Real-time monitoring optimization method and device for solid waste collection, transportation and sorting ERP system

Abstract

The invention relates to the technical field of solid waste sorting scheduling, in particular to a real-time monitoring optimization method and device for a solid waste collection, transportation and sorting ERP system. The method comprises the following steps: obtaining a real-time solid waste sorting log based on a solid waste collection, transportation and sorting ERP system; solid waste carrying vehicle tracking is carried out on the real-time solid waste sorting log, and a carrying track distribution visual view is constructed; acquiring an omnibearing monitoring image of a real-time sorting site; equipment sorting behavior visual identification is carried out on the real-time sorting site omnibearing monitoring image, dynamic sorting evolution is carried out, and a dynamic sorting twinborn model is constructed; carrying out multi-time-point solid waste sorting simulation on the dynamic sorting twinborn model, carrying out sorting load demand prediction, and generating a sorting load demand prediction value; and carrying out vehicle load calculation on the sorting load demand prediction value one by one, and then carrying out dynamic vehicle scheduling decision making to obtain a dynamic vehicle scheduling strategy. According to the invention, efficient and real-time solid waste sorting scheduling optimization is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of solid waste sorting and scheduling, and in particular to a real-time monitoring optimization method and device for a solid waste collection, transportation and sorting ERP system. Background Art

[0002] The collection, transportation and sorting of solid waste are important links in modern urban and industrial waste management systems, which directly affect resource recovery rates and environmental protection effects. With the acceleration of urbanization and the improvement of environmental protection requirements, traditional solid waste collection, transportation and sorting systems can no longer meet the growing demand for waste treatment. Traditional waste collection, transportation and sorting methods rely on manual scheduling and static process management, which often leads to problems such as low equipment utilization, low sorting efficiency and energy waste. Especially in large-scale and complex waste flow environments, manual scheduling not only has problems of low efficiency and slow response, but is also prone to misjudgment due to human factors, which in turn affects the sorting quality and the normal operation of the production line. Therefore, in order to improve the overall performance of the system and reduce labor costs, there is an urgent need for an optimization method that can dynamically adjust sorting tasks, intelligently schedule resources, and monitor system status in real time. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a real-time monitoring optimization method and device for a solid waste collection, transportation and sorting ERP system to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a real-time monitoring optimization method for a solid waste collection, transportation and sorting ERP system, comprising the following steps: Step S1: obtaining a real-time solid waste sorting log based on the solid waste collection, transportation and sorting ERP system; tracking the solid waste transport vehicles in the real-time solid waste sorting log, and constructing a visual view of the transport trajectory distribution; Step S2: Obtaining a full-scale monitoring image of the real-time sorting site; performing visual recognition of the equipment sorting behavior on the full-scale monitoring image of the real-time sorting site, and performing dynamic sorting evolution to construct a dynamic sorting twin model; Step S3: Perform multi-time point solid waste sorting simulation on the dynamic sorting twin model, and perform sorting load demand forecasting to generate a sorting load demand forecast value; Step S4: Calculate the load of each vehicle for the sorting load demand forecast value, and then make a dynamic vehicle scheduling decision to obtain a dynamic vehicle scheduling strategy; Step S5: performing vehicle scheduling evolution analysis on the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy, and performing dynamic path planning, thereby constructing a dynamic planning path; Step S6: Perform deep path planning optimization on the dynamic planning path, conduct cloud-based intelligent response analysis, and build an intelligent solid waste sorting and scheduling model.

[0005] The present invention achieves real-time monitoring and recording of the solid waste sorting process by acquiring real-time solid waste sorting logs, which helps to discover and solve problems, tracks vehicles in solid waste sorting logs, builds a visual view of the transport trajectory distribution, and provides managers with the ability to understand vehicle locations and sorting conditions in real time. It also acquires all-round monitoring images of the sorting site in real time, performs visual recognition of equipment sorting behavior, helps monitor the sorting process, improves production efficiency and quality, establishes a dynamic sorting twin model, simulates and evolves the sorting process, helps optimize the sorting process, improves resource utilization and reduces errors, performs multi-time point solid waste sorting simulations, predicts sorting load requirements, helps to reasonably arrange resources and manpower, improves sorting efficiency, generates sorting load demand prediction values, and helps optimize solid waste sorting scheduling. , reduce idle time and reduce costs, calculate the load of each vehicle according to the load demand forecast value, formulate dynamic vehicle scheduling strategies, improve vehicle utilization and transportation efficiency, dynamic vehicle scheduling decisions help reduce transportation costs, reduce waiting time, and improve distribution efficiency. Combined with dynamic vehicle scheduling strategies, conduct vehicle scheduling evolution analysis, optimize vehicle scheduling plans, improve transportation efficiency, perform dynamic path planning, build dynamic planning paths, reduce driving distance and time, and increase delivery speed. Deeply plan and optimize dynamic planning paths, improve the accuracy and efficiency of path planning, reduce transportation costs, conduct cloud-based intelligent response analysis, build an intelligent solid waste sorting scheduling model, improve the intelligence level and response speed of the system, and optimize solid waste sorting scheduling path decisions.

[0006] Preferably, step S1 comprises the following steps: Step S11: obtaining a real-time solid waste sorting log based on the solid waste collection, transportation and sorting ERP system; Step S12: performing data cleaning and optimization on the real-time solid waste sorting log to obtain an optimized real-time sorting log; Step S13: Tracking the solid waste transport vehicles for the optimized real-time sorting log to generate vehicle transport track state characteristic data; Step S14: performing a transportation track distribution analysis on the vehicle transportation track state characteristic data to generate real-time transportation track distribution data of the sorting station; Step S15: Perform a visual reconstruction of the transport trajectory distribution data of the sorting station in real time to construct a transport trajectory distribution visualization view.

[0007] The present invention can help monitor the sorting process by acquiring the solid waste sorting log in real time, timely discover abnormal situations and handle them, make decisions based on real-time data can improve the reaction speed, optimize the sorting operation process, and reduce resource waste, data cleaning and optimization can improve data quality, reduce errors and noise, and ensure the accuracy of subsequent analysis and decision-making, the optimized real-time sorting log is easier to analyze and understand, and provides a more reliable data basis for subsequent steps, and the real-time monitoring and analysis of vehicle carrying conditions can be achieved by tracking vehicles in the real-time sorting log and generating trajectory state feature data, and the trajectory state feature data is helpful to understand the vehicle carrying conditions, and provides a basis for subsequent path planning and scheduling decisions, and analyzing the vehicle carrying trajectory state feature data can reveal the carrying conditions and bottlenecks of the sorting station, and provide guidance for optimizing the sorting operation, and generating real-time carrying trajectory distribution data is helpful to fully understand the operation of the sorting station, and provide a reference for path planning and vehicle scheduling, and by visually reconstructing the real-time carrying trajectory data of the sorting station, the manager can intuitively understand the vehicle carrying conditions, make adjustments and decisions in time, and the visual view is helpful to discover potential problems and optimization opportunities, and improve the accuracy and efficiency of the sorting scheduling path decision of solid waste.

[0008] Preferably, the specific steps of step S13 are: Identify real-time sorting jobs based on optimized real-time sorting logs; Track solid waste transport vehicles for real-time sorting operations and extract vehicle status parameters; Calculate the solid waste load capacity of the transport vehicle based on the state parameters of the transport vehicle to generate the solid waste load capacity of the vehicle; Calculate the carrying frequency within the cycle for real-time sorting operations to generate the carrying frequency of the vehicle; Carry out load analysis based on the vehicle's transportation frequency and the vehicle's solid waste load to obtain the vehicle's load data; Analyze the vehicle transport trajectory of real-time sorting operations to obtain the vehicle operation transport trajectory; The vehicle's load data and vehicle operation trajectory are mined to generate vehicle trajectory status feature data.

[0009] The present invention realizes accurate identification of real-time sorting operations by optimizing real-time sorting logs, which helps to monitor the sorting process and improve operating efficiency. Real-time operation identification can help managers to timely understand the current operation status, make timely adjustments and decisions, and improve overall production efficiency. By tracking solid waste transport vehicles and extracting vehicle status parameters, real-time monitoring and analysis of vehicle position, speed and other information can be achieved. Extracting status parameters helps to understand the vehicle operation status and provide data support for subsequent load calculation and analysis. By calculating the carrying frequency, the number of times the vehicle is carried within a cycle can be understood, which helps to evaluate the vehicle's operating efficiency and utilization rate. The carrying frequency data helps to adjust the operation plan, improve transportation efficiency, reduce empty or fully loaded waiting time, reduce costs, and increase load. Load analysis combined with transportation frequency and load data can optimize vehicle load distribution and improve loading efficiency and transportation efficiency. The analysis results can help adjust transportation strategies, reduce empty or overloaded situations, and optimize the transportation process of solid waste. Vehicle transportation trajectory analysis can help understand the vehicle's driving route and operation trajectory, and discover potential optimization space and problem points. Through trajectory analysis, path planning can be optimized, driving distance and time can be reduced, and transportation efficiency and service level can be improved. By mining the characteristic data of the transportation trajectory status, the key characteristics and laws of the vehicle transportation process can be deeply understood, providing more basis for decision-making. The transportation trajectory status data helps to optimize vehicle scheduling and route planning, and improve the accuracy and effectiveness of solid waste sorting and scheduling path decisions.

[0010] Preferably, the specific steps of step S2 are: Step S21: obtaining a real-time all-round monitoring image of the sorting site based on the solid waste collection, transportation and sorting ERP system; Step S22: Perform visual recognition of equipment sorting behavior on the real-time sorting site omnidirectional monitoring image to extract real-time equipment sorting behavior data; Step S23: performing sorting process logic analysis on the real-time equipment sorting behavior data to generate sorting site sorting behavior logic data; Step S24: Calculate the solid waste sorting accumulation volume for the optimized real-time sorting log, and extract the real-time solid waste sorting accumulation volume; Step S25: analyzing the time series change of the accumulation amount of the optimized real-time sorting log to generate solid waste accumulation amount change data; Step S26: Dynamically sort and evolve the solid waste accumulation change data and the sorting behavior logic data at the sorting site to build a dynamic sorting twin model.

[0011] The present invention can provide an all-round view of the entire sorting site through real-time monitoring images, which is helpful for monitoring the progress of operations and equipment status. The real-time monitoring images provide an intuitive data source for subsequent behavior recognition and data analysis, which helps real-time monitoring and decision-making. Through visual recognition of sorting behavior, the operating status and efficiency of the equipment can be monitored in real time, which helps to discover potential problems and deal with them in a timely manner. Extracting equipment sorting behavior data can provide data support for subsequent process optimization and equipment management, improve production efficiency and quality. Analyzing equipment sorting behavior data can reveal the logical relationship and bottleneck of the sorting process, which helps to optimize the process flow and improve efficiency. Generating sorting behavior logic data can provide a basis for job scheduling and path decision-making, optimize the sorting of solid waste. During the sorting process, by calculating the accumulation of solid waste, we can understand the waste situation at the sorting site, help adjust the operation plan and resource allocation, and extract real-time solid waste sorting accumulation data to help monitor operation efficiency and quality and ensure the smooth progress of the operation. Analyzing the time series changes in the accumulation amount can reveal the rules and trends of the accumulation amount, and provide more accurate data support for operation scheduling and resource management. Generating accumulation amount change data can help to adjust the operation plan in time and avoid problems caused by excessive or small accumulation. Building a dynamic sorting twin model can combine equipment behavior data and accumulation amount change data to simulate the dynamic evolution of the sorting process. The dynamic sorting twin model can help predict future operation conditions, optimize scheduling strategies, and improve sorting efficiency and resource utilization.

[0012] Preferably, step S3 specifically comprises the following steps: Step S31: performing multi-time point solid waste sorting simulation on the dynamic sorting twin model, thereby generating solid waste sorting simulation data at multiple time points; Step S32: performing statistics on the solid waste inflow and outflow of the solid waste sorting simulation data at multiple time points to obtain the solid waste inflow and outflow of the sorting station; Step S33: performing sorting load demand analysis on the inflow and outflow of solid waste at the sorting station, thereby generating solid waste sorting load demand data; Step S34: performing long-term evolution of the input and output volume of solid waste at the sorting station, thereby obtaining solid waste input and output volume evolution trend data; Step S35: Use the solid waste inflow and outflow trend evolution data to predict the solid waste sorting load demand data, and generate a sorting load demand prediction value.

[0013] The present invention can simulate the sorting conditions in different time periods through the solid waste sorting simulation at multiple time points, which helps to understand the changes and laws in the solid waste sorting process. The solid waste sorting simulation data generated at multiple time points is helpful to evaluate the sorting efficiency and resource utilization at different times, and provide a reference for scheduling decisions. The statistics of the inflow and outflow of solid waste can accurately understand the flow of solid waste in the sorting station, and help to grasp the real-time data of solid waste management. The inflow and outflow data of solid waste are helpful to analyze the operation status and load of the sorting station, and provide a basis for resource allocation and job arrangement. By analyzing the inflow and outflow of solid waste in the sorting station, the load demand of the sorting station can be evaluated, which helps to reasonably arrange job plans and resources. Configuration, generating solid waste sorting load demand data helps to optimize the operating efficiency of the sorting station and improve the overall benefits of the sorting operation. Analyzing the long-term change trend of solid waste inflow and outflow can reveal the development trend and law of solid waste management and provide a reference for future planning. Obtaining the solid waste inflow and outflow trend evolution data helps to predict the load situation and resource demand of the sorting station and help formulate long-term development strategies. Using the solid waste inflow and outflow trend evolution data to predict the solid waste sorting load demand can plan resources and work arrangements in advance and avoid potential bottlenecks and problems. Generating sorting load demand forecast values ​​helps to optimize the sorting scheduling path decision and ensure the efficient operation of the sorting station and the effective treatment of solid waste.

[0014] Preferably, the specific steps of step S4 are: Step S41: Calculate the solid waste carrying capacity based on the sorting load demand forecast value, thereby extracting the solid waste carrying capacity forecast value of the sorting station; Step S42: performing vehicle sorting scheduling simulation on the dynamic sorting twin model based on the predicted value of the solid waste carrying capacity of the sorting station, and extracting sorting scheduling simulation data; Step S43: Calculating the load of each vehicle on the sorting scheduling simulation data, thereby generating a load value for each vehicle; Step S44: performing vehicle dispatch demand analysis according to the load value of each vehicle to generate transport vehicle dispatch demand data; Step S45: Perform dynamic vehicle scheduling decisions on the transport vehicle scheduling demand data to obtain a dynamic vehicle scheduling strategy.

[0015] The present invention can accurately evaluate the solid waste carrying capacity of the sorting station by calculating the solid waste carrying capacity of the sorting load demand prediction value, help to reasonably arrange transportation resources, extract the solid waste carrying capacity prediction value of the sorting station to help optimize the transportation plan, ensure the timely and efficient transportation of solid waste, simulate the scheduling of different vehicles at the sorting station through vehicle sorting scheduling simulation, help evaluate the effects of different scheduling strategies, extract sorting scheduling simulation data to help optimize the vehicle scheduling plan, improve transportation efficiency and reduce costs, calculate the load of each vehicle one by one to accurately evaluate the carrying capacity of each vehicle, help to reasonably arrange vehicle loading tasks, generate the load value of each vehicle to help optimize the vehicle loading plan, ensure that the vehicle safely and efficiently transports solid waste, perform vehicle scheduling demand analysis according to the load value of each vehicle to evaluate the vehicle scheduling demand and optimize the scheduling plan, generate the transport vehicle scheduling demand data to help reasonably arrange the vehicle transportation tasks, improve transportation efficiency and reduce costs, perform dynamic vehicle scheduling decisions on the transport vehicle scheduling demand data, flexibly adjust the vehicle transportation plan according to real-time conditions, and obtain a dynamic vehicle scheduling strategy to help optimize the vehicle scheduling arrangement, improve transportation efficiency and response speed.

[0016] Preferably, the specific steps of step S5 are: Step S51: performing vehicle scheduling evolution analysis on the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy to obtain real-time vehicle scheduling transport trajectory evolution data; Step S52: identifying the path sorting points of the real-time vehicle dispatching transport trajectory evolution data, and marking all sorting stations of the transport trajectory; Step S53: Analyze the optimal transport path sequence of all sorting sites on the transport track to obtain optimal transport path sequence data; Step S54: Perform dynamic path planning based on the optimal transport route sequence data, thereby constructing a dynamic planning path.

[0017] The present invention can monitor vehicle scheduling in real time and help discover potential problems by performing vehicle scheduling evolution analysis on the visualization view of the transport trajectory distribution. Obtaining real-time vehicle scheduling transport trajectory evolution data is helpful to timely adjust the vehicle scheduling strategy and improve transportation efficiency and punctuality. Marking all sorting sites on the transport trajectory can help determine the key nodes passed by the vehicle and optimize the transport path planning of the sorting sites. Identifying the sorting sites is helpful to improve the visualization effect of the transport trajectory and facilitate monitoring and adjustment of the vehicle's transportation route. Performing site optimal transport path sequence analysis on all sorting sites on the transport trajectory can find the best transportation route, reduce the vehicle's empty travel and reduce costs. Obtaining the optimal transport path sequence data is helpful to optimize the vehicle's transportation path, improve transportation efficiency and save resources. Dynamic path planning based on the optimal transport path sequence data can adjust the vehicle's transportation route according to real-time conditions, improve transportation flexibility and efficiency, and construct a dynamic planning path is helpful to optimize the vehicle scheduling strategy, reduce transportation time and cost, and improve service quality.

[0018] Preferably, the specific steps of step S6 are: Step S61: performing deep path planning optimization on the dynamic planning path and constructing a dynamic path optimization strategy; Step S62: Conduct collaborative scheduling learning on the dynamic path optimization strategy and the dynamic vehicle scheduling strategy to construct a collaborative sorting scheduling strategy; Step S63: Perform cloud-based intelligent response analysis on the collaborative sorting and scheduling strategy to build an intelligent solid waste sorting and scheduling model; Step S64: Perform real-time sorting monitoring and optimization operations based on the intelligent solid waste sorting scheduling model.

[0019] The present invention can further improve the accuracy and efficiency of path planning by performing deep path planning optimization on the dynamically planned path, reduce unnecessary mileage and time waste, construct a dynamic path optimization strategy that helps optimize vehicle scheduling plans, improve transportation efficiency, and reduce costs, and collaborative scheduling learning between the dynamic path optimization strategy and the dynamic vehicle scheduling strategy can achieve a more intelligent vehicle scheduling plan, improve the adaptability and flexibility of the system, and construct a collaborative sorting scheduling strategy that helps optimize the overall sorting scheduling process, improve transportation efficiency and service quality, and perform cloud-based intelligent response analysis on the collaborative sorting scheduling strategy to achieve real-time scheduling optimization and decision support, improve response speed and accuracy, and construct an intelligent solid waste sorting scheduling model that helps realize intelligent management of sorting scheduling, improve efficiency and reduce operating costs, and perform instant sorting monitoring and optimization operations based on the intelligent solid waste sorting scheduling model to achieve real-time monitoring and adjustment of the sorting process, improve operational efficiency and accuracy, and real-time sorting monitoring and optimization operations help to promptly discover and solve problems, ensure the smooth progress of sorting operations, and further improve overall efficiency and quality.

[0020] In this specification, a real-time monitoring and optimization device for a solid waste collection, transportation and sorting ERP system is provided, which is used to execute the real-time monitoring and optimization method for the solid waste collection, transportation and sorting ERP system as described above, including: The transport track distribution module is used to obtain real-time solid waste sorting logs based on the solid waste collection, transportation and sorting ERP system; track the solid waste transport vehicles based on the real-time solid waste sorting logs and build a visual view of the transport track distribution; The dynamic sorting evolution module is used to obtain all-round monitoring images of the real-time sorting site; perform visual recognition of the equipment sorting behavior on the all-round monitoring images of the real-time sorting site, and perform dynamic sorting evolution to build a dynamic sorting twin model; The load demand prediction module is used to simulate the solid waste sorting at multiple time points on the dynamic sorting twin model, and to predict the sorting load demand and generate the sorting load demand prediction value; The vehicle dispatch decision module is used to calculate the vehicle load for each vehicle based on the sorting load demand forecast value, and then make dynamic vehicle dispatch decisions to obtain a dynamic vehicle dispatch strategy; The path planning module is used to analyze the vehicle scheduling evolution of the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy and perform dynamic path planning to construct a dynamic planning path; The intelligent sorting and scheduling module is used to perform deep path planning optimization on the dynamically planned path, conduct cloud-based intelligent response analysis, and build an intelligent solid waste sorting and scheduling model.

[0021] The present invention acquires real-time solid waste sorting logs and tracks solid waste transport vehicles to construct a visual view of transport trajectory distribution, which can monitor and track the real-time position of vehicles, help optimize vehicle scheduling, and improve transportation efficiency. The visual view helps to promptly discover potential problems and bottlenecks, improve the level of visual management of solid waste sorting operations, reduce errors and improve accuracy. By building a dynamic sorting twin model through all-round monitoring images of the real-time sorting site and visual recognition of equipment sorting behavior, it can realize real-time monitoring and analysis of the situation on the sorting site and improve the intelligence of the sorting operation. The dynamic sorting evolution module helps to adjust the sorting strategy according to the real-time situation, improve operation efficiency and accuracy, and optimize the sorting process. Through multi-time point solid waste sorting simulation and load demand prediction, it can help predict the sorting load demand, optimize vehicle load planning, reduce empty driving, and save costs. The application of the prediction module can improve transportation Efficiency, avoid waste of resources, and improve the accuracy of the overall transportation plan. Vehicle-by-vehicle load calculation and dynamic vehicle scheduling decisions can adjust the vehicle scheduling strategy according to actual conditions, improve transportation efficiency and load balance, and reduce operating costs. Dynamic vehicle scheduling decisions help to achieve instant response and adjustment, and improve the flexibility and adaptability of vehicle scheduling. Through vehicle scheduling evolution analysis and dynamic path planning to build a dynamic planning path, you can optimize the vehicle's transportation route, improve transportation efficiency and save resources. The establishment of a dynamic planning path helps to optimize the vehicle scheduling plan, reduce transportation time and cost, and improve service quality. Deep planning optimization and cloud-based intelligent response analysis of the dynamic planning path, and the construction of an intelligent solid waste sorting and scheduling model can improve the system's intelligent management level and optimize sorting and scheduling decisions. The application of the intelligent sorting and scheduling module helps to achieve automated scheduling and optimization, and improve the efficiency and quality of the overall sorting operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of the steps of a real-time monitoring optimization method for a solid waste collection, transportation and sorting ERP system according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0024] The example of this application provides a method and device. The execution subjects of the method and device include but are not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of this application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0025] See also Figures 1 to 4 The present invention provides a real-time monitoring optimization method for a solid waste collection, transportation and sorting ERP system, and the real-time monitoring optimization method for a solid waste collection, transportation and sorting ERP system comprises the following steps: Step S1: obtaining a real-time solid waste sorting log based on the solid waste collection, transportation and sorting ERP system; tracking the solid waste transport vehicles in the real-time solid waste sorting log, and constructing a visual view of the transport trajectory distribution; Step S2: Obtaining a full-scale monitoring image of the real-time sorting site; performing visual recognition of the equipment sorting behavior on the full-scale monitoring image of the real-time sorting site, and performing dynamic sorting evolution to construct a dynamic sorting twin model; Step S3: Perform multi-time point solid waste sorting simulation on the dynamic sorting twin model, and perform sorting load demand forecasting to generate a sorting load demand forecast value; Step S4: Calculate the load of each vehicle for the sorting load demand forecast value, and then make a dynamic vehicle scheduling decision to obtain a dynamic vehicle scheduling strategy; Step S5: performing vehicle scheduling evolution analysis on the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy, and performing dynamic path planning, thereby constructing a dynamic planning path; Step S6: Perform deep path planning optimization on the dynamic planning path, conduct cloud-based intelligent response analysis, and build an intelligent solid waste sorting and scheduling model.

[0026] The present invention achieves real-time monitoring and recording of the solid waste sorting process by acquiring real-time solid waste sorting logs, which helps to discover and solve problems, tracks vehicles in solid waste sorting logs, builds a visual view of the transport trajectory distribution, and provides managers with the ability to understand vehicle locations and sorting conditions in real time. It also acquires all-round monitoring images of the sorting site in real time, performs visual recognition of equipment sorting behavior, helps monitor the sorting process, improves production efficiency and quality, establishes a dynamic sorting twin model, simulates and evolves the sorting process, helps optimize the sorting process, improves resource utilization and reduces errors, performs multi-time point solid waste sorting simulations, predicts sorting load requirements, helps to reasonably arrange resources and manpower, improves sorting efficiency, generates sorting load demand prediction values, and helps optimize solid waste sorting scheduling. , reduce idle time and reduce costs, calculate the load of each vehicle according to the load demand forecast value, formulate dynamic vehicle scheduling strategies, improve vehicle utilization and transportation efficiency, dynamic vehicle scheduling decisions help reduce transportation costs, reduce waiting time, and improve distribution efficiency. Combined with dynamic vehicle scheduling strategies, conduct vehicle scheduling evolution analysis, optimize vehicle scheduling plans, improve transportation efficiency, perform dynamic path planning, build dynamic planning paths, reduce driving distance and time, and increase delivery speed. Deeply plan and optimize dynamic planning paths, improve the accuracy and efficiency of path planning, reduce transportation costs, conduct cloud-based intelligent response analysis, build an intelligent solid waste sorting scheduling model, improve the intelligence level and response speed of the system, and optimize solid waste sorting scheduling path decisions.

[0027] In the embodiment of the present invention, refer to Figure 1 , is a flowchart of the steps of a real-time monitoring optimization method of a solid waste collection, transportation and sorting ERP system of the present invention. In this example, the steps of the real-time monitoring optimization method of the solid waste collection, transportation and sorting ERP system include: Step S1: obtaining a real-time solid waste sorting log based on the solid waste collection, transportation and sorting ERP system; tracking the solid waste transport vehicles in the real-time solid waste sorting log, and constructing a visual view of the transport trajectory distribution; In this embodiment, an API interface is configured in the solid waste collection, transportation and sorting ERP system to ensure that real-time solid waste sorting logs can be automatically extracted from the system. By writing a script (such as Python), the sorting logs are extracted from the ERP system regularly (for example, every minute), including timestamps, waste types, sorting results and other information, to ensure the integrity and accuracy of data collection, handle network or data format problems, store the acquired real-time sorting logs in a database (such as MySQL, PostgreSQL), design a corresponding data table, and the fields include timestamps, waste IDs, sorting status, operators, etc. After the data is stored, a data quality check is performed to ensure the integrity, accuracy and consistency of the records. Data visualization tools can be used to quickly check data distribution, connect to the vehicle GPS tracking system, obtain the location information (latitude and longitude, speed, status, etc.) of the transport vehicle in real time, and link the real-time sorting logs with the vehicle tracking data. Link, combine each sorting operation with the corresponding vehicle location data through timestamp and vehicle ID to form a comprehensive data set, extract the vehicle's trajectory data from the associated data, including the latitude and longitude information at each time point, and calculate the vehicle's driving route within a specific time period, organize the extracted trajectory data into a format suitable for visualization, ensure that it contains timestamp, longitude and latitude, vehicle ID and other information, select a suitable visualization tool (such as Tableau, PowerBI, Folium or Matplotlib in Python) for data visualization, design visualization charts as needed to show the vehicle's transportation trajectory distribution, you can use heat maps, path maps or scatter plots, etc., to intuitively display the vehicle's driving path and sorting points, use the selected visualization tool to generate the final transportation trajectory distribution view, and ensure that the chart is easy to understand and operate, you can set interactive functions such as zooming and filtering to facilitate users' in-depth analysis.

[0028] Step S2: Obtaining a full-scale monitoring image of the real-time sorting site; performing visual recognition of the equipment sorting behavior on the full-scale monitoring image of the real-time sorting site, and performing dynamic sorting evolution to construct a dynamic sorting twin model; In this embodiment, an all-round monitoring camera (such as a 360-degree camera, or a combination of multiple fixed cameras) is installed at the sorting site to ensure that the entire sorting area is covered and image data of the sorting operation can be collected in real time. The monitoring system is configured, the image collection frequency is set (for example, one image is taken per second), and the image is transmitted to a central database or storage server in real time. A streaming protocol (such as RTSP) or an API interface is used to ensure the stability and low latency of the data stream. An image data storage structure is designed in the database, including information such as timestamp, camera ID, and image file path for subsequent retrieval and analysis. The integrity and quality of the image data are regularly checked to ensure that the image is clear and contains the required information. The image processing algorithm can be used to detect the validity of the image. An image processing library (such as OpenCV) is used to pre-process the acquired image, including denoising, contrast enhancement, and brightness enhancement, to ensure the accuracy of subsequent recognition. A deep learning algorithm (such as a convolutional neural network CNN) is used to train a recognition model for the sorting behavior of the equipment. A labeled training data set is prepared, including sorting behavior samples of different equipment, and model training and verification are performed. A suitable framework (such as TensorFlow or PyTorch) is selected to improve the recognition accuracy of the model through transfer learning. The model is applied to real-time monitoring images to identify the sorting behavior of the equipment and extract relevant behavior data, such as sorting action type, frequency and duration. The extracted real-time equipment sorting behavior data is stored in the database, including timestamp, equipment ID, sorting behavior type and other information, for subsequent analysis. The collected sorting behavior data is analyzed to identify behavior patterns and changing trends. Data analysis tools (such as Python's Pandas and NumPy) are used to calculate indicators such as sorting frequency and pause time. System dynamics or discrete event simulation methods are used to build a dynamic sorting evolution model to simulate sorting operations under different conditions. changes, select appropriate modeling tools (such as AnyLogic, Simul8), build a model based on the behavioral data, set parameters and initial conditions, use historical data and real-time data to verify the constructed dynamic model, ensure that the model can accurately reflect the dynamic changes of the actual sorting process, adjust the model parameters according to the verification results, combine the status information of the real sorting system with the dynamic model, and build a dynamic sorting twin model. The model should be able to reflect the operating status and evolution of the sorting system in real time, and input the real-time equipment sorting behavior data, accumulation data and other relevant information into the twin model to achieve real-time monitoring and analysis.

[0029] Step S3: Perform multi-time point solid waste sorting simulation on the dynamic sorting twin model, and perform sorting load demand forecasting to generate a sorting load demand forecast value; In this embodiment, the specific objectives of the simulation are determined, such as evaluating the sorting capacity, equipment load and resource utilization efficiency in different time periods, clarifying the time points that need to be predicted (such as peak periods, non-peak periods, etc.), and obtaining historical sorting operation data from the sorting system, including sorting time, quantity, equipment usage, etc., to provide a basis for the simulation. According to historical data and actual operating conditions, the input parameters of the dynamic sorting twin model are set, including waste type, sorting speed, number of equipment and its efficiency, processing time, etc., and simulation tools (such as AnyLogic, Simul8, etc.) are used to perform multi-time point solid waste sorting simulation on the dynamic sorting twin model. The model is run to observe the sorting performance of the system at different time points. After the simulation, the sorting data at each time point is collected, including sorting quantity, equipment load, processing time and other information to form a simulation result data set. The collected simulation results are sorted to ensure that the data format is unified. First, to facilitate subsequent analysis and modeling, select appropriate load demand forecasting models according to data characteristics, such as time series analysis (ARIMA, SARIMA), machine learning algorithms (such as regression models, random forests), etc., use the sorted historical sorting data and simulation results to train the selected forecasting model to ensure that the model can capture the changing trend of load demand, use the trained model to predict future sorting load demand, input simulation result data, generate load demand forecast values ​​for different time points, analyze the generated forecast values, evaluate their rationality and accuracy, and verify the effectiveness of the forecasting model by comparing with historical data. Organize the forecast results into a report, including forecast values, analysis and interpretation, and recommended measures, to provide decision support for management, and apply the sorting load demand forecast values ​​to actual operations to help optimize resource allocation, equipment scheduling and sorting plans, and improve overall sorting efficiency.

[0030] Step S4: Calculate the load of each vehicle for the sorting load demand forecast value, and then make a dynamic vehicle scheduling decision to obtain a dynamic vehicle scheduling strategy; In this embodiment, relevant information of each vehicle is extracted from the vehicle management system, including vehicle ID, load capacity, current status (empty or fully loaded), availability, etc., and the estimated load of each vehicle is calculated one by one according to the sorting load demand forecast value, where the estimated load = sorting load demand forecast value × vehicle allocation ratio, wherein the vehicle allocation ratio can be set according to the historical efficiency, current status and availability of the vehicle, and the calculated estimated load is integrated with the vehicle information to form a comprehensive data set including vehicle ID, estimated load and other relevant information, to ensure that the estimated load of each vehicle does not exceed its maximum load capacity. If overloading is found, the calculation method should be adjusted or the load should be reallocated, and the goal of the scheduling decision should be clarified, such as minimizing transportation time, maximizing vehicle utilization or reducing operating costs. According to the scheduling goal, a suitable scheduling algorithm is selected, such as genetic algorithm, particle swarm optimization, linear programming or heuristic algorithm, etc., to establish a dynamic vehicle scheduling model, taking into account the vehicle's load capacity. Factors such as power, sorting demand, traffic conditions and time windows are taken into consideration. Mathematical modeling tools (such as Lingo and GAMS) or programming languages ​​(such as Python) are used to implement the model. The set scheduling model and algorithm are used to calculate the optimal vehicle scheduling plan and generate scheduling information for each vehicle, including departure time, transportation route and estimated arrival time. The feasibility of the generated scheduling plan is checked to ensure that all vehicles meet the sorting demand within the specified time and do not violate the load limit. The scheduling results are organized into a readable format, including the scheduling plan, estimated load and transportation route of each vehicle. A detailed dynamic vehicle scheduling strategy is formulated, including a scheduling schedule, emergency plans (such as vehicle failures and traffic congestion), etc., to ensure the effectiveness and flexibility of the strategy. A real-time monitoring and feedback mechanism is set up to track the actual implementation of vehicle scheduling, and dynamic adjustments and optimizations are made based on actual data. The dynamic vehicle scheduling strategy is applied to actual operations to ensure the execution of the scheduling plan and continuous optimization based on feedback.

[0031] Step S5: performing vehicle scheduling evolution analysis on the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy, and performing dynamic path planning, thereby constructing a dynamic planning path; In this embodiment, historical transport trajectory data is obtained from the vehicle management system, including information such as the driving path, stop points, timestamps, and speed of each vehicle. A visualization tool (such as Tableau, PowerBI, Folium in Python, or Matplotlib) is used to design and create a visualization view of the transport trajectory distribution to display the vehicle's driving path and sorting points, ensure that the visualization chart can effectively display the vehicle activity in different time periods, analyze the visualization results, identify high-frequency sections, bottleneck areas, and common stop points, use heat maps or path maps to help identify potential efficiency improvement areas, clarify the goals of dynamic path planning, such as the shortest path, minimum transportation time, minimum cost, or maximum vehicle utilization, select a suitable path planning algorithm according to the set goal, such as the Dijkstra algorithm, A* algorithm, genetic algorithm, or ant colony algorithm, etc., and use a geographic information system (GIS) or path planning software to build a dynamic path. Planning model. The model should consider factors such as real-time traffic information, road conditions, vehicle status and load limits. Input historical trajectory data and real-time traffic information into the selected path planning algorithm, calculate the best driving path, generate a dynamic path for each vehicle, including the starting point, waypoints and destination, check the feasibility and rationality of the generated path, ensure the effectiveness of the path under actual conditions, and make necessary adjustments. Organize the calculated dynamic planning path into a readable format, including the planned path, estimated travel time and traffic conditions of each vehicle, formulate a detailed dynamic path implementation plan, including a real-time monitoring and adjustment mechanism for the path, so as to flexibly respond to changes in actual operations, develop a real-time monitoring system, track the comparison between the actual driving path of the vehicle and the planned path, dynamically adjust the path planning according to the feedback information to deal with emergencies (such as traffic jams, accidents, etc.), and apply the constructed dynamic planning path to actual operations to guide vehicle scheduling and driving to ensure the optimal use of resources.

[0032] Step S6: Perform deep path planning optimization on the dynamic planning path, conduct cloud-based intelligent response analysis, and build an intelligent solid waste sorting and scheduling model.

[0033] In this embodiment, the goal of deep optimization is clearly defined, such as shortening transportation time, reducing fuel consumption, improving vehicle utilization or reducing operating costs. Real-time data related to path planning is collected, including traffic conditions, weather information, road condition changes, vehicle status and expected sorting load, etc. Historical transportation data is analyzed to identify common obstacles and delay factors so that they can be considered in the optimization process. According to the optimization goal and data characteristics, a suitable optimization algorithm is selected. Commonly used algorithms include: genetic algorithm: used for global optimization, suitable for complex path problems, particle swarm optimization (PSO): used to find the optimal path, suitable for dynamic environments, mixed integer linear programming (MILP): used to handle optimization problems with multiple constraints, the dynamic planning path and related real-time data are input into the optimization model, deep path planning optimization is performed, and optimized path suggestions are generated. The optimization results are evaluated to ensure their feasibility and effectiveness in actual operations. A cloud architecture is designed to support data storage, processing and analysis. Services provided by cloud service platforms (such as AWS, Azure, Google Cloud) can be used to integrate real-time data, historical data and optimization results into The cloud system ensures the real-time and consistency of data, develops intelligent response algorithms that can process and analyze data in real time, automatically adjusts routes and scheduling strategies according to changing environmental conditions (such as traffic congestion and accidents), and designs response strategies, such as automatically selecting alternative routes in traffic congestion, or adjusting sorting plans in bad weather. Real-time monitoring is implemented in the cloud system to track the actual driving conditions of the vehicle compared with the preset routes, and adjust the intelligent response strategy according to the monitoring data. A feedback mechanism is developed to allow the system to continuously learn and optimize the scheduling strategy based on real-time data, integrate the deep optimization path and the cloud-based intelligent response analysis results, and build an intelligent solid waste sorting scheduling model. The model should have real-time scheduling, route optimization and response adjustment functions. The intelligent solid waste sorting scheduling model is verified using historical data and actual operation data to ensure its accuracy and reliability. The operation effect of the intelligent scheduling model is tested in a simulated environment, and its performance in different scenarios is evaluated. The intelligent solid waste sorting scheduling model is applied to actual operations to guide vehicle scheduling, route selection and sorting plans. Based on actual operation feedback, the scheduling model and algorithm are continuously optimized to ensure that they adapt to the changing environment and needs.

[0034] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: obtaining a real-time solid waste sorting log based on the solid waste collection, transportation and sorting ERP system; Step S12: performing data cleaning and optimization on the real-time solid waste sorting log to obtain an optimized real-time sorting log; Step S13: Tracking the solid waste transport vehicles for the optimized real-time sorting log to generate vehicle transport track state characteristic data; Step S14: performing a transportation track distribution analysis on the vehicle transportation track state characteristic data to generate real-time transportation track distribution data of the sorting station; Step S15: Perform a visual reconstruction of the transport trajectory distribution data of the sorting station in real time to construct a transport trajectory distribution visualization view.

[0035] In this embodiment, an API interface is configured in the solid waste collection, transportation and sorting ERP system to obtain sorting log data in real time, ensuring that the interface can provide necessary real-time data, such as sorting time, waste type, sorting results, etc., and an automated script (such as Python, Java, etc.) is implemented to obtain sorting logs from the ERP system regularly (for example, every minute) and store them in a local or cloud database to ensure data integrity and timeliness. An appropriate data table structure is designed in the database to store sorting log information, including fields such as timestamp, waste type, sorting status, operator, etc., and a data processing tool (such as Python's P The real-time sorting logs acquired are cleaned using the andas library to remove duplicate records, missing values, and outliers. For example, records with a sorting status of "error" are identified and deleted to ensure data quality. All fields are standardized in a unified format. For example, the date format is unified as YYYY-MM-DD to ensure data consistency and readability. After cleaning and formatting, the optimized real-time sorting logs are stored in a new database table to prepare for subsequent analysis. The interface with the vehicle GPS tracking system is configured to obtain vehicle location data (such as latitude and longitude, speed, status, etc.) in real time and combined with the optimized sorting logs. The time stamp and vehicle ID are used to associate the sorting log with the vehicle tracking data to generate a complete data set containing sorting operations and vehicle locations. The vehicle transportation trajectory status characteristics, such as driving routes, stop times, sorting stations, etc., are extracted from the associated data to form structured trajectory status data. Data analysis tools (such as Python's NumPy, SciPy, etc.) are selected to perform statistical analysis of the transportation trajectory data, analyze the transportation trajectory of vehicles in different time periods, and count the visit frequency, average stay time, and distribution of transportation routes of each sorting station. For example, a statistical table of the number of visits to each sorting station is generated to understand the high-frequency and low-frequency For each site, the analysis results are organized into real-time transport trajectory distribution data of the sorting station, including the visit frequency, average transport time and other information of each site. Appropriate visualization tools (such as Tableau, PowerBI, Matplotlib, Plotly, etc.) are selected for data visualization. Visualization charts are designed according to requirements, including heat maps, bar charts, line charts, etc., to show the distribution of transport trajectories, visit frequency and residence time, etc. The final visualization view is generated using the selected visualization tool, and the chart is ensured to be easy to understand and analyze, and can be output as an interactive dashboard for subsequent data analysis and reporting.

[0036] In this embodiment, the specific steps of step S13 are: Identify real-time sorting jobs based on optimized real-time sorting logs; Track solid waste transport vehicles for real-time sorting operations and extract vehicle status parameters; Calculate the solid waste load capacity of the transport vehicle based on the state parameters of the transport vehicle to generate the solid waste load capacity of the vehicle; Calculate the carrying frequency within the cycle for real-time sorting operations to generate the carrying frequency of the vehicle; Carry out load analysis based on the vehicle's transportation frequency and the vehicle's solid waste load to obtain the vehicle's load data; Analyze the vehicle transport trajectory of real-time sorting operations to obtain the vehicle operation transport trajectory; The vehicle's load data and vehicle operation trajectory are mined to generate vehicle trajectory status feature data.

[0037] In this embodiment, an optimized real-time sorting log is extracted from the database, which contains detailed information about the sorting operation, such as sorting time, waste type, sorting results, etc. The log is analyzed using a data processing tool (such as Python Pandas) to identify all completed sorting operations. The log can be filtered according to the timestamp and sorting status. For example, the records with a sorting status of "completed" are extracted as the basic data of the real-time sorting operation. The vehicle GPS tracking system is connected to obtain the location information of the transport vehicle (latitude and longitude, speed, driving direction, etc.) in real time. The tracking data of the solid waste transport vehicle is associated with the real-time sorting operation record through the timestamp and vehicle ID. , generate a comprehensive data set including sorting operations and vehicle status, extract vehicle status parameters from the associated data, including current speed, driving direction, parking status, etc., build a vehicle status feature set, obtain the weight information of each batch of solid waste from the solid waste sorting system, usually recorded when the sorting is completed, and calculate the solid waste load of each transport vehicle based on the weight data of each sorting record. For example, if a vehicle sorts multiple types of solid waste in a certain operation, the weight of all solid wastes is added together to obtain the total load. According to the real-time sorting operation records and vehicle tracking data, the operation records of each vehicle in a specific time period are sorted out, and the transportation weight of each vehicle in a set period (such as daily or weekly) is counted. The number of trips, for example, using SQL queries or Python scripts, calculate the number of trips for each vehicle and generate the trip frequency data, store the trip frequency data for each vehicle in the database to support subsequent analysis, associate the vehicle's load data with the trip frequency data, and generate a comprehensive data set of each vehicle's load and frequency, select appropriate statistical analysis methods (such as regression analysis, cluster analysis), evaluate the vehicle's load, and determine the average load of each vehicle through analysis, for example, the total load of each vehicle can be calculated and divided by its trip frequency to obtain the average load, organize the vehicle's tracking data, and prepare for trajectory analysis, ensuring that the data includes timestamps, Longitude and latitude, vehicle ID and other information, select appropriate tools (such as Python's GeoPandas, Folium library) for trajectory analysis, generate the vehicle's transportation trajectory map according to the vehicle's latitude and longitude data, and use the path drawing method to display the vehicle's driving route in a specific time period. Extract state features from the transportation trajectory data, such as changes in driving speed, number of stops, complexity of the driving route, etc., select appropriate data mining algorithms (such as cluster analysis, decision trees, etc.), analyze the transportation trajectory state features, use the selected algorithm to analyze the extracted state features, identify vehicles with similar trajectory patterns, and generate the corresponding state feature data set.

[0038] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: obtaining a real-time all-round monitoring image of the sorting site based on the solid waste collection, transportation and sorting ERP system; Step S22: Perform visual recognition of equipment sorting behavior on the real-time sorting site omnidirectional monitoring image to extract real-time equipment sorting behavior data; Step S23: performing sorting process logic analysis on the real-time equipment sorting behavior data to generate sorting site sorting behavior logic data; Step S24: Calculate the solid waste sorting accumulation volume for the optimized real-time sorting log, and extract the real-time solid waste sorting accumulation volume; Step S25: analyzing the time series change of the accumulation amount of the optimized real-time sorting log to generate solid waste accumulation amount change data; Step S26: Dynamically sort and evolve the solid waste accumulation change data and the sorting behavior logic data at the sorting site to build a dynamic sorting twin model.

[0039] In this embodiment, all-round monitoring cameras (such as 360-degree cameras or multiple surveillance cameras) are installed at the sorting site to ensure that the entire sorting area can be covered, and real-time monitoring image data is obtained from the solid waste collection and sorting ERP system. The data should include timestamps, image files and related metadata. The acquired monitoring images are stored in the cloud or local server, and it is ensured that the image data can be quickly accessed and processed for subsequent analysis. Deep learning algorithms (such as convolutional neural networks (CNN)) are used for visual recognition of equipment sorting behavior. Open source frameworks such as TensorFlow or PyTorch can be used. The model is trained using annotated sorting behavior image data sets. The annotated data should include samples of different sorting behaviors (such as picking, placing, and classification). The trained model is applied to the real-time monitoring images to automatically identify the sorting behavior of the equipment and extract real-time equipment sorting behavior data. The extracted real-time equipment sorting behavior data is compared with the standard process of the sorting process to ensure that the logical relationship of each sorting behavior can be identified. A state machine model or a logical reasoning method is used to analyze the execution of the sorting process to determine the before and after relationship of each behavior. Based on the analysis results , generate logical data of sorting behavior at the sorting site, record the start and end time of each sorting behavior, and its position in the entire process, extract the solid waste sorting record of each sorting station from the optimized real-time sorting log, calculate the solid waste accumulation of each sorting station, associate the calculated solid waste sorting accumulation data with the timestamp, generate real-time solid waste sorting accumulation records, perform time series analysis on the real-time accumulation data, use moving average, exponential smoothing and other methods to identify the trend and periodic changes of the accumulation, record the accumulation changes in each time period, and generate solid waste accumulation change data, Including maximum, minimum, average and fluctuation range, use visualization tools (such as Matplotlib or Tableau) to visualize the accumulation change data for easy analysis and decision-making, combine the solid waste accumulation change data with the sorting behavior logic data, analyze the dynamic evolution law in the sorting process, and build a dynamic sorting twin model based on dynamic sorting evolution analysis. The model should include mathematical descriptions of solid waste accumulation, sorting behavior and their relationship. Verify the accuracy of the twin model through historical data, and adjust the model parameters based on feedback to improve the model's predictive ability.

[0040] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: performing multi-time point solid waste sorting simulation on the dynamic sorting twin model, thereby generating solid waste sorting simulation data at multiple time points; Step S32: performing statistics on the solid waste inflow and outflow of the solid waste sorting simulation data at multiple time points to obtain the solid waste inflow and outflow of the sorting station; Step S33: performing sorting load demand analysis on the inflow and outflow of solid waste at the sorting station, thereby generating solid waste sorting load demand data; Step S34: performing long-term evolution of the input and output volume of solid waste at the sorting station, thereby obtaining solid waste input and output volume evolution trend data; Step S35: Use the solid waste inflow and outflow trend evolution data to predict the solid waste sorting load demand data, and generate a sorting load demand prediction value.

[0041] In this embodiment, a dynamic sorting twin model is used to set input conditions at multiple time points, including the current solid waste sorting status, environmental factors, equipment operation status, etc., and the simulation algorithm is run to perform multi-time point simulation of solid waste sorting according to the model parameters and input conditions. Discrete event simulation, system dynamics or agent-based modeling methods can be used to record the solid waste sorting simulation data at each time point, including sorting quantity, sorting efficiency, equipment utilization, etc., to generate a multi-time point solid waste sorting simulation data set, and extract the input and output information of each sorting station from the multi-time point solid waste sorting simulation data. The input and output should include the quantity and volume of each solid waste type. The following formula is used to count the input and output: Input and output = total input − total output. According to the solid waste input and output of the sorting station, a load demand model is established. The model should take into account the processing capacity, equipment performance and operating efficiency of the sorting station. Regression analysis or time series analysis methods are used to analyze the relationship between the solid waste input and output and the sorting load, and identify the main factors affecting the sorting load demand. , generate solid waste sorting load demand data, record the load demand at each time point, including the expected number of sorters, equipment usage, etc., conduct long-term time series analysis on the solid waste inflow and outflow of the sorting station, and use methods such as moving average and seasonal decomposition to identify long-term trends and seasonal changes, establish a trend evolution model, and describe the law of solid waste inflow and outflow changes over time. Linear regression, exponential smoothing and other methods can be used to record the changing trend of inflow and outflow, generate a solid waste inflow and outflow trend evolution data set to ensure that the data can reflect the dynamics of long-term changes, select a suitable prediction model such as ARIMA, SARIMA or machine learning model (such as random forest, XGBoost) according to the solid waste inflow and outflow trend evolution data, use historical data to train the selected prediction model, and verify it through cross-validation or holdout method to ensure the accuracy of the model, use the trained model to predict the solid waste sorting load demand data, and generate the sorting load demand forecast value for the future time period.

[0042] In this embodiment, step S4 includes the following steps: Step S41: Calculate the solid waste carrying capacity based on the sorting load demand forecast value, thereby extracting the solid waste carrying capacity forecast value of the sorting station; Step S42: performing vehicle sorting scheduling simulation on the dynamic sorting twin model based on the predicted value of the solid waste carrying capacity of the sorting station, and extracting sorting scheduling simulation data; Step S43: Calculating the load of each vehicle on the sorting scheduling simulation data, thereby generating a load value for each vehicle; Step S44: performing vehicle dispatch demand analysis according to the load value of each vehicle to generate transport vehicle dispatch demand data; Step S45: Perform dynamic vehicle scheduling decisions on the transport vehicle scheduling demand data to obtain a dynamic vehicle scheduling strategy.

[0043] In this embodiment, the solid waste carrying capacity forecast value of the sorting station is calculated according to the sorting load demand forecast value, where carrying capacity = load demand × the load capacity of each vehicle. The sorting load forecast value is integrated with the vehicle load data to ensure that the carrying capacity forecast value of each sorting station can reflect the actual demand. The solid waste carrying capacity forecast value of each sorting station is recorded to ensure that the data is arranged in chronological order for subsequent scheduling simulation analysis. Based on the dynamic sorting twin model, a vehicle sorting scheduling simulation environment is prepared to ensure that the model can simulate the operation of the sorting station and the scheduling strategy of the vehicle. The simulation is run to perform vehicle scheduling simulation according to the solid waste carrying capacity forecast value. The discrete event simulation method can be used to simulate the loading, transportation and unloading processes of the vehicle. The operating status, loading conditions, transportation time, etc. of each vehicle during the simulation process are recorded to generate a sorting scheduling simulation data set. The sorting scheduling simulation data is analyzed, and the load of each vehicle is calculated one by one. The calculated load value is associated with the actual loading condition of the vehicle to ensure that the load of each vehicle is The load records are complete, recording the load value of each vehicle, ensuring that the data is arranged by time and vehicle number for subsequent analysis. According to the load value of each vehicle, the scheduling needs of the transport vehicles are analyzed. Demand forecasting models, such as regression analysis or time series analysis, can be used to identify the patterns and trends of scheduling needs. The scheduling demand data of each vehicle, including the expected number of transportation times, loading volume and number of vehicles required, etc., are recorded. The scheduling demand data is integrated with the existing vehicle resources to ensure that it is possible to evaluate whether the current scheduling capacity meets the demand, and a dynamic vehicle scheduling decision model is constructed. Considering factors such as scheduling needs, vehicle availability, and transportation timeliness, linear programming, integer programming or optimization algorithms (such as genetic algorithms) can be used for modeling. According to the output of the scheduling model, a dynamic vehicle scheduling strategy is generated to ensure that the scheduling strategy can respond to changes in demand in real time and optimize the utilization efficiency of vehicles. The generated scheduling strategy is implemented in the actual scheduling system, the scheduling status of the vehicle is adjusted in real time, and a feedback mechanism is set to monitor the scheduling effect for subsequent optimization.

[0044] In this embodiment, the specific steps of step S5 are: Step S51: performing vehicle scheduling evolution analysis on the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy to obtain real-time vehicle scheduling transport trajectory evolution data; Step S52: identifying the path sorting points of the real-time vehicle dispatching transport trajectory evolution data, and marking all sorting stations of the transport trajectory; Step S53: Analyze the optimal transport path sequence of all sorting sites on the transport track to obtain optimal transport path sequence data; Step S54: Perform dynamic path planning based on the optimal transport route sequence data, thereby constructing a dynamic planning path.

[0045] In this embodiment, based on the dynamic vehicle scheduling strategy, the real-time vehicle transport trajectory data is collected. This data should include the vehicle's current location, transportation status, timestamp and other information. The time series analysis method is used to analyze the evolution trend of vehicle scheduling. The sliding window analysis, periodic analysis and other technologies can be applied to identify vehicle scheduling patterns and changes, and the real-time vehicle scheduling transport trajectory evolution data is recorded, including the vehicle's scheduling status and trajectory characteristics at different time points, which is convenient for subsequent analysis. The real-time vehicle scheduling transport trajectory data is analyzed to identify all sorting sites. This can be achieved through cluster analysis or location-based recognition algorithms. The identified sorting sites are marked to ensure that each trajectory data point can be associated with the corresponding sorting site. The location information of each sorting site and the associated transport trajectory are recorded for subsequent path optimization analysis. A transport path sequence analysis model is constructed, considering each The distance, transportation time and transportation cost between the sorting sites are used to form the evaluation criteria for the transportation route sequence. The shortest path algorithm (such as Dijkstra algorithm) or the traveling salesman problem (TSP) algorithm is applied to determine the optimal transportation route sequence of all sorting sites. The analysis results are recorded, including the optimal transportation sequence of each sorting site and its corresponding transportation time and cost, to ensure that the data can be used for dynamic path planning. Based on the optimal transportation route sequence data, a dynamic path planning model is constructed. Graph theory methods can be used, and the sorting sites are regarded as nodes in the graph and the connected paths are regarded as edges. A dynamic programming algorithm (such as A* algorithm or other heuristic algorithms) is used to calculate the optimal path from the starting point to each sorting site, ensuring that real-time traffic conditions and other dynamic factors are taken into account, and the dynamic planning path is output. The generated path is integrated with the vehicle scheduling system to ensure that the vehicle can be scheduled according to the optimized path.

[0046] In this embodiment, step S6 includes the following steps: Step S61: performing deep path planning optimization on the dynamic planning path and constructing a dynamic path optimization strategy; Step S62: Conduct collaborative scheduling learning on the dynamic path optimization strategy and the dynamic vehicle scheduling strategy to construct a collaborative sorting scheduling strategy; Step S63: Perform cloud-based intelligent response analysis on the collaborative sorting and scheduling strategy to build an intelligent solid waste sorting and scheduling model; Step S64: Perform real-time sorting monitoring and optimization operations based on the intelligent solid waste sorting scheduling model.

[0047] In this embodiment, according to the dynamic planning path, the path is deeply optimized using graph theory and optimization algorithms (such as genetic algorithms, simulated annealing, etc.), and factors including transportation time, cost and environmental conditions are considered. The path optimization algorithm is implemented, and the path sequence and selection are adjusted to ensure that the optimized path can reduce the total transportation time and energy consumption. The optimized path and strategy are recorded and integrated into a dynamic path optimization strategy to ensure that it can be used for subsequent scheduling decisions. The dynamic path optimization strategy is integrated with the dynamic vehicle scheduling strategy to form a comprehensive data set containing information on different scheduling scenarios and path selections. A collaborative scheduling learning model is constructed, and a machine learning algorithm (such as reinforcement learning) can be used to train the model so that it can optimize scheduling decisions under different circumstances. Through the collaborative learning process, a collaborative sorting scheduling strategy is generated to ensure that the strategy can dynamically adapt to different operating situations. Based on the collaborative sorting and scheduling strategy, a cloud-based intelligent response model is built to monitor and analyze the data in the sorting and transportation process in real time using cloud computing and big data analysis technology. A data stream processing framework is designed to receive status data from the sorting site and transportation vehicles in real time for rapid analysis and response. According to the real-time analysis results, an intelligent solid waste sorting and scheduling model is built to ensure rapid response to emergencies and changing needs. An instant sorting monitoring system is established, and an intelligent solid waste sorting and scheduling model is integrated to ensure real-time monitoring of sorting operations and vehicle scheduling status. According to the output of the intelligent scheduling model, the sorting operation and vehicle scheduling strategy are automatically adjusted to achieve optimal sorting efficiency and resource utilization. A feedback mechanism is established to continuously optimize the intelligent model by collecting actual operation data and comparing it with the model prediction results to ensure its accuracy and effectiveness.

[0048] In this embodiment, a real-time monitoring and optimization device for a solid waste collection, transportation and sorting ERP system is provided, which is used to execute the real-time monitoring and optimization method for the solid waste collection, transportation and sorting ERP system as described above, including: The transport track distribution module is used to obtain real-time solid waste sorting logs based on the solid waste collection, transportation and sorting ERP system; track the solid waste transport vehicles based on the real-time solid waste sorting logs and build a visual view of the transport track distribution; The dynamic sorting evolution module is used to obtain all-round monitoring images of the real-time sorting site; perform visual recognition of the equipment sorting behavior on the all-round monitoring images of the real-time sorting site, and perform dynamic sorting evolution to build a dynamic sorting twin model; The load demand prediction module is used to simulate the solid waste sorting at multiple time points on the dynamic sorting twin model, and to predict the sorting load demand and generate the sorting load demand prediction value; The vehicle dispatch decision module is used to calculate the vehicle load for each vehicle based on the sorting load demand forecast value, and then make dynamic vehicle dispatch decisions to obtain a dynamic vehicle dispatch strategy; The path planning module is used to analyze the vehicle scheduling evolution of the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy and perform dynamic path planning to construct a dynamic planning path; The intelligent sorting and scheduling module is used to perform deep path planning optimization on the dynamically planned path, conduct cloud-based intelligent response analysis, and build an intelligent solid waste sorting and scheduling model.

[0049] The present invention acquires real-time solid waste sorting logs and tracks solid waste transport vehicles to construct a visual view of transport trajectory distribution, which can monitor and track the real-time position of vehicles, help optimize vehicle scheduling, and improve transportation efficiency. The visual view helps to promptly discover potential problems and bottlenecks, improve the level of visual management of solid waste sorting operations, reduce errors and improve accuracy. By building a dynamic sorting twin model through all-round monitoring images of the real-time sorting site and visual recognition of equipment sorting behavior, it can realize real-time monitoring and analysis of the situation on the sorting site and improve the intelligence of the sorting operation. The dynamic sorting evolution module helps to adjust the sorting strategy according to the real-time situation, improve operation efficiency and accuracy, and optimize the sorting process. Through multi-time point solid waste sorting simulation and load demand prediction, it can help predict the sorting load demand, optimize vehicle load planning, reduce empty driving, and save costs. The application of the prediction module can improve transportation Efficiency, avoid waste of resources, and improve the accuracy of the overall transportation plan. Vehicle-by-vehicle load calculation and dynamic vehicle scheduling decisions can adjust the vehicle scheduling strategy according to actual conditions, improve transportation efficiency and load balance, and reduce operating costs. Dynamic vehicle scheduling decisions help to achieve instant response and adjustment, and improve the flexibility and adaptability of vehicle scheduling. Through vehicle scheduling evolution analysis and dynamic path planning to build a dynamic planning path, you can optimize the vehicle's transportation route, improve transportation efficiency and save resources. The establishment of a dynamic planning path helps to optimize the vehicle scheduling plan, reduce transportation time and cost, and improve service quality. Deep planning optimization and cloud-based intelligent response analysis of the dynamic planning path, and the construction of an intelligent solid waste sorting and scheduling model can improve the system's intelligent management level and optimize sorting and scheduling decisions. The application of the intelligent sorting and scheduling module helps to achieve automated scheduling and optimization, and improve the efficiency and quality of the overall sorting operation.

[0050] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0051] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A real-time monitoring and optimization method for a solid waste collection, transportation and sorting ERP system, characterized in that: The following steps are involved: Step S1: obtaining real-time solid waste sorting logs based on the solid waste collection, transportation and sorting ERP system; Track solid waste transport vehicles based on real-time solid waste sorting logs and build a visual view of transport trajectory distribution; Step S2: Acquire a real-time all-round monitoring image of the sorting site; Perform visual recognition of equipment sorting behavior on all-round monitoring images of the real-time sorting site, perform dynamic sorting evolution, and build a dynamic sorting twin model; Step S3: Perform multi-time point solid waste sorting simulation on the dynamic sorting twin model, and perform sorting load demand forecasting to generate a sorting load demand forecast value; Step S4: Calculate the load of each vehicle for the sorting load demand forecast value, and then make a dynamic vehicle scheduling decision to obtain a dynamic vehicle scheduling strategy; Step S5: performing vehicle scheduling evolution analysis on the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy, and performing dynamic path planning, thereby constructing a dynamic planning path; Step S6: Perform deep path planning optimization on the dynamic planning path, conduct cloud-based intelligent response analysis, and build an intelligent solid waste sorting and scheduling model.

2. The real-time monitoring and optimization method of the solid waste collection, transportation and sorting ERP system according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: obtaining a real-time solid waste sorting log based on the solid waste collection, transportation and sorting ERP system; Step S12: performing data cleaning and optimization on the real-time solid waste sorting log to obtain an optimized real-time sorting log; Step S13: Tracking the solid waste transport vehicles for the optimized real-time sorting log to generate vehicle transport track state characteristic data; Step S14: performing a transportation track distribution analysis on the vehicle transportation track state characteristic data to generate real-time transportation track distribution data of the sorting station; Step S15: Perform a visual reconstruction of the transport trajectory distribution data of the sorting station in real time to construct a transport trajectory distribution visualization view.

3. The real-time monitoring optimization method of the solid waste collection, transportation and sorting ERP system according to claim 2 is characterized in that: The specific steps of step S13 are: Identify real-time sorting jobs based on optimized real-time sorting logs; Track solid waste transport vehicles for real-time sorting operations and extract vehicle status parameters; Calculate the solid waste load capacity of the transport vehicle based on the state parameters of the transport vehicle to generate the solid waste load capacity of the vehicle; Calculate the carrying frequency within the cycle for real-time sorting operations to generate the carrying frequency of the vehicle; Carry out load analysis based on the vehicle's transportation frequency and the vehicle's solid waste load to obtain the vehicle's load data; Analyze the vehicle transport trajectory of real-time sorting operations to obtain the vehicle operation transport trajectory; The vehicle's load data and vehicle operation trajectory are mined to generate vehicle trajectory status feature data.

4. The real-time monitoring and optimization method of the solid waste collection, transportation and sorting ERP system according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: obtaining a real-time all-round monitoring image of the sorting site based on the solid waste collection, transportation and sorting ERP system; Step S22: Perform visual recognition of equipment sorting behavior on the real-time sorting site omnidirectional monitoring image to extract real-time equipment sorting behavior data; Step S23: performing sorting process logic analysis on the real-time equipment sorting behavior data to generate sorting site sorting behavior logic data; Step S24: Calculate the solid waste sorting accumulation volume for the optimized real-time sorting log, and extract the real-time solid waste sorting accumulation volume; Step S25: analyzing the time series change of the accumulation amount of the optimized real-time sorting log to generate solid waste accumulation amount change data; Step S26: Dynamically sort and evolve the solid waste accumulation change data and the sorting behavior logic data at the sorting site to build a dynamic sorting twin model.

5. The real-time monitoring and optimization method of the solid waste collection, transportation and sorting ERP system according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: performing multi-time point solid waste sorting simulation on the dynamic sorting twin model, thereby generating solid waste sorting simulation data at multiple time points; Step S32: performing statistics on the solid waste inflow and outflow of the solid waste sorting simulation data at multiple time points to obtain the solid waste inflow and outflow of the sorting station; Step S33: performing sorting load demand analysis on the inflow and outflow of solid waste at the sorting station, thereby generating solid waste sorting load demand data; Step S34: performing long-term evolution of the input and output volume of solid waste at the sorting station, thereby obtaining solid waste input and output volume evolution trend data; Step S35: Use the solid waste inflow and outflow trend evolution data to predict the solid waste sorting load demand data, and generate a sorting load demand prediction value.

6. The real-time monitoring and optimization method of the solid waste collection, transportation and sorting ERP system according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: Calculate the solid waste carrying capacity based on the sorting load demand forecast value, thereby extracting the solid waste carrying capacity forecast value of the sorting station; Step S42: performing vehicle sorting scheduling simulation on the dynamic sorting twin model based on the predicted value of the solid waste carrying capacity of the sorting station, and extracting sorting scheduling simulation data; Step S43: Calculating the load of each vehicle on the sorting scheduling simulation data, thereby generating a load value for each vehicle; Step S44: performing vehicle dispatch demand analysis according to the load value of each vehicle to generate transport vehicle dispatch demand data; Step S45: Perform dynamic vehicle scheduling decisions on the transport vehicle scheduling demand data to obtain a dynamic vehicle scheduling strategy.

7. The real-time monitoring and optimization method of the solid waste collection, transportation and sorting ERP system according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: performing vehicle scheduling evolution analysis on the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy to obtain real-time vehicle scheduling transport trajectory evolution data; Step S52: identifying the path sorting points of the real-time vehicle dispatching transport trajectory evolution data, and marking all sorting stations of the transport trajectory; Step S53: Analyze the optimal transport path sequence of all sorting sites on the transport track to obtain optimal transport path sequence data; Step S54: Perform dynamic path planning based on the optimal transport route sequence data, thereby constructing a dynamic planning path.

8. The real-time monitoring and optimization method of the solid waste collection, transportation and sorting ERP system according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: performing deep path planning optimization on the dynamic planning path and constructing a dynamic path optimization strategy; Step S62: Conduct collaborative scheduling learning on the dynamic path optimization strategy and the dynamic vehicle scheduling strategy to construct a collaborative sorting scheduling strategy; Step S63: Perform cloud-based intelligent response analysis on the collaborative sorting and scheduling strategy to build an intelligent solid waste sorting and scheduling model; Step S64: Perform real-time sorting monitoring and optimization operations based on the intelligent solid waste sorting scheduling model.

9. A real-time monitoring and optimization device for a solid waste collection, transportation and sorting ERP system, characterized in that: The real-time monitoring optimization method for executing the solid waste collection, transportation and sorting ERP system according to claim 1 comprises: The transport track distribution module is used to obtain real-time solid waste sorting logs based on the solid waste collection, transportation and sorting ERP system; track the solid waste transport vehicles based on the real-time solid waste sorting logs and build a visual view of the transport track distribution; The dynamic sorting evolution module is used to obtain all-round monitoring images of the real-time sorting site; perform visual recognition of the equipment sorting behavior on the all-round monitoring images of the real-time sorting site, and perform dynamic sorting evolution to build a dynamic sorting twin model; The load demand prediction module is used to simulate the solid waste sorting at multiple time points on the dynamic sorting twin model, and to predict the sorting load demand and generate the sorting load demand prediction value; The vehicle dispatch decision module is used to calculate the vehicle load for each vehicle based on the sorting load demand forecast value, and then make dynamic vehicle dispatch decisions to obtain a dynamic vehicle dispatch strategy; The path planning module is used to analyze the vehicle scheduling evolution of the transport trajectory distribution visualization view based on the dynamic vehicle scheduling strategy and perform dynamic path planning to construct a dynamic planning path; The intelligent sorting and scheduling module is used to perform deep path planning optimization on the dynamically planned path, conduct cloud-based intelligent response analysis, and build an intelligent solid waste sorting and scheduling model.

Images