A method for evaluating coordination and scheduling of an intelligent patrol vehicle in an open road and a closed park

Abstract

The application relates to a method for evaluating coordination and scheduling of an intelligent patrol vehicle in an open road and a closed park, which comprises the following steps: R1. During the process of coordinating and executing tasks in an open road and a closed park, a patrol vehicle queue collects historical data information of the time spent by the patrol vehicle in completing tasks in the open road and the number of manual takeover times, collects historical data information of the time spent by the patrol vehicle in completing tasks in the closed park and the number of manual takeover times, and adopts a Fourier series fitting one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor to represent the probability distribution of the time spent by the patrol vehicle in completing tasks and the number of manual takeover times, so as to obtain data information of the probability distribution of the time spent by the patrol vehicle in completing tasks and the number of manual takeover times. The application can not only judge whether an existing vehicle scheduling scheme is efficient, so as to adjust the scheduling scheme in time, but also is favorable for real-time correction of the scheduling scheme, and guarantees work efficiency and vehicle energy efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent patrol vehicles, in particular to a public road and closed park coordination scheduling evaluation method of an intelligent patrol vehicle. BACKGROUND

[0002] Due to the acceleration of urbanization, a large number of people flow into the urban environment, so that the number of population and the number of vehicles in the city increase a lot, which also brings many related problems, so that the priority of maintaining urban public safety gradually increases, and the demand for upgrading of the security industry also begins to appear. In densely populated places such as residential communities, business districts and business office areas, various events occur frequently, and it is often necessary to deploy police personnel and equip patrol vehicles to facilitate patrol inspection and rapid response to emergency events. The robot with autonomous patrol (automatic driving) function to serve as an image acquisition device to combine information acquisition and analysis to complete the security patrol task is a more appropriate solution. The intelligent unmanned security patrol vehicle is one of such robots.

[0003] Therefore, the application scenarios of intelligent patrol vehicles can be roughly divided into two categories: one is a public road environment, mainly referring to a social public road connecting various communities. In this scenario, the intelligent patrol vehicle mainly implements the task of receiving a dispatch instruction and going to the destination community for patrol, and the vehicle itself mainly performs line tracking driving. The other is a closed park road environment (such as a park, a community, a scenic area, etc.). In this scenario, the intelligent patrol vehicle mainly implements specific patrol tasks, and the vehicle itself realizes regional coverage driving and functions such as line cycle driving.

[0004] Therefore, for the intelligent patrol vehicle scheduling scheme, the public road and community road scenarios cannot be considered separately, and both scenarios should be coordinated to ensure that the patrol business actions and vehicle driving actions remain continuous or timely, thereby maximizing the patrol vehicle operation efficiency and vehicle energy efficiency and solving the actual patrol vehicle operation economic efficiency and cost problems. SUMMARY

[0005] In view of the above problems, the present application provides a public road and closed park coordination scheduling evaluation method of an intelligent patrol vehicle, which can not only judge whether the existing vehicle scheduling scheme is efficient to adjust the scheduling scheme in time, but also is beneficial to real-time correction of the scheduling scheme to ensure the operation efficiency and vehicle energy efficiency.

[0006] In order to achieve the above object and other related objects, the technical scheme provided by the present application is as follows: a public road and closed park coordination scheduling evaluation method of an intelligent patrol vehicle, the method comprising:

[0007] R1. The patrol vehicle queue collects historical data information of the time taken by the patrol vehicle to complete the task on the open road and the number of manual takeovers, and collects historical data information of the time taken by the patrol vehicle to complete the task in the closed park during the coordinated execution of the task on the open road and in the closed park;

[0008] R2. Based on the historical data information of the time taken by the patrol vehicle to complete the task on the open road and the number of manual takeovers, and the historical data information of the time taken by the patrol vehicle to complete the task in the closed park, a one-dimensional probability distribution algorithm based on Fourier series fitting with adaptive feedback adjustment factor is used to characterize the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, to obtain data information of the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers;

[0009] R3. Based on the data information of the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, an improved gardener bird optimization algorithm based on adaptive weight is used to optimize the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, to obtain data information of the optimized probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers;

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

[0011] Further, the method further comprises:

[0012] R5. Based on the data information of the evaluation value of the coordination and scheduling of the patrol vehicle, a preset threshold is set, the threshold is adjusted according to the actual situation, if the evaluation value of the coordination and scheduling of the patrol vehicle is greater than the preset threshold, the coordination and scheduling is evaluated as good, if the evaluation value of the coordination and scheduling of the patrol vehicle is less than the preset threshold, the coordination and scheduling is evaluated as not meeting the requirements, a warning prompt is issued by the task management subsystem, and the scheduling scheme needs to be modified again.

[0013] Further, in step R2, the one-dimensional probability distribution algorithm based on Fourier series fitting with adaptive feedback adjustment factor is used to characterize the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, which comprises:

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

[0015]

[0016] wherein x1 is historical data information of time taken by the patrol vehicle to complete the task on the open road, x2 is historical data information of number of manual takeovers by the patrol vehicle to complete the task on the open road, a1, a2 and a3 are adaptive feedback adjustment factors of probability distribution of the patrol vehicle to complete the task on the open road, and the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task on the open road is characterized to obtain data information of the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task on the open road;

[0017] R22. establishing a probability distribution function W of the patrol vehicle in the closed park based on historical data information of time taken and number of manual takeovers by the patrol vehicle to complete the task in the closed park,

[0018] wherein y1 is historical data information of time taken by the patrol vehicle to complete the task in the closed park, y2 is historical data information of number of manual takeovers by the patrol vehicle to complete the task in the closed park, b1, b2 and b3 are weight factors of the patrol vehicle to complete the task in the closed park, and the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task in the closed park is characterized to obtain data information of the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task in the closed park;

[0019] R23. establishing a probability distribution fusion function U of the patrol vehicle to complete the task based on the data information of the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task on the open road, and the data information of the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task in the closed park,

[0020]

[0021] wherein x is data information of the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task on the open road, y is data information of the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task in the closed park, d1, d2 and d3 are fusion factors of the probability distribution of the patrol vehicle to complete the task, and the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task is characterized to obtain data information of the probability distribution of the time taken and the number of manual takeovers by the patrol vehicle to complete the task.

[0022] Further, the constraint conditions of the fusion factors d1, d2 and d3 of the probability distribution of the patrol vehicle to complete the task are,

[0023]

[0024] Further, the adaptive feedback adjustment factors a1, a2 and a3 of the probability distribution of the patrol vehicle completing the task on the public road are,

[0025]

[0026] wherein x1 is the historical data information of the time taken by the patrol vehicle to complete the task on the public road, and x2 is the historical data information of the number of manual takeovers of the patrol vehicle to complete the task on the public road.

[0027] Further, in step R3, the optimization of the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers by using the improved Finch optimization algorithm based on adaptive weight includes:

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

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

[0030]

[0031] wherein z is the data information of the initialized Finch population, and γ1, γ2 and γ3 are the fitness adjustment factors of the Finch population, which are used to calculate the fitness values of the individuals of the Finch population, and the data information of the fitness values of the individuals of the Finch population is obtained;

[0032] R33. Based on the data information of the fitness values of the individuals of the Finch population, the target optimization function G is established,

[0033]

[0034] wherein r is the data information of the fitness values of the individuals of the Finch population, and η1, η2 and η3 are the adaptive weight factors of the Finch population, which are used to optimize the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, and the data information of the optimized probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers is obtained.

[0035] Further, the adaptive weight factors η1, η2 and η3 of the Finch population are,

[0036] wherein r is the data information of the fitness values of the individuals of the Finch population.

[0037] Further, the coordination scheduling evaluation function F of the patrol vehicle is,

[0038]

[0039] H is the data information of the probability distribution of the time spent by the optimized patrol vehicle to complete the task and the number of manual takeovers, and λ1, λ2 and λ3 are evaluation factors of the patrol vehicle to complete the task.

[0040] In order to achieve the above-mentioned purpose and other related purposes, the present application also provides an open road and closed park coordination scheduling evaluation system of an intelligent patrol vehicle, comprising a computer device programmed or configured to perform the steps of any one of the intelligent patrol vehicle open road and closed park coordination scheduling evaluation methods.

[0041] In order to achieve the above-mentioned purpose and other related purposes, the present application also provides a computer readable storage medium having a computer program programmed or configured to perform any one of the intelligent patrol vehicle open road and closed park coordination scheduling evaluation methods stored thereon.

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

[0043] 1. The present application characterizes the probability distribution of the time spent by the patrol vehicle to complete the task and the number of manual takeovers by adopting the Fourier series fitting one-dimensional probability distribution algorithm based on adaptive feedback adjustment factors, and optimizes the probability distribution of the time spent by the patrol vehicle to complete the task and the number of manual takeovers by adopting the improved gardener bird optimization algorithm based on adaptive weights, which not only can judge whether the existing vehicle scheduling scheme is efficient, so as to adjust the scheduling scheme in time, but also is conducive to real-time correction of the scheduling scheme, ensuring the work efficiency and vehicle energy efficiency.

[0044] 2. The present application establishes a coordination scheduling evaluation function F of the patrol vehicle to evaluate the coordination scheduling of the patrol vehicle, not only designs a scientific and reasonable evaluation system scheme for the coordination scheduling problem of the two application scenarios of the intelligent patrol vehicle group, and designs a specific execution process according to the artificial prior experience, solves the problem of periodic evaluation of the scheduling scheme, but also is conducive to real-time correction of the scheduling scheme, ensuring the work efficiency and vehicle energy efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 It is a method flowchart of the present application;

[0046] Figure 2 It is a flowchart of the Fourier series fitting one-dimensional probability distribution algorithm based on adaptive feedback adjustment factors of the present application;

[0047] Figure 3 It is a flowchart of the improved gardener bird optimization algorithm based on adaptive weights of the present application. Detailed Implementation

[0048] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0049] Example 1: As Figure 1 As shown, a method for coordinating and scheduling intelligent patrol vehicles on public roads and in closed parks is described, the method comprising:

[0050] R1. During the coordinated execution of tasks on public roads and in closed areas, the patrol vehicle convoy collects historical data on the time spent by the patrol vehicles in completing tasks on public roads and the number of times manual intervention was required, as well as historical data on the time spent by the patrol vehicles in completing tasks in closed areas.

[0051] R2. Based on the historical data of the time spent by the patrol vehicle in completing the task on public roads and the number of times the patrol vehicle was manually intervened, and the historical data of the time spent by the patrol vehicle in completing the task in closed parks, a one-dimensional probability distribution algorithm based on adaptive feedback adjustment factor Fourier series fitting is used to characterize the probability distribution of the time spent by the patrol vehicle in completing the task and the number of times the patrol vehicle was manually intervened, so as to obtain the data information of the probability distribution of the time spent by the patrol vehicle in completing the task and the number of times the patrol vehicle was manually intervened.

[0052] R3. Based on the data information of the probability distribution of the time spent by the patrol vehicle to complete the task and the number of times manual intervention was performed, the improved gardener bird optimization algorithm based on adaptive weight was used to optimize the probability distribution of the time spent by the patrol vehicle to complete the task and the number of times manual intervention was performed, and the optimized data information of the probability distribution of the time spent by the patrol vehicle to complete the task and the number of times manual intervention was obtained.

[0053] R4. Based on the data information of the probability distribution of the time spent by the optimized patrol vehicle to complete the task and the number of times manual intervention was performed, a coordination and scheduling evaluation function F for the patrol vehicle was established to evaluate the coordination and scheduling of the patrol vehicle and obtain the data information of the evaluation value of the coordination and scheduling of the patrol vehicle.

[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 vehicle, a preset threshold is set, the threshold is adjusted according to the actual situation, if the evaluation value of the coordinated scheduling of the patrol vehicle is greater than the preset threshold, it is evaluated that the coordinated scheduling is good, if the evaluation value of the coordinated scheduling of the patrol vehicle is less than the preset threshold, it is evaluated that the coordinated scheduling does not meet the requirements, a warning prompt is issued by the task management subsystem, and the scheduling scheme needs to be modified again.

[0056] In the embodiment, as shown in FIG. 2, in step R2, the one-dimensional probability distribution algorithm based on adaptive feedback adjustment factor is used to characterize the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task, which includes: Figure 2

[0057] R21. Based on the historical data information of the time and the number of manual takeovers of the patrol vehicle completing the task on the public road, a probability distribution function Q of the patrol vehicle on the public road is established,

[0058]

[0059] wherein x1 is the historical data information of the time of the patrol vehicle completing the task on the public road, x2 is the historical data information of the number of manual takeovers of the patrol vehicle completing the task on the public road, α1, α2 and α3 are adaptive feedback adjustment factors of the probability distribution of the patrol vehicle completing the task on the public road, which characterize the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task on the public road, and data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task on the public road is obtained;

[0060] R22. Based on the historical data information of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park, a probability distribution function W of the patrol vehicle in the closed park is established,

[0061] wherein y1 is the historical data information of the time of the patrol vehicle completing the task in the closed park, y2 is the historical data information of the number of manual takeovers of the patrol vehicle completing the task in the closed park, β1, β2 and β3 are weight factors of the patrol vehicle completing the task in the closed park, which characterize the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park, and data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park is obtained;

[0062] R23. Based on the data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task on the public road, and the data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park, a probability distribution fusion function U of the patrol vehicle completing the task is established,​

[0063]

[0064] wherein x is data information of the probability distribution of the time taken by the patrol vehicle to complete the task on the open road and the number of times of manual takeover, y is data information of the probability distribution of the time taken by the patrol vehicle to complete the task in the closed park, δ1, δ2 and δ3 are fusion factors of the probability distribution of the patrol vehicle completing the task, and the probability distribution of the time taken by the patrol vehicle to complete the task and the number of times of manual takeover is characterized to obtain the data information of the probability distribution of the time taken by the patrol vehicle to complete the task and the number of times of manual takeover.

[0065] In the embodiment, the constraint condition of the fusion factors δ1, δ2 and δ3 of the probability distribution of the patrol vehicle completing the task is,

[0066]

[0067] In the embodiment, the adaptive feedback adjustment factors α1, α2 and α3 of the probability distribution of the patrol vehicle completing the task on the open road are,

[0068]

[0069] wherein x1 is historical data information of the time taken by the patrol vehicle to complete the task on the open road, and x2 is historical data information of the number of times of manual takeover of the patrol vehicle completing the task on the open road.

[0070] Embodiment 2: Based on the open road and closed park coordination scheduling evaluation method of the intelligent patrol vehicle in embodiment 1, the present application is further described and explained as follows.

[0071] As shown in Figure 1 Fig. 1, an open road and closed park coordination scheduling evaluation method of an intelligent patrol vehicle, the method comprising:

[0072] R1. In the process of the patrol vehicle queue coordinating to perform the task on the open road and in the closed park, historical data information of the time taken by the patrol vehicle to complete the task on the open road and the number of times of manual takeover is collected, and historical data information of the time taken by the patrol vehicle to complete the task in the closed park and the number of times of manual takeover is collected;

[0073] R2. based on the historical data information of the time taken by the patrol vehicle to complete a task on an open road and the number of manual takeovers, the historical data information of the time taken by the patrol vehicle to complete a task in a closed park, and using a one-dimensional probability distribution algorithm based on an adaptive feedback adjustment factor to fit a Fourier series to represent the probability distribution of the time taken by the patrol vehicle to complete a task and the number of manual takeovers, data information of the probability distribution of the time taken by the patrol vehicle to complete a 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 vehicle to complete a task and the number of manual takeovers, using an improved gardener bird optimization algorithm based on adaptive weight to optimize the probability distribution of the time taken by the patrol vehicle to complete a task and the number of manual takeovers, data information of the optimized probability distribution of the time taken by the patrol vehicle to complete a task and the number of manual takeovers is obtained;

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

[0076] In this embodiment, as shown in Figure 3 in step R3, the optimization of the probability distribution of the time taken by the patrol vehicle to complete a task and the number of manual takeovers using the improved gardener bird optimization algorithm based on adaptive weight includes:

[0077] R31. based on the data information of the probability distribution of the time taken by the patrol vehicle to complete a 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] wherein z is the data information of the initialized gardener bird population, γ1, γ2 and γ3 are the fitness adjustment factors of the gardener bird population, the fitness values of the individuals of the gardener bird population are calculated, and the data information of the fitness values of the individuals of the gardener bird population is obtained;

[0081] R33. based on the data information of the fitness values of the individuals of the gardener bird population, a target optimization function G is established,

[0082]

[0083] Wherein, r is the data information of fitness value of individual of the finch population, and η1, η2 and η3 are self-adaptive weight factors of the finch population, which optimize the probability distribution of time spent by the patrol vehicle to complete the task and the probability distribution of the number of manual takeovers, to obtain the data information of the optimized probability distribution of time spent by the patrol vehicle to complete the task and the number of manual takeovers.

[0084] Further, the self-adaptive weight factors η1, η2 and η3 of the finch population are,

[0085] Wherein, r is the data information of fitness value of individual of the finch population.

[0086] In the embodiment, the coordination and scheduling evaluation function F of the patrol vehicle is,

[0087]

[0088] H is the data information of the probability distribution of time spent by the patrol vehicle to complete the task and the number of manual takeovers, and λ1, λ2 and λ3 are evaluation factors of the patrol vehicle to complete the task.

[0089] In the embodiment, the present application provides a coordination and scheduling evaluation system for open roads and closed parks of an intelligent patrol vehicle, which comprises a computer device programmed or configured to perform the steps of any one of the coordination and scheduling evaluation methods for open roads and closed parks of the intelligent patrol vehicle.

[0090] In the embodiment, the present application provides a computer readable storage medium having stored thereon a computer program programmed or configured to perform the coordination and scheduling evaluation method for open roads and closed parks of the intelligent patrol vehicle.

[0091] Any reference to storage, memory, database or other medium herein can include non-volatile and / or volatile storage. Non-volatile storage can include read-only memory (ROM), programmable ROM (PROM), electronically programmable ROM (EPROM), or electrically erasable programmable ROM (EEPROM). Volatile storage can include random-access memory (RAM). By way of illustration, and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM). The RAM can also include a basic-oxide-of-silicon (BOS) memory.

[0092] In summary, the present application can not only judge whether the existing vehicle scheduling scheme is efficient, so as to adjust the scheduling scheme in time, but also is beneficial to real-time correction of the scheduling scheme, and ensures work efficiency and vehicle energy efficiency.

[0093] The foregoing detailed description has not been presented to limit the scope of the present disclosure. Various modifications and changes can be made to the embodiments described without departing from the spirit and scope of the disclosure. Any modifications, equivalent substitutions, improvements, and the like made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.

Claims

1. An intelligent patrol vehicle public road and closed park coordination scheduling evaluation method, characterized in that, The method comprises: R1. During the coordination of the patrol vehicle queue in the open road and the closed park to perform the task, historical data information of the time taken by the patrol vehicle to complete the task on the open road and the number of manual takeovers is collected, and historical data information of the time taken by the patrol vehicle to complete the task in the closed park and the number of manual takeovers is collected; R2. Based on the historical data information of the time taken by the patrol vehicle to complete the task on the open road and the number of manual takeovers, and the historical data information of the time taken by the patrol vehicle to complete the task in the closed park and the number of manual takeovers, a one-dimensional probability distribution algorithm based on Fourier series fitting is used to characterize the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, to obtain data information of the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers; R3. Based on the data information of the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, an improved gardener bird optimization algorithm based on adaptive weight is used to optimize the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, to obtain data information of the optimized probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers; R4. Based on the data information of the optimized probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, a coordination and scheduling evaluation function F of the patrol vehicle is established to evaluate the coordination and scheduling of the patrol vehicle, to obtain data information of the evaluation value of the coordination and scheduling of the patrol vehicle; In step R3, the improved gardener bird optimization algorithm based on adaptive weight is used to optimize the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, which comprises: R31. Based on the data information of the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers, the gardener bird population is initialized to determine the population parameters and the maximum number of iterations, to obtain data information of the initialized gardener bird population; R32. Based on the data information of the initialized gardener bird population, a fitness function S of the gardener bird population is established, ， wherein z is the data information of the initialized gardener bird population, γ1, γ2 and γ3 are the fitness adjustment factors of the gardener bird population, the fitness values of the individuals of the gardener bird population are calculated, and data information of the fitness values of the individuals of the gardener bird population is obtained; R33. Based on the data information of the fitness values of the individuals of the gardener bird population, a target optimization function G is established, ， wherein r is the data information of the fitness values of the individuals of the gardener bird population, η1, η2 and η3 are the adaptive weight factors of the gardener bird population, the probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers is optimized, and data information of the optimized probability distribution of the time taken by the patrol vehicle to complete the task and the number of manual takeovers is obtained.

2. The method of claim 1, wherein the method further comprises: The method further comprises: R5. Based on the data information of the evaluation value of the coordinated scheduling of the patrol vehicle, a preset threshold is set, the threshold is adjusted according to the actual situation, if the evaluation value of the coordinated scheduling of the patrol vehicle is greater than the preset threshold, the coordinated scheduling is evaluated as good, if the evaluation value of the coordinated scheduling of the patrol vehicle is less than the preset threshold, the coordinated scheduling is evaluated as not meeting the requirements, a warning prompt is issued by the task management subsystem, and the scheduling scheme needs to be modified again.

3. The method of claim 1, wherein the method further comprises: In step R2, the one-dimensional probability distribution algorithm based on the adaptive feedback adjustment factor is used to characterize the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task, which includes: R21. Based on the historical data information of the time and the number of manual takeovers of the patrol vehicle completing the task on the open road, a probability distribution function Q of the patrol vehicle on the open road is established, ， Wherein, x1 is the historical data information of the time of the patrol vehicle completing the task on the open road, x2 is the historical data information of the number of manual takeovers of the patrol vehicle completing the task on the open road, α1, α2 and α3 are adaptive feedback adjustment factors of the probability distribution of the patrol vehicle completing the task on the open road, which characterize the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task on the open road, and data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task on the open road is obtained; R22. Based on the historical data information of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park, a probability distribution function W of the patrol vehicle in the closed park is established, ， Wherein, y1 is the historical data information of the time of the patrol vehicle completing the task in the closed park, y2 is the historical data information of the number of manual takeovers of the patrol vehicle completing the task in the closed park, β1, β2 and β3 are weight factors of the patrol vehicle completing the task in the closed park, which characterize the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park, and data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park is obtained; R23. Based on the data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task on the open road, the data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park, a probability distribution fusion function U of the patrol vehicle completing the task is established, ， Wherein, x is the data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task on the open road, y is the data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task in the closed park, δ1, δ2 and δ3 are fusion factors of the probability distribution of the patrol vehicle completing the task, which characterize the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task, and data information of the probability distribution of the time and the number of manual takeovers of the patrol vehicle completing the task is obtained.

4. The method of claim 3, wherein the method further comprises: determining a number of the intelligent patrol vehicles in the open road and the closed park; and determining a number of the intelligent patrol vehicles in the open road and the closed park based on the number of the intelligent patrol vehicles in the open road and the closed park. The constraint conditions of the fusion factors δ1, δ2 and δ3 of the probability distribution of the patrol vehicle completing the task are, 。 5. The method of claim 3, wherein the method further comprises: determining a number of the intelligent patrol vehicles in the open road and the closed park; and determining a number of the intelligent patrol vehicles in the open road and the closed park based on the number of the intelligent patrol vehicles in the open road and the closed park. Adaptive feedback adjustment factors of the probability distribution of the patrol vehicle completing the task on the open road are α1, α2 and α3, ， ， ， Wherein, x1 is the historical data information of the time spent by the patrol vehicle in completing the task on the open road, and x2 is the historical data information of the number of manual takeovers of the patrol vehicle in completing the task on the open road.

6. The method of claim 1, wherein the method further comprises: Adaptive weight factors of the population of the mynah bird are η1, η2 and η3, ， ， ， Wherein, r is the data information of the fitness value of the individual of the population of the mynah bird.

7. The method of claim 1, wherein the method further comprises: The coordination scheduling evaluation function F of the patrol vehicle is ， h is the data information of the probability distribution of the time spent by the patrol vehicle in completing the task and the number of manual takeovers, and λ1, λ2 and λ3 are the evaluation factors of the patrol vehicle in completing the task.

8. An open road and closed park coordination scheduling evaluation system for an intelligent patrol vehicle, comprising a computer device, characterized in that, The computer device is programmed or configured to perform the steps of the coordination scheduling evaluation method of the open road and the closed park of the intelligent patrol vehicle according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program programmed or configured to perform the coordination scheduling evaluation method of the open road and the closed park of the intelligent patrol vehicle according to any one of claims 1-7.

Images