Open road and closed park coordinated scheduling evaluation method for intelligent patrol car

Abstract

The invention relates to an open road and closed park coordinated scheduling evaluation method for an intelligent patrol car, and the method comprises the steps: R1, collecting the time consumed by the patrol car to complete a task on an open road and the historical data information of the number of manual takeover times in a process that a patrol car queue carries out the task on the open road and closed park in a coordinated manner, historical data information of time and manual takeover times for the patrol car to complete the task in the closed park is collected, and probability distribution of the time and the manual takeover times for the patrol car to complete the task is represented by adopting a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback regulation factor; and the data information of the probability distribution of the time spent by the patrol car to complete the task and the manual takeover frequency is obtained. Whether the existing vehicle scheduling scheme is efficient or not can be judged so that the scheduling scheme can be adjusted timely, the scheduling scheme can be corrected in real time, and the operation efficiency and the vehicle energy efficiency can be guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent patrol vehicles, and in particular to a method for evaluating coordinated dispatching of an open road and a closed park of an intelligent patrol vehicle. Background Art

[0002] Due to the accelerated urbanization process, a large number of people have poured into the urban environment, resulting in a large increase in the number of people and vehicles in the city, which has also brought about many related problems, making the priority of maintaining urban public security gradually increase, and the demand for upgrading the security industry has also begun to emerge. In densely populated areas such as residential communities, commercial areas, and business office areas, various incidents occur frequently, and it is often necessary to deploy police officers and patrol cars to facilitate patrol inspections and rapid response to emergency events. It is a more appropriate solution for robots with autonomous patrol (automatic driving) functions to act as image acquisition devices, thereby combining information collection and analysis to complete the task of security patrol. Intelligent unmanned security patrol cars are one of such robots.

[0003] Therefore, the application scenarios of smart patrol cars can be roughly divided into two categories: one is the public road environment, which mainly refers to the public roads connecting various communities. In this type of scenario, the smart patrol car mainly receives dispatch instructions and goes to the destination community to perform patrol tasks. The vehicle itself mainly performs route tracking. The other is the closed park road environment (such as parks, communities, scenic spots, etc.). In this type of scenario, the smart patrol car mainly implements specific patrol tasks. The vehicle itself realizes regional coverage driving and line circulation driving and other functions.

[0004] Therefore, for the intelligent patrol car dispatching solutions in public road and community road scenarios, the two cannot be considered separately, but should be coordinated in an overall manner so that both scenarios, whether patrol business actions or vehicle driving actions, maintain continuity or timeliness, thereby maximizing the patrol car operating efficiency and vehicle energy efficiency, and solving the actual patrol car operation economic efficiency and cost issues. Summary of the invention

[0005] In view of the above problems, the present invention provides a method for evaluating the coordinated scheduling of open roads and closed parks for intelligent patrol vehicles, which can not only judge whether the existing vehicle scheduling plan is efficient so as to adjust the scheduling plan in time, but also facilitate real-time correction of the scheduling plan to ensure operational efficiency and vehicle energy efficiency.

[0006] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: a method for evaluating the coordinated dispatch of open roads and closed parks for intelligent patrol vehicles, the method comprising:

[0007] R1. When patrol cars are coordinating to perform tasks on public roads and closed parks, historical data information on the time it takes for patrol cars to complete tasks on public roads and the number of manual takeovers is collected, and historical data information on the time it takes for patrol cars to complete tasks on closed parks and the number of manual takeovers is collected;

[0008] R2. Based on the historical data information of the time taken by the patrol car to complete the task on the public road and the number of manual takeovers, and the historical data information of the time taken by the patrol car to complete the task in the closed park and the number of manual takeovers, the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is characterized by using a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor, and the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is obtained;

[0009] R3. Based on the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, the improved bowerbird optimization algorithm based on adaptive weights is used to optimize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, and the optimized data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is obtained;

[0010] R4. Based on the data information of the probability distribution of the time taken by the optimized patrol car to complete the task and the number of manual takeovers, a patrol car coordination scheduling evaluation function F is established to evaluate the patrol car coordination scheduling and obtain data information of the evaluation value of the patrol car coordination scheduling.

[0011] Furthermore, the method further comprises:

[0012] R5. Based on the data information of the evaluation value of the coordinated scheduling of the patrol car, a preset threshold is set, and the threshold is adjusted according to the actual situation. If the evaluation value of the coordinated scheduling of the patrol car is greater than the preset threshold, the coordinated scheduling is evaluated to be good. If the evaluation value of the coordinated scheduling of the patrol car is less than the preset threshold, the coordinated scheduling does not meet the requirements, and the task management subsystem issues an early warning prompt, and the scheduling plan needs to be modified.

[0013] Further, in step R2, the use of a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor to characterize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers includes:

[0014] R21. Based on the historical data information of the time it takes for the patrol car to complete the task on the open road and the number of manual takeovers, a probability distribution function Q of the patrol car on the open road is established.

[0015]

[0016] Among them, x 1 is the historical data information of the time it takes for patrol cars to complete tasks on public roads, x 2 is the historical data information of the number of manual takeovers of patrol vehicles on public roads, α 1 , α 2 and α 3 The adaptive feedback adjustment factor is the probability distribution of the patrol car completing the task on the public road, and the probability distribution of the time it takes for the patrol car to complete the task on the public road and the number of manual takeovers is characterized, and the data information of the probability distribution of the time it takes for the patrol car to complete the task on the public road and the number of manual takeovers is obtained;

[0017] R22. Based on the historical data information of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers, a probability distribution function W of the patrol car in the closed park is established.

[0018] Among them, y 1 is the historical data information of the time it takes for patrol cars to complete tasks in a closed park, y 2 is the historical data information of the number of manual takeovers of patrol vehicles in closed parks, 1 , β 2 and β 3 is the weight factor for the patrol car to complete the task in the closed park, and the probability distribution of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers is characterized, and the data information of the probability distribution of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers is obtained;

[0019] R23. Based on the data information of the probability distribution of the time it takes for the patrol car to complete the task on the open road and the number of manual takeovers, and the data information of the probability distribution of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers, a probability distribution fusion function U for the patrol car to complete the task is established.

[0020]

[0021] Among them, x is the data information of the probability distribution of the time it takes for a patrol car to complete a task on an open road and the number of manual takeovers, y is the data information of the probability distribution of the time it takes for a patrol car to complete a task in a closed park and the number of manual takeovers, δ 1 , δ 2 and δ 3The fusion factor of the probability distribution of the patrol car completing the task is used to characterize the probability distribution of the time it takes for the patrol car to complete the task and the number of manual takeovers, and the data information of the probability distribution of the time it takes for the patrol car to complete the task and the number of manual takeovers is obtained.

[0022] Furthermore, the fusion factor δ of the probability distribution of the patrol car completing the task 1 ,δ 2 and δ 3 The constraints are:

[0023]

[0024] Furthermore, the adaptive feedback adjustment factor α of the probability distribution of the patrol car completing the task on the open road is 1 , α 2 and α 3 for,

[0025]

[0026] Among them, x 1 is the historical data information of the time it takes for patrol cars to complete tasks on public roads, x 2 It is historical data information on the number of manual takeovers of patrol vehicles when completing tasks on public roads.

[0027] Furthermore, in step R3, the optimization of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers using the improved adaptive weight-based bowerbird optimization algorithm includes:

[0028] R31. Based on the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, the gardener bird population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized gardener bird population is obtained;

[0029] R32. Based on the data information of the initialized gardener bird population, a fitness function S of the gardener bird population is established.

[0030]

[0031] Among them, z is the data information of the initialized gardener bird population, γ 1 , γ 2 and γ 3 is the fitness adjustment factor of the bowerbird population, and the fitness values ​​of the individuals in the bowerbird population are estimated to obtain the data information of the fitness values ​​of the individuals in the bowerbird population;

[0032] R33. Based on the data information of the fitness value of the individual gardener bird population, establish the target optimization function G,

[0033]

[0034] Among them, r is the data information of the fitness value of the individual bowerbird population, η 1 , η 2 and η 3 The adaptive weight factor of the bowerbird population is used to optimize the probability distribution of the time it takes for a patrol car to complete a task and the number of times manual takeover is performed, and the data information of the probability distribution of the time it takes for a patrol car to complete a task and the number of times manual takeover is obtained.

[0035] Furthermore, the adaptive weight factor η of the bowerbird population is 1 , η 2 and η 3 for,

[0036] Among them, r is the data information of the fitness value of the individual bowerbird population.

[0037] Furthermore, the patrol car coordination dispatch evaluation function F is:

[0038]

[0039] H is the data information of the probability distribution of the time it takes for the patrol car to complete the task and the number of manual takeovers after optimization, λ 1 , 2 and λ 3 Evaluation factor for patrol car to complete the task.

[0040] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a system for evaluating the coordinated dispatching of open roads and closed parks for intelligent patrol vehicles, including a computer device, which is programmed or configured to execute the steps of any one of the methods for evaluating the coordinated dispatching of open roads and closed parks for intelligent patrol vehicles.

[0041] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the methods for evaluating the coordinated scheduling of open roads and closed parks for intelligent patrol vehicles.

[0042] The present invention has the following positive effects:

[0043] 1. The present invention adopts a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor to characterize the probability distribution of the time taken by a patrol car to complete a task and the number of manual takeovers, and combines the improved bowerbird optimization algorithm based on adaptive weights to optimize the probability distribution of the time taken by a patrol car to complete a task and the number of manual takeovers. This can not only judge whether the existing vehicle scheduling plan is efficient so as to adjust the scheduling plan in a timely manner, but also facilitate real-time correction of the scheduling plan to ensure operational efficiency and vehicle energy efficiency.

[0044] 2. The present invention evaluates the coordinated scheduling of patrol cars by establishing a coordinated scheduling evaluation function F for patrol cars. It not only designs a scientific and reasonable evaluation system solution for the coordinated scheduling problems in two application scenarios of intelligent patrol car groups, but also designs a specific execution process based on artificial prior experience, which solves the problem of periodic evaluation of scheduling solutions and is conducive to real-time correction of scheduling solutions to ensure operational efficiency and vehicle energy efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0046] Figure 2 It is a flow chart of the algorithm for fitting one-dimensional probability distribution by Fourier series based on adaptive feedback adjustment factor of the present invention;

[0047] Figure 3 The figure is a flow chart of the improved bowerbird optimization algorithm based on adaptive weights of the present invention. DETAILED DESCRIPTION

[0048] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0049] Example 1: Figure 1 As shown, a method for evaluating coordinated dispatching of an open road and a closed park for an intelligent patrol car comprises:

[0050] R1. When patrol cars are coordinating to perform tasks on public roads and closed parks, historical data information on the time it takes for patrol cars to complete tasks on public roads and the number of manual takeovers is collected, and historical data information on the time it takes for patrol cars to complete tasks on closed parks and the number of manual takeovers is collected;

[0051] R2. Based on the historical data information of the time taken by the patrol car to complete the task on the public road and the number of manual takeovers, and the historical data information of the time taken by the patrol car to complete the task in the closed park and the number of manual takeovers, the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is characterized by using a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor, and the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is obtained;

[0052] R3. Based on the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, the improved bowerbird optimization algorithm based on adaptive weights is used to optimize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, and the optimized data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is obtained;

[0053] R4. Based on the data information of the probability distribution of the time taken by the optimized patrol car to complete the task and the number of manual takeovers, a patrol car coordination scheduling evaluation function F is established to evaluate the patrol car coordination scheduling and obtain data information of the evaluation value of the patrol car coordination scheduling.

[0054] In this embodiment, the method further includes:

[0055] R5. Based on the data information of the evaluation value of the coordinated scheduling of the patrol car, a preset threshold is set, and the threshold is adjusted according to the actual situation. If the evaluation value of the coordinated scheduling of the patrol car is greater than the preset threshold, the coordinated scheduling is evaluated to be good. If the evaluation value of the coordinated scheduling of the patrol car is less than the preset threshold, the coordinated scheduling does not meet the requirements, and the task management subsystem issues an early warning prompt, and the scheduling plan needs to be modified.

[0056] In this embodiment, if Figure 2 As shown, in step R2, the method of using a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor to characterize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers includes:

[0057] R21. Based on the historical data information of the time it takes for the patrol car to complete the task on the open road and the number of manual takeovers, a probability distribution function Q of the patrol car on the open road is established.

[0058]

[0059] Among them, x 1 is the historical data information of the time it takes for patrol cars to complete tasks on public roads, x 2 is the historical data information of the number of manual takeovers of patrol vehicles on public roads, α1 , α 2 and α 3 The adaptive feedback adjustment factor is the probability distribution of the patrol car completing the task on the public road, and the probability distribution of the time it takes for the patrol car to complete the task on the public road and the number of manual takeovers is characterized, and the data information of the probability distribution of the time it takes for the patrol car to complete the task on the public road and the number of manual takeovers is obtained;

[0060] R22. Based on the historical data information of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers, a probability distribution function W of the patrol car in the closed park is established.

[0061] Among them, y 1 is the historical data information of the time it takes for patrol cars to complete tasks in a closed park, y 2 is the historical data information of the number of manual takeovers of patrol vehicles in closed parks, 1 , β 2 and β 3 is the weight factor for the patrol car to complete the task in the closed park, and the probability distribution of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers is characterized, and the data information of the probability distribution of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers is obtained;

[0062] R23. Based on the data information of the probability distribution of the time it takes for the patrol car to complete the task on the open road and the number of manual takeovers, and the data information of the probability distribution of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers, a probability distribution fusion function U for the patrol car to complete the task is established.

[0063]

[0064] Among them, x is the data information of the probability distribution of the time it takes for a patrol car to complete a task on an open road and the number of manual takeovers, y is the data information of the probability distribution of the time it takes for a patrol car to complete a task in a closed park and the number of manual takeovers, δ 1 , δ 2 and δ 3 The fusion factor of the probability distribution of the patrol car completing the task is used to characterize the probability distribution of the time it takes for the patrol car to complete the task and the number of manual takeovers, and the data information of the probability distribution of the time it takes for the patrol car to complete the task and the number of manual takeovers is obtained.

[0065] In this embodiment, the fusion factor δ of the probability distribution of the patrol car completing the task 1 , δ 2 and δ 3The constraints are:

[0066]

[0067] In this embodiment, the adaptive feedback adjustment factor α of the probability distribution of the patrol car completing the task on the public road is 1 , α 2 and α 3 for,

[0068]

[0069] Among them, x 1 is the historical data information of the time it takes for patrol cars to complete tasks on public roads, x 2 It is historical data information on the number of manual takeovers of patrol vehicles when completing tasks on public roads.

[0070] Example 2: Based on the evaluation method for coordinated dispatching of an open road and a closed park for an intelligent patrol car in Example 1, the present invention is further illustrated and described below.

[0071] like Figure 1 As shown, a method for evaluating coordinated dispatching of an open road and a closed park for an intelligent patrol car comprises:

[0072] R1. When patrol cars are coordinating to perform tasks on public roads and closed parks, historical data information on the time it takes for patrol cars to complete tasks on public roads and the number of manual takeovers is collected, and historical data information on the time it takes for patrol cars to complete tasks on closed parks and the number of manual takeovers is collected;

[0073] R2. Based on the historical data information of the time taken by the patrol car to complete the task on the public road and the number of manual takeovers, and the historical data information of the time taken by the patrol car to complete the task in the closed park and the number of manual takeovers, the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is characterized by using a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor, and the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is obtained;

[0074] R3. Based on the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, the improved bowerbird optimization algorithm based on adaptive weights is used to optimize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, and the optimized data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is obtained;

[0075] R4. Based on the data information of the probability distribution of the time taken by the optimized patrol car to complete the task and the number of manual takeovers, a patrol car coordination scheduling evaluation function F is established to evaluate the patrol car coordination scheduling and obtain data information of the evaluation value of the patrol car coordination scheduling.

[0076] In this embodiment, if Figure 3 As shown, in step R3, the use of the improved adaptive weight-based bowerbird optimization algorithm to optimize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers includes:

[0077] R31. Based on the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, the gardener bird population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized gardener bird population is obtained;

[0078] R32. Based on the data information of the initialized gardener bird population, a fitness function S of the gardener bird population is established.

[0079]

[0080] Among them, z is the data information of the initialized gardener bird population, γ 1 , γ 2 and γ 3 is the fitness adjustment factor of the bowerbird population, and the fitness values ​​of the individuals in the bowerbird population are estimated to obtain the data information of the fitness values ​​of the individuals in the bowerbird population;

[0081] R33. Based on the data information of the fitness value of the individual gardener bird population, establish the target optimization function G,

[0082]

[0083] Among them, r is the data information of the fitness value of the individual bowerbird population, η 1 , η 2 and η 3 The adaptive weight factor of the bowerbird population is used to optimize the probability distribution of the time it takes for a patrol car to complete a task and the number of times manual takeover is performed, and the data information of the probability distribution of the time it takes for a patrol car to complete a task and the number of times manual takeover is obtained.

[0084] Furthermore, the adaptive weight factor η of the bowerbird population is 1 , η 2 and η 3 for,

[0085] Among them, r is the data information of the fitness value of the individual bowerbird population.

[0086] In this embodiment, the patrol car coordination dispatch evaluation function F is:

[0087]

[0088] H is the data information of the probability distribution of the time it takes for the patrol car to complete the task and the number of manual takeovers after optimization, λ 1 , 2 and λ 3 Evaluation factor for patrol car to complete the task.

[0089] In this embodiment, the present invention provides a system for evaluating the coordinated dispatching of open roads and closed parks for intelligent patrol vehicles, including a computer device that is programmed or configured to execute the steps of any one of the methods for evaluating the coordinated dispatching of open roads and closed parks for intelligent patrol vehicles.

[0090] In this embodiment, the present invention provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the methods for evaluating coordinated scheduling of open roads and closed parks for smart patrol vehicles.

[0091] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0092] In summary, the present invention can not only judge whether the existing vehicle dispatching scheme is efficient so as to adjust the dispatching scheme in time, but also facilitate to correct the dispatching scheme in real time to ensure the operation efficiency and vehicle energy efficiency.

[0093] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for evaluating coordinated dispatching of open roads and closed parks for intelligent patrol vehicles, characterized in that: The method comprises: R1. When patrol cars are coordinating to perform tasks on public roads and closed parks, historical data information on the time it takes for patrol cars to complete tasks on public roads and the number of manual takeovers is collected, and historical data information on the time it takes for patrol cars to complete tasks on closed parks and the number of manual takeovers is collected; R2. Based on the historical data information of the time taken by the patrol car to complete the task on the public road and the number of manual takeovers, and the historical data information of the time taken by the patrol car to complete the task in the closed park and the number of manual takeovers, the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is characterized by using a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor, and the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is obtained; R3. Based on the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, the improved bowerbird optimization algorithm based on adaptive weights is used to optimize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, and the optimized data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is obtained; R4. Based on the data information of the probability distribution of the time taken by the optimized patrol car to complete the task and the number of manual takeovers, a patrol car coordination scheduling evaluation function F is established to evaluate the patrol car coordination scheduling and obtain data information of the evaluation value of the patrol car coordination scheduling.

2. The method for evaluating coordinated dispatching of open roads and closed parks for intelligent patrol vehicles according to claim 1 is characterized in that: The method further comprises: R5. Based on the data information of the evaluation value of the coordinated scheduling of the patrol car, a preset threshold is set, and the threshold is adjusted according to the actual situation. If the evaluation value of the coordinated scheduling of the patrol car is greater than the preset threshold, the coordinated scheduling is evaluated to be good. If the evaluation value of the coordinated scheduling of the patrol car is less than the preset threshold, the coordinated scheduling does not meet the requirements, and the task management subsystem issues an early warning prompt, and the scheduling plan needs to be modified.

3. The method for evaluating coordinated dispatching of open roads and closed parks for intelligent patrol vehicles according to claim 1 is characterized in that: In step R2, the method of using a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor to characterize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers includes: R21. Based on the historical data information of the time it takes for the patrol car to complete the task on the open road and the number of manual takeovers, a probability distribution function Q of the patrol car on the open road is established. Among them, x1 is the historical data information of the time it takes for patrol cars to complete tasks on public roads, x2 is the historical data information of the number of manual takeovers for patrol cars to complete tasks on public roads, α1, α2 and α3 are adaptive feedback adjustment factors of the probability distribution of patrol cars completing tasks on public roads, which characterize the probability distribution of the time it takes for patrol cars to complete tasks on public roads and the number of manual takeovers, and obtain the data information of the probability distribution of the time it takes for patrol cars to complete tasks on public roads and the number of manual takeovers; R22. Based on the historical data information of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers, a probability distribution function W of the patrol car in the closed park is established. Among them, y1 is the historical data information of the time it takes for patrol cars to complete tasks in closed parks, y2 is the historical data information of the number of manual takeovers for patrol cars to complete tasks in closed parks, β1, β2 and β3 are weight factors for patrol cars to complete tasks in closed parks, and the probability distribution of the time it takes for patrol cars to complete tasks in closed parks and the number of manual takeovers is characterized to obtain the data information of the probability distribution of the time it takes for patrol cars to complete tasks in closed parks and the number of manual takeovers; R23. Based on the data information of the probability distribution of the time it takes for the patrol car to complete the task on the open road and the number of manual takeovers, and the data information of the probability distribution of the time it takes for the patrol car to complete the task in the closed park and the number of manual takeovers, a probability distribution fusion function U for the patrol car to complete the task is established. Among them, x is the data information of the probability distribution of the time it takes for a patrol car to complete a task on an open road and the number of manual takeovers, y is the data information of the probability distribution of the time it takes for a patrol car to complete a task in a closed park and the number of manual takeovers, δ1, δ2 and δ3 are the fusion factors of the probability distribution of the patrol car completing the task, which characterize the probability distribution of the time it takes for a patrol car to complete the task and the number of manual takeovers, and obtain the data information of the probability distribution of the time it takes for a patrol car to complete the task and the number of manual takeovers.

4. The method for evaluating coordinated dispatching of open roads and closed parks for intelligent patrol vehicles according to claim 3 is characterized in that: The constraints of the fusion factors δ1, δ2 and δ3 of the probability distribution of the patrol car completing the task are:

5. The method for evaluating coordinated dispatching of open roads and closed parks for intelligent patrol vehicles according to claim 3 is characterized in that: The adaptive feedback adjustment factors α1, α2 and α3 of the probability distribution of the patrol car completing the task on the open road are, Among them, x1 is the historical data information of the time it takes for the patrol car to complete the task on the public road, and x2 is the historical data information of the number of manual takeovers when the patrol car completes the task on the public road.

6. The method for evaluating coordinated dispatching of open roads and closed parks for intelligent patrol vehicles according to claim 1 is characterized in that: In step R3, the use of the improved adaptive weight-based bowerbird optimization algorithm to optimize the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers includes: R31. Based on the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers, the gardener bird population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized gardener bird population is obtained; R32. Based on the data information of the initialized gardener bird population, a fitness function S of the gardener bird population is established. Among them, z is the data information of the initialized bowerbird population, γ1, γ2 and γ3 are the fitness adjustment factors of the bowerbird population, and the fitness values ​​of the individuals in the bowerbird population are calculated to obtain the data information of the fitness values ​​of the individuals in the bowerbird population; R33. Based on the data information of the fitness value of the individual gardener bird population, establish the target optimization function G, Among them, r is the data information of the fitness value of the individual of the bowerbird population, η1, η2 and η3 are the adaptive weight factors of the bowerbird population, and the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers is optimized to obtain the data information of the probability distribution of the time taken by the patrol car to complete the task and the number of manual takeovers after optimization.

7. The method for evaluating coordinated dispatching of open roads and closed parks for intelligent patrol vehicles according to claim 6 is characterized in that: The adaptive weight factors η1, η2 and η3 of the bowerbird population are: Among them, r is the data information of the fitness value of the individual bowerbird population.

8. The method for evaluating coordinated dispatching of open roads and closed parks for intelligent patrol vehicles according to claim 1 is characterized in that: The patrol car coordination dispatch evaluation function F is: H is the data information of the probability distribution of the time taken by the optimized patrol car to complete the task and the number of manual takeovers, and λ1, λ2 and λ3 are the evaluation factors for the patrol car to complete the task.

9. A coordinated dispatching and evaluation system for open roads and closed parks of intelligent patrol vehicles, including computer equipment, characterized in that: The computer device is programmed or configured to execute the steps of the method for evaluating coordinated scheduling of public roads and closed parks for intelligent patrol vehicles as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the method for evaluating coordinated scheduling of open roads and closed parks for intelligent patrol vehicles as described in any one of claims 1 to 8.

Images