Government-oriented environmental sanitation station planning distribution intelligent decision-making method and system

Abstract

The invention discloses a government-oriented environmental sanitation station planning distribution intelligent decision-making method and system, and relates to the technical field of environmental sanitation station planning decision-making. The method comprises the following steps: acquiring multi-class distribution decision data related to environmental sanitation station planning, wherein the distribution decision data comprises geographic information data, territorial resource planning data, demographic data, traffic flow data and economic data; obtaining an influence factor between each type of distribution decision data and the garbage generation amount; inputting the influence factors into a deep learning-based environmental sanitation station planning distribution prediction model to obtain the probability that each position in the to-be-planned area is set as an environmental sanitation station; and obtaining a sanitation station layout result of the to-be-planned area according to the numerical value of the probability that each position is set as the sanitation station. By means of the method and the related system, the scientific layout of the environmental sanitation station can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of sanitation station planning and decision-making, and more specifically to a government-oriented sanitation station planning distribution intelligent decision-making method and system. Background Art

[0002] At present, the preliminary planning of sanitation stations is based on the existing land use of the streets, relying on experience and subjective judgment, and lacking a decision-making process based on data analysis, which leads to the unscientific site selection and layout of sanitation stations. As a result, the planning results of sanitation stations have defects such as insufficient coverage with a certain probability, and a large amount of resources need to be allocated in the later stage, resulting in high operating costs and slow response speed in the later stage.

[0003] Therefore, how to design a data-driven intelligent decision-making method and system for sanitation station planning and distribution is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0004] In view of this, the present invention provides a government-oriented intelligent decision-making method and system for planning and distributing sanitation stations, which is used to at least solve some of the technical problems in the background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] The present invention first discloses a government-oriented intelligent decision-making method for sanitation station planning and distribution, comprising the following steps:

[0007] Acquire multiple types of distribution decision data related to sanitation station planning, the distribution decision data including: geographic information data, land resources planning data, demographic data, traffic flow data and economic data;

[0008] Obtain the influencing factors between each type of distribution decision data and the amount of garbage generated;

[0009] The influencing factors are input into a deep learning-based sanitation station planning distribution prediction model to obtain the probability of each location in the planned area being set as a sanitation station;

[0010] The layout result of sanitation stations in the area to be planned is obtained according to the numerical value of the probability of each location being set as a sanitation station.

[0011] Further, the influencing factors between each type of distribution decision data and the amount of garbage generated are obtained, which specifically includes the following steps:

[0012] Based on the characteristics of each type of distribution decision data, a regression analysis model between garbage production and each type of distribution decision data is constructed;

[0013] According to the regression model, the relationship between the garbage production volume and the corresponding distribution decision data is obtained;

[0014] The relationship value obtained for each type of distribution decision data is multiplied by the weight value of the distribution decision data as the influencing factor between each type of distribution decision data and the amount of garbage generated.

[0015] Furthermore, the sanitation station planning distribution prediction model is constructed through the Keras deep learning framework.

[0016] Furthermore, it is characterized in that the influencing factors are input into a sanitation station planning distribution prediction model based on deep learning to obtain the probability of each location in the planned area being set as a sanitation station, which specifically includes the following steps:

[0017] The output results of the sanitation station planning distribution prediction model are mapped to the probability space through the linear transformation layer, and the softmax layer is used to generate the probability of each location being set as a sanitation station.

[0018] Furthermore, the layout result of the sanitation stations in the area to be planned is obtained according to the numerical value of the probability of each location being set as a sanitation station, which specifically includes:

[0019] When the probability value of a certain location in the area to be planned is greater than or equal to the set threshold, the location is planned as a sanitation station;

[0020] When the probability value of a certain location in the planned area is less than the set threshold, the planning layout of the sanitation station will not be carried out at that location.

[0021] Furthermore, the above method also includes: using simulation technology to simulate the garbage collection process of the sanitation station layout results to evaluate the effect of the sanitation station layout results.

[0022] Furthermore, in the above method, the geographic information data includes: existing urban road network data, building distribution data, green space data, and topographic data in the area;

[0023] Land and resources planning data include: land use planning data, transportation planning data, and policies, regulations and environmental protection standards data;

[0024] Demographic data include: population distribution data, population quantity data, population density data, and population flow data in the area;

[0025] Traffic flow data include: road traffic flow monitoring data and public transportation route data;

[0026] Economic data include: construction cost data, operating cost data, waste disposal and transportation cost data, and fiscal budget and funding allocation data.

[0027] Furthermore, the above method also includes: visually displaying the layout results of the sanitation stations in the area to be planned in three dimensions.

[0028] Furthermore, the above method also includes: performing actual layout of sanitation stations based on the layout results of sanitation stations in the area to be planned, and remotely monitoring the garbage storage status and garbage classification characteristics of each sanitation station in real time, and issuing a reminder message when the garbage storage volume of the sanitation station exceeds a preset value.

[0029] The present invention also provides a government-oriented intelligent decision-making system for sanitation station planning and distribution, comprising:

[0030] Data acquisition module: used to acquire multiple types of distribution decision data related to sanitation station planning, including geographic information data, land resources planning data, demographic data, traffic flow data and economic data;

[0031] Impact factor construction module: used to obtain the impact factor between each type of distribution decision data and the amount of garbage generated by using the regression analysis model;

[0032] Sanitation station distribution prediction module: used to input the influencing factors into the sanitation station planning distribution prediction model based on deep learning, to obtain the probability of each location in the area to be planned being set as a sanitation station; and to obtain the sanitation station layout result of the area to be planned according to the numerical value of the probability of each location being set as a sanitation station.

[0033] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a government-oriented intelligent decision-making method and system for sanitation station planning and distribution, which has the following beneficial effects:

[0034] The present invention comprehensively considers the impact of various distribution decision data on the layout of sanitation stations, and adopts a data-driven approach to predict the distribution results of sanitation stations using a sanitation station planning distribution prediction model based on deep learning, thereby realizing the scientific layout of sanitation stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0036] Figure 1 A schematic diagram of the overall process of the government-oriented intelligent decision-making method for planning and distribution of sanitation stations provided by the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] The embodiment of the present invention first discloses a government-oriented intelligent decision-making method for sanitation station planning distribution. Figure 1 The following steps are shown:

[0039] Acquire multiple types of distribution decision data related to sanitation station planning, the distribution decision data including: geographic information data, land resources planning data, demographic data, traffic flow data and economic data;

[0040] Obtain the influencing factors between each type of distribution decision data and the amount of garbage generated;

[0041] The influencing factors are input into a deep learning-based sanitation station planning distribution prediction model to obtain the probability of each location in the planned area being set as a sanitation station;

[0042] The layout result of sanitation stations in the area to be planned is obtained according to the numerical value of the probability of each location being set as a sanitation station.

[0043] Each step of the embodiment of the present invention is further explained below. First, in order to improve the rationality and scientificity of sanitation station planning, the present invention obtains multiple types of distribution decision data related to sanitation station planning. Specifically, the distribution decision data includes but is not limited to: geographic information data, land and resources planning data, demographic data, traffic flow data, and economic data.

[0044] Furthermore, the geographic information data includes: existing urban road network data, building distribution data, green space data, and topographic data in the area. The geographic information data in this embodiment can be derived from remote sensing data and CIM data. The building distribution data can specifically include the location and distribution data of infrastructure such as parks, squares, schools, shopping malls, residences, hospitals, fire stations, and police stations.

[0045] Land and resources planning data include: land use planning data, traffic planning data, and policy and regulations and environmental protection standards data; the land and resources planning data in this embodiment can come from the government planning department

[0046] The demographic data includes: population distribution data, population quantity data, population density data, and population flow data of the region; in this embodiment, the demographic data comes from the government statistics department.

[0047] Traffic flow data includes: road traffic flow monitoring data and public transportation line data; in this embodiment, the traffic flow data can be obtained through the traffic management department.

[0048] The economic data includes: construction cost data, operation cost data, garbage disposal and transportation cost data, and fiscal budget and fund allocation data. In this embodiment, the economic data comes from the government finance department.

[0049] Then, according to each type of distribution decision data obtained, the influence factor between each type of distribution decision data and the amount of garbage generated is determined. In this embodiment, a regression model is first used to obtain the predicted value of each type of distribution decision number and garbage output, and then the predicted value is multiplied by the corresponding weight to obtain the final influence factor. The specific steps are as follows:

[0050] Based on the characteristics of each type of distribution decision data, a regression analysis model between garbage production and each type of distribution decision data is constructed;

[0051] According to the regression model, the relationship between the garbage production volume and the corresponding distribution decision data is obtained;

[0052] The relationship value obtained for each type of distribution decision data is multiplied by the weight value of the distribution decision data as the influence factor between each type of distribution decision data and the amount of garbage generated. In this step, the sum of the weights of each type of distribution decision data is 1.

[0053] In addition, before using the regression model to predict the garbage production volume of the distribution decision data, preprocessing operations such as data completion and normalization are also included for the distribution decision data. The detailed steps of the preprocessing are not discussed again.

[0054] Next, a deep learning-based sanitation station planning distribution prediction model was constructed using the Keras deep learning framework. The sanitation station planning distribution prediction model uses an input layer to accept the influencing factors between each type of distribution decision data and the amount of garbage generated, and maps the output results of the sanitation station planning distribution prediction model to a probability space through a linear transformation layer. Finally, a softmax layer is used to generate the probability of each location being set as a sanitation station.

[0055] Finally, the layout of sanitation stations in the planned area is obtained according to the numerical value of the probability of each location being set as a sanitation station. Specifically:

[0056] When the probability value of a certain location in the area to be planned is greater than or equal to the set threshold, the location is planned as a sanitation station;

[0057] When the probability value of a certain location in the planned area is less than the set threshold, the planning layout of the sanitation station will not be carried out at that location.

[0058] For the planning and layout results of sanitation stations, other prediction models can also be used for prediction in other embodiments, such as directly predicting the distribution decision data by constructing a convolutional neural network (CNN) model. For such neural network prediction models, the number of nodes in the input layer should match the dimension of the features, and the complexity and learning ability of the model can be increased by adding hidden layers. The following is a detailed introduction to some specific structures and optional features of the convolutional neural network model.

[0059] 1. Input layer: Design an appropriate input layer to process the input data. For image data, it is usually a three-dimensional shape (width, height, number of channels), and for time series data it may be a two-dimensional or three-dimensional shape (time step, feature dimension, number of channels). The input layer accepts feature data related to the sanitation station, which may include the location of the sanitation station, the surrounding environment, weather conditions, etc. These feature data may be two-dimensional or three-dimensional.

[0060] 2. Convolutional layer and pooling layer: to improve the representation ability of the model. Add a Flatten layer before the fully connected layer to flatten the feature map. The convolutional layer is used to extract feature information. The input data is convolved by a sliding convolution kernel to generate a feature map. The pooling layer is used to reduce the dimension of the feature map, reduce the amount of calculation and retain important information. Usually, the maximum pooling or average pooling operation is used.

[0061] 3. Fully connected layer for classification or regression tasks. The output of the pooling layer is flattened into a one-dimensional vector as the input of the fully connected layer. The fully connected layer is used to learn the relationship between features. It can contain multiple hidden layers and neurons, and introduce nonlinearity through activation functions.

[0062] 4. Output layer: The output layer is determined according to the task requirements. It can be one node for binary classification tasks (such as whether the sanitation station is suitable), or multiple nodes for multi-classification tasks (such as the distribution area of ​​sanitation stations). For binary classification tasks, the sigmoid activation function is usually used; for multi-classification tasks, the softmax activation function is usually used.

[0063] In order to facilitate observation of the layout results, in a specific embodiment, the layout results of the sanitation stations in the area to be planned are displayed in three-dimensional visualization, and are displayed in a management manner of one map of the sanitation stations.

[0064] In order to ensure the accuracy of the planning and layout of the sanitation station, after obtaining the planning and layout results, simulation technology can also be used to simulate the garbage collection process of the sanitation station layout results to evaluate the effect of the sanitation station layout results.

[0065] The sanitation station layout results can also be evaluated using the following models or formulas:

[0066] Calculate the service lines or areas of sanitation stations:

[0067] The service density here refers to the number of people served by each unit.

[0068] Calculate the total demand for sanitation station facilities:

[0069] This formula is used to provide the required number of sanitation stations.

[0070] Determine resource allocation for sanitation stations:

[0071] The resource allocation of each sanitation station can be determined by the demand ratio.

[0072] Determine resource allocation based on waste generation:

[0073] Where N: the number of sanitation stations required; D: the predicted amount of garbage generated (tons / day); C: the processing capacity of a single sanitation station (tons / day); H: working hours (hours / day).

[0074] Cost analysis and evaluation: TC = (FC + VC) * N, TC: total cost; FC: fixed cost (construction and equipment investment); VC: variable cost (operation and maintenance cost); N: number of sanitation stations.

[0075] Determine transport efficiency:

[0076] TE=T\D, where TE: transportation efficiency; T: transportation time (hours); D: transportation distance (kilometers).

[0077] Through the above formula, the location, number, service scope and cost of sanitation stations can be analyzed and evaluated to ensure the rationality and economy of the planning.

[0078] As a further extension, the above method also includes: performing actual layout of sanitation stations based on the layout results of sanitation stations in the area to be planned, and remotely monitoring the garbage storage status and garbage classification characteristics of each sanitation station in real time, and issuing a reminder message when the garbage storage volume of the sanitation station exceeds a preset value.

[0079] In general, the ultimate goal of this application is to optimize resource allocation and service quality, and improve the efficiency and coverage of sanitation services. Through data-driven decision support, reduce transportation costs and evaluate environmental impacts to achieve sustainable urban development goals. By rationally planning the location and number of sanitation stations, optimize the allocation of human, material and financial resources, and improve resource utilization efficiency. Ensure the coverage of sanitation services, improve residents' satisfaction, and reduce the response time of cleaning and garbage disposal. By optimizing transportation routes and reducing transportation distances, reduce operating costs, thereby improving overall efficiency.

[0080] The present invention also provides a government-oriented intelligent decision-making system for sanitation station planning and distribution, comprising:

[0081] Data acquisition module: used to acquire multiple types of distribution decision data related to sanitation station planning, including geographic information data, land resources planning data, demographic data, traffic flow data and economic data;

[0082] Impact factor construction module: used to obtain the impact factor between each type of distribution decision data and the amount of garbage generated by using the regression analysis model;

[0083] Sanitation station distribution prediction module: used to input the influencing factors into the sanitation station planning distribution prediction model based on deep learning, to obtain the probability of each location in the area to be planned being set as a sanitation station; and to obtain the sanitation station layout result of the area to be planned according to the numerical value of the probability of each location being set as a sanitation station.

[0084] In this distributed decision-making system, the specific data processing process of each module can be referred to the description in the distributed decision-making method, and will not be repeated here. The system can be embedded in the urban planning management system as a whole to provide reliable technical support for the planning and distribution layout of sanitation stations.

[0085] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0086] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one 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 rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A government-oriented intelligent decision-making method for sanitation station planning and distribution, characterized in that: The following steps are involved: Acquire multiple types of distribution decision data related to sanitation station planning, the distribution decision data including: geographic information data, land resources planning data, demographic data, traffic flow data and economic data; Obtain the influencing factors between each type of distribution decision data and the amount of garbage generated; The influencing factors are input into a deep learning-based sanitation station planning distribution prediction model to obtain the probability of each location in the planned area being set as a sanitation station; The layout result of sanitation stations in the area to be planned is obtained according to the numerical value of the probability of each location being set as a sanitation station.

2. According to claim 1, a government-oriented intelligent decision-making method for sanitation station planning and distribution is characterized in that: Obtain the influencing factors between each type of distribution decision data and the amount of garbage generated, specifically The following steps are included: Based on the characteristics of each type of distribution decision data, a regression analysis model between garbage production and each type of distribution decision data is constructed; According to the regression model, the relationship between the garbage production volume and the corresponding distribution decision data is obtained; The relationship value obtained for each type of distribution decision data is multiplied by the weight value of the distribution decision data as the influencing factor between each type of distribution decision data and the amount of garbage generated.

3. According to claim 1, a government-oriented intelligent decision-making method for sanitation station planning and distribution is characterized in that: The sanitation station planning distribution prediction model is constructed using the Keras deep learning framework.

4. According to claim 1, a government-oriented intelligent decision-making method for sanitation station planning and distribution is characterized in that: The influencing factors are input into a sanitation station planning distribution prediction model based on deep learning to obtain the probability of each location in the planned area being set as a sanitation station, which specifically includes the following steps: The output results of the sanitation station planning distribution prediction model are mapped to the probability space through the linear transformation layer, and the softmax layer is used to generate the probability of each location being set as a sanitation station.

5. According to claim 1, a government-oriented intelligent decision-making method for sanitation station planning and distribution is characterized in that: The layout of sanitation stations in the planned area is obtained according to the numerical value of the probability of each location being set as a sanitation station, including: When the probability value of a certain location in the area to be planned is greater than or equal to the set threshold, the location is planned as a sanitation station; When the probability value of a certain location in the planned area is less than the set threshold, the planning layout of the sanitation station will not be carried out at that location.

6. According to claim 1, a government-oriented intelligent decision-making method for sanitation station planning and distribution is characterized in that: It also includes: using simulation technology to simulate the garbage collection process of the sanitation station layout results to evaluate the effectiveness of the sanitation station layout results.

7. According to claim 1, a government-oriented intelligent decision-making method for sanitation station planning and distribution is characterized in that: Geographic information data includes: existing urban road network data, building distribution data, green space data, and topographic data in the area; Land and resources planning data include: land use planning data, transportation planning data, and policies, regulations and environmental protection standards data; Demographic data include: population distribution data, population quantity data, population density data, and population flow data in the area; Traffic flow data include: road traffic flow monitoring data and public transportation route data; Economic data include: construction cost data, operating cost data, waste disposal and transportation cost data, and fiscal budget and funding allocation data.

8. According to claim 1, a government-oriented intelligent decision-making method for sanitation station planning and distribution is characterized in that: Also includes: The layout results of sanitation stations in the area to be planned are displayed in three-dimensional visualization.

9. According to claim 1, a government-oriented intelligent decision-making method for sanitation station planning and distribution is characterized in that: Also includes: The actual layout of sanitation stations is carried out based on the layout results of sanitation stations in the area to be planned, and the garbage storage status and garbage classification characteristics of each sanitation station are monitored remotely in real time. When the garbage storage volume of the sanitation station exceeds the preset value, a reminder message is issued.

10. A government-oriented intelligent decision-making system for sanitation station planning and distribution, characterized in that: include: Data acquisition module: used to acquire multiple types of distribution decision data related to sanitation station planning, including geographic information data, land resources planning data, demographic data, traffic flow data and economic data; Impact factor construction module: used to obtain the impact factor between each type of distribution decision data and the amount of garbage generated by using the regression analysis model; Sanitation station distribution prediction module: used to input the influencing factors into the sanitation station planning distribution prediction model based on deep learning, to obtain the probability of each location in the area to be planned being set as a sanitation station; and to obtain the sanitation station layout result of the area to be planned according to the numerical value of the probability of each location being set as a sanitation station.

Images