Environmental sanitation task management method and device, computing equipment and storage medium

Abstract

The invention discloses an environmental sanitation task management method and apparatus, a computing device and a storage medium. The method comprises the steps of obtaining urban road data, data of each garbage throwing point, data of each charging / refueling point and environmental sanitation data; according to the garbage throwing point data, the future garbage can full load condition and the garbage clearance requirement are predicted, and a plurality of environmental sanitation tasks are generated; according to the specific information and environmental sanitation data of the environmental sanitation tasks, adopting a reinforcement learning optimization scheduling strategy to distribute the environmental sanitation tasks to corresponding environmental sanitation vehicles and / or environmental sanitation workers; and based on the urban road data and the data of each charging / refueling point, providing an optimal path for the sanitation vehicle and / or the sanitation worker to go to the task execution site. According to the invention, the environmental sanitation tasks can be automatically generated, the environmental sanitation tasks can be dynamically coordinated and allocated, the execution state of the environmental sanitation tasks is monitored, the urban environmental sanitation efficiency is remarkably improved, and the environmental sanitation cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent environmental sanitation, and particularly relates to a method, device, computing device and storage medium for managing environmental sanitation tasks. Background Art

[0002] In urban environmental sanitation work, it is necessary to detect garbage in real time, generate environmental sanitation tasks for garbage cleaning, and then perform reasonable task allocation and scheduling to distribute the environmental sanitation tasks to the corresponding sanitation vehicles and sanitation workers. However, the existing environmental sanitation tasks are numerous, and the management and allocation still rely on the number of people, with high complexity, low efficiency, low intelligence level, and often unreasonable allocation. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes a method, device, computing device and storage medium for managing environmental sanitation tasks.

[0004] In a first aspect, the present invention discloses a method for managing environmental sanitation tasks, including:

[0005] Step S1: Obtain urban road data, data of each garbage disposal point, data of each charging / refueling point, and environmental sanitation data;

[0006] The urban road data includes one or more of the following information: road identifier, road name, road location, road width, average vehicle speed of the current traffic flow, whether there is construction closure, number of lanes, list of road IDs directly connected to this road, road intersection coordinates, turning restrictions, road priority, whether it is a two-way road, traffic conditions in different time periods;

[0007] The data of the garbage disposal point includes one or more of the following information: garbage bin identifier, garbage bin location, garbage bin filling rate, last cleaning time, sensor status;

[0008] The data of the charging / refueling point includes one or more of the following information: charging / refueling point identifier, charging / refueling point name, charging / refueling point location, number of vehicles that can be served simultaneously, current available service parking spaces, specific type, supported vehicle types, output power of a single charging pile, fuel type provided, whether it is currently available, working time period;

[0009] The environmental sanitation data includes one or more of the following information: location of the sanitation vehicle, location of the sanitation worker, total number of sanitation vehicles, total number of sanitation workers, number of idle sanitation vehicles, number of idle sanitation workers;

[0010] Step S2: According to the data of the garbage disposal point, predict the future full-load situation of the garbage bin and the garbage removal demand, and generate several environmental sanitation tasks;

[0011] Each sanitation task has one or more of the following information: task number, task type, task description, task execution location, task priority, time range during which the task can be executed, resources required for the task, task prediction source, task merging group number, reason for dynamic adjustment, manual intervention remarks, current task status, expected completion status;

[0012] Step S3: According to the specific information of the sanitation task and the sanitation data, use reinforcement learning to optimize the scheduling strategy to allocate the sanitation task to the corresponding sanitation vehicle and / or sanitation worker;

[0013] Step S4: Based on the urban road data and the data of each charging / fueling point, provide the optimal path for the sanitation vehicle and / or sanitation worker to the task execution location.

[0014] To achieve the above object, the technical solution of the present invention is as follows:

[0015] On the basis of the above technical solution, the following improvements can also be made:

[0016] As a preferred solution, in step S2, a scoring model is used to score and sort each generated sanitation task, and the task priority is set.

[0017] As a preferred solution, in step S3, the reward function of the reinforcement learning optimization scheduling strategy is as follows:

[0018] R = α 1 *R 效率 +α 2 *R 成本 +α 3 *R 及时性 ;

[0019] Where: R 效率 is the efficiency index;

[0020] R 成本 is the cost index;

[0021] R 及时性 is the timeliness index;

[0022] α 1 、α 2 、α 3 are coefficients respectively.

[0023] As a preferred solution, it further includes:

[0024] Step S5: Perform one or more of the following monitors on the sanitation task: real-time task status tracking, task completion rate statistics, abnormal situation warning, data archiving and analysis.

[0025] In a second aspect, the present invention discloses a sanitation task management device, including:

[0026] An acquisition module for acquiring urban road data, data of each garbage disposal point, data of each charging / refueling point, and sanitation data;

[0027] The urban road data includes one or more of the following information: road identifier, road name, road location, road width, average speed of the current traffic flow, whether there is construction closure, number of lanes, list of road IDs directly connected to this road, road intersection coordinates, turning restrictions, road priority, whether it is a two-way road, traffic conditions in different time periods;

[0028] The garbage disposal point data includes one or more of the following information: garbage bin identifier, garbage bin location, garbage bin filling rate, last cleaning time, sensor status;

[0029] The charging / refueling point data includes one or more of the following information: charging / refueling point identifier, charging / refueling point name, charging / refueling point location, number of vehicles that can be served simultaneously, current number of available service parking spaces, specific type, supported vehicle types, output power of a single charging pile, fuel types provided, whether it is currently available, working time period;

[0030] The sanitation data includes one or more of the following information: location of sanitation vehicles, location of sanitation workers, total number of sanitation vehicles, total number of sanitation workers, number of idle sanitation vehicles, number of idle sanitation workers;

[0031] A task generation module for predicting the future fullness of garbage bins and garbage collection requirements based on the garbage disposal point data, and generating several sanitation tasks;

[0032] Each sanitation task has one or more of the following information: task number, task type, task description, task execution location, task priority, time range during which the task can be executed, resources required for the task, task prediction source, task merging group number, reason for dynamic adjustment, manual intervention remarks, current status of the task, expected completion situation;

[0033] An allocation and scheduling module for allocating sanitation tasks to corresponding sanitation vehicles and / or sanitation workers according to the specific information of the sanitation tasks and the sanitation data, using reinforcement learning to optimize the scheduling strategy;

[0034] A path generation module for providing the optimal path for sanitation vehicles and / or sanitation workers to the task execution location based on the urban road data and the data of each charging / refueling point.

[0035] As a preferred solution, in the task generation module, a scoring model is used to score and sort each generated sanitation task, and the task priority is set.

[0036] As a preferred solution, in the allocation and scheduling module, the reward function for optimizing the scheduling policy by reinforcement learning is as follows:

[0037] R = α 1 *R 效率 + α 2 *R 成本 + α 3 *R 及时性 ;

[0038] Where: R 效率 is the efficiency index;

[0039] R 成本 is the cost index;

[0040] R 及时性 is the timeliness index;

[0041] α 1 、α 2 、α 3 are coefficients respectively.

[0042] As a preferred solution, it further includes:

[0043] A task monitoring module for performing one or more of real-time task status tracking, task completion rate statistics, early warning of abnormal situations, data archiving and analysis on sanitation tasks.

[0044] In a third aspect, the present invention discloses a computing device, including:

[0045] One or more processors;

[0046] A memory;

[0047] And one or more programs, where one or more programs are stored in the memory and are configured to be executed by one or more processors, and one or more programs include instructions for any of the above sanitation task management methods.

[0048] In a fourth aspect, the present invention discloses a storage medium storing one or more computer-readable programs, and one or more programs include instructions adapted to be loaded and executed by the memory for any of the above sanitation task management methods.

[0049] The present invention discloses a sanitation task management method, device, computing device and storage medium, having the following beneficial effects:

[0050] The present invention can automatically generate sanitation tasks, dynamically coordinate and allocate sanitation tasks, and at the same time monitor the execution status of sanitation tasks, significantly improving the urban sanitation efficiency and reducing the sanitation cost. Brief Description of the Drawings

[0051] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0052] Figure 1 It is a flowchart of the environmental sanitation task management method provided by the embodiments of the present invention.

[0053] Figure 2 It is a schematic diagram of the road topology structure provided by the embodiments of the present invention. Detailed implementation manners

[0054] The following will specifically describe the preferred implementation manners of the present invention with reference to the drawings.

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present invention.

[0056] The expression "including" elements is an "open-ended" expression, which only means the existence of corresponding components or steps and should not be interpreted as excluding additional components or steps.

[0057] In order to achieve the purpose of the present invention, in some embodiments of the environmental sanitation task management method, as Figure 1 shown, the environmental sanitation task management method includes:

[0058] Step S101: Obtain urban road data, data of each garbage disposal point, data of each charging / refueling point, and environmental sanitation data;

[0059] The urban road data includes one or more of the following information: road identifier, road name, road location, road width, average vehicle speed of the current traffic flow, whether there is construction closure, number of lanes, list of road IDs directly connected to this road, road intersection coordinates, turning restrictions, road priority, whether it is a two-way road, traffic conditions at different time periods;

[0060] The garbage disposal point data includes one or more of the following information: garbage bin identifier, garbage bin location, garbage bin filling rate, last cleaning time, sensor status;

[0061] Charging / refueling point data includes one or more of the following information: charging / refueling point identifier, charging / refueling point name, charging / refueling point location, number of vehicles that can be served simultaneously, current number of available service parking spaces, specific type, supported vehicle types, output power of a single charging pile, type of fuel provided, current availability, working hours;

[0062] Sanitation data includes one or more of the following information: location of sanitation vehicles, location of sanitation workers, total number of sanitation vehicles, total number of sanitation workers, number of idle sanitation vehicles, number of idle sanitation workers;

[0063] Step S102: According to the garbage disposal point data, predict the future fullness of garbage bins and the garbage collection requirements, and generate a number of sanitation tasks;

[0064] Each sanitation task has one or more of the following information: task number, task type, task description, task execution location, task priority, time range during which the task can be executed, resources required for the task, task prediction source, task merger group number, reason for dynamic adjustment, manual intervention remarks, current status of the task, expected completion;

[0065] Step S103: According to the specific information of the sanitation tasks and the sanitation data, use reinforcement learning to optimize the scheduling strategy and assign the sanitation tasks to the corresponding sanitation vehicles and / or sanitation workers;

[0066] Step S104: Based on the urban road data and the data of each charging / refueling point, provide the optimal path for the sanitation vehicles and / or sanitation workers to the task execution location.

[0067] The following elaborates on each of the above steps in detail.

[0068] Step S101 obtains the urban road data, the data of each garbage disposal point, the data of each charging / refueling point, and the sanitation data.

[0069] The urban road data includes road width, congestion situation, construction closure, etc., as well as the topological structure relationship between roads, as shown in Table 1. Further, the road topological structure is as Figure 2 shown. When any road on the map is selected, it turns blue, and all attributes of the road are displayed.

[0070] Table 1 Urban road data

[0071]

[0072]

[0073] The data of each garbage disposal point includes static data such as garbage disposal points and garbage bin capacities, as shown in Table 2.

[0074] Table 2 Waste Disposal Point Data

[0075]

[0076] Data of each charging / refueling point is shown in Table 3 below.

[0077] Table 3 Charging / Refueling Point Data

[0078]

[0079]

[0080] In step S102, based on the waste disposal point data, predict the future fullness of trash bins and waste collection requirements, and generate a number of sanitation tasks to ensure the rationality and integrity of task generation.

[0081] Based on waste generation hotspot data (such as crowded areas), divide the cleaning priorities of regions; and divide the task types, which include waste cleaning, trash bin replacement, vehicle maintenance, etc.

[0082] Use a scoring model to score and sort each generated sanitation task, and set the task priorities. Conduct a comprehensive assessment of task urgency and geographical location importance (such as commercial areas and around schools).

[0083] Use an adaptive algorithm to dynamically adjust the priorities according to the real-time importance of tasks. For example, some tasks may become more urgent due to special weather or holidays. Introduce a flexible task window to allow some tasks to be executed during low-load periods to avoid concentrated use of resources.

[0084] The present invention collects waste disposal point data (such as: trash bin filling rate, cleaning cycle, hotspot location, etc.); extracts features such as time (weekend / weekday), location attributes (commercial area, residential area), weather conditions, etc.; uses a time series prediction model (such as LSTM) to predict the future fullness of trash bins and cleaning requirements, and generate sanitation tasks.

[0085] It should be noted that sanitation task merging can also be carried out. Considering the capabilities of sanitation vehicles and workers, integrate small tasks in adjacent areas into a group of tasks to reduce scheduling complexity and avoid resource waste.

[0086] In some other embodiments, an artificial intervention interface can also be added. Managers can manually adjust tasks through this interface to handle emergencies, and implement a mechanism that combines automatic generation and manual optimization of sanitation tasks.

[0087] Data of each sanitation task is shown in Table 4 below.

[0088] Table 4 Sanitation Task Data

[0089]

[0090]

[0091] Step S103 generates a real-time task allocation plan based on the specific information of the sanitation tasks, the positions of the sanitation vehicles, the availability of sanitation workers, etc.

[0092] The present invention uses reinforcement learning (RL) to optimize the scheduling strategy, and the detailed steps are as follows:

[0093] First, problem modeling.

[0094] State: The filling degree of the current trash can, the number of available vehicles and personnel, the task priority of each area, the current time, other special conditions (such as weather, holidays)

[0095] Action design: The actions are to assign tasks to specific vehicles and personnel, assign vehicles and personnel to specific areas, delay or merge tasks, and adjust task priorities.

[0096] Reward function: The rewards mainly aim at the number of completed tasks, reducing the driving distance, and saving time. It includes the following four aspects: task completion efficiency (rewarding for efficiently completing tasks), optimization of resource use (reducing vehicle idling or over-mobilization), timeliness of emergency tasks (responding promptly to high-priority tasks), and overall operating costs (minimizing costs such as fuel and labor).

[0097] Environment: It includes the dynamic changes in garbage generation, the real-time adjustment requirements of tasks, the availability of vehicles and personnel, etc.

[0098] Second, training and simulation.

[0099] Collect task data: including task types (such as garbage collection, road cleaning, garbage transfer), complexity (such as large garbage cleaning, medium, low), execution time (start and end times of task execution), location and other information (latitude and longitude coordinates of the area where the task is located).

[0100] Collect vehicle capacity data: including vehicle functions (garbage collection vehicle, sprinkler, sweeper), applicable scope (suitable task types, such as garbage collection, cleaning), load limit (maximum weight of garbage that can be carried), current status (available, under repair, charging), etc.

[0101] Collect personnel skill data: including the work skills of sanitation workers (garbage classification, equipment maintenance, road cleaning), experience (junior, intermediate, senior), and available time (working hours and weekly available time), etc.

[0102] Reward function design, the reward function needs to comprehensively consider multi-dimensional indicators (such as efficiency, cost, and timeliness), specifically as follows:

[0103] R = α 1 *R 效率 +α 2 *R 成本 +α 3 *R 及时性 ;

[0104] Where: R 效率 is the efficiency index;

[0105] R 成本 is the cost index;

[0106] R 及时性 is the timeliness index;

[0107] α 1 、α 2 、α 3 are coefficients respectively.

[0108] Training strategy: Use historical data and simulation environment for strategy training to optimize the scheduling strategy; Add environmental noise to simulate actual complex situations (such as: vehicle failure, task temporary change).

[0109] Third, scheduling rules. Prioritize the allocation of idle vehicles and personnel; If both are busy, prioritize the vehicles and personnel with fewer tasks for real-time scheduling adjustment. Adjust task allocation according to the task completion progress and traffic accidents (such as road closure); Combine the status (battery level, location) reported by the vehicle in real time, re-allocate tasks, and prioritize the vehicles with sufficient battery and close location.

[0110] Fourth, optimization of scheduling strategy. Use reinforcement learning to optimize the scheduling strategy and reduce the total job completion time; Consider multi-objective optimization (such as: efficiency, cost, service level).

[0111] Step S104 provides the optimal path for the sanitation vehicle and / or sanitation worker to the task execution location based on the urban road data and the data of each charging / refueling point.

[0112] The present invention can but is not limited to adopt the A* algorithm as the path planning algorithm to calculate the optimal path. At the same time, in the path calculation, add the time window time_windows constraint to ensure that the path selection considers the traffic flow during the operation period, as shown in Table 5.

[0113] Table 5 time_windows data

[0114]

[0115]

[0116] When calculating the minimum cost function value, multiply it by the cost adjustment coefficient cost_multiplier to avoid planning during peak congestion periods and on congested roads. That is to say, for roads during congestion periods, the cost will increase.

[0117] For autonomous sanitation vehicles, considering the endurance of the autonomous sanitation vehicles, prioritize arranging charging / fueling points in the path. During path planning, check the remaining endurance of the current vehicle. If the estimated energy consumption to reach a certain section of the road exceeds the remaining endurance, forcefully insert a charging / fueling point as a relay station. When optimizing the path, prioritize roads with charging facilities. If the remaining mileage of the vehicle is sufficient, ignore the above restrictions.

[0118] Furthermore, based on the above embodiments, the sanitation task management method further includes:

[0119] Step S105: Perform one or more of the following monitors on the sanitation task: real-time task status tracking, task completion rate statistics, abnormal situation warning, data archiving and analysis.

[0120] Through real-time data collection and analysis, the present invention comprehensively supervises the task execution situation to ensure the high-quality completion of the cleaning work, which is specifically reflected in the following four aspects.

[0121] 1) Real-time status tracking. Utilize GPS, vehicle sensors, etc. to monitor the running trajectories of sanitation vehicles or sanitation workers in real time; collect task status information, including task start, completion time, and execution feedback.

[0122] 2) Task completion rate statistics. Automatically generate task completion rate and delay rate reports; for uncompleted tasks, analyze the reasons and prompt solutions.

[0123] 3) Abnormal situation warning. Issue alarms for situations such as task timeout, vehicle failure, garbage overload, etc.; provide automatic reallocation suggestions.

[0124] 4) Data archiving and analysis. Archive all task execution records for subsequent data analysis; optimize future scheduling plans based on historical data.

[0125] In some other embodiments, the present invention discloses a sanitation task management device, including:

[0126] An acquisition module, configured to acquire urban road data, data of each garbage disposal point, data of each charging / fueling point, and sanitation data;

[0127] Urban road data includes one or more of the following information: road identifier, road name, road location, road width, average speed of the current traffic flow, whether there is construction closure, number of lanes, list of road IDs directly connected to this road, road intersection coordinates, turning restrictions, road priority, whether it is a two-way road, traffic conditions in different time periods;

[0128] Garbage disposal point data includes one or more of the following information: garbage bin identifier, garbage bin location, garbage bin filling rate, last cleaning time, sensor status;

[0129] Charging / refueling point data includes one or more of the following information: charging / refueling point identifier, charging / refueling point name, charging / refueling point location, number of vehicles that can be served simultaneously, current number of available service parking spaces, specific type, supported vehicle types, output power of a single charging pile, type of fuel provided, whether it is currently available, working time period;

[0130] Sanitation data includes one or more of the following information: location of sanitation vehicles, location of sanitation workers, total number of sanitation vehicles, total number of sanitation workers, number of idle sanitation vehicles, number of idle sanitation workers;

[0131] The task generation module is used to predict the future fullness of garbage bins and garbage removal requirements based on the garbage disposal point data, and generate several sanitation tasks;

[0132] Each sanitation task has one or more of the following information: task number, task type, task description, task execution location, task priority, time range during which the task can be executed, resources required for the task, task prediction source, task merge group number, reason for dynamic adjustment, manual intervention remarks, current status of the task, expected completion situation;

[0133] The allocation and scheduling module is used to allocate the sanitation tasks to the corresponding sanitation vehicles and / or sanitation workers according to the specific information of the sanitation tasks and the sanitation data, using a reinforcement learning optimized scheduling strategy;

[0134] The path generation module is used to provide the optimal path for the sanitation vehicles and / or sanitation workers to travel to the task execution location based on the urban road data and the data of each charging / refueling point.

[0135] Furthermore, in the task generation module, a scoring model is used to score and rank each generated sanitation task, and set the task priority.

[0136] Furthermore, in the allocation and scheduling module, the reward function of the reinforcement learning optimized scheduling strategy is as follows:

[0137] R = α 1 *R 效率 +α 2 *R成本 +α 3 *R 及时性 ;

[0138] Where: R 效率 is the efficiency index;

[0139] R 成本 is the cost index;

[0140] R 及时性 is the timeliness index;

[0141] α 1 、α 2 、α 3 are coefficients respectively.

[0142] Furthermore, it further includes:

[0143] A task monitoring module for performing one or more of real-time task status tracking, task completion rate statistics, early warning of abnormal situations, data archiving and analysis on sanitation tasks.

[0144] Furthermore, it should be noted that: when the sanitation task management device provided in the above embodiment performs sanitation task management, only the division of the above function modules is used for illustration. In actual application, the above functions can be allocated to different function modules according to needs, that is, the internal structure of the sanitation task management device is divided into different function modules to complete all or part of the functions described above.

[0145] In addition, the sanitation task management device provided in the above embodiment and the embodiment of the sanitation task management method belong to the same concept. For the specific implementation process, please refer to the method embodiment, which will not be elaborated here.

[0146] In addition, in some other embodiments, the present invention also discloses a computing device, including:

[0147] One or more processors;

[0148] A memory;

[0149] And one or more programs, where one or more programs are stored in the memory and are configured to be executed by one or more processors, and one or more programs include the instructions of the sanitation task management method disclosed in the above embodiment.

[0150] The processor may include one or more processing cores, such as: a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, and the AI processor is used to process computational operations related to machine learning.

[0151] The memory may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory is used to store at least one instruction, and the at least one instruction is used to be executed by the processor to implement the sanitation task management method provided in the method embodiments of the present invention.

[0152] In addition, the computing device may optionally further include: a peripheral device interface and at least one peripheral device. The processor, the memory, and the peripheral device interface may be connected through a bus or signal lines. Each peripheral device may be connected to the peripheral device interface through a bus, signal lines, or a circuit board. Schematically, the peripheral devices include but are not limited to: radio frequency circuits, touch display screens, audio circuits, and power supplies, etc.

[0153] Of course, the computing device may also include fewer or more components, and this embodiment does not limit this.

[0154] In addition, in some other embodiments, the present invention also discloses a storage medium, and the storage medium stores one or more computer-readable programs. The one or more programs include instructions, and the instructions are adapted to be loaded and executed by the memory to perform the sanitation task management method disclosed in the above embodiments.

[0155] The present invention discloses a sanitation task management method, device, computing device and storage medium, which has the following beneficial effects:

[0156] The present invention can automatically generate sanitation tasks, dynamically coordinate and allocate sanitation tasks, and at the same time monitor the execution status of sanitation tasks, significantly improving the urban sanitation efficiency and reducing the sanitation cost.

[0157] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification only illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A sanitation task management method, characterized in that: include: Step S1: Obtaining urban road data, data of each garbage disposal point, data of each charging / refueling point and sanitation data; The urban road data includes one or more of the following information: road identifier, road name, road location, road width, average speed of current traffic flow, whether there is construction closure, number of lanes, list of road IDs directly connected to the road, road intersection coordinates, turning restrictions, road priority, whether it is a two-way road, and traffic conditions at different time periods; The waste drop-off point data includes one or more of the following information: waste bin identifier, waste bin location, waste bin fill rate, last cleaning time, sensor status; The charging / refueling point data includes one or more of the following information: charging / refueling point identifier, charging / refueling point name, charging / refueling point location, number of vehicles that can be served simultaneously, number of currently available service spaces, specific type, supported vehicle types, output power of a single charging pile, type of fuel provided, whether it is currently available, and working time period; The sanitation data includes one or more of the following information: the location of sanitation vehicles, the location of sanitation workers, the total number of sanitation vehicles, the total number of sanitation workers, the number of idle sanitation vehicles, and the number of idle sanitation workers; Step S2: Based on the garbage placement point data, predict the future garbage bin fullness and garbage removal needs, and generate several sanitation tasks; Each of the sanitation tasks has one or more of the following information: task number, task type, task description, task execution location, task priority, task executable time range, task required resources, task prediction source, task merge group number, dynamic adjustment reason, manual intervention notes, task current status, and expected completion status; Step S3: According to the specific information and data of the sanitation tasks, the sanitation tasks are assigned to the corresponding sanitation vehicles and / or sanitation workers using a reinforcement learning optimization scheduling strategy; Step S4: Based on the urban road data and the data of each charging / refueling point, provide the sanitation vehicle and / or sanitation worker with the optimal route to the task execution location.

2. The sanitation task management method according to claim 1, characterized in that: In step S2, a scoring model is used to score and sort each generated sanitation task, and a task priority is set.

3. The sanitation task management method according to claim 1, characterized in that: In step S3, the reward function of the reinforcement learning optimization scheduling strategy is as follows: R=α1*R 效率 +α2*R 成本 +α3*R 及时性 ; Where: R 效率 is an efficiency indicator; R 成本 is a cost indicator; R 及时性 It is a timeliness indicator; α1, α2, and α3 are coefficients respectively.

4. The sanitation task management method according to claim 1, characterized in that: Also includes: Step S5: Perform one or more of the following monitoring on the sanitation tasks: real-time task status tracking, task completion rate statistics, abnormal situation warning, data archiving and analysis.

5. The sanitation task management device is characterized by: include: The acquisition module is used to obtain urban road data, data of various garbage disposal points, data of various charging / refueling points, and sanitation data; The urban road data includes one or more of the following information: road identifier, road name, road location, road width, average speed of current traffic flow, whether there is construction closure, number of lanes, list of road IDs directly connected to the road, road intersection coordinates, turning restrictions, road priority, whether it is a two-way road, and traffic conditions at different time periods; The waste drop-off point data includes one or more of the following information: waste bin identifier, waste bin location, waste bin fill rate, last cleaning time, sensor status; The charging / refueling point data includes one or more of the following information: charging / refueling point identifier, charging / refueling point name, charging / refueling point location, number of vehicles that can be served simultaneously, number of currently available service spaces, specific type, supported vehicle types, output power of a single charging pile, type of fuel provided, whether it is currently available, and working time period; The sanitation data includes one or more of the following information: the location of sanitation vehicles, the location of sanitation workers, the total number of sanitation vehicles, the total number of sanitation workers, the number of idle sanitation vehicles, and the number of idle sanitation workers; The task generation module is used to predict the future garbage bin fullness and garbage removal needs based on the garbage drop point data, and generate several sanitation tasks; Each of the sanitation tasks has one or more of the following information: task number, task type, task description, task execution location, task priority, task executable time range, task required resources, task prediction source, task merge group number, dynamic adjustment reason, manual intervention notes, task current status, and expected completion status; The allocation and scheduling module is used to allocate sanitation tasks to corresponding sanitation vehicles and / or sanitation workers based on the specific information and sanitation data of the sanitation tasks and the optimization scheduling strategy of reinforcement learning; The path generation module is used to provide sanitation vehicles and / or sanitation workers with the optimal path to the task execution location based on urban road data and data of various charging / refueling points.

6. The sanitation task management device according to claim 5, characterized in that: In the task generation module, a scoring model is used to score and sort each generated sanitation task, and set the task priority.

7. The sanitation task management device according to claim 5, characterized in that: In the allocation scheduling module, the reward function of the reinforcement learning optimization scheduling strategy is as follows: R=α1*R 效率 +α2*R 成本 +α3*R 及时性 ; Where: R 效率 is an efficiency indicator; R 成本 is a cost indicator; R 及时性 It is a timeliness indicator; α1, α2, and α3 are coefficients respectively.

8. The sanitation task management device according to claim 5, characterized in that: Also includes: The task monitoring module is used to perform one or more of the following monitoring on sanitation tasks: real-time task status tracking, task completion rate statistics, abnormal situation warning, data archiving and analysis.

9. A computing device, characterized in that include: one or more processors; Memory; And one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and one or more of the programs include instructions of the sanitation task management method described in any one of claims 1-4 above.

10. A storage medium, characterized in that The storage medium stores one or more computer-readable programs, and the one or more programs include instructions, and the instructions are suitable for being loaded by the memory and executing the sanitation task management method described in any one of claims 1-4.

Images