A method, device and medium for sanitation garbage collection and dispatching based on hierarchical clustering

Abstract

The present invention discloses a method, device and medium for dispatching sanitation garbage collection based on hierarchical clustering, the method comprising: obtaining location information of garbage sites, initially allocating garbage sites according to the location information; determining initial clusters according to the results of the initial allocation; performing a first calculation according to the initial clusters, determining the labeling type of the first target garbage site according to the results of the first calculation, the labeling type including excess type, shortage type and reasonable type; determining the second target garbage site according to the labeling type of the first target site, and reallocating the second target garbage site; determining the second cluster according to the results of the reallocation, hierarchically clustering garbage collection points according to the second clusters, and determining the third cluster; and performing path planning according to the third cluster. The present invention can break the limitations of sanitation operations in area planning, realize balanced distribution of garbage volume and optimization of garbage collection and transportation paths, and can be widely used in the field of sanitation garbage treatment technology.

Description

Technical Field

[0001] The present invention relates to the technical field of sanitation garbage treatment, and in particular to a sanitation garbage removal and dispatching method, device and medium based on hierarchical clustering. Background Art

[0002] With the improvement of the living standards of Chinese residents and the acceleration of urbanization, the amount of urban domestic waste has also shown a rapid growth trend. The sharp increase in domestic waste has brought great challenges to the urban environment and waste treatment. Scientific and reasonable treatment and disposal of domestic waste is an urgent need at present. The treatment and disposal of domestic waste have to consider one issue - the operating cost of waste treatment. The collection, transportation and storage of urban domestic waste account for 60%-80% of the total cost of urban domestic waste management. Garbage collection and transportation is an important link in the waste treatment system. Among the many factors that affect the cost of transportation, the most important factors are the constraints of the existing operation plan, the geographical layout of the sanitation components involved in the garbage collection process, and the vehicle dispatch strategy.

[0003] At present, in sanitation operations, garbage collection and transportation is mainly carried out in a zoned manner. Each zone is actually operated independently. This zoned operation scheme has the following problems: the zoned operation limits the garbage collection and transportation process. The garbage collected and transported in a certain street in a certain zone can only be compressed and processed at the garbage transfer station in this street in this zone, and then transported to the terminal disposal plant specified in the zone for final disposal. The boundary constraints between zones and between streets lead to high operating costs. At the same time, since the zone specifies the terminal disposal plant that can be transported, each plant has formed a corresponding quota indicator for the amount of garbage entering the plant in each district. Combined with the current actual situation, it is known that the frequency of regional quota over-standard events is high, which will further threaten the disposal capacity of the terminal disposal plant and cause other problems. This is also a limitation brought by the existing zoned operation method. Due to the restrictions of zoned operations, the garbage collection and transportation vehicles can only collect and transport the garbage from a certain street in a certain zone to the garbage transfer station in this street in this zone, and the terminal disposal plant to which they are transported is also restricted, and the scheduling lacks flexibility. The current vehicle dispatch is mainly based on manual scheduling, which is not ideal in terms of manpower consumption and garbage collection consumption. Summary of the invention

[0004] In view of this, the embodiments of the present invention provide a method, device and medium for sanitation garbage collection and transportation scheduling based on hierarchical clustering, which can balance and flexibly plan the sanitation garbage treatment process, thereby saving garbage collection and transportation costs.

[0005] A first aspect of an embodiment of the present invention provides a method for dispatching sanitation garbage collection based on hierarchical clustering, comprising:

[0006] Acquire location information of garbage sites, and initially allocate the garbage sites according to the location information, wherein the garbage sites include garbage collection points, garbage transfer stations, and terminal disposal plants;

[0007] Determining an initial cluster according to the result of the initial allocation;

[0008] Performing a first calculation according to the initial cluster, and determining a labeling type of the first target garbage site according to a result of the first calculation, wherein the labeling type includes an excess type, a shortage type, and a reasonable type;

[0009] Determine a second target junk site according to the first target site label type, and reallocate the second target junk site;

[0010] Determine a second type of cluster according to the reallocation result;

[0011] hierarchically clustering the garbage collection points according to the second clusters, and determining a third cluster;

[0012] Path planning is performed according to the third type of cluster.

[0013] Optionally, the acquiring location information of the garbage sites and initially allocating the garbage sites according to the location information includes:

[0014] Initially allocating the waste transfer station according to the location information of the terminal disposal plant;

[0015] The garbage collection points are initially allocated according to the location information of the garbage transfer station.

[0016] Optionally, performing a first calculation according to the initial cluster and determining the label type of the first target spam site according to a result of the first calculation includes:

[0017] Calculating the garbage receiving amount of the terminal disposal plant under the initial cluster, and determining the labeling type of the terminal disposal plant according to the garbage receiving amount;

[0018] According to the marking type of the terminal disposal plant, the marking type of the garbage transfer station under the terminal disposal plant is determined.

[0019] Optionally, determining a second target junk site according to the first target site label type, and reallocating the second target junk site includes:

[0020] According to the waste transfer station marking type, a waste transfer station of a target marking type is determined, where the target marking type includes the shortage type and the excess type.

[0021] Optionally, the determining a second target junk site according to the first target site label type, and reallocating the second target junk site further includes:

[0022] Determine a target garbage transfer station that meets a first preset condition according to the target marked type of the garbage transfer station;

[0023] Determining a target garbage collection point that meets a second preset condition according to the target garbage transfer station;

[0024] The target garbage collection point is reallocated.

[0025] Optionally, performing hierarchical clustering on the garbage collection points according to the second clusters includes:

[0026] Initializing the garbage collection points under the second type of cluster as a point cluster;

[0027] According to the location information of the point clusters, the distance between the point clusters is determined, and a distance matrix is ​​constructed;

[0028] According to the distance matrix, point clusters are merged into clusters.

[0029] Optionally, performing path planning according to the third type of cluster includes:

[0030] Get all candidate paths under the third type of cluster;

[0031] Determining the path costs of all the candidate paths;

[0032] A travel route is determined according to the path cost.

[0033] A second aspect of an embodiment of the present invention provides a sanitation garbage removal and dispatching device based on hierarchical clustering, comprising:

[0034] An initial allocation module, used to obtain location information of garbage sites, and to initially allocate the garbage sites according to the location information, wherein the garbage sites include garbage collection points, garbage transfer stations and terminal disposal plants;

[0035] A labeling module, used for determining an initial cluster according to the result of the initial allocation;

[0036] Performing a first calculation according to the initial cluster, and determining a labeling type of the first target garbage site according to a result of the first calculation, wherein the labeling type includes an excess type, a shortage type, and a reasonable type;

[0037] A reallocation module, configured to determine a second target junk site according to the first target site label type, and reallocate the second target junk site;

[0038] Determine a second type of cluster according to the reallocation result;

[0039] A clustering module, used for performing hierarchical clustering on the garbage collection points according to the second clusters, and determining a third cluster;

[0040] A path planning module is used to perform path planning according to the third type of cluster.

[0041] A third aspect of an embodiment of the present invention provides an electronic device, including a processor and a memory;

[0042] The memory is used to store programs;

[0043] The processor executes the program to implement the method described above.

[0044] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0045] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0046] The beneficial effects of the embodiments of the present invention are:

[0047] The location information of the garbage sites is obtained, and the garbage sites are initially allocated according to the location information, and the garbage sites include garbage collection points, garbage transfer stations and terminal disposal plants; according to the results of the initial allocation, the initial clusters are determined. The garbage site allocation method with location information as the weight replaces the planning method of dividing the area, which reduces the limitations of the subsequent sanitation work process such as garbage collection, transfer and disposal.

[0048] A first calculation is performed based on the initial cluster, and based on the result of the first calculation, a labeling type of the first target garbage site is determined, wherein the labeling type includes an excess type, a shortage type, and a reasonable type. By labeling the types of garbage sites, a basis is provided for achieving balanced garbage distribution.

[0049] According to the first target site label type, the second target garbage site is determined, and the second target garbage site is reallocated. Through the reallocation, the garbage collection points in the initial cluster that only considers the location factor are reallocated, and the intelligent and balanced distribution of garbage is achieved, so as to avoid the occurrence of excessive garbage in the terminal disposal plant.

[0050] According to the result of the reallocation, a second cluster is determined; according to the second cluster, the garbage collection points are hierarchically clustered and a third cluster is determined. By using the hierarchical clustering algorithm, the location and type factors are used as clustering conditions, and the carrying capacity of the sanitation vehicles can be used to the greatest extent, and the number of sanitation vehicles put into use can be greatly reduced.

[0051] Path planning is performed based on the third type of clusters. By improving the control of the amount of garbage in the agglomerative clustering algorithm, the total amount of garbage in each cluster is controlled within the maximum nuclear load of the vehicle, so that the number of garbage collection points in each cluster is at a relatively small level, which provides conditions for realizing the optimal collection and transportation path of the collection and transportation vehicles. The optimal collection and transportation path algorithm for garbage points realizes the optimal collection and transportation path scheduling of vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 An overall flow chart of a method for dispatching sanitation garbage removal based on hierarchical clustering provided in an embodiment of the present invention;

[0054] Figure 2 A schematic diagram showing a clustering algorithm provided by an embodiment of the present invention;

[0055] Figure 3 An overall flow chart of a sanitation garbage removal and dispatching device based on hierarchical clustering provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] In order to make the content and technical solution of this application clearer, the relevant terms and their meanings are explained:

[0058] Vehicle dispatching: Vehicle dispatching refers to formulating driving routes so that vehicles can pass through a series of loading and unloading points in an orderly manner under certain constraints to achieve goals such as shortest distance, minimum cost, and least time.

[0059] Clustering: The process of dividing a collection of physical or abstract objects into multiple classes consisting of similar objects is called clustering. The clusters generated by clustering are a collection of data objects that are similar to objects in the same cluster and different from objects in other clusters. Cluster analysis, also known as group analysis, is a statistical analysis method for studying (sample or indicator) classification problems. Cluster analysis originated from taxonomy, but clustering is not equal to classification. The difference between clustering and classification is that the classes required for clustering are unknown. Cluster analysis is very rich in content, including systematic clustering, ordered sample clustering, dynamic clustering, fuzzy clustering, graph clustering, cluster prediction, etc.

[0060] Agglomerative hierarchical clustering: Agglomerative means that at the beginning of the algorithm, each point is regarded as a cluster, and the two closest clusters are merged at each step. First, it is assumed that each sample is an independent cluster. If the number of clusters counted is greater than the expected number of clusters, then each sample is started from another sample closest to itself, and it is aggregated with it to form a larger cluster, while reducing the total number of clusters. The above process is repeated until the number of clusters counted reaches the expected value.

[0061] Garbage collection point: a place used to collect domestic waste generated by units or residents in daily life.

[0062] Garbage transfer station: Garbage transfer station is a garbage transfer station set up between the garbage source (or concentrated location) and the treatment plant in order to reduce the transportation cost of garbage collection. Here, the garbage collected from various collection points is concentrated and transferred to large or other low-cost transport vehicles for further transportation to the treatment site.

[0063] Garbage treatment plant: A garbage treatment plant is a specific place where garbage generated by industry, production, medical and health care is collected and processed to reduce environmental pollution. Common methods of garbage treatment include sanitary landfill, composting and direct incineration.

[0064] Optimal path algorithm: The optimal path algorithm is an undirected graph that satisfies all vertices (except the starting point and the end point) on the path and all edges are also different. Applied in road transportation, it can provide the shortest path between the starting point and the end point, saving transportation costs. It can greatly improve transportation efficiency.

[0065] The current urban domestic waste removal process mainly involves three fixed components, namely, garbage collection points, garbage transfer stations and terminal disposal plants, and a mobile component, namely, sanitation removal vehicles. The removal process is shown in the figure and can be roughly divided into the following steps:

[0066] 1) Garbage collection and transportation. The collection and transportation vehicle passes through various collection points on the route to collect garbage until the vehicle's rated load is reached and then transports the collected garbage to the garbage transfer station. The collection and transportation vehicle has its maximum rated load M;

[0067] 2) Garbage transfer. The collection and transportation vehicles transport the collected garbage to the garbage transfer station, where it is compressed and processed before being transferred;

[0068] 3) Waste transfer. The process of transporting waste to the final disposal plant for disposal after being compressed and processed at the waste transfer station;

[0069] 4) Final disposal. It is mainly to do the final treatment of the garbage entering the factory. Each final disposal plant has its maximum amount of garbage entering the plant, and the amount of garbage entering the plant cannot exceed the upper limit of the garbage disposal of the corresponding final disposal plant.

[0070] Under the zoning operation, the garbage collection points of a street in a certain area can only be transferred to the garbage transfer station of the street in the area, and then transported to the terminal disposal plant designated by the area for disposal. However, the cross-area operation scheme proposed by this civilization has no area restrictions. Each garbage collection point\type can be transferred to any garbage transfer station and can be transported to any terminal disposal plant that meets the disposal capacity. After clustering the garbage collection points, a single garbage collection point cluster C i (Garbage collection point list i =[s i1 ,…,s il ,…],1≤l≤k, where s il represents the lth element in the i-th garbage collection point list, and k represents the i-th garbage collection point cluster C i The number of garbage collection points) The collection and transportation costs of garbage are:

[0071]

[0072] Where k represents the i-th garbage collection point cluster C i The number of garbage collection points, j represents the jth garbage collection point, s ij and i(j+1) They represent the jth and j+1th garbage collection points in the i-th garbage collection point cluster, respectively. ik represents the kth garbage collection point in the i-th garbage collection point cluster, z i Represents the garbage collection point cluster C i Corresponding garbage transfer station.

[0073] The cost of transferring garbage from a single garbage collection point cluster from the garbage transfer station to the final disposal plant is:

[0074] Cost=dis(z i ,ci )

[0075] In the formula, z i Represents the garbage collection point cluster C i The corresponding garbage transfer station, c i Represents the garbage collection point cluster C i The corresponding final disposal plant.

[0076] Therefore, the total removal cost of a single garbage collection point cluster Ci is:

[0077]

[0078] The total cost of the removal operation for each garbage collection point cluster is:

[0079]

[0080] Where i represents the i-th garbage collection point cluster, and K represents the number of garbage collection point clusters.

[0081] The total amount of garbage in a single collection point cluster Ci should satisfy:

[0082]

[0083] Where W i represents the total amount of garbage in a single collection point cluster Ci, w ij represents the amount of garbage at the jth garbage collection point in the i-th garbage collection point cluster, and M represents the maximum nuclear load of the garbage collection and transportation vehicle.

[0084] The amount of waste entering each terminal disposal plant should meet the following requirements:

[0085]

[0086] Where, WP h represents the amount of waste entering the hth terminal disposal plant, r represents the rth waste collection point cluster, R h represents the number of garbage collection points corresponding to the hth terminal disposal plant, WC r Represents the total amount of garbage in the rth garbage collection point cluster, MP h It represents the upper limit of the amount of waste to be disposed of at the hth terminal disposal plant.

[0087] In contrast, each garbage collection point cluster C under the clustering-based cross-area operation scheme i Waste transfer station i Destination and final disposal plantc i The possible range of destinations is greater than the currently used sharding operation scheme.

[0088] Therefore, in view of the above-mentioned sanitation vehicle operation mode and garbage collection and transportation scheduling problems, the present invention proposes the following general sanitation vehicle collection and transportation cost mathematical model:

[0089] (1)

[0090] (2)

[0091] Formula (1) defines the optimization objective function of the vehicle operating distance in the process of sanitation vehicle transportation scheduling, that is, f represents the minimization of the total operating distance of the sanitation vehicle, where is the driving cost of the sanitation vehicle to collect garbage from the garbage collection point in the garbage collection point cluster Ci, dis(s ik ,z i ) is the driving distance of the sanitation vehicle to the corresponding garbage transfer station after collecting the collection point cluster to meet the nuclear load, that is, the distance from the last garbage collection point in the cluster to the corresponding garbage transfer station, dis(z i ,c i ) is the operating distance of the sanitation vehicles from the garbage transfer station corresponding to the garbage collection point cluster to the corresponding terminal disposal plant. Formula (2)st indicates that the garbage carrying capacity of each sanitation vehicle is within its maximum nuclear capacity. While considering the driving cost of sanitation vehicles, the garbage volume is evenly distributed to ensure that the garbage volume entering each terminal disposal plant is within its disposal upper limit.

[0092] The implementation principle of the method of the present invention is described in detail below in conjunction with the accompanying drawings:

[0093] Figure 1 The figure shows an overall flow chart of a method for dispatching sanitation garbage removal based on hierarchical clustering provided by an embodiment of the present invention, the method comprising:

[0094] Obtaining the location information of garbage sites, and initially allocating the garbage sites according to the location information, the garbage sites include garbage collection points, garbage transfer stations and terminal disposal plants;

[0095] According to the results of the initial allocation, the initial cluster is determined;

[0096] Perform a first calculation based on the initial cluster, and determine a labeling type of the first target garbage site based on a result of the first calculation, where the labeling type includes an excess type, a shortage type, and a reasonable type;

[0097] Determine a second target garbage site according to the first target site label type, and reallocate the second target garbage site;

[0098] According to the result of the reallocation, the second type of cluster is determined, the garbage collection points are hierarchically clustered according to the second type of cluster, and the third type of cluster is determined;

[0099] Path planning is performed based on the third type of cluster.

[0100] In some embodiments, the location information of the garbage sites is obtained, and the garbage sites are initially allocated according to the location information. The garbage sites include garbage collection points, garbage transfer stations, and terminal disposal plants, including:

[0101] Initially allocating the waste transfer station according to the location information of the terminal disposal plant;

[0102] Specifically, the destination of the corresponding terminal disposal plant of the garbage at each garbage transfer station is designated, that is, the garbage transfer stations are divided according to the distance from the terminal disposal plant. Each garbage transfer station is assigned to the terminal disposal plant closest to it. The division in this step is not restricted by the area.

[0103] The garbage collection points are initially allocated according to the location information of the garbage transfer station.

[0104] Specifically, the destination of the garbage collection point's garbage is designated as the corresponding garbage transfer station, that is, the garbage collection points are divided according to their distance from the garbage transfer station. Each garbage collection point is classified into the garbage transfer station closest to it. The division in this step is not restricted by the area.

[0105] It should be noted that, in some embodiments, an initial cluster is determined based on the result of the initial allocation, wherein the initial cluster includes a plurality of transfer station clusters obtained by dividing the garbage transfer station according to the distance between the garbage transfer station and the terminal disposal plant, and a plurality of collection point clusters obtained by dividing the garbage collection point according to the distance between the garbage collection point and the garbage transfer station.

[0106] In some embodiments, performing a first calculation based on the initial cluster and determining the label type of the first target spam site based on the result of the first calculation includes:

[0107] Calculating the garbage receiving amount of the terminal disposal plant under the initial cluster, and determining the labeling type of the terminal disposal plant according to the garbage receiving amount;

[0108] According to the marking type of the terminal disposal plant, the marking type of the garbage transfer station under the terminal disposal plant is determined.

[0109] Specifically, the calculation range is defined for each cluster under the initial cluster, so as to calculate the total amount of garbage accepted by each terminal disposal plant under the initial cluster and mark the type of the terminal disposal plant according to this value (excess type: exceeding the disposal upper limit of this disposal plant, shortfall type: less than 19 / 20 of the disposal upper limit of this disposal plant, reasonable type: the amount of garbage is between 19 / 20 of the disposal upper limit of the disposal plant and the maximum disposal upper limit). According to the marked terminal disposal plant type, the garbage transfer station assigned to this terminal disposal plant is further marked with the type (excess type, shortfall type, reasonable type).

[0110] In some embodiments, determining a second target spam site according to the first target site label type and reallocating the second target spam site includes:

[0111] According to the marking type of the garbage transfer station, the target marking type of the garbage transfer station is determined, and the target marking type includes a shortage type and an excess type.

[0112] Specifically, garbage transfer stations of corresponding types are obtained, including all garbage transfer stations of the shortage type and the excess type, and the subsequent reallocation is performed based on these two types of garbage transfer stations and the garbage collection points associated with the initial clusters.

[0113] In some embodiments, determining a second target spam site according to the first target site label type and reallocating the second target spam site further includes:

[0114] Determine a target garbage transfer station that meets a first preset condition according to the target marked type of the garbage transfer station;

[0115] Specifically, determine the excess type of garbage transfer station and its corresponding shortage type of garbage transfer station, give priority to the excess type of garbage transfer station with only one corresponding garbage collection point (in order to maximize the use of the resources of the collection and transportation vehicles put into operation), and then consider the distance between the two garbage transfer stations (the excess type of garbage transfer station and the shortage type of garbage transfer station) and the total amount of garbage in the excess type of garbage transfer station (the higher the excess garbage volume, the higher the priority, which can minimize the impact of the re-division of garbage collection points on the theoretical optimal cost). Therefore, according to these factors, determine the priority list of the two garbage transfer stations involved in the reallocation, and match the excess type of garbage transfer station to the shortage type of garbage transfer station according to the priority list as the first preset condition.

[0116] Determining a target garbage collection point that meets a second preset condition according to the target garbage transfer station;

[0117] Specifically, determine the corresponding garbage collection points to be reallocated in the excess type garbage transfer station, taking into account the distances from each garbage collection point corresponding to the excess type garbage transfer station to the shortage type garbage transfer station and the garbage amount factor of each garbage collection point (the larger the garbage amount, the higher the priority, which can minimize the number of garbage collection points to be reallocated, and thus minimize the impact on the theoretical optimal cost), and determine the garbage collection points to be reallocated based on these factors as the second preset conditions.

[0118] Reallocate the target garbage collection point.

[0119] Specifically, the determined garbage collection points that need to be reallocated are obtained, and the garbage collection points corresponding to the excess type garbage transfer stations are re-divided (divided into eligible shortage type garbage transfer stations) until the garbage entering all excess type terminal disposal plants and shortage type terminal disposal plants returns to a reasonable range (that is, the types of the corresponding excess type transfer stations and shortage type transfer stations also return to reasonable types).

[0120] It should be noted that, in some embodiments, based on the results of reallocation, a second type of cluster is determined, wherein the second type of cluster includes multiple Class II transfer station clusters and multiple Class II collection point clusters that are obtained after reallocation so that both the terminal disposal plants and the garbage transfer stations return to reasonable types.

[0121] In some embodiments, according to the cross-district operation scheme proposed in the present application, it is necessary to cluster the garbage collection points corresponding to each garbage transfer station obtained after the above steps according to the geographical location, so that the garbage collection points of each cluster are relatively clustered in geographical location. Since the time complexity of the agglomerative clustering algorithm is O(n3), the larger the amount of data, the less ideal its operating efficiency is. After the previous initial allocation and reallocation steps, the garbage collection points to be clustered have been converted from the order of the entire city to the order of multiple garbage collection point clusters, so it is feasible to use the agglomerative clustering algorithm. Therefore, based on this and the research scenario requirements of the present invention, the agglomerative hierarchical clustering algorithm is improved, and an improved agglomerative hierarchical clustering algorithm is proposed. For the step of hierarchically clustering garbage collection points according to the second type of clusters, the steps specifically include:

[0122] Initialize the garbage collection points under the second type of cluster as point clusters;

[0123] Specifically, clustering units are defined by each cluster under the second type of cluster, each garbage collection point in the unit is initialized as a cluster, the position of each cluster is initialized to the position of the collection point, and the total amount of garbage in each cluster is initialized to the amount of garbage at the collection point.

[0124] According to the location information of the point clusters, determine the distance between the point clusters and build a distance matrix;

[0125] Specifically, the distance between any two clusters is calculated according to the position of each cluster (the position of each cluster is the center of all collection points in the cluster), and the distance matrix C is built according to the calculation results.

[0126] Merge point clusters into clusters based on the distance matrix.

[0127] Specifically, the two clusters with the closest distance are determined according to the distance matrix C, and it is judged whether the two clusters meet the conditions for merging (1. The total mass of garbage in the merged cluster ≤ the maximum nuclear load M of the vehicle; 2. The transportation cost of this cluster after the merger ≤ the transportation cost of the first cluster + the transportation cost of the second cluster). The two clusters that meet the merging conditions are added to the set of merged pairs P; the clusters recorded in P are merged (such as cluster j is merged into cluster i) and the relevant variables are updated, including: 1) adding members of cluster j to cluster i; 2) deleting cluster j; 3) updating the position of cluster i; 4) deleting the position information of cluster j; 5 updating the total amount of garbage in cluster i (plus the total amount of garbage in cluster j); 6) deleting the garbage amount information of cluster j; 7) recalculating the distance matrix C. Repeat the above steps until the merged pair P is empty, and obtain the cluster of the final merged result. Refer to Figure 2 The clustering algorithm is roughly divided into three steps: (1) 2D initial data set; (2) merging pairs that meet the conditions; (3) the clusters of the final merging results.

[0128] In some embodiments, clusters of garbage collection points are formed through clustering, and the total amount of garbage in each cluster is controlled within the maximum nuclear load of the collection and transportation vehicle. At this time, finding the collection point driving path with the lowest transportation cost is the key to controlling costs. Due to the control of the total amount of garbage in each cluster, the number of garbage collection points in each cluster is also at a relatively small level. Therefore, the idea of ​​greedy search can be used to search for the best collection and transportation path for the collection points. Searching for the best collection order of collection points\vehicle collection driving path can be regarded as a problem with multiple starting points and a single end point. The starting point can be any garbage collection point in the cluster, and the end point can only be the garbage transfer station corresponding to this garbage collection point cluster. That is, the step of path planning according to the third cluster, the steps specifically include:

[0129] Get all candidate paths under the third type of cluster;

[0130] Specifically, each cluster under the third type of cluster is used to define the path planning range, and all possible paths (i.e., paths to be selected) are obtained. All permutations of the list can be obtained by using the full permutation function permutations.

[0131] Determining the path costs of all the candidate paths;

[0132] Specifically, the collection and transportation distances (i.e., path costs) of all paths are calculated. Based on all the collection and transportation paths of all garbage collection points in each cluster under the third type of cluster, the driving distance and transportation cost of each path are calculated, including the distance between each garbage collection point and the distance from the last collection point to the garbage transfer station corresponding to the cluster.

[0133] A travel route is determined according to the path cost.

[0134] Specifically, the path with the minimum distance\cost is selected, and the path with the minimum distance is selected as the optimal collection and transportation path for the collection point of the cluster according to the distance result of each path calculated by the path cost.

[0135] The embodiment of the present invention provides a sanitation garbage removal and dispatching device based on hierarchical clustering, comprising:

[0136] An initial allocation module is used to obtain the location information of the garbage sites and to initially allocate the garbage sites according to the location information. The garbage sites include garbage collection points, garbage transfer stations and terminal disposal plants.

[0137] A labeling module is used to determine the initial cluster according to the results of the initial allocation;

[0138] Perform a first calculation based on the initial cluster, and determine a labeling type of the first target garbage site based on a result of the first calculation, where the labeling type includes an excess type, a shortage type, and a reasonable type;

[0139] A reallocation module, used to determine a second target junk site according to the first target site label type, and reallocate the second target junk site;

[0140] According to the results of the reallocation, the second type of cluster is determined;

[0141] A clustering module, used for performing hierarchical clustering on the garbage collection points according to the second clusters, and determining a third cluster;

[0142] The path planning module is used to perform path planning according to the third type of cluster.

[0143] The contents of the method embodiments of the present invention are all applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0144] In some embodiments, reference Figure 3 The operation flow of the device embodiment to implement the above method is as follows:

[0145] The initial allocation module is implemented as follows: according to the distance between the garbage transfer station and the terminal disposal plant, the transfer station cluster is determined according to the standard of fixed randomness and no area restriction; according to the distance between the garbage collection point and the garbage transfer station, the collection point cluster is determined according to the standard of fixed randomness and no area restriction.

[0146] The labeling module is implemented as follows: the clusters under the initial allocation are determined according to the transfer station cluster and the collection point cluster. At the same time, under the theoretical support of the theoretical optimal cost, the terminal disposal plant type is labeled, and the labeling types include reasonable range, shortage range and excess range; the garbage transfer station type in the transfer station cluster based on the terminal disposal plant is labeled according to the labeling type of the disposal plant, and the labeling types include reasonable range, shortage range and excess range. The labeling type of the garbage transfer station corresponds to the labeling type of its corresponding terminal disposal plant. The purpose of labeling is to allocate the garbage stations under the excess range type to the shortage range so that they all reach the reasonable range.

[0147] The reallocation module realizes: the corresponding garbage collection points under the excess garbage transfer station are allocated to the shortage garbage transfer station. Through reallocation, the garbage transfer stations and terminal treatment plants in the excess and shortage ranges are brought into a reasonable range.

[0148] Clustering module implementation: Based on the reallocated garbage sites, the final clusters are determined by hierarchical distances improved with multiple small data volumes.

[0149] Path planning module implementation: According to the final garbage collection points under each cluster determined by the clustering module, the optimal collection and transportation path algorithm of the collection point is used to determine the optimal vehicle operation path, and realize dynamic and balanced distribution of garbage.

[0150] An embodiment of the present invention provides an electronic device, including a processor and a memory;

[0151] The memory is used to store programs;

[0152] The processor executes the program to implement a sanitation garbage collection and transportation scheduling method based on hierarchical clustering.

[0153] The contents of the method embodiments of the present invention are all applicable to the electronic device embodiments. The functions specifically implemented by the electronic device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0154] In summary, this method aims at the existing sanitation vehicle operation mode and garbage collection scheduling problems, and proposes a general sanitation vehicle collection cost mathematical model and a cross-district sanitation garbage collection scheduling strategy based on agglomerative hierarchical clustering. Through the cross-district operation mode, the limitations of the original operation plan are broken, and the various districts are interconnected, and the driving distance / time cost of sanitation vehicles for garbage collection is greatly reduced; by converting the initial single garbage collection point set of the entire city into multiple garbage collection point sets, that is, converting a single large data volume into multiple small data volumes, it provides a basis for using the proposed improved agglomerative hierarchical clustering algorithm. By combining the improved agglomerative hierarchical clustering algorithm with the optimal collection and transportation path algorithm of the collection point, the optimal collection and transportation path of the vehicle is determined, and the intelligent scheduling of vehicle garbage collection is realized. Compared with the manual scheduling of sanitation vehicle operations under the original plan, it has achieved intelligence. In the proposed improved agglomerative hierarchical clustering algorithm, by taking distance and garbage volume factors as clustering conditions, the carrying capacity of sanitation vehicles can be utilized to the greatest extent, and the number of sanitation vehicles in use can be greatly reduced; the cross-area operation plan realizes the balanced distribution of garbage volume according to the disposal capacity of each terminal disposal plant, eliminating the threat to the disposal capacity of the terminal disposal plant under the original operation mode.

[0155] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0156] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0157] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0158] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0159] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0160] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0161] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0162] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0163] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0164] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for dispatching sanitation garbage removal based on hierarchical clustering, characterized in that: include: Acquire location information of garbage sites, and initially allocate the garbage sites according to the location information, wherein the garbage sites include garbage collection points, garbage transfer stations, and terminal disposal plants; Determining an initial cluster according to the result of the initial allocation; Performing a first calculation according to the initial cluster, and determining a labeling type of the first target garbage site according to a result of the first calculation, wherein the labeling type includes an excess type, a shortage type, and a reasonable type; The performing of a first calculation based on the initial cluster and determining the labeling type of the first target spam site based on a result of the first calculation includes: Calculating the garbage receiving amount of the terminal disposal plant under the initial cluster, and determining the labeling type of the terminal disposal plant according to the garbage receiving amount; According to the labeling type of the terminal disposal plant, determine the labeling type of the waste transfer station under the terminal disposal plant; Determine a second target junk site according to the first target site label type, and reallocate the second target junk site; The step of determining a second target spam site according to the first target site label type and reallocating the second target spam site includes: According to the waste transfer station marking type, determine a waste transfer station of a target marking type, wherein the target marking type includes the shortage type and the excess type; According to the target marked type of garbage transfer station, determine the target garbage transfer station that meets the first preset condition; the first preset condition indicates that priority is given to the excess type garbage transfer station that has only one corresponding garbage collection point, and then the distance between the excess type garbage transfer station and the shortage type garbage transfer station and the total amount of garbage in the excess type garbage transfer station are considered; wherein, the higher the excess garbage amount, the priority is given; According to the target garbage transfer station, determine the target garbage collection point that meets the second preset condition; the second preset condition represents the distance from each garbage collection point corresponding to the excess type garbage transfer station to the shortage type garbage transfer station and the garbage volume factor of each garbage collection point; wherein, the larger the garbage volume, the higher the priority; reallocating the target garbage collection point; Determine a second type of cluster according to the reallocation result; hierarchically clustering the garbage collection points according to the second clusters, and determining a third cluster; The step of performing hierarchical clustering on the garbage collection points according to the second clusters comprises: Initializing the garbage collection points under the second type of cluster as a point cluster; According to the location information of the point clusters, the distance between the point clusters is determined, and a distance matrix is ​​constructed; According to the distance matrix, merging point clusters into clusters; Path planning is performed according to the third type of cluster.

2. A method for dispatching sanitation garbage removal based on hierarchical clustering according to claim 1, characterized in that: The obtaining of location information of garbage sites and initially allocating the garbage sites according to the location information includes: Initially allocating the waste transfer station according to the location information of the terminal disposal plant; The garbage collection points are initially allocated according to the location information of the garbage transfer station.

3. The method for dispatching sanitation garbage removal based on hierarchical clustering according to claim 1 is characterized in that: The performing path planning according to the third type of cluster includes: Get all candidate paths under the third type of cluster; Determining the path costs of all the candidate paths; A travel route is determined according to the path cost.

4. A sanitation garbage removal and dispatching device based on hierarchical clustering, characterized in that: include: An initial allocation module, used to obtain location information of garbage sites, and to initially allocate the garbage sites according to the location information, wherein the garbage sites include garbage collection points, garbage transfer stations and terminal disposal plants; A labeling module, used for determining an initial cluster according to the result of the initial allocation; Performing a first calculation according to the initial cluster, and determining a labeling type of the first target garbage site according to a result of the first calculation, wherein the labeling type includes an excess type, a shortage type, and a reasonable type; The performing of a first calculation based on the initial cluster and determining the labeling type of the first target spam site based on a result of the first calculation includes: Calculating the garbage receiving amount of the terminal disposal plant under the initial cluster, and determining the labeling type of the terminal disposal plant according to the garbage receiving amount; According to the labeling type of the terminal disposal plant, determine the labeling type of the waste transfer station under the terminal disposal plant; A reallocation module, configured to determine a second target junk site according to the first target site label type, and reallocate the second target junk site; The step of determining a second target spam site according to the first target site label type and reallocating the second target spam site includes: According to the waste transfer station marking type, determine a waste transfer station of a target marking type, wherein the target marking type includes the shortage type and the excess type; According to the target marked type of garbage transfer station, determine the target garbage transfer station that meets the first preset condition; the first preset condition indicates that priority is given to the excess type garbage transfer station that has only one corresponding garbage collection point, and then the distance between the excess type garbage transfer station and the shortage type garbage transfer station and the total amount of garbage in the excess type garbage transfer station are considered; wherein, the higher the excess garbage amount, the priority is given; According to the target garbage transfer station, determine the target garbage collection point that meets the second preset condition; the second preset condition represents the distance from each garbage collection point corresponding to the excess type garbage transfer station to the shortage type garbage transfer station and the garbage volume factor of each garbage collection point; wherein, the larger the garbage volume, the higher the priority; reallocating the target garbage collection point; Determine a second type of cluster according to the reallocation result; A clustering module, used for performing hierarchical clustering on the garbage collection points according to the second clusters, and determining a third cluster; The step of performing hierarchical clustering on the garbage collection points according to the second clusters comprises: Initializing the garbage collection points under the second type of cluster as a point cluster; According to the location information of the point clusters, the distance between the point clusters is determined, and a distance matrix is ​​constructed; According to the distance matrix, merging point clusters into clusters; A path planning module is used to perform path planning according to the third type of cluster.

5. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 3.

Images