0067] In this embodiment, the information storage module is used to store employee information and shuttle bus information, the message notification module is used to publish temporary passenger tasks and allocate scheduling tasks, and the weather impact module is used to input the weather at the corresponding time point in history into the constructed traffic congestion time neural network prediction model under the influence of weather, and output the traffic congestion time of each road section under the influence of the weather at the corresponding time point in history;

[0068] In this embodiment, the traffic flow impact module is used to input the traffic flow at the corresponding time point in history into the constructed traffic congestion time neural network prediction model under the influence of traffic flow, and output the traffic congestion time of each road section under the influence of traffic flow at the corresponding time point in history. The comprehensive traffic congestion calculation module is used to calculate the comprehensive traffic congestion time of each road section according to the traffic congestion time of each road section under the influence of weather and the traffic congestion time of each road section under the influence of traffic flow, and estimate the time when the selected shuttle bus arrives at the destination station;

[0069] In this embodiment, the control module is used to control the operation of the information storage module, the message notification module, the weather impact module, the vehicle flow impact module and the comprehensive traffic congestion calculation module.

[0070] Example 3

[0071] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned cloud-management-based shuttle transportation task scheduling method by calling the computer program stored in the memory.

[0072] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement a cloud-management-based shuttle transport task scheduling method provided in the above method embodiment.

[0073] Example 4

[0074] This embodiment provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer executes the above-mentioned cloud-management-based shuttle transportation task scheduling method.

[0075] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0076] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0077] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0078] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments 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 or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention 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 device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable 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 contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0079] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

Claims

1. A method for scheduling shuttle bus transportation tasks based on cloud management, characterized in that: It includes the following specific steps: S1. Extract and store employee information and shuttle bus information, and obtain the number of shuttle bus departures, departure time, and travel route; S2, the receiving end receives the employee's temporary ride application and screens the buses that meet the passenger carrying conditions; S3, constructing a neural network prediction model for traffic congestion time under the influence of weather, inputting the weather at the corresponding historical time point into the neural network prediction model for traffic congestion time under the influence of weather, and outputting the traffic congestion time of each road section under the influence of the weather at the corresponding historical time point; S4, constructing a neural network prediction model for traffic congestion time under the influence of traffic flow, inputting the traffic flow at the corresponding historical time point into the neural network prediction model for traffic congestion time under the influence of traffic flow, and outputting the traffic congestion time of each road section under the influence of the traffic flow at the corresponding historical time point; S5. Calculate the comprehensive traffic congestion time of each road section according to the comprehensive traffic congestion calculation strategy and estimate the time for the selected shuttle buses to arrive at the destination station, and assign the scheduling task to the optimal shuttle bus; The S3 includes the following specific steps: S31. Obtain historical weather information and traffic congestion conditions of each road section under historical weather conditions and divide the data into two subsets, wherein the first 80% is a training data set and the second 20% is a test data set. The first 80% of the training data set is input into a neural network prediction model for traffic congestion time under weather influence for training to obtain an initial neural network prediction model for traffic congestion time under weather influence. The second 20% of the test data set is used to test the initial neural network prediction model for traffic congestion time under weather influence, and output a neural network prediction model for traffic congestion time under weather influence with the highest accuracy in judging traffic congestion time. The calculation formula for the accuracy of the neural network prediction model for traffic congestion time under weather influence is: in, is the traffic congestion time output by the neural network model of the traffic congestion time in the i-th area under the influence of weather, x i is the traffic congestion time of the ith area under the influence of actual weather conditions, k is the number of congested areas for each road section, and · is the dot product between the vectors; S32. The calculation formula of the neural network prediction model for traffic congestion time under the influence of weather is: Among them, w i is the connection weight between the neurons in the hidden layer and the output layer, w0 is the deviation, p i is the input data of the ith region, e1 is the center of the neuron basis function, σ1 is the basis function width, and ||·|| is the norm; S33, substituting the weather at the corresponding time point in history into the constructed neural network prediction model for traffic congestion time under the influence of weather to output the traffic congestion time of each road section under the influence of the weather at the corresponding time point in history; The S4 comprises the following specific steps: S41, obtaining historical traffic flow information and traffic congestion conditions of each road section under historical traffic flow and dividing the data into two subsets, wherein the first 80% is a training data set and the second 20% is a test data set, inputting the first 80% of the training data set into the traffic congestion time neural network prediction model under the influence of traffic flow for training, and obtaining an initial traffic congestion time neural network prediction model under the influence of traffic flow, and then using the second 20% of the test data set to test the initial traffic congestion time neural network prediction model under the influence of traffic flow, and outputting a traffic congestion time neural network prediction model under the influence of traffic flow with the smallest judgment error for traffic congestion time, wherein the calculation formula for the traffic congestion time judgment error of the traffic congestion time neural network prediction model under the influence of traffic flow is: in, is the traffic congestion time output by the neural network model of the traffic congestion time in the jth area under the influence of traffic flow, y j is the traffic congestion time of the jth area under the influence of actual traffic flow, l is the number of congested areas for each road section; S42. The calculation formula of the neural network prediction model for traffic congestion time under the influence of the traffic flow is: Among them, m j is the connection weight between the neurons in the hidden layer and the output layer, m0 is the deviation, t j is the input data of the jth region, e2 is the center of the neuron basis function, σ2 is the basis function width, and ||·|| is the norm; S43, substituting the traffic volume at the corresponding time point in history into the constructed traffic congestion time neural network prediction model under the influence of traffic volume to output the traffic congestion time of each road section under the influence of the traffic volume at the corresponding time point in history; The S5 comprises the following specific steps: S51, substituting the outputted traffic congestion time of each road section under the influence of the weather at the corresponding time point in history and the traffic congestion time of each road section under the influence of the traffic volume at the corresponding time point in history into the traffic comprehensive congestion time calculation formula to calculate the traffic comprehensive congestion time of each road section, the traffic comprehensive congestion time calculation formula is: Among them, α1 is the coefficient of weather affecting traffic, α2 is the coefficient of traffic flow affecting traffic, α1>0, α2>0 and α1+α2=1; S52, based on the calculated comprehensive traffic congestion time of each road section, the estimated arrival time of the selected shuttle buses at the destination station, and assigning the dispatching task to the shuttle bus with the shortest arrival time at the destination station. After receiving the dispatching task, the shuttle bus will go to the destination station to pick up employees according to the on-board navigation.

2. A method for scheduling shuttle transport tasks based on cloud management as claimed in claim 1, characterized in that: The S1 comprises the following specific steps: Employee information includes employee name, boarding point, alighting point and shift information. Shuttle bus information includes the approved passenger capacity, real-time passenger capacity, real-time location and real-time speed of the shuttle bus. Employee information and shuttle bus information are extracted and stored in the information storage module to obtain the number of shuttle bus departures, departure time and route.

3. A method for scheduling shuttle transport tasks based on cloud management as claimed in claim 2, characterized in that: The S2 comprises the following specific steps: When an employee temporarily applies to take a shuttle bus, the message notification module publishes a temporary passenger-carrying task, obtains the employee's boarding and alighting points, and selects the buses that have routes that include the employee's boarding and alighting points and have vacancies from the dispatched buses.

4. A cloud-based shuttle transport task scheduling system, which is implemented based on the cloud-based shuttle transport task scheduling method according to any one of claims 1 to 3, characterized in that: It includes an information storage module, a message notification module, a weather impact module, a traffic flow impact module, a comprehensive traffic congestion calculation module and a control module. The information storage module is used to store employee information and shuttle bus information. The message notification module is used to issue temporary passenger-carrying tasks and allocate scheduling tasks. The weather impact module is used to input the weather at the corresponding historical time point into the constructed traffic congestion time neural network prediction model under the influence of weather, and output the traffic congestion time of each road section under the influence of the weather at the corresponding historical time point.

5. A cloud-based shuttle transport task scheduling system as claimed in claim 4, characterized in that: The vehicle flow impact module is used to input the vehicle flow at the corresponding historical time point into the constructed traffic congestion time neural network prediction model under the influence of vehicle flow, and output the traffic congestion time of each road section under the influence of vehicle flow at the corresponding historical time point. The comprehensive traffic congestion calculation module is used to calculate the comprehensive traffic congestion time of each road section according to the traffic congestion time of each road section under the influence of weather and the traffic congestion time of each road section under the influence of vehicle flow, and estimate the time when the selected shuttle bus arrives at the destination station. The control module is used to control the operation of the information storage module, the message notification module, the weather impact module, the vehicle flow impact module and the comprehensive traffic congestion calculation module.

6. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program that can be called by the processor, and the processor executes a cloud-management-based shuttle transport task scheduling method as described in any one of claims 1 to 3 by calling the computer program stored in the memory.

7. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute a cloud-management-based shuttle transportation task scheduling method as described in any one of claims 1-3.

Images