Big data-based sanitation vehicle scheduling method and system, product and medium

Abstract

An environmental sanitation vehicle scheduling method and system based on big data, a product and a medium relate to the field of vehicle scheduling, and the method comprises the following steps: obtaining real-time people flow data of a target clean area, and establishing a people flow decline curve according to the real-time people flow data, dividing the target clean area into a plurality of operation time sequence areas based on the human traffic decline curve, calculating an operation priority score of each operation time sequence area according to the garbage accumulation amount, the vehicle GPS position and the road network congestion degree data, and when the operation priority score of the target time sequence area is greater than a preset score threshold value, determining that the target time sequence area is the target time sequence area. Obtaining all target vehicles, the distances between which and the target time sequence region are within a preset distance range; calculating the matching degree of all the target vehicles and the target time sequence region according to the vehicle information of the target vehicles; and sending a scheduling instruction to the target vehicle with the highest matching degree with the target time sequence area. By implementing the method, the vehicle scheduling efficiency of the sanitation vehicles can be improved.

Description

Technical Field

[0001] This application relates to the field of vehicle scheduling, and particularly to a sanitation vehicle scheduling method, system, product, and medium based on big data. Background Art

[0002] With the continuous advancement of urbanization, the importance of urban sanitation work has become increasingly prominent. In order to improve the efficiency of sanitation operations, intelligent means have been adopted everywhere to achieve the scheduling management of sanitation vehicles, so as to ensure the urban environmental sanitation quality and improve the living quality of citizens.

[0003] The current sanitation vehicle scheduling system usually arranges operations at fixed time points and routes. The system dispatches sanitation vehicles to designated areas for cleaning operations according to the pre-set schedule. At the same time, dispatchers will also manually adjust the vehicle operation routes based on daily experience when receiving sanitation requirements.

[0004] However, this fixed-mode scheduling method is difficult to adapt to the dynamic changes of the urban environment. When there are temporary large-scale events or emergencies in the city, the sanitation requirements in some areas will increase sharply, and the pre-set scheduling plan cannot respond to this change in time. In addition, during the actual operation process, due to the failure to fully consider factors such as road conditions and vehicle status, the vehicle scheduling efficiency is often low. Summary of the Invention

[0005] This application provides a sanitation vehicle scheduling method, system, product, and medium based on big data, which is used to improve the vehicle scheduling efficiency of sanitation vehicles.

[0006] In a first aspect, this application provides a sanitation vehicle scheduling method based on big data, which is applied to a sanitation vehicle scheduling system based on big data. The method includes: obtaining real-time pedestrian flow data of a target cleaning area, and establishing a pedestrian flow decline curve based on the real-time pedestrian flow data; dividing the target cleaning area into multiple operation time sequence areas based on the pedestrian flow decline curve; collecting garbage accumulation, vehicle GPS position, and road network congestion data of the target cleaning area, and calculating the operation priority score of each operation time sequence area according to the garbage accumulation, the vehicle GPS position, and the road network congestion data; when there is an operation priority score of a target time sequence area greater than a preset score threshold, obtaining all target vehicles within a preset distance range from the target time sequence area; calculating the matching degree of all the target vehicles with the target time sequence area according to the vehicle information of the target vehicles; and sending a scheduling instruction to the target vehicle with the highest matching degree with the target time sequence area.

[0007] By adopting the above technical solution, the pedestrian flow data is obtained to establish a curve, which provides a basis for operation planning. According to this, the area is divided, multiple types of data are collected to calculate the operation priority score, the vehicles are screened, and the matching degree is calculated and then the dispatching instruction is sent, realizing the accurate dynamic dispatching of vehicles, improving the efficiency of environmental sanitation operations, ensuring the efficient utilization of cleaning resources and the improvement of environmental sanitation quality.

[0008] Combined with some embodiments of the first aspect, in some embodiments, the step of dividing the target cleaning area into multiple operation time sequence areas based on the pedestrian flow decline curve specifically includes: obtaining the decline rate of the pedestrian flow decline curve at different time points; segmenting the target cleaning area according to the decline rate, and dividing the area corresponding to the time period in which the decline rate is continuously greater than the first preset threshold into the first operation time sequence area, and dividing the area corresponding to the time period in which the decline rate is continuously less than the first preset threshold into the second operation time sequence area; generating an operation time sequence area sequence according to the division time sequence of the first operation time sequence area and the second operation time sequence area, and obtaining multiple operation time sequence areas.

[0009] By adopting the above technical solution, the pedestrian flow decline rate is obtained and segmented accordingly, different operation time sequence areas are divided, and then a sequence is generated, enabling the environmental sanitation operations to orderly adapt to the dynamic changes of the pedestrian flow, avoiding resource waste, improving the overall efficiency, and ensuring the effective cleaning of each area.

[0010] Combined with some embodiments of the first aspect, in some embodiments, the step of calculating the matching degree between all the target vehicles and the target time sequence area according to the vehicle information of the target vehicle specifically includes: obtaining the real-time status information of the target vehicle, where the real-time status information includes the current operation load, the remaining operation capacity, and the historical operation record; calculating the available operation capacity index of each target vehicle according to the real-time status information; and performing a weighted calculation on the available operation capacity index and the distance from each target vehicle to the target time sequence area to obtain the matching degree between the target vehicle and the target time sequence area.

[0011] By adopting the above technical solution, the real-time status information of the vehicle is obtained to calculate the available operation capacity index, and the matching degree is obtained by combining the weighted distance from the target area, accurately measuring the adaptability between the vehicle and the area, reasonably allocating vehicle resources, improving the pertinence and effectiveness of environmental sanitation operations, and ensuring the progress of operations and environmental cleanliness.

[0012] In some embodiments in combination with some embodiments of the first aspect, after the step of sending a scheduling instruction to the target vehicle with the highest matching degree to the target time sequence area, the method further includes: when the descending rate of the pedestrian flow descending curve is greater than a first preset threshold, marking the target time sequence area as a quick cleaning area, and obtaining a target vehicle with a matching degree greater than a second preset threshold to the quick cleaning area as a collaborative operation vehicle; when the descending rate is less than the first preset threshold, marking the target time sequence area as a regular cleaning area, sorting the target vehicles according to the operation priority score, and sequentially sending a scheduling warning instruction to each target vehicle according to the sorting result.

[0013] By adopting the above technical solution, the target time sequence area is classified according to the descending rate of the pedestrian flow. The collaborative operation vehicles are screened in the quick cleaning area, which can concentrate efforts for efficient cleaning. In the regular cleaning area, the warning instructions are sent according to the sorting of the priority scores, which can make the vehicles operate in an orderly manner, improving the timeliness and orderliness of the overall operation.

[0014] In some embodiments in combination with some embodiments of the first aspect, after the step of sending a scheduling instruction to the target vehicle with the highest matching degree to the target time sequence area, the method further includes: statistically analyzing the operation efficiency data of each target vehicle in different types of areas, where the operation efficiency data includes the operation area per unit time and the garbage disposal volume; calculating the operation efficiency scores of the target vehicle in the quick cleaning area and the regular cleaning area according to the operation efficiency data; when the target time sequence area is a quick cleaning area, determining the upper limit of the number of collaborative operation vehicles based on the operation efficiency score; when the target time sequence area is a regular cleaning area, adjusting the scheduling priority order of the target vehicle based on the operation efficiency score.

[0015] By adopting the above technical solution, the operation efficiency data of the vehicle in different areas is statistically analyzed and the scores are calculated. The upper limit of the collaborative vehicles is determined in the quick cleaning area to avoid congestion and chaos. In the regular cleaning area, the scheduling order is adjusted according to the scores, optimizing the task allocation, improving the operation efficiency and quality, and making the process more scientific and reasonable.

[0016] In some embodiments in combination with some embodiments of the first aspect, after the step of determining the upper limit of the number of collaborative operation vehicles based on the operation efficiency score when the target time sequence area is a quick cleaning area, the method further includes: obtaining the area information and road distribution information of the target time sequence area; dividing the target time sequence area into a plurality of sub-operation areas according to the area information and the road distribution information; allocating a target operation duration for each sub-operation area based on the operation efficiency score, and generating an operation instruction including the target operation duration and sending it to the target vehicle.

[0017] By adopting the above technical solution, after determining the upper limit of collaborative vehicles in the quick cleaning area, obtain the area information to divide sub-areas, and then allocate the operation duration according to the operation efficiency score and issue instructions to refine the tasks, improve the cleaning efficiency, and ensure environmental cleanliness.

[0018] In combination with some embodiments of the first aspect, in some embodiments, when the target time sequence area is a regular cleaning area, after the step of adjusting the scheduling priority order of the target vehicle based on the operation efficiency score, the method further includes: obtaining the traffic congestion index within the target time sequence area; when it is detected that the traffic congestion index is greater than a preset congestion threshold, calculating an alternative operation route for the target vehicle; and sending a route adjustment instruction including the alternative operation route to the target vehicle.

[0019] By adopting the above technical solution, after adjusting the scheduling order in the regular cleaning area, it is crucial to obtain the traffic congestion index and calculate the alternative route when it exceeds the threshold. Because congestion affects operations, this route is screened through comprehensive consideration by the algorithm. After sending the adjustment instruction, the vehicle can avoid congestion, operate smoothly, reduce delays, improve efficiency, and ensure environmental cleanliness.

[0020] In a second aspect, an embodiment of the present application provides a sanitation vehicle scheduling system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the sanitation vehicle scheduling system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product containing instructions, when the above computer program product runs on a sanitation vehicle scheduling system, enabling the above sanitation vehicle scheduling system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions, when the above instructions run on a sanitation vehicle scheduling system, enabling the above sanitation vehicle scheduling system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the sanitation vehicle scheduling system provided in the second aspect above, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, and will not be elaborated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application establishes a curve by obtaining pedestrian flow data, provides a basis for operation planning, divides regions accordingly, collects various types of data to calculate the operation priority score, screens vehicles, calculates the matching degree, and then sends a scheduling instruction, achieving precise dynamic scheduling of vehicles, improving the efficiency of environmental sanitation operations, ensuring the efficient utilization of cleaning resources, and enhancing the environmental sanitation quality.

[0025] 2. This application segments according to the obtained decline rate of pedestrian flow, divides different operation time sequence regions, and then generates a sequence, enabling environmental sanitation operations to orderly adapt to the dynamic changes of pedestrian flow, avoiding resource waste, improving the overall efficiency, and ensuring effective cleaning of each region.

[0026] 3. This application calculates the available operation capacity index by obtaining the real-time status information of vehicles, combines it with the distance to the target region weighted to obtain the matching degree, accurately measures the adaptability of vehicles to regions, reasonably allocates vehicle resources, enhances the pertinence and effectiveness of environmental sanitation operations, and guarantees the progress of operations and environmental cleanliness. Description of the Drawings

[0027] Figure 1 is a flowchart of a method for scheduling environmental sanitation vehicles based on big data in an embodiment of this application; Figure 2 is another flowchart of a method for scheduling environmental sanitation vehicles based on big data in an embodiment of this application; Figure 3 is a schematic structural diagram of an entity device of an environmental sanitation vehicle scheduling system in an embodiment of this application. Detailed Embodiments

[0028] The terms used in the following embodiments of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application, the singular forms "a", "an", "the above", "the", and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or indicating relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of this application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0030] For ease of understanding, the following describes the process of the method provided in this embodiment. Please refer to Figure 1, which is a schematic flowchart of the method for scheduling sanitation vehicles based on big data in an embodiment of the present application.

[0031] S101. Obtain the real-time pedestrian flow data of the target cleaning area, and establish a pedestrian flow decline curve based on the real-time pedestrian flow data.

[0032] Among them, the target cleaning area refers to a specific geographical range that needs to carry out sanitation operations, including public places such as roads and squares. The real-time pedestrian flow data refers to the number of people in the area measured at a specific time point, which is used to reflect the change of the personnel density in the area. The pedestrian flow decline curve is used to represent the functional relationship between the pedestrian flow in the target cleaning area and time. The horizontal axis is time, and the vertical axis is the pedestrian flow. The curve formed by continuous data points intuitively shows the change trend of the pedestrian flow.

[0033] This step is executed at the initial stage of the sanitation operation plan to obtain the pedestrian flow characteristics of the operation area. Specifically, the system continuously collects pedestrian flow data at a preset time interval (such as 5 minutes) through data collection devices such as video monitoring devices and pedestrian flow detectors deployed in the target cleaning area. The collected data includes time stamps and corresponding pedestrian flow values, forming a time series data set. The system preprocesses the collected data, including operations such as outlier removal and data smoothing, and then uses data analysis algorithms to draw the pedestrian flow decline curve.

[0034] In some embodiments, the collection of pedestrian flow data and the establishment of the curve can be achieved in various ways: Optionally, the video analysis method is adopted. The system collects images through video monitoring devices, uses a person detection algorithm to identify the number of people in the images, records the data at fixed intervals, and draws a curve after data preprocessing; Optionally, the sensor network method is adopted. Infrared sensors, pressure sensors and other detection devices are deployed in the area to count the number of people passing through per unit time, and the data of multiple sensors are merged through a data fusion algorithm to generate a pedestrian flow curve. It can be understood that other methods for collecting pedestrian flow data and establishing curves can also be adopted, which are not limited here.

[0035] S102. Divide the target cleaning area into multiple operation time sequence areas based on the pedestrian flow decline curve.

[0036] Among them, the operation time sequence area refers to an area unit with a similar pedestrian flow decline trend divided according to the change characteristics of the pedestrian flow. The pedestrian flow decline curve represents the functional relationship between the pedestrian flow in the target cleaning area and time. The target cleaning area refers to a specific geographical range that needs to carry out sanitation operations. The area division result refers to the set of sub-areas formed after dividing the target cleaning area according to the time sequence characteristics.

[0037] This step is executed after obtaining the pedestrian flow decline curve and is used to achieve the temporal division of the area. Specifically, the system first analyzes the characteristic parameters of the pedestrian flow decline curve, including the decline rate, decline time period, curve shape, etc. Then, based on these characteristic parameters, the areas with similar decline characteristics are divided into the same operation time sequence area. The division process takes into account the spatial continuity of the area and the similarity of the pedestrian flow changes, ensuring that the division result not only meets the requirements of the time sequence characteristics but also facilitates subsequent operation arrangements.

[0038] In some embodiments, the temporal division of the area can be achieved in various ways: Optionally, a clustering analysis method is adopted, taking the characteristic parameters of the pedestrian flow decline curve as clustering features, and using clustering algorithms such as K-means to divide the area into multiple categories, with each category corresponding to an operation time sequence area; Optionally, a threshold segmentation method is adopted, setting thresholds for key parameters such as the pedestrian flow decline rate and decline time, and dividing according to whether the parameters of the area meet the threshold conditions to form sub-areas with different time sequence characteristics. It can be understood that other area temporal division methods can also be adopted, which are not limited here.

[0039] This step specifically includes: Obtain the decline rate of the pedestrian flow decline curve at different time points.

[0040] Perform time segmentation on the target cleaning area according to the decline rate, dividing the area corresponding to the time period when the decline rate is continuously greater than the first preset threshold into the first operation time sequence area, and dividing the area corresponding to the time period when the decline rate is continuously less than the first preset threshold into the second operation time sequence area.

[0041] Generate an operation time sequence area sequence according to the chronological order of the division of the first operation time sequence area and the second operation time sequence area to obtain multiple operation time sequence areas.

[0042] Among them, the pedestrian flow decline curve represents the functional relationship between the pedestrian flow in the area and time. The decline rate refers to the change amount of the pedestrian flow per unit time, expressed by the slope. The first preset threshold represents the critical value for judging the speed of pedestrian flow change, usually set to -30 people / minute. Time segmentation refers to dividing continuous time into multiple time intervals with different characteristics. The first operation time sequence area refers to the area corresponding to the period of rapid decline in pedestrian flow. The second operation time sequence area refers to the area corresponding to the period of slow decline in pedestrian flow. The operation time sequence area sequence represents a list of areas arranged in chronological order.

[0043] This step is executed after obtaining the pedestrian flow decline curve and is used to divide the operation area based on the characteristics of pedestrian flow changes. Specifically, the system first calculates the instantaneous decline rate of the curve at each sampling point using the difference calculation method for two adjacent points: decline rate = (pedestrian flow at the current moment - pedestrian flow at the previous moment) / (current moment - previous moment). Then, the area where the decline rate is greater than -30 people / minute within a continuous time period is divided into the first operation time sequence area, and the area where the decline rate is less than -30 people / minute is divided into the second operation time sequence area. For example, if the decline rate of a certain area from 17:00 to 18:00 is -45 people / minute and the decline rate from 18:00 to 19:00 is -20 people / minute, then the area corresponding to the period from 17:00 to 18:00 is divided into the first operation time sequence area, and the area corresponding to the period from 18:00 to 19:00 is divided into the second operation time sequence area. Finally, all areas are arranged in chronological order to form a complete operation time sequence area sequence.

[0044] In some embodiments, the regional time sequence division can be achieved in various ways: Optionally, the sliding window method is adopted. First, a time window with a fixed size is set, which slides on the curve and calculates the average decline rate within the window. Then, the area type is divided according to the comparison result between the rate and the threshold. Finally, continuous areas of the same type are merged to form the final division result. Optionally, the clustering analysis method is adopted. First, the decline rate at each time point is used as a feature value, and then the K-means algorithm is used to cluster the time points with similar decline characteristics. Finally, the area type is determined according to the relationship between the clustering center and the threshold. It can be understood that other regional time sequence division methods can also be adopted, which are not limited here.

[0045] S103. Collect the garbage accumulation amount, vehicle GPS location, and road network congestion degree data of the target cleaning area, and calculate the operation priority score of each operation time sequence area according to the garbage accumulation amount, vehicle GPS location, and road network congestion degree data.

[0046] Among them, the garbage accumulation amount refers to the quantity of accumulated garbage in the area, which is quantitatively represented by weight or volume. The vehicle GPS location represents the real-time geographical coordinate information of the sanitation vehicle, including longitude, latitude, and timestamp. The road network congestion degree is a quantitative index of the road traffic condition, with a value range of 0 - 1, and the larger the value, the more serious the congestion degree. The operation priority score is used to represent the cleaning urgency of the operation time sequence area and is a comprehensive scoring index. The operation time sequence area refers to the area unit divided according to the characteristics of pedestrian flow changes.

[0047] This step is executed after the regional timing division is completed and is used to determine the job priority order of each region. Specifically, the system collects data in real time through garbage monitoring devices, vehicle-mounted GPS terminals, and traffic monitoring devices. A weighted calculation method is used to calculate the job priority score, and the calculation formula is: Job priority score = 0.4 × garbage accumulation index + 0.35 × location distance index + 0.25 × (1 - road network congestion degree). Among them, the garbage accumulation index = (current accumulation - minimum threshold) / (maximum threshold - minimum threshold), and the location distance index = 1 - actual distance / maximum reference distance.

[0048] In some embodiments, data collection and priority score calculation can be achieved in various ways: Optionally, an integrated perception method is adopted. First, garbage images are collected by a garbage monitoring camera and the accumulation is calculated. Then, the position data of the vehicle-mounted GPS module is read. Next, the real-time congestion data of the road network monitoring system is obtained. Finally, the three types of data are input into the scoring model to calculate the score. Optionally, a distributed collection method is adopted. First, garbage weight sensors are deployed to measure the accumulation. Then, the Beidou positioning system is used to obtain the vehicle position. Next, traffic flow data is collected by road surface electronic detectors to calculate the congestion degree. Finally, all the data is fused to calculate the priority score. It can be understood that other data collection and score calculation methods can also be adopted, which are not limited herein.

[0049] S104. When the job priority score of a target timing region is greater than the preset score threshold, all target vehicles within the preset distance range from the target timing region are obtained.

[0050] Among them, the target timing region refers to the regional unit that needs to be given priority in job arrangement. The preset score threshold refers to the critical score for triggering priority jobs, usually set to 0.8. The preset distance range is used to represent the maximum service radius of schedulable vehicles, generally set to 3 kilometers. The target vehicle refers to a sanitation vehicle that meets the job conditions and can perform cleaning tasks. The job priority score is used to represent the urgency of regional jobs.

[0051] This step is executed after the job priority score is calculated and is used to screen suitable job vehicles. Specifically, the system first sorts the priority scores of all job timing regions and identifies the target timing regions with scores exceeding the preset threshold. Then, based on the vehicle GPS positioning data, the actual driving distance between each sanitation vehicle and the target timing region is calculated. A vehicle list that meets the distance requirements is obtained through distance screening, providing candidate resources for subsequent scheduling and allocation.

[0052] In some embodiments, vehicle screening and distance calculation can be achieved in various ways: Optionally, the road network analysis method is adopted. First, the complete road network data of the electronic map is obtained, then the shortest path distance from the vehicle to the target area is calculated, and then the distance is compared with the preset range for screening. Finally, a list of vehicles meeting the conditions is output. Optionally, the coordinate calculation method is adopted. First, the GPS coordinates of the vehicle and the target area are obtained, then the straight-line distance is calculated and multiplied by the path correction coefficient. Then, range judgment is performed based on the corrected distance. Finally, a list of vehicles to be scheduled is generated. It can be understood that other vehicle screening and distance calculation methods can also be adopted, which are not limited herein.

[0053] S105. Calculate the matching degree between all the target vehicles and the target time sequence area according to the vehicle information of the target vehicle.

[0054] Among them, the vehicle information refers to the data set describing the characteristics of the sanitation vehicle, including attributes such as vehicle type, operation ability, equipment status, and historical operation records. The target vehicle refers to the sanitation vehicle located within the preset distance range and capable of performing cleaning tasks. The target time sequence area refers to the area unit that needs to be given priority for operation. The matching degree is used to represent the adaptability score between the vehicle and the operation area, with a value range of 0 - 1. The larger the value, the higher the matching degree. The operation ability refers to the cleaning efficiency and garbage collection ability of the vehicle. The historical operation record represents the operation performance data of the vehicle in similar areas.

[0055] This step is executed after obtaining the candidate target vehicles and is used to evaluate the adaptability between the vehicle and the operation area. Specifically, the system adopts a multi-dimensional evaluation method to calculate the matching degree. The calculation formula is: Matching degree = 0.3 × Type matching degree + 0.25 × Ability matching degree + 0.25 × Status matching degree + 0.2 × Experience matching degree. Among them, the type matching degree is determined according to the correspondence between the vehicle type and the area requirements; Ability matching degree = Vehicle operation ability / Area operation requirements; The status matching degree is calculated according to the equipment intact rate; Experience matching degree = Historical operation success rate. For example, if a vehicle has a type matching degree of 0.9, an operation ability of 6000 ㎡ / h corresponding to an area operation requirement of 8000 ㎡ / h, resulting in an ability matching degree of 0.75, an equipment intact rate of 0.95, resulting in a status matching degree of 0.95, and a historical operation success rate of 0.85, then the final matching degree = 0.3 × 0.9 + 0.25 × 0.75 + 0.25 × 0.95 + 0.2 × 0.85 = 0.8625.

[0056] In some embodiments, the calculation of vehicle matching degree can be achieved in various ways: Optionally, the analytic hierarchy process is adopted. First, an evaluation index system is established and the index weights are determined. Then, each index is quantitatively scored. Next, the weighted comprehensive score is calculated. Finally, the optimal matching vehicle is determined according to the score ranking. Optionally, the fuzzy comprehensive evaluation method is adopted. First, the evaluation factor set and the comment set are constructed. Then, the fuzzy relation matrix is established. Next, the fuzzy transformation calculation is carried out. Finally, the matching degree between the vehicle and the region is obtained. It can be understood that other vehicle matching degree calculation methods can also be adopted, which are not limited herein.

[0057] This step specifically includes: Obtain the real-time status information of the target vehicle, where the real-time status information includes the current operation load, the remaining operation capacity, and the historical operation records.

[0058] According to the real-time status information, calculate the available operation capacity index of each target vehicle.

[0059] Perform a weighted calculation on the available operation capacity index and the distance of each target vehicle to the target time sequence region to obtain the matching degree between the target vehicle and the target time sequence region.

[0060] Among them, the real-time status information represents the current working status data set of the sanitation vehicle. The current operation load refers to the proportion of the garbage loaded by the vehicle to the maximum capacity. The remaining operation capacity represents the cleaning area or the amount of garbage that the vehicle can still complete in the current state. The historical operation records are used to represent the completion situation and efficiency data of the vehicle in performing similar tasks in the past. The available operation capacity index refers to the actual working ability score after comprehensively considering the vehicle status. The matching degree represents the adaptability score between the vehicle and the operation area.

[0061] This step is executed after candidate vehicles are screened out and is used to evaluate the actual operation ability and adaptability of the vehicles. Specifically, the system first obtains vehicle status data through on-vehicle sensors and management systems, including the utilization rate of the garbage bin capacity, the status of cleaning equipment, the remaining cruising range, etc. Then, the available operation ability index is calculated, and the calculation formula is: available operation ability index = basic ability coefficient × (1 - current load rate) × equipment status coefficient × historical performance coefficient. Among them, the basic ability coefficient is determined by the vehicle model, the equipment status coefficient is determined according to the status of key components, and the historical performance coefficient is calculated based on the operation completion rate in the past 30 days. Finally, the matching degree is calculated, and the calculation formula is: matching degree = 0.6 × available operation ability index + 0.4 × (1 - distance / maximum service radius). For example, for a vehicle with a basic ability coefficient of 1.0, a current load rate of 0.3, an equipment status coefficient of 0.95, and a historical performance coefficient of 0.9, the calculated available operation ability index is 0.665; the vehicle is 2 kilometers away from the target area and the maximum service radius is 5 kilometers, and finally the calculated matching degree is 0.6 × 0.665 + 0.4 × 0.6 = 0.639.

[0062] In some embodiments, state evaluation and matching degree calculation can be achieved in various ways: Optionally, a multi-sensor fusion method is adopted. First, the current load is measured by a weight sensor, the working status is detected by an equipment sensor, the remaining mileage is calculated by GPS positioning, then the data of each item is standardized, and then the comprehensive ability index is calculated. Finally, the matching degree is obtained by combining the distance factor; Optionally, an intelligent evaluation method is adopted. First, a vehicle status database is established, historical data is analyzed through a deep learning model, then the operation ability is predicted based on real-time data, then the road network distance to the target area is calculated, and finally the matching degree is calculated by fusing various indicators. It can be understood that other state evaluation and matching degree calculation methods can also be adopted, which are not limited here.

[0063] S106. Send a scheduling instruction to the target vehicle with the highest matching degree to the target time sequence area.

[0064] The following further describes the method provided in this embodiment in a more specific process. Please refer to Figure 2 , which is another process schematic diagram of the sanitation vehicle scheduling method based on big data in the embodiment of the present application.

[0065] S201. Send a scheduling instruction to the target vehicle with the highest matching degree to the target time sequence area.

[0066] S202. When the descending rate of the pedestrian flow decline curve is greater than the first preset threshold, mark the target time sequence area as a rapid cleaning area, and obtain the target vehicle with a matching degree greater than the second preset threshold to the rapid cleaning area as a collaborative operation vehicle.

[0067] The pedestrian flow decline curve reflects the functional relationship between the pedestrian flow in a specific area and time. Its decline rate is obtained by calculating the difference in pedestrian flow between adjacent time points divided by the time interval, which reflects the speed of the reduction of pedestrian flow in the area. The first preset threshold is the critical value for judging the urgency of area cleaning and is used to identify areas that need to be processed quickly. The rapid cleaning area refers to the area where the pedestrian flow drops rapidly and needs to be cleaned preferentially and intensively. The collaborative operation vehicle refers to the auxiliary vehicle that jointly executes the cleaning task with the main cleaning vehicle and is selected through matching degree evaluation. The matching degree is a quantitative index that comprehensively considers factors such as vehicle operation ability, distance, and historical performance.

[0068] The system collects pedestrian flow data at fixed time intervals through the sensor network, calculates the decline rate, and compares it with the preset threshold. When the decline rate exceeds the first preset threshold (such as 40 people per minute), the system marks the area as a rapid cleaning area and updates the area status in the database. Subsequently, the system calculates the matching degree scores of all sanitation vehicles within the preset range around. The score calculation uses a weighted method, including three dimensions: remaining operation ability, current distance, and historical operation score. For vehicles with a matching degree exceeding the second preset threshold (such as 0.8 points), the system determines them as collaborative operation vehicles, updates their task status, and sends collaborative operation instructions, thus establishing a multi-vehicle collaborative cleaning mechanism with rapid response.

[0069] S203. When the decline rate is less than the first preset threshold, mark the target time series area as a regular cleaning area, sort the target vehicles according to the operation priority score, and send scheduling warning instructions to each target vehicle in turn according to the sorting result.

[0070] The decline rate refers to the reduction value of pedestrian flow per unit time, which is obtained by calculating the ratio of the difference in pedestrian flow between adjacent time points to the time interval. The regular cleaning area refers to the area where the pedestrian flow changes relatively smoothly and can be cleaned according to the regular operation plan. The operation priority score is a comprehensive score calculated based on factors such as garbage accumulation, vehicle GPS location, and road network congestion. The scheduling warning instruction is a job preparation notice sent by the system to the sanitation vehicle, including information such as the estimated operation time and area location.

[0071] When the system detects that the decline rate of the regional pedestrian flow is lower than the first preset threshold, it marks the area as a regular cleaning area. Subsequently, the system sorts the target vehicles in the area in descending order according to the previously calculated operation priority scores. The score calculation adopts a weighted method: operation priority score = 0.4 × garbage accumulation index + 0.3 × location distance index + 0.3 × road network smoothness index. After the sorting is completed, the system sequentially sends a scheduling warning instruction containing operation area information, estimated start time, and operation requirements to each target vehicle in descending order of the scores. This scheduling warning instruction contains a prompt message to prompt the target vehicle for pre-operation.

[0072] S204. Statistically calculate the operation efficiency data of each target vehicle in different types of areas. This operation efficiency data includes the operation area per unit time and the garbage disposal volume.

[0073] The operation efficiency data is a set of quantitative indicators to measure the work performance of sanitation vehicles. The operation area per unit time refers to the area of the region cleaned by the vehicle within one hour, measured in square meters per hour. The garbage disposal volume refers to the quantity of garbage collected and processed by the vehicle within the unit time, measured in kilograms per hour. Different types of areas include rapid cleaning areas and regular cleaning areas, and each type of area has different operation characteristics and requirements.

[0074] The system continuously collects vehicle operation data through on-vehicle sensors and GPS positioning devices. For the statistics of the operation area, the system calculates the actual area covered by cleaning according to the vehicle GPS trajectory; for the statistics of the garbage disposal volume, it measures the weight difference before and after garbage collection through on-vehicle weight sensors. The system summarizes the data on an hourly basis and records and stores them separately according to the area type. For example, in the rapid cleaning area, the system records the average operation area and garbage disposal volume of the vehicle per hour; in the regular cleaning area, the same two indicators are recorded. These statistical data will be used to evaluate the vehicle operation ability and optimize subsequent scheduling decisions.

[0075] S205. Calculate the operation efficiency scores of the target vehicle in the rapid cleaning area and the regular cleaning area according to the operation efficiency data.

[0076] The operation efficiency data includes two key indicators: the operation area per unit time and the garbage disposal volume, which respectively represent the cleaning efficiency and garbage collection efficiency of sanitation vehicles. The operation efficiency score is a comprehensive score obtained by weighted calculation of these two indicators, used to quantitatively evaluate the operation performance of the vehicle in different types of areas. Different weight coefficients are adopted for the rapid cleaning area and the regular cleaning area to adapt to their respective operation characteristics.

[0077] For each target vehicle, the system calculates its operation efficiency scores in two types of areas respectively using a weighted calculation method. The calculation formula is: Operation efficiency score = α × (Operation area per unit time / Benchmark operation area) + β × (Waste treatment volume / Benchmark treatment volume). Among them, the weight coefficients for the rapid cleaning area are α = 0.6 and β = 0.4, and the weight coefficients for the regular cleaning area are α = 0.5 and β = 0.5. The benchmark values are taken from the historical best performance of all vehicles in the corresponding areas. For example, if a vehicle's operation area per unit time in the rapid cleaning area is 2000 square meters per hour (benchmark value 2500), and the waste treatment volume is 180 kilograms per hour (benchmark value 200), then its operation efficiency score is: 0.6 × (2000 / 2500) + 0.4 × (180 / 200) = 0.48 + 0.36 = 0.84.

[0078] S206. When the target time sequence area is a rapid cleaning area, determine the upper limit of the number of collaborative operation vehicles based on this operation efficiency score.

[0079] Collaborative operation vehicles refer to auxiliary vehicles that cooperate with the main cleaning vehicles to jointly perform cleaning tasks. The upper limit of the number refers to the maximum number of collaborative vehicles operating simultaneously in the rapid cleaning area. The operation efficiency score is a quantitative indicator for evaluating the operation ability of vehicles, and is used to screen high-performance vehicles to participate in collaborative operations.

[0080] The system dynamically determines the upper limit of the number of collaborative operation vehicles according to the area and operation efficiency score of the target time sequence area. The calculation process includes three steps: First, calculate the area coefficient K1 = Actual area / Standard reference area; then calculate the average efficiency coefficient K2 = Average operation efficiency score of all candidate vehicles; finally, calculate through the formula: Upper limit of the number N = Basic number × K1 × K2. For example, if the area of a rapid cleaning area is 10000 square meters (standard reference area 8000 square meters), the average operation efficiency score of the candidate vehicles is 0.85, and the basic number is 3 vehicles, then the upper limit of the number of collaborative operation vehicles N = 3 × (10000 / 8000) × 0.85 = 3.19. After rounding, the final upper limit is 3 vehicles. The system will strictly control the number of collaborative vehicles operating simultaneously not to exceed 3 vehicles during subsequent scheduling.

[0081] S207. When the target time sequence area is a regular cleaning area, adjust the scheduling priority order of the target vehicle based on this operation efficiency score.

[0082] The scheduling priority order refers to the order of sanitation vehicles to perform cleaning tasks. The target vehicle refers to a sanitation vehicle located within a preset range and meeting the basic scheduling conditions. The operation efficiency score reflects the operation performance of the vehicle in the regular cleaning area and is an important basis for determining the scheduling order.

[0083] The system uses a comprehensive sorting algorithm to adjust the scheduling priority order of vehicles. First, the operation efficiency scores are standardized: Standard score = (Original score - Lowest score) / (Highest score - Lowest score); then, the priority index is calculated in combination with the current vehicle position: Priority index = 0.7×Standard score + 0.3×(1 - Current distance / Maximum reference distance). The system determines the final scheduling order by arranging in descending order of the priority index. For example, if the operation efficiency scores of three vehicles are 0.85, 0.76, and 0.92 respectively, and the current distances are 2 km, 1 km, and 3 km (maximum reference distance 5 km), then their standard scores are 0.56, 0, and 1 respectively, and the priority indexes are 0.58, 0.34, and 0.82 respectively. The final scheduling order is: the third vehicle, the first vehicle, and the second vehicle.

[0084] S208. Obtain the area information and road distribution information of the target time sequence area.

[0085] The target time sequence area refers to a specific area that needs to carry out environmental sanitation operations, which is determined by the system according to the change of the pedestrian flow. The area information includes data in three dimensions: the total area, the cleanable area, and the non-cleanable area of the area, with the unit of square meters. The road distribution information includes elements such as road grades (arterial roads, secondary arterial roads, branch roads), road widths, road lengths, road connection relationships, and road types (motor vehicle lanes, non-motor vehicle lanes, sidewalks).

[0086] The system obtains the detailed information of the target time sequence area through the electronic map database. First, read the sequence of boundary coordinate points of the area, and calculate the total area using the polygon area calculation formula. Then, extract the road network data within the area, including the start and end point coordinates, width parameters, and attribute labels of the roads. For example, the total area of a certain target time sequence area is 50,000 square meters, of which the cleanable area is 45,000 square meters, including 2 arterial roads (width 20 meters, total length 1,200 meters), 4 secondary arterial roads (width 15 meters, total length 2,400 meters), and 8 branch roads (width 8 meters, total length 3,600 meters). The system stores these data in a temporary data table to provide basic data support for subsequent area division.

[0087] S209. Divide the target time sequence area into multiple sub-operation areas according to the area information and the road distribution information.

[0088] The sub-operation area refers to a smaller area unit obtained by dividing the target time sequence area according to the characteristics of the cleaning operation. The division process comprehensively considers the area size of the area and the road distribution characteristics to ensure that each sub-operation area has a relatively independent operation space and clear boundaries. The road network is used as the main reference basis for division to determine the boundary lines of the sub-operation areas.

[0089] The system performs the partitioning operation using a zoning algorithm. First, the area is divided into main blocks based on the main roads, and the area of each main block does not exceed 15,000 square meters. Then, the main blocks are subdivided into secondary blocks with the secondary roads as the boundaries, and the area is controlled within the range of 5,000 - 8,000 square meters. Finally, the final partitioning is completed using the branch roads to ensure that the area of each sub-operation area is between 2,000 - 3,000 square meters. When partitioning, it is ensured that each sub-operation area contains at least one main road as the access route for the operation vehicles. For example, a target time-series area with an area of 45,000 square meters is finally divided into 20 sub-operation areas according to the above algorithm, with an average area of 2,250 square meters for each sub-operation area, and each having an independent vehicle access route.

[0090] S210. Allocate a target operation duration for each such sub-operation area based on the operation efficiency score, and generate an operation instruction containing the target operation duration and send it to the target vehicle.

[0091] The target operation duration refers to the estimated time required to complete the cleaning task of the sub-operation area. The operation instruction is a task execution instruction sent by the system to the sanitation vehicle, including content such as the location of the operation area, operation time requirements, and operation quality standards. The operation efficiency score is a quantitative indicator for evaluating the vehicle's operation ability and is used to calculate a reasonable operation duration.

[0092] The system calculates the target operation duration based on the characteristics of the sub-operation area and the vehicle operation efficiency score. The calculation formula is: target operation duration = sub-operation area ÷ (benchmark operation rate × operation efficiency score), where the benchmark operation rate is 1,000 square meters per hour. At the same time, a correction is made considering the road type coefficient: the main road coefficient is 1.2, the secondary road coefficient is 1.0, and the branch road coefficient is 0.8. For example, a sub-operation area with an area of 2,250 square meters contains 50% of the secondary roads and 50% of the branch roads, and the assigned vehicle operation efficiency score is 0.85. Then the target operation duration of this area = 2,250 ÷ (1,000 × 0.85) × [(1.0 + 0.8) ÷ 2] = 2.38 hours. The system generates an operation instruction containing information such as the operation area number, target operation duration, start time, etc., and sends it to the target vehicle through the in-vehicle terminal.

[0093] S211. Obtain the traffic congestion index within the target time-series area.

[0094] The traffic congestion index is a quantitative indicator reflecting the road traffic conditions, with a value range of 0 - 10. The larger the value, the more serious the congestion degree. The traffic congestion index is calculated from the data of three dimensions: road traffic volume, vehicle driving speed, and road traffic capacity. The traffic congestion index within the target time-series area refers to the weighted average congestion index of all roads in this area.

[0095] The system collects traffic data in real time through electronic road monitoring equipment and vehicle-mounted GPS terminals. For each road, the number of vehicles passing through per unit time and the average driving speed are first obtained, and then the single-section congestion index is calculated according to the formula: 4×(current traffic volume / road design traffic volume)+6×(1-current average speed / road design speed). Finally, the overall congestion index of the region is calculated according to the road grade weight (main road 0.5, secondary road 0.3, branch road 0.2). For example, the current traffic volume of the main road in a certain area is 80% of the design traffic volume, and the average speed is 40% of the design speed. The single-section congestion index is calculated to be 4×0.8+6×0.6=6.8; similarly, the secondary road index is 5.2 and the branch road index is 4.1, then the overall congestion index of the region is 6.8×0.5+5.2×0.3+4.1×0.2=5.89.

[0096] S212: When it is detected that the traffic congestion index is greater than a preset congestion threshold, an alternative operating route for the target vehicle is calculated.

[0097] The preset congestion threshold is the critical value for judging whether the road traffic conditions require adjustment of the operation route, which is usually set to 6.0. An alternative operation route refers to an alternative route that can complete the same operation task when the original operation route is not suitable for traffic. The target vehicle refers to the sanitation vehicle performing the cleaning task.

[0098] The system calculates alternative operation routes through a path planning algorithm. First, the complete road network data of the target time series area is extracted, and the road sections with congestion index exceeding the preset threshold are eliminated. Then, with the current location as the starting point and the operation area as the end point, the A* algorithm is used to calculate multiple path plans. A comprehensive score is calculated for each path plan: score = 0.4×(1-path length / longest path)+0.3×(1-average congestion index / maximum congestion index)+0.3×(1-number of turns / maximum number of turns). The path with the highest score is the alternative operation route. For example, the original route length of a sanitation vehicle is 2.5 kilometers. When the regional congestion index reaches 7.2, the system calculates three alternative paths with lengths of 3.0, 2.8, and 3.2 kilometers, respectively. The average congestion indexes are 4.5, 4.8, and 4.2, respectively. The number of turns is 5, 4, and 6, respectively. The calculated comprehensive scores are 0.72, 0.78, and 0.65, respectively. Therefore, the second path is selected as the alternative operation route.

[0099] S213: Sending a route adjustment instruction including the alternative operating route to the target vehicle.

[0100] The route adjustment instruction is a route change notice sent by the system to the sanitation vehicle, including information such as the new route coordinate sequence, turning prompts at key intersections, and estimated time of arrival. The alternative operation route is the optimal alternative path calculated, including detailed road section information and navigation data.

[0101] The system sends the route adjustment instruction to the target vehicle through the in-vehicle terminal. The instruction content includes: route adjustment reason code, original route number, new route number, route coordinate point sequence, traffic status of each road section, turning instructions at key nodes, estimated completion time, etc. The coordinate point sequence adopts the longitude and latitude format, and each coordinate point contains position and timestamp information. For example, a certain route adjustment instruction contains 50 navigation coordinate points, the starting point coordinate is (116.404, 39.915), the ending point coordinate is (116.427, 39.903), passing through 5 key intersections, and the estimated time of arrival is 45 minutes. The system packs these data into a standard format instruction message and sends it to the in-vehicle terminal through the 4G network, and requests the terminal to return a reception confirmation message.

[0102] The following describes the sanitation vehicle scheduling system in the embodiment of the present invention application from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of the sanitation vehicle scheduling system in the embodiment of the present application.

[0103] It should be noted that Figure 3 the structure of the sanitation vehicle scheduling system shown is only an example and should not bring any limitations to the functions and usage scope of the embodiments of the present invention.

[0104] As Figure 3 shown, the sanitation vehicle scheduling system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage section 308 into the random access memory (RAM) 303, such as executing the method described in the above embodiments. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other through a bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0105] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD), an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. The drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed on the drive 310 as needed so that a computer program read from it can be installed into the storage section 308 as needed.

[0106] Specifically, according to an embodiment of the present invention, the processes described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are executed.

[0107] It should be noted that specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the block may occur in a different order than that marked in the accompanying drawings.

[0109] Specifically, the sanitation vehicle scheduling system of this embodiment includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, it implements the method for scheduling sanitation vehicles based on big data provided in the above-mentioned embodiment.

[0110] On the other hand, the present invention also provides a computer-readable storage medium. This storage medium may be included in the sanitation vehicle scheduling system described in the above-mentioned embodiment; or it may exist alone without being assembled into the sanitation vehicle scheduling system. The above storage medium carries one or more computer programs. When the above one or more computer programs are executed by a processor of the sanitation vehicle scheduling system, the sanitation vehicle scheduling system is enabled to implement the method for scheduling sanitation vehicles based on big data provided in the above-mentioned embodiment.

[0111] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

[0112] As used in the above embodiments, depending on the context, the term "when..." may be interpreted to mean "if...", or "after...", or "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detecting (the stated condition or event)" may be interpreted to mean "if determining...", or "in response to determining...", or "when detecting (the stated condition or event)", or "in response to detecting (the stated condition or event)".

[0113] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by relevant hardware instructed by a computer program. This program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The aforementioned storage medium includes various media that can store program codes, such as ROM, random access memory (RAM), magnetic disks, or optical discs.

Claims

1. A sanitation vehicle dispatching method based on big data, characterized in that: Applied to a sanitation vehicle dispatching system, the method comprises: Acquire real-time human flow data of the target cleaning area, and establish a human flow decline curve based on the real-time human flow data; Dividing the target cleaning area into a plurality of operation timing areas based on the human flow decline curve; Collecting garbage accumulation, vehicle GPS location and road network congestion data in the target cleaning area, and calculating the operation priority score of each operation timing area according to the garbage accumulation, vehicle GPS location and road network congestion data; When there is a target time sequence area whose job priority score is greater than a preset score threshold, all target vehicles within a preset distance range from the target time sequence area are acquired; Calculating the matching degree between all the target vehicles and the target time series area according to the vehicle information of the target vehicle; A dispatch instruction is sent to the target vehicle that has the highest matching degree with the target timing area.

2. The method according to claim 1, characterized in that The step of dividing the target cleaning area into a plurality of operation timing areas based on the human flow decline curve specifically includes: Obtain the decline rate of the pedestrian flow decline curve at different time points; The target cleaning area is divided into time segments according to the drop rate, and the area corresponding to the time period in which the drop rate is continuously greater than the first preset threshold is divided into a first operation timing area, and the area corresponding to the time period in which the drop rate is continuously less than the first preset threshold is divided into a second operation timing area; According to the division time sequence of the first operation timing region and the second operation timing region, an operation timing region sequence is generated to obtain a plurality of operation timing regions.

3. The method according to claim 1, characterized in that The step of calculating the matching degree between all the target vehicles and the target time series area according to the vehicle information of the target vehicle specifically includes: Acquiring real-time status information of the target vehicle, wherein the real-time status information includes current operating load, remaining operating capacity and historical operating records; Calculating the available operating capacity index of each of the target vehicles according to the real-time status information; The available operating capability index and the distance from each target vehicle to the target timing area are weightedly calculated to obtain the matching degree between the target vehicle and the target timing area.

4. The method according to claim 1, characterized in that After the step of sending the dispatch instruction to the target vehicle with the highest matching degree with the target time sequence area, the method further includes: When the decreasing rate of the pedestrian flow decreasing curve is greater than a first preset threshold, the target time series area is marked as a fast cleaning area, and a target vehicle whose matching degree with the fast cleaning area is greater than a second preset threshold is obtained as a cooperative operation vehicle; When the decreasing rate is less than the first preset threshold, the target time sequence area is marked as a regular cleaning area, the target vehicles are sorted according to the job priority scores, and a dispatch warning instruction is sent to each of the target vehicles in turn according to the sorting results.

5. The method according to claim 4, characterized in that After the step of sending the dispatch instruction to the target vehicle with the highest matching degree with the target time sequence area, the method further includes: Counting the operating efficiency data of each target vehicle in different types of areas, wherein the operating efficiency data includes the operating area per unit time and the amount of garbage processed; Calculating the operating efficiency scores of the target vehicle in the fast cleaning area and the regular cleaning area according to the operating efficiency data; When the target time sequence area is a fast cleaning area, determining an upper limit on the number of the cooperative working vehicles based on the working efficiency score; When the target time sequence area is a regular cleaning area, the dispatch priority of the target vehicle is adjusted based on the work efficiency score.

6. The method according to claim 5, characterized in that When the target time sequence area is a fast cleaning area, after the step of determining the upper limit of the number of the cooperative working vehicles based on the working efficiency score, the method further includes: Acquiring area information and road distribution information of the target time series area; Dividing the target time sequence area into a plurality of sub-operation areas according to the area information and the road distribution information; A target operation duration is allocated to each of the sub-operation areas based on the operation efficiency score, and an operation instruction including the target operation duration is generated and sent to the target vehicle.

7. The method according to claim 5, characterized in that After the step of adjusting the dispatch priority of the target vehicle based on the work efficiency score when the target time sequence area is a regular cleaning area, the method further includes: Obtaining a traffic congestion index within the target time series area; When it is detected that the traffic congestion index is greater than a preset congestion threshold, calculating an alternative operating route for the target vehicle; A route adjustment instruction including the alternative working route is sent to the target vehicle.

8. A sanitation vehicle dispatching system, characterized in that: The sanitation vehicle dispatching system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the sanitation vehicle dispatching system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the sanitation vehicle dispatching system, the sanitation vehicle dispatching system executes the method as described in any one of claims 1-7.

10. A computer program product, characterized in that When the computer program product runs on a sanitation vehicle dispatching system, the sanitation vehicle dispatching system executes the method according to any one of claims 1 to 7.

Images