Environmental sanitation area division method based on garbage handling capacity business balance

Abstract

The invention discloses an environmental sanitation region division method based on garbage handling capacity business balance, and relates to the technical field of intelligent environmental sanitation management, and the method comprises the steps: recognizing a garbage amount abnormal increase region according to the predicted garbage amount and the preliminarily processed real-time data, and dynamically adjusting the region division through employing an optimization algorithm; according to the adjusted region division, re-planning an operation route of the garbage collection vehicle and implementing a resource scheduling plan; the state of a garbage collection point is monitored in real time, and when abnormal accumulation occurs, an emergency plan is started immediately; and according to the emergency plan, rapidly adjusting region division, re-planning an operation route and dynamically adjusting a resource allocation strategy. According to the predicted garbage amount and the real-time data after primary treatment, the garbage amount abnormal increase area is identified, the area division is dynamically adjusted by applying the optimization algorithm, and the area division is optimized by combining the genetic algorithm, so that the garbage treatment capacity is matched with the garbage amount, and the response speed and adaptability of environmental sanitation work are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent sanitation management technology, and in particular to a method for dividing sanitation areas based on the balance of waste disposal volume. Background Technology

[0002] In recent years, with the rapid development of big data and artificial intelligence technologies, smart sanitation systems have gradually become an important part of urban solid waste management. Traditional waste collection and treatment models mainly rely on manual experience and lack accurate prediction and dynamic management of waste generation, which often leads to a mismatch between waste treatment capacity and collection demand. Especially during holidays, severe weather, or special events, waste accumulation occurs frequently, seriously affecting the urban environment and public health safety.

[0003] Existing technologies have the following shortcomings in managing the balance of waste disposal volume: First, the real-time performance and accuracy of waste volume prediction models need improvement. Second, the regional division and resource allocation strategies are too static, lacking a rapid response mechanism for abnormal increases in waste volume. Finally, the formulation and execution of emergency plans are inefficient; in the face of emergencies, manual intervention is often required, the decision-making process is time-consuming and prone to errors, reducing the overall operational efficiency and response speed of the sanitation system. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a sanitation area division method based on the balance of waste disposal volume to solve the problem of business imbalance caused by inaccurate waste disposal volume prediction and static area division and resource scheduling in the existing sanitation management system.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide a method for dividing sanitation areas based on the balance of waste disposal volume, which includes real-time collection of the average daily waste volume of each waste collection point, the processing efficiency of waste transfer stations, geographical location information and external influencing factor data, and preliminary processing thereof; Based on a deep learning model, predict the amount of waste in each region over a future period. Based on the predicted waste volume and real-time data after preliminary treatment, identify areas with abnormal waste growth and dynamically adjust the area division; Based on the adjusted zoning, the operating routes of garbage collection vehicles were replanned and a resource scheduling plan was implemented; Monitor the status of garbage collection points in real time, and immediately activate the emergency plan if abnormal accumulation occurs; Based on the emergency plan, the area division was quickly adjusted, the operation route was replanned, and the resource allocation strategy was dynamically adjusted.

[0007] As a preferred embodiment of the sanitation area division method based on the balance of waste treatment volume as described in this invention, the external influencing factor data includes data on the impact of weather, holidays, population flow and activities on waste generation.

[0008] As a preferred embodiment of the sanitation area division method based on the balance of waste treatment volume described in this invention, the preliminary processing includes filling missing values, detecting and correcting outliers, and standardizing data for the daily average waste volume, the processing efficiency of waste transfer stations, geographical location information, and external influencing factors. For non-numerical external influencing factors, one-hot encoding is used to convert them into numerical data.

[0009] As a preferred embodiment of the sanitation area division method based on waste disposal volume business balance described in this invention, the following steps are included in predicting the waste volume of each area in the future based on a deep learning model: Choose a hybrid model combining convolutional neural networks and recurrent neural networks, and design the model structure; Recurrent neural networks capture the temporal nature of sequential data by processing the local correlation of features through neural network layers in the model structure. The model is trained using the pre-processed data, and the mean squared error loss function between the predicted amount of garbage and the actual amount of garbage is minimized. Input current waste volume data and external influencing factor data into a trained hybrid model in real time to predict the change in waste volume in various regions over a future period.

[0010] As a preferred embodiment of the sanitation area division method based on the operational balance of waste disposal volume described in this invention, the following steps are included: Identifying areas with abnormal waste volume growth and dynamically adjusting the area division using an optimization algorithm based on predicted waste volume and real-time data after preliminary treatment: Construct a balance evaluation function to measure whether the waste treatment efficiency of different regions is balanced; An abnormal growth threshold is set. When the ratio of the predicted amount of waste in region A to the amount of waste in region B is greater than the abnormal growth threshold, the amount of waste in region A is considered to have increased abnormally. A fitness function is designed, which combines the predicted waste volume, the processing capacity of regional transfer stations, and location information, and a genetic algorithm is used to optimize the regional division.

[0011] As a preferred embodiment of the sanitation area division method based on the balanced operation of waste disposal volume as described in this invention, the following steps are included in replanning the operating routes of waste collection vehicles and implementing a resource scheduling plan based on the adjusted area division: Based on the optimized area division results, the TSP algorithm combined with the particle swarm optimization algorithm is used to plan the operation route of the garbage collection truck and minimize the total travel distance. Design a resource scheduling function to dynamically allocate sanitation vehicles and personnel based on the predicted amount of garbage and the number of areas with abnormal growth.

[0012] As a preferred embodiment of the sanitation area division method based on balanced waste disposal volume described in this invention, the following steps are included in the real-time monitoring of the status of waste collection points and the immediate activation of the emergency plan when abnormal accumulation occurs: The monitoring system acquires real-time status data of garbage collection points in each area, including real-time garbage volume and predicted garbage volume; An anomaly detection algorithm is used to calculate the deviation ratio between the amount of garbage in each area and the predicted value, and compare it with the abnormal growth threshold. When the deviation ratio is greater than the threshold, it is determined that the amount of garbage in area A has increased abnormally. Once an area of ​​abnormal growth is identified, the emergency plan will be automatically triggered, including increasing the temporary deployment of waste treatment facilities, mobilizing additional cleaning teams, adjusting waste collection frequency measures, and immediately notifying relevant management personnel to initiate the emergency response procedure.

[0013] As a preferred embodiment of the sanitation zone division method based on balanced waste disposal volume as described in this invention, the following steps are included: rapidly adjusting the zone division, replanning operational routes, and dynamically adjusting resource allocation strategies according to the emergency plan: Use the balance assessment function to reassess the balance of waste treatment capacity under the current zoning and identify which zoning areas need adjustment; Based on the location information and waste volume of abnormal areas, a genetic algorithm is used to optimize the area division so that the waste processing capacity of each area matches the waste volume. By combining the TSP algorithm with the particle swarm optimization algorithm, the operating routes of garbage collection vehicles are replanned by prioritizing abnormal areas, thus quickly handling garbage accumulation. The optimized operating routes are sent to the navigation system of the garbage collection trucks and updated in real time. Based on the updated zoning and operational routes, the required manpower and vehicle resources for each zone are recalculated using resource scheduling functions. For areas with severe garbage accumulation, the scheduling of sanitation vehicles and personnel is increased. Update the resource scheduling plan to allocate and utilize resources rationally and efficiently; Based on the latest resource scheduling plan, the system automatically generates scheduling instructions for sanitation workers and vehicles; Dispatch instructions are instantly pushed to frontline staff and garbage collection trucks via mobile terminals and vehicle-mounted systems to carry out garbage collection work.

[0014] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the sanitation area division method based on waste disposal volume business balancing as described in the first aspect of the present invention.

[0015] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the sanitation area division method based on waste disposal volume business balancing as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By collecting and pre-processing data on the average daily amount of garbage at each garbage collection point, the processing capacity of garbage transfer stations, geographical location information, and external influencing factors, the comprehensiveness and accuracy of the data are improved; by predicting the amount of garbage in each area in the future based on a deep learning model, and by using a hybrid model combining convolutional neural networks and recurrent neural networks, accurate prediction of garbage volume trends is achieved; based on the predicted garbage volume and the real-time data after pre-processing, areas with abnormal garbage volume growth are identified, and optimization algorithms are used to dynamically adjust the area division, improving the response speed and adaptability of sanitation work; by monitoring the status of garbage collection points in real time, an emergency plan is immediately activated when abnormal accumulation occurs. Through anomaly detection algorithms and emergency response procedures, areas with abnormal garbage volume growth can be quickly identified and dealt with, avoiding environmental problems and social impacts caused by delayed garbage disposal, and ensuring environmental sanitation and public health. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the sanitation area division method based on the business balance of waste disposal volume in the embodiment.

[0019] Figure 2 This is a threshold division diagram for abnormal growth in the embodiment. Detailed Implementation

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0023] Reference Figure 1 and Figure 2 This is one embodiment of the present invention, which provides a method for dividing sanitation areas based on the balance of waste disposal volume, including the following steps: S1. Collect and process in real time the average daily amount of garbage at each garbage collection point, the processing efficiency of garbage transfer stations, geographical location information, and data on external influencing factors.

[0024] External influencing factor data includes data on the impact of weather, holidays, population flow and activities on waste generation; preliminary processing includes filling missing values, detecting and correcting outliers, and standardizing data for daily average waste volume, waste transfer station processing efficiency, geographical location information and external influencing factor data, and converting non-numerical external influencing factors into numerical data using one-hot encoding.

[0025] S2. Based on a deep learning model, predicting the amount of garbage in each region over a future period includes the following steps: External influencing factor data is feature-encoded, with one-hot encoding used for categorical variables to convert them into numerical types. A hybrid model combining convolutional neural networks and recurrent neural networks is selected, and the model structure is designed. The neural network layers in the model structure handle the local correlation of features, while the recurrent neural network captures the temporal sequence of the data. The model is trained using the pre-processed data to minimize the mean squared error loss function between the predicted and actual waste amounts. An attention mechanism is introduced to enhance the hybrid model's ability to capture important features. Current waste amount data and external influencing factor data are input into the trained model in real time to predict the waste amount changes in various regions over a future period, expressed as: ; in, E(t) represents the predicted amount of garbage at time t, where E(t) represents the historical garbage growth rate at time t. This parameter represents the adjustment of the historical waste volume growth rate. represents the adjustment factor for the amount of garbage at time point 𝑡, and 𝑐 represents the predictor factor that adjusts the scale of the predicted value. This indicates the intensity of the impact of quantified weather factors on waste volume forecasting. This represents the amount of garbage data at point in time. This represents data on external influencing factors at point in time, including holidays, population movement, and activities. This indicates the strength of the impact of external influencing factors such as holidays, population movement, and activity data on waste volume prediction. This indicates the weather factors at point in time.

[0026] It should be noted that feature encoding of external influencing factor data and one-hot encoding of categorical variables, converting them into numerical types, allow the model to independently learn the influence of each category, avoiding potential biases between categories and thus improving prediction accuracy. Convolutional Neural Networks (CNNs) excel at handling spatial local correlations, while Recurrent Neural Networks (RNNs) can capture time-series dependencies. Combining the two, the model can simultaneously analyze the spatial distribution and temporal trends of waste volume, enabling the system to understand not only historical waste volume patterns in a specific region but also recent fluctuations and long-term trends, resulting in more accurate predictions. By training the model using historical waste volume data and external influencing factor data and minimizing the mean squared error loss function between the predicted and actual waste volume, the system can more reliably predict future waste volume, which is crucial for resource planning and emergency preparedness. By centrally processing key information, the model's predictive ability is enhanced, especially when dealing with complex or nonlinear relationships, enabling it to more accurately reflect the impact of external factors on waste volume. Real-time data input allows the system to dynamically adjust predictions based on the latest situation, ensuring the timeliness and practicality of the prediction results.

[0027] S3. Based on the predicted waste volume and real-time data after preliminary treatment, identify areas of abnormal waste growth and dynamically adjust the area division using optimization algorithms, including the following steps: Construct a balance evaluation function to measure whether the waste treatment capacity of each region is balanced at point R. The expression is: ; in, This represents the equilibrium assessment value of waste management efficiency across different areas at time point N, where N is the total number of areas. This represents the predicted amount of waste in the nth area at time point R. This indicates the waste disposal efficiency of the nth area at time point R. This represents the average waste disposal efficiency across all areas of the region at a given time point. Set an abnormal growth threshold 𝜃. When the ratio of the predicted amount of waste in region 𝑖 to the amount of waste in region 𝑖 is greater than the abnormal growth threshold, the amount of waste in region 𝑖 is considered to have increased abnormally. The fitness function is designed, combining the predicted waste volume, the processing capacity of regional transfer stations, and location information. A genetic algorithm is then used to optimize the region partitioning. The expression is: ; in, Indicates the regional division scheme. Indicating the regional division scheme The fitness function value, It is a weighting coefficient that measures the balance of waste treatment efficiency across different regions. It is a weighting coefficient that measures the maximum waste management efficiency across all regions. It is a geographical distance weighting coefficient. It is the average geographical distance.

[0028] Furthermore, we define an abnormal growth region identification function to identify regions with abnormally increasing garbage volume. The expression is: ; in, A binary identifier for anomaly detection in the nth region at time point r. The average predicted amount of waste for all areas. The standard deviation is used to indicate an area with abnormal growth if the predicted amount of waste exceeds the average plus one standard deviation.

[0029] Furthermore, the fitness function The range of its value is [0, 1].

[0030] when When =1, it indicates that the waste treatment efficiency of each area is completely balanced, and the processing capacity of the regional transfer station is fully utilized.

[0031] when A value less than 1 indicates a certain degree of imbalance or underutilization of processing capacity.

[0032] when When the value is 0, it indicates that the waste disposal efficiency in different areas is extremely uneven, or that the processing capacity of the regional transfer station is seriously insufficient.

[0033] Furthermore, the expression for the average geographical distance under the regional division scheme is: ; in, Indicates the first A collection of garbage collection points within a certain area. Indicates the first The distance from the garbage collection point in the area to the nearest garbage transfer station.

[0034] It should be noted that by calculating the sum of squared deviations between the predicted waste volume and processing capacity ratio of each region and the average ratio, the degree of imbalance between regions is quantified. This helps to identify areas with high waste processing pressure in real time and promotes a balanced allocation of resources throughout the system, avoiding situations where some areas are overloaded while other areas are idle, thereby improving the overall waste processing efficiency and system stability. Setting an abnormal growth threshold and comparing the predicted waste volume with the current processing volume accurately identifies areas with abnormal waste growth, preventing processing delays caused by sudden increases in waste volume, reducing the impact on the urban environment, and ensuring the normal order of citizens' lives. By minimizing the average distance between waste collection points and transfer stations, logistics costs are reduced while ensuring a match between waste processing capacity and demand, thereby improving the overall system's operational efficiency and economic benefits. By defining an abnormal growth area identification function, the system can automatically identify areas where waste volume exceeds the normal range and promptly activate the early warning mechanism, ensuring that the system can take rapid measures when waste volume increases abnormally, avoiding environmental pollution and public health problems caused by waste accumulation, and protecting the cleanliness of the city and the health of residents.

[0035] S4. Based on the adjusted zoning, replan the operating routes of garbage collection vehicles and implement a resource scheduling plan, including the following steps: Based on the optimized region division results, the TSP (Traveling Salesman Problem) algorithm combined with the particle swarm optimization algorithm is used to plan the operating routes of garbage collection trucks and minimize the total travel distance. A resource scheduling function is designed to dynamically allocate sanitation vehicles and personnel based on the predicted garbage volume and the number of abnormally growing areas. The expression is as follows: ; in, For at a certain point in time The resource scheduling function value, It is the distance influence factor. It refers to the number of areas with abnormal growth. Indicates based on the number of abnormal growth areas Adjustment coefficient.

[0036] Furthermore, the specific process for defining the abnormal growth threshold is as follows: Low abnormal growth threshold range (0 < R ≤ 1.2): This means that even a slight increase in the amount of garbage will be marked as abnormal. It is suitable for scenarios that are very sensitive to changes in the amount of garbage, such as high-density residential areas, before holidays, and before major events. In these scenarios, the amount of garbage may increase suddenly and slightly, requiring early warning and preparation. The abnormal growth threshold range (1.2 < R ≤ 1.5) indicates the distinction between normal fluctuations in waste volume and more obvious abnormal growth. It is suitable for most daily scenarios, such as regular weekdays or non-holidays. The amount of waste fluctuates normally with time and weather, but is generally controllable. It is necessary to allocate resources reasonably to deal with possible increases in waste volume. High abnormal growth threshold range (p>1.5): This means that only when there is a significant increase in waste volume will it be marked as abnormal. This setting is suitable for areas with strong waste treatment capacity or a large buffer margin, such as waste treatment facilities in industrial areas or remote areas. These places have relatively small fluctuations in waste volume and relatively sufficient treatment capacity, and need to respond to sudden large increases in waste volume while ensuring efficient use of resources.

[0037] It should be noted that, based on the optimized regional division, the TSP algorithm combined with the particle swarm optimization algorithm is used to plan the operation routes of garbage collection vehicles, thereby minimizing the total travel distance, reducing fuel consumption, lowering carbon emissions, alleviating urban traffic pressure, and improving overall operational efficiency. Sanitation vehicles and personnel are dynamically allocated based on the predicted garbage volume and the number of abnormally growing areas. The exponential function's sensitive response to the number of abnormally growing areas ensures that additional resource support can be quickly obtained in areas with abnormally increasing garbage volume.

[0038] S5. Monitor the status of garbage collection points in real time. If abnormal accumulation occurs, immediately activate the emergency plan, including the following steps: The monitoring system acquires real-time status data of garbage collection points in each area, including real-time garbage volume and predicted garbage volume; it uses an anomaly detection algorithm to calculate the deviation ratio between the garbage volume and the predicted value in each area, and compares it with the abnormal growth threshold. When the deviation ratio is greater than the threshold, it is determined that the garbage volume in area A has increased abnormally; once an area with abnormal growth is identified, the system automatically triggers the emergency plan, increases the temporary deployment of garbage treatment facilities, mobilizes additional cleaning teams, adjusts garbage collection frequency measures, and immediately notifies relevant management personnel to start the emergency response procedure.

[0039] It should be noted that by monitoring the status of garbage collection points in real time, the system achieves immediate control over the operation of the urban waste management system, enabling rapid response to abnormal increases in garbage volume. The system uses an anomaly detection algorithm to accurately calculate the deviation ratio between the garbage volume and the predicted value, comparing it with a pre-set abnormal growth threshold. This intelligently distinguishes between normal fluctuations and abnormal growth, avoiding ineffective resource allocation. Once an abnormal growth area is accurately identified, the system immediately activates its emergency plan, demonstrating its ability for immediate response and optimized resource allocation. Additional cleaning teams are mobilized to ensure sufficient manpower for cleaning work, improving efficiency. The garbage collection frequency is adjusted dynamically based on the actual garbage volume to avoid over-collection or under-collection, balancing resource usage. Simultaneously, the system immediately notifies relevant management personnel to activate emergency response procedures, ensuring timely information transmission and coordinated response actions.

[0040] S6. Based on the emergency plan, quickly adjust the area division, re-plan the operation route, and dynamically adjust the resource allocation strategy, including the following steps: The system uses a balance evaluation function to reassess the balance of waste disposal capacity under the current regional division, identifying which areas require adjustment. Based on the location information and waste volume of abnormal areas, a genetic algorithm is used to optimize the regional division, ensuring that the waste disposal capacity of each area matches the waste volume. A combination of the TSP algorithm and particle swarm optimization algorithm is employed to prioritize abnormal areas and replan the operating routes of waste collection trucks for rapid waste disposal. The optimized operating routes are then sent to the navigation systems of the waste collection trucks for real-time updates. Based on the updated regional division and operating routes, a resource scheduling function is used to recalculate the required manpower and vehicle resources for each area. For areas with severe waste accumulation, the scheduling of sanitation vehicles and personnel is increased. The resource scheduling plan is updated to allocate and utilize resources rationally and efficiently. Based on the latest resource scheduling plan, the system automatically generates scheduling instructions for sanitation personnel and vehicles. These instructions are then pushed to frontline staff and waste collection trucks in real-time via mobile terminals and vehicle systems to execute waste collection work.

[0041] It should be noted that through re-evaluation, the system can promptly identify imbalances in processing capacity caused by fluctuations in waste volume, thereby accurately locating areas requiring adjustment. This improves the overall flexibility and responsiveness of the waste management system, avoids resource waste and overload, and ensures stable operation of waste management. The genetic algorithm can simulate the natural selection process to find the optimal regional division scheme, ensuring that the waste processing capacity of each region is optimally matched with the waste volume. This not only improves the efficiency of waste management but also reduces the risk of accumulation due to insufficient processing capacity, while reducing unnecessary resource consumption and achieving refined management and efficient utilization of resources. The TSP algorithm, combined with particle swarm optimization, provides optimal path planning for waste collection vehicles. Especially in the face of abnormal waste accumulation, it can quickly adjust the operating route, prioritizing the cleaning of areas with larger waste volumes, improving operational efficiency, reducing waste retention time, avoiding environmental pollution and public health problems, and also reducing transportation costs and improving the overall economic benefits of the operation. By updating routes and scheduling plans in real time, the system can flexibly respond to emergencies, ensuring the continuity and effectiveness of waste management. The rational allocation and efficient use of resources not only improves the overall efficiency of sanitation work but also promotes resource conservation. The generation and instant push of automated dispatch instructions ensure the rapid transmission and execution of information, reduce human error, and improve the accuracy and speed of operations. Frontline staff and garbage collection trucks can receive the latest instructions immediately, respond quickly, and execute cleaning tasks efficiently, which greatly improves the responsiveness and operational efficiency of sanitation work and ensures the high-standard maintenance of urban environmental sanitation.

[0042] This embodiment also provides a computer device applicable to the sanitation area division method based on the balance of waste disposal volume, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the sanitation area division method based on the balance of waste disposal volume proposed in the above embodiment.

[0043] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0044] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the sanitation area division method based on the balanced operation of waste disposal volume as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0045] In summary, this invention improves the comprehensiveness and accuracy of data by collecting and pre-processing data on the average daily waste volume at each waste collection point, the processing capacity of waste transfer stations, geographical location information, and external influencing factors. It predicts waste volume trends in various regions over a future period using a deep learning model and a hybrid model combining convolutional neural networks and recurrent neural networks. Based on the predicted waste volume and the pre-processed real-time data, it identifies areas of abnormal waste growth and dynamically adjusts area divisions using optimization algorithms, improving the response speed and adaptability of sanitation work. Real-time monitoring of waste collection point status triggers emergency plans immediately upon abnormal accumulation. Through anomaly detection algorithms and emergency response procedures, it can quickly identify and address areas of abnormal waste growth, avoiding environmental problems and social impacts caused by delayed waste disposal, and safeguarding environmental sanitation and public health.

[0046] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for dividing sanitation areas based on the operational balance of waste disposal volume, characterized in that: include, The system collects and processes data in real time, including the average daily amount of waste at each collection point, the processing efficiency of waste transfer stations, geographical location information, and data on external influencing factors. Based on a deep learning model, predict the amount of waste in each region over a future period. Based on the predicted waste volume and real-time data after preliminary treatment, identify areas with abnormal waste growth and dynamically adjust the area division; Based on the adjusted zoning, the operating routes of garbage collection vehicles were replanned and a resource scheduling plan was implemented; Monitor the status of garbage collection points in real time, and immediately activate the emergency plan if abnormal accumulation occurs; Based on the emergency plan, the area division was quickly adjusted, the operation route was replanned, and the resource allocation strategy was dynamically adjusted.

2. The sanitation area division method based on waste disposal volume business balance as described in claim 1, characterized in that: The data on external influencing factors includes data on the impact of weather, holidays, population movement, and activities on waste generation.

3. The sanitation area division method based on waste disposal volume business balance as described in claim 1, characterized in that: The preliminary processing includes filling missing values, detecting and correcting outliers, and standardizing data on daily average waste volume, waste transfer station processing efficiency, geographical location information, and external influencing factors. Non-numerical external influencing factors are converted into numerical data using one-hot encoding.

4. The sanitation area division method based on waste disposal volume business balance as described in claim 3, characterized in that: Predicting the amount of waste in various regions over a future period based on a deep learning model includes the following steps: Choose a hybrid model combining convolutional neural networks and recurrent neural networks, and design the model structure; Recurrent neural networks capture the temporal nature of sequential data by processing the local correlation of features through neural network layers in the model structure. The model is trained using the pre-processed data, and the mean squared error loss function between the predicted amount of garbage and the actual amount of garbage is minimized. Input current waste volume data and external influencing factor data into a trained hybrid model in real time to predict the change in waste volume in various regions over a future period.

5. The sanitation area division method based on waste disposal volume business balance as described in claim 4, characterized in that: Based on the predicted waste volume and real-time data after preliminary treatment, areas with abnormal waste growth are identified, and optimization algorithms are used to dynamically adjust the area division, including the following steps: Construct a balance evaluation function to measure whether the waste treatment efficiency of different regions is balanced; An abnormal growth threshold is set. When the ratio of the predicted amount of waste in region A to the amount of waste in region B is greater than the abnormal growth threshold, the amount of waste in region A is considered to have increased abnormally. A fitness function is designed, which combines the predicted waste volume, the processing capacity of regional transfer stations, and location information, and a genetic algorithm is used to optimize the regional division.

6. The sanitation area division method based on waste disposal volume business balance as described in claim 5, characterized in that: Based on the adjusted zoning, the replanning of garbage collection truck operating routes and the implementation of resource scheduling plans include the following steps: Based on the optimized area division results, the TSP algorithm combined with the particle swarm optimization algorithm is used to plan the operation route of the garbage collection truck and minimize the total travel distance. Design a resource scheduling function to dynamically allocate sanitation vehicles and personnel based on the predicted amount of garbage and the number of areas with abnormal growth.

7. The sanitation area division method based on waste disposal volume business balance as described in claim 6, characterized in that: Real-time monitoring of the status of garbage collection points, and immediate activation of the emergency plan upon detection of abnormal accumulation, including the following steps: The monitoring system acquires real-time status data of garbage collection points in each area, including real-time garbage volume and predicted garbage volume; An anomaly detection algorithm is used to calculate the deviation ratio between the amount of garbage in each area and the predicted value, and compare it with the abnormal growth threshold. When the deviation ratio is greater than the threshold, it is determined that the amount of garbage in area A has increased abnormally. Once an area of ​​abnormal growth is identified, the emergency plan will be automatically triggered, including increasing the temporary deployment of waste treatment facilities, mobilizing additional cleaning teams, adjusting waste collection frequency measures, and immediately notifying relevant management personnel to initiate the emergency response procedure.

8. The sanitation area division method based on waste disposal volume business balance as described in claim 7, characterized in that: According to the emergency plan, the rapid adjustment of the area division, the replanning of the operation route, and the dynamic adjustment of the resource allocation strategy include the following steps: Use the balance assessment function to reassess the balance of waste treatment capacity under the current zoning and identify which zoning areas need adjustment; Based on the location information and waste volume of abnormal areas, a genetic algorithm is used to optimize the area division so that the waste processing capacity of each area matches the waste volume. By combining the TSP algorithm with the particle swarm optimization algorithm, the operating routes of garbage collection vehicles are replanned by prioritizing abnormal areas, thus quickly handling garbage accumulation. The optimized operating routes are sent to the navigation system of the garbage collection trucks and updated in real time. Based on the updated zoning and operational routes, the required manpower and vehicle resources for each zone are recalculated using resource scheduling functions. For areas with severe garbage accumulation, the scheduling of sanitation vehicles and personnel is increased. Update the resource scheduling plan to allocate and utilize resources rationally and efficiently; Based on the latest resource scheduling plan, the system automatically generates scheduling instructions for sanitation workers and vehicles; Dispatch instructions are instantly pushed to frontline staff and garbage collection trucks via mobile terminals and vehicle-mounted systems to carry out garbage collection work.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the sanitation area division method based on the balance of waste disposal volume as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the sanitation area division method based on the balance of waste disposal volume as described in any one of claims 1 to 7.

Images