An intelligent sanitation supervision platform and sanitation operation planning method

Abstract

The present invention relates to the technical field of path planning, and in particular to an intelligent sanitation supervision platform and a sanitation operation planning method, comprising: obtaining the conventional operation volume and operation floating volume of each operation node and the current remaining load of a sanitation vehicle; determining the compatibility of the operation volume of each operation node according to the conventional operation volume, operation floating volume and the current remaining load, and determining the visibility and pheromone concentration between each operation node; determining the selection probability of each operation node in combination with the visibility, pheromone concentration and compatibility between each operation node, and determining the selection probability of a rest node closest to the sanitation vehicle; selecting a next node from a set of nodes to be operated and a rest node based on all selection probabilities, and continuously iterating to determine the next node until all routes of the sanitation vehicle at the current iteration are obtained, so that the selection of the next node in the route planning process is more in line with the actual situation of the sanitation operation.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to an intelligent sanitation supervision platform and a sanitation operation planning method. Background Art

[0002] As an important part of modern urban management, the intelligent sanitation supervision platform integrates cutting-edge technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence, and can achieve comprehensive monitoring, reasonable scheduling, and optimized management of sanitation work. The existing intelligent sanitation supervision platform often uses ant colony algorithms to optimize the sanitation operation route planning, but the traditional ant colony algorithm overly relies on the optimal solution under idealized conditions and ignores the dynamic change factors in actual operations. In particular, the existing algorithms usually do not take into account the actual situation that sanitation vehicles may need to rest, refuel, or adjust routes during the operation, resulting in incorrect selection of the next node in the path planning, deviating from the actual situation, and causing the sanitation operation route planning results to deviate from the actual operation situation. Summary of the invention

[0003] In order to solve the technical problem that the next node selection in the existing sanitation operation route planning is incorrect, resulting in a deviation between the sanitation operation route planning result and the actual operation situation, the purpose of the present invention is to provide an intelligent sanitation supervision platform and a sanitation operation planning method, and the technical solutions adopted are as follows:

[0004] An embodiment of the present invention provides a method for planning sanitation operations, the method comprising the following steps:

[0005] Obtaining a historical workload set of each operation node when planning sanitation operations for sanitation vehicles, and determining a regular workload and a floating workload of each operation node based on the historical workload set; obtaining a current remaining load of the sanitation vehicle;

[0006] Determine the compatibility of the current load of the sanitation vehicle with respect to the load of each operation node according to the conventional operation volume and operation floating volume of each operation node and the current remaining load; determine the visibility and pheromone concentration between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated;

[0007] Determine the selection probability of each operating node in the set of nodes to be operated by combining the visibility, pheromone concentration and the compatibility between the current operating node where the sanitation vehicle is located and each operating node in the set of nodes to be operated; wherein the selection probability is the possibility of selecting the operating node as the next node;

[0008] According to the minimum value of the current remaining load of the sanitation vehicle and the regular operating volume of all operating nodes, the selection probability of the rest node closest to the sanitation vehicle is determined; based on all the selection probabilities, the next node is selected from the set of nodes to be operated and the rest nodes, and the next node is determined iteratively until all routes of the sanitation vehicle in the current iteration are obtained.

[0009] Further, the determining of the regular workload and the floating workload of each operation node based on the historical workload set includes:

[0010] For any operation node, the average value of all historical operation volumes in the historical operation volume set of the operation node is calculated to obtain the normal operation volume of the operation node;

[0011] The fluctuation of all historical workloads in the historical workload set of the workload node is analyzed to determine the workload floating amount of the workload node.

[0012] Furthermore, the determining of the compatibility of the current load of the sanitation vehicle with respect to the operation volume of each operation node according to the conventional operation volume and the operation floating volume of each operation node and the current remaining load includes:

[0013] Get the regular workload and workload floating amount of each job node in the set of nodes to be worked on;

[0014] For any operation node in the set of nodes to be operated, the operation volume fluctuation degree of the operation node is determined according to the regular operation volume and operation floating volume of the operation node;

[0015] The difference between the current remaining load and the normal operation volume of the operation node is calculated as a first difference, and the value after the operation floating amount is added to the preset constant is calculated as a sum;

[0016] Determine the compatibility of the current load of the sanitation vehicle with respect to the load of the operating nodes in the set of nodes to be operated, based on the degree of fluctuation of the operating load, the first difference and the sum;

[0017] The workload fluctuation degree and the sum value are negatively correlated with the compatibility degree, and the first difference value is positively correlated with the compatibility degree.

[0018] Further, determining the degree of fluctuation of the workload of the operation node according to the normal workload and the floating workload of the operation node includes:

[0019] The ratio of the floating amount of the operation to the regular amount of the operation is calculated, and the square of the ratio is obtained to obtain the degree of fluctuation of the amount of the operation node.

[0020] Furthermore, the determining of the visibility and pheromone concentration between the current operating node where the sanitation vehicle is located and each operating node in the set of nodes to be operated includes:

[0021] Acquire the actual position of the current working node and each working node in the set of nodes to be worked on, and determine the travel distance between the current working node and each working node in the set of nodes to be worked on based on the actual position;

[0022] Determine the visibility between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated according to the travel distance; wherein the travel distance is negatively correlated with the visibility;

[0023] The pheromone concentration matrix of the current iteration is obtained, and the pheromone concentration between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated is determined according to the pheromone concentration matrix.

[0024] Furthermore, an initial pheromone concentration matrix is ​​obtained, including:

[0025] Obtain the travel distance between every two operation nodes, and then construct a travel distance matrix; based on the travel distance matrix, obtain the shortest path through a greedy algorithm;

[0026] The number of ants is set to a preset number, and the ratio of the preset number to the shortest path is used as the initial pheromone, so as to obtain an initial pheromone matrix.

[0027] Furthermore, the selection probability of each operating node in the set of nodes to be operated is determined by combining the visibility, pheromone concentration and the compatibility between the current operating node where the sanitation vehicle is located and each operating node in the set of nodes to be operated, including:

[0028] Setting the weight of the visibility, the weight of the pheromone concentration, and the weight of the compatibility degree;

[0029] For any job node in the set of nodes to be operated, the visibility between the current job node and the job node in the set of nodes to be operated, the weight of the visibility, the pheromone concentration, the weight of the pheromone concentration, the compatibility degree and the weight of the compatibility degree are multiplied, the obtained product is normalized, and the normalized product is used as the selection probability of the job node in the set of nodes to be operated.

[0030] Furthermore, the method of determining the selection probability of the rest node closest to the sanitation vehicle according to the minimum value between the current remaining load of the sanitation vehicle and the conventional operation volume of all operation nodes includes:

[0031] Calculate the difference between the current remaining load and the minimum value as a second difference;

[0032] The second difference is subjected to negative correlation normalization processing to obtain the selection probability of the rest node closest to the sanitation vehicle.

[0033] Furthermore, after obtaining all routes of the sanitation vehicle at the current iteration, the method further includes:

[0034] Obtaining the total length of each route, and determining the amount of pheromone change on each route based on the total length; wherein the total length is negatively correlated with the amount of pheromone change;

[0035] For every two working nodes, the pheromone increment of every two working nodes on each route is determined according to the positional relationship of every two working nodes relative to each route and the pheromone change on each route;

[0036] The pheromone concentration of every two operating nodes in the next iteration is determined according to the pheromone concentration of every two operating nodes in the current iteration, the pheromone increment on each route, and the preset pheromone evaporation rate.

[0037] Another embodiment of the present invention provides an intelligent sanitation supervision platform, including a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement the sanitation operation planning method.

[0038] The present invention has the following beneficial effects:

[0039] The present invention provides an intelligent sanitation supervision platform and a sanitation operation planning method. The method uses big data analysis technology to conduct in-depth mining and analysis of the collected data, and can provide decision support for managers. Specifically, the traditional ant colony algorithm used in the field of sanitation operation planning is improved by combining the historical operation volume set of each operation node and the current remaining load of the sanitation vehicle, so that the ant colony algorithm is more suitable for the actual sanitation operation situation, that is, the sanitation vehicle operation planning result finally obtained by the ant colony algorithm is more in line with the actual operation situation, so as to improve the operational efficiency of the sanitation operation; the conventional operation volume and the operation floating volume are calculated by the historical operation volume set of each operation node, and the operation floating volume of each operation node can be quantified. The fluctuation degree of the operating volume of the business node is helpful to determine the compatibility of the current load of the sanitation vehicle with the operating volume of each operation node in the future; the compatibility determined by multiple calculation factors such as the conventional operating volume, the operating floating volume and the current remaining load can reduce the secondary operation caused by the operation planning ignoring the real-time situation of the load, and to a certain extent avoid the unnecessary workload of sanitation vehicles; when analyzing the selection probability, not only the influence of the vehicle load factor is taken into account, but also the possibility that the sanitation vehicle needs to rest, which makes the selection of the next node more in line with the actual situation of sanitation operations, optimizes the operation route, and facilitates a more reasonable allocation of sanitation resources and improves resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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 these drawings without paying creative work.

[0041] Figure 1 A flowchart of a method for planning sanitation operations according to an embodiment of the present invention;

[0042] Figure 2 is a flowchart of step S21 in an embodiment of the present invention;

[0043] Figure 3 4 is a flowchart of step S41 in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0045] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0046] The application scenarios targeted by the present invention may be:

[0047] When using the traditional ant colony algorithm to plan the operation route of sanitation vehicles, the paths of different operation nodes are usually taken into account to optimize the operation path. However, when sanitation vehicles are operating, they need to consider not only the shortest path of the theoretical route, but also the actual operation progress and process of the sanitation vehicles. If the sanitation vehicle is a sprinkler truck, the remaining water in the water tank needs to be considered. If the sanitation vehicle is a garbage truck, the loading condition of the vehicle needs to be considered. When the carrying capacity of the sanitation vehicle is not enough to continue working, it needs to drive to a nearby rest point for rest before operating. This will cause a large deviation between the actual operation situation and the theoretical route, and the theoretically planned route cannot adapt well to the actual operation situation.

[0048] In view of the above situation, the present invention combines the real-time loading situation of sanitation vehicles and the workload changes of different operation nodes to make targeted improvements to the ant colony algorithm, so that the planned operation route is more suitable for the actual operation situation, thereby improving the actual operation efficiency of sanitation vehicles and avoiding the same operation node from performing secondary operations due to the influence of the sanitation vehicle loading factor. As a specific implementation method, taking any sanitation vehicle as an example, the optimal sanitation route of the sanitation vehicle is determined.

[0049] An embodiment of the present invention provides a method for planning sanitation operations, such as Figure 1 As shown, the following steps are included:

[0050] S1, obtaining the historical workload set of each operation node when planning sanitation operations for sanitation vehicles, determining the regular workload and operation floating volume of each operation node based on the historical workload set; obtaining the current remaining load of the sanitation vehicle.

[0051] The above step S1 can be implemented through steps S11 to S13 (not shown in the figure):

[0052] S11, obtaining a historical operation volume set of each operation node when planning sanitation operations for sanitation vehicles.

[0053] The smart sanitation platform can collect and integrate data through the Internet of Things and sensors.

[0054] Specifically, the operation nodes and rest nodes of sanitation vehicles are obtained through GIS (Geographic Information System) technology and prior information. The operation node is the task location, and the rest node is the rest location; the historical workload set of sanitation vehicles at each operation node is obtained through the intelligent sanitation platform. Among them, the historical workload set contains the historical workload in the past month. The historical workload is equal to the absolute value of the difference between the load of the sanitation vehicle before the operation node and the load of the sanitation vehicle after the operation. The sanitation vehicle can be a sprinkler truck or a garbage truck. The number of historical workloads in the historical workload set can be set by the implementer according to the specific actual situation, without specific limitation. The number of historical workloads in the historical workload set of each operation node is equal.

[0055] S12, determining the regular workload and the floating workload of each job node based on the historical workload set.

[0056] For any operation node, step S12 may determine the normal operation amount and operation floating amount of the operation node through steps S121 to S122 (not shown in the figure):

[0057] S121, calculating the average value of all historical workloads in the historical workload set of the operation node to obtain the regular workload of the operation node.

[0058] Here, the regular workload refers to the average workload that the job node needs to process in the current month.

[0059] S122, analyzing the fluctuation of all historical workloads in the historical workload set of the workload node, and determining the workload floating amount of the workload node.

[0060] Here, job fluctuation refers to the change in the workload processed by the job node in the current month.

[0061] As an example, the standard deviation of all historical workloads in the historical workload set of the job node is calculated, and the standard deviation is used as the job floating amount of the job node.

[0062] In another example, the variance of all historical workloads in the historical workload set of the job node is calculated, and the variance is used as the job floating amount of the job node.

[0063] S13, obtaining the current remaining load of the sanitation vehicle.

[0064] Specifically, the current load of the sanitation vehicle is collected in real time through cameras and sensors. If the sanitation vehicle is a garbage truck, the difference between the full load and the current load of the sanitation vehicle is used as the current remaining load; if the sanitation vehicle is a sprinkler truck, the current load of the sanitation vehicle is directly used as the current remaining load for subsequent calculations. The reason is that the load of sanitation vehicles such as sprinkler trucks increases with the progress of the operation, while the load of sanitation vehicles such as garbage trucks decreases with the progress of the operation.

[0065] So far, this embodiment obtains the historical operation volume set to determine the regular operation volume and operation floating volume of each operation node, as well as the current remaining load of the sanitation vehicle.

[0066] S2, based on the regular operating volume, operating floating volume and current remaining load of each operating node, determine the compatibility of the current load of the sanitation vehicle with the operating volume of each operating node; determine the visibility and pheromone concentration between the current operating node where the sanitation vehicle is located and each operating node in the set of nodes to be operated.

[0067] The compatibility degree, visibility and pheromone concentration are determined to facilitate the subsequent adaptive determination of the selection probability of each operating node in the set of nodes to be operated. The set of nodes to be operated here refers to the operating nodes that have not been visited yet. By improving the calculation method of the selection probability, the optimization of the ant colony algorithm can be achieved to avoid performing secondary operations and increasing the workload due to ignoring the real-time vehicle load of sanitation vehicles.

[0068] When optimizing the ant colony algorithm to adapt it to the actual situation of sanitation operations, the loading problem of sanitation vehicles needs to be considered on the basis of analyzing the original visibility and pheromone concentration factors, that is, quantifying the compatibility of the current loading capacity of the sanitation vehicle with the operating capacity of each operating node. If the current loading capacity of the sanitation vehicle is similar to the operating capacity of the operating node, it means that the priority of the operating node is also higher when analyzing only the loading capacity.

[0069] The above step S2 can be implemented through steps S21 to S22 (not shown in the figure):

[0070] S21, determining the compatibility of the current load of the sanitation vehicle with respect to the operation volume of each operation node according to the regular operation volume and operation floating volume of each operation node and the current remaining load.

[0071] Here, the degree of compatibility refers to the possibility that the sanitation vehicle can handle all the workload of the operation node at one time based on the current load analysis. The greater the degree of compatibility, the greater the possibility that the sanitation vehicle can handle all the workload of the operation node at one time, which can effectively avoid secondary operations and increase workload.

[0072] The stronger the operation volatility of a certain operation node in the set of nodes to be operated, the more unstable the operation volume of the operation node is, and the greater the difference between the actual operation volume of the operation node and the regular operation volume is. At this time, when the current remaining load of the sanitation vehicle is smaller, the compatibility of the current load of the sanitation vehicle with the operation volume of the operation node is worse, the possibility of performing secondary work is higher, and the possibility of increasing the workload is also higher.

[0073] For any operating node in the set of nodes to be operated, the above step S21 can be performed by Figure 2 The steps S211 to S214 shown implement:

[0074] S211, obtaining the regular operation amount and operation floating amount of the operation nodes in the set of nodes to be operated.

[0075] S212: Determine the degree of fluctuation of the workload of the operation node according to the regular workload and the floating workload of the operation node.

[0076] In this embodiment, the degree of fluctuation of the workload can be determined by analyzing the fluctuation relative to the normal workload.

[0077] As an example, the ratio of the floating amount of the job to the regular amount of the job is calculated, and the square of the ratio is taken to obtain the degree of fluctuation of the amount of the job node. The calculation formula can be:

[0078] ; In the formula, Indicates the degree of fluctuation of the workload of the i-th job node, represents the job floating amount of the i-th job node, i represents the i-th job node, It represents the regular workload of the i-th job node. Under normal circumstances, the regular workload of any job node cannot be zero.

[0079] S213, calculating the difference between the current remaining load and the normal operation volume of the operation node as a first difference, and calculating the sum of the operation floating amount and a preset constant as a sum.

[0080] S214, combining the degree of fluctuation of the workload, the first difference and the sum, determining the degree of compatibility of the current load of the sanitation vehicle with the workload of the operating nodes in the set of nodes to be operated.

[0081] In this embodiment, the workload fluctuation degree and the sum are negatively correlated with the compatibility degree, while the first difference is positively correlated with the compatibility degree.

[0082] As an example, the calculation formula for the compatibility of the current load of the sanitation vehicle with the operation volume of the i-th operation node in the set of nodes to be operated can be:

[0083] ; In the formula, It indicates the compatibility of the current load of the sanitation vehicle with the work load of the i-th work node in the set of work nodes to be worked on. r is used to distinguish the work nodes in the set of work nodes to be worked on. Norm indicates the linear normalization function. Indicates the current remaining load of the sanitation vehicle. Indicates the regular workload of the i-th job node in the set of nodes to be worked on. represents the first difference, It represents the floating workload of the i-th job node in the set of nodes to be worked on. Indicates the workload fluctuation degree of the i-th job node, 0.01 represents the preset constant, Represents and value.

[0084] In the calculation formula of the degree of compatibility, the larger the first difference is, the larger the difference between the current remaining load of the sanitation vehicle and the regular load of the operation node is, the more it can be said that the sanitation vehicle can complete the operation of the operation node, and the stronger the compatibility of the current load of the sanitation vehicle with respect to the operation of the operation node in the set of nodes to be operated is; the larger the sum is, the larger the operation fluctuation of the operation node is, which means that the operation volume of the operation node changes more, then the difference between the regular operation volume and the actual operation volume of the operation node at this time may be greater, the credibility of the first difference calculation is worse, and then the numerical accuracy of the compatibility is also affected; the preset constant can be set to 0.01, which is used to avoid the possibility of the operation fluctuation being zero, and the implementer can also set it to other numerical sizes without limitation; the greater the degree of fluctuation of the operation volume is, the greater the degree of fluctuation relative to the regular operation volume, the worse the stability of the operation volume of the operation node, and the worse the compatibility of the current load of the sanitation vehicle with the operation volume of the operation point is, then the more likely it is to perform secondary operations, so that the workload of sanitation operations is increased.

[0085] S22, determining the visibility and pheromone concentration between the current operating node where the sanitation vehicle is located and each operating node in the set of nodes to be operated.

[0086] Here, the current operating node of the sanitation vehicle can be the starting node or any operating node in the sanitation planning process; visibility can represent heuristic information, which helps to accelerate convergence and can be used to judge the quality of the path; and pheromone concentration can reflect the superiority of the path. Both are key factors in determining the subsequent selection probability.

[0087] The above step S22 can be implemented through steps S221 to S223 (not shown in the figure):

[0088] S221, obtaining the actual position of the current working node and each working node in the set of nodes to be worked on, and determining the travel distance between the current working node and each working node in the set of nodes to be worked on based on the actual position.

[0089] In this embodiment, the current position of the sanitation vehicle can be obtained by using GPS (Global Positioning System) technology, and compared with the actual position of each operating node in the set of nodes to be operated. Then, GIS technology is used to determine the travel distance between the current operating node and each operating node in the set of nodes to be operated, and the communication distance is used to facilitate the subsequent determination of visibility.

[0090] S222, determining the visibility between the current operating node where the sanitation vehicle is located and each operating node in the set of nodes to be operated according to the travel distance.

[0091] In this embodiment, the communication distance is negatively correlated with the visibility, that is, the longer the communication distance is, the lower the visibility between the two operating nodes is.

[0092] As an example, the calculation formula for the visibility between the current working node and the i-th working node in the set of nodes to be worked on can be:

[0093] ; In the formula, Indicates the visibility between the current job node and the i-th job node in the set of nodes to be worked on. Represents the communication distance between the current job node and the i-th job node in the set of nodes to be worked on.

[0094] In the visibility calculation formula, only the communication distance of the same working node has a value equal to 0, and the working nodes in the set of nodes to be worked on are nodes that have not been visited yet, so the communication distance between the current working node and each working node in the set of nodes to be worked on does not have a value equal to zero.

[0095] S223, obtaining the pheromone concentration matrix of the current iteration, and determining the pheromone concentration between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated according to the pheromone concentration matrix.

[0096] If the current iteration is the first iteration process, the initial pheromone concentration matrix can be obtained. The steps of setting the initial pheromone include: first, obtaining the travel distance between each two operation nodes, and then constructing the travel distance matrix; based on the travel distance matrix, the shortest path is obtained through the greedy algorithm. Then, the number of ants is set to a preset number, and the ratio of the preset number and the shortest path is used as the initial pheromone, thereby obtaining the initial pheromone matrix.

[0097] In this embodiment, the number of ants refers to the number of ants participating in pathfinding in each iteration, and the number of ants can be set to 100. Initially, the pheromones on all paths are usually set to be the same, but the calculation formula for the initial pheromone in this embodiment can be: , where represents the initial pheromone, m represents the number of ants, Represents the shortest path. Based on the communication distance between every two working nodes, all initial pheromones are obtained, and the matrix of all initial pheromones is obtained as the initial pheromone matrix. Among them, the implementation process of the greedy algorithm is a prior art, which is not within the protection scope of the present invention and will not be elaborated here.

[0098] So far, this embodiment has obtained all the factor indicators that affect the operation path of the sanitation vehicle as much as possible, namely visibility, pheromone concentration and compatibility, which is helpful for the subsequent determination of the selection probability of the operation node with higher numerical accuracy.

[0099] S3, combining the visibility, pheromone concentration and compatibility between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated, determines the selection probability of each operation node in the set of nodes to be operated.

[0100] Here, the selection probability refers to the probability that after completing the workload of the current operation node where the sanitation vehicle is located, the subsequent sanitation vehicle will travel to a certain operation node in the set of nodes to be operated to perform the operation again. The greater the probability, the greater the possibility of selecting the operation node in the set of nodes to be operated as the next node.

[0101] The above step S3 can be implemented by the following steps:

[0102] Set the weight of visibility, the weight of pheromone concentration and the weight of compatibility; for any job node in the set of nodes to be worked on, multiply the visibility, the weight of visibility, the pheromone concentration, the weight of pheromone concentration, the compatibility and the weight of the compatibility between the current job node and the job nodes in the set of nodes to be worked on, normalize the obtained product, and use the normalized product as the selection probability of the job node in the set of nodes to be worked on.

[0103] In this embodiment, when calculating the selection probability, different calculation factors have different importance, so it is necessary to set corresponding weights for visibility, pheromone concentration and compatibility. Here, the weight of pheromone concentration is set to 1, and the weights of visibility and compatibility are set to 2, which can amplify the impact of visibility and compatibility on the selection probability, so that the selection of the next node is more focused on the actual operation of the sanitation vehicle.

[0104] As an example, the calculation formula for the selection probability of the i-th operation node in the set of nodes to be operated can be:

[0105] ; In the formula, represents the selection probability of the i-th job node in the set of nodes to be worked on, represents the weight of pheromone concentration, represents the pheromone concentration between the current operation node where the sanitation vehicle is located and the i-th operation node in the set of nodes to be operated. represents the weight of visibility, It represents the visibility between the current operation node where the sanitation vehicle is located and the i-th operation node in the set of nodes to be operated. The weight representing the degree of compatibility, It indicates the compatibility of the current load of the sanitation vehicle with the operating capacity of the i-th operating node in the set of nodes to be operated, and Norm indicates the linear normalization function.

[0106] In the calculation formula of the selection probability, visibility, pheromone concentration and compatibility are all positively correlated with the selection probability. That is, the higher the compatibility of pheromone concentration, visibility and workload between the current operation node where the sanitation vehicle is located and the i-th operation node in the set of nodes to be operated, the greater the possibility that the i-th operation node will be selected as the next node of the current operation node.

[0107] It should be noted that the selection probability takes into account the current loading situation of the operating vehicle, that is, the quantification process of the selection probability integrates the compatibility of the operating volume, which can effectively improve the selection reliability of the next node and optimize the selection process of the next node of the ant colony algorithm. It can avoid secondary operations caused by improper selection of the next node, increase additional workload, and make the operating efficiency of sanitation vehicles low.

[0108] So far, relative to the current working node where the working vehicle is located, this embodiment obtains the selection probability of each working node in the set of nodes to be worked on.

[0109] S4, according to the minimum value of the current remaining load of the sanitation vehicle and the regular operation volume of all operation nodes, determine the selection probability of the rest node closest to the sanitation vehicle; based on all selection probabilities, select the next node from the set of nodes to be operated and the rest nodes, and continuously iterate to determine the next node until all routes of the sanitation vehicle in the current iteration are obtained.

[0110] Here, for the garbage truck, the rest node is the place used to process the garbage that has reached full load on the sanitation vehicle, and for the sprinkler truck, the rest node is the place for the sanitation vehicle to refill water. In addition, there is a possibility that the next node of the current operating node where the sanitation vehicle is located is a rest node, and the selection probability of the rest node needs to be added to the candidate sequence of the next node.

[0111] The above step S4 can be implemented through steps S41 to S42 (not shown in the figure):

[0112] S41, determining the selection probability of the rest node closest to the sanitation vehicle according to the minimum value between the current remaining load of the sanitation vehicle and the regular work load of all work nodes.

[0113] In this embodiment, when the current remaining load of the sanitation vehicle is greater than the regular operating volume, it means that the possibility of the sanitation vehicle continuing to operate is greater, and the possibility that the next node of the sanitation vehicle is a rest node is smaller. On the contrary, when the current remaining load of the sanitation vehicle is not enough to continue the operation, the possibility that the next node of the sanitation vehicle is a rest node will be greater.

[0114] The above step S41 can be performed by Figure 3 The steps S411 to S412 shown implement:

[0115] S411, calculating the difference between the current remaining load and the minimum value as a second difference.

[0116] S412, performing negative correlation normalization processing on the second difference to obtain the selection probability of the rest node closest to the sanitation vehicle.

[0117] As an example, the calculation formula for the selection probability of the rest node closest to the sanitation vehicle can be:

[0118] ; In the formula, represents the probability of selecting the rest node closest to the sanitation vehicle, exp represents an exponential function with a natural constant as the base, Indicates the current remaining load of the sanitation vehicle. Indicates the regular workload of the i-th job node in the set of nodes to be worked on. Indicates the minimum value of the regular workload of all job nodes in the set of job-to-be-job nodes. Represents the second difference.

[0119] In the calculation formula of the selection probability of the rest node, The smaller it is, the less likely the sanitation vehicle is to continue working at the next node, and the greater the possibility of needing to rest. Therefore, the probability of selecting the rest node closest to the sanitation vehicle is also greater. exp(-) can achieve normalization of the negative correlation of the data. Of course, implementers can also use other methods to achieve normalization of the negative correlation of the data, which is not specifically limited here.

[0120] S42, selecting the next node from the set of nodes to be operated and the rest nodes based on all selection probabilities, and continuously iterating to determine the next node until all routes of the sanitation vehicle in the current iteration are obtained.

[0121] In this embodiment, after obtaining the selection probability of each working node in the set of nodes to be worked and the selection probability of the rest node closest to the sanitation vehicle, the maximum value is selected from all the selection probabilities, and the working node or rest node corresponding to the maximum value is used as the next node of the sanitation vehicle, and the above step S1 is repeated to obtain the current remaining load of the working vehicle and steps S2 to S4, and the next node of the current node is determined iteratively. The driving route of an ant can be obtained, and then m ants can be calculated according to the above driving route calculation method to obtain m routes, that is, all routes of the sanitation vehicle in the current iteration are obtained.

[0122] So far, this embodiment has obtained all routes of the sanitation vehicle in the current iteration.

[0123] S5, according to the total length of all routes in the current iteration, determine the pheromone concentration matrix in the next iteration; set the iteration number threshold, when the iteration number reaches the iteration number threshold, obtain the optimal sanitation route, and push the optimal sanitation route to the sanitation vehicle.

[0124] In this embodiment, after obtaining all the routes of the sanitation vehicle in the current iteration, during the implementation of the ant colony algorithm, it is necessary to update the pheromone concentration matrix of the current iteration to obtain the pheromone concentration matrix of the next iteration of the current iteration, and then determine all the routes of the sanitation vehicle in the next iteration until the number of iterations reaches the set threshold. At this time, the route with the shortest total distance can be selected from all the routes in the last iteration as the optimal sanitation route, and the optimal sanitation route is pushed to the sanitation vehicle. Among them, the iteration number threshold can be set to 100, and the implementer can set the size of the iteration number threshold according to the specific actual situation without specific limitation.

[0125] As an example, according to the total length of all routes in the current iteration, the pheromone concentration matrix in the next iteration is determined, as shown in steps S51 to S53 (not shown in the figure), including:

[0126] S51, obtaining the total distance of each route, and determining the pheromone change amount on each route based on the total distance.

[0127] In this embodiment, for the mth route, the total distance of the mth route is obtained. Since the total distance length is negatively correlated with the pheromone change, the calculation formula for the pheromone change on the mth route can be:

[0128] ; In the formula, represents the change in pheromone on the mth route, Represents the total length of the mth route.

[0129] In the calculation formula of the pheromone change, the total distance of each route every day has no possibility of being zero, so There is no possibility of zero. It should be noted that when the total distance of the route is large, the pheromone evaporates faster, resulting in a lower concentration, which reduces the pheromone change on these paths. In addition, the long path is less attractive, and ants tend to choose shorter paths when choosing a path, which makes the pheromone change on the long path smaller.

[0130] S52, for every two operating nodes, according to the positional relationship between the two operating nodes and each route and the pheromone change amount on each route, determine the pheromone increment of every two operating nodes on each route.

[0131] In this embodiment, for any two job nodes and , when there are these two working nodes on any route, that is, and , and The pheromone increment on the route is equal to the pheromone change on the route; on the contrary, when there is no pheromone on any route, and hour, and The pheromone increment on this route is equal to zero.

[0132] S53, determining the pheromone concentration of every two operating nodes in the next iteration according to the pheromone concentration of every two operating nodes in the current iteration, the pheromone increment on each route, and the preset pheromone evaporation rate.

[0133] In this embodiment, for two job nodes and , the calculation formula for the pheromone concentration in the next iteration can be:

[0134] ; In the formula, Represents a job node and The pheromone concentration at the next iteration, represents the preset pheromone evaporation rate, m represents the number of ants, and also represents the number of routes, h represents the hth route, Represents a job node and The pheromone increment on the hth route, express and The pheromone concentration at this iteration (the current iteration).

[0135] In the calculation formula of pheromone concentration, the pheromone evaporation rate can be set to 0.5. The implementer can set the pheromone evaporation rate according to the actual situation without specific restrictions; refer to the operation node and The pheromone concentration at the next iteration is calculated by calculating the pheromone concentration of every two job nodes at the next iteration and completing the replacement, that is, completing one iteration of the pheromone concentration matrix.

[0136] Another embodiment of the present invention provides an intelligent sanitation supervision platform, including a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement the sanitation operation planning method.

[0137] The main functions of the intelligent sanitation supervision platform of this embodiment include: data integration, data analysis and planning. In terms of data integration, the platform realizes real-time connection and data collection through the Internet of Things technology, which helps to improve operational efficiency and realize intelligent management; in the field of data analysis, the platform uses big data analysis technology to conduct in-depth mining and analysis of the collected data, extract valuable information and rules, and provide decision-making support for managers; as for planning, the intelligent sanitation supervision platform that applies the sanitation operation planning method can optimize the cleaning routes and garbage removal processes through the intelligent scheduling system, which helps to reduce costs and realize efficient operations.

[0138] In summary, the present invention proposes an ant colony algorithm optimization method based on historical sanitation operation data and real-time parameters of sanitation vehicles. By introducing historical sanitation operation data, a more targeted reference can be provided for the algorithm, and regular characteristics in the operation process can be identified, thereby optimizing path planning. At the same time, real-time vehicle parameters are also fed back to the algorithm in real time to ensure that the system can flexibly adjust the path in the face of emergencies, avoid unnecessary secondary operations, and thus optimize the annual workload of sanitation vehicles. By optimizing the ant colony algorithm, not only can the efficiency of sanitation operations be improved, but also the fuel consumption of sanitation vehicles can be reduced, and resource waste can be reduced. At the same time, the flexibility and real-time performance of the sanitation supervision platform have been improved, and the operation path can be adjusted in time according to real-time changes to adapt to complex actual environments. In actual applications, it can better balance the operating efficiency and vehicle rest needs, and improve the overall sanitation operation efficiency and the operation management level of sanitation vehicles.

[0139] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A sanitation operation planning method, characterized in that: The following steps are involved: Obtaining a historical workload set of each operation node when planning sanitation operations for sanitation vehicles, and determining a regular workload and a floating workload of each operation node based on the historical workload set; obtaining a current remaining load of the sanitation vehicle; Determine the compatibility of the current load of the sanitation vehicle with respect to the load of each operation node according to the conventional operation load and the operation floating load of each operation node and the current remaining load; Determine the visibility and pheromone concentration between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated; Determine the selection probability of each operating node in the set of nodes to be operated by combining the visibility, pheromone concentration and the compatibility between the current operating node where the sanitation vehicle is located and each operating node in the set of nodes to be operated; wherein the selection probability is the possibility of selecting the operating node as the next node; According to the minimum value of the current remaining load of the sanitation vehicle and the regular operation volume of all operation nodes, the selection probability of the rest node closest to the sanitation vehicle is determined; based on all the selection probabilities, the next node is selected from the set of nodes to be operated and the rest nodes, and the next node is determined iteratively until all routes of the sanitation vehicle at the current iteration are obtained; The determining, based on the conventional operation volume and operation floating volume of each operation node and the current remaining load volume, the compatibility degree of the current load volume of the sanitation vehicle with respect to the operation volume of each operation node comprises: Get the regular workload and workload floating amount of each job node in the set of nodes to be worked on; For any operation node in the set of nodes to be operated, the operation volume fluctuation degree of the operation node is determined according to the regular operation volume and operation floating volume of the operation node; The difference between the current remaining load and the normal operation volume of the operation node is calculated as a first difference, and the value obtained by adding the operation floating amount to a preset constant is calculated as a sum; Determine the compatibility of the current load of the sanitation vehicle with respect to the load of the operating nodes in the set of nodes to be operated, based on the degree of fluctuation of the operating load, the first difference and the sum; The workload fluctuation degree, the sum value and the compatibility degree are negatively correlated, and the first difference value and the compatibility degree are positively correlated; The determining of the visibility between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated includes: Acquire the actual position of the current working node and each working node in the set of nodes to be worked on, and determine the travel distance between the current working node and each working node in the set of nodes to be worked on based on the actual position; The visibility between the current operating node where the sanitation vehicle is located and each operating node in the set of nodes to be operated is determined according to the travel distance; wherein the travel distance is negatively correlated with the visibility.

2. The sanitation operation planning method according to claim 1, characterized in that: The determining of the regular workload and the floating workload of each operation node based on the historical workload set includes: For any operation node, the average value of all historical operation volumes in the historical operation volume set of the operation node is calculated to obtain the normal operation volume of the operation node; The fluctuation of all historical workloads in the historical workload set of the workload node is analyzed to determine the workload floating amount of the workload node.

3. The sanitation operation planning method according to claim 1, characterized in that: The determining of the degree of fluctuation of the workload of the operation node according to the normal workload and the floating workload of the operation node includes: The ratio of the floating amount of the operation to the regular amount of the operation is calculated, and the square of the ratio is obtained to obtain the degree of fluctuation of the amount of the operation node.

4. The sanitation operation planning method according to claim 1, characterized in that: Determine the pheromone concentration between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated, including: The pheromone concentration matrix of the current iteration is obtained, and the pheromone concentration between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated is determined according to the pheromone concentration matrix.

5. The sanitation operation planning method according to claim 4, characterized in that: Get the initial pheromone concentration matrix, including: Obtain the travel distance between every two operation nodes, and then construct a travel distance matrix; based on the travel distance matrix, obtain the shortest path through a greedy algorithm; The number of ants is set to a preset number, and the ratio of the preset number to the shortest path is used as the initial pheromone, so as to obtain an initial pheromone matrix.

6. The sanitation operation planning method according to claim 1, characterized in that: The step of combining the visibility, pheromone concentration, and compatibility between the current operation node where the sanitation vehicle is located and each operation node in the set of nodes to be operated to determine the selection probability of each operation node in the set of nodes to be operated includes: Setting the weight of the visibility, the weight of the pheromone concentration, and the weight of the compatibility degree; For any job node in the set of nodes to be operated, the visibility between the current job node and the job node in the set of nodes to be operated, the weight of the visibility, the pheromone concentration, the weight of the pheromone concentration, the compatibility degree and the weight of the compatibility degree are multiplied, the obtained product is normalized, and the normalized product is used as the selection probability of the job node in the set of nodes to be operated.

7. The sanitation operation planning method according to claim 1, characterized in that: The method of determining the selection probability of the rest node closest to the sanitation vehicle according to the minimum value of the current remaining load of the sanitation vehicle and the conventional operation volume of all operation nodes includes: Calculate the difference between the current remaining load and the minimum value as a second difference; The second difference is subjected to negative correlation normalization processing to obtain the selection probability of the rest node closest to the sanitation vehicle.

8. The sanitation operation planning method according to claim 1, characterized in that: After obtaining all the routes of the sanitation vehicles in the current iteration, it also includes: Obtaining the total length of each route, and determining the amount of pheromone change on each route based on the total length; wherein the total length is negatively correlated with the amount of pheromone change; For every two working nodes, the pheromone increment of every two working nodes on each route is determined according to the positional relationship of every two working nodes relative to each route and the pheromone change on each route; The pheromone concentration of every two operating nodes in the next iteration is determined according to the pheromone concentration of every two operating nodes in the current iteration, the pheromone increment on each route, and the preset pheromone evaporation rate.

9. An intelligent sanitation supervision platform, characterized in that: It comprises a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement the sanitation operation planning method as described in any one of claims 1-8.

Images