Municipal Facility Inspection and Scheduling Method and System Based on Urban General Butler

Abstract

The present invention relates to the technical field of urban municipal facility management, and discloses a method and system for inspecting and scheduling municipal facilities based on an urban butler. The method includes obtaining municipal facility data and performing structured processing, constructing a spatio-temporal grid coordinate system, mapping to generate facility spatio-temporal coordinate information, generating an initial inspection path and optimizing it according to traffic and fault probabilities, splitting tasks and reasonably allocating them, collecting progress in real time and optimizing the path again, issuing instructions and receiving feedback, and updating data. The system includes multiple modules such as data collection and processing to implement this method. Through the present invention, facility data can be integrated, the inspection path can be optimized, tasks can be reasonably allocated, sudden faults can be quickly responded to, and the accuracy of fault prediction can be improved based on feedback, effectively improving the efficiency and quality of municipal facility inspection and scheduling, and ensuring the stable operation of urban facilities.

Description

Technical Field

[0001] The present invention relates to the technical field of urban municipal facility management, and specifically to a method and system for inspecting and scheduling municipal facilities based on the urban general manager. Background Art

[0002] With the acceleration of the urbanization process, the scale of cities is constantly expanding, and the quantity and types of municipal facilities are increasing rapidly. These facilities include roads, bridges, drainage systems, lighting equipment, etc., which are the basic guarantees for the normal operation of cities. However, the traditional methods for inspecting and scheduling municipal facilities have gradually exposed many problems and are difficult to meet the needs of modern urban management.

[0003] In terms of data management, the basic information and real-time status data of municipal facilities are often scattered in different systems and departments, lacking effective integration and structured processing. For example, the geographical coordinate information of facilities may be managed by the surveying and mapping department, while the maintenance cycle information is in the hands of the operation and maintenance department. The data formats and standards of each department are not unified, resulting in difficulty in data sharing and comprehensive utilization. This makes it impossible to quickly and accurately obtain comprehensive facility information during inspection scheduling, affecting the scientificity and timeliness of decision-making.

[0004] In terms of inspection route planning, traditional methods mostly arrange based on experience or simple geographical order, without fully considering dynamic factors such as real-time traffic conditions and facility failure probabilities. During traffic congestion periods, patrolling according to a fixed route will lead to low inspection efficiency, wasting a lot of time on the road and being unable to reach the facility locations that need to be inspected in a timely manner. At the same time, due to ignoring the facility failure probability, some areas with frequent failures cannot be promptly concerned, increasing the risk of sudden facility failures and affecting the normal operation of the city.

[0005] In the task assignment link, the traditional method usually divides tasks according to the general area of inspectors or equipment, without fully considering the skill levels of personnel, the load status of equipment, and the urgency of tasks. This may result in personnel with insufficient skills being assigned complex inspection tasks and being unable to detect and handle facility problems in a timely manner; or the equipment being overloaded, affecting the inspection quality and efficiency, and even causing equipment damage. Moreover, for urgent tasks, there is no timely response, delaying the best opportunity for facility maintenance.

[0006] In addition, when encountering sudden facility failures, the traditional inspection scheduling system lacks a fast and effective emergency handling mechanism. It is unable to quickly adjust the inspection plan and handle the failure in a timely manner, which may lead to an expansion of the scope of influence of the failure and cause greater losses to the city. At the same time, due to the lack of feedback and analysis on the inspection effect, it is difficult to optimize and improve the inspection scheduling method, making the problem persist for a long time and unable to be fundamentally solved. Summary of the Invention

[0007] The purpose of the present invention is to provide a municipal facility inspection and scheduling method and system based on the urban general steward to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions: A municipal facility inspection and scheduling method based on the urban general steward, the method comprising:

[0009] Obtain the basic information and real-time status data of municipal facilities, structurally process the basic information according to preset attribute dimensions, and generate facility feature data;

[0010] Construct a spatio-temporal grid coordinate system, divide grid cells based on the urban geographical area, define the X-axis of the spatio-temporal grid coordinate system as the time axis, the Y-axis as the space axis, the Z-axis as the facility type axis, and assign dynamic weights to each grid cell;

[0011] Map the facility feature data into the corresponding spatio-temporal grid coordinate system to generate facility spatio-temporal coordinate information;

[0012] Based on the preset inspection task requirements, extract the type, geographical location and priority of the inspection target facilities to generate an initial inspection path;

[0013] According to the real-time traffic flow data and the facility failure probability prediction model, dynamically adjust the weights of each grid cell in the initial inspection path, and generate an optimized inspection path based on the greedy algorithm;

[0014] Split the optimized inspection path into multiple inspection subtasks, and allocate the inspection subtasks according to the real-time location and load status of the inspection personnel or equipment;

[0015] Real-time collect the execution progress data of the inspection subtasks, and combine with the dynamic weights of the spatio-temporal grid coordinate system to re-optimize the paths of the uncompleted inspection subtasks;

[0016] Send the re-optimized inspection path and task allocation instructions to the corresponding inspection terminals, and receive the inspection result data fed back by the terminals;

[0017] Update the facility feature data and the dynamic weights of the spatio-temporal grid coordinate system according to the inspection result data.

[0018] Preferably, the preset attribute dimensions include facility type, geographical coordinates, maintenance cycle and historical failure records.

[0019] Preferably, the dynamically adjusting the weights of each grid cell in the initial inspection path includes:

[0020] Obtain the real-time traffic congestion index and weather data, and calculate the travel time cost of each grid cell;

[0021] Predict the failure probability of each facility based on the historical failure records of the facilities and a machine learning model;

[0022] Dynamically update the weight of the grid cell according to the product of the travel time cost and the failure probability.

[0023] Preferably, the machine learning model is an LSTM network based on time series, the input data includes facility operation parameters, environmental data and historical maintenance records, and the output is the failure probability within a preset future time period.

[0024] Preferably, the allocation of the inspection sub-tasks includes:

[0025] Construct a priority scoring matrix according to the skill level, current location and task urgency of the inspection personnel or equipment;

[0026] Use the Hungarian algorithm to perform optimal matching on the scoring matrix to determine the allocation result of the inspection sub-tasks.

[0027] Preferably, the method further includes:

[0028] Cooperatively plan multiple inspection tasks within the same geographical area, and optimize the path intersection points between multiple tasks by introducing the ant colony algorithm to reduce the repeated inspection areas.

[0029] Preferably, the method further includes:

[0030] Construct a multi-objective optimization model with the optimization objectives of minimizing the total inspection time, balancing the load distribution and maximizing the failure coverage rate, use the NSGA-II algorithm to solve the Pareto optimal solution set, and select the final inspection plan based on preset rules.

[0031] Preferably, the method further includes:

[0032] When a sudden facility failure is detected, interrupt the current inspection path, insert an emergency inspection task based on the spatio-temporal coordinates and priority of the failed facility, and recalculate the optimized path.

[0033] Preferably, the method further includes:

[0034] Establish an inspection effect feedback strategy, and dynamically correct the parameters of the facility failure probability prediction model according to the correlation between historical inspection data and changes in facility status.

[0035] Preferably, the present invention further includes a municipal facility inspection and scheduling system based on the urban butler for implementing the method for municipal facility inspection and scheduling based on the urban butler, and the system includes:

[0036] Data acquisition and processing module: It is used to obtain the basic information and real-time status data of municipal facilities, structurally process the basic information according to preset attribute dimensions, and generate facility feature data;

[0037] Spatio-temporal grid construction module: Construct a spatio-temporal grid coordinate system, divide grid units based on the urban geographical area, define the X-axis of the spatio-temporal grid coordinate system as the time axis, the Y-axis as the space axis, the Z-axis as the facility type axis, and assign dynamic weights to each grid unit;

[0038] Mapping module: Map the facility feature data into the corresponding spatio-temporal grid coordinate system to generate facility spatio-temporal coordinate information;

[0039] Initial path generation module: Based on the preset inspection task requirements, extract the types, geographical locations and priorities of the inspection target facilities, and generate an initial inspection path;

[0040] Path optimization module: According to the real-time traffic flow data and the facility failure probability prediction model, dynamically adjust the weights of each grid unit in the initial inspection path, and generate an optimized inspection path based on the greedy algorithm;

[0041] Task allocation module: Split the optimized inspection path into multiple inspection subtasks, and allocate the inspection subtasks according to the real-time positions and load statuses of inspection personnel or equipment;

[0042] Monitoring and re-optimization module: Real-time collect the execution progress data of inspection subtasks, and combine with the dynamic weights of the spatio-temporal grid coordinate system to re-optimize the paths of uncompleted inspection subtasks;

[0043] Instruction issuance and feedback reception module: Issue the re-optimized inspection path and task allocation instructions to the corresponding inspection terminals, and receive the inspection result data fed back by the terminals;

[0044] Data update module: Update the facility feature data and the dynamic weights of the spatio-temporal grid coordinate system according to the inspection result data.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] In terms of data processing and management, by obtaining the basic information and real-time status data of municipal facilities, and structurally processing them according to preset attribute dimensions to generate facility feature data, the effective integration and standardized management of data are realized. This enables various facility information to be centrally stored and shared, facilitating the management department to query and call at any time. For example, when it is necessary to maintain the street lights in a certain area, information such as the geographical coordinates, maintenance cycle, and historical failure records of the street lights can be quickly obtained, providing comprehensive and accurate data support for formulating maintenance plans and avoiding management difficulties caused by scattered data and inconsistent formats.

[0047] The construction of the spatio-temporal grid coordinate system and the mapping of facility feature data provide an intuitive spatio-temporal perspective for facility management. By defining the X-axis as the time axis, the Y-axis as the space axis, and the Z-axis as the facility type axis, and assigning dynamic weights to each grid cell, the distribution and importance of facilities within the urban spatio-temporal scope can be clearly displayed. This helps managers quickly understand the real-time status of different types of facilities in different regions, providing a visual basis for inspection scheduling decisions. For example, by observing the spatio-temporal grid coordinate system, it is possible to quickly discover that facilities in a certain area frequently malfunction, thus promptly adjusting the inspection plan to increase the inspection frequency and priority of that area.

[0048] In terms of inspection path planning, the present invention generates an initial inspection path based on preset inspection task requirements, dynamically adjusts the weights of each grid cell in the path according to real-time traffic flow data and the facility failure probability prediction model, and then uses the greedy algorithm to generate an optimized inspection path. This approach fully considers traffic conditions and facility failure risks, effectively improving the inspection efficiency. Taking urban road inspection as an example, during the morning rush hour, the system will avoid congested sections according to the real-time traffic congestion index, select a smooth route for inspection, reducing the time wasted by inspection personnel on the road and enabling them to have more time for facility inspection. At the same time, since facilities with a high probability of failure are inspected first, potential problems can be discovered and handled in a timely manner, reducing the likelihood of sudden facility failures and ensuring the normal operation of urban facilities.

[0049] In the task assignment link, the optimized inspection path is split into multiple inspection subtasks, and they are reasonably assigned according to the real-time location, load status, and skill level of inspection personnel or equipment. This ensures that each inspection task can be undertaken by the most suitable personnel or equipment, improving the inspection quality and efficiency. For example, for the inspection task of power facilities with a high technical difficulty, it will be preferentially assigned to inspection personnel with a high skill level and rich experience; for inspection personnel or equipment that are close and have a low load, nearby inspection subtasks will be assigned, reducing the time cost of task execution. Moreover, by constructing a priority scoring matrix and using the Hungarian algorithm for optimal matching, the intelligence and scientific nature of task assignment are realized, avoiding the irrationality of traditional assignment methods.

[0050] When a sudden facility failure is detected, the system can interrupt the current inspection path, insert an emergency inspection task, and recalculate and optimize the path. This mechanism ensures a quick response to sudden failures, enables timely handling of the failures, and prevents the expansion of the scope of influence of the failures. For example, in the urban drainage system, once a blockage is detected in a certain section of the pipeline, the system will immediately adjust the inspection plan, arrange the nearest inspection personnel to go for handling, and at the same time re-plan the paths of other inspection tasks to ensure the normal operation of the entire drainage system and reduce the impact on urban traffic and residents' lives caused by waterlogging.

[0051] In addition, the established inspection effect feedback strategy dynamically corrects the parameters of the facility failure probability prediction model based on the correlation between historical inspection data and changes in facility status. This continuously improves the prediction accuracy of the model and further optimizes the inspection scheduling plan. Over time, the system can more accurately predict facility failures, arrange inspection tasks in advance, achieve preventive maintenance, reduce facility maintenance costs, extend the service life of facilities, and thus comprehensively improve the management level and operation efficiency of urban municipal facilities, providing a strong guarantee for the sustainable development of the city. Brief Description of the Drawings

[0052] Figure 1 is the working principle diagram of the municipal facility inspection scheduling method described in the present invention;

[0053] Figure 2 is the flowchart of grid weight adjustment and path optimization based on traffic and failure probability;

[0054] Figure 3 is the flowchart of the assignment of municipal facility inspection subtasks;

[0055] Figure 4 is the flowchart of collaborative planning of multiple inspection tasks in the same geographical area. Detailed Embodiment

[0056] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0057] Please refer to Figures 1-4 , the present invention provides a municipal facility inspection scheduling method based on the urban butler, and the specific implementation steps are as follows:

[0058] By connecting with the municipal facilities management system and collecting data in real time through sensors, the basic information and real-time status data of municipal facilities are obtained. The basic information covers various aspects such as the name, model, construction time, etc. of the facilities. These basic information are structured according to the preset attribute dimensions, and the preset attribute dimensions include facility type, geographical coordinates, maintenance cycle, and historical fault records, etc. For example, for a bridge, the facility type is a bridge, the geographical coordinates are accurate to longitude and latitude, the maintenance cycle may be once every six months, and the historical fault records include situations such as bridge deck cracks and pier displacements that have occurred. After processing, facility feature data is generated for subsequent analysis and use.

[0059] Based on the urban geographical area as a benchmark, the city is divided into multiple grid units. A spatio-temporal grid coordinate system is defined, where the X-axis is the time axis, with units such as hours and days, used to record information at different time points; the Y-axis is the space axis, corresponding to the geographical space position of the city; the Z-axis is the facility type axis, used to distinguish different types of municipal facilities, such as road facilities, lighting facilities, drainage facilities, etc. A dynamic weight is assigned to each grid unit, and the initial value of the weight can be determined according to factors such as the importance of the facilities within the grid unit and the historical fault frequency.

[0060] Map the previously generated facility feature data into the corresponding spatio-temporal grid coordinate system. Determine its position on the Y-axis according to the geographical coordinates of the facility, determine its position on the Z-axis according to the facility type, and then combine the current time or the planned inspection time to determine the position on the X-axis, thus generating facility spatio-temporal coordinate information. This information can intuitively display the distribution of facilities within the urban spatio-temporal range.

[0061] Based on the preset inspection task requirements, extract the type, geographical location, and priority of the inspection target facilities from the facility feature data. For example, the power facilities in some key areas have a higher priority and need to be inspected first. According to this information, use the existing path planning algorithm to generate an initial inspection path to ensure that all facilities that need to be inspected can be covered.

[0062] Obtain real-time traffic flow data, which can be obtained from the traffic management department or collected through sensors installed on the road. At the same time, use the facility failure probability prediction model to predict the failure probability of each facility. Calculate the travel time cost of each grid unit according to the real-time traffic flow data, and combine the failure probability to dynamically adjust the weight of each grid unit in the initial inspection path. Then, based on the greedy algorithm, when selecting the next inspection point each time, select the grid unit with the optimal current weight, thus generating an optimized inspection path to improve the inspection efficiency.

[0063] The optimized inspection path is split into multiple inspection subtasks. These inspection subtasks are allocated according to the real-time location and load status of the inspection personnel or equipment. For example, if an inspection personnel is currently near a certain grid cell and has a low load, the inspection subtasks near this area are preferentially allocated to ensure the rationality and efficiency of task allocation.

[0064] The execution progress data of the inspection subtasks is collected in real time through the positioning device and feedback system carried by the inspection personnel or equipment. Combining with the dynamic weights of the spatio-temporal grid coordinate system, the path of the uncompleted inspection subtasks is optimized again. If there is a sudden traffic jam in a certain area, resulting in the obstruction of the original planned path, the path is re-planned to avoid the congested area and ensure that the inspection tasks are completed on time.

[0065] Instruction issuance and result feedback: The re-optimized inspection path and task allocation instructions are sent to the corresponding inspection terminals through wireless communication technology, such as the handheld devices of inspection personnel or the in-vehicle systems of inspection vehicles. After receiving the instructions, the inspection terminals execute the inspection tasks and feedback the inspection result data. The inspection result data includes information such as the actual status of the facilities and whether faults are found.

[0066] The facility feature data and the dynamic weights of the spatio-temporal grid coordinate system are updated according to the inspection result data. If a fault is found in a certain facility, the historical fault records of this facility are updated; if the facilities in a certain grid cell frequently have faults, the weight of this grid cell is appropriately increased to focus on inspecting this area more in the future.

[0067] The present invention will be further described below in conjunction with Embodiments 1 to 6:

[0068] Embodiment 1: After obtaining the basic information and real-time status data of municipal facilities, structured processing is carried out according to the preset attribute dimensions. Taking street lamp facilities as an example, the facility type is clearly defined as lighting facilities; the geographical coordinates are obtained through the GPS positioning module installed on the street lamps, accurate to six decimal places to ensure the accuracy of positioning; the maintenance cycle is set according to the service life of the street lamps, the manufacturer's suggestions, and the local maintenance standards, generally with a full maintenance once a year; the historical fault records detail information such as the fault types, fault times, and maintenance situations that have occurred to the street lamps. Through the sorting and integration of these attributes, comprehensive and targeted facility feature data is generated.

[0069] When dynamically adjusting the weights of each grid cell in the initial inspection path, the real-time traffic congestion index and weather data are obtained. The real-time traffic congestion index can be obtained from the traffic big data platform, which reflects the congestion degree of the road, with a value range of 0 - 10, and the larger the value, the more serious the congestion. The weather data can be obtained from the interface of the meteorological department, including weather conditions (such as sunny, rainy, snowy, etc.), temperature, humidity and other information.

[0070] Calculate the travel time cost of each grid cell, with the formula: , where represents the travel time cost of the grid cell, is the base time required to pass through this grid cell under normal traffic conditions, which is statistically obtained from historical traffic data; is the real-time traffic congestion index; is the weather impact factor. When it is sunny, when it is rainy, when it is snowy or in other bad weather conditions, . For example, for a certain grid cell, is 10 minutes, the real-time traffic congestion index , and the current weather is rainy. Then the travel time cost minutes.

[0071] Based on the historical failure records of facilities and a machine learning model, predict the failure probability of each facility. In this embodiment, an LSTM network based on time series is used as the machine learning model. The input data includes facility operation parameters (such as the voltage and current of street lights), environmental data (temperature, humidity, light intensity, etc.), and historical maintenance records. Among them, the facility operation parameters are collected in real time by sensors installed on the street lights; the environmental data is obtained from nearby weather stations or environmental monitoring devices; the historical maintenance records are extracted from the municipal facility maintenance management database. The output is the failure probability within a preset future time period, and the preset time period can be set according to the actual situation, such as the next week or month.

[0072] According to the product of the travel time cost and the failure probability, dynamically update the weight of the grid cell. Suppose there is a street light in a certain grid cell, with a travel time cost minutes, and the failure probability within the next week is predicted by the LSTM network . Then the weight update value of this grid cell is . If the initial weight of this grid cell is 5, the updated weight is . In this way, by comprehensively considering traffic factors and facility failure risks, reasonably adjust the weights of grid cells to provide a more accurate basis for optimizing the inspection path.

[0073] Embodiment 2: In this embodiment, the specific implementation process of the inspection sub-task allocation is emphasized.

[0074] After generating the optimized inspection path, split it into multiple inspection sub-tasks. To reasonably allocate these inspection sub-tasks, it is necessary to construct a priority scoring matrix according to the skill level, current location, and task urgency of the inspection personnel or equipment.

[0075] The skill levels of the patrol personnel or equipment are classified according to their training experiences, work experiences, and acquired professional qualifications. For example, they are divided into three levels: junior, intermediate, and senior, corresponding to different skill scores. The junior level is 3 points, the intermediate level is 5 points, and the senior level is 8 points. Through this quantitative method, the professional ability levels of different patrol personnel or equipment are clarified.

[0076] The current location is obtained through the positioning device installed on the patrol personnel or equipment, accurate to the specific grid cell. The task urgency is determined according to the priority of the facility and the failure probability. For the patrol tasks corresponding to the facilities with high priority and high failure probability, the urgency is set to high, with an assigned value of 8 points; for the tasks with relatively high priority but relatively low failure probability, the urgency is medium, with an assigned value of 5 points; for the tasks with low priority and low failure probability, the urgency is low, with an assigned value of 3 points.

[0077] When constructing the priority scoring matrix, the patrol personnel or equipment are in rows and the patrol subtasks are in columns. The element values in the matrix are calculated comprehensively based on the skill level of the patrol personnel or equipment, the distance between the current location and the task location, and the task urgency. The calculation method is: , where represents the element value in the scoring matrix, is the skill level score of the patrol personnel or equipment, is the distance between the current location of the patrol personnel or equipment and the grid cell where the task is located (the distance is calculated through the coordinates of the grid cell, with the unit of kilometers), is the task urgency score.

[0078] For example, there is a patrol personnel A with an intermediate skill level ( ), currently located in grid cell (1, 2), and there is a current patrol subtask in grid cell (3, 4), with a distance of kilometers, and the task urgency is high , then the score of this patrol personnel A for this patrol subtask is points.

[0079] The Hungarian algorithm is used to perform the optimal matching on the scoring matrix. The Hungarian algorithm is a classic algorithm for solving the assignment problem. Its core idea is to continuously find the augmenting path, transform the original problem into an equivalent matching problem, and thus find the optimal allocation scheme. In this embodiment, using the Hungarian algorithm to process the constructed priority scoring matrix can quickly and accurately determine the allocation results of the patrol subtasks, ensure that each patrol subtask can be assigned to the most suitable patrol personnel or equipment, and improve the overall efficiency and quality of the patrol work.

[0080] Example 3: During the inspection of urban municipal facilities, there are often multiple inspection tasks in the same geographical area. This example details the specific method for collaborative planning of multiple inspection tasks in the same geographical area.

[0081] First, collect information on multiple inspection tasks in the same geographical area, including the target facility type, geographical location, priority, and estimated inspection time for each task. For example, in the central area of a certain city, there are three inspection tasks. Task A is to inspect the road facilities in the area, including multiple intersections and sections; Task B is to check the street lamp facilities; Task C is to detect whether there is a blockage in the drainage pipeline.

[0082] Introduce the ant colony algorithm to optimize the path intersection points between multiple tasks and reduce the overlapping inspection areas. The ant colony algorithm is a heuristic algorithm that simulates the foraging behavior of ants. Ants leave pheromones on the path during the process of finding food. The higher the concentration of pheromones on a path, the greater the probability of being selected by other ants.

[0083] In this example, each inspection task is regarded as an ant, and the starting point and ending point of the task are used as the starting point and target point of the ant. At the beginning of the algorithm, a random initial path is assigned to each inspection task. During the iteration process, ants release pheromones on the path, and the update formula for pheromones is: , where represents the pheromone concentration on path at time ; is the pheromone evaporation coefficient, with a value range between , usually set to about 0.5, which is used to simulate the natural evaporation of pheromones over time; is the number of ants, that is, the number of inspection tasks; represents the amount of pheromones released by the -th ant on path at time , and the calculation method is: , is a constant used to control the release intensity of pheromones, usually with a value of 100; is the length of the path traveled by the -th ant.

[0084] When an ant selects the next path point, it makes a decision based on the pheromone concentration and heuristic information on the path, and the selection probability formula is: , where represents the probability that the -th ant selects node from node at time ; and are two parameters, representing the relative importance of pheromone and heuristic information respectively. Usually , ; is the heuristic information, generally taken as the reciprocal of the length of the path , that is , is the node and the node distance between; is the set of nodes that the th ant can currently choose.

[0085] Through continuous iteration, the ants will gradually find a better path, reducing the path intersections of multiple inspection tasks and the repeated inspection areas accordingly. For example, after multiple iterations, there was originally a situation of repeated inspection for Task A and Task B on a certain road section. After optimization by the ant colony algorithm, the paths of the two tasks are reasonably planned, avoiding repeated inspection on this road section, effectively improving the inspection efficiency, and reducing the labor and time costs.

[0086] Example 4: This example details the process of constructing a multi-objective optimization model and solving it using the NSGA-II algorithm. The specific method is as follows:

[0087] Construct a multi-objective optimization model with the optimization objectives of minimizing the total inspection time, balancing the load distribution, and maximizing the fault coverage rate.

[0088] Minimize the total inspection time, that is, the shortest total duration required to complete all inspection tasks. Let the set of inspection tasks be , and the inspection time for each task is , then the total inspection time . In actual calculation, can be determined according to factors such as the complexity of the task, the number of target facilities, and the expected inspection speed. For example, for an inspection task involving 10 street lights, with an expected inspection time of 5 minutes for each street light and a moving time of 10 minutes in between, then the inspection time minutes.

[0089] Balancing the load distribution means ensuring that the workloads borne by each inspection personnel or equipment are relatively balanced, avoiding the situation where some inspection personnel have too heavy tasks while some have too light tasks. Let the set of inspection personnel or equipment be , and the set of tasks borne by each inspection personnel or equipment is , and the workload it bears , the load balance degree can be measured by calculating the standard deviation of the workload, and the standard deviation formula is: , where is the average value of the workloads of all inspection personnel or devices. The smaller the standard deviation, the more balanced the load distribution.

[0090] Maximizing the fault coverage rate requires discovering as many potential facility faults as possible. Let the set of faulty facilities be , and the set of faulty facilities discovered by the inspection be , then the fault coverage rate , where and represent the number of elements in the sets and respectively.

[0091] The NSGA-II algorithm is used to solve the Pareto optimal solution set. The NSGA-II algorithm is an efficient multi-objective optimization algorithm, and its main steps include initializing the population, calculating the individual fitness, selection, crossover, and mutation, etc.

[0092] When initializing the population, a certain number of inspection plans are randomly generated, and each plan contains information such as the planning of the inspection path and the assignment of tasks. Calculate the individual fitness, that is, evaluate each inspection plan according to the above three optimization objectives to obtain the fitness value corresponding to each objective.

[0093] The selection operation adopts the tournament selection method, randomly selects a certain number of individuals from the population for comparison, and selects the individuals with better fitness to enter the next generation. The crossover operation is to exchange genes of the selected individuals to generate new individuals. The mutation operation is to randomly change the genes of the individuals to increase the diversity of the population.

[0094] Through continuous iteration, the algorithm will gradually converge to the Pareto optimal solution set. The Pareto optimal solution set is a set of non-dominated solutions. In this set, there is no solution that is better than other solutions in all objectives. For example, if solution A is shorter than solution B in the total inspection time but lower than solution B in the fault coverage rate, and there is no other solution that can be better than A and B in both of these two objectives at the same time, then both A and B belong to the Pareto optimal solution set.

[0095] Select the final inspection plan based on preset rules. The preset rules can be set according to actual needs. For example, when paying more attention to the fault coverage rate, you can preferentially select the plan with a high fault coverage rate and relatively good total inspection time and load balance degree; if the current manpower is limited and more attention is paid to the load balance, you can preferentially select the plan with a good load balance degree. In this way, the most practical final inspection plan is selected from the Pareto optimal solution set to improve the comprehensive effect of the inspection scheduling of municipal facilities.

[0096] Example 5: During the inspection of municipal facilities, it is inevitable to encounter sudden facility failures. This example details the processing flow for dealing with sudden facility failures.

[0097] Through a real-time monitoring system, such as sensors installed on municipal facilities and citizen feedback platforms, sudden facility failures are detected in a timely manner. When the system receives the fault information, it immediately obtains the spatio-temporal coordinates and priority of the faulty facility.

[0098] Taking the drainage pipe system of a certain city as an example, assume that during the inspection, the pressure sensor of a drainage pipe located in a certain section suddenly detects an abnormal increase in pressure, far exceeding the normal range. The system determines that the drainage pipe is blocked. At this time, the system quickly locates the spatio-temporal coordinates of the drainage pipe. For example, in the spatio-temporal grid coordinate system, the Y-axis coordinate represents the specific geographical location where the pipe is located (such as a specific section of a certain street), the Z-axis coordinate indicates the type of drainage facility, and the X-axis coordinate is the time point when the fault occurs. At the same time, its priority is determined according to factors such as the importance of the area where the drainage pipe is located and the scope of influence. If the pipe is located in the central business district of the city and a blockage may cause serious waterlogging, affecting traffic and commercial activities, then its priority is set to high.

[0099] After detecting a sudden facility failure, the system immediately interrupts the current inspection path. Taking the inspection personnel who are performing the comprehensive inspection task in this area as an example, the inspection personnel were originally inspecting road facilities, lighting facilities, etc. according to the established optimized inspection path. After receiving the fault alarm, the inspection terminal in their hand will receive an interruption instruction and stop the current inspection task being carried out.

[0100] Based on the spatio-temporal coordinates and priority of the faulty facility, an emergency inspection task is inserted. The system will re-plan the path, giving priority to the location and priority of the faulty facility. When planning the path, calculate the shortest path from the current position of the inspection personnel to the position of the faulty facility, and avoid traffic congestion sections at the same time. For example, if it is known through real-time traffic data that a certain conventional road to the faulty drainage pipe is congested, the system will automatically select another road that is slightly longer but has smooth traffic as the temporary inspection path.

[0101] When recalculating the optimized path, the system will take emergency inspection tasks into overall consideration. It not only needs to consider the path to the faulty facility, but also plan the subsequent inspection path after the fault is handled. Assuming that after the fault is handled, the inspector still needs to continue to complete the remaining inspection tasks, the system will recalculate an optimized inspection path based on factors such as the time, traffic conditions, location and priority of the remaining facilities at this time to ensure that the subsequent inspection tasks can be completed efficiently. During the process of replanning the path, the weights of relevant grid cells in the spatio-temporal grid coordinate system will also be updated in real time. For example, the weight of the grid cell in the fault occurrence area will increase due to this fault, so as to pay more attention to this area in the future.

[0102] Embodiment 6: Establish an inspection effect feedback strategy, which can continuously improve the accuracy of the facility fault probability prediction model, thereby optimizing the inspection scheduling of municipal facilities. The specific method is as follows:

[0103] Collect historical inspection data, including information such as the time, location, type of facilities involved, and facility status (normal, faulty, and specific fault types) of each inspection. For example, in the street lamp inspection records in the past year, the specific time of each inspection was detailedly recorded, accurate to the minute; the specific location of the street lamp, accurate to the street number; the type of street lamp, such as high-pressure sodium lamp, LED lamp, etc.; the status of the street lamp at that time, whether it was normally lit, partially damaged or completely extinguished, and if there was damage, the specific cause of the damage was recorded, such as the bulb burned out, the circuit was short-circuited, etc.

[0104] At the same time, collect data on the changes in the facility status during the corresponding period. Taking street lamps as an example, in addition to the status recorded during the inspection, it will also collect whether there have been any faults reported by citizens between two inspections of the street lamp, as well as the handling time and results of these faults. By analyzing these data, the correlation between historical inspection data and changes in facility status is established.

[0105] When analyzing the correlation, data mining and statistical analysis methods are used. For example, through statistics, it is found that for street lamps in a certain area, when the ambient temperature continuously exceeds 35°C and the operating duration reaches 5000 hours, the probability of the bulb burning out increases significantly. This indicates that there is a certain correlation between the ambient temperature and the operating duration and the fault of the street lamp bulb.

[0106] According to the above correlation, dynamically correct the parameters of the facility fault probability prediction model. Assuming that an LSTM network based on time series is used as the facility fault probability prediction model, and its input data includes facility operation parameters, environmental data, and historical maintenance records. According to the analyzed correlation, adjust the parameters such as the weights and biases of the model. If it is found that the ambient temperature has a greater impact on the street lamp fault, then increase the weight of the ambient temperature input feature in the model, so that the model can more accurately reflect the impact of environmental factors when predicting the street lamp fault probability.

[0107] In actual operation, the model parameters are corrected regularly. For example, every month, based on the newly collected historical inspection data and the data on changes in the status of facilities, the relevance is re-analyzed, and the model parameters are adjusted. Through continuous feedback and correction, the accuracy of the facility failure probability prediction model is gradually improved, thereby providing a more reliable basis for the inspection and scheduling of municipal facilities. This helps to more reasonably plan inspection tasks, detect potential failures in advance, reduce the adverse effects brought by facility failures, and improve the operation efficiency and reliability of urban municipal facilities.

[0108] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0109] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A municipal facility inspection and scheduling method based on the urban general manager, characterized in that, Including: Obtain the basic information and real-time status data of municipal facilities, structurally process the basic information according to preset attribute dimensions, and generate facility feature data; Construct a spatio-temporal grid coordinate system, divide grid cells based on the urban geographical area, define the X-axis of the spatio-temporal grid coordinate system as the time axis, the Y-axis as the spatial axis, the Z-axis as the facility type axis, and assign dynamic weights to each grid cell; Map the facility feature data into the corresponding spatio-temporal grid coordinate system to generate facility spatio-temporal coordinate information; Based on the preset inspection task requirements, extract the type, geographical location, and priority of the target facilities to be inspected, and generate an initial inspection path; According to the real-time traffic flow data and the facility failure probability prediction model, dynamically adjust the weights of each grid cell in the initial inspection path, and generate an optimized inspection path based on the greedy algorithm; Split the optimized inspection path into multiple inspection subtasks, and allocate the inspection subtasks according to the real-time location and load status of the inspection personnel or equipment; Real-time collect the execution progress data of the inspection subtasks, and combine with the dynamic weights of the spatio-temporal grid coordinate system to re-optimize the paths of the uncompleted inspection subtasks; Send the re-optimized inspection path and task allocation instructions to the corresponding inspection terminals, and receive the inspection result data feedback from the terminals; Update the facility feature data and the dynamic weights of the spatio-temporal grid coordinate system according to the inspection result data.

2. The municipal facility inspection and scheduling method based on the urban butler according to claim 1, characterized in that The preset attribute dimensions include facility type, geographical coordinates, maintenance cycle, and historical failure records.

3. The municipal facility inspection and scheduling method based on the urban butler according to claim 1, characterized in that, The dynamically adjusting the weights of each grid cell in the initial inspection path includes: Obtain the real-time traffic congestion index and weather data, and calculate the travel time cost of each grid cell; Predict the failure probability of each facility based on the facility historical failure records and the machine learning model; Dynamically update the weights of the grid cells according to the product of the travel time cost and the failure probability.

4. The municipal facility inspection and scheduling method based on the urban grand steward according to claim 3, wherein, The machine learning model is an LSTM network based on time series, the input data includes facility operation parameters, environmental data, and historical maintenance records, and the output is the failure probability within a preset future time period.

5. The municipal facility inspection and scheduling method based on the urban butler according to claim 1, characterized in that, The allocating the inspection subtasks includes: Construct a priority scoring matrix according to the skill level, current location, and task urgency of the inspection personnel or equipment; Use the Hungarian algorithm to perform optimal matching on the scoring matrix to determine the allocation result of the inspection subtasks.

6. The municipal facility inspection and scheduling method based on the urban general steward according to claim 1, characterized in that, The method further includes: Cooperatively plan multiple inspection tasks within the same geographical area, and optimize the path intersection points between multiple tasks by introducing the ant colony algorithm to reduce the overlapping inspection areas.

7. The municipal facility inspection and scheduling method based on the urban butler according to claim 1, characterized in that, The method further includes: Construct a multi-objective optimization model, with minimizing the total inspection time, balancing the load distribution, and maximizing the failure coverage rate as the optimization objectives, use the NSGA-II algorithm to solve the Pareto optimal solution set, and select the final inspection plan based on preset rules.

8. The municipal facility inspection and scheduling method based on the urban grand steward according to claim 1, wherein, The method further includes: When a sudden facility failure is detected, interrupt the current inspection path, insert an emergency inspection task based on the spatio-temporal coordinates and priority of the failed facility, and recalculate the optimized path.

9. The municipal facility inspection and scheduling method based on the urban grand steward according to claim 1, characterized in that, The method further includes: Establish an inspection effect feedback strategy, and dynamically correct the parameters of the facility failure probability prediction model according to the relevance between historical inspection data and changes in facility status.

10. A municipal facility inspection and scheduling system based on the urban general manager, which is used to implement the method described in any one of claims 1 to 9, and is characterized in that, It includes: Data acquisition and processing module: used to obtain the basic information and real-time status data of municipal facilities, structurally process the basic information according to preset attribute dimensions, and generate facility feature data; Space-time grid construction module: construct a space-time grid coordinate system, divide grid units based on the urban geographical area, define the X-axis of the space-time grid coordinate system as the time axis, the Y-axis as the space axis, the Z-axis as the facility type axis, and assign dynamic weights to each grid unit; Mapping module: map the facility feature data into the corresponding space-time grid coordinate system to generate facility space-time coordinate information; Initial path generation module: based on preset inspection task requirements, extract the types, geographical locations, and priorities of the inspection target facilities, and generate an initial inspection path; Path optimization module: dynamically adjust the weights of each grid unit in the initial inspection path according to real-time traffic flow data and the facility failure probability prediction model, and generate an optimized inspection path based on the greedy algorithm; Task allocation module: split the optimized inspection path into multiple inspection subtasks, and allocate the inspection subtasks according to the real-time positions and load status of inspection personnel or equipment; Monitoring and re-optimization module: collect the execution progress data of inspection subtasks in real time, and re-optimize the paths of uncompleted inspection subtasks in combination with the dynamic weights of the space-time grid coordinate system; Instruction issuance and feedback reception module: issue the re-optimized inspection path and task allocation instructions to the corresponding inspection terminals, and receive the inspection result data feedback from the terminals; Data update module: update the facility feature data and the dynamic weights of the space-time grid coordinate system according to the inspection result data.

Images