Digital twin drive solid waste real-time matching optimization method and system

Abstract

The invention relates to the technical field of digital twinning, in particular to a digital twinning drive solid waste real-time matching optimization method and system. The method comprises the following steps: obtaining building solid waste source end data, and carrying out solid waste source end twinning modeling according to the building solid waste source end data to obtain a digital twinning source end model; obtaining building solid waste receiving end data, and carrying out receiving point twinborn modeling according to the building solid waste receiving end data to obtain a digital twinborn receiving end model; performing matching according to the digital twin source end model and the digital twin receiving end model to obtain a solid waste matching model; and performing task splitting fusion scheduling according to the solid waste matching model to obtain solid waste scheduling data. According to the method, the digital twinborn model of the building solid waste source end and the building solid waste receiving end is constructed, fine modeling and dynamic mapping of solid waste attributes, processing capacity and pollution loads are achieved, the environment diffusion risk in the transportation process is effectively reduced, and the feasibility of task splitting and fusion and the resource bearing efficiency are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a digital twin-driven solid waste real-time matching optimization method and system. Background Art

[0002] Digital twins are a technical approach that leverages multi-source data from physical entities (such as equipment, systems, and buildings) to construct dynamic, real-time mapping models of them in virtual space, enabling perception, simulation, prediction, and control of the entity's state. The core of this approach lies in enabling bidirectional interaction and synchronous updates between physical and virtual models by integrating physical models, sensor data, historical behavior, and operational logic. Currently, the resource transfer and treatment of construction solid waste often relies on coarse-grained matching between sources and receivers based on manual experience, lacking systematic modeling and precise coordination of factors such as pollutant type, receiving capacity, and transportation route risks. This approach not only leads to low solid waste transportation efficiency and high pollution transfer risks, but also easily causes congestion and compliance overload at receiving points during peak hours. While some systems incorporate static rules or geographic routing technologies, these systems struggle to implement real-time updates and integrated decision-making with dynamic, multi-source data. The challenge is how to integrate digital twin technology with the resource transfer and treatment of construction solid waste. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes a digital twin-driven solid waste real-time matching optimization method and system to solve at least one of the above technical problems.

[0004] This application provides a digital twin-driven real-time matching optimization method for solid waste, the method comprising: S1. Obtain construction solid waste source data, and perform solid waste source twin modeling based on the construction solid waste source data to obtain a digital twin source model; S2. Obtain the construction solid waste receiving end data, and perform receiving point twin modeling based on the construction solid waste receiving end data to obtain a digital twin receiving end model; S3. Match the digital twin source model and the digital twin receiving model to obtain a solid waste matching model; S4. Perform task splitting and fusion scheduling based on the solid waste matching model to obtain solid waste scheduling data.

[0005] The present invention achieves high-precision and dynamic modeling of the construction solid waste generating and receiving ends by introducing digital twin modeling methods, which not only improves the information symmetry between the source and receiving ends in the time and space dimensions, but also provides an accurate data basis for matching and scheduling. Combined with multi-model collaborative matching, adaptation is performed according to factors such as solid waste characteristics, receiving capacity, and pollution restrictions to avoid resource waste and path conflict problems in traditional static scheduling schemes. At the scheduling level, the task splitting and fusion strategy is adopted to effectively improve the transport load efficiency ratio and path loadability, reduce transportation costs, and enhance the dynamic control capabilities of multi-source heterogeneous solid waste flows. It is suitable for large-scale intelligent distribution sites for construction solid waste.

[0006] Optionally, S1 includes: Collect basic data on sources of construction solid waste to obtain basic data on solid waste sources; Standardize the attributes based on the basic data of solid waste sources to obtain the source data of construction solid waste; Construct digital twin objects based on construction solid waste source data to obtain digital twin data of solid waste source; The scheduling accessibility evolution simulation is performed based on the digital twin data of the solid waste source to obtain the digital twin source model.

[0007] In this invention, by conducting structured collection and attribute standardization of construction solid waste generation sources, a source-end data system with a unified format and semantic labels is constructed, solving the problems of heterogeneous, dispersed, and lacking spatiotemporal consistency in solid waste data. Through the construction of digital twin objects, the system can reproduce the generation status, storage characteristics, and emission rhythm of source-end solid waste in real time in a virtual environment, providing an interactive digital mapping body for simulation scheduling. Through the simulation of the evolution of scheduling reachability, the source-end model not only reflects the current status, but also has the dynamic prediction function of the scheduling response capability after the task is triggered, which helps to improve the rationality of path planning and resource organization efficiency of solid waste matching.

[0008] Optionally, S2 includes: Acquire construction solid waste receiving end data, and extract solid waste treatment features based on the construction solid waste receiving end data to obtain solid waste treatment feature data; Extract pollutant limits based on construction solid waste receiving end data to obtain pollutant limit data; Construct digital twin objects based on the data of the construction solid waste receiving end to obtain the digital twin data of the solid waste receiving end; The digital twin data of the solid waste receiving end is run and evolved according to the solid waste treatment characteristic data and pollutant limit data to obtain the digital twin receiving end model.

[0009] In this invention, through the systematic collection and in-depth mining of construction solid waste receiving end data, the processing capacity, response characteristics and pollutant constraints of the receiving point are accurately extracted, thereby constructing a multi-dimensional and quantifiable receiving feature characterization system. Through the construction of digital twin objects, the static receiving capacity is transformed into a digital entity that can evolve dynamically, realizing the fitting and prediction of the actual processing process. The operation evolution modeling based on solid waste treatment characteristics and pollutant restriction data not only improves the response expression ability of the receiving end model to task load fluctuations, pollution impacts and resource occupation, but also provides a simulation foundation with environmental constraint perception capabilities for pollution adaptation, load assessment and scheduling coordination in solid waste matching.

[0010] Optionally, S3 includes: Perform cross-batch collaborative matching based on the digital twin source model and the digital twin receiving model to obtain the first solid waste matching model; Matching the polluted building solid waste is performed based on the digital twin source model and the digital twin receiving model to obtain a second solid waste matching model; Path risk avoidance control is performed according to the first solid waste matching model and the second solid waste matching model to obtain a solid waste matching model.

[0011] In this invention, a multi-granularity solid waste matching mechanism is constructed based on the digital twin model of the source and receiving ends, which can realize cross-batch resource coordination and dynamic allocation, effectively improving the integrated utilization rate of construction solid waste in multi-source and multi-stream scenarios. By modeling the exclusive matching path of contaminated construction solid waste, introducing pollutant migration simulation and load limit constraints, the system has the processing adaptability under high pollution load scenarios, ensuring that the matching results meet environmental protection standards and processing capacity boundaries. Through path risk avoidance control, combined with dynamic adjustment of multi-dimensional constraints such as construction interference, route congestion, and pollution diffusion in the scheduling network, the safety of the solid waste transportation process and the reliability of path planning are improved.

[0012] Optionally, the cross-batch collaborative matching includes: Extract collaborative entities based on the digital twin source model and the digital twin receiver model to obtain collaborative entity data; Perform reachable entity division and splittable entity division based on collaborative entity data to obtain reachable entity data and splittable entity data respectively; According to the digital twin receiving end model, a collaborative batch path diagram is generated for the reachable entity data and the splittable entity data to obtain the first solid waste matching model.

[0013] The present invention introduces collaborative entity extraction to break the traditional static division boundaries between batches, and realizes the coupled modeling of the source and receiving ends in the dimensions of spatial accessibility and task structure divisibility. By dividing collaborative entities into reachable entities and divisible entities, the system can flexibly deal with the problems of task granularity differences and uneven batch sizes while ensuring the physical accessibility of the transportation path, significantly improving the flexibility and adaptability of the solid waste scheduling process. Combined with the receiving end model to generate a collaborative batch path graph, a structured graph covering multiple batches and multiple task paths is formed, which not only optimizes the utilization of transportation path resources, but also improves the reconstruction capability of the overall scheduling system under conditions of multi-source redundancy, critical load and supply and demand mismatch.

[0014] Optionally, the reachability entity division includes: Performing hierarchical road network path processing based on collaborative entity data and preset electronic map data to obtain hierarchical road network path data; Constructing a multi-level road network graph based on the hierarchical road network path data to obtain multi-level road network graph data; Process the multi-level road network data with source group requirements to obtain path layer data; Perform fusion path traffic reachability extraction on the path stacking data to obtain fusion path traffic data; Perform convolution processing on the fused path traffic data to obtain the peak window data that can be combined; According to the digital twin receiving end model, the multi-entry path assignment conflict of the peak window data that can be spliced ​​is carried out to obtain the reachability entity data.

[0015] The present invention introduces a hierarchical road network and a multi-level graph modeling mechanism to achieve a fine-grained analysis of the transportation routes of construction solid waste, fully considering the hierarchical differences of various traffic network structures such as main roads, branch roads and temporary construction channels. The processing of the demand for the combined source group enables the system to identify task groups that can be collaboratively loaded in the early stage of scheduling, and to construct a composite path structure covering multiple task requirements in combination with the path overlay data. By fusing the traffic accessibility extraction and convolution operations of the path, time windows with high carrying potential in dynamic traffic flows are identified, thereby effectively supporting the temporal organization and capacity aggregation of scheduling resources. The multi-entry path assignment conflict analysis is carried out based on the digital twin receiving end model, fully considering the traffic bottlenecks and task interference problems under the multi-path access conditions of the receiving end, ensuring that the selected path plan has the executable and resource coordination capabilities during peak hours, and improving the load efficiency and road adaptability of the solid waste transportation plan.

[0016] Optionally, the contaminated construction solid waste matching includes: Extract pollutant load characteristics based on the digital twin source model and the digital twin receiving model to obtain pollutant load characteristic data; Performing receiving-end pollution load processing according to pollutant load characteristic data to obtain receiving-end pollution load data; Perform pollution migration simulation on the digital twin source model and the digital twin receiving model based on the pollution carrying data of the receiving end to obtain pollution migration data; According to the pollution migration data, the digital twin source model and the digital twin receiving model are marked with pollution solid waste matching to obtain a second solid waste matching model; The pollutant load feature extraction includes: Extract pollutant data based on the digital twin source model to obtain pollutant data; Extract interaction paths based on the digital twin source model and the digital twin receiver model to obtain interaction path data; Perform pollution potential attenuation processing on the interactive path data according to the pollutant data to obtain the pollutant path data; Perform multi-step particle migration deduction on pollutant path data and preset electronic map data to obtain multi-step particle migration data; Based on the multi-step particle migration data, the path overlap diffusion enhancement is performed to obtain the pollution exposure map data; Based on the pollution exposure map data, the digital twin receiving end model is simulated for pollution migration field-receiving end load to obtain pollutant load characteristic data.

[0017] In this invention, a multi-stage modeling mechanism for dynamic matching of pollutant load assessment and carrying capacity is established to address the transmission and reception risks of highly polluting construction solid waste. Through the extraction of pollutant load characteristics, not only the diffusion trend of source pollutants in the space-time dimension is quantified, but also the exposure risk distribution of the interactive path is combined to provide data support for pollution path identification and control. Based on the pollution load processing at the receiving end, the system can dynamically adjust the processing strategy of the receiving unit, accurately identify the critical point of pollution load, and avoid the risk of secondary pollution caused by overload reception. Through pollution migration simulation, a co-evolutionary map of the pollution diffusion field and the carrying field is constructed to achieve forward-looking simulation of pollution links and identification of avoidance paths.

[0018] By constructing a dynamic migration mechanism for pollutants in complex transportation networks, quantitative analysis of the source-end pollutant transmission potential and path perception are achieved. By combining the interactive path data extracted from the digital twin source model and the receiving-end model, a full-cycle perspective of the pollution transmission link is constructed; through pollution potential attenuation processing, the diffusion rate and attenuation trend of pollutants during transmission are effectively portrayed, avoiding static factors from underestimating the actual exposure risk. Through multi-step particle migration deduction, the pollutant path data and map data are integrated, and the multi-step migration process is simulated from a particle dynamic perspective, significantly improving the perception of spatial diffusion and path tortuosity. The path overlapping diffusion enhancement strategy performs exposure superposition modeling for the intersection of multiple source paths to generate more realistic pollution exposure map data. Through the pollution migration field-receiving-end load simulation, the dynamic coupling modeling from pollution source diffusion, propagation path to receiving capacity is completed.

[0019] Optionally, the path risk avoidance control includes: Performing path risk extraction on the first solid waste matching model and the second solid waste matching model to obtain first path risk data and second path risk data respectively; constructing a path risk map based on the first path risk data and the second path risk data to obtain path risk map data; The path risk map data is processed to avoid the occurrence of solid waste matching models.

[0020] The present invention effectively improves the risk identification granularity and dynamic avoidance capabilities in the solid waste scheduling process by introducing dual-source extraction of path risks and graph structure modeling. By extracting path risk information from the first solid waste matching model and the second solid waste matching model respectively, the system can form a full-dimensional risk perception map under the background of superposition of conventional transportation constraints and high-pollution paths. The path risk map construction link comprehensively considers multiple risk factors such as geographically sensitive areas, traffic bottlenecks, pollution transmission channels, and overloaded nodes at the receiving end to achieve a structured expression of the spatiotemporal evolution of transportation paths. Path avoidance processing not only supports path reconstruction based on weight adjustment, but also performs dynamic path replacement and risk transfer strategy optimization in combination with real-time scheduling status, thereby ensuring that the final matching model achieves a balance between safety, ecology, and timeliness.

[0021] Optionally, S4 includes: Extract task scheduling units based on the solid waste matching model to obtain task scheduling unit data; Perform task splitting criterion on task scheduling unit data to obtain task splitting data; Perform risk reorganization on the task splitting data to obtain task reorganization data; The task reorganization data is screened for fusion feasibility to obtain solid waste scheduling data.

[0022] The present invention realizes the refined disassembly and reconstruction of solid waste transportation tasks by constructing a multi-stage task scheduling mechanism oriented to the matching model. Based on the solid waste matching model, the task scheduling unit data is extracted, so that the scheduling granularity is changed from batch to controllable unit, which enhances the system's adaptability to actual scenarios such as complex construction sites and distributed receiving points. The introduction of task splitting criteria enables the system to dynamically divide tasks according to multiple conditions such as transportation capacity, pollution level, time constraints, etc., thereby improving resource utilization and reducing the risk of single-path conflicts. The risk reorganization stage is based on intelligent merging of path exposure, load threshold and historical scheduling feedback to ensure that the reorganized tasks have controllable risk thresholds and executability. The fusion feasibility screening finally combines the current road conditions, platform scheduling load and collaborative needs to perform constraint verification on the reorganized tasks to ensure that the output scheduling plan achieves an optimal balance between transportation efficiency, safety and ecological constraints.

[0023] Optionally, the present application further provides a digital twin-driven solid waste real-time matching optimization system for executing the digital twin-driven solid waste real-time matching optimization method described above, wherein the digital twin-driven solid waste real-time matching optimization system comprises: The source-end twin modeling module is used to obtain construction solid waste source data and perform solid waste source twin modeling based on the construction solid waste source data to obtain a digital twin source model; The receiving end twin modeling module is used to obtain the construction solid waste receiving end data and perform receiving point twin modeling based on the construction solid waste receiving end data to obtain a digital twin receiving end model; The solid waste matching modeling module is used to match the digital twin source model and the digital twin receiving end model to obtain a solid waste matching model; The task splitting and fusion scheduling module is used to perform task splitting and fusion scheduling according to the solid waste matching model to obtain solid waste scheduling data.

[0024] The purpose of this invention is to construct a real-time source twin through structured collection and attribute standardization of source data (S1), and incorporate scheduling accessibility evolution to make solid waste calculable and predictable across multiple dimensions ("type-volume-pollution-location-time"), eliminating matching biases caused by data heterogeneity. S2 On the receiving end, processing capacity and pollution limits are extracted, and a receiving twin model is constructed that dynamically changes with shifts, equipment status, and policy constraints. This transforms static production capacity into a time-series load curve, proactively identifying overload and violation risks. S3 Based on the twins at both ends, cross-batch collaboration and high-pollution-specific matching are performed, and path risk maps are superimposed for avoidance control. This achieves joint optimization of "compatibility-distance-capacity-pollution-route safety," significantly reducing the probability of rejection and rollback. S4 refines the matching results into task scheduling units, introduces splitting criteria and risk reorganization, and then outputs an executable plan through integrated feasibility screening, thereby improving loading rates and vehicle utilization, and reducing detour mileage and waiting time. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A flowchart showing the steps of a digital twin-driven solid waste real-time matching optimization method according to one embodiment is shown; Figure 2 A flowchart of the steps of a source-side twin modeling method according to an embodiment is shown; Figure 3 A flowchart of a receiving-end twin modeling method according to an embodiment is shown; Figure 4 A flowchart showing the steps of a solid waste matching modeling method according to an embodiment is shown; Figure 5 A flowchart of a task splitting and merging scheduling method according to an embodiment is shown; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0026] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0027] Furthermore, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0028] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0029] See also Figures 1 to 5 , this application provides a digital twin driven solid waste real-time matching optimization method, the method comprising: S1. Obtain construction solid waste source data, and perform solid waste source twin modeling based on the construction solid waste source data to obtain a digital twin source model; Specifically, the system collects data from multiple solid waste sources, including but not limited to physical locations such as construction sites, demolition projects, and prefabricated component factories. Collected data fields include solid waste type (such as concrete, bricks, metal, and insulation); mass per unit volume (measured in kilograms per cubic meter); particle size distribution (described in microns); initial storage location coordinates (using GPS positioning); generated timestamps (indicating when the solid waste was generated); estimated removal deadlines; and contaminant labeling information (such as whether it contains harmful components such as paint residue and asbestos). The system standardizes raw solid waste attribute data, including dimensionality reduction encoding using principal component analysis (PCA) for similar solid waste data. This generates a unified attribute vector containing solid waste type number, mass per unit volume, particle size index, and contaminant label information. All time data is converted to the ISO8601 standard time format, and all spatial coordinate data uses the WGS-84 geographic projection system. The system constructs a digital twin based on this standardized source solid waste data. Each solid waste entity will be mapped to a unique source digital twin, bound to the following information: unique solid waste entity number; life cycle status (such as generation, sealing, waiting for removal, etc.); real-time fields, including weather impact status (such as rainy day operation restrictions), sealing status (such as covered), etc.

[0030] S2. Obtain the construction solid waste receiving end data, and perform receiving point twin modeling based on the construction solid waste receiving end data to obtain a digital twin receiving end model; Specifically, the system collects receiving-end data from construction solid waste receiving stations. The collected information includes but is not limited to basic information about the receiving and processing site, such as its unique number, maximum processing capacity (for example, in tons per hour), operating hours, and the type of processing equipment equipped; threshold limits for acceptable pollutants, including the maximum allowable content of volatile organic compounds (VOCs), pH range, and upper concentration limits of metal ions (such as lead and cadmium); the current system processing load (i.e., the amount of solid waste processed per unit time), the scheduled task schedule, and the maximum capacity of the storage yard. The system structures and standardizes the above data, including constructing a receiving capacity vector for each receiving site, which includes the processing capacity value, a list of acceptable solid waste types, the operating time period, and the current load value; and constructing a pollutant restriction matrix for pollutant reception restrictions, with each pollutant corresponding to the set maximum allowable value and the current remaining acceptable capacity. After completing the data structuring, the system constructs a receiving-end digital twin object for each receiving and processing site. Each processing site corresponds to a digital twin receiving body with a unique number, which contains the scheduling window list of the receiving site (recording the time period when it is open for operation), the pollution load cache (recording the current accepted and pending pollutant loads), and the task trajectory history (recording the time, type and source of all previous received tasks); at the same time, each receiving site is bound to its physical space location and the path map node number.

[0031] S3. Match the digital twin source model and the digital twin receiving model to obtain a solid waste matching model; Specifically, the system constructs a source set and a receiver set respectively, which are recorded as a source digital twin set and a receiver digital twin set. Based on these two types of objects, the system constructs a bipartite graph structure consisting of a source node set and a receiver node set, where the edges of the graph represent the matching relationship between the source and the receiver. The attributes of the connected edges include material compatibility, which indicates the degree of material adaptation between the solid waste type and the receiver's processing capacity, with reference to the preset material matching table; pollution matching, which indicates the degree of matching between the source pollutant characteristics and the receiver's pollutant restrictions, calculated by the pollutant load function; the operation time window intersection ratio, which characterizes the degree of overlap between the source's estimated removal time and the receiver's schedulable time; the source receives accessibility data, which is calculated based on the traffic accessibility between the source and the receiver, such as normalized calculation based on the travel distance between the preset electronic maps. The edge weight is calculated based on the aforementioned edge attributes: ; in is the edge weight data, is the material compatibility weight data, For material compatibility, is the pollution matching weight data, is the pollution matching degree, is the weighted data of the window intersection ratio during operation, is the window intersection ratio during operation, Receive reachability weight data for the source, Receive accessibility data for the source end. Extract candidate paths based on edge weights, and construct a bipartite graph based on the candidate paths to form a collaborative matching network. For source-end solid waste objects marked as highly polluting (i.e., their pollutant flag field is 1), the system adopts a priority matching mechanism. Specifically, it only screens targets from receiving ends that have pollutant treatment qualifications and have remaining pollutant receiving space; performs path pollution propagation simulation before matching, and if the path passes through an identified sensitive area (such as a school, residential area, or water source protection area), the weight of the path in the scoring function will be reduced accordingly. In serious cases, the candidate relationship of the path will be eliminated.

[0032] S4. Perform task splitting and fusion scheduling based on the solid waste matching model to obtain solid waste scheduling data.

[0033] Specifically, the system constructs scheduling task units based on the source and destination matching pairs identified in the solid waste matching model and combined with transportation requirements. Each task unit contains key scheduling fields such as the source number, destination number, estimated transport weight, and corresponding arrival time requirement. This process considers vehicle deployment plans and maps each matching pair into a set of specific, executable transport task units. Based on the parameters in the scheduling task unit, the system sets task splitting criteria. If the transport weight of a single task exceeds the maximum load capacity of the system-assigned vehicle; or if the arrival time window of the task does not overlap with the target destination's open hours, the original task is split into multiple subtasks. The splitting process must meet the following three basic requirements: each subtask must have a clear, accessible path; each subtask's destination destination must have receiving capacity; and the transportation cost of the resulting subtasks must not significantly increase compared to the original task. The system evaluates the potential for reassembly of the resulting subtasks. If multiple tasks share the same destination destination and their transportation routes have a high degree of overlap (e.g., over 80%), the system determines that they have potential for combined transport. Before reorganization, the system performs time alignment processing and fine-tunes the departure time of each subtask so that they enter the loading process within the same time window, realize task consolidation, and improve transportation efficiency and vehicle utilization. For all tasks that are attempted to be merged, the system performs fusion feasibility testing to ensure the feasibility of the scheduling plan. It mainly includes the following three tests: evaluating whether there are scheduling conflicts or traffic resource competition in the path of the merged task; ensuring that the merged task is still within the processing time period allowed by the receiving end; for consolidation tasks involving polluted solid waste, detect whether the overall pollutant index after the merger exceeds the critical threshold set by the receiving end. If all the above tests are passed, the system will mark the scheduling task as an executable task, include it in the scheduling result set, and form a scheduling data output set.

[0034] Optionally, S1 includes: S11. Collect basic data on sources of construction solid waste to obtain basic data on solid waste sources; Specifically, the system uses the main nodes that generate construction solid waste as collection objects, including construction sites, building demolition sites, concrete prefabrication plants and other actual scenes with material outflow or demolition tasks. Each collection object has an independently identifiable physical area and operation unit, and has the ability to independently generate solid waste. The system deploys various forms of data collection devices and terminals at the above-mentioned solid waste source nodes, including on-site IoT sensors, such as silo weighing sensors, volume monitoring sensors, and environmental component detection sensors; mobile operation terminals, such as smart mobile terminals carried by operators (supporting photo upload and task registration); drone scanning systems for periodic collection of yard images or three-dimensional point cloud data. For each solid waste unit, the system collects and records the unique solid waste number, solid waste type information (solid waste classification coding is performed according to the national or industry five-level classification standards (such as broken concrete, old bricks, waste steel bars, insulation boards, etc.)), physical quantity parameters at the exit, spatial location information, timestamp information, pollution risk preliminary judgment label (through preliminary identification by sensors or labeling by operators, recording whether the batch of solid waste may contain specific pollutants (such as volatile organic compounds, asbestos, oily residues, etc.)), sealing status information (: recording the current solid waste stacking or transportation status, including exposed stacking, temporary covering, sealed transfer, etc.), scheduling status code (recording the scheduling process status of the solid waste in the station, including "waiting for loading", "dispatched", "abnormal interruption", etc.).

[0035] S12. Standardize the attributes based on the basic data of solid waste sources to obtain the source data of construction solid waste; Specifically, the system standardizes the raw data collected at the source to eliminate discrepancies between different units of measurement. Weights and volumes are uniformly converted to SI units (e.g., kg, m³); coordinate projections are standardized to the WGS-84 system, retaining at least six decimal places of precision; timestamps are converted to the UTC standard format to facilitate cross-regional calculations; multi-valued categorical variables (e.g., solid waste type) are mapped to one-hot codes or enumerated IDs; and pollution risk labels are Boolean mapped, meaning that Boolean values ​​take on the value 1 or 0.

[0036] S13. Construct a digital twin object based on the construction solid waste source data to obtain the solid waste source digital twin data; Specifically, based on standardized construction solid waste source data, a corresponding digital twin object is constructed for each solid waste entity. This object dynamically reflects the state evolution, scheduling behavior characteristics, and physical parameter simulation process of the solid waste entity during its actual lifecycle. The twin object includes a unique digital twin ID, standardized entity data references, state transition logic (such as {to be collected} → {to be transferred} → {in transit} → {arrived}), interface fields (such as whether joint loading is supported, supported loading and unloading types (lifting / pushing / manual), whether covered transportation is required), real-time fields (such as temperature and humidity environment, current weight change, current location), and risk fields (such as proximity to water sources / communities, etc.) requiring special treatment. A stream processing system (such as Kafka + Flink) is used to update the twin object's status in real time.

[0037] S14. Perform scheduling accessibility evolution simulation based on the digital twin data of the solid waste source to obtain the digital twin source model.

[0038] Specifically, the system constructs a scheduling accessibility graph structure for each solid waste source digital twin object in the traffic space, specifically mapping the solid waste twin object to the starting node in the traffic network; constructing a traffic graph G(V,E), where V represents a traffic node (such as an intersection or hub station) and E represents a connecting edge (such as a road segment, bridge, tunnel, etc.); each edge is accompanied by multiple weighted indicators, including travel time (in minutes), distance (in meters), road congestion state coefficient (range [0,1]), whether it is affected by construction closures, whether it is in a no-traffic period, etc.; for path segments that pass through highly polluted areas, the system sets the pollution path crossing risk value based on the building attributes of the traversing area through a preset parameter library as one of the negative constraint indicators of the edge. Calculate the path accessibility function: ,in is the path reachability data, To estimate the travel time weight data, the unit is the negative first power of minutes, The estimated travel time of the shortest path from the source to the sink, in minutes, is the average congestion coefficient weight data, is the average congestion coefficient along the path, with a value range of [0,1]. The larger the value, the more serious the congestion. is the total risk weight data, The total risk weight of highly polluted areas traversed by the path (such as ecological protection areas, schools, and hospitals) is calculated by accumulating the risk values ​​of each segment. Path accessibility data is added to the solid waste source digital twin data, and a path accessibility scheduling threshold is set. If the current path accessibility data falls below the path accessibility scheduling threshold, scheduling is deemed unavailable. The corresponding solid waste twin object will then be placed in the queue for scheduling, and the system will reassess its scheduling feasibility in the next round of accessibility evolution updates.

[0039] Optionally, S2 includes: S21. Acquire construction solid waste receiving end data, and extract solid waste treatment features based on the construction solid waste receiving end data to obtain solid waste treatment feature data; Specifically, the system collects key operating data of each solid waste treatment node through multi-source information channels. The data includes the SCADA systems deployed at receiving stations, transfer stations and terminal processing centers; programmable logic controller (PLC) equipment and loading machinery control terminals connected to the production line; heat treatment systems, physical sorting equipment, compaction devices, etc. used in the solid waste treatment line; and auxiliary collection systems, such as intelligent weighing systems, video recognition and material recognition systems. The system extracts the following fields for each receiving point and organizes them in a structured form: the receiving site number and its spatial coordinate information (latitude, longitude and elevation); the maximum processing capacity and the current processing capacity, in kilograms per hour (kg / h), which allows dynamic updates; the process types available at the receiving point, including but not limited to pyrolysis, physical crushing, screening, biological treatment, etc.; the current operating status of the process line, with optional statuses including "in operation", "standby", "under maintenance", etc.; the processing cost model, which supports pricing based on solid waste category, pollution risk level or processing weight, and the modeling method can be linear function, piecewise function or polynomial fitting; the daily receiving window period, such as "08:00-18:00"; the current cumulative receiving volume (statisticed on a daily basis); on-site logistics constraints, including height limit (in meters) and weight limit (in tons); loading and unloading method requirements, such as whether lifting, pushing, manual unloading, etc. are supported.

[0040] S22. Extract pollutant limits based on the construction solid waste receiving end data to obtain pollutant limit data; Specifically, each receiving end systematically identifies its acceptance tolerances and treatment boundaries for pollutant types, specifically including the types of pollutants it will not accept, the maximum acceptable concentrations, and the required classification and isolation conditions during treatment. The system integrates multi-source data and platform interfaces to extract pollutant restriction information. By connecting to regional environmental management platforms (such as the provincial hazardous waste supervision information system), the system accesses data on legal pollutant acceptance permits for each site, including permitted pollutant types, maximum acceptance concentrations, and total volume limits. Based on key process parameters of the receiving end's treatment line (such as heat treatment temperature, gas purification method, and biodegradation treatment pathway), the system determines the acceptable range for a specific pollutant at that site. For example, if the treatment equipment lacks VOC adsorption capacity, that type of pollutant will be designated as unacceptable. The system analyzes a site's historical acceptance records and environmental penalties. If a site has been penalized for accepting illegal pollutants (such as asbestos or lead-containing solid waste), the system will assign a "restricted acceptance" or "blacklist" label to that type of pollutant. During this process, the system constructs a pollutant tolerance matrix, where each row represents a pollutant type (for example, the first row, VOC), its corresponding maximum allowable concentration (in ppm), and whether or not it is permitted to be accepted (a Boolean value).

[0041] S23. Construct a digital twin object based on the construction solid waste receiving end data to obtain the solid waste receiving end digital twin data; Specifically, an independent digital twin object is constructed for each construction solid waste receiving end. Each digital twin object includes a unique identification number of the receiving end; a bound standardized processing feature structure, including processing technology, equipment capacity, operating time window, loading and unloading constraints, etc.; a bound pollutant restriction structure, including acceptable pollutant types, concentration limits, blacklist lists, etc.; a set of real-time operating status variables of the receiving end, including remaining processing capacity, current inbound queue status, historical load curves, etc.; a pollutant reception feasibility calculation function, which calculates the acceptability of candidate tasks based on factors such as current capacity status, pollutant type, and historical violation records. The specific calculation process can be obtained based on weighting or linear mapping based on the current capacity status; a scheduling linkage interface field, which marks whether the scheduling system docking is supported, such as whether advance reservations are supported, whether load feedback capabilities are available, etc.; a visual display field for the map system or control panel, such as a virtual space display and the use of color (green / orange / red) or saturation to reflect the remaining proportion of processing capacity or the restriction level. When it is detected that the current receiving end's cumulative daily receiving volume has reached 80% or more of its maximum processing capacity, the system updates the status of the twin object to restricted reception and significantly reduces the receiving capacity for new tasks. If the system detects that the candidate transportation task contains a VOC type pollution source, and the Boolean value in the current receiving end's acceptance limit = 0 (i.e., the acceptance of such pollutants is prohibited), the system automatically removes the task-receiving end combination and does not schedule it for matching. If the SCADA system or PLC data feedback receiving end processing equipment is in a down state, the system will push a message to the scheduling engine through the interface, automatically triggering a temporary adjustment of transportation capacity and site switching.

[0042] S24. The digital twin data of the solid waste receiving end is run and evolved according to the solid waste treatment characteristic data and the pollutant restriction data to obtain a digital twin receiving end model.

[0043] Specifically, based on the current processing capacity curve and the queued task list, the system simulates the processing capacity consumption per unit time in the future time period, and dynamically deducts the capacity required for the current task to predict the remaining capacity. Based on the existing transportation tasks and pollution types, the system calculates the expected arrival volume of various pollutants in each future time period, compares it with the upper tolerance limit of pollutants at the receiving end, and forms an estimate of the remaining pollutant tolerance. This estimate is used to derive the pollutant load score indicator, reflecting the trend of pollution risk backlog. The system executes the state prediction process with a time granularity of 30 minutes, with the longest prediction period of 24 hours, forming a set of time series state evolution trajectories.

[0044] Optionally, S3 includes: S31. Perform cross-batch collaborative matching based on the digital twin source model and the digital twin receiving model to obtain a first solid waste matching model; Specifically, solid waste entities with geographical proximity (within the spatial range threshold), generation time proximity (generation time is within the allowable error range) and material compatibility (based on material type (such as concrete, bricks, steel bars, etc.) similarity calculation, judgment within the threshold range, excluding source points with significant chemical conflicts or incompatible loading and unloading methods) are extracted from multiple source models as a "collaborative entity set" to build a batch pool. Based on the above collaborative matching relationship, the system constructs a collaborative batch graph G=(V,E), where the node V represents the digital twin object of the solid waste source; the edge E represents the possible collaborative path that meets the matching rules, and each edge can be accompanied by a weight value, such as a collaborative strength score. The system uses a density-based graph clustering algorithm (such as DBSCAN or density-guided partitioning method) to divide the collaborative graph into batch units to generate a collaborative batch set.

[0045] S32. Matching the polluted building solid waste is performed according to the digital twin source end model and the digital twin receiving end model to obtain a second solid waste matching model; Specifically, the pollutant types, concentrations, and estimated release amounts are extracted for batches marked as highly polluting at the source (such as lead-containing paints, asbestos boards, etc.); for each receiving-end digital twin model, the system extracts its maximum tolerance threshold for pollutants, which can be derived from the equipment's processing capacity, environmental protection license restrictions, or historical penalty records. If the estimated release amount is greater than the maximum tolerance threshold for pollutants, the pairing is automatically eliminated. Combined with map data and historical wind direction / drainage models, the flow path of pollutants is simulated, and a pollution particle migration simulation (such as Gaussian particle diffusion) is used to estimate the pollution transfer risk heat map. If the polluted batch is estimated to pass through highly sensitive areas (such as schools, hospitals, and drinking water sources) during the path, the system prohibits the pairing; otherwise, it is marked as a compliant pairing.

[0046] S33. Perform path risk avoidance control according to the first solid waste matching model and the second solid waste matching model to obtain a solid waste matching model.

[0047] Specifically, for each pair of solid waste transportation source-receiver combinations determined by the previous batch matching (first solid waste matching model) and pollution adaptation (second solid waste matching model), the system extracts its dispatch transportation path and divides the path into several unit sections. For each unit path segment, the traffic congestion index is extracted, which represents the average congestion level of the path segment in the historical period, which can be provided by the traffic big data platform or the historical traffic volume database; the accident frequency index represents the average frequency of traffic accidents in the path segment in recent years, which can be derived from the traffic management system or the public security database; the sensitive area crossing penalty, if the path segment passes through an environmentally sensitive area (such as a school, hospital, or a historically high-incidence area of ​​pollution complaints), the value is set as a non-zero penalty factor, and quantitative marking is performed according to the sensitivity level. The system constructs a weighted graph structure based on the above risk factors, where the nodes are a set of path nodes, the edges are a set of path segments (each segment connects two path nodes), and the edge weights are the edge weights of the path segments from the nodes to the connected nodes, which are obtained by weighted summation based on the above indexes. In the constructed weighted risk graph, the system uses The algorithm, or Dijkstra's shortest path algorithm, calculates the minimum risk path from the source node to the receiving node and obtains its cumulative risk score, which is the sum of the edge weights of all path segments.

[0048] Optionally, the cross-batch collaborative matching includes: Extract collaborative entities based on the digital twin source model and the digital twin receiver model to obtain collaborative entity data; Specifically, the system sets the following collaborative conditions to limit the solid waste entities that can be classified as the same collaborative batch. Category consistency rule: Collaborative entities must belong to the same solid waste category, such as concrete, bricks and tiles, wood, etc., based on the material category field recorded in the digital twin source model; Time proximity rule: The generation time difference of collaborative entities should not exceed the preset threshold (for example, 24 hours); Geographic proximity rule: The spatial distance of collaborative entities does not exceed the preset distance threshold (for example, 5-20 kilometers); Receiving capacity constraint rule: The total mass of collaborative entities shall not exceed the maximum receiving and processing capacity of any target receiving point per unit time (which can be queried through the processing capacity field in the receiving end twin model). The system completes the collaborative entity clustering and screening process according to the following steps: (1) Extracting basic feature tuples of solid waste from multiple source twin models, including geographic location (latitude and longitude coordinates), material type identification, solid waste generation timestamp, and solid waste weight; (2) Executing a clustering algorithm based on physical properties on the above tuple set, such as K-Means or density clustering algorithm (DBSCAN), to group solid waste entities that meet the characteristics of "similar, close in time, and close in place"; (3) For each clustering result, call the digital twin receiving end model to query the current available processing capacity of its corresponding receiving point. If the total mass in the cluster group exceeds the upper limit, it will be eliminated or split.

[0049] Perform reachable entity division and splittable entity division based on collaborative entity data to obtain reachable entity data and splittable entity data respectively; Specifically, the system constructs a multi-level road network model for the target area based on electronic map data. This model divides regional roads into a main road layer, representing high-grade roads with high carrying capacity; a branch road layer, connecting the main road with solid waste generation or treatment nodes; and a restricted / closed section layer, including construction closures, time-limited sections, and other areas requiring special treatment. For each pair of potential routes between a solid waste source and a waste receiving point, the system calculates: ,in is the entity reachability data, is the shortest feasible distance from solid waste source point i to receiving point j, is a natural constant term, The congestion coefficient is calculated based on historical traffic data and real-time road conditions, e.g., actual speed / speed limit. The system sets an entity accessibility threshold. The system classifies entities according to the following rules: If the entity accessibility data is greater than or equal to the entity accessibility threshold, entity i is classified as accessible, indicating that it has good transportation conditions and is prioritized for scheduling. Otherwise, the entity is marked as an entity to be optimized or an unreachable entity, and can be optimized or removed based on scheduling requirements.

[0050] The system determines the physical properties and material composition of collaborative entities, and a split mark is triggered if any of the following conditions are met: the total mass of the entity exceeds the maximum carrying mass threshold of the transport carrier (for example, 3.5 tons); the total volume of the entity exceeds the maximum volume threshold of the temporary storage yard at the receiving end (for example, 2.0 cubic meters); the entity contains two or more components with material conflicts (such as asbestos and gypsum, which need to be handled separately at the receiving end). The system constructs a material mutual exclusion rule table based on expert experience or preset parameters. For example, asbestos must not be mixed with combustible plastics, and gypsum must not be processed in the same batch as high-cement concrete. If an entity contains a combination of mutually exclusive materials, it is determined that a material conflict exists. For each entity marked as splittable, the system records the reason for triggering the split, including but not limited to mass overload, volume excess, and material composition conflict.

[0051] According to the digital twin receiving end model, a collaborative batch path diagram is generated for the reachable entity data and the splittable entity data to obtain the first solid waste matching model.

[0052] Specifically, the system combines the spatiotemporal distribution characteristics of reachable entities and splittable entities, takes the digital twin receiving end model as the target node, constructs a traffic path diagram and batch path planning for the source solid waste entities, and forms a collaborative scheduling graph structure. With each solid waste receiving end as the target node and all source entities to be scheduled as the starting nodes of the graph, a directed traffic graph G=(V,E) is constructed, where V represents the key location points in the traffic network, such as source points, receiving points, and intersection nodes; E represents the road connection edge, which has an attributed weight. For each path edge in the graph, the cost weight function is calculated: ,in is the path cost weight, is the distance factor weight, is the path distance weight coefficient from node i to j, which is obtained based on the normalization of the path distance. is the time factor weight, is the estimated transportation time weight coefficient, which is obtained based on the normalized estimated transportation time. is the distance factor weight, is the traffic risk level weight coefficient for each path segment, derived from a normalized traffic risk level, accident probability, and historical congestion levels, or a preset value. For solid waste entities marked as splittable in the previous stage, the system executes the following processing logic: Large or multi-component solid waste entities are split into multiple sub-batches based on maximum transport load, receiving yard capacity, or material conflict requirements, with each sub-batch meeting the scheduling criteria. The system can match these sub-batches to different receivers or schedule them to the same receiver within different time periods. During the matching process, the system automatically reuses the path graph structure and selects the optimal solution by comparing path costs. The system detects overlap between receiver entry nodes across all paths at a given time. If the scheduling density within the same time window exceeds the receiver's capacity limit (e.g., vehicle queue length or number of concurrent unloading operations), a path conflict is identified. If a conflict exists, the system replaces it with an equivalent but riskier alternative path. A scheduling delay mechanism is activated to adjust some entities to later available time windows. If the conflict cannot be resolved, the matching path is marked as infeasible. The system outputs a collaborative batch path graph model that includes information such as path planning, entity allocation, and arrival times. This model records the dispatch path of each member entity, whether it is split, and related arrival information, using collaborative batches as units. This includes the collaborative batch identifier; path information for each source entity (including the source point, receiving point, and a list of nodes passed through); and the estimated time of arrival (ETA). If an entity is split, the split status and the independent paths of each sub-batch are also recorded.

[0053] Optionally, the reachability entity division includes: Performing hierarchical road network path processing based on collaborative entity data and preset electronic map data to obtain hierarchical road network path data; Specifically, the system divides all roads in the electronic map data into the following three levels of network layers according to the physical properties of the roads and the traffic level: the main road layer is a road with a width of not less than 10 meters, and is marked as a municipal main road, urban expressway or national and provincial road; the secondary road layer is a road with a width between 5 and 10 meters, allowing medium and large vehicles to pass at a lower speed; the branch road layer is a road with a width of less than 5 meters, which is an internal road within residential and industrial areas. The system extracts the attributes of each road segment based on the electronic map data. For each starting point in the collaborative entity data, the system combines the target receiving point and the road network level it is in. The system can select a heuristic search algorithm (such as algorithm) or shortest path search algorithm (such as Dijkstra algorithm): The algorithm is suitable for searching for multi-weighted optimal paths in the presence of traffic penalties (such as congestion and traffic restrictions); the Dijkstra algorithm is suitable for calculating the shortest path in static graph structures. The system automatically limits the search space based on the road grade of the entity. For large solid waste transport tasks, it prioritizes main and secondary roads. For heavily loaded entities where branch roads are inaccessible, the candidate path set excludes all branch road segments. For small batches, combined paths connecting branch roads to main roads can be considered. Several optional paths are generated for each entity, and the system records each path's node sequence (i.e., the road intersections it passes through); the total length and estimated time of the path; the distribution of road grades involved; and the congestion risk assessment results.

[0054] Constructing a multi-level road network graph based on the hierarchical road network path data to obtain multi-level road network graph data; Specifically, the system constructs a graph structure based on each road segment in the hierarchical road network path data, formalized as a directed weighted graph. The starting and ending locations of each path segment are abstracted as graph nodes, and graph edges are formed between any two adjacent path segments. Graph edges are directed, indicating the direction of road traffic. For two-way roads, two edges are established, one in the forward direction and one in the reverse direction. The system divides the overall graph structure into multiple layers based on road grade and scheduling priority. Each layer constitutes a multi-level road network diagram. The first layer (Level 1) contains all main road nodes and edges that meet high-level standards; the second layer (Level 2) contains secondary roads connecting main roads to local target areas; and the third layer (Level 3) contains branch roads or temporary passages that are only accessible to light vehicles.

[0055] Process the multi-level road network data with source group requirements to obtain path layer data; Specifically, the system processes the collaborative entities in each collaborative batch and extracts the set of transport path segments that have been assigned to them. Each element in the set corresponds to a sequence of path segments from the source point to the receiving end, including a specific graph node number and estimated travel time information. For any two entities, the system checks whether there is a graph node intersection in the path segment set, that is, whether there is a shared path segment; based on the travel time window data corresponding to the path segment, it determines whether there is an overlapping area of ​​the time window for the two paths to be spliced. The time window is the interval between the earliest departure time and the latest arrival time allowed by the task. For path pairs that meet the overlap conditions in both space and time, the system calculates their splicing suitability using the following splicing calculation function: ,in To combine the suitability data, The set of segments of the path selected for task i, is the set of segments of the path selected for task j, is the smaller of the two path segment numbers, is the degree of alignment of path scheduling time, , is the maximum value symbol, for Estimated time of arrival, for Estimated time of arrival, The maximum allowed time deviation threshold preset for the system (for example, 5 minutes, 15 minutes, half an hour, or one hour), The number of segments in the two sets that have the same path segment identifier (i.e., the same start and end node numbers). When the threshold is exceeded, the system marks the paths of the group of entities as stackable and constructs a path stacking structure, merging the transport tasks of two or more entities into a unified transport resource and scheduling track based on shared path segments. The system outputs the identified path stacking data in the form of a structured path graph, which includes the sequence of shared path segments (i.e., the intersection of the path segment sets); a list of the entity numbers being merged; and the order of the path graph nodes and their estimated arrival times.

[0056] Perform fusion path traffic reachability extraction on the path stacking data to obtain fusion path traffic data; Specifically, for each shared overlapping path segment in a shared path, the system extracts and aggregates the following traffic accessibility-related parameters: the maximum allowable load parameter, which is the maximum traffic load allowed by the current road segment design, in tonnage (t), with the minimum value among all shared path segments as the upper constraint limit; the current and predicted traffic flow parameters, which obtain the current vehicle traffic flow based on traffic sensor data, historical traffic models, or map service APIs, and predict traffic flow trends in a specific time period in the future; the real-time road condition level parameter, which identifies the current or predicted traffic pressure level of the road segment with a preset level (such as low, medium, and high) and assigns a numerical weight (for example, low = 0.5, medium = 1, and high = 2). The system constructs a fusion accessibility index based on the above parameters, and the specific calculation formula is as follows: ,in is the accessibility index of the fusion path, is the average permissible load value of the shared path segment, is the estimated delay time in minutes. This is a real-time traffic pressure factor derived from the road condition level conversion results. The system sets an accessibility threshold. When the accessibility index of the fused path corresponding to a shared path falls below the threshold, it is deemed to lack sufficient accessibility. Such a path is removed from the accessible path set and does not participate in subsequent scheduling.

[0057] Perform convolution processing on the fused path traffic data to obtain the peak window data that can be combined; Specifically, the traffic data for each route is encoded as a time series vector, where each bit represents the congestion index at a specific moment. A sliding convolution kernel window (e.g., 5 minutes, length 5, stride 1, kernel content [1, -1, 0, 0]) is applied to extract congestion mutation edges and stable low-flow intervals. The convolution kernel performs edge detection and pattern recognition on the congestion sequence within the current window, identifying sudden congestion bursts (e.g., sudden increases or decreases) based on a preset mutation threshold. Stable low-congestion segments, defined as time periods with locally low congestion values ​​in the convolution result, are selected as candidate time windows for load-sharing operations. Continuous low-pressure areas in the convolution result (e.g., areas with a congestion coefficient less than 0.3 for 10 minutes) are marked as load-sharing peak windows. The efficient load-sharing time periods for each route are output.

[0058] According to the digital twin receiving end model, the multi-entry path assignment conflict of the peak window data that can be spliced ​​is carried out to obtain the reachability entity data.

[0059] Specifically, the system constructs a multi-entry structure for each receiving end. Each entrance (such as the east gate, west gate, and temporary construction zone entry point) is bound to corresponding constraint parameters, including but not limited to restrictions on the types of solid waste acceptable at the entrance (e.g., only concrete is allowed, not asbestos-containing materials); maximum carrying capacity (e.g., the maximum vehicle flow or weight limit per unit time); permitted entry time windows (e.g., 8:00–10:30 AM is a construction-only window); and current cumulative entry tasks and historical distribution information. The system performs a target receiving end adaptation check for each peak loading window. Specifically, if multiple loading entities are assigned to the same entrance simultaneously and their peak loading windows overlap, it is considered a time overlap. If the materials carried by the entities do not match the supported types of the entrance (e.g., gypsum materials are contained but the entrance is prohibited), it is marked as a category conflict. If there are already scheduled or in-progress vehicles that have caused the entrance load to exceed its set capacity threshold, it is considered a load conflict. Based on the judgment results, the system handles each potential conflict in a graded manner: severe conflict level: if there is a material conflict or the cumulative load is seriously exceeded, the path will be regenerated, or the current loading task will be split at the entity level; medium conflict level: if the entry time overlap is high but has not exceeded the threshold, a waiting mechanism will be introduced, or switching to an alternative entrance will be carried out; minor conflict level: if the estimated waiting time is short or the vehicle is not yet fully loaded, the system can be judged as an "reachability entity" and directly scheduled for execution.

[0060] Optionally, the contaminated construction solid waste matching includes: Extract pollutant load characteristics based on the digital twin source model and the digital twin receiving model to obtain pollutant load characteristic data; Specifically, the system extracts the following fields for each source entity: mass and volume indicators: including total mass (tons), volume (cubic meters), moisture content (percentage); pollutant concentration list: such as lead (Pb, unit ppm), cadmium (Cd, ppm), chromium (Cr, ppm), volatile organic compounds (VOC, mg / m³), asbestos flag (Boolean type), pH value, chloride ion concentration (percentage); particle size distribution data (including d10, d50 and d90 (microns)); time and geographic location data (including generation time (ISO 8601 format), latitude and longitude coordinates (WGS-84 coordinate system) and transportable time window (formatted as start and end time interval)). All pollutant concentration fields are converted to units, so that metals are unified into mass fraction units of ppm, and gases / vapors are unified into mass concentration units of mg / m³. For each type of pollutant, the system calculates the source pollutant load value according to the following formula: ,in is the total load of entity i on pollutant k (the unit is automatically matched according to the pollutant type), is the physical unit of the source entity (tons for solid state and cubic meters for gaseous state), is the mass concentration of pollutant k (e.g. Pb is ppm, VOC is mg / m³). The system calculates the toxicity hazard index, which is expressed as follows: ,in is the toxicity hazard index, is the pollutant type index, is the pollutant weight, is the pollutant load value, is the reference limit.

[0061] Performing receiving-end pollution load processing according to pollutant load characteristic data to obtain receiving-end pollution load data; Specifically, a load matrix is ​​established based on the pollutant load characteristic data, that is, the hourly / daily upper limit and current usage of pollutant k at site j. Based on the matrix, the recovery / attenuation coefficient is constructed based on historical data: ,in is the remaining available capacity, The maximum load limit, Indexing historical moments, is the current time, The system determines whether the current source material is permitted to be received based on the receiving end configuration and pollutant properties. Specific rules include, but are not limited to, prohibiting the acceptance of materials marked as asbestos if the site does not have an asbestos handling permit. If the predicted peak value of a pollutant (such as VOC) exceeds the hourly limit at the receiving point, staggered scheduling or material splitting is required. If the pH value exceeds the acceptable range at the receiving end, pretreatment is required before acceptance.

[0062] Perform pollution migration simulation on the digital twin source model and the digital twin receiving model based on the pollution carrying data of the receiving end to obtain pollution migration data; Specifically, for each pair of source and receiver, the system generates multiple candidate transport path sets in the digital twin scene. The transport area is divided into two-dimensional grid cells with equal spacing (e.g., 50 meters). 50 meters), construct a grid set and mark sensitive areas in it, including schools, hospitals, water source protection areas, etc. The system uses Gaussian plume or discrete convection-diffusion model to simulate the diffusion process of pollutants in the air. The migration equation is: ,in is the pollutant concentration function, is the pollutant concentration function, is the wind speed vector, is the concentration gradient, is the diffusion coefficient, is the source term release rate, is a position function. The pollution source is located at a certain time t , is the spatial position vector, i.e. the observed spatial position (two-dimensional or three-dimensional), The system uses an explicit time advancement mechanism, with each simulation step length set to (e.g., 1-5 minutes), dynamically updating the vehicle trajectory, pollutant release point, and diffusion field state to obtain pollution migration data.

[0063] According to the pollution migration data, the digital twin source model and the digital twin receiving model are marked with pollution solid waste matching to obtain a second solid waste matching model; Specifically, after completing the simulation of pollutant migration paths and risk distribution, the system combines the pollutant carrying capacity of the receiving end, the pollution output intensity of the source end, and the migration risk level on the path, and based on the preset environmental compliance rules and sensitive area avoidance strategies, conducts multi-factor operability evaluation and labeling for each pair of path combinations between the source end solid waste entity and the receiving end resource unit. The labeling results include matching feasibility level, pollutant category adaptability, time window matching, and path risk level.

[0064] The pollutant load feature extraction includes: Extract pollutant data based on the digital twin source model to obtain pollutant data; Specifically, pollutant data is extracted based on the digital twin source model, including solid waste type labels, component composition parameters, initial mass and volume parameters, particle size distribution parameters, and the time when the solid waste entity is generated or reported.

[0065] Extract interaction paths based on the digital twin source model and the digital twin receiver model to obtain interaction path data; Specifically, the system is based on an electronic map engine (such as access to the AutoNavi Map API, Baidu Map Service, or deployment of a locally developed GIS engine). For each set of source entities and receiving entities, the system extracts a set of paths that meet the following conditions from the map service based on the loading requirements, road access levels, and traffic supervision restrictions of the current solid waste scheduling task, as candidate interaction paths from the source to the receiving end: can accommodate the transportation load (the load limit meets the vehicle tonnage requirements); avoid closed / restricted areas; the path travel time is within the transportation time window set by the scheduling task (such as 08:00–20:00); the total path length and duration are within the allowable range.

[0066] Perform pollution potential attenuation processing on the interactive path data according to the pollutant data to obtain the pollutant path data; Specifically, based on the migration characteristics of pollutants in different forms, such as gaseous pollutants (such as volatile organic compounds (VOCs), an exponential decay model is used to simulate the natural decay trend of concentration over time: ,in is the pollutant concentration at time t, is the initial concentration (the concentration at the source or entering the path segment), is the natural exponential term, is the attenuation coefficient, which is set based on volatility / photolysis reaction experience. is the propagation time of the segment. For solid particulate pollutants (such as construction dust and metal particles), the half-life is derived from the settling velocity and the volatility parameters of the material, and a segmented attenuation estimation model is constructed. Parameters are fitted based on the particle diameter, density, settling velocity under the meteorological environment, and resuspension probability to form a settling-residue function. The system divides each interaction path into several consecutive equidistant sub-segments and calculates the potential attenuation value of the pollutant in each segment. The attenuation value of each segment is estimated by the following formula: ,in is the potential attenuation value of the pollutant in the kth path, is the attenuation coefficient related to the pollutant material, is the length of the k-th path, is the average transport speed, is the local environmental sensitivity weight coefficient, It is the residual risk factor of pollution in a local area (dimensionless or linked to the pollution grade table).

[0067] This paper provides a formula for simulating the natural decay of concentration over time. This formula is based on the fact that gaseous pollutants undergo natural processes such as diffusion, photolysis, and oxidation during their propagation, resulting in an exponential decay of their concentration over time. This formula is derived from the first-order kinetics of pollutant concentration and its basic form is: ,in is the pollutant concentration at time t, is the propagation time of the segment, is the attenuation coefficient of the pollutant per unit time, which is set according to empirical parameters such as the volatility, photolysis reaction rate, and oxidation reaction rate of the pollutant, indicating that the concentration change rate of the pollutant per unit time is proportional to the current concentration. Solving this ordinary differential equation, we get the closed-form solution above. . The formula accurately reflects the physical behavior of volatile gaseous pollutants during the propagation process, such as natural diffusion, photolysis reaction, etc., and improves the scientific rationality of the model. A clear concentration change trend can be constructed through only three variables: initial concentration, propagation time and attenuation coefficient, which is conducive to parameter calibration and on-site deployment. The exponential model can be embedded in a path map or a pollution migration network to achieve segmented attenuation superposition and construct a pollution distribution map. The present invention provides a formula for calculating the attenuation value of each path, which can be applied to both gaseous pollutants and solid particulate pollutants, and reflects the intrinsic properties of the material through volatilization / photolysis parameters or sedimentation / residual parameters, thereby improving the universality of the model. The formula consists of two parts, one is the path propagation attenuation term , which expresses the “path stay time The intrinsic decay rate of pollutants” constitutes the first-order expansion result of exponential decay, where and The “path retention effect of speed control” is a function of time. At the micro level, the concentration of pollutants follows the first-order exponential decay law over time. , for a small time period (or weak attenuation condition), take its first-order Taylor expansion: , divide the path into paragraphs (It can also be expressed as the kth segment mentioned above), the propagation time of each segment is , only substitute the numerical value into the above formula to get the dominant term; the second is the environmental impact adjustment term This part represents the correction of the main item, reflecting the amplification or suppression of pollution attenuation under environmental conditions. is the residual pollution risk factor for a local area, a normalized value between 0 and 1, representing the residual accumulation effect caused by factors such as low wind speed, high obstruction, and dense pedestrian traffic. By estimating the attenuation value for each sub-path segment, a complete pollution path attenuation curve can be generated by superimposing each segment. This formula is a linear combination, eliminating the need for iterative solutions and making it suitable for rapid deployment and dynamic updates in large path networks.

[0068] Perform multi-step particle migration deduction on pollutant path data and preset electronic map data to obtain multi-step particle migration data; Specifically, the electronic map data of the coverage area is rasterized. Each grid cell is defined as a square grid cell with a side length of 50 meters. A particle release point is set at the midpoint or representative position of each path segment; the corresponding pollutant release mass is the residual pollutant mass obtained in the previous attenuation processing step. The pollutant release mass of each segment is proportionally converted into a number of simulated particles, set according to the minimum particle mass unit; at any grid position and at any time, the pollution concentration is expressed as: ,in is the pollutant concentration at time t and location (x, y), is the initial release mass, is pi, is the diffusion coefficient, which is set based on the empirical data of the example, and the unit is , is the diffusion time (from the start of release to the current moment), is the diffusion thickness, is an exponential function, is the horizontal coordinate of the current position, is the horizontal coordinate of the pollution source release position, is the ordinate of the current position, The vertical coordinate of the pollution source release location. With a set time step (e.g., 1 to 5 minutes), the system updates the pollution concentration value for each grid cell at every moment and records any concentration accumulation or threshold triggering behavior. Each update step is based on the particle diffusion results of the previous moment, forming a continuous time series of migration process data.

[0069] The present invention provides a method for calculating pollution concentration. To simulate the multi-step spatial migration process of pollutants in a path network, a two-dimensional Gaussian diffusion simulation is performed to express the diffusion concentration distribution of pollutants from the release point to the surrounding grid cells in an open environment. Through this diffusion model, the influence range of each pollution source can be simulated to provide support for pollution impact area assessment, risk warning and point monitoring. The formula consists of two parts: one is the intensity term The intensity level is controlled by the pollution intensity, and the overall amplitude is obtained by the diffusion coefficient, time coefficient and diffusion thickness (i.e. the thickness of the vertical impact layer, which can be set to the thickness of the near-ground layer (such as 1.5-2m) for surface propagation); the second is the exponential term , determines the shape and boundary of the spatial distribution. , Concentric concentration maps are constructed using the diffusion distance as the radius and the diffusion point as the center, suitable for local diffusion under the assumption of a uniform surface. An exponential function ensures that the concentration decays rapidly to near zero, ensuring physical plausibility and boundary closure. The unit combination of all parameters ensures that the results are in concentration units (kg / m³), meeting the engineering requirements of pollution simulation. Particle concentrations at multiple release points can be directly accumulated without solving partial differential equations.

[0070] Based on the multi-step particle migration data, the path overlap diffusion enhancement is performed to obtain the pollution exposure map data; Specifically, the system has obtained the pollution path, and each path has formed a corresponding pollution particle concentration migration data after multiple steps of particle migration deduction. The contribution weight of each path is set according to the residual pollution load after its attenuation. The residual pollution load can be calculated based on the total mass of pollutants in the path segment attenuation model. For example, the weight can be set to ,in For the The pollution contribution weight of each path, is the residual mass of pollutants at the end point, is the total number of paths participating in the superposition, is the path index variable, is the residual mass of pollutants at the end point of the jth path. The system performs weighted superposition of all particle migration data on the preset electronic map and structures the map to obtain the total pollution exposure distribution map, that is, the total pollution concentration on any grid cell is defined as: ,in The total pollution exposure concentration distribution map Pollution concentration values ​​at grid points, is the path index variable, is the total number of paths, For the The pollution contribution weight of each path, For the The path in The concentration of pollutant particles at .

[0071] The present invention provides a formula for calculating the contribution weight of each pollutant path on the same road section. The weight in the formula is obtained based on the normalization of the residual pollution load at the end of the path, and characterizes the contribution intensity of each path to the overall pollution exposure of a single location; the present invention provides a formula for calculating the total pollution concentration on any grid unit, which systematically superimposes the pollution contributions of multiple paths to form an overall pollution exposure map, avoiding the local deviation caused by single-path analysis; in actual situations, each path has an independent pollution diffusion area on the electronic map; the release points of different paths do not interfere with each other, and the diffusion of their pollution particles obeys the principle of linear superposition; the pollution contribution intensity of each path is positively correlated with the residual mass at its end point. Derived from the particle migration deduction process (such as Gaussian diffusion simulation), it determines the The pollution propagation range and concentration distribution of different paths in space are constructed to ensure the time scale consistency of the diffusion data of different paths. When using the unified reference time or the cumulative concentration or weighted average concentration within the specified time window, it is used to represent the stable pollution exposure value of path m to the spatial point (x, y), thereby avoiding the timing deviation caused by the difference in release timing of different paths; Characterize the contribution intensity of each pathway to the overall pollution exposure; It indicates the superposition of multiple pollution sources at this point, which is the result of weighted average; it reflects the enhanced diffusion of overlapping pollution, that is, when multiple paths intersect in the same area, the concentration will increase significantly. It can be pre-calculated and cached, and there is no need to re-simulate when weights are adjusted, which improves the system's computing efficiency; the mathematical structure meets distributed processing requirements and is suitable for large-scale map rendering or edge computing deployment.

[0072] Based on the pollution exposure map data, the digital twin receiving end model is simulated for pollution migration field-receiving end load to obtain pollutant load characteristic data.

[0073] Specifically, the system maps the two-dimensional grid units defined in the pollution exposure map to specific physical sub-units in the digital twin receiving end model. The mapping is established based on the internal structure of the receiving end to ensure that each grid area corresponds one-to-one or many-to-one to the key functional areas in the receiving end model (such as processing workshops, chemical pools, ventilation points, etc.). For each key unit mapped to, the system sets the upper limit of the acceptable pollutant exposure concentration within its unit time period. The system traverses each grid in the exposure map. If the grid concentration value is greater than the upper limit of the pollutant exposure concentration, the exposure impact period is marked as "unreachable", indicating that the unit cannot normally undertake the task of adding new pollutants during this period. For receiving units that do not exceed the exposure threshold, the receiving unit The current theoretical carrying capacity is , if the pollution exposure value of its associated grid cell is , the system dynamically calculates its adjusted carrying capacity through the following linear deduction model: ,in For receiving unit Pollutants At the moment Adjusted load-bearing capacity, For receiving unit Pollutants At the moment The theoretical carrying capacity of is the attenuation coefficient of the effect of exposure concentration on carrying capacity, is the total concentration of pollutants at the grid position (x,y) in the exposure map.

[0074] The present invention provides a linear exposure attenuation calculation formula for dynamically adjusting the pollutant load carrying capacity based on the linkage between the pollution exposure map and the digital twin receiving end model. The formula maps the pollution exposure map with the functional area of ​​the receiving end, and opens up the coupling path between the pollution migration simulation and the structural response simulation. The task acceptance capacity of each sub-unit is automatically reduced according to the real-time pollution exposure concentration, so that the system has the ability to dynamically schedule tasks based on the exposure situation. If the exposure concentration exceeds the preset threshold, the area is automatically set to the state of "unacceptable new pollutants", thereby enhancing the system's safety constraint capabilities under high pollution conditions. Among them It is determined by factors such as the receiving end structure, equipment type, and pollutant treatment capacity; it is the upper limit of the system's load under ideal conditions. It indicates the degree of weakening of receiving capacity by unit concentration; the formula adopts a linear subtraction structure, which is conducive to engineering implementation.

[0075] Optionally, the path risk avoidance control includes: Performing path risk extraction on the first solid waste matching model and the second solid waste matching model to obtain first path risk data and second path risk data respectively; Specifically, the system extracts the first solid waste matching model Matching model with the second solid waste The set of all paths in . For each path , the system divides it into several sub-segments , and quantify the risk of each sub-segment. The risk value of each path segment is calculated using the following weighted model: ,in For path segments The risk value, is the risk factor index, is the total number of risk factors supported by the system, The corresponding risk factor weights are trained and set based on the regional historical scheduling failure probability, legal and regulatory sensitivity level, and operation and maintenance safety standards. is the k-th risk factor in the path segment The value function on , for example is the traffic delay coefficient (based on the real-time congestion level); Air pollution sensitivity (e.g. concentration level); Mark crossing areas with high risks (such as those involving water, construction sites, and water sources).

[0076] The present invention provides a method for calculating the risk value of each path segment by weight, wherein the system divides it into several sub-segments at fixed distance intervals (or according to node distribution characteristics) , and the historical experience data corresponding to each sub-segment (such as the risk of traffic delay during congestion, air pollution sensitivity (such as Concentration level), and whether the route crosses an environmental protection control zone (i.e., high-risk area crossing indicators (e.g., water crossing, construction, water source areas)) are weighted and summed using preset weights to quantify risk. This formula provides a refined description of route-level risk, facilitating the incorporation of risk perception into solid waste dispatch routing planning. It also facilitates expansion and training adjustments, and weight parameters can be based on historical data fitting, expert experience, or dynamic learning, offering high flexibility.

[0077] constructing a path risk map based on the first path risk data and the second path risk data to obtain path risk map data; Specifically, the system first extracts turning points, key scheduling locations, grid boundary intersections, and other information from the path segments in the first and second path risk data, constructing a graph node set. Each node contains information about its path, coordinates, and whether it is an entrance to a sensitive area (such as a school or residential area). Based on this node set, the system identifies pairs of nodes with direct access relationships based on the path structure or geographic layer constraints. These pairs form the graph edge set, which includes distance, path segment risk, current congestion delay, and pollution exposure. A multidimensional attribute graph representation is used, or a multi-layered graph is constructed.

[0078] The path risk map data is processed to avoid the occurrence of solid waste matching models.

[0079] Specifically, based on the constructed path risk graph, a new avoidance optimization path is generated; the maximum allowable threshold of path risk R_max is set; if a path R(path)>R_max, it is considered a high-risk path and enters the heavy avoidance optimization process. , ant colony algorithm (ACO) or deep reinforcement learning (DRL) scheduling strategy network, setting the optimization goal to minimize the total path risk; ensuring the path length or time constraint; and giving priority to avoiding sensitive areas / pollution diffusion areas.

[0080] Optionally, S4 includes: S41. Extracting task scheduling units based on the solid waste matching model to obtain task scheduling unit data; Specifically, the input is the valid matching triples that have passed the screening in the solid waste matching model: ,in represents the i-th solid waste generation source; represents the jth receiving and processing terminal; It represents the transportation path between the source and the receiving point; it also includes the matched material type, available transportation capacity, pollution load information, and the scheduling time window. The system groups the matching triples according to the following key-value combination as the minimum execution granularity for task scheduling units: ,in Number the solid waste source station, is the receiving station number, For solid waste categories (such as construction waste, heavy metal waste, volatile organic compounds, etc.), It is the unique identifier of the transport route. For the time window interval allowed for arrival, a separate TEU entity is generated for each group. The system calculates the estimated arrival time based on the digital twin simulation results of the path and the receiving end, and based on the above integration, obtains the task scheduling unit data.

[0081] S42, performing a task splitting criterion on the task scheduling unit data to obtain task splitting data; Specifically, when a single task scheduling unit (TEU) cannot be completed within a single transportation task due to factors such as capacity, pollution restrictions, or time windows, it is split using multi-dimensional criteria to generate a set of sub-task units that meet the execution conditions. If the total mass or volume of solid waste exceeds the vehicle's carrying capacity, it needs to be split. The calculation method is as follows: ,in is the number of task splits under the vehicle load criterion, is the maximum value function, The mass and volume of solid waste corresponding to the task scheduling unit, is the vehicle's rated load, is the total volume of solid waste, is the vehicle's rated loading volume, When the pollution treatment capacity of the receiving end is constrained, the pollution load should be split according to the remaining carrying capacity: ,in is the number of splits under pollution load constraints, is the maximum value operation (pollutant category), is the load value of the pollutant k to be treated, is the remaining processing capacity of the receiving end j for pollutant k at time t. If the maximum receiving capacity of the receiving point (such as the gate or unloading point capacity) is insufficient to complete a scheduling task within a given arrival time window, it needs to be split: ,in is the number of splits under the time window limit, is the total mass of solid waste corresponding to the task unit, is the processing capacity per unit time of the gate (such as tons / hour), The width of the time window allowed for arrival. If there is a bridge or channel weight limit section in the matched path, and the TEU weight exceeds the weight limit value of any edge section of the path, the split process should be triggered. At this time, the record: ,in is the number of splits under the path weight limit, For solid waste quality, is the minimum weight limit of all segments in the path. is the weight limit of any edge segment.

[0082] The present invention aims to solve the practical problem that a task scheduling unit (such as a solid waste transport task) may not be fully executed under resource, path or time window constraints. It constructs a multi-dimensional splitting criterion model to calculate the minimum feasible number of subtask splits according to capacity constraints, pollution load constraints, arrival time window constraints and path weight constraints. For example, the present invention provides a capacity-limited splitting formula. If any dimension of mass or volume is overloaded, the more serious one will be split to ensure that the vehicle can fit. If the task is too large, the time window is too short or the efficiency of the gatekeeper is too low, it is necessary to split multiple subtasks and arrange them in staggered order. If the weight limit of a bridge or channel in the solid waste transportation route is lower than the task load, it must be split in advance to prevent it from being impassable. A single transportation or processing task must meet the following requirements: the transportation can be executed, the reception is not overloaded, the arrival is not congested, and the path does not exceed the limit; if any of the conditions is not met, the task must be disassembled (iteratively disassembled according to fixed parameters (proportional disassembly) until the conditions are met) to reduce the unit load. Each dimension is regarded as a "hard constraint", and the corresponding resource capacity is used to reversely infer the maximum allowable load; if the actual load exceeds the capacity, it is necessary to calculate the minimum number of times to complete → the number of splits; rounding up is used to ensure that the task can actually be completed. The number of splits calculated by all criteria is summarized and the maximum value is uniformly taken to ensure that all restrictions are met; the corresponding number of subtasks can be generated and handed over to subsequent scheduling.

[0083] S43, performing risk reorganization on the task splitting data to obtain task reorganization data; Specifically, the system determines the reorganization by constructing a feasible task fusion graph, where a node represents each sub-TEU to be merged; an edge represents a potential merging relationship between two sub-TEUs that meets the fusion conditions. When two sub-TEUs meet all of the following conditions simultaneously, a mergeable edge is established for them in the graph structure; there must be a sufficient path sharing ratio between the path segments used by the two sub-TEUs, that is, their path overlap must meet the following requirements: ,in is the preset lower limit threshold for path overlap (e.g., 0.6). The difference in the estimated time of arrival (ETA) of the two sub-TEUs should be less than the synchronization tolerance value (the maximum allowable range of time difference between different tasks arriving at the receiving end). The receiving entrances of the two sub-TEUs should be the same or switchable (i.e., they can serve as alternative entrances and will not cause path conflicts or congestion) to meet the spatial conditions for merging and unloading. The total amount of pollutant load of the two sub-TEUs after merging must not exceed the residual pollution carrying capacity of the receiving end at the corresponding time: ,in For the pollutants of the merged subtasks The total load, For the receiving end Pollutants exist The total combined mass must not exceed the rated load of the available vehicles: ,in is the total mass after merging, is the rated load of the vehicle. Evaluate all mergeable edges and select the merging solutions with positive benefits: ,in For positive return data, To reduce the dispatch mileage through merging, The weighted data of the risk increase is expressed in km / risk coefficient, and the range is 0.3-0.6, or it can be obtained by regression calculation based on empirical values. is the increase in path risk after merging, The weight data of the waiting time increment is in km / waiting time, and the selection range is 0.1-0.5, or it can be obtained by regression calculation based on empirical values. The system calculates the waiting time increment for all queues after merging. The candidate edges are processed first, and the maximum matching algorithm or heuristic greedy strategy is used to gradually perform merging optimization.

[0084] This invention optimizes the execution efficiency of split tasks in solid waste transportation scheduling. It proposes a reorganization calculation based on the construction of a task fusion feasible graph and a benefit-driven reorganization criterion. This method improves overall transportation efficiency while ensuring scheduling feasibility. By merging similar subtasks, vehicle load and receiving-end load utilization are increased, reducing resource waste. By identifying task pairs with overlapping paths and temporal and spatial proximity for parallel scheduling, mileage savings and task merging are achieved. Only when all constraints are met does the system create a mergeable edge for that task pair in the task fusion graph. A positive formula for merging edges is provided: benefit = cost savings - risk cost - waiting cost. A positive result indicates that the merge is worthwhile. A graph structure is used to model the possibility of merging, ensuring that all merge actions comply with scheduling, path, and space constraints. A multi-factor benefit evaluation function, leveraging the concept of net benefit in economics, is constructed to achieve a joint balance of cost, risk, and time. The merging benefit is determined by ensuring that the total dispatch distance of the two original task routes exceeds the new merged task route. Risk and waiting time, as non-negligible negative impacts, are controlled through weighted penalty terms. A task fusion relationship graph is constructed based on the graph theory model, which facilitates the introduction of optimization algorithms such as maximum matching and greedy strategies to quickly solve the optimal merging solution.

[0085] S44. Perform fusion feasibility screening on the task reorganization data to obtain solid waste scheduling data.

[0086] Specifically, the system performs the following four types of hard checks for each task to be scheduled. All checks must pass before the dispatch plan can be generated. These checks include ensuring that the assigned vehicle's load, volume, axle load, and dimensions are within vehicle manufacturing specifications and road control regulations and must not exceed these limits. Each task's estimated time of arrival (ETA) must fall within the open window set by the receiving gate. The system assesses the gate's throughput capacity based on the concentration of tasks within the ETA time period. The total mass of all tasks within the ETA window must not exceed the gate's processing limit per unit time. The material categories and contamination factors included in each transport task must match the whitelist configured at the receiving end or gate to avoid entry restrictions due to unauthorized substances. The pollutant load of all transport tasks must not exceed the receiving end's remaining pollution carrying capacity at the ETA time, ensuring that processing capacity is not exceeded. If a transport task contains specially regulated substances (such as asbestos and volatile organic compounds (VOCs)), verification of environmental permit status is required. The scheduling path's risk level and probability of violation must not exceed preset limits to ensure task safety and control. Each task must be completed no later than the customer's agreed-upon deadline. If the system integrates driver schedule data, it must also ensure that drivers' work hours and rest intervals comply with transportation safety regulations, and that overtime is not permitted. For tasks that pass these mandatory checks, the system automatically generates dispatch instructions encompassing the following elements: vehicle assignment, loading and unloading sequence scheduling, and dispatch schedule construction.

[0087] Optionally, the present application further provides a digital twin-driven solid waste real-time matching optimization system for executing the digital twin-driven solid waste real-time matching optimization method described above, wherein the digital twin-driven solid waste real-time matching optimization system comprises: The source-end twin modeling module is used to obtain construction solid waste source data and perform solid waste source twin modeling based on the construction solid waste source data to obtain a digital twin source model; The receiving end twin modeling module is used to obtain the construction solid waste receiving end data and perform receiving point twin modeling based on the construction solid waste receiving end data to obtain a digital twin receiving end model; The solid waste matching modeling module is used to match the digital twin source model and the digital twin receiving end model to obtain a solid waste matching model; The task splitting and fusion scheduling module is used to perform task splitting and fusion scheduling according to the solid waste matching model to obtain solid waste scheduling data.

[0088] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, the scope of the present invention is limited by the attached application documents rather than the above description, and it is intended that all changes that fall within the meaning and scope of equivalent elements of the application documents are included in the present invention.

[0089] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A digital twin driven solid waste real-time matching optimization method, characterized in that: The method comprises: S1. Obtain construction solid waste source data, and perform solid waste source twin modeling based on the construction solid waste source data to obtain a digital twin source model; S2. Obtain the construction solid waste receiving end data, and perform receiving point twin modeling based on the construction solid waste receiving end data to obtain a digital twin receiving end model; S3. Match the digital twin source model and the digital twin receiving model to obtain a solid waste matching model; S4. Perform task splitting and fusion scheduling based on the solid waste matching model to obtain solid waste scheduling data.

2. The method according to claim 1, characterized in that S1 includes: Collect basic data on sources of construction solid waste to obtain basic data on solid waste sources; Standardize the attributes based on the basic data of solid waste sources to obtain the source data of construction solid waste; Construct digital twin objects based on construction solid waste source data to obtain digital twin data of solid waste source; The scheduling accessibility evolution simulation is performed based on the digital twin data of the solid waste source to obtain the digital twin source model.

3. The method according to claim 1, characterized in that S2 include: Acquire construction solid waste receiving end data, and extract solid waste treatment features based on the construction solid waste receiving end data to obtain solid waste treatment feature data; Extract pollutant limits based on construction solid waste receiving end data to obtain pollutant limit data; Construct digital twin objects based on the data of the construction solid waste receiving end to obtain the digital twin data of the solid waste receiving end; The digital twin data of the solid waste receiving end is run and evolved according to the solid waste treatment characteristic data and pollutant limit data to obtain the digital twin receiving end model.

4. The method according to claim 1, characterized in that S3 include: Perform cross-batch collaborative matching based on the digital twin source model and the digital twin receiving model to obtain the first solid waste matching model; Matching the polluted building solid waste is performed based on the digital twin source model and the digital twin receiving model to obtain a second solid waste matching model; Path risk avoidance control is performed according to the first solid waste matching model and the second solid waste matching model to obtain a solid waste matching model.

5. The method according to claim 4, characterized in that The cross-batch collaborative matching includes: Extract collaborative entities based on the digital twin source model and the digital twin receiver model to obtain collaborative entity data; Perform reachable entity division and splittable entity division based on collaborative entity data to obtain reachable entity data and splittable entity data respectively; According to the digital twin receiving end model, a collaborative batch path diagram is generated for the reachable entity data and the splittable entity data to obtain the first solid waste matching model.

6. The method according to claim 5, characterized in that The reachability entity division includes: Performing hierarchical road network path processing based on collaborative entity data and preset electronic map data to obtain hierarchical road network path data; Constructing a multi-level road network graph based on the hierarchical road network path data to obtain multi-level road network graph data; Process the multi-level road network data with source group requirements to obtain path layer data; Perform fusion path traffic reachability extraction on the path stacking data to obtain fusion path traffic data; Perform convolution processing on the fused path traffic data to obtain the peak window data that can be combined; According to the digital twin receiving end model, the multi-entry path assignment conflict of the peak window data that can be spliced ​​is carried out to obtain the reachability entity data.

7. The method according to claim 5, characterized in that The matching of polluted construction solid waste includes: Extract pollutant load characteristics based on the digital twin source model and the digital twin receiving model to obtain pollutant load characteristic data; Performing receiving-end pollution load processing according to pollutant load characteristic data to obtain receiving-end pollution load data; Perform pollution migration simulation on the digital twin source model and the digital twin receiving model based on the pollution carrying data of the receiving end to obtain pollution migration data; According to the pollution migration data, the digital twin source model and the digital twin receiving model are marked with pollution solid waste matching to obtain a second solid waste matching model; The pollutant load feature extraction includes: Extract pollutant data based on the digital twin source model to obtain pollutant data; Extract interaction paths based on the digital twin source model and the digital twin receiver model to obtain interaction path data; Perform pollution potential attenuation processing on the interactive path data according to the pollutant data to obtain the pollutant path data; Perform multi-step particle migration deduction on pollutant path data and preset electronic map data to obtain multi-step particle migration data; Based on the multi-step particle migration data, the path overlap diffusion enhancement is performed to obtain the pollution exposure map data; Based on the pollution exposure map data, the digital twin receiving end model is simulated for pollution migration field-receiving end load to obtain pollutant load characteristic data.

8. The method according to claim 4, characterized in that The path risk avoidance control includes: Performing path risk extraction on the first solid waste matching model and the second solid waste matching model to obtain first path risk data and second path risk data respectively; constructing a path risk map based on the first path risk data and the second path risk data to obtain path risk map data; The path risk map data is processed to avoid the occurrence of solid waste matching models.

9. The method according to claim 1, characterized in that S4 includes: Extract task scheduling units based on the solid waste matching model to obtain task scheduling unit data; Perform task splitting criterion on task scheduling unit data to obtain task splitting data; Perform risk reorganization on the task splitting data to obtain task reorganization data; The task reorganization data is screened for fusion feasibility to obtain solid waste scheduling data.

10. A digital twin driven solid waste real-time matching optimization system, characterized in that: For executing the digital twin driven solid waste real-time matching optimization method according to claim 1, the digital twin driven solid waste real-time matching optimization system comprises: The source-end twin modeling module is used to obtain construction solid waste source data and perform solid waste source twin modeling based on the construction solid waste source data to obtain a digital twin source model; The receiving end twin modeling module is used to obtain the construction solid waste receiving end data and perform receiving point twin modeling based on the construction solid waste receiving end data to obtain a digital twin receiving end model; The solid waste matching modeling module is used to match the digital twin source model and the digital twin receiving end model to obtain a solid waste matching model; The task splitting and fusion scheduling module is used to perform task splitting and fusion scheduling according to the solid waste matching model to obtain solid waste scheduling data.

Images