Garbage clearance vehicle path planning method considering dynamic demand

Abstract

The invention relates to a garbage clearance vehicle path planning method considering a dynamic demand, and the method comprises the steps: obtaining first clearance planning information after receiving a new clearance request sent by at least one target collection point; detecting first path planning information corresponding to the target clearing day from all first path planning information of the first clearing planning information, and performing path planning updating by using a TLBO algorithm based on the first path planning information and target information of the target collection point to generate second path planning information corresponding to the target clearing day; when it is judged that the target collection point requests to carry out clearing on each periodic clearing day except the target clearing day, path re-planning is carried out on the target collection point and a first collection point associated with each periodic clearing day by using a GA algorithm, and third path planning information corresponding to each periodic clearing day is generated; and taking the second path planning information and the third path planning information as corresponding planning results.

Description

Technical Field

[0001] This application relates to the technical field of garbage collection and transportation, and particularly to a method for planning the routes of garbage collection and transportation vehicles considering dynamic demands. Background Art

[0002] The collection and transportation of municipal domestic garbage is a daily task that lasts for a long time and needs to be carried out according to a plan every day. However, on a relatively long time scale, the garbage collection and transportation demand is not constant, but has the characteristics of dynamic changes. Such changes may be affected by various factors such as holiday activities, population flow, and urban development, manifested as an increase or decrease in the collection volume or a change in the collection date.

[0003] In related technologies, there are differences in the required collection and transportation service frequencies between domestic garbage collection points, which brings difficulties to the garbage collection and transportation parties in formulating vehicle route plans. Among them, for collection points with a fixed collection and transportation frequency, during the process of the collection and transportation fleet selecting a service plan for such collection points and implementing it, there will also be dynamic changes. For example, some collection points may adjust their collection and transportation arrangements due to special circumstances, or newly signed collection points need to be included in the collection and transportation plan, thus putting forward a need for amending the original collection and transportation route plan; for collection points with an unfixed collection and transportation frequency, the garbage generation volume at the locations of such collection points is small and volatile, and they will send out collection and transportation demands irregularly. These collection points with unfixed collection and transportation frequencies bring dynamics to the garbage collection and transportation route plan and pose challenges to the reasonable planning of their collection and transportation service routes.

[0004] In related technologies, the scheme for planning the routes of domestic garbage collection and transportation is to plan the vehicle routes based on static demands, and the planning of the collection and transportation service routes to meet dynamic demands is unreasonable, resulting in untimely garbage collection and transportation, causing environmental negative effects, and high collection and transportation costs.

[0005] Currently, for the scheme of planning the routes of domestic garbage collection and transportation in related technologies, it is easy to lead to untimely collection and transportation and the explosion of collection points, which in turn causes secondary pollution, an increase in environmental negative effects, and high collection and transportation costs, and no effective solution has been proposed yet. Summary of the Invention

[0006] The embodiments of this application provide a method for planning the routes of garbage collection and transportation vehicles considering dynamic demands, so as to at least solve the problems in the scheme for planning the routes of domestic garbage collection and transportation in related technologies, which are easy to lead to untimely collection and transportation and the explosion of collection points, and in turn cause secondary pollution, an increase in environmental negative effects, and high collection and transportation costs.

[0007] In a first aspect, an embodiment of the present application provides a garbage collection vehicle route planning method considering dynamic requirements, including: after receiving a new collection request sent by at least one target collection point, obtaining first collection plan information for collecting garbage from a plurality of current first collection points, where the new collection request includes target information and a target collection date of the target collection point, and the first collection plan information includes one of the collection plan information generated by iteratively planning the route using the TLBO-GA hybrid algorithm for the initial collection plan information and the initial collection plan information, and the initial collection plan information is generated by using the TLBO-GA hybrid algorithm to plan the collection date and the collection route for the initial collection points; detecting, from all the first route planning information of the first collection plan information, the first route planning information corresponding to the target collection date, and based on the corresponding first route planning information and the target information, using the TLBO algorithm of the TLBO-GA hybrid algorithm to update the route planning to generate the second route planning information corresponding to the target collection date; determining whether the target collection point requests collection on periodic collection dates other than the target collection date, and in the case where it is determined that the target collection point requests collection on each of the periodic collection dates, using the GA algorithm of the TLBO-GA hybrid algorithm to re-plan the routes for the target collection point and the first collection points associated with each of the periodic collection dates to generate the third route planning information corresponding to each of the periodic collection dates; and generating a planning result including second collection plan information according to the second route planning information and the third route planning information.

[0008] Compared with the related art, the garbage collection vehicle route planning method considering dynamic requirements provided by the embodiments of the present application, after receiving a new collection request sent by at least one target collection point, obtains the first collection and transportation planning information for cleaning up the current multiple first collection points. The first collection and transportation planning information includes one of the collection and transportation planning information generated by iteratively planning the route using the TLBO-GA hybrid algorithm for the initial collection and transportation planning information and the initial collection and transportation planning information. The initial collection and transportation planning information is generated by using the TLBO-GA hybrid algorithm to perform the collection day planning and the collection route planning for the initial collection points; from all the first route planning information of the first collection and transportation planning information, the first route planning information corresponding to the target collection day is detected, and based on the corresponding first route planning information and the target information, the TLBO algorithm of the TLBO-GA hybrid algorithm is used to update the route planning to generate the second route planning information corresponding to the target collection day; it is determined whether the target collection point requests collection and transportation on the periodic collection days other than the target collection day, and when it is determined that the target collection point requests collection and transportation on each of the periodic collection days, the GA algorithm of the TLBO-GA hybrid algorithm is used to perform route replanning for the target collection point and the first collection points associated with each of the periodic collection days to generate the third route planning information corresponding to each of the periodic collection days; according to the second route planning information and the third route planning information, a planning result including the second collection and transportation planning information is generated; by using the periodic optimization strategy in the dynamic adjustment stage and using the TLBO-GA hybrid algorithm for solution, the vehicle route plan corresponding to the first collection and transportation planning information is adjusted, and on the day of responding to the new demand point, the dynamic insertion strategy is used to insert the new point into the original vehicle route plan, and on the remaining days, the route is replanned according to the change of the service plan of the collection point, so as to realize the dynamic adjustment of the garbage collection vehicle route, and solve the problems in the related art that the route planning scheme for domestic garbage collection and transportation is prone to cause untimely collection and transportation and explosion of the collection point, resulting in secondary pollution, increased environmental negative effects and high collection and transportation costs.

[0009] Details of one or more embodiments of the present application are set forth in the following drawings and description, so that other features, objects, and advantages of the present application will become more comprehensible. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings: Figure 1 is a hardware structure block diagram of a terminal for the garbage collection vehicle route planning method considering dynamic requirements according to an embodiment of the present application; Figure 2 is a flowchart of a garbage collection vehicle path planning method considering dynamic demands according to an embodiment of the present application; Figure 3 is a flowchart of a garbage collection vehicle path planning method considering dynamic demands according to a preferred embodiment of the present application; Figure 4 is a schematic diagram of a gene sequence for performing a combined crossover operation according to an embodiment of the present application; Figure 5 is a structural block diagram of a garbage collection vehicle path planning device considering dynamic demands according to an embodiment of the present application; Figure 6 is a structural block diagram of a garbage collection vehicle path planning device considering dynamic demands according to a preferred embodiment of the present application. Detailed implementation manners

[0011] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be described and explained 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments provided in the present application without making creative efforts fall within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and time-consuming, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacturing or production changes made on the basis of the technical content disclosed in the present application are only conventional technical means and should not be understood as the content disclosed in the present application being insufficient.

[0012] Referring to "embodiment" in the present application means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those of ordinary skill in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0013] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the ordinary meanings understood by those with ordinary skills in the technical field to which this application belongs. The words such as "a", "an", "one", "the" and the like involved in this application do not indicate a limitation in quantity and may represent a singular or plural number. The terms "including", "comprising", "having" and any variations thereof involved in this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include unlisted steps or units, or may further include other steps or units inherent to these processes, methods, products or devices. The "multiple links" involved in this application refer to links greater than or equal to two. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may represent: A exists alone, A and B exist simultaneously, and B exists alone. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order of the objects.

[0014] The method embodiments provided in this embodiment can be executed on a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 1 is a hardware structure block diagram of a terminal for the garbage collection vehicle path planning method considering dynamic requirements in the embodiments of this application. As Figure 1 shown, the terminal may include one or more ( Figure 1 only one is shown in the figure) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the above terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic and does not limit the structure of the above terminal. For example, the terminal may further include more or fewer components than those shown in Figure 1 the figure, or have a different configuration from that shown in Figure 1 the figure.

[0015] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the garbage collection vehicle path planning method considering dynamic requirements in the embodiments of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above-mentioned method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories can be connected to the terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and combinations thereof.

[0016] The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include the wireless network provided by the communication provider of the terminal. In one instance, the transmission device 106 includes a network adapter (abbreviated as NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0017] This embodiment provides a garbage collection vehicle path planning method considering dynamic requirements running on the above-mentioned terminal. Figure 2 It is a flowchart of the garbage collection vehicle path planning method considering dynamic requirements according to the embodiments of the present application, as Figure 2 shown, and this process includes the following steps:

[0018] Step S201, after receiving a new garbage collection request sent by at least one target collection point, obtain the first garbage collection planning information for garbage collection of the current multiple first collection points, where the new garbage collection request includes the target information and target garbage collection date of the target collection point, and the first garbage collection planning information includes one of the garbage collection planning information and the initial garbage collection planning information generated by iteratively planning the path of the initial garbage collection planning information using the TLBO-GA hybrid algorithm, and the initial garbage collection planning information is generated by planning the garbage collection date and garbage collection path for the initial collection points using the TLBO-GA hybrid algorithm.

[0019] In this embodiment, the execution entity for implementing the garbage collection vehicle route planning method of the embodiments of the present application is a management system or a decision-making system deployed at the collection party (e.g., a collection company) responsible for the collection task; in this embodiment, the vehicle route planning performed is a corrective planning, that is, when the collection points (corresponding demand customers) for garbage collection put forward dynamic collection demands according to the requirements, the currently executing collection planning information is corrected to achieve the goal of minimizing the collection cost and the lowest environmental negative effect while meeting the newly added dynamic collection demands; in this embodiment, the basis for the correction of the collection plan is the first collection plan information. At the same time, according to the timing of the newly added collection request sent by the target collection point, the correlation between the initial collection plan information and the first collection plan information is determined. For example, when the target collection point puts forward a newly added collection request and the execution entity has not corrected the initial collection plan information, the first collection plan information is the initial collection plan information; when the target collection point puts forward a newly added collection request and the initial collection plan information has been iterated at least once, at this time, the first collection plan information is the corresponding collection plan information generated by the previous iteration according to the route planning method of the embodiments of the present application before the current time; it should be understood that in this embodiment, when planning the initial collection plan information, for the initial collection points with a fixed collection frequency, the teaching-learning-based optimization and genetic algorithm (TLBO-GA algorithm) are used to plan the service plan (corresponding to the collection day plan) and the collection route for each collection day. Among them, the teaching-learning-based optimization algorithm (Teaching-Learning-Based Optimization, abbreviated as TLBO) of the TLBO-GA algorithm is used to determine the collection day plan for each initial collection point, and the genetic algorithm (Genetic Algorithm, abbreviated as GA) of the TLBO-GA algorithm is used to solve the collection route plan for each day to form a complete periodic vehicle route plan.

[0020] In the embodiments of the present application, the collection point is a garbage station for collecting domestic garbage, and the collection party is the main body responsible for the collection task. By arranging the collection vehicles it owns or is associated with, starting from the garbage transfer station (the starting point of the vehicle route), passing through the corresponding collection points for garbage collection, and then returning to the corresponding transfer station; it should be noted that the collection vehicle route planned in the embodiments of the present application is default to start from the corresponding garbage transfer station and return to the set garbage transfer station after completing the collection task, that is, the starting points of the collection vehicle routes all correspond to the garbage transfer stations, and the collection points are not considered as the corresponding starting points.

[0021] Step S202: Detect, from all the first path planning information of the first waste collection plan information, the first path planning information corresponding to the target waste collection date, and based on the corresponding first path planning information and the target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning and generate the second path planning information corresponding to the target waste collection date.

[0022] In this embodiment, according to the waste collection frequency of the collection points, the target collection points can be divided into two types: the fixed waste collection frequency type and the non-fixed waste collection frequency type (temporary waste collection type). Furthermore, the received new waste collection requests include: an existing collection point of the fixed waste collection frequency type (a first collection point) requests waste collection on a date other than the waste collection date corresponding to the first waste collection plan information (corresponding to the day when the request is sent), a newly added collection point of the fixed waste collection frequency type requests waste collection on a determined waste collection date (determined based on the request date and the corresponding waste collection frequency), and a certain collection point of the non-fixed waste collection frequency type requests waste collection on the same day from the waste collection party at any time.

[0023] In this embodiment, to ensure the timeliness of waste collection and transportation and reduce the computing resources during the process of corrective planning, on the day when three new waste collection and transportation requests are proposed, it is set that a response is required for all of them. And the target collection point is inserted into the waste collection and transportation vehicle route existing on the day when the request is proposed, that is, the target collection point of the proposed request is added to the waste collection and transportation vehicle route corresponding to the first path planning information (regarding the target collection point as the service object to be waste-collected and transported), so as to adjust the original vehicle route planning corresponding to the target waste collection and transportation day (the day when the target collection point proposes a new waste collection and transportation request); in this embodiment, during the process of adjusting the original vehicle route planning corresponding to the target waste collection and transportation day, the TLBO algorithm is used to update the route planning, so as to generate the second path planning information that meets the waste collection and transportation requirements on the target waste collection and transportation day; it should be noted that before correcting and adjusting the original vehicle route corresponding to the target waste collection and transportation day, while meeting the new waste collection and transportation request for the target collection point, it is also necessary to judge whether the target collection point can be inserted into the original vehicle route on the day, and judge whether the newly added waste collection and transportation demand meets the vehicle remaining capacity constraint, and / or whether the current waste collection and transportation working time exceeds the specified waste collection and transportation working time; at the same time, for a certain collection point with an unfixed waste collection and transportation frequency that proposes to conduct waste collection and transportation on the day, the waste collection and transportation party should try to respond on the day of the request, and by checking the remaining vehicle capacity and remaining working time of all vehicle trips in the original waste collection and transportation work plan on that day, find a vehicle route that can be inserted. If there is no vehicle route that simultaneously meets the vehicle capacity constraint and the working time constraint, then check whether the number of trips of each vehicle has reached the upper limit. If it has not reached the upper limit, then choose to increase the vehicle departure trips to meet the waste collection and transportation demand; it can be understood that if it has reached the upper limit, then force it to be inserted into the waste collection and transportation route plan of the next waste collection and transportation working day (the next day after the target waste collection and transportation day). At this time, the day after the day when the request is proposed is used as the target waste collection and transportation day, and the steps of updating the route planning using the TLBO algorithm of the TLBO-GA hybrid algorithm based on the corresponding first path planning information and target information are executed.

[0024] Step S203: Judge whether the target collection point requests to conduct waste collection and transportation on the periodic waste collection and transportation days other than the target waste collection and transportation day. And in the case of judging that the target collection point requests to conduct waste collection and transportation on each periodic waste collection and transportation day, use the GA algorithm of the TLBO-GA hybrid algorithm to re-plan the routes for the target collection point and the first collection points associated with each periodic waste collection and transportation day, and generate the third path planning information corresponding to each periodic waste collection and transportation day.

[0025] In this embodiment, when a new waste collection request is that a certain collection point with an unfixed collection frequency requests waste collection from the waste collection party on the same day, it means that the corresponding waste collection request is a one-time new demand. The waste collection party only provides services to the corresponding target collection point on the target waste collection day. For the waste collection days after the target waste collection day, the corresponding collection point remains unchanged. The waste collection day planning scheme and the waste collection route planning scheme in the first waste collection planning information are the schemes that meet the requirements and have the best waste collection effect. Therefore, for the waste collection days after the target waste collection day, waste collection services are provided according to the waste collection days corresponding to the first waste collection planning information and the existing route planning information within each corresponding waste collection day; in this embodiment, when the new waste collection request is one of the other two waste collection requests, the waste collection party also needs to provide waste collection services to the target collection point on the waste collection days after the target waste collection day. At this time, for the waste collection days after the target waste collection day, the GA algorithm is used to re-plan the routes for the target collection point and the first collection points associated with each periodic waste collection day to generate the corresponding third route planning information.

[0026] Step S204: Generate a planning result including the second waste collection planning information according to the second route planning information and the third route planning information.

[0027] In this embodiment, the second route planning information corresponding to the target waste collection day and the third route planning information corresponding to the waste collection days after the target waste collection day are merged into the new waste collection planning information after correction, that is, merged into the second waste collection planning information, and the waste collection vehicles belonging to the waste collection party are guided by the second waste collection planning information to collect garbage from the contracted collection points (including the first collection points and the target collection points) according to the plan until the waste collection task is completed.

[0028] Through the above steps S201 to S204, after receiving a new waste collection request sent by at least one target collection point, obtain the first waste collection plan information for collecting and transporting the current multiple first collection points; from all the first path planning information in the first waste collection plan information, detect the first path planning information corresponding to the target waste collection day, and based on the corresponding first path planning information and target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning, and generate the second path planning information corresponding to the target waste collection day; determine whether the target collection point requests waste collection on periodic waste collection days other than the target waste collection day, and in the case where it is determined that the target collection point requests waste collection on each periodic waste collection day, use the GA algorithm of the TLBO-GA hybrid algorithm to re-plan the paths of the target collection point and the first collection points associated with each periodic waste collection day, and generate the third path planning information corresponding to each periodic waste collection day; according to the second path planning information and the third path planning information, generate a planning result including the second waste collection plan information, adopt a periodic optimization strategy in the dynamic adjustment stage, and use the TLBO-GA hybrid algorithm to solve, so as to adjust the vehicle routing plan corresponding to the first waste collection plan information, and adopt a dynamic insertion strategy to insert the new point into the original vehicle routing plan on the day of responding to the new demand point, and re-plan the path according to the change of the service plan of the collection point on the remaining dates, realizing the dynamic adjustment of the waste collection vehicle path, and solving the problem that the path planning scheme for domestic waste collection in the related technology is likely to cause untimely waste collection and the explosion of the collection point, resulting in secondary pollution, increased environmental negative effects and high waste collection costs.

[0029] Figure 3 is a flowchart of a waste collection vehicle routing planning method considering dynamic demands according to a preferred embodiment of the present application, as Figure 3 shown, the process includes the following steps:

[0030] Step S301, after receiving a new waste collection request sent by at least one target collection point, obtain the first waste collection plan information for collecting and transporting the current multiple first collection points, where the new waste collection request includes the target information and the target waste collection day of the target collection point, and the first waste collection plan information includes one of the waste collection plan information generated by iteratively planning the path of the initial waste collection plan information using the TLBO-GA hybrid algorithm and the initial waste collection plan information, and the initial waste collection plan information is generated by using the TLBO-GA hybrid algorithm to plan the waste collection day and the waste collection path for the initial collection points.

[0031] Step S302: From all the first path planning information of the first waste collection plan information, detect the first path planning information corresponding to the target waste collection date. Based on the corresponding first path planning information and the target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning and generate the second path planning information corresponding to the target waste collection date.

[0032] Step S303: Determine whether the target collection point requests waste collection on periodic waste collection dates other than the target waste collection date. If it is determined that the target collection point does not request waste collection on each periodic waste collection date, update the first path planning information corresponding to the target waste collection date in the first waste collection plan information to the second path planning information to obtain the third waste collection plan information, and use the third waste collection plan information as the currently corresponding planning result.

[0033] In this embodiment, when the new waste collection request is that a certain collection point with an unfixed waste collection frequency requests waste collection on the same day from the waste collection party, it means that the corresponding waste collection request is a one-time new demand. The waste collection party only provides services to the corresponding target collection point on the target waste collection date. For the waste collection dates after the target waste collection date, the waste collection party provides services to the collection points corresponding to the first waste collection plan information (corresponding to the first collection points), and the corresponding collection points do not change. The waste collection date planning scheme and the waste collection path planning scheme in the first waste collection plan information are the schemes that meet the requirements and have the best waste collection effect. Therefore, for the waste collection dates after the target waste collection date, waste collection services are provided according to the waste collection dates corresponding to the first waste collection plan information and the existing path planning information within each corresponding waste collection date; in this embodiment, the second path planning information corresponding to the target waste collection date (corresponding to the vehicle routing scheme after the correction plan is completed) is replaced with the first path planning information corresponding to the target waste collection date (corresponding to the vehicle routing scheme before the correction plan), so as to generate a new waste collection plan information after the correction plan is completed, that is, generate the third waste collection plan information, and use the third waste collection plan information to guide the waste collection vehicles belonging to the waste collection party to perform waste collection on the contracted collection points (including the first collection point and the target collection point) according to the plan until the waste collection task is completed.

[0034] Through steps S301 to S303, after receiving a new waste collection request sent by at least one target collection point, obtain the first waste collection planning information for collecting waste from the current multiple first collection points; from all the first path planning information in the first waste collection planning information, detect the first path planning information corresponding to the target waste collection day, and based on the corresponding first path planning information and target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning, and generate the second path planning information corresponding to the target waste collection day; determine whether the target collection point requests waste collection on periodic waste collection days other than the target waste collection day. In the case where it is determined that the target collection point does not request waste collection on each periodic waste collection day, update the first path planning information corresponding to the target waste collection day in the first waste collection planning information to the second path planning information to obtain the third waste collection planning information, and use the third waste collection planning information as the current corresponding planning result, realizing the insertion of new points into the original vehicle routing plan by adopting a dynamic insertion strategy.

[0035] In some embodiments, determining whether the target collection point requests waste collection on periodic waste collection days other than the target waste collection day is implemented through the following steps:

[0036] Step 21, according to the target information, determine the waste collection frequency type of the target collection point, where the waste collection frequency type includes a fixed frequency type and a temporary waste collection type.

[0037] In this embodiment, a collection point with a fixed waste collection frequency type refers to the waste collection party providing waste collection services to the corresponding collection point according to the agreed waste collection frequency (for example: once a day, once every two days, once every three days).

[0038] Step 22, in the case where it is determined that the target collection point is a collection point with a fixed frequency type, determine that the target collection point requests waste collection on each periodic waste collection day.

[0039] In this embodiment, when the target collection point is a collection point with a fixed frequency type, it is determined that there must be waste collection days other than the target waste collection day for the target collection point, that is, it is determined that the waste collection party needs to provide waste collection services to the target collection point on waste collection days other than the target waste collection day. At this time, it is determined that the target collection point requests waste collection within each periodic waste collection day.

[0040] To determine the periodic waste collection days of the target collection point with a fixed frequency type, in some alternative embodiments, when it is determined that the target collection point is a collection point with a fixed frequency type, the following steps are also implemented:

[0041] Step 221, according to the target information, detect the target collection point among the first collection points.

[0042] In this embodiment, based on the target information, it is checked whether the target collection point is an existing first collection point, so as to determine whether the target collection point is a newly added collection point or an existing collection point.

[0043] Step 223, when the target collection point is detected, from the first waste collection plan information, obtain the first collection interval corresponding to the target collection point as the first collection point, and with the target waste collection day as the first day, at the time interval of the first collection interval, rearrange to generate the first periodic waste collection days excluding the target waste collection day, where the collection interval is used to represent the number of days between two adjacent waste collection days of the corresponding first collection point, and the first periodic waste collection days are the periodic waste collection days corresponding to the target collection point.

[0044] In this embodiment, when the target collection point is detected among the first collection points, it means that the target collection point is an existing collection point. At this time, the target waste collection day in the newly added waste collection demand requested by the target collection point is a waste collection day outside the original periodic waste collection days, that is, a request to correct the waste collection day service plan. However, since the agreed collection interval with the waste collection party remains unchanged, the waste collection days in the current waste collection cycle and subsequent waste collection cycles will change. For example: the target collection point is a collection point with a waste collection frequency of once every two days, and the corresponding waste collection day plan in the first waste collection plan information is {d1, d3, d5}. The target collection point submits a new waste collection request on the target waste collection day d2 when there is no original waste collection demand. After the waste collection party responds on d2, it will also change the subsequent periodic waste collection days, that is, with the target waste collection day d2 as the first day, arranged according to a waste collection frequency of once every two days, rearrange to generate the first periodic waste collection days excluding the target waste collection day, that is, change the waste collection day plan of the current cycle to {d2, d4, d6}. Since the target waste collection day d2 has been determined, the first periodic waste collection days generated by rearranging and excluding the target waste collection day are d3 and d5, and the waste collection day plan corresponding to the next waste collection cycle is {d2, d4, d6}.

[0045] Step 223, when the target collection point is not detected, obtain the preset waste collection frequency information from the target information of the target collection point, and after determining the second collection interval according to the waste collection frequency information, with the target waste collection day as the first day, at the time interval of the second collection interval, plan the second periodic waste collection days excluding the target waste collection day, where the second periodic waste collection days are the periodic waste collection days corresponding to the target collection point.

[0046] In this embodiment, when the target collection point is not detected at the first collection point, it means that the target collection point is a newly added collection point. At this time, all the collection days corresponding to the target collection point start with the target collection day, and are arranged at time intervals (for example: once every two days) determined according to the corresponding collection frequency information, generating the periodic collection days within a collection cycle. The target collection point is a collection point of the type of being collected once every two days. When the target collection point submits a new collection request on the target collection day d2, after the collection party responds on d2, the collection day plan {d2, d4, d6} will be used as the collection day plan service solution corresponding to the target collection point, and the collection service will also be provided to the target collection point with the collection day plan {d2, d4, d6} in the next collection cycle.

[0047] Step 23, in the case of determining that the target collection point is a collection point of the temporary collection type, it is determined that the target collection point does not request collection on each periodic collection day.

[0048] In this embodiment, when it is determined that the target collection point is a collection point of the temporary collection type, that is, the corresponding new collection request is that the target collection point, as a newly added collection point, temporarily requests the collection party to provide collection services, and only requests to provide one-time collection services. At this time, it can be determined that the target collection point does not request collection on collection days other than the target collection day.

[0049] Through the above steps 21 to 23, it is realized to determine whether the target collection point requests collection within the determined periodic collection days, so as to determine whether to only update the path planning using the TLBO algorithm to insert the target collection point into the vehicle path on the target collection day, and to determine whether it is necessary to perform the GA algorithm of the TLBO-GA hybrid algorithm to re-plan the paths of the target collection point and the first collection points associated with each periodic collection day, so as to re-plan the path planning of the collection days after the target collection day.

[0050] In order to formulate an initial collection plan for providing collection to the initial collection points that have signed contracts with the collection party, in some of these embodiments, before obtaining the first collection plan information, the following steps are also implemented:

[0051] Step 31: According to the preset hybrid coding rule, perform hybrid coding corresponding to the TLBO-GA hybrid algorithm on all initial collection points to generate multiple first hybrid coding bodies. Among them, the first hybrid coding body includes a first service coding body and a first vehicle route coding body. The first service coding body is used to represent an allocation result of assigning the first collection day for multiple initial collection points according to the corresponding waste collection service frequency, and the collection days within a cycle associated with the initial collection points are arranged starting from the first collection day at a collection interval corresponding to the waste collection service frequency. The first vehicle route coding body is used to represent a route planning result of using the target waste collection vehicle to collect waste from multiple initial collection points.

[0052] In this embodiment, after determining the initial collection points signed with the waste collection party, definition parameters will be input first, including population size, maximum number of iterations, crossover probability, mutation probability, collection point target information, available vehicle information, speed function, and noise value acceptance threshold function. After starting the initial decision-making plan, a set of random solutions related to the initial overall individuals will be generated to determine the waste collection day planning scheme and vehicle route plan selected for each collection point within the cycle. Then, the random solutions will be divided into two parts of decision variables. The teaching-learning-based optimization algorithm is used to perform evolutionary solution on the first part of the decision variables that determine the selection of the waste collection day planning scheme for the initial collection points, and the genetic algorithm (GA) is used to optimize the population individuals of the second part of the decision variables that determine the vehicle route for collecting waste from the initial collection points. The algorithm ends when the maximum number of iterations is reached. In this embodiment, it is set that within the target area, there is at least one waste transfer station and a certain number of waste collection points (corresponding to the initial collection points). There is a vehicle yard in the waste transfer station, and a certain number of different types of waste collection vehicles are parked, responsible for providing waste collection services for each initial collection point. The collection method is to pour the waste in the trash cans at the collection points into the compression device of the collection vehicle for loading, and each trip starts from the vehicle yard and finally the vehicle returns to the transfer station for unloading. The service object of the collection work is each waste collection point.

[0053] In the TLBO-GA hybrid algorithm of this embodiment, hybrid coding is selected and the decision variables are divided into two parts. The specific coding method is as follows: Suppose there are n initial collection points and the total number of days in the cycle is D days. Among them,

[0054] The first part of the decision variables is used to determine the day when each initial collection point is visited for the first time. The lower bound of this part of the decision variables is 1, and the upper bound of the first visit is determined by the known waste collection service frequency of the initial collection points, that is, the latest day d for providing waste collection service to the initial collection points. For example: among the initial collection points with a waste collection service frequency of once every three days, the date for providing waste collection service to the initial collection point can and can only be selected from the first three days of the cycle, that is, the lower bound is 1 and the upper bound is 3, and its time interval is known. Therefore, the subsequent waste collection days can be determined. That is, the number of the first part of the decision variables is equal to the number of initial collection points n, and the value range is [1, d]. Suppose there are 5 initial collection points, and the initial collection points require waste collection every day. Initial collection point 2, initial collection point 4, and initial collection point 5 require waste collection every two days, and initial collection point 3 requires waste collection every three days. Then one possible first service coding body is [1, 2, 3, 1, 2], which means that initial collection point 1 is first waste collected on the 1st day, initial collection point 2 is first waste collected on the 2nd day, initial collection point 3 is first waste collected on the 3rd day, initial collection point 4 is first waste collected on the 1st day, and customer 5 is first waste collected on the 2nd day. In decoding, a two-dimensional array of n*D is established to record the visit situation of each initial collection point in each time period: This array shows that the waste collection day planning scheme for initial collection point 1 in a cycle is ; the waste collection day planning scheme for initial collection point 2 and initial collection point 5 in a cycle is ; the waste collection day planning scheme for customer 3 in a cycle is ; the waste collection day planning scheme for initial collection point 4 in a cycle is .

[0055] The second part of the decision variables is used to determine the vehicle routes corresponding to the collection days within each period. Since the vehicles can make multiple departure trips, this part uses a combined coding. If the total number of days in the period is D, the number of vehicles is m, each vehicle can make f departure trips, and there are n collection points, then the variable length is (n + m×f)×D. For example, in a period of 6 days, there are 2 vehicles that can serve 5 initial collection points, and the maximum number of trips for each vehicle is 2. Then the variable length per day is 5 + 2×2 = 9, and the variable length for the complete period is 9×6 = 54. The chromosome does not contain the depot number, and the vehicle number is used as a symbol for the starting and ending points of the vehicle trips. For example, the sequence of multiple first vehicle path coding bodies corresponding to one collection day is [6, 1, 2, 7, 3, 6, 4, 5, 7], where the numbers 1 - 5 are the numbers of the initial collection points, and 6 and 7 are the vehicle numbers. The first trip corresponding to the first vehicle path coding body of the first vehicle is: transfer station - initial collection point 1 - initial collection point 2 - transfer station. The first trip corresponding to the first vehicle path coding body of the second vehicle is: transfer station - initial collection point 3 - transfer station. The second trip corresponding to the first vehicle path coding body of the first vehicle is: transfer station - initial collection point 4 - initial collection point 5 - transfer station. The second vehicle does not make a second trip.

[0056] In this embodiment, the number of decision variables in the first part and the second part are combined into an array to represent the structure of the entire decision variable. The total number of decision variables is equal to the sum of the number of decision variables in the first part and the second part. The decision variables in the first part determine the plan for the collection day schedule of the collection points, and the decision variables in the second part determine the path sequence of the vehicles regardless of the collection day schedule. Therefore, the final vehicle path plan needs to be screened according to the plan for the collection day schedule in the first part. Suppose on a certain day within the period, the vehicle path sequence for 5 initial collection points is [6, 1, 2, 7, 3, 6, 4, 5, 7], and the situation of the collection day schedule is , then initial collection point 2 and initial collection point 5 do not need to be collected on this day. After removing the collection points that do not need to be collected, the actual path sequence is [6, 1, 7, 3, 6, 4, 7].

[0057] Step 32, after determining the fitness corresponding to each first hybrid coding body by using the fitness function corresponding to the TLBO-GA hybrid algorithm, based on the random selection of the first service coding body and the first vehicle route coding body, perform one of the following iterative operations: perform sub-population search iteration on the selected first service coding body by using the TLBO algorithm, and perform sub-population genetic evolution operation on the selected first vehicle route coding body by using the GA algorithm. Wherein, during the execution of the selected iterative operation, use the fitness corresponding to each first hybrid coding body as the fitness of the corresponding sub-population. The fitness function is based on the waste collection departure cost, waste collection transportation cost, overloading waste collection penalty cost, the first penalty cost generated by exceeding the total waste collection working time, and the second penalty cost generated by the noise value exceeding the threshold. The first penalty cost and the second penalty cost are determined according to a preset time-dependent function.

[0058] In this embodiment, before obtaining the first waste collection planning information, plan the waste collection routes of the known initial collection points with a fixed waste collection frequency within a waste collection plan cycle to obtain a periodic waste collection route plan, that is, the initial waste collection planning information, and realize the optimization of the time-dependent multi-vehicle multi-trip periodic vehicle route with waste collection day planning with the goal of minimizing costs; in this embodiment, make the following assumptions for the following mathematical model: 1. Assume that the time-variation of the vehicle driving speed is only related to the characteristics of the functional area where it is located, and do not consider the time-variation caused by weekends and other holidays or accidental events; 2. The fuel tank state of the waste collection vehicle is full before each work, and the gasoline will not be exhausted, that is, do not consider the time and cost caused by refueling; 3. When the vehicle speed changes, do not consider the vehicle acceleration or deceleration time; 4. The total amount of waste collected in each route per trip does not exceed the maximum load capacity of the vehicle, and the waste collection demand of each initial collection point is determined; 5. The trash cans for waste collection at each initial collection point are defaulted to be full, and the difference in the amount of waste between the initial collection points is reflected in the difference in the number of trash cans; 6. There is only one driving route between every two initial collection points, and the route is known; 7. Only consider the noise generated when the compression device carried by the waste collection vehicle is running, and do not consider other noises generated during the driving of the vehicle itself.

[0059] In this embodiment, the fitness function corresponding to the TLBO-GA hybrid algorithm is formed by combining the capacity constraint condition (mapping the corresponding time-dependent function) and the objective function, and the overloading penalty factor is set to 10 8 , and the fitness function is: Wherein, represents the overloading waste collection penalty cost, and the objective function is: M = M1 + M2 + M3 + M4, M1 = , represents the waste collection departure cost; M2 = , representing the cost of waste transportation, M3 = , representing the first penalty cost incurred for exceeding the total waste transportation working hours; M4 = , representing the second penalty cost incurred for the noise value exceeding the threshold.

[0060] In this embodiment, the fitness function also obeys the following constraints: 1. It is restricted that each trip of the vehicle must start from the depot every day and return to the depot after completing the trip task. The corresponding constraint function is: ; 2. Each initial collection point can and can only select one waste transportation day planning scheme. The corresponding constraint function is: ; 3. The load of the vehicle during each waste transportation trip every day cannot exceed its maximum capacity, and only the selected vehicles can be used. The corresponding constraint function is: ; 4. The connectivity of the vehicle route is restricted. The corresponding constraint function is: ; 5. Each trip must start from the parking lot once. The constraint formula is: ; 6. The waste transportation vehicle satisfies the multi-trip constraint. The constraint formula is: ; 7. Each initial collection point is visited at most once every day. The constraint formula is: ; 8. Restrict the maximum number of departures of each vehicle every day. The constraint formula is: ; 9. The total working hours per day, ; 10. According to the waste transportation day planning scheme selected for the initial collection point, the vehicle needs to provide corresponding waste transportation services for the initial collection point on the waste transportation day specified in the scheme, and each initial collection point is served by at most one vehicle in one trip every day. The constraint formula is: ; 11. The logical relationship between the waste transportation day variable and the route variable. The relational formula is: ; 12. Calculate the instantaneous noise value received at the receiving point ; 13. Calculate the total noise received at the receiving point corresponding to the waste transportation at the initial collection point i on the d-th day ; 14. Decision on the selection of a limited path, with the functional form: ; 15. Decision on the selection of the waste collection day planning scheme for each initial collection point, with the functional form: ; 16. Decision on the selection of the waste collection day planning scheme for the initial collection points in a single trip, with the functional form: ; 17. Constraint on whether each vehicle is selected for use each day: .

[0061] Among them, T represents the total working time, D represents the cycle, M represents the vehicle plan, i represents the i-th initial collection point, j represents the j-th initial collection point, i ∈ I, j ∈ I, I represents the set of initial collection points, K represents the set of waste collection service plans, F represents the multi-trip set parameter of waste collection vehicles, c s represents the vehicle departure cost, c u represents the unit combustion cost, c z represents the unit transportation cost, represents the penalty cost for exceeding the working time on the d-th day, represents the penalty cost generated due to the receiving point corresponding to the initial collection point i receiving noise exceeding the threshold; v ij represents the driving speed of the route from the initial collection point i to the initial collection point j, t ij represents the driving time of the route from the initial collection point i to the initial collection point j, l ij represents the length of the route from the initial collection point i to the initial collection point j, q i represents the waste collection demand of the initial collection point i, q0 represents the amount of garbage processed by the compressor per unit time, Q m represents the vehicle capacity, T max represents the maximum allowable working time per day, T d represents the total working time on the d-th day, s i represents the straight-line distance between the initial collection point i and the nearest noise initial collection point, L w represents the noise value generated by the compression device at the initial collection point, P i represents the highest acceptable noise threshold at the receiving point corresponding to the initial collection point i, β represents the compression coefficient determined according to the vehicle type, represents whether the k-th waste collection service requires waste collection on the d-th waste collection day, = 1 indicates a requirement, , indicates others, o represents the waste collection vehicle parking lot, o ∈ I; is a path variable, It means that the path of vehicle m on the d-th day from the initial collection point i to the initial collection point j in the f-th trip is selected. It means that it is not selected. It is a service variable. When it is equal to 1, it means that vehicle m provides waste collection service for the initial collection point i on the d-th day in the f-th trip. When it is equal to 0, it means that no service is provided; yik is an assignment variable. When it is equal to 1, it means that the waste collection service k selected by the initial collection point i. When it is equal to 0, it means that it is not selected. = 1 means that vehicle m departs for the f-th time on the d-th day.

[0062] It should be noted that when planning the path of waste collection vehicles in the urban road network, it is easy to ignore the time-varying nature of the vehicle driving speed and the negative environmental effects caused by the noise pollution during the operation of waste collection vehicles, resulting in a high cost of the waste collection system and affecting the quality of residents' lives. Therefore, the fitness function of the embodiment of the present application fully considers the time-dependent functions affecting the noise threshold and speed, and then determines the first penalty cost generated by exceeding the total waste collection working time and the second penalty cost generated by the noise value exceeding the threshold.

[0063] In this embodiment, after determining the fitness corresponding to the first hybrid coding body, corresponding operations will be performed on the sub-populations corresponding to the first part of decision variables and the second part of decision variables, and which part of the corresponding sub-population is randomly selected. For example: after completing the fitness corresponding to the current corresponding hybrid coding body, one of the first service coding body and the first vehicle path coding body can be selected, and then a corresponding iterative operation is performed once.

[0064] Step 33: Combine one of the first service coding body and the first vehicle path coding body that has completed the selected iterative operation with the other one that has not performed the corresponding iterative operation to obtain a plurality of second hybrid coding bodies, and after determining the fitness corresponding to each second hybrid coding body, perform the corresponding random selection and iterative operation.

[0065] In this embodiment, after one iteration operation is performed, the next iteration operation can be to repeat the previous iteration operation. For example, perform the sub-population search iteration on the selected first service coding body using the TLBO algorithm as performed in the previous time, or it can be to perform an iteration operation that was not performed last time. For example, perform the sub-population genetic evolution operation on the selected first vehicle route coding body using the GA algorithm. At the same time, it can be understood that in multiple iteration operations, the same sub-population can be repeatedly selected, or different sub-populations can be alternately selected. For example, set the sub-population search iteration on the service coding body as W, and set the sub-population genetic evolution operation on the vehicle route coding body as x. Then the iteration operations performed can be w1(x1), w2(x1), (w2)x2, w3(x2), w4(x2). When performing the next iteration operation, for the fitness calculation of the individuals in the sub-population, the corresponding hybrid coding body is used to calculate the corresponding fitness. For example, when generating w2 during the iteration operation, the hybrid coding body corresponding to w2x1 is used to calculate the fitness.

[0066] Step 34, repeatedly execute the steps of determining the fitness of the corresponding hybrid coding body, randomly selecting one of the service coding body and the vehicle route coding body corresponding to the corresponding hybrid coding body, and performing the corresponding iteration operation until the fitness of the corresponding hybrid coding body is higher than the fitness threshold to obtain the target hybrid coding body, and decode the target service coding body and the target vehicle route coding body corresponding to the target hybrid coding body, and use the decoded first-day waste collection plan information and waste collection route plan information as the initial waste collection plan information.

[0067] In this embodiment, whether it is to perform the sub-population search iteration on the selected first service coding body using the TLBO algorithm or to perform the sub-population genetic evolution operation on the selected first vehicle route coding body using the GA algorithm, both are steps well-known and achievable by those skilled in the art. Therefore, performing the sub-population search iteration on the selected first service coding body using the TLBO algorithm and performing the sub-population genetic evolution operation on the selected first vehicle route coding body using the GA algorithm do not constitute an unclear limitation to the embodiments of this application.

[0068] In this embodiment, an initial population is initialized based on the encoded first service coding body and the first vehicle path coding body. Among them, for the first service coding body corresponding to the first part of the decision variables, several individuals that meet the service frequency conditions of each initial collection point are randomly generated, so as to form an initial population composed of several individuals; the initialization process of the second part of the decision variables of each individual is as follows: starting from the transfer station, continuously randomly select initial collection points from the initial collection point list and add them to the path. If the capacity constraint of the vehicle is reached, insert the transfer station node to construct the next trip sub-path. Repeat the above steps until all initial collection points are added to the path, thereby generating a complete path. Subsequently, repair operations are performed on individuals that violate the constraints to increase the diversity and effectiveness of the initial population; in this embodiment, when completing the iteration operation for the individuals of the sub-populations corresponding to the two parts of the decision variables, a strong elite strategy is adopted for the selection of sub-population individuals, that is, when selecting sub-population individuals, the parent generation and the offspring generation are merged, sorted according to the fitness from small to large, and the N individuals with the highest fitness are selected as the new population.

[0069] In this embodiment, the first service coding body and the first vehicle path coding body corresponding to the first hybrid coding body are split and decoded through the splitting program Split, and one of the sub-populations corresponding to the first service coding body and the first vehicle path coding body is randomly selected for evolution. In this embodiment, the corresponding hybrid coding body is split into two sub-populations for evolution operations respectively. Specifically,

[0070] 1. When the sub-population for the first part of the decision variables is selected (corresponding to the first service coding body), the TLBO algorithm is used to evolve it. Specifically,

[0071] Teaching stage: Calculate the average fitness of the current population (calculated based on the corresponding hybrid coding body), and select the individual with the best current fitness as the teacher , according to the update formula , where is the teaching factor, r is the learning step size, and its dimension is the same as the number of decision variables of the individual, and both are randomly generated. For example: the population mean is [1, 1.6, 2.8, 1.4, 1.7], the teacher individual is [1, 1, 2, 2, 2], and the current solution is [1, 2, 3, 1, 2]. As a student learning from the teacher, the randomly generated teaching factor is 1, and the learning step size r is [0.5, 0.3, 0.7, 0.2, 0.4], then the new solution is: newindividual = [1, 2, 3, 1, 2] + [0.5, 0.3, 0.7, 0.2, 0.4] × ([1, 1, 2, 2, 2] - 1 × [1, 1.6, 2.8, 1.4, 1.7])

[0072] =[1, 1.82, 2.44, 1.12, 2.12]. The first part of the decision variables is integer-coded. Therefore, after further rounding operations, the new solution is [1, 2, 2, 1, 2]. Then, a fitness comparison is performed to decide whether to keep the new solution.

[0073] Learning stage: Randomly select another student individual, compare their fitness values, and the student with the poorer fitness learns from the student with the better fitness. The update formula is: For example, the randomly selected student individual is [1, 1, 1, 1, 2], and its fitness value is less than that of the current individual [1, 2, 3, 1, 2]. Therefore, learning occurs. A learning step size of [0.8, 0.1, 0.6, 0.3, 0.5] is randomly generated again for the learning stage. Then the new solution is: newindividual = [1, 2, 3, 1, 2] + [0.8, 0.1, 0.6, 0.3, 0.5] × ([1, 1, 2, 2, 2] - [1, 2, 3, 1, 2]) = [1, 1.9, 1.8, 1, 2]. After further rounding operations, the new solution is [1, 2, 2, 1, 2]. Then, a fitness comparison is performed to decide whether to keep the new solution.

[0074] 2. When the sub-population of the second part of the decision variables (corresponding to the first vehicle route coding body) is selected, an improved GA algorithm is used to perform genetic evolution operations on it. In this embodiment, an improved combination crossover operation and a commonly used existing mutation operation are used to achieve genetic evolution iteration of the sub-population.

[0075] In this embodiment, it is preferably to use the interval reverse mutation method for the mutation operation, that is, each path sub-code in the first vehicle route coding body has a certain probability of triggering mutation. Traverse each path sub-code. Once a path sub-code triggers mutation, randomly select a path sub-code at another position from the current corresponding vehicle route coding body and reverse the order within this interval. Suppose the sequence of path sub-codes of a certain first vehicle route coding body is: individual 1 = [6, 1, 2, 7, 3, 6, 4, 5, 7], and the mutation rate mutationrate = 0.01. If the mutation is triggered at the path sub-code r0 = 1, randomly select another path sub-code r1 = 4 and ensure that r0 < r1, and reverse the coding values between the two. Then individual 1 = [6, 1, 2, 7, 3, 6, 4, 5, 7] becomes new individual 1 = [6, 4, 6, 3, 7, 2, 1, 5, 7], which is recorded as the new vehicle route coding body.

[0076] In this embodiment, the maximum number of iterations is set as the termination condition of the algorithm. The selection and evolutionary operations in the above algorithm are repeated until the maximum number of iterations is reached, at which point the calculation is terminated and the current optimal solution is output, forming the service date plan selection for each collection point within a cycle and the vehicle routing plan for each day.

[0077] Through the above steps 31 to 33, the initial waste collection plan information is generated based on the TLBO-GA hybrid algorithm, thereby planning the waste collection routes of the known fixed collection points with a fixed collection frequency within a waste collection plan cycle, and obtaining the periodic domestic waste collection route plan.

[0078] To achieve the response to dynamic demands, the target collection point is inserted into the vehicle routing of the waste collection vehicle corresponding to the target waste collection day when a new waste collection request is proposed. In some embodiments, based on the corresponding first routing plan information and target information, the TLBO algorithm of the TLBO-GA hybrid algorithm is used to update the routing plan for responding to dynamic demands, generating the second routing plan information corresponding to the target waste collection day, which is achieved through the following steps:

[0079] Step 41: Determine the third hybrid coding body corresponding to the first waste collection plan information, and determine the first coding body corresponding to the third hybrid coding body. The third hybrid coding body further includes a second service coding body used to represent that the first waste collection day of the corresponding collection point is assigned as the target waste collection day. The first coding body is associated with the first vehicle routing corresponding to the first routing plan information corresponding to the target waste collection day. The first coding body includes a plurality of first sub-codings, each first sub-coding is associated with a first collection point that is a routing node on the first vehicle routing, and the coding position corresponding to each first sub-coding is used to represent the order of waste collection for the first collection point.

[0080] In this embodiment, on the target waste collection day corresponding to the response to the new demand request, the dynamic insertion strategy is adopted to insert the new target collection point into the original vehicle routing plan. Therefore, it is necessary to obtain the first coding body (corresponding to a vehicle routing coding body) representing the first routing plan information corresponding to the target waste collection day from the hybrid coding body corresponding to the first waste collection plan information, and use this first coding body as the initial individual to perform the population search iteration based on the TLBO algorithm to achieve the update of the routing plan for responding to dynamic demands.

[0081] It should be noted that during the operation of the TLBO-GA hybrid algorithm, the corresponding hybrid coding body is used as an individual for population iteration. Although the target collection points are inserted into the original vehicle routes corresponding to the target waste collection days, the TLBO algorithm is used to iterate the vehicle route coding body part in the hybrid coding body, and the service coding body representing the waste collection day allocation plan also exists synchronously, but no iteration operation is performed. In this embodiment, the service coding body that exists synchronously and does not perform iteration operation is the second service coding body. Similarly, during the iteration operation of the service coding body, the vehicle route coding body representing the route planning information also exists synchronously, but no iteration operation is performed.

[0082] Step 42, after encoding the target information corresponding to all target collection points into new sub-codes, according to a preset random generation rule, randomly generate the initial insertion order corresponding to the new sub-codes, and based on the initial insertion order, insert all the new sub-codes into the first coding body to generate multiple second coding bodies, where one second coding body is used to represent a vehicle route planning result.

[0083] In this embodiment, by randomly initializing several insertion positions for the new sub-codes, and then inserting the new sub-codes into all the first sub-codes of the first coding body according to the corresponding insertion positions, multiple second coding bodies representing vehicle route planning results are generated. Then, based on the multiple second coding bodies and the TLBO algorithm, the route planning update in response to dynamic demands is performed.

[0084] In some alternative embodiments, randomly generating the initial insertion order corresponding to the new sub-codes according to a preset random generation rule is achieved through the following steps:

[0085] Step 421, calculate the product of the number of target collection points and a preset random insertion coefficient to obtain a first insertion order parameter, where the random insertion coefficient is p, and p ∈ [0, 1].

[0086] In this embodiment, since the insertion position can only be the position between two first sub-codes in the first coding body, the available insertion positions are numbered starting from 2, generating a second part of the decision variable with a length of n', whose upper bound is an all-1 variable and the lower bound is an all-0 variable. After the algorithm starts, a group of initial solutions are randomly generated, that is, the initial insertion order is randomly generated. This part of the sequence is a group of real number elements r with a value range of [0, 1], and its insertion position (corresponding to the first insertion order parameter) is r = p * (n + 1 - 2) + 2, that is, the product of the number of target collection points and the preset random insertion coefficient.

[0087] Step 422, round the value corresponding to the first insertion order parameter to obtain the initial insertion order corresponding to each new sub-code.

[0088] In this embodiment, the final insertion position is obtained by rounding r, that is, the initial insertion order corresponding to each newly added sub-code.

[0089] Step 43: Using multiple second code bodies as the initial sub-population, and utilizing the TLBO algorithm to perform population search iteration corresponding to the TLBO algorithm until multiple alternative code bodies are generated. Among them, during the population search iteration process, the fitness of the fourth hybrid code body calculated by using the fitness function is used as the fitness of the current code body generated in the current iteration. The fourth hybrid code body is generated by combining the current code body with the second service code body.

[0090] In this embodiment, when calculating the individual fitness in the sub-population corresponding to the vehicle path code body, the fitness of the hybrid code body combining the service code body and the vehicle path code body is adopted, that is, the fitness corresponding to the same fitness function as in the initial waste collection plan information is calculated, and the fitness of the hybrid code body is used as the fitness of the corresponding sub-population individual; in this embodiment, although when using the TLBO algorithm to perform population search iteration corresponding to the TLBO algorithm, it is carried out separately, but when calculating the fitness of the current code body, the service code body representing the waste collection day plan is introduced, that is, the service code body representing the waste collection day allocation plan part also exists synchronously, but no iteration operation is performed, and it participates in the corresponding fitness calculation as a constant or a zero quantity in the fitness function, so as to reflect the fitness of the corresponding sub-population individual with the fitness of the population individual corresponding to the hybrid code body; it should be understood that, similarly, during the iteration operation of the service code body, the vehicle path code body representing the path planning information also exists synchronously, but no iteration operation is performed.

[0091] Step 44: According to the fitness corresponding to the alternative code body, select the alternative code body with the highest fitness, and use the second vehicle path corresponding to the alternative code body with the highest fitness and the path node information of the target collection point in the second vehicle path as the second path planning information, where the fitness of the fifth hybrid code body formed by combining the alternative code body with the second service code body is used as the fitness corresponding to the alternative code body.

[0092] It should be noted that in this embodiment, on the day of responding to the newly added demand points, the dynamic insertion strategy is adopted to insert the newly added points into the original vehicle routing plan. In the hybrid coding of the dynamic adjustment stage algorithm, the decision variables are divided into three parts. The first part and the third part correspond to the two parts of the decision variables in the initial planning stage, which respectively determine the waste collection day planning scheme (designated as the target waste collection day) for each first collection point after dynamic adjustment and the specific vehicle routing for each day. The newly added second part of the decision variables determines the insertion position of the target collection points of the newly added demands within the target waste collection day into the original vehicle routing. Real number coding is adopted. In this embodiment, the TLBO algorithm is used to optimize and solve the insertion of the target collection points.

[0093] In this embodiment, the encoding and decoding operations of a preferred embodiment are as follows:

[0094] Suppose there are n' target collection points with newly added service demands. In the first coding body, the first coding position and the last coding position are vehicle numbers, representing the starting point and the ending point of the vehicle itinerary respectively. Therefore, the insertion position can only be the positions between two first sub-codings in the first coding body. The available insertion positions are numbered starting from 2, generating the second part of the decision variables with a length of n'. Its upper bound is a variable of all 1s, and its lower bound is a variable of all 0s. After the algorithm starts, a group of initial solutions are randomly generated, that is, a random initial insertion order is generated. This part of the sequence is a group of real number elements r with a value range of [0, 1]. Its insertion position is r = p * (n + 1 - 2) + 2. For example: Suppose there is 1 newly added target collection point in the initial routing plan of the original 5 first collection points, and the corresponding first coding bodies with a length of n = 9 in the original route plan are [6, 1, 2, 7, 3, 6, 4, 5, 7]. There are n + 1 - 2 = 8 positions where insertion can be made. The newly added target collection point is numbered 9. After the algorithm starts, the randomly generated element is p = 0.7. Then the final insertion position is r = 8, and the updated route is [6, 1, 2, 7, 3, 6, 4, 9, 5, 7].

[0095] Through the above steps 41 to 44, on the day of responding to the newly added demand points, the dynamic insertion strategy is adopted to insert the newly added points into the original vehicle routing plan.

[0096] In some of the embodiments, using the GA algorithm of the TLBO-GA hybrid algorithm, path re-planning is performed on the target collection points and the first collection points associated with each periodic waste collection day to generate the third path planning information corresponding to each periodic waste collection day. This is achieved through the following steps:

[0097] Step 51: From the first path planning information corresponding to the periodic waste collection days, obtain the first collection points corresponding to each periodic waste collection day, and combine the corresponding first collection points and all target collection points into a candidate collection point set corresponding to each periodic waste collection day. Also, from the third mixed coding body, obtain the third service coding body that assigns the waste collection day of the corresponding collection point to the corresponding periodic waste collection day.

[0098] In this embodiment, on the waste collection days other than the target waste collection day, re-plan the path according to the change in the waste collection day assignment of the corresponding collection points, and use the GA algorithm to re-plan the path for the updated candidate collection point set and the corresponding waste collection requirements to achieve the update of the path planning in response to dynamic requirements.

[0099] Step 52: Take the collection points randomly selected from the candidate collection point set in order as a third path node, and repeatedly execute the encoding of multiple third path nodes arranged in order to generate multiple first path coding bodies. Each first path coding body is used to represent the result of re-planning the vehicle path within a periodic waste collection day. The first path coding body includes multiple first path sub-codes, and each first path sub-code corresponds to a collection point.

[0100] In this embodiment, after obtaining the candidate collection point sets corresponding to each waste collection day other than the target waste collection day, encode the candidate collection points according to a preset rule to generate the first path coding body representing the vehicle path planning result, and use multiple first path coding bodies as the initial sub-population for genetic evolution iteration.

[0101] Step 53: Use the GA algorithm to perform genetic evolution operations on multiple first path coding bodies to generate corresponding multiple second path coding bodies, and perform iterative genetic evolution operations on multiple second path coding bodies based on the fitness corresponding to the second path coding bodies to generate multiple alternative path coding bodies. The genetic evolution operations include: strong elitist strategy retention selection operation, combinatorial crossover operation, and mutation. The fitness corresponding to the second path coding body includes the fitness of the real-time mixed coding body calculated using the fitness function. The real-time mixed coding body is generated by combining the second path coding body with the corresponding third service coding body.

[0102] In this embodiment, the corresponding genetic evolution operations performed on the first path encoding body include, but are not limited to, selection, crossover, and mutation operations in the prior art. In this embodiment, a strong elitist strategy is adopted to retain the selection slots, and the second path encoding body is selected. That is, when selecting the corresponding path encoding body individuals, the parent generation and the offspring are combined, sorted from smallest to largest according to fitness, and the N individuals with the highest fitness are selected as the new population. In this embodiment, an interval reverse mutation method is preferably used for the mutation operation. That is, each first path sub-code in the first path encoding body has a certain probability of triggering mutation. Traverse each first path sub-code. Once a first path sub-code triggers mutation, randomly select a first path sub-code at another position from the current corresponding first path encoding body, and reverse the order within this interval.

[0103] In some alternative embodiments, a combined crossover operation is performed on multiple second path encoding bodies, including the following steps:

[0104] Step 531, after randomly selecting a target path encoding body from multiple third path encoding bodies, determine the magnitude relationship between the first crossover probability corresponding to the current genetic operation and the randomly generated reference crossover probability parameter. Among them, the third path encoding body is selected by performing a strong elitist strategy retention selection operation on multiple second path encoding bodies, and the reference crossover probability parameter is within a preset parameter interval.

[0105] Step 532, in the case where it is determined that the first crossover probability is greater than the reference crossover probability parameter, randomly select a target path sub-code from all the first path sub-codes corresponding to the target path encoding body, and perform crossover between the target path sub-code and any first path sub-code other than the target path sub-code to generate a new path encoding body corresponding to the target path encoding body.

[0106] In this embodiment, referring to Figure 4 , randomly select a first path sub-code G1 corresponding to a third path encoding body from the sequence composed of multiple third path encoding bodies, and generate a random decimal p in the range of [0, 1] (corresponding to the reference crossover probability parameter), and compare p with the first crossover probability; if p is less than the first crossover probability, the second first path sub-code G2 (corresponding to the target path sub-code) comes from any path sub-code in the same sequence composed of multiple third path encoding bodies, and reverse the sequence part between the first path sub-code G1 and the first path sub-code G2 to generate a new individual, that is, generate multiple new path encoding bodies. For example, the sequence composed of multiple third path encoding bodies is: individual I = [6, 1, 2, 7, 3, 6, 4, 5, 7], where the first 1-5 are candidate collection points, 6-7 are vehicle numbers, and each can have 2 trips. The sequence length is 9, representing the path sequence on a certain day within the cycle (refer to Figure 4In individual I), the crossover rate crossrate = 0.6; randomly select one of the first path sub-codes G1, and assume G1 = 2; generate a random decimal p in the range [0, 1], compare p with the crossover rate crossrate. If p < crossrate, then randomly select another first path sub-code G2 from the same sequence composed of multiple third path coding bodies, and assume G2 = 5; invert the genes between G1 and G2, so individual I = [6, 1, 2, 7, 3, 6, 4, 5, 7] becomes new individual I = [6, 1, 5, 4, 6, 3, 7, 2, 7].

[0107] Step 533, when it is determined that the first crossover probability is not greater than the reference crossover probability, determine the first position of the target path sub-code in the target path coding body, select the intended path sub-code after the first position from all the first path sub-codes corresponding to the intended path coding body, and detect the intended path sub-code among all the first path sub-codes corresponding to the target path coding body, and determine the second position corresponding to the intended path sub-code. Here, the intended path coding body is any one of the third path coding bodies other than the target path coding body among the multiple third path coding bodies.

[0108] Step 534, determine whether the first position is before the second position, and when it is determined that the first position is before the second position, cross the first path sub-code after the target path sub-code of the target path coding body with the intended path sub-code corresponding to the target path coding body to generate a new path coding body corresponding to the target path coding body.

[0109] Step 535, when it is determined that the first position is after the second position, cross the first path sub-code after the intended path sub-code corresponding to the target path coding body with the target path sub-code to generate a new path coding body corresponding to the target path coding body.

[0110] In this embodiment, if p is greater than or equal to the first crossover probability, then randomly select another sequence composed of multiple third-path coding bodies from the population, find the first path sub-code G1 in this sequence, and mark the next first path sub-code as G3 (if it exceeds the sequence length, take the previous first path sub-code), and return to the original sequence to find the position where the same first path sub-code G3 is located. Judge the positions of G1 and G3 in the original sequence. If G1 < G3, then invert the sequence part between the next first path sub-code after G1 and the first path sub-code G3; if G3 < G1, then invert the sequence part between the next first path sub-code after G3 and the first path sub-code G1 in the original sequence, so that the G1 and G3 gene points in the sequence are still adjacent, while the rest of the sequence changes. For example, the sequence composed of multiple third-path coding bodies is: individual I = [6, 1, 2, 7, 3, 6, 4, 5, 7], where the first 1-5 are candidate collection points, 6-7 are vehicle numbers, and each can have 2 trips. The sequence length is 9, representing the path sequence of a certain day within a cycle (refer to Figure 4 individual I in). The crossover rate crossrate = 0.6; randomly select one of the first path sub-codes G1, and set G1 = 2; generate a random decimal p in the range of [0, 1], compare p with the crossover rate crossrate. If p ≥ crossrate, then find another sequence composed of multiple third-path coding bodies in the population, find the position of the first path sub-code G1 in this sequence. If multiple positions are found, only take the first matching position, select the adjacent gene at this position, and judge the index of this sequence. If it is already the last first path sub-code in this sequence, then select the first path sub-code on the left, otherwise select the next first path sub-code and record it as G3. In individual II, let individual II = [6, 5, 2, 4, 7, 3, 6, 1, 7]. G1 is in the third position, and G3 takes the first path sub-code in the fourth position, that is, G3 = 4. Return to the original chromosome individualⅠ, find the position of the coding value 4 in the original sequence, judge the positions of G1 and G3. If G1 < G3, then invert the sequence part between the next first path sub-code after G1 and the first path sub-code G3; if G1 > G3, then invert the sequence part between the next first path sub-code after G3 and the first path sub-code G1 in the original sequence. At this time, G1 < G3, that is, after the operation, individual I = [6, 1, 2, 7, 3, 6, 4, 5, 7] becomes new individual I = [6, 1, 2, 4, 6, 3, 7, 5, 7], which is recorded as a new individual. If G1 and G3 are exactly adjacent, then the middle path sub-code is empty, and there is no need to perform inversion, and the new sequence is the same as the original sequence.

[0111] Step 54: Select the alternative path coding body with the highest fitness according to the fitness corresponding to the alternative path coding body, and use the third vehicle path corresponding to the alternative path coding body with the highest fitness as the third path planning information corresponding to each periodic waste collection day. Herein, the fitness corresponding to the sixth hybrid coding body formed by combining the alternative path coding body and the corresponding third service coding body is used as the fitness corresponding to the alternative path coding body.

[0112] This embodiment also provides a garbage collection vehicle path planning device considering dynamic demands. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0113] Figure 5 is a structural block diagram of a garbage collection vehicle path planning device considering dynamic demands according to an embodiment of the present application, as Figure 5 shown. This device includes a first acquisition module 51, a first insertion module 52, a processing module 53, and a first generation module 54, wherein,

[0114] The first acquisition module 51, after receiving a new waste collection request sent by at least one target collection point, acquires the first waste collection planning information for cleaning the current multiple first collection points. Herein, the new waste collection request includes the target information and the target waste collection day of the target collection point, and the first waste collection planning information includes one of the waste collection planning information and the initial waste collection planning information generated by iteratively planning the path of the initial waste collection planning information using the TLBO-GA hybrid algorithm. The initial waste collection planning information is generated by planning the waste collection day and the waste collection path for the initial collection points using the TLBO-GA hybrid algorithm.

[0115] The first insertion module 52, which is coupled to the first acquisition module 52, is used to detect the first path planning information corresponding to the target waste collection day from all the first path planning information of the first waste collection planning information, and based on the corresponding first path planning information and the target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning and generate the second path planning information corresponding to the target waste collection day.

[0116] A processing module 53, coupled to the first insertion module 52, is configured to determine whether a target collection point requests collection on a periodic collection day other than the target collection day. When it is determined that the target collection point requests collection on each periodic collection day, the GA algorithm of the TLBO-GA hybrid algorithm is used to re-plan the paths of the target collection point and the first collection points associated with each periodic collection day, and third path planning information corresponding to each periodic collection day is generated.

[0117] A first generation module 54, coupled to the processing module 53 and the insertion module 52, is configured to generate a planning result including second collection planning information according to the second path planning information and the third path planning information.

[0118] Figure 6 It is a structural block diagram of a garbage collection vehicle path planning device considering dynamic requirements according to a preferred embodiment of the present application. As Figure 6 shown, the device includes a second acquisition module 61, a second insertion module 62, and a second generation module 63, where

[0119] The second acquisition module 61, after receiving a new collection request sent by at least one target collection point, acquires first collection planning information for collecting the current multiple first collection points. The new collection request includes the target information and the target collection day of the target collection point. The first collection planning information includes one of the collection planning information and the initial collection planning information generated by iteratively planning the path of the initial collection planning information using the TLBO-GA hybrid algorithm. The initial collection planning information is generated by planning the collection day and the collection path for the initial collection points using the TLBO-GA hybrid algorithm.

[0120] The second insertion module 62, coupled to the first acquisition module 61, is configured to detect the first path planning information corresponding to the target collection day from all the first path planning information of the first collection planning information, and based on the corresponding first path planning information and the target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning and generate the second path planning information corresponding to the target collection day.

[0121] The second generation module 63, coupled to the second insertion module 62, determines whether the target collection point requests collection on a periodic collection day other than the target collection day. When it is determined that the target collection point does not request collection on each periodic collection day, the first path planning information corresponding to the target collection day in the first collection planning information is updated to the second path planning information to obtain third collection planning information, and the third collection planning information is used as the current corresponding planning result.

[0122] This embodiment also provides a planning system, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any of the above method embodiments.

[0123] Optionally, the above planning system may further include a transmission device and an input / output device. Among them, the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0124] Optionally, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0125] S1. After receiving a new waste collection request sent by at least one target collection point, obtain the first waste collection planning information for cleaning the current multiple first collection points.

[0126] S2. From all the first path planning information in the first waste collection planning information, detect the first path planning information corresponding to the target waste collection date, and based on the corresponding first path planning information and target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning, and generate the second path planning information corresponding to the target waste collection date.

[0127] S3. Determine whether the target collection point requests waste collection on periodic waste collection dates other than the target waste collection date, and in the case of determining that the target collection point requests waste collection on each periodic waste collection date, use the GA algorithm of the TLBO-GA hybrid algorithm to re-plan the paths for the target collection point and the first collection points associated with each periodic waste collection date, and generate the third path planning information corresponding to each periodic waste collection date.

[0128] S4. Generate a planning result including the second waste collection planning information according to the second path planning information and the third path planning information.

[0129] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation manners, and will not be elaborated here.

[0130] In addition, in combination with the above method for planning the routes of waste collection vehicles considering dynamic demands in the embodiments, an embodiment of the present application can provide a storage medium to implement. A computer program is stored on the storage medium; when the computer program is executed by a processor, it implements any one of the above methods for planning the routes of waste collection vehicles considering dynamic demands.

[0131] Those skilled in the art should understand that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as falling within the scope described in this specification.

[0132] The above embodiments only represent several implementation manners of the present application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A garbage collection vehicle route planning method considering dynamic demand, characterized in that Including: After receiving a new waste collection request sent by at least one target collection point, obtain the first waste collection plan information for collecting waste from the current multiple first collection points, where the new waste collection request includes the target information and the target waste collection date of the target collection point, and the first waste collection plan information includes one of the waste collection plan information generated by iteratively planning the path of the initial waste collection plan information using the TLBO-GA hybrid algorithm and the initial waste collection plan information, and the initial waste collection plan information is generated by using the TLBO-GA hybrid algorithm to plan the waste collection date and the waste collection path for the initial collection points; Detect the first path planning information corresponding to the target waste collection date from all the first path planning information of the first waste collection plan information, and based on the corresponding first path planning information and the target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning and generate the second path planning information corresponding to the target waste collection date; Judge whether the target collection point requests to collect waste on periodic waste collection dates other than the target waste collection date, and in the case where it is judged that the target collection point requests to collect waste on each of the periodic waste collection dates, use the GA algorithm of the TLBO-GA hybrid algorithm to re-plan the path for the target collection point and the first collection points associated with each of the periodic waste collection dates, and generate the third path planning information corresponding to each of the periodic waste collection dates; Generate a planning result including the second waste collection plan information according to the second path planning information and the third path planning information.

2. The method according to claim 1, wherein The method further includes: in the case where it is judged that the target collection point does not request to collect waste on each of the periodic waste collection dates, update the first path planning information corresponding to the target waste collection date in the first waste collection plan information to the second path planning information to obtain the third waste collection plan information, and use the third waste collection plan information as the current corresponding planning result.

3. The method according to claim 2, wherein Judging whether the target collection point requests to collect waste on periodic waste collection dates other than the target waste collection date includes: According to the target information, judge the waste collection frequency type of the target collection point, where the waste collection frequency type includes a fixed frequency type and a temporary waste collection type; In the case where it is judged that the target collection point is a collection point of the fixed frequency type, determine that the target collection point requests to collect waste on each of the periodic waste collection dates; In the case where it is judged that the target collection point is a collection point of the temporary waste collection type, determine that the target collection point does not request to collect waste on each of the periodic waste collection dates.

4. The method according to claim 3, wherein When it is judged that the target collection point is a collection point of the fixed frequency type, the method further includes: According to the target information, detect the target collection point among the first collection points; When the target collection point is detected, obtain, from the first waste collection plan information, the first collection interval corresponding to the target collection point as the first collection point, and, with the target waste collection day as the first day, rearrange and generate a first periodic waste collection day excluding the target waste collection day at the time interval of the first collection interval, where the collection interval is used to represent the number of days between two adjacent waste collection days of the corresponding first collection point, and the first periodic waste collection day is the periodic waste collection day corresponding to the target collection point; When the target collection point is not detected, obtain the preset waste collection frequency information from the target information of the target collection point, and after determining a second collection interval according to the waste collection frequency information, plan a second periodic waste collection day excluding the target waste collection day with the target waste collection day as the first day at the time interval of the second collection interval, where the second periodic waste collection day is the periodic waste collection day corresponding to the target collection point.

5. The method according to claim 3, wherein Before obtaining the first waste collection plan information, the method further includes: According to a preset hybrid coding rule, perform hybrid coding corresponding to the TLBO-GA hybrid algorithm on all the initial collection points to generate a plurality of first hybrid coding bodies, where the first hybrid coding body includes a first service coding body and a first vehicle route coding body, the first service coding body is used to represent a distribution result of allocating a first waste collection day to a plurality of the initial collection points according to the corresponding waste collection service frequency, and the waste collection days within one cycle associated with the initial collection point are arranged starting from the first waste collection day at the collection interval corresponding to the waste collection service frequency, and the first vehicle route coding body is used to represent a route planning result of using a target waste collection vehicle to collect waste from a plurality of the initial collection points; After determining the fitness corresponding to each first hybrid coding body by using the fitness function corresponding to the TLBO-GA hybrid algorithm, based on the random selection of the first service coding body and the first vehicle route coding body, perform one of the following iterative operations: perform a sub-population search iteration on the selected first service coding body by using the TLBO algorithm, perform a sub-population genetic evolution operation on the selected first vehicle route coding body by using the GA algorithm, where during the execution of the selected iterative operation, use the fitness corresponding to each first hybrid coding body as the fitness of the corresponding sub-population, and the fitness function is based on the waste collection departure cost, the waste collection transportation cost, the overloaded waste collection penalty cost, a first penalty cost generated by exceeding the total waste collection working time, and a second penalty cost generated by the noise value exceeding the threshold, and the first penalty cost and the second penalty cost are determined according to a preset time-dependent function; Combine one of the first service coding body and the first vehicle path coding body that have completed the selected iterative operation with the other that has not performed the corresponding iterative operation to obtain a plurality of second hybrid coding bodies, and after determining the fitness corresponding to each second hybrid coding body, perform the corresponding random selection and iterative operation; Repeat the steps of determining the fitness of the corresponding hybrid coding body, randomly selecting one of the service coding body and the vehicle path coding body corresponding to the corresponding hybrid coding body, and performing the corresponding iterative operation until the fitness of the corresponding hybrid coding body is higher than the fitness threshold to obtain the target hybrid coding body, and decode the target service coding body and the target vehicle path coding body corresponding to the target hybrid coding body, and use the decoded first-day waste collection planning information and waste collection path planning information as the initial waste collection planning information.

6. The method according to claim 5, wherein Based on the corresponding first path planning information and the target information, use the TLBO algorithm of the TLBO-GA hybrid algorithm to update the path planning for responding to dynamic demands, and generate the second path planning information corresponding to the target waste collection day, including: Determine the third hybrid coding body corresponding to the first waste collection planning information, and determine the first coding body corresponding to the third hybrid coding body. Among them, the third hybrid coding body further includes a second service coding body used to represent that the first-day waste collection of the corresponding collection point is assigned to the target waste collection day. The first coding body is associated with the first vehicle path corresponding to the first path planning information corresponding to the target waste collection day. The first coding body includes a plurality of first sub-codings, and each first sub-coding is associated with the first collection point that is a path node on the first vehicle path. The coding position corresponding to each first sub-coding is used to represent the order of waste collection for the first collection point; After encoding the target information corresponding to all the target collection points into new sub-codings, according to a preset random generation rule, randomly generate the initial insertion order corresponding to the new sub-codings, and based on the initial insertion order, insert all the new sub-codings into the first coding body to generate a plurality of second coding bodies, where one second coding body is used to represent a vehicle path planning result; Use the plurality of second coding bodies as the initial sub-population, and use the TLBO algorithm to perform population search iterations corresponding to the TLBO algorithm until a plurality of alternative coding bodies are generated. Among them, during the population search iteration process, the fitness of the fourth hybrid coding body calculated by using the fitness function is used as the fitness of the current coding body generated in the current iteration. The fourth hybrid coding body is generated by combining the current coding body with the second service coding body; Select the alternative coding body with the highest fitness according to the fitness corresponding to the alternative coding body, and use the second vehicle path corresponding to the alternative coding body with the highest fitness and the path node information of the target collection point in the second vehicle path as the second path planning information, where the fitness corresponding to the fifth hybrid coding body formed by combining the alternative coding body and the second service coding body is used as the fitness corresponding to the alternative coding body.

7. The method according to claim 6, characterized in that Randomly generate the initial insertion order corresponding to the newly added sub-coding according to a preset random generation rule, including: Calculate the product of the number of target collection points and a preset random insertion coefficient to obtain a first insertion order parameter, where the random insertion coefficient is p, and p ∈ [0, 1]; Round the value corresponding to the first insertion order parameter to obtain the initial insertion order corresponding to each newly added sub-coding.

8. The method according to claim 6, characterized in that, Use the GA algorithm of the TLBO-GA hybrid algorithm to re-plan the paths of the target collection points and the first collection points associated with each periodic cleaning day, and generate third path planning information corresponding to each periodic cleaning day, including: Obtain the first collection points corresponding to each periodic cleaning day from the first path planning information corresponding to the periodic cleaning day, and merge the corresponding first collection points and all the target collection points into a candidate collection point set corresponding to each periodic cleaning day, and obtain a third service coding body that assigns the cleaning days of the corresponding collection points to the corresponding periodic cleaning days from the third hybrid coding body; Take the collection points randomly selected from the candidate collection point set in order as a third path node, and repeat the operation of coding multiple arranged third path nodes to generate multiple first path coding bodies, where each first path coding body is used to represent a result of re-planning the vehicle path within a periodic cleaning day, and the first path coding body includes multiple first path sub-codes, and each first path sub-code corresponds to a collection point; Use the GA algorithm to perform genetic evolution operations on multiple first path coding bodies to generate corresponding multiple second path coding bodies, and perform iterative genetic evolution operations on multiple second path coding bodies based on the fitness corresponding to the second path coding bodies to generate multiple alternative path coding bodies, where the genetic evolution operations include: strong elite strategy retention selection operation, combinatorial crossover operation, mutation, and the fitness corresponding to the second path coding body includes the fitness of the real-time hybrid coding body calculated using the fitness function, and the real-time hybrid coding body is generated by combining the second path coding body and the corresponding third service coding body; Select the alternative path encoding body with the highest fitness according to the fitness corresponding to the alternative path encoding body, and use the third vehicle path corresponding to the alternative path encoding body with the highest fitness as the third path planning information corresponding to each of the periodic waste collection days, where the fitness corresponding to the sixth hybrid encoding body formed by combining the alternative path encoding body and the corresponding third service encoding body is used as the fitness corresponding to the alternative path encoding body.

9. The method according to claim 8, wherein Perform a combination crossover operation on multiple second path encoding bodies, including: After randomly selecting a target path encoding body from multiple third path encoding bodies, determine the magnitude relationship between the first crossover probability corresponding to the current genetic operation and a randomly generated reference crossover probability parameter, where the third path encoding body is selected by performing the strong elite strategy retention selection operation on multiple second path encoding bodies, and the reference crossover probability parameter is within a preset parameter range; In the case where it is determined that the first crossover probability is greater than the reference crossover probability parameter, randomly select a target path sub-code from all the first path sub-codes corresponding to the target path encoding body, and perform crossover between the target path sub-code and any one of the first path sub-codes other than the target path sub-code to generate a new path encoding body corresponding to the target path encoding body.

10. The method according to claim 9, characterized in that In the case where it is determined that the first crossover probability is not greater than the reference crossover probability, the method further includes: Determine the first position of the target path sub-code in the target path encoding body, select the intended path sub-code after the first position from all the first path sub-codes corresponding to the intended path encoding body, and detect the intended path sub-code among all the first path sub-codes corresponding to the target path encoding body and determine the corresponding second position, where the intended path encoding body is any one of the third path encoding bodies other than the target path encoding body among the multiple third path encoding bodies; Judge whether the first position is before the second position, and in the case where it is determined that the first position is before the second position, perform crossover between the first path sub-code after the target path sub-code of the target path encoding body and the intended path sub-code corresponding to the target path encoding body to generate a new path encoding body corresponding to the target path encoding body; In the case where it is determined that the first position is after the second position, perform crossover between the first path sub-code after the intended path sub-code corresponding to the target path encoding body and the target path sub-code to generate a new path encoding body corresponding to the target path encoding body.

Images