Garbage collaborative transfer method and system based on big data

Abstract

The invention relates to the technical field of garbage collection and transportation, in particular to a garbage collaborative transfer method and system based on big data. The method comprises the steps that a particle swarm is initialized, the size of the particle swarm is set, and each particle represents a co-transport path; calculating an evaluation function value of each particle, and selecting the particle corresponding to the maximum evaluation function value as a current optimal solution; iteratively updating each particle, performing mutation operation on each updated particle to obtain a new particle after mutation, and continuing to calculate an evaluation function value of each new particle to obtain a current global optimal solution; and carrying out iteration updating for multiple times, stopping updating until a set condition is met, and obtaining a final global optimal solution so as to obtain an optimal collaborative transfer path. According to the scheme, the optimal collaborative transfer path can be obtained, and the garbage transfer process is more flexible and efficient.

Description

Technical Field

[0001] The present invention relates to the field of garbage removal technology. More specifically, the present invention relates to a garbage collaborative transportation method and system based on big data. Background Art

[0002] With the increasing amount of urban garbage generated, the effective management and transportation of garbage has become an important issue in urban management.

[0003] Traditional garbage collection and transfer methods often rely on manual scheduling and static route design, which are inefficient and easily affected by real-time conditions (such as traffic, weather, etc.), resulting in the garbage transfer process being inflexible and inefficient.

[0004] With the rapid development of technologies such as big data, the Internet of Things (IoT), and cloud computing, the coordinated transfer of garbage has become the main method of garbage collection and transportation. Among them, coordinated transfer of garbage is to maximize the efficiency of garbage transfer, reduce resource waste, and optimize the urban garbage management system through information sharing and collaborative cooperation among multiple participants (such as garbage collection points, transportation fleets, and treatment plants). Among them, during collaborative cooperation, through real-time acquisition and analysis of the entire process of garbage collection, transfer, and treatment, it can better realize the intelligence, coordination, and efficiency of garbage transfer.

[0005] In the related technology, such as the Chinese patent application document of the garbage transfer vehicle scheduling method and system based on the big data platform disclosed with application publication number CN110428130A, it uploads the real-time garbage inventory information of each garbage transfer station to the big data platform; obtains the real-time garbage inventory information corresponding to each garbage transfer station from the big data platform at regular intervals; calculates the combination of garbage transfer stations that can fully load a garbage transfer vehicle based on the real-time garbage inventory information, and dispatches the garbage transfer vehicle to each of the garbage transfer stations, thereby improving the garbage transportation efficiency.

[0006] However, the above scheme only performs scheduling analysis from a single perspective (garbage inventory information) when scheduling garbage transfer vehicles, which can easily lead to problems such as the garbage transfer process being inflexible and inefficient. Summary of the invention

[0007] The purpose of the present invention is to propose a method and system for coordinated garbage transfer based on big data, so as to solve the problem that in the prior art, when transferring garbage, the influence of real-time environmental conditions is not taken into consideration, resulting in the garbage transfer process being not flexible and efficient enough; to this end, the present invention provides solutions in the following two aspects.

[0008] In a first aspect, the present invention provides a method for coordinated garbage transportation based on big data, comprising: Initialize a particle swarm and set the size of the particle swarm. Each particle represents a coordinated transport path, where the coordinated transport path is a comprehensive transport path for multiple garbage trucks in a target area to coordinately transport garbage in multiple garbage bins. Calculate the evaluation function value of each particle, select the particle corresponding to the maximum evaluation function value as the current optimal solution; iteratively update each particle to obtain a new particle, continue to calculate the evaluation function value of each new particle, and obtain the current global optimal solution; perform multiple iterative updates until the set conditions are met, stop updating, and obtain the final global optimal solution to obtain the best collaborative transport path; Among them, the evaluation function value for: ; is the normalization function, is the filling degree of the jth garbage truck in any particle at the mth iteration, is the filling degree of the i-th trash bin in any particle at the m-th iteration, is the ratio of the loading capacity of a single garbage truck to that of a single garbage bin, a>1, is a natural constant, is the length of the transportation path of the jth garbage truck in any particle at the mth iteration, J is the number of garbage trucks, and I is the number of garbage bins.

[0009] The above scheme constructs an evaluation function value that is more in line with the garbage collection scenario by obtaining the filling degree of garbage trucks and garbage bins in the target area, as well as the length of the transportation path of the garbage trucks. In the iterative optimization process, the global optimal solution for garbage transfer can be determined based on the evaluation function value at each iteration. That is, the scheme of the present invention can start from the perspective of the capacity of garbage trucks and garbage bins and the possible transportation routes of garbage trucks, construct the evaluation function value in the optimization algorithm, obtain the best collaborative path, and ensure the flexibility and efficiency of the garbage transfer process.

[0010] Optionally, the iterative updating of each particle includes: screening each particle to obtain a target particle, and performing a mutation operation on a similar particle of each target particle to obtain a mutated new particle.

[0011] The above scheme also introduces mutation operations, which can prevent the population from falling into a local optimal solution.

[0012] Optionally, the similar particles are: Taking particles whose evaluation function values ​​are greater than a threshold as target particles; searching for particles similar to each target particle; The similar particles are obtained by matching the target particle with any other particle using a maximum matching algorithm; when performing the maximum matching, the edge weight at the maximum matching is the similarity between the target particle and the garbage truck in the other particles.

[0013] The above scheme selects target particles from particles and updates the target particles, which can simplify calculations.

[0014] Optionally, the similarity for: ; in, , are the number of garbage bins in the intersection of the set of garbage bins on the transport path of the j-th garbage truck in any target particle and the set of garbage bins on the transport path of the k-th garbage truck in any other particle, and the number of garbage bins in the union, respectively. To obtain the maximum value, is the maximum value of the length of the common path between the transport paths of the j-th garbage truck and the k-th garbage truck, , are the lengths of the transportation paths of the j-th garbage truck and the k-th garbage truck respectively.

[0015] By calculating the similarity between the garbage trucks in the two particles, the matching degree of the two particles can be obtained, thereby determining similar particles similar to the target particle.

[0016] Optionally, the similarity is the ratio of the number of garbage bins with the same connection relationship on the transport path of each garbage truck in any target particle and any garbage truck in any other particle to the number of garbage bins with different connection relationships; the same connection relationship means that the paths passing through the garbage bins on the transport paths of the two garbage trucks are the same.

[0017] Optionally, performing a mutation operation on each similar particle includes: According to the mutation probability, the transportation path of each garbage truck in each similar particle is mutated to obtain a new particle after mutation; the mutation probability for: ; is a natural constant, is the matching degree between the hth new particle at the nth iteration and the global optimal solution before the nth iteration, n is greater than 1, and the matching degree is the sum of all edge weights when matching is performed using the maximum matching algorithm.

[0018] The purpose of the above mutation operation is to increase the diversity of the population and prevent the population from falling into a local optimal solution.

[0019] Optionally, the setting condition is that the difference between the maximum evaluation function values ​​obtained from two consecutive iterations is less than a set threshold or reaches a maximum number of iterations.

[0020] Optionally, the number of the similar particles is the same as the size of the particle group, which is 100.

[0021] Optionally, the filling degree of the trash can is: the ratio of the actual amount of trash in the trash can to the corresponding rated loading amount; or, the ratio of the depth of the garbage in the bin to the depth of the corresponding bin; The filling degree of the garbage truck is: the ratio of the actual amount of garbage in the garbage truck to the rated loading capacity of the corresponding garbage truck.

[0022] In a second aspect, a garbage coordinated transport system based on big data includes: processor; A memory storing computer instructions for coordinated garbage transfer based on big data. When the computer instructions are executed by the processor, the system executes the above-mentioned method for coordinated garbage transfer based on big data.

[0023] The beneficial effects of the present invention are: The solution of the present invention constructs a collaborative transport evaluation function through the filling degree of garbage trucks and garbage bins and the length of the transportation path of each garbage truck, and uses an optimization algorithm to find the optimal value of the evaluation function, so as to efficiently obtain the best collaborative transport path. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of the steps of a garbage collaborative transport method based on big data in this embodiment is schematically shown; Figure 2 The structural block diagram of a garbage collaborative transfer system based on big data in this embodiment is schematically shown. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0026] The present invention is directed to a scenario where multiple garbage trucks transfer garbage in multiple garbage bins at the same time.

[0027] like Figure 1 As shown, a garbage collaborative transport method based on big data in this embodiment includes the following steps: Step S1, collecting in real time the filling levels of multiple garbage bins, the filling levels of garbage trucks, and the transportation routes of each garbage truck in the target area.

[0028] In this embodiment, by installing sensors (such as weight sensors, position sensors, etc.) on garbage bins, garbage trucks and other facilities, the filling levels of garbage bins and garbage trucks are collected in real time; at the same time, the transportation routes of each garbage truck are also obtained; and using the Internet of Things technology, the data collected by these sensors and the transportation routes of each garbage truck are transmitted to the cloud or local server for processing and analysis.

[0029] The target area may be a community, which may include multiple neighborhoods; or a street in a city, which may include multiple trash cans.

[0030] In one embodiment, the process of obtaining the filling degree is as follows: sensors are installed on each garbage bin, garbage truck and other garbage transfer related facilities to collect the amount of garbage in the garbage bin and garbage truck, and the real-time filling degree of each garbage device (the garbage device is a garbage bin or a garbage truck) is calculated according to the corresponding rated loading capacity. The ratio of the amount of loaded garbage collected by the garbage device in real time to the rated loading capacity is the filling degree of the garbage device. These data are transmitted to the cloud or local server to provide supporting data for the subsequent planning of the best collaborative transfer route.

[0031] In another embodiment, the ratio of the depth of the garbage in the garbage bin to the depth of the corresponding garbage bin.

[0032] Step S2, using an improved intelligent optimization algorithm to find the best coordinated transfer path in the target area to achieve garbage transfer in the target area.

[0033] Taking the intelligent optimization algorithm as a genetic algorithm as an example, the process of obtaining the best coordinated transport path for garbage transport in a certain target area in this embodiment is introduced as follows: Step S21, initialize the particle swarm, set the size of the particle swarm, and each particle represents a coordinated transport path.

[0034] When transferring garbage in a target area, there are many ways to combine multiple garbage trucks and garbage bins, each of which corresponds to a coordinated transfer route.

[0035] Among them, the collaborative transfer path is a comprehensive transportation path for multiple garbage trucks in the target area to collaboratively transfer garbage in multiple garbage bins, that is, the collaborative transfer path includes the transportation paths of multiple garbage trucks and the location information of the garbage bins.

[0036] In this embodiment, by initializing the particle group, each particle in the particle group is assigned a value as a coordinated transport path when the garbage in the target area is transported. Multiple particles are multiple coordinated transport paths.

[0037] The size of the particle group can be 100, and can also be set according to actual conditions. In this embodiment, the maximum number of iterations also needs to be set.

[0038] Step S22, calculate the evaluation function value of each particle, select the particle corresponding to the maximum evaluation function value as the optimal solution; iteratively update each particle, perform mutation operation on each updated particle to obtain a mutated new particle, continue to calculate the evaluation function value of each new particle, and obtain the current sub-optimal solution.

[0039] In one embodiment, there are many situations for coordinated garbage transportation. The types of transportation paths tend to increase with the increase of the locations of the garbage bins to be transported. However, in the case of coordinated garbage transportation, it is particularly important to select from a large number of coordinated transportation paths the one that can transport all the garbage in the garbage bins that need to be transported, and at the same time make the transportation path of the garbage truck as good as possible. Therefore, in this embodiment, the evaluation function value of each particle is constructed, specifically: The evaluation function value at each iteration for: ; is the normalization function, is the filling degree of the jth garbage truck in any particle at the mth iteration, is the filling degree of the ith trash can in any particle at the mth iteration. a is the ratio of the loading capacity of a single garbage truck to that of a single trash can. If a is greater than 1, is a natural constant, is the length of the transport path of the jth garbage truck in any particle at the mth iteration, J is the number of garbage trucks, and I is the number of garbage bins. The above normalization function can be normalized to the maximum and minimum values.

[0040] It represents the difference between the remaining loading capacity of all garbage trucks on each collaborative transfer path and the amount of garbage stored in all garbage bins at each iteration. The larger the difference is, the more the garbage truck can completely clear the garbage in the garbage bin, and the larger the evaluation function value is. At the same time, the shorter the length of the transportation path of all garbage trucks, the larger the evaluation function value is. Therefore, the larger the evaluation function value is, the shorter the transportation path of each garbage truck in the collaborative transfer path is, and the more the needs of garbage transfer are met, the better the result of collaborative transfer will be.

[0041] In this embodiment, the process of iteratively updating each particle is as follows: selecting particles whose evaluation function values ​​are greater than a threshold as target particles; and searching for particles similar to each target particle.

[0042] The similar particles are matched with the target particle and any other particle by using the maximum matching algorithm to obtain similar particles similar to the target particle; that is, when performing the maximum matching, the edge weight at the maximum matching is the similarity between the target particle and the garbage truck in the other particles.

[0043] Since the maximum matching algorithm is an existing technology, it will not be described in detail here.

[0044] In one embodiment, the similarity for: ; in, , are the number of garbage bins in the intersection of the set of garbage bins on the transport path of the j-th garbage truck in any target particle and the set of garbage bins on the transport path of the k-th garbage truck in any other particle, and the number of garbage bins in the union, respectively. To obtain the maximum value, is the maximum value of the length of the common path between the transport paths of the j-th garbage truck and the k-th garbage truck, , are the lengths of the transportation paths of the j-th garbage truck and the k-th garbage truck respectively.

[0045] The more the number of identical garbage bins between two transport paths is, the greater the similarity between the two transport paths is; the longer the path that the two transport paths travel together is, the greater the similarity between the transport paths of the two garbage trucks is.

[0046] In another embodiment, since the paths of garbage trucks to collect garbage bins have a sequence and can be regarded as a topological structure, the similarity of the transportation paths of two garbage trucks is calculated based on the connection relationship between the garbage bins in the transportation paths of the garbage trucks.

[0047] Specifically, the similarity for: ;in, , are the number of garbage bins with the same connection relationship and the number of garbage bins with different connection relationship on the transportation path of the j-th garbage truck in any target particle and the k-th garbage truck in any other particle, respectively.

[0048] The number of identical connection relationships is the number of common paths on the transport paths of the two garbage trucks.

[0049] For example, taking garbage truck A and garbage truck B as examples, whether the connection relationship is the same is introduced: when the garbage trucks are transferring garbage, the garbage bins passed by garbage truck A in the transportation path are garbage bin a, garbage bin b, garbage bin c, garbage bin d, garbage bin e, garbage bin f, garbage bin g, and garbage bin q in sequence; and the garbage bins passed by garbage truck B in the transportation path are garbage bin b, garbage bin c, garbage bin d, garbage bin x, garbage bin f, garbage bin g, and garbage bin l in sequence. At this time, the paths of garbage truck A and garbage truck B passing through the garbage bins are the same in the connection relationship bcd and the connection relationship fg. At this time, there are 2 connection relationships that are the same, and there are 5 connection relationships that are different, including ab, def, gq, dxf, and gl. See details. Figure 2 .

[0050] In this embodiment, the process of performing mutation operation on each similar particle is as follows: According to the mutation probability, the transportation path of each garbage truck in each similar particle is mutated to obtain a new particle after mutation; the mutation probability for: ; is a natural constant, is the matching degree between the hth new particle at the nth iteration and the global optimal solution before the nth iteration, where n is greater than 1.

[0051] The above matching degree is the sum of the similarities between each garbage truck in the hth new particle and each garbage truck in the global optimal solution before the nth iteration when the maximum matching algorithm is used for matching. This similarity is used as the edge weight in the maximum matching algorithm.

[0052] The similarity calculation method is the same as the similarity calculation method in the above two embodiments.

[0053] The above mutation probability refers to the number of particle transformations. The above global optimal solution is the optimal solution obtained after each iteration.

[0054] It should be noted that when performing mutation operation, considering that the direction of all particle iterations is to iterate in the direction of the global optimal solution, when the matching degree between the particle and the global optimal solution is high, the difference between the particle and the global optimal solution is small, and the probability of particle mutation during iteration is small; on the contrary, when the matching degree between the particle and the global optimal solution is low, the probability of particle mutation during iteration is greater, because the difference between the particle and the global optimal solution is large at this time, and the current particle is definitely not the global optimal solution. Therefore, in the above embodiment, the probability of mutation of each particle is calculated based on the similarity between each particle in the current iteration and the global optimal solution before the current iteration.

[0055] Step S23, perform multiple iterations of updates according to S22 until the set conditions are met and stop updating to obtain the final global optimal solution to obtain the best collaborative transport path.

[0056] When performing iterations, the set condition for stopping the iteration is: the difference between the maximum evaluation function values ​​obtained from the previous and subsequent iterations is less than the set threshold or the maximum number of iterations is reached.

[0057] The maximum number of iterations may be 50 or 100; the threshold is set to 0.01; of course, it may be set according to actual conditions.

[0058] The above-mentioned iterative method is used for optimization, and after the optimization is completed, the best collaborative transport path can be obtained.

[0059] In this embodiment, according to the above-mentioned improved optimization algorithm, the best coordinated transport path of the target area can be obtained.

[0060] The intelligent optimization algorithm of the present invention may be a particle swarm algorithm, a genetic algorithm, etc. When the intelligent optimization algorithm is a particle swarm algorithm, the mutation operation in the genetic algorithm is introduced to obtain the best collaborative transport path.

[0061] The solution of the present invention can monitor the amount of garbage generated, its distribution and the operating status of garbage trucks in real time according to big data technology. Based on these data, the route, time, transportation volume, etc. of garbage transfer can be dynamically optimized according to real-time information.

[0062] The present invention also provides a garbage collaborative transport system based on big data. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the above-mentioned method for coordinated garbage transfer based on big data according to the present invention is implemented.

[0063] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0064] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented by computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0065] In the description of this specification, “plurality” means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0066] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the idea and spirit of the present invention.

Claims

1. A garbage collaborative transport method based on big data, characterized in that: include: Initialize a particle swarm and set the size of the particle swarm. Each particle represents a coordinated transport path, where the coordinated transport path is a comprehensive transport path for multiple garbage trucks in a target area to coordinately transport garbage in multiple garbage bins. Calculate the evaluation function value of each particle, select the particle corresponding to the maximum evaluation function value as the current optimal solution; iteratively update each particle to obtain a new particle, continue to calculate the evaluation function value of each new particle, and obtain the current global optimal solution; perform multiple iterative updates until the set conditions are met, stop updating, and obtain the final global optimal solution to obtain the best collaborative transport path; Among them, the evaluation function value for: ; is the normalization function, is the filling degree of the jth garbage truck in any particle at the mth iteration, is the filling degree of the ith trash bin in any particle at the mth iteration, is the ratio of the loading capacity of a single garbage truck to that of a single garbage bin, a>1, is a natural constant, is the length of the transportation path of the jth garbage truck in any particle at the mth iteration, J is the number of garbage trucks, and I is the number of garbage bins.

2. The method for coordinated garbage transportation based on big data according to claim 1, characterized in that: The iterative updating of each particle includes: screening each particle to obtain a target particle, and performing a mutation operation on a similar particle of each target particle to obtain a mutated new particle.

3. The method for coordinated garbage transportation based on big data according to claim 1, characterized in that: The similar particles are: Taking particles whose evaluation function values ​​are greater than a threshold as target particles; searching for particles similar to each target particle; The similar particles are obtained by matching the target particle with any other particle using a maximum matching algorithm; when performing the maximum matching, the edge weight at the maximum matching is the similarity between the target particle and the garbage truck in the other particles.

4. The method for coordinated garbage transportation based on big data according to claim 3 is characterized in that: The similarity for: ； in, , are the number of garbage bins in the intersection of the set of garbage bins on the transport path of the j-th garbage truck in any target particle and the set of garbage bins on the transport path of the k-th garbage truck in any other particle, and the number of garbage bins in the union, respectively. To obtain the maximum value, is the maximum value of the length of the common path between the transport paths of the j-th garbage truck and the k-th garbage truck, , are the lengths of the transportation paths of the j-th garbage truck and the k-th garbage truck respectively.

5. The method for coordinated garbage transportation based on big data according to claim 3 is characterized in that: The similarity is the ratio of the number of garbage bins with the same connection relationship on the transportation path of each garbage truck in any target particle and any garbage truck in any other particle to the number of garbage bins with different connection relationships; the same connection relationship means that the paths passing through the garbage bins on the transportation paths of the two garbage trucks are the same.

6. The method for coordinated garbage transportation based on big data according to claim 2, characterized in that: The mutation operation on each similar particle includes: According to the mutation probability, the transportation path of each garbage truck in each similar particle is mutated to obtain a new particle after mutation; the mutation probability for: ; is a natural constant, is the matching degree between the hth new particle at the nth iteration and the global optimal solution before the nth iteration, n is greater than 1, and the matching degree is the sum of all edge weights when the maximum matching algorithm is used for matching.

7. The method for coordinated garbage transportation based on big data according to claim 1, characterized in that: The setting condition is that the difference between the maximum evaluation function values ​​obtained from two consecutive iterations is less than a set threshold or the maximum number of iterations is reached.

8. The method for coordinated garbage transportation based on big data according to claim 6, characterized in that: The number of the similar particles is the same as the size of the particle group, which is 100.

9. The method for coordinated garbage transportation based on big data according to claim 1, characterized in that: The filling degree of the trash can is: the ratio of the actual amount of trash in the trash can to the corresponding rated loading amount; or, the ratio of the depth of the garbage in the bin to the depth of the corresponding bin; The filling degree of the garbage truck is: the ratio of the actual amount of garbage in the garbage truck to the rated loading capacity of the corresponding garbage truck.

10. A garbage collaborative transport system based on big data, characterized in that: include: processor; A memory storing computer instructions for coordinated garbage transfer based on big data. When the computer instructions are executed by the processor, the system executes a method for coordinated garbage transfer based on big data according to any one of claims 1 to 9.

Images