Sanitation vehicle AI intelligent scheduling method and system based on carbon footprint perception, medium and product

Abstract

The application provides a sanitation vehicle AI intelligent scheduling method and system based on carbon footprint awareness, medium and product, relating to the technical field of intelligent scheduling. The method comprises real-time collection of current position and real-time load of sanitation vehicles and other vehicle state information; obtaining target operation area road network topology data, covering road slope, real-time congestion, and red light node density; combining with the established sanitation operation task, planning multiple alternative driving routes for each sanitation vehicle; integrating vehicle state and various road network data, respectively accounting for the comprehensive carbon emissions of each candidate route; taking carbon emissions as the core evaluation basis, generating the optimal sanitation vehicle scheduling scheme, and issuing it to each sanitation vehicle for execution. The method includes key factors affecting carbon emissions such as vehicle load and road conditions in route evaluation, and completes intelligent scheduling by quantifying the carbon footprint of each route, which can effectively reduce the overall carbon emissions of sanitation operations and achieve low-carbon sanitation operation scheduling.

Description

Technical Field

[0001] This application relates to the field of intelligent scheduling technology, and in particular to an AI-based intelligent scheduling method, system, medium, and product for sanitation vehicles based on carbon footprint perception. Background Technology

[0002] Sanitation vehicles (such as water trucks, street sweepers, and garbage trucks) are special-purpose vehicles that operate frequently in urban road networks. Their long operating routes and high frequency of operations result in carbon emissions (fuel or electricity consumption) that constitute a significant portion of the carbon footprint of urban public services. Reasonable vehicle scheduling is not only fundamental to ensuring the quality of urban environmental sanitation operations but also a key means to achieve low-carbon and refined management of urban sanitation operations.

[0003] Currently, most existing sanitation vehicle dispatching methods employ traditional route planning algorithms based on static road network data, primarily using "shortest travel distance" or "least estimated travel time" as the single optimization objective to generate dispatch routes. Some newer, more environmentally friendly dispatching schemes introduce carbon emission estimation mechanisms. Based on the vehicle's fixed weight (empty or fully loaded) and average energy consumption per 100 kilometers, the total route length is multiplied by the average carbon emission factor to estimate the carbon emissions of the entire route. The corresponding driving or operating routes are then assigned to sanitation vehicles based on the estimation results.

[0004] However, existing scheduling methods have significant technical flaws, failing to accurately calculate and optimize the true carbon footprint of sanitation vehicle operations. Sanitation vehicles possess a unique "dynamic load" attribute: the load of consumable vehicles (such as water trucks) continuously decreases during operation, while the load of collection vehicles (such as garbage trucks) continuously increases. Existing technologies use fixed loads for carbon emission estimation, completely detaching from real-world operating conditions. This often leads to the system incorrectly scheduling vehicles that are gradually approaching full capacity to long uphill sections or congested areas, ultimately resulting in scheduling schemes that are not truly "low-carbon optimal," severely limiting the carbon reduction ceiling of the sanitation system. Summary of the Invention

[0005] This application provides an AI-based intelligent scheduling method, system, medium, and product for sanitation vehicles based on carbon footprint perception, which can be used to achieve low-carbon, efficient, and intelligent scheduling of sanitation operations.

[0006] Firstly, this application provides an AI-based intelligent dispatching method for sanitation vehicles based on carbon footprint perception. The method includes: real-time collection of vehicle status information for each sanitation vehicle, including the vehicle's current location and real-time load data; acquisition of road network topology data for the target work area, including slope information of each road segment, real-time traffic congestion status, and traffic light density; determination of multiple candidate routes for each sanitation vehicle based on preset sanitation work tasks; determination of comprehensive carbon emission data for each candidate route based on the vehicle status information and the road network topology data; and generation of a dispatching plan based on the comprehensive carbon emission data and distribution it to each sanitation vehicle for execution.

[0007] By adopting the above technical solution, the real-time load data of vehicles is coupled with dynamic topological features of the road network such as slope, congestion, and traffic lights, so that carbon emission calculation is transformed from static estimation that relies on fixed parameters to dynamic quantification that reflects the actual working conditions. On this basis, comprehensive carbon emission data is used as a route evaluation criterion to select the best from multiple candidate routes, so that the final dispatching plan can meet the operational needs while tending to the lowest global carbon emissions, thereby significantly improving the carbon reduction accuracy and carbon reduction limit of the sanitation vehicle fleet as a whole.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, the step of obtaining the real-time load data of the sanitation vehicle specifically includes: for consumable sanitation vehicles, reading the liquid level sensor data of the on-board water tank and converting it into the current liquid load of the vehicle in real time; for collection-type sanitation vehicles, reading the weighing sensor at the bottom of the vehicle compartment and converting it into the current solid load of the vehicle in real time.

[0009] By adopting the above technical solution, the two sensing methods are matched with the corresponding material morphology characteristics, so that the load data can reflect the completely opposite load change trends of different types of sanitation vehicles in the operation process in real time and accurately. This provides a dynamic load input that is highly consistent with the actual working conditions for subsequent carbon emission calculations, avoiding the estimation deviation caused by replacing the actual load with a fixed self-weight.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining the comprehensive carbon emission data of each candidate route based on the vehicle status information and the road network topology data specifically includes: determining the initial carbon emission of each candidate route; extracting the slope sections in each candidate route; determining the expected load when the target sanitation vehicle enters the slope section based on the real-time load data; determining the slope carbon emission adjustment amount for each slope section based on the vehicle type of the target sanitation vehicle, the vehicle type including consumable sanitation vehicles and collection sanitation vehicles; and superimposing the initial carbon emission amount with the carbon emission adjustment amount to obtain the first carbon emission amount.

[0011] By adopting the above technical solution, a load-sensitive correction for slope sections is further introduced on the basis of the initial carbon emissions. Since the load directly affects the additional driving energy consumption or potential energy recovery of the vehicle on the slope, by predicting the expected load when the vehicle enters each slope section and making differentiated adjustments according to vehicle type, the nonlinear coupling effect of terrain factors and dynamic load on fuel consumption can be accurately incorporated into the carbon emission assessment model, so that the first carbon emissions are closer to the actual emission level of the vehicle under real slope conditions than the initial value.

[0012] In some embodiments of the first aspect, the step of determining the comprehensive carbon emission data of each candidate route based on the vehicle status information and the road network topology data specifically includes: determining the estimated start-stop frequency of the target vehicle by combining the real-time traffic congestion status and the traffic light node density; determining the standard carbon emission amount of the target sanitation vehicle passing through traffic light nodes and congested road sections based on the estimated start-stop frequency; determining the corresponding start-stop carbon emission adjustment amount based on the vehicle type of the target sanitation vehicle and the estimated start-stop frequency; superimposing the standard carbon emission amount and the start-stop carbon emission adjustment amount to obtain the second carbon emission amount; and superimposing the first carbon emission amount and the second carbon emission amount to obtain the comprehensive carbon emission data.

[0013] By adopting the above technical solution, the frequent starts and stops caused by congested road sections and traffic light nodes are quantified as an independent carbon emission impact dimension. The inertial energy consumption of each start and stop is corrected by combining the load change trend caused by vehicle type. This makes the carbon emission assessment not only cover constant speed driving and slope conditions, but also the acceleration and deceleration scenarios that account for a large proportion of urban roads. Finally, the first carbon emission and the second carbon emission are superimposed to form comprehensive carbon emission data, forming a complete carbon footprint profile that integrates multiple factors, ensuring that the route selection conclusion has the ability to cover all working conditions.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining the expected load of the target sanitation vehicle when entering the sloping road section based on the real-time load data specifically includes: determining the dynamic load change of the target sanitation vehicle within the most recent preset time period; extracting the estimated working distance between the current position of the target sanitation vehicle and the sloping road section; and combining the real-time load data and the dynamic load change of the target sanitation vehicle to determine the expected load of the target sanitation vehicle when entering the sloping road section.

[0015] By adopting the above technical solution, the current operating consumption or collection rate of the vehicle is characterized by the dynamic load change within the most recent preset time period. Then, the estimated operating distance between the current location and the slope section is extrapolated, enabling the system to predict the load status of the vehicle before it even reaches the slope. This forward-looking calculation based on historical trends overcomes the lag caused by relying solely on instantaneous load, allowing subsequent adjustments to carbon emissions on the slope to be based on load expectations that are more in line with actual operating conditions, thus improving the spatiotemporal accuracy of carbon emission assessment.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining the slope carbon emission adjustment amount for each slope segment based on the vehicle type of the target sanitation vehicle specifically includes: extracting the slope aspect characteristics of each slope segment, the slope aspect characteristics including uphill and downhill segments; when the slope segment is an uphill segment, calculating the carbon emission increase based on the expected load capacity, uphill slope value and preset climbing resistance coefficient, the carbon emission increase being positively correlated with the expected load capacity; when the slope segment is a downhill segment, calculating the carbon emission reduction based on the expected load capacity, downhill slope value and preset potential energy conversion coefficient, the carbon emission reduction being positively correlated with the expected load capacity; and statistically analyzing the carbon emission increase and carbon emission reduction for each slope segment in each candidate route to obtain the slope carbon emission adjustment amount.

[0017] By adopting the above technical solution, the slope characteristics are distinguished into uphill and downhill, and carbon emission corrections are applied in opposite directions: when going uphill, the greater the load, the greater the climbing resistance, thus increasing carbon emissions; when going downhill, the greater the load, the more potential energy can be recovered, thus reducing carbon emissions. This positive and negative two-way correction mechanism enables the carbon emission model to truly reflect the differentiated energy consumption impact of terrain on vehicles under different load states. The final calculated slope carbon emission adjustment takes into account the cumulative net effect of all slopes in the route, avoiding systematic bias caused by single-direction estimation.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining the corresponding start-stop carbon emission adjustment amount based on the vehicle type of the target sanitation vehicle and the estimated start-stop frequency specifically includes: when the target sanitation vehicle is a consumable sanitation operation vehicle, determining multiple first estimated load capacities of the target sanitation vehicle when starting and stopping based on the estimated start-stop frequency; calculating corresponding first start-stop carbon emission correction values ​​based on each of the first estimated load capacities and a preset start-stop inertial drag coefficient; and superimposing the first start-stop carbon emission correction values ​​to obtain the start-stop carbon emission adjustment amount; when the target sanitation vehicle is a collection-type sanitation operation vehicle, determining multiple second estimated load capacities of the target sanitation vehicle when starting and stopping based on the estimated start-stop frequency; calculating corresponding second start-stop carbon emission correction values ​​based on each of the second estimated load capacities and the start-stop inertial drag coefficient; and superimposing the second start-stop carbon emission correction values ​​to obtain the start-stop carbon emission adjustment amount.

[0019] By adopting the above technical solution, the estimated load weight is calculated for each start and stop of consumable and collection-type sanitation vehicles. Since the load of consumable vehicles decreases as the operation progresses while the load of collection-type vehicles increases, the inertial resistance corresponding to each start and stop is significantly different. By calculating independent start and stop carbon emission correction values ​​for each start and stop and then accumulating them, the start and stop carbon emission adjustment accurately reflects the step-by-step impact of dynamic load changes on acceleration and deceleration energy consumption. Compared with the method of uniformly estimating by average load, it has higher calculation granularity and evaluation accuracy.

[0020] In a second aspect, this application provides a scheduling system comprising: one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code including computer instructions, wherein the one or more processors invoke the computer instructions to cause the scheduling system to perform the methods described in the first aspect and any possible implementation thereof.

[0021] Thirdly, this application provides a computer-readable storage medium including instructions that, when executed on a scheduling system, cause the scheduling system to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, this application provides a computer program product, including a computer program that, when run on a scheduling system, causes the scheduling system to perform the method described in the first aspect and any possible implementation thereof. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of a scenario of the AI-based intelligent dispatching method for sanitation vehicles based on carbon footprint perception in the embodiments of this application;

[0024] Figure 2 This is a flowchart illustrating an AI-powered intelligent dispatching method for sanitation vehicles based on carbon footprint perception, as described in this application.

[0025] Figure 3 This is another flowchart illustrating the AI-powered intelligent dispatching method for sanitation vehicles based on carbon footprint perception, as described in this application.

[0026] Figure 4 This is a schematic diagram of the physical device structure of the scheduling system in the embodiments of this application. Detailed Implementation

[0027] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to and includes any or all possible combinations of one or more of the listed items.

[0028] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0029] The following describes an AI-based intelligent dispatching method for sanitation vehicles based on carbon footprint perception, using a scenario from this embodiment as an example. Please refer to [link / reference]. Figure 1 , Figure 1 This is an exemplary scenario diagram of an AI-based intelligent dispatching method for sanitation vehicles based on carbon footprint perception, as described in this application.

[0030] exist Figure 1In this system, multiple sanitation vehicles perform sanitation tasks within the target work area's road network. The dispatch system collects real-time vehicle status information for each vehicle, including its current location and real-time load data. Simultaneously, the system acquires road network topology data for the target work area, including slope information for each road segment, real-time traffic congestion status, and traffic light density. Based on preset sanitation tasks, the dispatch system identifies multiple candidate routes for each sanitation vehicle. Combining the collected vehicle status information and road network topology data, it calculates and evaluates the comprehensive carbon emission data for each candidate route, determining the comprehensive carbon emission data under the influence of multiple factors such as dynamic vehicle load changes, slope terrain, traffic congestion, and traffic light start / stop. Finally, the dispatch system generates an optimal carbon emission dispatch plan based on the comprehensive carbon emission data of each candidate route and distributes this plan to each sanitation vehicle for execution. This ensures that each sanitation vehicle completes its corresponding sanitation task along the route with the lowest carbon emissions, thereby achieving intelligent dispatching of sanitation vehicles towards the goal of optimal carbon footprint.

[0031] For ease of understanding, the method provided in this implementation is described in process below. Please refer to [link / reference]. Figure 2 This is a flowchart illustrating an AI-powered intelligent dispatching method for sanitation vehicles based on carbon footprint perception, as described in this application.

[0032] S101. Real-time collection of vehicle status information for each sanitation vehicle, including the vehicle's current location and real-time load data.

[0033] Sanitation vehicles refer to special-purpose vehicles that perform sanitation tasks within the target work area, including but not limited to water trucks, road sweepers, and garbage trucks.

[0034] Once the dispatch system is activated or a sanitation operation begins, it enters a continuous data acquisition state. In this state, the dispatch system establishes a communication connection with the onboard terminals installed on each sanitation vehicle, periodically receiving vehicle status information reported by each vehicle. For current location data acquisition, the dispatch system receives latitude and longitude coordinate data output from the GPS or BeiDou positioning modules in the onboard terminals and maps it onto an electronic map of the target work area, thereby determining the real-time location of each sanitation vehicle within the road network. For real-time load data acquisition, the dispatch system receives load values ​​read by the onboard terminals from load sensors mounted on the vehicles; these load sensors vary depending on the type of sanitation vehicle.

[0035] When the dispatch system identifies the target sanitation vehicle's vehicle type as a consumable sanitation vehicle, it establishes a communication connection with the vehicle's onboard terminal and reads the real-time liquid level data output by the liquid level sensor installed in the vehicle's water tank. Upon receiving the liquid level data, the dispatch system retrieves pre-stored geometric parameters of the vehicle's water tank (including the cross-sectional area and the full-load volume corresponding to the total height of the water tank) and the density parameters of the loaded liquid. It then converts the liquid level value into the current volume of liquid in the water tank and multiplies it by the liquid density to obtain the current liquid load capacity of the consumable sanitation vehicle.

[0036] When the dispatch system identifies the target sanitation vehicle's vehicle type label as a collection-type sanitation operation vehicle, it establishes a communication connection with the vehicle's onboard terminal and reads the real-time weight data output by the weighing sensor installed at the bottom of the vehicle compartment. The weighing sensor directly outputs the total weight of the solid materials carried inside the compartment by detecting changes in pressure on the compartment floor. After receiving this weight data, the dispatch system calibrates it using a preset calibration coefficient (to eliminate the influence of the compartment's own weight and sensor zero-point offset) and converts it into the current solid load capacity of the collection-type sanitation operation vehicle.

[0037] S102. Obtain the road network topology data of the target work area. The road network topology data includes the slope information of each road segment, real-time traffic congestion status and traffic light node density.

[0038] The target work area refers to the urban geographical area covered by the current sanitation operation, such as the area enclosed by a certain administrative district or several designated roads. Road network topology data refers to a set of data that digitally describes the structural characteristics and real-time operating status of the road network within the target work area.

[0039] After the dispatch system completes the collection of vehicle status information of each sanitation vehicle in step S101, or when it is executed in parallel with step S101, the dispatch system obtains the road network topology data of the target operation area.

[0040] For obtaining slope information, the scheduling system reads the elevation data of each road segment in the target operation area from the pre-stored high-precision electronic map database, calculates the longitudinal slope value of each road segment based on the elevation difference and horizontal distance between the start and end points of the road segment, and marks the slope aspect characteristics of each road segment as uphill or downhill. This slope information is relatively static data and can be updated according to a preset cycle.

[0041] To obtain real-time traffic congestion status, the dispatch system connects to the city traffic management platform or a third-party traffic data service system through a communication interface. It receives data such as traffic flow speed, vehicle density, or congestion index of each road segment within the target operation area in real time and converts it into corresponding congestion level labels. For example, when the average vehicle speed of a road segment is lower than a certain threshold, it is marked as a congested state.

[0042] To obtain the traffic light node density, the dispatching system extracts the coordinates and number of signal-controlled intersections in each road segment within the target operation area from the urban traffic signal management system or electronic map data. It then calculates the number of signal light nodes per unit length of each road segment as the traffic light node density value for that segment. The dispatching system associates these three types of data with the corresponding road segments in the road network topology model, forming a comprehensive road network description that includes terrain features, traffic conditions, and signal control information.

[0043] The execution of this step enables the dispatch system to fully grasp the key road condition factors affecting the energy consumption of sanitation vehicles, providing complete environmental data support for subsequent multi-dimensional carbon emission quantitative analysis of each candidate route, and ensuring that the carbon emission assessment can cover the two core impact dimensions of slope load effect and start-stop energy consumption effect.

[0044] S103. Based on the preset sanitation operation tasks, determine multiple candidate routes for each sanitation vehicle.

[0045] The preset sanitation operation tasks refer to the set of operation instructions pre-configured in the dispatch system, including but not limited to the operation type of each sanitation vehicle, the operation section or area to be covered, the start and end time of the operation, and the start and end points of the operation. Candidate routes refer to multiple feasible travel paths for each sanitation vehicle to start from its current location, complete the specified operation content, and reach the destination under the constraints of the sanitation operation tasks.

[0046] The dispatch system reads preset sanitation operation task information, which specifies the tasks that each sanitation vehicle needs to complete and the corresponding spatial constraints. The dispatch system uses the current location of each sanitation vehicle as the starting point of the path and the specified endpoint or the next necessary operation node in the task as the endpoint of the path. At the same time, the operation sections that need to be covered in the task are marked as necessary constraints of the path.

[0047] Under the aforementioned constraints, the dispatching system performs path search within the road network topology model, generating multiple candidate routes for each sanitation vehicle. These candidate routes all meet the coverage requirements of the operational tasks, but they differ in specific intermediate road sections, slope distribution of the routes, traffic congestion levels, and traffic light density. For example, for a particular garbage truck, the dispatching system might generate one candidate route that traverses many uphill sections but has fewer traffic lights, while simultaneously generating another candidate route with flat terrain but traversing more congested sections.

[0048] The execution of this step provides decision-making space for subsequent carbon emission assessment and comparison, enabling the scheduling system to select the option with the lowest carbon emissions from multiple routes that can complete the task, rather than passively determining a single route based solely on the shortest distance or the shortest time.

[0049] S104. Based on the vehicle status information and the road network topology data, determine the comprehensive carbon emission data for each candidate route;

[0050] Among them, the comprehensive carbon emission data refers to the carbon emission quantification result calculated by the dispatching system for each candidate route after comprehensively considering multiple factors such as vehicle dynamic load, road slope characteristics, traffic congestion status and traffic light node density. The result is expressed in a unified carbon emission equivalent unit to represent the estimated total carbon emission of each candidate route.

[0051] After the dispatch system determines multiple candidate routes for each sanitation vehicle through step S103, the dispatch system sequentially performs the following carbon emission quantification calculation process for each candidate route.

[0052] First, the dispatching system determines the initial carbon emissions for each candidate route. The system reads the total mileage of each candidate route and retrieves the basic energy consumption parameters per 100 kilometers for the target sanitation vehicles, as well as the carbon emission factor per unit energy consumption corresponding to that energy type, from the vehicle parameter database. The dispatching system multiplies the total mileage by the basic energy consumption parameters per 100 kilometers to obtain a baseline energy consumption value, and then multiplies it by the carbon emission factor to obtain the initial carbon emissions for each candidate route. This initial carbon emissions serve as a baseline reference value for subsequent adjustment calculations.

[0053] Secondly, the scheduling system extracts the slope segments from each candidate route. The system iterates through all segments traversed by each candidate route, reading the slope information obtained in step S102 for each segment. Segments with longitudinal slope values ​​exceeding a preset slope threshold (e.g., an absolute slope greater than 3%) are marked as slope segments, and the slope value, aspect characteristic (uphill or downhill), segment length, and sequential position within the candidate routes are recorded. Segments with longitudinal slope values ​​not exceeding the preset slope threshold are considered flat segments, and their slope impact is already included in the initial carbon emission calculation, requiring no additional adjustment.

[0054] Next, the dispatch system determines the expected load of the target sanitation vehicle when it enters each slope section based on real-time load data. Specifically, the dispatch system first determines the dynamic load change of the target sanitation vehicle within the most recent preset time period. The most recent preset time period refers to a fixed time interval counting backward from the current moment, such as the last 5 minutes or the last 10 minutes. The dispatch system retrieves the historical load data sequence of the target sanitation vehicle within the most recent preset time period from the database. This sequence consists of multiple timestamped load data points continuously recorded at fixed intervals in step S101. The dispatch system reads the load value of the earliest record and the load value of the latest record in this sequence, and calculates the difference between them to obtain the total load change value within this time period. Subsequently, the dispatch system divides this total load change value by the actual distance traveled by the target sanitation vehicle within the most recent preset time period (calculated by the cumulative distance of the vehicle's position trajectory within this time period) to obtain the load change rate per unit distance as the dynamic load change amount. For example, if a water truck's load capacity decreases from 4,500 kg to 4,000 kg in the last 10 minutes, and the vehicle actually travels 2.5 km during this period, the dispatch system calculates the dynamic load change as a decrease of 200 kg per km (i.e., -200 kg / km).

[0055] The dispatching system extracts the estimated working distance between the current location of the target sanitation vehicle and the sloping road segment. The system obtains the current location coordinates of the target sanitation vehicle from step S101 and locates the road segment and specific mileage marker of the current location in the segment sequence of the candidate route. Simultaneously, the system determines the mileage marker of the starting position of the target sloping road segment within the candidate route. The system subtracts the current location's mileage marker from the starting position's mileage marker to obtain the estimated working distance for the target sanitation vehicle to travel from its current location along the candidate route to the starting position of that sloping road segment. When there are multiple sloping road segments in the candidate route, the dispatching system calculates the estimated working distance from the current location to the starting position of each sloping road segment, forming a sequence of estimated working distances corresponding one-to-one with each sloping road segment. For example, if a candidate route contains three sloping road segments with starting positions 3 km, 7 km, and 12 km from the current location, the dispatching system obtains an estimated working distance sequence of 3 km, 7 km, and 12 km.

[0056] The dispatching system combines the real-time load data and dynamic load changes of the target sanitation vehicles to determine the expected load when the vehicles enter each slope section. Using the latest real-time load data collected in step S101 as the prediction baseline, the system multiplies the dynamic load change by the estimated working distance for the corresponding slope section to obtain the total expected load change from the current location to the starting point of that slope section. The system then adds the real-time load data to the total expected load change (this total is negative for consumable sanitation vehicles and positive for collection-type sanitation vehicles) to obtain the expected load when the target sanitation vehicle enters that slope section.

[0057] Subsequently, the dispatching system calculates the slope value, length, and expected load capacity of each gradient road segment by substituting them into a preset slope carbon emission adjustment model. Specific implementation details can be found in steps S201-S204, and will not be described in detail here.

[0058] Finally, the scheduling system superimposes the initial carbon emissions with the slope carbon emission adjustments for each gradient segment. The system accumulates the slope carbon emission adjustments for all gradient segments in each candidate route to obtain the total slope carbon emission adjustment for that candidate route. This total adjustment is then added to the initial carbon emissions to obtain the first carbon emissions for each candidate route. This first carbon emission has already taken into account the combined effects of terrain influence and dynamic vehicle load changes along the route's gradient segments, but it does not yet consider the energy consumption impact of traffic congestion and traffic light-induced start-stop cycles. In some embodiments, start-stop carbon emission adjustments can be further superimposed in subsequent steps to obtain the final comprehensive carbon emission data.

[0059] In some embodiments, after obtaining the first carbon emissions of each candidate route, the scheduling system continues to perform the following start-stop carbon emission quantification calculation process for each candidate route to complete the final determination of the comprehensive carbon emission data.

[0060] First, the dispatch system traverses all road segments traversed by each candidate route, evaluating the number of start-stop contributions due to traffic congestion and traffic light control for each segment. For the assessment of start-stop contributions caused by traffic congestion, the dispatch system reads the real-time traffic congestion status of each road segment, determines the number of start-stops per unit distance due to congestion based on a preset mapping relationship between congestion levels and start-stop frequencies, and then multiplies this by the length of the road segment to obtain the congestion start-stop contribution count for that segment. For example, if the real-time congestion level of a road segment is "slow," the corresponding number of start-stops per unit distance is 3. If the length of the road segment is 2 kilometers, then the congestion start-stop contribution count for that segment is 6. To assess the number of starts and stops caused by traffic light control, the dispatching system counts the total number of traffic light nodes passed through each candidate route and assigns a probability value for stopping at a red light to each traffic light node (this probability value can be calculated based on the signal timing scheme of each intersection or using a preset empirical probability value, such as 0.5). The expected number of starts and stops due to traffic light control for the candidate route is obtained by summing the probability values ​​of stopping at red lights for each traffic light node. The dispatching system then summarizes the number of starts and stops contributing to congestion on each road segment and adds it to the expected number of starts and stops at traffic lights to obtain the estimated start and stop frequency for the candidate route. For example, if a candidate route passes through 5 road segments with congestion start and stop contributions of 0, 6, 12, 3, and 0 times respectively, totaling 21 starts and stops; and passes through 8 traffic light nodes with a probability of stopping at a red light of 0.5 at each node, resulting in an expected number of starts and stops of 4; then the estimated start and stop frequency for this candidate route is 21 plus 4 equals 25.

[0061] Secondly, the dispatching system retrieves the single start-stop energy consumption parameters of the target sanitation vehicle under standard reference load conditions from the vehicle parameter database. This parameter represents the extra energy consumed by the vehicle to complete one acceleration from a standstill to normal driving speed under standard reference load conditions (compared to the extra energy consumed during constant speed driving). The dispatching system multiplies the single start-stop energy consumption parameter by the estimated start-stop frequency to obtain the total extra energy consumption under start-stop conditions, and then multiplies it by the carbon emission factor of the corresponding energy type to obtain the standard carbon emissions of the candidate route.

[0062] The dispatch system then recognizes that the actual energy consumption of each vehicle start-stop event is closely related to the vehicle's actual load at that moment; the greater the load, the greater the kinetic energy required to accelerate from a standstill, and thus the higher the energy consumption. Since the load of the target sanitation vehicle continuously changes dynamically as it travels along the candidate route, the actual load at the moment of each start-stop event deviates to varying degrees from the standard reference load. Therefore, it is necessary to calculate the start-stop carbon emission adjustment based on the vehicle type to correct the standard carbon emission level.

[0063] For sanitation vehicles of two distinct types—consumption-type and collection-type—with diametrically opposed load variation patterns, the start-stop carbon emission correction value is calculated sequentially for each estimated start-stop action along the candidate route under the corresponding actual load conditions. All correction values ​​are then accumulated and summed to obtain the start-stop carbon emission adjustment amount that accurately reflects the impact of vehicle dynamic load on start-stop energy consumption. Specifically, the dispatching system first reads the vehicle type identifier of the target sanitation vehicle determined in the previous steps, and then proceeds to the corresponding calculation branch.

[0064] The processing flow for consumable sanitation vehicles is as follows: The dispatch system reads the current real-time load data of the target sanitation vehicle as the starting load and reads the dynamic load change of the vehicle in the most recent preset time period (i.e., the load reduction rate corresponding to the unit operation process). Based on the estimated start-stop frequency N, the dispatch system divides the total travel distance of the candidate route into segments according to the estimated start-stop frequency evenly or according to the road segment distribution, and determines the estimated occurrence position of each start-stop action in the travel distance of the candidate route; for the i-th start-stop action, the dispatch system combines the estimated operation process corresponding to the target sanitation vehicle traveling from the current position to the start-stop occurrence position, uses the current real-time load as the benchmark, and performs linear extrapolation based on the dynamic load change to calculate the first estimated load Wi¹ of the target sanitation vehicle at the i-th start-stop time; since the load of consumable vehicles continuously decreases with operation, as i increases, W1¹>W2¹>…>WN¹, and each first estimated load constitutes a monotonically decreasing sequence. Subsequently, for each start-stop action, the dispatching system multiplies the corresponding first estimated load weight Wi¹ by the preset start-stop inertial drag coefficient k to calculate the first start-stop carbon emission correction value Ci¹ for that action, i.e., Ci¹ = Wi¹ × k. Each first start-stop carbon emission correction value decreases monotonically as the load weight decreases. Finally, the dispatching system accumulates all N first start-stop carbon emission correction values, i.e., calculates ∑Ci¹ (i = 1 to N), to obtain the start-stop carbon emission adjustment amount for consumable sanitation vehicles on the candidate route.

[0065] The processing procedure for collection-type sanitation operation vehicles is as follows: The dispatching system also reads the current real-time load weight data of the target sanitation vehicle as the initial load weight, and reads the dynamic load variation of the vehicle within the latest preset time period (i.e., the load increase rate corresponding to each unit operation process). Based on the estimated start-stop frequency N, the dispatching system uses the same segmentation method as that for consumption-type vehicles to determine the estimated occurrence position of each start-stop action. For the i-th start-stop action, the dispatching system combines the estimated operation process amount corresponding to the target sanitation vehicle traveling from the current position to the occurrence position of this start-stop action, performs linear extrapolation based on the current real-time load weight and according to the dynamic load variation, and calculates the second estimated load weight Wi² of the target sanitation vehicle at the i-th start-stop moment. Since the load weight of the collection-type vehicle continues to increase with the operation, as i increases, W1²<W2²<…<WN², and all the second estimated load weights form a monotonically increasing sequence. Subsequently, for each start-stop action, the dispatching system multiplies the corresponding second estimated load weight Wi² by the same preset start-stop inertial resistance coefficient k to calculate the second start-stop carbon emission correction value Ci² corresponding to this start-stop action, that is, Ci²=Wi²×k. Each second start-stop carbon emission correction value increases monotonically with the increase of the load weight, which means that the inertial energy consumption carbon emission generated by each start-stop of the collection-type vehicle in the fully loaded state in the later stage of the operation is significantly higher than that in the light-load state in the initial stage of the operation, and dispatching it to sections with dense traffic lights or congestion will cause a greater carbon emission cost. Finally, the dispatching system accumulates and sums all N second start-stop carbon emission correction values, that is, calculates ∑Ci² (i=1 to N), to obtain the start-stop carbon emission adjustment amount of the collection-type sanitation operation vehicle on the candidate route.

[0066] Next, the dispatching system adds the calculated start-stop carbon emission adjustment amount (positive or negative) to the standard carbon emission amount to obtain the second carbon emission amount of the candidate route. The second carbon emission amount represents the actual total carbon emission generated by start-stop events during the whole journey of the target sanitation vehicle traveling along the candidate route, and has accurately incorporated the influence of the dynamic load variation of the vehicle on the start-stop energy consumption.

[0067] The dispatching system adds the first carbon emission amount of each candidate route (which already includes the reference driving emission and the ramp carbon emission adjustment amount) to the corresponding second carbon emission amount calculated in this step (which already includes the start-stop standard carbon emission and the start-stop carbon emission adjustment amount), to obtain the final comprehensive carbon emission data of each candidate route. This comprehensive carbon emission data comprehensively covers the carbon emission contributions from three dimensions: reference driving emission, ramp terrain load effect and start-stop working condition energy consumption effect, and each dimension accurately incorporates the dynamic load variation characteristics of the target sanitation vehicle, forming a complete evaluation result of the carbon emission level of each candidate route.

[0068] S105. Generate a dispatching scheme based on the comprehensive carbon emission data and issue it to each sanitation vehicle for execution.

[0069] After the dispatch system completes the comprehensive carbon emission data calculation for each candidate route in step S104, it enters the dispatch decision-making stage. For each sanitation vehicle, the dispatch system sorts its multiple candidate routes according to their comprehensive carbon emission data from low to high, selecting the candidate route with the lowest comprehensive carbon emission data as the optimal execution route for that sanitation vehicle. At the global level, when there are segment conflicts or resource competition among the candidate routes of multiple sanitation vehicles, the dispatch system further performs global coordination and optimization. Under the premise of ensuring that all vehicles can complete their tasks, the system uses minimizing the total comprehensive carbon emission data of the entire fleet as the optimization objective to determine the final dispatch plan. After the dispatch plan is determined, the dispatch system encapsulates the execution route, work node sequence, and navigation guidance information corresponding to each sanitation vehicle into a standard format dispatch instruction, which is then sent to the onboard terminal of each sanitation vehicle via a 4G / 5G wireless communication network. After receiving the dispatch instruction, the onboard terminal displays the navigation route on the onboard display screen for the driver to follow, or transmits the route instructions to the vehicle's automatic driving control module for automatic execution. The execution of this step enables the carbon emission optimization calculation results of the dispatching system to be directly transformed into the actual operating behavior of each sanitation vehicle, realizing a complete closed loop from carbon footprint perception and quantitative assessment to low-carbon path execution. This ensures that the sanitation vehicle fleet always operates on the carbon emission-optimal path during actual operations, minimizing the overall carbon footprint of sanitation operations.

[0070] In the above embodiment, by collecting the current location and real-time load data of each sanitation vehicle in real time, and obtaining the slope information, real-time traffic congestion status and traffic light node density of each road segment in the target operation area, and by determining the comprehensive carbon emission data of each candidate route based on the collaborative analysis of the dynamic load change characteristics of vehicles and the multi-dimensional environmental factors of the road network, it is possible to accurately quantify the actual carbon emission differences of different routes under the slope load effect and start-stop working condition energy consumption effect. This effectively solves the problem that traditional sanitation vehicle dispatching only relies on mileage or time for route planning and ignores the impact of terrain features, traffic dynamics and vehicle load changes on carbon emissions, resulting in inaccurate carbon emission assessment of the dispatching scheme. Thus, intelligent dispatching of sanitation vehicles aimed at the optimal carbon emission target is realized.

[0071] In some embodiments, in the process of determining the comprehensive carbon emission data of each candidate route based on the vehicle status information and the road network topology data, it may be necessary to conduct a quantitative analysis of the carbon emission impact of the slope sections traversed by each candidate route. Since the slope characteristics of different slope sections are different, uphill sections require vehicles to overcome additional climbing resistance, thereby increasing carbon emissions, while downhill sections allow vehicles to convert gravitational potential energy into kinetic energy, thereby reducing carbon emissions. Both of these effects are closely related to the expected load of the vehicle when driving on the slope section. In this case, the following steps can be performed, specifically including S201 to S204.

[0072] In light of the above scenarios, the method provided in this implementation will now be described in more detail. Please refer to [link / reference]. Figure 3 This is another flowchart illustrating the AI-powered intelligent dispatching method for sanitation vehicles based on carbon footprint perception, as described in this application.

[0073] S201. Extract the slope aspect characteristics of each road segment with this slope, including uphill and downhill road segments;

[0074] Among them, the slope aspect characteristic refers to the slope orientation attribute of each slope section along the actual driving direction of the target sanitation vehicle, which is used to distinguish whether the vehicle is moving uphill or downhill when driving on the slope section.

[0075] The dispatch system traverses all slope segments along each candidate route. For each slope segment, it reads the starting and ending elevations recorded in the road network topology data and determines the slope aspect based on the actual travel direction of the target sanitation vehicle along the candidate route. When the ending elevation is higher than the starting elevation as the vehicle travels along the route, the dispatch system marks the slope segment as uphill; when the ending elevation is lower than the starting elevation, it marks it as downhill. After extracting the slope aspect features of all slope segments, the dispatch system provides a classification basis for subsequently calculating the carbon emission increase of uphill segments and the carbon emission reduction of downhill segments.

[0076] S202. When the slope section is an uphill section, the carbon emission increase is calculated based on the expected load, the uphill slope value and the preset climbing resistance coefficient. The carbon emission increase is positively correlated with the expected load.

[0077] The uphill gradient value refers to the slope of an uphill section along the driving direction. It is provided by the slope information of each road segment in the road network topology data and is usually expressed as a percentage gradient or angle. A larger uphill gradient value indicates a steeper road surface inclination, and a greater component of gravity that the vehicle needs to overcome. The climbing resistance coefficient is a pre-calibrated constant parameter that correlates the vehicle's total mass, gradient value, and additional climbing energy consumption. This coefficient comprehensively reflects the energy conversion efficiency of the vehicle's power system when overcoming the gravity component of the slope and the corresponding carbon emission conversion relationship. The increase in carbon emissions refers to the additional carbon emissions generated by a target sanitation vehicle while overcoming climbing resistance on a specific uphill section, compared to emissions from a flat road surface.

[0078] When the dispatch system determines that a certain slope section is uphill, it obtains the expected load capacity of the target sanitation vehicle traveling on that uphill section and reads the uphill gradient value from the road network topology data. The dispatch system adds the expected load capacity to the vehicle's tare weight to obtain the total vehicle mass, then multiplies the total vehicle mass, the uphill gradient value, and the climbing resistance coefficient, and finally multiplies by the length of the uphill section to obtain the carbon emission increase for that uphill section. Since the expected load capacity directly participates in the calculation of the total vehicle mass and the carbon emission increase is proportional to the total vehicle mass, the carbon emission increase is positively correlated with the expected load capacity.

[0079] For consumable sanitation vehicles, if the uphill section is located in the latter half of the candidate route, the expected load capacity is lower due to material consumption, and the corresponding increase in carbon emissions is relatively small. For collection-type sanitation vehicles, if the uphill section is located in the latter half of the candidate route, the expected load capacity is higher due to material collection, and the corresponding increase in carbon emissions is relatively large.

[0080] S203. When the slope section is a downhill section, the carbon emission reduction is calculated based on the expected load capacity, downhill slope value and preset potential energy conversion coefficient. The carbon emission reduction is positively correlated with the expected load capacity.

[0081] The potential energy conversion coefficient is a pre-calibrated constant parameter that correlates the vehicle's total mass, gradient, and downhill potential energy savings. This coefficient comprehensively reflects the effective utilization ratio of gravitational potential energy to kinetic energy during downhill driving and the corresponding carbon emission savings. The potential energy conversion coefficient is typically smaller than the climbing resistance coefficient because the utilization efficiency of gravitational potential energy during downhill driving is constrained by factors such as braking energy loss and transmission system efficiency, preventing complete conversion into effective driving savings. Carbon emission reduction refers to the reduction in carbon emissions of a target sanitation vehicle compared to a flat road surface due to the assistance of gravitational potential energy during a downhill journey; this value is positive.

[0082] Similarly, when the dispatch system determines that a certain slope section is a downhill section, it also obtains the expected load capacity of the target sanitation vehicle traveling on that downhill section and reads the downhill slope value from the road network topology data. The dispatch system adds the expected load capacity to the vehicle's tare weight to obtain the vehicle's total mass, then multiplies the total mass, the downhill slope value, and the potential energy conversion coefficient, and then multiplies by the length of the downhill section to obtain the carbon emission reduction for that downhill section. Since the expected load capacity directly participates in the calculation of the vehicle's total mass and the carbon emission reduction is proportional to the vehicle's total mass, the carbon emission reduction is positively correlated with the expected load capacity.

[0083] For consumable sanitation vehicles, if the downhill section is located in the first half of the candidate route, the expected load capacity is higher because the materials have not yet been consumed in large quantities, and the corresponding carbon emission reduction is relatively large, which is conducive to making full use of the downhill potential energy to save energy. For collection-type sanitation vehicles, if the downhill section is located in the first half of the candidate route, the expected load capacity is lower because the materials have not yet been collected in large quantities, and the corresponding carbon emission reduction is relatively small.

[0084] S204. Calculate the increase and decrease of carbon emissions for each slope section in each candidate route to obtain the carbon emission adjustment amount for that slope.

[0085] For each candidate route, the scheduling system sums up the carbon emission increases calculated in step S202 for all uphill sections to obtain the total carbon emission increase, and sums up the carbon emission reductions calculated in step S203 for all downhill sections to obtain the total carbon emission reduction. Then, the total carbon emission increase is subtracted from the total carbon emission reduction to obtain the slope carbon emission adjustment for that candidate route. A positive slope carbon emission adjustment indicates that the carbon emission increase effect of the uphill sections is greater than the carbon emission reduction effect of the downhill sections, and the overall slope topography contributes to the increase in carbon emissions for that route. A negative slope carbon emission adjustment indicates that the carbon emission reduction effect of the downhill sections is greater than the carbon emission increase effect of the uphill sections, and the overall slope topography contributes to the reduction in carbon emissions for that route. The scheduling system uses the slope carbon emission adjustment for each candidate route in subsequent steps to superimpose it with the baseline carbon emission amount to obtain the first carbon emission amount for each candidate route.

[0086] In this embodiment, the positive increase effect and negative reduction effect of different slope sections on carbon emissions under dynamic vehicle load conditions can be accurately quantified. This effectively solves the problem that the traditional scheduling method uniformly estimates the carbon emission impact of slope sections without distinguishing the differences in slope and the coupling effect of load, resulting in a large deviation in the assessment of slope carbon emissions. This achieves a refined quantitative assessment of slope carbon emissions based on slope classification and load correlation.

[0087] The scheduling system in this application embodiment is described below from a hardware processing perspective. Please refer to [link / reference]. Figure 4 This is a schematic diagram of the physical device structure of the scheduling system in an embodiment of this application.

[0088] It should be noted that, Figure 4 The structure of the scheduling system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0089] like Figure 4As shown, the scheduling system includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 402 or programs loaded from storage section 408 into Random Access Memory (RAM) 403, such as performing the methods described in the above embodiments. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0090] The following components are connected to I / O interface 405: input section 406 including audio input devices, push-button switches, etc.; output section 407 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 408 including a hard disk, etc.; and communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 409 performs communication processing via a network such as the Internet. Drive 410 is also connected to I / O interface 405 as needed. Removable media 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 410 as needed so that computer programs read from them can be installed into storage section 408 as needed.

[0091] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs the various functions defined in this application.

[0092] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0093] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0094] Specifically, the scheduling system in this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the AI-based intelligent scheduling method for sanitation vehicles based on carbon footprint perception provided in the above embodiment.

[0095] In another aspect, this application also provides a computer-readable storage medium, which may be included in the scheduling system described in the above embodiments; or it may exist independently and not assembled into the scheduling system. The storage medium carries one or more computer programs, which, when executed by a processor of the scheduling system, enable the scheduling system to implement the AI-based intelligent scheduling method for sanitation vehicles based on carbon footprint perception provided in the above embodiments.

[0096] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0097] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0098] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for intelligent scheduling of sanitation vehicles based on carbon footprint perception, characterized in that, The method includes: Real-time collection of vehicle status information for each sanitation vehicle, including the current location and real-time load data of the sanitation vehicle. Obtain road network topology data for the target work area, including slope information of each road segment, real-time traffic congestion status, and traffic light node density; Based on the preset sanitation operation tasks, multiple candidate routes are determined for each sanitation vehicle. Based on the vehicle status information and the road network topology data, the comprehensive carbon emission data of each candidate route is determined; A scheduling scheme is generated based on the comprehensive carbon emission data and issued to each sanitation vehicle for execution.

2. The method according to claim 1, characterized in that, The steps for real-time collection of vehicle status information for each sanitation vehicle include: For consumable sanitation vehicles, the liquid level sensor data of the vehicle's water tank is read and converted into the vehicle's current liquid load in real time. For collection-type sanitation vehicles, the weighing sensors at the bottom of the vehicle compartment are read and converted into the vehicle's current solid load capacity in real time.

3. The method according to claim 1, characterized in that, The step of determining the comprehensive carbon emission data of each candidate route based on the vehicle status information and the road network topology data specifically includes: Determine the initial carbon emissions for each of the candidate routes; Extract the slope segments from each of the candidate routes; Based on the real-time load data, the expected load of the target sanitation vehicle when it enters the sloping road section is determined. The slope carbon emission adjustment amount for each of the slope sections is determined based on the vehicle type of the target sanitation vehicles. The vehicle types include consumable sanitation vehicles and collection sanitation vehicles. The initial carbon emissions are added together with the ramp carbon emission adjustment to obtain the first carbon emissions.

4. The method according to claim 1, characterized in that, The step of determining the comprehensive carbon emission data of each candidate route based on the vehicle status information and the road network topology data specifically includes: The estimated start-stop frequency of the target sanitation vehicle is determined by combining the real-time traffic congestion status and the density of traffic light nodes. Based on the estimated start-stop frequency, the standard carbon emissions of the target sanitation vehicle when passing through traffic light nodes and congested road sections are determined; The corresponding start-stop carbon emission adjustment amount is determined based on the vehicle type of the target sanitation vehicle and the estimated start-stop frequency. The standard carbon emissions are added together with the start-stop carbon emission adjustment to obtain the second carbon emissions. The first carbon emission figure is superimposed with the second carbon emission figure to obtain the comprehensive carbon emission data.

5. The method according to claim 3, characterized in that, The step of determining the expected load of the target sanitation vehicle when entering the sloping road section based on the real-time load data specifically includes: Determine the dynamic load change of the target sanitation vehicle within the most recent preset time period; Extract the estimated working distance between the current location of the target sanitation vehicle and the slope section; By combining the real-time load data and dynamic load change of the target sanitation vehicle, the expected load when the target sanitation vehicle enters the sloping road section is determined.

6. The method according to claim 3, characterized in that, The step of determining the slope carbon emission adjustment amount for each of the slope sections based on the vehicle type of the target sanitation vehicles specifically includes: Extract the slope aspect features of each of the aforementioned slope sections, the slope aspect features including uphill sections and downhill sections; When the slope section is an uphill section, the increase in carbon emissions is calculated based on the expected load capacity, the uphill slope value, and the preset climbing resistance coefficient. The increase in carbon emissions is positively correlated with the expected load capacity. When the slope section is a downhill section, the carbon emission reduction is calculated based on the expected load capacity, the downhill slope value and the preset potential energy conversion coefficient. The carbon emission reduction is positively correlated with the expected load capacity. The carbon emission increase and carbon emission reduction of each slope segment in each candidate route are statistically analyzed to obtain the slope carbon emission adjustment amount.

7. The method according to claim 4, characterized in that, The step of determining the corresponding start-stop carbon emission adjustment based on the vehicle type of the target sanitation vehicle and the estimated start-stop frequency specifically includes: When the target sanitation vehicle is a consumable sanitation operation vehicle, based on the estimated start-stop frequency, a number of first estimated load capacities are determined when the target sanitation vehicle starts and stops. The first start-stop carbon emission correction value is calculated based on each of the first estimated load capacities and the preset start-stop inertial drag coefficients; The start-stop carbon emission adjustment amount is obtained by summing up the first start-stop carbon emission correction values; When the target sanitation vehicle is the collection-type sanitation operation vehicle, based on the estimated start-stop frequency, a number of second estimated load capacities are determined when the target sanitation vehicle starts and stops. The corresponding second start-stop carbon emission correction value is calculated based on each of the second estimated load capacities and the start-stop inertial drag coefficients; The start-stop carbon emission adjustment amount is obtained by summing up the second start-stop carbon emission correction values.

8. A scheduling system, characterized in that, The scheduling 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 including computer instructions, and the one or more processors call the computer instructions to cause the scheduling system to perform the method as 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 scheduling system, it causes the scheduling system to perform the method as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is run on the scheduling system, it causes the scheduling system to perform the method as described in any one of claims 1-7.

Images