An island city integrated management method and system

Abstract

The present invention relates to an integrated management method and system for an island city, comprising the following steps: collecting historical environmental monitoring data, traffic monitoring data and resource data of the island city; constructing a meteorological prediction model and performing meteorological prediction, and calculating various natural disaster coefficients of the island city based on the meteorological prediction results and the historical environmental monitoring data; constructing a road flow model through the traffic monitoring data, and calculating the flow coefficient of each road in the island city through the road flow model; constructing a resource utilization efficiency model based on the resource data, and calculating the resource utilization efficiency coefficient of the island city through the resource utilization efficiency model; constructing an island city management decision model through various natural disaster coefficients of the island city, the flow coefficient of each road and the resource utilization efficiency coefficient, and providing a reference management decision plan for the island city through the island city management decision model.

Description

Technical Field

[0001] The invention relates to an island city integrated management method and system, belonging to the technical field of city management. Background Art

[0002] Island cities are usually affected by a marine climate, with mild temperatures and high humidity. They may also face extreme weather events, such as typhoons and storm surges, which have an impact on urban infrastructure and residents' lives. Climate change may cause sea level rise, threatening the survival of low-lying islands.

[0003] Since island cities are small in size, their traffic dispatch needs to ensure efficiency and reliability. Water resources and energy in island cities usually rely on local production or transportation from the main land. Due to the geographical area, local production is not efficient and land transportation has a certain timeliness, so it is necessary to plan resource allocation reasonably;

[0004] Existing patents, such as the invention patent with publication number "CN114282769A", disclose a digital twin island characteristic township management platform based on GIS, BIM and IoT, which can unify the Internet of Things IoT data, geographic information system GIS data, and building information model BIM data of island characteristic townships to form an integrated scheduling management system, solving the problems of complex data and easy information loss in traditional township management methods; according to the information collected by the data acquisition module, a twin island characteristic township management model is established, and real-time mapping is carried out with the actual island characteristic township. On the basis of the visualization of the actual island characteristic township data information, it also overcomes the problems of information asymmetry between users and management levels and untimely information transmission in traditional township management methods. However, the solution only proposes solutions for land management of island cities, and does not propose good solutions to the meteorological, transportation and resource allocation problems of island cities. Based on the above problems, it is necessary to design a comprehensive management method for island cities to solve them. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention proposes an island city integrated management method and system.

[0006] The technical solution of the present invention is as follows:

[0007] In one aspect, the present invention provides an island city integrated management method, comprising the following steps:

[0008] Collect historical environmental monitoring data, traffic monitoring data, and resource data of island cities;

[0009] Construct a meteorological forecast model and conduct meteorological forecasts, and calculate various natural disaster coefficients for island cities based on meteorological forecast results and historical environmental monitoring data;

[0010] A road flow model is constructed through traffic monitoring data, and the flow coefficient of each road in the island city is calculated through the road flow model;

[0011] Construct a resource utilization efficiency model based on resource data, and calculate the resource utilization efficiency coefficient of the island city through the resource utilization efficiency model;

[0012] An island city management decision model is constructed through various natural disaster coefficients of island cities, flow coefficients of each road, and resource utilization efficiency coefficients. The island city management decision model provides a reference management decision plan for island cities.

[0013] As a preferred embodiment of the present invention, the weather forecast model is constructed based on a ridge regression model;

[0014] The historical meteorological data of the island city is constructed as a training set and input into the meteorological prediction model. The meteorological prediction model is trained and the model outputs the future The forecast results of the day are used to calculate the loss of the meteorological forecast model based on the training forecast results, as shown in the following formula:

[0015]

[0016] in: represents the loss function of the weather forecast model; represents the parameter matrix of the model; represents the transpose of the model parameter matrix; The output of the model is Weather forecast for the day; Indicates The actual meteorological value corresponding to the weather forecast value; represents the ridge coefficient; Indicates the total number of forecast days;

[0017] The loss of the model is calculated by the above formula. If the loss is greater than the preset threshold, the parameters of the model are adjusted and trained again. If the loss is less than the preset threshold, the training is stopped to obtain a trained meteorological forecast model.

[0018] As a preferred embodiment of the present invention, the natural disaster coefficient of the island city includes a typhoon disaster coefficient and a tsunami disaster coefficient;

[0019] Divide island cities into multiple regions and construct typhoon disaster coefficients The calculation formula is as follows:

[0020]

[0021] in: Indicates the highest wind speed in the weather forecast results; Indicates the lowest air pressure in the weather forecast results; Indicates the overall rainfall in the weather forecast results; represents the total number of island city areas; Indicates the island city Population density of the area; Indicates the island city The economic coefficient of a region; , are all weight parameters.

[0022] As a preferred embodiment of the present invention, the tsunami disaster coefficient The calculation formula is:

[0023]

[0024] in: Indicates the maximum wave height in the surrounding sea area during the observation time; It indicates the average distance between the starting point of waves in the surrounding sea area and the coast during the observation time; It represents the maximum rate at which waves from the surrounding sea area propagate to the coast during the observation time; represents the seabed friction coefficient; It represents the average population density in the area surrounding the coast; represents the economic coefficient of the coastal surrounding area; Indicates the volume of water in the surrounding sea; Indicates the length of observation time; represents the risk factor that changes over time; represents the seafloor sediment coefficient; , , , are all weight parameters.

[0025] As a preferred embodiment of the present invention, the road flow model is constructed based on a graph neural network, and the urban traffic network is represented by a graph neural network, wherein nodes represent intersections and edges represent roads. The corresponding feature vectors of each node and edge are defined based on the road traffic data in the traffic monitoring data, and the feature vectors of the network nodes at each time step are updated and iterated by the following formula:

[0026]

[0027] in: Representation Node In the The feature vector of the iteration; is the activation function; Indicates The weight matrix of the iteration; Representation Node The total number of adjacent nodes; Representation Node Neighboring nodes In the The feature vector of the iteration; Indicates The bias matrix for the iteration; Representation Node In the The feature vector of the iteration;

[0028] The final model outputs the flow data of each road at each time step, and calculates the flow coefficient of each road based on the flow data, as shown in the following formula:

[0029]

[0030]

[0031] in: Indicates The next time step Road flow coefficient; represents the total number of time steps; Indicates the road flow per unit time; Indicates the current road length; Indicates the current maximum road capacity; Indicates the average vehicle speed per unit time on the current road; Indicates the maximum speed of the current road per unit time; Indicates the average accident area per unit time on the current road; Indicates the number of traffic accidents per unit time on the current road; Indicates the length of the current time step.

[0032] As a preferred embodiment of the present invention, the resource utilization efficiency model is constructed based on the LightGBM model;

[0033] The preprocessed resource data is used to extract the distance between residential areas and reservoirs, water supply network layout, power grid layout, season, historical water and electricity demand in residential areas, and historical water and electricity demand in industrial areas, and a training set is constructed.

[0034] The training set is input into the LightGBM model for training, and the model loss is calculated by the following formula:

[0035]

[0036] in: Represents the loss function of the LightGBM model; Represents the gradient sum of all samples in the left subtree of the model; Represents the gradient sum of all samples in the right subtree of the model; Represents the gradient sum of all samples of the parent node; , , Respectively represent the number of samples of the left subtree, right subtree and parent node of the model; represents the weight parameter;

[0037] The gain of the split point at each iteration of the model is calculated through the above loss function, and the point with the maximum gain is selected as the split target for the next iteration;

[0038] The trained LightGBM model is used to predict the water and electricity demand in residential and industrial areas;

[0039] Construct a resource utilization efficiency coefficient calculation formula to calculate the resource utilization efficiency coefficient of each area , as shown in the following formula:

[0040]

[0041] in: Indicates the overall water demand of the current area; Indicates the current water demand of regional industrial areas; Indicates the water demand of residential areas in the current area; Indicates the average annual wastewater recovery rate of the current area; Indicates the overall area of ​​the current region; Indicates the electricity demand of the residential area in the current region; It represents the maintenance cost of power equipment in the current regional industrial zone; Indicates the current electricity demand of the regional industrial zone; Indicates the total amount of green energy available in the current area; Indicates the total amount of common energy available in the current area.

[0042] As a preferred embodiment of the present invention, the island city management decision model is used to manage the disaster prevention decision, road planning decision and resource allocation decision of the island city respectively;

[0043] For disaster prevention decisions, disaster prevention strategies for different natural disasters are set. Multiple levels are set based on the coefficient of each type of natural disaster. Each level corresponds to a different degree of disaster severity. According to the size of the natural disaster coefficient, the disaster prevention strategy of the corresponding level is selected;

[0044] For road planning decisions, roads are classified according to their flow coefficients, and different planning plans are set for different types of roads;

[0045] For resource allocation decisions, the resource allocation priority of each region is set based on the resource utilization efficiency coefficient of each region, and different resource allocation plans are implemented for regions with different priorities.

[0046] On the other hand, the present invention also provides an island city integrated management system, including a data acquisition module, a meteorological model construction module, a road flow model construction module, a resource utilization efficiency model construction module and an island city management decision module;

[0047] The data acquisition module is used to collect historical environmental monitoring data, traffic monitoring data and resource data of the island city;

[0048] The meteorological model building module is used to build a meteorological prediction model and perform meteorological prediction, and calculate various natural disaster coefficients of island cities based on meteorological prediction results and historical environmental monitoring data;

[0049] The road flow model building module is used to build a road flow model through traffic monitoring data, and calculate the flow coefficient of each road in the island city through the road flow model;

[0050] The resource utilization efficiency model building module is used to build a resource utilization efficiency model based on resource data, and calculate the resource utilization efficiency coefficient of the island city through the resource utilization efficiency model;

[0051] The island city management decision module is used to construct an island city management decision model through various natural disaster coefficients of the island city, the flow coefficient of each road and the resource utilization efficiency coefficient, and provide a reference management decision plan for the island city through the island city management decision model.

[0052] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0053] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0054] The present invention has the following beneficial effects:

[0055] 1. The present invention conducts comprehensive management of disaster prevention decisions, road planning decisions and resource allocation decisions of island cities based on constructing corresponding models and calculating natural disaster coefficients, road flow coefficients and resource utilization efficiency coefficients, thereby realizing integrated management of problems that are easily encountered in the development of island cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0057] 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.

[0058] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0059] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0060] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0061] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0062] Embodiment 1:

[0063] See also Figure 1 , an island city integrated management method, comprising the following steps:

[0064] Collect historical environmental monitoring data, traffic monitoring data, and resource data of island cities;

[0065] Construct a meteorological forecast model and conduct meteorological forecasts, and calculate various natural disaster coefficients for island cities based on meteorological forecast results and historical environmental monitoring data;

[0066] A road flow model is constructed through traffic monitoring data, and the flow coefficient of each road in the island city is calculated through the road flow model;

[0067] Construct a resource utilization efficiency model based on resource data, and calculate the resource utilization efficiency coefficient of the island city through the resource utilization efficiency model;

[0068] An island city management decision model is constructed through various natural disaster coefficients of island cities, flow coefficients of each road, and resource utilization efficiency coefficients. The island city management decision model provides a reference management decision plan for island cities.

[0069] As a preferred implementation of this embodiment, the weather forecast model is based on a ridge regression model and is used to predict future weather information for island cities;

[0070] The training set constructed based on the environmental monitoring data, which includes the temperature, humidity, wind speed, air pressure, wind direction, precipitation data of the island city and the historical ocean current, sea temperature, tide, and sea level change data of the surrounding sea areas of the island city, is input into the meteorological prediction model to train the meteorological prediction model and output the future The forecast results for the day include future wind speed, air pressure, rainfall probability, and rainfall. The loss of the meteorological forecast model is calculated based on the training forecast results, as shown in the following formula:

[0071]

[0072] in: represents the loss function of the weather forecast model; represents the parameter matrix of the model; represents the transpose of the model parameter matrix; The output of the model is Weather forecast for the day; Indicates The actual meteorological value corresponding to the weather forecast value; Represents the ridge coefficient, which is a hyperparameter that needs to be manually defined and adjusted to obtain the optimal value; Indicates the total number of forecast days;

[0073] The loss of the model is calculated by the above formula. If the loss is greater than the preset threshold, the parameters of the model are adjusted through the back propagation algorithm and then trained again. If the loss is less than the preset threshold, the training is stopped to obtain the trained weather forecast model.

[0074] The final model predicts the future weather of the island city using the following formula:

[0075]

[0076]

[0077]

[0078]

[0079]

[0080] in: It indicates the future temperature of the island city; It indicates the future rainfall of the island city; It represents the probability of future rainfall in the island city; It indicates the future wind speed of the island city; Indicates the future air pressure of the island city; Indicates the real-time temperature of the island city; Indicates the real-time humidity of the island city; Indicates the real-time wind speed of the island city; Indicates the real-time wind direction of island cities; Indicates the real-time rainfall in the island city; Indicates the ocean current information around the island city; Indicates the sea temperature information of the sea area surrounding the island city; Indicates the tidal information of the sea area surrounding the island city; Indicates the sea level information of the sea area surrounding the island city; - is the model parameter matrix The parameters of the training are completed.

[0081] As a preferred implementation of this embodiment, the natural disaster coefficient of the island city includes a typhoon disaster coefficient and a tsunami disaster coefficient;

[0082] Divide island cities into multiple regions and construct typhoon disaster coefficients The calculation formula is as follows:

[0083]

[0084] in: Indicates the highest wind speed in the weather forecast results; Indicates the lowest air pressure in the weather forecast results; Indicates the overall rainfall in the weather forecast results; represents the total number of island city areas; Indicates the island city Population density of the area; Indicates the island city The economic coefficient of a region; , They are all weight parameters, set based on experience.

[0085] The economic coefficient of the island city area The calculation formula is:

[0086]

[0087] in: Indicates the total GDP of the current region; represents the per capita labor cost in the current region; Indicates the total population of the current area; Indicates the infrastructure cost of the current area;

[0088] As a preferred implementation of this embodiment, the tsunami disaster coefficient The calculation formula is:

[0089]

[0090] in: Indicates the maximum wave height in the surrounding sea area during the observation time; It indicates the average distance between the starting point of waves in the surrounding sea area and the coast during the observation time; It represents the maximum rate at which waves from the surrounding sea area propagate to the coast during the observation time; represents the seabed friction coefficient; It represents the average population density in the area surrounding the coast; Indicates the economic coefficient of the coastal area. The calculation method is the same as the economic coefficient. ; Indicates the volume of water in the surrounding sea; Indicates the length of observation time; It indicates the risk factor that changes with time. The longer the time is, the greater the coefficient is. represents the seafloor sediment coefficient; , , , They are all weight parameters, set based on experience.

[0091] As a preferred implementation of this embodiment, the traffic dispatch management model is based on a graph neural network, which represents the urban traffic network, wherein nodes represent intersections and edges represent roads. The corresponding feature vectors of each node and edge are defined based on the road traffic data in the traffic monitoring data. The feature vector of the node includes the traffic light information at the intersection and the scheduling strategy of the traffic light. The feature vector of the edge includes the historical traffic flow information of the road and the waiting time of the traffic light of the vehicle at different times. The feature vector of the network node at each time step is updated and iterated by the following formula:

[0092]

[0093] in: Representation Node In the The feature vector of the iteration; is the activation function; Indicates The weight matrix of the iteration; Representation Node The total number of adjacent nodes; Representation Node Neighboring nodes In the The feature vector of the iteration; Indicates The bias matrix for the iteration; Representation Node In the The feature vector of the iteration;

[0094] The purpose of updating each network node is to propagate information in the network to each node, so that each node can take into account the status of its neighboring nodes and better predict information such as traffic flow and congestion;

[0095] The final model outputs the flow data of each road at each time step, and calculates the flow coefficient of each road based on the flow data, as shown in the following formula:

[0096]

[0097]

[0098] in: Indicates The next time step Road flow coefficient; represents the total number of time steps; Indicates the road flow per unit time; Indicates the current road length; Indicates the current maximum road capacity; Indicates the average vehicle speed per unit time on the current road; Indicates the maximum speed of the current road per unit time; Indicates the average accident area per unit time on the current road; Indicates the number of traffic accidents per unit time on the current road; Indicates the length of the current time step.

[0099] As a preferred implementation of the embodiment, the resource utilization efficiency model is constructed based on the LightGBM model, and the specific training steps are:

[0100] The preprocessed resource data is used to extract the distance between residential areas and reservoirs, water supply network layout, power grid layout, season, historical water and electricity demand in residential areas, and historical water and electricity demand in industrial areas, and a training set is constructed.

[0101] The training set is input into the LightGBM model for training, and the model loss is calculated by the following formula:

[0102]

[0103] in: Represents the loss function of the LightGBM model; Represents the gradient sum of all samples in the left subtree of the model; Represents the gradient sum of all samples in the right subtree of the model; Represents the gradient sum of all samples of the parent node; , , Respectively represent the number of samples of the left subtree, right subtree and parent node of the model; represents the weight parameter;

[0104] The gain of the split point at each iteration of the model is calculated through the above loss function, and the point with the maximum gain is selected as the split target for the next iteration;

[0105] In each iteration, the LightGBM model calculates the gradient of the loss function with respect to the current model prediction. In this embodiment, the gradient is the difference between the actual water and electricity demand and the model prediction.

[0106] Taking residential water use as an example, assuming that we already have the predicted water demand for each residential area and actual water demand , the gradient can be calculated by the following formula :

[0107]

[0108] Then, the split point is selected based on these gradients and feature data. For example, the feature data is the distance from the reservoir. Classification is performed based on the data features, the gain under different distance thresholds is calculated, and then the point with the largest gain is selected as the split point.

[0109] The trained LightGBM model is used to predict the water and electricity demand in residential and industrial areas;

[0110] Construct a resource utilization efficiency coefficient calculation formula to calculate the resource utilization efficiency coefficient of each area , as shown in the following formula:

[0111]

[0112] in: Indicates the overall water demand of the current area; Indicates the current water demand of regional industrial areas; Indicates the water demand of residential areas in the current area; Indicates the average annual wastewater recovery rate of the current area; Indicates the overall area of ​​the current region; Indicates the electricity demand of the residential area in the current region; It represents the maintenance cost of power equipment in the current regional industrial zone; Indicates the current electricity demand of the regional industrial zone; Indicates the total amount of green energy available in the current area; Indicates the total amount of common energy available in the current area.

[0113] As a preferred implementation of this embodiment, the island city management decision model is used to manage the disaster prevention decision, road planning decision and resource allocation decision of the island city respectively;

[0114] For disaster prevention decisions, disaster prevention strategies for different natural disasters are set. Multiple levels are set based on the coefficient of each type of natural disaster. Each level corresponds to a different degree of disaster severity. According to the size of the natural disaster coefficient, the disaster prevention strategy of the corresponding level is selected, as shown in the following table:

[0115]

[0116] For road planning decisions, roads are classified according to their flow coefficients, and different planning plans are set for different types of roads;

[0117] Specifically, roads are classified into high-volume roads, medium-volume roads, and low-volume roads;

[0118] High-traffic roads: preferably expand or add new roads, optimize traffic signals, and increase public transportation coverage;

[0119] Medium-volume roads: perform routine maintenance, monitor traffic conditions, and adjust traffic control measures in a timely manner;

[0120] Low-traffic roads: Maintain existing planning and conduct regular inspections to ensure that roads are in good condition.

[0121] For resource allocation decisions, the resource allocation priority of each region is set based on the resource utilization efficiency coefficient of each region, and different resource allocation plans are implemented for regions with different priorities;

[0122] Specifically, it is divided into high priority area, medium priority area and low priority area;

[0123] High priority area: optimally allocate resources to improve overall resource utilization efficiency;

[0124] Medium priority areas: Allocate resources appropriately according to demand and maintain stable development;

[0125] Low-priority areas: Adjust resources based on actual conditions to improve resource utilization efficiency.

[0126] Embodiment 2:

[0127] An island city integrated management system, comprising a data collection module, a meteorological model building module, a road flow model building module, a resource utilization efficiency model building module and an island city management decision module;

[0128] The data acquisition module is used to collect historical environmental monitoring data, traffic monitoring data and resource data of the island city;

[0129] The meteorological model building module is used to build a meteorological prediction model and perform meteorological prediction, and calculate various natural disaster coefficients of island cities based on meteorological prediction results and historical environmental monitoring data;

[0130] The road flow model building module is used to build a road flow model through traffic monitoring data, and calculate the flow coefficient of each road in the island city through the road flow model;

[0131] The resource utilization efficiency model building module is used to build a resource utilization efficiency model based on resource data, and calculate the resource utilization efficiency coefficient of the island city through the resource utilization efficiency model;

[0132] The island city management decision module is used to construct an island city management decision model through various natural disaster coefficients of the island city, the flow coefficient of each road and the resource utilization efficiency coefficient, and provide a reference management decision plan for the island city through the island city management decision model.

[0133] This system is used to implement the functions in the first embodiment, which will not be described in detail here.

[0134] Embodiment three:

[0135] This embodiment proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the island city integrated management method as described in any embodiment of the present invention is implemented.

[0136] Embodiment 4:

[0137] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the island city integrated management method as described in any embodiment of the present invention is implemented.

[0138] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0139] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0141] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0142] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An integrated management method for island cities, characterized in that: The following steps are involved: Collect historical environmental monitoring data, traffic monitoring data, and resource data of island cities; Construct a meteorological forecast model and conduct meteorological forecasts, and calculate various natural disaster coefficients of island cities based on meteorological forecast results and historical environmental monitoring data, wherein the natural disaster coefficients of island cities include typhoon disaster coefficients and tsunami disaster coefficients; Divide island cities into multiple regions and construct typhoon disaster coefficients The calculation formula is as follows: in: Indicates the highest wind speed in the weather forecast results; Indicates the lowest air pressure in the weather forecast results; Indicates the overall rainfall in the weather forecast results; represents the total number of island city areas; Indicates the island city Population density of the area; Indicates the island city The economic coefficient of a region; , All are weight parameters; The tsunami hazard factor The calculation formula is: in: Indicates the maximum wave height in the surrounding sea area during the observation time; It indicates the average distance between the starting point of waves in the surrounding sea area and the coast during the observation time; It represents the maximum rate at which waves from the surrounding sea area propagate to the coast during the observation time; represents the seabed friction coefficient; It represents the average population density in the area surrounding the coast; represents the economic coefficient of the coastal surrounding area; Indicates the volume of water in the surrounding sea; Indicates the length of observation time; represents the risk factor that changes over time; represents the seafloor sediment coefficient; , , , All are weight parameters; A road flow model is constructed through traffic monitoring data, and the flow coefficient of each road in the island city is calculated through the road flow model; Construct a resource utilization efficiency model based on resource data, and calculate the resource utilization efficiency coefficient of the island city through the resource utilization efficiency model; An island city management decision model is constructed through various natural disaster coefficients of island cities, flow coefficients of each road, and resource utilization efficiency coefficients. The island city management decision model provides a reference management decision plan for island cities.

2. The integrated management method of an island city according to claim 1, characterized in that: The weather forecast model is based on a ridge regression model; The historical meteorological data of the island city is constructed as a training set and input into the meteorological prediction model. The meteorological prediction model is trained and the model outputs the future The forecast results of the day are used to calculate the loss of the meteorological forecast model based on the training forecast results, as shown in the following formula: in: represents the loss function of the weather forecast model; represents the parameter matrix of the model; represents the transpose of the model parameter matrix; The output of the model is Weather forecast for the day; Indicates The actual meteorological value corresponding to the weather forecast value; represents the ridge coefficient; Indicates the total number of forecast days; The loss of the model is calculated by the above formula. If the loss is greater than the preset threshold, the parameters of the model are adjusted and trained again. If the loss is less than the preset threshold, the training is stopped to obtain a trained meteorological forecast model.

3. The integrated management method of an island city according to claim 1, characterized in that: The road flow model is constructed based on a graph neural network, which represents the urban traffic network. The nodes represent intersections and the edges represent roads. The corresponding feature vectors of each node and edge are defined based on the road traffic data in the traffic monitoring data, and the feature vectors of the network nodes at each time step are updated and iterated by the following formula: in: Representation Node In the The feature vector of the iteration; is the activation function; Indicates The weight matrix of the iteration; Representation Node The total number of adjacent nodes; Representation Node Neighboring nodes In the The feature vector of the iteration; Indicates The bias matrix for the iteration; Representation Node In the The feature vector of the iteration; The final model outputs the flow data of each road at each time step, and calculates the flow coefficient of each road based on the flow data, as shown in the following formula: in: Indicates The next time step Road flow coefficient; represents the total number of time steps; Indicates the road flow per unit time; Indicates the current road length; Indicates the current maximum road capacity; Indicates the average vehicle speed per unit time on the current road; Indicates the maximum speed of the current road per unit time; Indicates the average accident area per unit time on the current road; Indicates the number of traffic accidents per unit time on the current road; Indicates the length of the current time step.

4. The integrated management method for island cities according to claim 1, characterized in that: The resource utilization efficiency model is built based on the LightGBM model; The pre-processed resource data is used to extract the distance between residential areas and reservoirs, water supply network layout, power grid layout, season, historical water and electricity demand in residential areas, and historical water and electricity demand in industrial areas, and a training set is constructed; The training set is input into the LightGBM model for training, and the model loss is calculated by the following formula: in: Represents the loss function of the LightGBM model; Represents the gradient sum of all samples in the left subtree of the model; Represents the gradient sum of all samples in the right subtree of the model; Represents the gradient sum of all samples of the parent node; , , Respectively represent the number of samples of the left subtree, right subtree and parent node of the model; represents the weight parameter; The gain of the split point at each iteration of the model is calculated through the above loss function, and the point with the maximum gain is selected as the split target for the next iteration; The trained LightGBM model is used to predict the water and electricity demand in residential and industrial areas; Construct a resource utilization efficiency coefficient calculation formula to calculate the resource utilization efficiency coefficient of each area , as shown in the following formula: in: Indicates the overall water demand of the current area; It represents the current water demand of the regional industrial area; Indicates the water demand of residential areas in the current area; Indicates the average annual wastewater recycling rate in the current area; Indicates the overall area of ​​the current region; Indicates the electricity demand of residential areas in the current region; It represents the maintenance cost of power equipment in the current regional industrial zone; Indicates the current electricity demand of the regional industrial zone; Indicates the total amount of green energy available in the current area; Indicates the total amount of common energy available in the current area.

5. The integrated management method for island cities according to claim 1, characterized in that: The island city management decision model is used to manage the disaster prevention decision, road planning decision and resource allocation decision of the island city respectively; For disaster prevention decisions, disaster prevention strategies for different natural disasters are set. Multiple levels are set based on the coefficient of each type of natural disaster. Each level corresponds to a different degree of disaster severity. According to the size of the natural disaster coefficient, the disaster prevention strategy of the corresponding level is selected; For road planning decisions, roads are classified according to their flow coefficients, and different planning plans are set for different types of roads; For resource allocation decisions, the resource allocation priority of each region is set based on the resource utilization efficiency coefficient of each region, and different resource allocation plans are implemented for regions with different priorities.

6. An island city integrated management system, used to execute the method according to any one of claims 1 to 5, characterized in that: It includes data collection module, meteorological model building module, road flow model building module, resource utilization efficiency model building module and island city management decision-making module; The data acquisition module is used to collect historical environmental monitoring data, traffic monitoring data and resource data of the island city; The meteorological model building module is used to build a meteorological prediction model and perform meteorological prediction, and calculate various natural disaster coefficients of island cities based on meteorological prediction results and historical environmental monitoring data; The road flow model building module is used to build a road flow model through traffic monitoring data, and calculate the flow coefficient of each road in the island city through the road flow model; The resource utilization efficiency model building module is used to build a resource utilization efficiency model based on resource data, and calculate the resource utilization efficiency coefficient of the island city through the resource utilization efficiency model; The island city management decision module is used to construct an island city management decision model through various natural disaster coefficients of the island city, the flow coefficient of each road and the resource utilization efficiency coefficient, and provide a reference management decision plan for the island city through the island city management decision model.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images