Park safety inspection method based on multiple weight ratios

Abstract

The invention discloses a park safety inspection method based on multiple weight ratios, and the method comprises the following steps: S1, carrying out the period optimization according to an inspection period automatic adjustment algorithm, so as to enable the previous q * v times of inspection to meet a period adjustment condition; s2, updating the inspection period of the inspection point; s3, updating a routing inspection point list of the routing inspection task, wherein the routing inspection point list comprises a routing inspection point importance level coefficient, a routing inspection point alarm weight and a routing inspection point period weight; s4, calculating the comprehensive inspection weight of the inspection point based on the importance level coefficient of the inspection point, the alarm weight of the inspection point and the periodic weight of the inspection point; and S5, calculating an inspection execution route which highlights the inspection priority according to the comprehensive inspection weight of the inspection points. The inspection efficiency and the coping capacity of the smart park can be remarkably improved, potential risks are reduced, and resources are effectively saved.

Description

Technical Field

[0001] The present invention relates to the field of park inspection technology, and in particular to a park safety inspection method based on multiple weight ratios. Background Art

[0002] The current inspection strategy of the park is to formulate inspection tasks and plan specific inspection points in the inspection tasks to generate inspection routes. The inspection routes are usually manually specified, or a single inspection route is generated by the minimum path algorithm. The inspection tasks are fixed and cannot cover the inspection points that need to be inspected in time. There is no function to automatically correct the relevant inspection points in the inspection tasks;

[0003] The inspection route (sequence) planning was too simple, and it was impossible to adjust the inspection priority for inspection points where problems frequently occurred; it was not combined with the operating data of the park monitoring system, and there was no channel for multi-system collaboration.

[0004] The following problems exist in the simple traversal inspection strategy that only relies on inspection points: (1) Waste of resources: Time and cost: Inspectors may spend too much time on points that do not need to be checked frequently, and not enough time on points of higher importance, thus wasting resources. Low inspection efficiency: Failure to consider the importance and status of the inspection points may lead to low inspection efficiency.

[0005] (1)Unclear priorities: Ignoring important points: Important inspection points (such as potential safety hazards or key facilities) may not be inspected first, increasing potential risks. Indiscriminate inspection: All inspection points are treated equally, and the inspection frequency cannot be adjusted according to actual conditions.

[0006] (2) Poor ability to deal with unexpected problems: Lack of dynamic adjustment. When encountering new problems or emergencies, the existing inspection mode cannot quickly adjust the inspection strategy to cope with these changes. It is not adaptable to environmental changes and has no dynamic response mechanism for changes in environmental conditions (such as equipment aging, environmental changes).

[0007] (3) Insufficient data utilization: Historical data is not fully utilized. The current inspection model does not fully utilize historical inspection data, resulting in the inability to optimize inspection strategies based on actual conditions. Monitoring data is not integrated, and the data from the park monitoring system is not effectively combined with the inspection plan, which reduces the accuracy and timeliness of inspections. Summary of the invention

[0008] The purpose of the present invention is to provide a park security inspection method based on multiple weight ratios to solve the technical problem of how to improve the inspection efficiency and response capability of smart parks.

[0009] The object of the present invention is to adopt the following technical solution to achieve: a park safety inspection method based on multiple weight ratios, comprising the following steps: S1: Optimize the cycle according to the inspection cycle automatic adjustment algorithm so that the first q*v inspections meet the cycle adjustment conditions; S2: Update the inspection cycle of the inspection point; S3: Update the inspection point list of the inspection task, wherein the inspection point list includes inspection point importance level coefficients, inspection point alarm weights, and inspection point cycle weights; S4: Calculate the comprehensive inspection weight of the inspection point based on the inspection point importance level coefficient, inspection point alarm weight and inspection point cycle weight; S5: Calculate the inspection execution route with prominent inspection priority according to the comprehensive inspection weights of the inspection points.

[0010] Furthermore, step S1 includes the following sub-steps: S11: Refer to historical inspection data and accumulate q disks, with v consecutive and identical inspection tasks for each disk. Each inspection task has n inspection points, each of which needs to be inspected once; S12: Collect statistics on inspection points where abnormalities occur in each inspection task, and shorten the inspection cycle of the inspection point.

[0011] Furthermore, step S2 is specifically as follows: updating the inspection periods of the inspection points to P1, P2, P3, ..., Pi, wherein the inspection period of P1 is the shortest and the inspection period of Pi is the longest.

[0012] Furthermore, step S3 includes the following sub-steps: S31: Update the inspection point period weight value: When the inspection cycle of the inspection point is shortened, the weight of the inspection point is modified to W+d; when the inspection cycle of the inspection point is restored, the weight of the inspection point is modified to Wd; where W is the initial weight of the inspection point cycle, and d is the weight change adjustment amount; S32: Update the alarm weight of the inspection point: W alarm = L1C1 + L2C2 + L3C3; where L1, L2, L3 are alarm levels; C1, C2, C3 are the alarm numbers corresponding to L1, L2, L3; S33: Update the inspection point importance level coefficients I1, I2, and I3, among which I1 is the lowest and I3 is the highest.

[0013] Furthermore, step S4 is specifically as follows: If the current task has n inspection points, the cycle weights of the inspection points are arrive ; The alarm weights of the inspection points are arrive ; The inspection point importance level coefficient is I; then the calculation method of the inspection point comprehensive inspection weight is: = + ).

[0014] Furthermore, step S5 is specifically as follows: S51: Compare the comprehensive inspection weight of the inspection point with the independent inspection threshold. If the independent inspection threshold is exceeded, the inspection has absolute inspection priority authority. S52: determining the inspection order of the inspection points according to the priority and path comprehensive factors; S53: Calculate the shortest inspection route.

[0015] Further, step S52 is specifically: calculating random inspection points To the inspection point Probability: ; in, is the routing weight value on the path from inspection point i to inspection point j; is the distance from inspection point i to inspection point j; is the comprehensive inspection weight value; α, β, and γ are the influencing factors controlling the routing weight ratio, distance weight ratio, and priority weight ratio respectively; remain is the set of uninspected points.

[0016] Furthermore, step S53 includes using multiple rounds of iterations to continuously update the routing weights. : ; in, The calculation is the residual value after the evaporation of the routing weight in each cycle. A decimal number less than 1 and greater than 0; What is calculated is the incremental value of the inspection route weight generated by inspection j at each step during the last simulated inspection by n inspection personnel; It is the change in the inspection route and is inversely proportional to the total distance before the inspection point.

[0017] Furthermore, step S53 also includes: specifying the number of iterations, and comparing with the sum of the inspection path lengths of the last group of inspection personnel to find the inspection route with the shortest path as the inspection point route for the next inspection task.

[0018] The beneficial effects of the present invention are: Improve inspection efficiency and save time and cost: By optimizing inspection routes and dynamically adjusting inspection cycles, unnecessary inspection time and resource waste are reduced, and inspection resources are more reasonably allocated to high-priority inspection points, thereby improving inspection efficiency.

[0019] Enhanced problem response capability and real-time response: The inspection strategy can be adjusted in real time according to monitoring data and alarm conditions, which improves the ability to respond to sudden problems and dynamically adjusts the inspection cycle and priority, which helps to promptly discover and deal with potential problems and reduce safety risks.

[0020] Optimized decision support, data-driven: Decision support based on historical data and real-time data makes the inspection strategy more scientific and accurate, adaptable to changes in the park environment, and able to flexibly adjust the inspection strategy to cope with different situations.

[0021] In general, this technology that comprehensively utilizes data, optimization strategies, and path planning can significantly improve the inspection efficiency and response capabilities of smart parks, reduce potential risks, and effectively save resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0023] Figure 1 It is a flow chart of the present invention; Figure 2 Calculate the flow chart for the inspection route; Figure 3 This is a simulation diagram of the inspection point; Figure 4 for Figure 3 Corresponding inspection route planning map. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0026] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0027] The park inspection strategy is an algorithm solution for planning the number and cycle of inspection points and ensuring the priority of inspection points in the inspection task. Conventional inspection strategies in smart parks:

[0028] 1. There are n inspection points A1, A2, A3, ..., An in total.

[0029] 2. Based on the inspection cycle, there are i inspection cycles P1, P2, P3, ..., Pi, and the inspection points with the same inspection frequency are arranged in the same task.

[0030] 3. Get j inspection tasks R1, R2, R3, ..., Rj, j <= n.

[0031] 4. Plan inspection routes for all inspection points in each inspection task, or allow inspection personnel to arrange the inspection order by themselves. The inspection route can cover all inspection points and take distance factors into consideration.

[0032] 5. Inspection personnel shall inspect all inspection points one by one according to the inspection point list in the inspection task. If there is no inspection route specified, they shall inspect all inspection points one by one. If there is an inspection route, they shall inspect according to the route recommended by the shortest path algorithm.

[0033] The present invention mainly optimizes the above inspection strategy.

[0034] In response to the above point 2, an automatic adjustment algorithm for inspection frequency is used to optimize the cycle.

[0035] In response to the above point 4, an inspection execution route algorithm that highlights inspection priorities based on a weight ratio is used to optimize the inspection route.

[0036] The specific process is as follows: See also Figure 1 , a park safety inspection method based on multiple weight ratios, comprising the following steps: S1: Optimize the cycle according to the inspection cycle automatic adjustment algorithm so that the first q*v inspections meet the cycle adjustment conditions; S2: Update the inspection cycle of the inspection point; S3: Update the inspection point list of the inspection task, wherein the inspection point list includes inspection point importance level coefficients, inspection point alarm weights, and inspection point cycle weights; S4: Calculate the comprehensive inspection weight of the inspection point based on the inspection point importance level coefficient, inspection point alarm weight and inspection point cycle weight; S5: Calculate the inspection execution route with prominent inspection priority according to the comprehensive inspection weights of the inspection points.

[0037] Step S1 is specifically as follows: The cycle adjustment calculation needs to refer to the historical inspection data, which requires q disks to be accumulated, v consecutive and identical inspection tasks for each disk, and n inspection points in each inspection task, each of which needs to be inspected once. In other words, q*v inspection result data for each inspection point is required.

[0038] For each disk inspection task of v times, the abnormal threshold of the same inspection point is x (x≤v), that is, the number of abnormalities that occur in a certain inspection point during v inspections is ≥x, then this inspection point is shown as an abnormal value in this disk inspection, and the disk inspection abnormal value (initial 0) is +1.

[0039] When disk q is executed and the disk inspection abnormal value is ≥ y, the inspection cycle of the current inspection point will be shortened.

[0040] That is, when the number of abnormalities of a single inspection point Am (1≤m≤n) in v inspection tasks is F, if F ≥ x, the disk inspection abnormality value Fq is increased by 1. After q consecutive disk inspections, Fq ≥ y. Then the inspection cycle of Am changes from the original Pm to Pm-1. If m=1, the inspection cycle of Am remains unchanged. If the above conditions are not met, the inspection cycle will be extended and gradually restored to the set value.

[0041] Step S2 specifically includes: updating the inspection periods of the inspection points to P1, P2, P3, ..., Pi, wherein the inspection period of P1 is the shortest and the inspection period of Pi is the longest.

[0042] Step S3 includes: Update the cycle weight value of the inspection point: The initial cycle weight of the inspection point is W. When the inspection cycle of the inspection point Am is shortened, the weight of Am becomes W+d. If it is shortened, it becomes Wd, where d is the weight change adjustment amount, until it returns to the set value W. The set value W is changeable.

[0043] Update the alarm weight of the inspection point: The alarm content of the inspection point is obtained through the integrated monitoring system of the park. This time, it mainly targets the equipment alarms of the inspection points, which are divided into L1, L2, and L3 levels. Among them, the L3 level alarm has the highest weight, and the alarm weight ratio of this inspection point is calculated as a weighted average. In the previous inspection cycle, the number of L1, L2, and L3 alarms was C1, C2, and C3 respectively. That is:

[0044] WALARM = L1C1 + L2C2 + L3C3.

[0045] Update the importance level coefficient of the inspection point. Each inspection point has three levels of importance: I1, I2, and I3. The weight coefficient can be 1, 1.5, or 2.

[0046] Step S4 is as follows: the current task has n inspection points, and the cycle weight of each inspection point is arrive , the alarm weight of each inspection point is arrive , calculate the comprehensive weight based on the cycle weight ratio and alarm weight ratio, and the comprehensive weight of the inspection point = + ).

[0047] Step S5 is specifically: based on the comprehensive weight, calculating the inspection execution route with prominent inspection priority: n inspection points of the current task arrive , each with its own inspection weight arrive ; Exceeding the independent inspection threshold The inspection points of the tasks have absolute inspection priority. That is, these tasks will be inspected in priority order.

[0048] The inspection order of the remaining inspection points is determined by the priority and path comprehensive factors. To the inspection point The probability formula is:

[0049] ; in, is the routing weight value on the path from point i to point j; It is the distance from point i to point j or the inverse of the inspection route, which means that the closer the distance is, the better the route should be to the nearby inspection point. is the comprehensive inspection weight value; α, β, γ are the influencing factors that control the routing weight ratio, distance weight ratio, and priority weight ratio, which determine which factor has an important influence on the result probability; remain is the set of uninspected points.

[0050] Obtain the best inspection path by using multiple rounds of iterations and continuously calculating the routing weights , find the sequential queue with the shortest route and taking priority factors into account. For details, see Figure 2 : The algorithm starts by simulating and randomly assigning an inspector to each inspection point.

[0051] The sum of the probabilities from the current point to all inspection points is 1. The inspector generates a random value that falls within If the route is within the interval, it will be routed to point j for inspection, and the distance value and order of the inspected points will be recorded.

[0052] Repeat the above steps until all inspection points are inspected.

[0053] renew In the formula Routing weight value. The update strategy for this value is to update the parameter value after completing each round of simulated inspection. The update strategy is:

[0054] ; in, What is calculated is the residual value after the evaporation of the routing weight in each cycle. A decimal number less than 1 and greater than 0; What is calculated is the incremental value of the inspection route weight generated by inspection j at each step during the last simulated inspection by n inspection personnel; The change in inspection route is inversely proportional to the total distance before the inspection point. Its calculation formula is: , m means that at this step, m inspectors come to the current inspection point at the same time. It means that the current inspection point is the sth inspection point, and the total path length of the kth inspector is calculated. It is the inspection weight value variation coefficient constant.

[0055] Iterate the specified number of times as above. Compare the sum of the inspection path lengths of the last group of n inspectors to find the inspection route with the shortest path, which will be used as the inspection point route for the next inspection task.

[0056] Effect verification: Simulate 20 inspection points. Assume that the first three inspection points 1, 2, and 3 have a higher comprehensive inspection weight after calculation, and these three points are inspected first. The distribution coordinates of the inspection points are: (23, 16), (12, 34), (22, 3), (15, 48), (16, 30), (21, 1), (38, 32), (41, 14), (26, 27), (11, 19), (14, 14), (22, 32), (2, 49), (3, 29), (20, 24), (49, 43), (7, 37), (5, 44), (3, 24), (18, 21) The scattered point distribution is as follows: Figure 3 shown.

[0057] The reasonable inspection path calculated by the algorithm is: the optimal path route [2, 1, 3, 6, 8, 7, 16, 4, 13, 18, 17, 14, 19, 10, 11, 20, 15, 9, 12, 5]. For details, please refer to Figure 4 .

[0058] Compared with other inspection routes, the priority and relatively short paths of inspection points 1, 2, and 3 are guaranteed. After multiple rounds of data comparison tests, the following data are obtained (sorted by path length): 220.52, [2,1,3,6,8,7,16,4,13,18,17,14,19,10,11,20,15,9,12,5]; 225.18, [3,1,2,5,12,9,15,20,10,11,19,14,17,18,13,4,16,7,8,6]; 229.1, [2,1,3,6,8,7,16,4,13,18,17,14,19,10,11,20,15,9,5,12]; ...; 372.44, [19, 1, 3, 2, 17, 14, 10, 20, 15, 12, 9, 5, 4, 8, 6, 11, 18, 13, 7, 16]; 376.95, [6, 3, 1, 2, 5, 20, 15, 12, 8, 18, 13, 14, 19, 10, 9, 7, 11, 4, 17, 16]; 395, [1, 2, 3, 6, 5, 4, 14, 19, 10, 20, 11, 12, 9, 7, 18, 17, 8, 16, 13, 15]; Among them, the length of the optimal path is 220.52, the average value of all paths is 264, and the maximum value of all paths is 395. Without considering other factors, the calculation results show that compared with the average level, the inspection efficiency is improved by 17%, and compared with the worst case, the inspection efficiency is improved by 44%.

[0059] In other embodiments, in order to implement the above inspection method, the following operations may be performed: (1) Preparation work: divide the inspection points, connect to the smart park monitoring system, configure the inspection points with relevant equipment and sensor alarm items, and formulate reasonable inspection cycles and inspection contents for different inspection points.

[0060] (2) System design and development, implement the algorithm based on Python, and publish the calling interface through http; realize the automatic generation of inspection tasks based on the task scheduling framework. Before generating tasks, it is necessary to plan the inspection strategy for the inspection points at the current time point. That is, call the algorithm interface and update the inspection point information; the calling logic is to enter the inspection point number, query the database historical alarm data, historical inspection data, and equipment parameter information, and realize the automatic adjustment of the cycle and weight through the algorithm; obtain the inspection task information of this task; the inspection personnel conduct inspections and feedback according to the task information. The main content of the feedback is the abnormal inspection point problems and information records.

[0061] (3) System integration and testing: data integration, integrating the actual operating monitoring system data into the inspection system; functional testing, testing the various functions of the system to ensure the accuracy of data processing and path optimization; user testing, inviting actual inspectors to use the system, collecting feedback and making adjustments; at the current stage, it is recommended that one inspection task be performed by one inspector.

[0062] (4) System launch and training: System launch: deploy the tested inspection system to the actual environment; Training: provide system usage training to park inspectors to ensure that they can operate the new system proficiently.

[0063] (5) Monitoring and maintenance: real-time monitoring of the system operation status to ensure the normal operation of the system, and timely handling of problems arising during system operation, and performing system maintenance and updates.

[0064] (6) Application effect evaluation: Implementation effect: By dynamically adjusting the inspection cycle and optimizing the route, the inspectors’ working time is reduced, and the overall inspection efficiency is expected to increase by 15%; problem response capability is enhanced: after real-time adjustment of the inspection strategy, the response time to sudden problems in the park is shortened; resource utilization is more reasonable, and the inspection cost is reduced. Inspector feedback: according to the inspectors’ feedback, the system interface and inspection route suggestions are continuously improved. Managers’ feedback: the data and reports provided by the system help managers make better decisions, and the safety and management level of the park are improved.

[0065] Based on the above embodiments, the present invention is based on alarm data adjustment: using the alarm data of the monitoring system and the historical data of the inspection points, through the cycle dynamic adjustment algorithm, dynamically adjust the inspection cycle to ensure that key points are inspected more frequently. Introducing alarm weights, cycle weights and location importance weights, through the comprehensive weight ratio algorithm, the inspection cycle and priority are made more reasonable and scientific.

[0066] The present invention not only meets the inspection priority, but also finds the shortest inspection route through algorithm calculation, improves inspection efficiency, optimizes inspection routes, reduces the walking time and cost of inspectors, and improves overall work efficiency. In addition, the present invention uses inspection historical data and real-time monitoring data to make decisions, making the inspection strategy more scientific and effective, identifying high-risk areas through historical data, and dynamically adjusting the inspection strategy to deal with different risk situations.

[0067] It should be noted that, for the above embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification belong to preferred embodiments, and the actions involved are not necessarily required by the present application.

[0068] The above embodiments describe the basic principles and main features of the present invention and the advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the changes and modifications made by those skilled in the art shall be within the scope of protection of the appended claims of the present invention without departing from the spirit and scope of the present invention.

Claims

1. A park safety inspection method based on multiple weight ratios, characterized in that: The steps include: S1: Optimize the inspection cycle according to the inspection cycle automatic adjustment algorithm so that the first q*v inspections meet the cycle adjustment conditions, where q is the cumulative number of inspection disks and v is the number of consecutive and identical inspection tasks in each disk; S2: Update the inspection cycle of the inspection point; S3: Update the inspection point list of the inspection task, wherein the inspection point list includes inspection point importance level coefficients, inspection point alarm weights, and inspection point cycle weights; S4: Calculate the comprehensive inspection weight of the inspection point based on the inspection point importance level coefficient, inspection point alarm weight and inspection point cycle weight; S5: Calculate the inspection execution route with prominent inspection priority according to the comprehensive inspection weights of the inspection points.

2. A park safety inspection method based on multiple weight ratios as described in claim 1, characterized in that: Step S1 includes the following sub-steps: S11: Refer to historical inspection data and accumulate q disks, with v consecutive and identical inspection tasks for each disk. Each inspection task has n inspection points, each of which needs to be inspected once; S12: Collect statistics on inspection points where abnormalities occur in each inspection task, and shorten the inspection cycle of the inspection point.

3. A park safety inspection method based on multiple weight ratios as described in claim 2, characterized in that: Step S2 specifically includes: updating the inspection periods of the inspection points to P1, P2, P3, ..., Pi, wherein the inspection period of P1 is the shortest and the inspection period of Pi is the longest.

4. A park safety inspection method based on multiple weight ratios as described in claim 3, characterized in that: Step S3 includes the following sub-steps: S31: Update the inspection point period weight value: When the inspection period of the inspection point is shortened, the weight of the inspection point is modified to W+d; When the inspection cycle of the inspection point is restored, the weight of the inspection point is modified to Wd; where W is the initial weight of the inspection point cycle, and d is the weight change adjustment amount; S32: Update the alarm weight of the inspection point: W alarm = L1C1 + L2C2 + L3C3; where L1, L2, L3 are alarm levels; C1, C2, C3 are the alarm numbers corresponding to L1, L2, L3; S33: Update the inspection point importance level coefficients I1, I2, and I3, among which I1 is the lowest and I3 is the highest.

5. A park safety inspection method based on multiple weight ratios as claimed in claim 4, characterized in that: Step S4 is specifically as follows: If the current task has n inspection points, the cycle weights of the inspection points are arrive ; The alarm weights of the inspection points are arrive ; The inspection point importance level coefficient is I; the calculation method of the inspection point comprehensive inspection weight is: = + ）。 6. A park safety inspection method based on multiple weight ratios as claimed in claim 5, characterized in that: Step S5 is specifically as follows: S51: Compare the comprehensive inspection weight of the inspection point with the independent inspection threshold. If the independent inspection threshold is exceeded, the inspection has absolute inspection priority authority. S52: determining the inspection order of the inspection points according to the priority and path comprehensive factors; S53: Calculate the shortest inspection route.

7. A park safety inspection method based on multiple weight ratios as claimed in claim 6, characterized in that: Step S52 specifically includes: calculating random inspection points To the inspection point Probability: ； in, is the routing weight value on the path from inspection point i to inspection point j; is the distance from inspection point i to inspection point j; is the comprehensive inspection weight value; α, β, and γ are the influencing factors controlling the routing weight ratio, distance weight ratio, and priority weight ratio respectively; remain is the set of uninspected points.

8. A park safety inspection method based on multiple weight ratios as claimed in claim 7, characterized in that: Step S53 includes using multiple rounds of iterations to continuously update the routing weights. : ； in, The calculation is the residual value after the evaporation of the routing weight in each cycle. A decimal number less than 1 and greater than 0; What is calculated is the incremental value of the inspection route weight generated by inspection j at each step during the last simulated inspection by n inspection personnel; It is the change in the inspection route and is inversely proportional to the total distance before the inspection point.

9. A park safety inspection method based on multiple weight ratios as claimed in claim 8, characterized in that: Step S53 also includes: specifying the number of iterations, and comparing with the sum of the inspection path lengths of the last group of inspection personnel to find the inspection route with the shortest path as the inspection point route for the next inspection task.

Images