Smart city greening management methods and systems, as well as storage media and devices

Abstract

This specification provides a smart city greening management method, system, storage medium, and device. The method is executed by a management platform and includes: acquiring vegetation data of the monitoring area corresponding to the object platform through a sensor network platform, wherein the vegetation data includes at least one of species information, climate information, soil information, maintenance information, and actual growth parameters; obtaining vegetation anomaly information of the monitoring area based on the vegetation data, wherein the vegetation anomaly information includes the location and amount of vegetation anomalies; obtaining the predicted air quality of the monitoring area based on the vegetation anomaly information, combined with the traffic flow and population density of the monitoring area; and determining the priority of greening treatment in the monitoring area based on the predicted air quality and vegetation anomaly information.

Description

Technical Field

[0001] This specification relates to the field of Internet of Things (IoT) technology, and in particular to a smart city greening management method and system, as well as storage media and devices. Background Technology

[0002] Urban greening directly or indirectly affects urban air quality, and urban greening work involves multiple departments such as landscaping, traffic management, and municipal road management. At the same time, greening work may impact urban traffic and roads. Therefore, it is necessary to coordinate the work arrangements and progress of various departments to avoid improper greening work affecting the normal operation of urban traffic and road management. The Internet of Things (IoT) technology can utilize internet resources to connect people and things, and things with each other, achieving the goals of informatization, remote management and control, and intelligentization.

[0003] Therefore, there is a need to provide a smart city greening management method based on the Internet of Things. Summary of the Invention

[0004] This specification provides one or more embodiments of a smart city greening management method, which is executed by a management platform and includes: acquiring vegetation data of a monitoring area corresponding to the object platform through a sensor network platform, wherein the vegetation data includes at least one of species information, climate information, soil information, maintenance information, and actual growth parameters; obtaining vegetation anomaly information of the monitoring area based on the vegetation data, wherein the vegetation anomaly information includes the location and quantity of vegetation anomalies; obtaining the predicted air quality of the monitoring area based on the vegetation anomaly information, combined with the traffic flow and population density of the monitoring area; and determining the greening treatment priority of the monitoring area based on the predicted air quality and the vegetation anomaly information.

[0005] This specification provides an Internet of Things (IoT) system for smart city greening management through one or more embodiments, including an object platform, a sensor network platform, and a management platform. The management platform is configured to perform the following operations: acquiring vegetation data of the monitoring area corresponding to the object platform through the sensor network platform, the vegetation data including at least one of species information, climate information, soil information, maintenance information, and actual growth parameters; obtaining vegetation anomaly information of the monitoring area based on the vegetation data, the vegetation anomaly information including abnormal vegetation location and abnormal vegetation quantity; obtaining the predicted air quality of the monitoring area based on the vegetation anomaly information, combined with the traffic flow and population density of the monitoring area; and determining the greening treatment priority of the monitoring area based on the predicted air quality and the vegetation anomaly information.

[0006] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the smart city greening management method as described in any of the above embodiments. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0008] Figure 1 These are schematic diagrams illustrating application scenarios of the smart city greening management system according to some embodiments of this specification;

[0009] Figure 2 This is a system module diagram of smart city greening management according to some embodiments of this specification;

[0010] Figure 3 This is an exemplary flowchart of a smart city greening management method according to some embodiments of this specification;

[0011] Figure 4 This is an exemplary flowchart of a smart city greening management method for determining vegetation anomalies, as shown in some embodiments of this specification.

[0012] Figure 5 This is a flowchart illustrating the process of predicting regional air quality based on a predictive model in a smart city greening management method according to some embodiments of this specification.

[0013] Figure 6 This is an exemplary flowchart illustrating the method for determining the priority of vegetation anomaly handling in a smart city greening management system according to some embodiments of this specification. Detailed Implementation

[0014] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0015] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0016] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0018] Figure 1 These are schematic diagrams illustrating application scenarios of a smart city greening management system based on some embodiments of this specification. For example... Figure 1 As shown in the diagram, the application scenario 100 of the smart city greening management system may include data information 110, a network 120, a storage device 130, a processing device 140, and a terminal 150. In some embodiments, the components in application scenario 100 may be connected to each other and / or communicate via the network 120 (e.g., a wireless connection, a wired connection, or a combination thereof). For example, the processing device 140 may be connected to the storage device 130 via the network 120.

[0019] Data information 110 can be used as auxiliary information for predicting regional air quality. For example, data information 110 may include basic vegetation information 110-1, population density information 110-2, traffic flow information 110-3, etc.

[0020] In some embodiments, the basic vegetation information 110-1 may include one or more types of information such as vegetation species information, vegetation location information, climate information, soil information, maintenance information, height of vegetation growth, and canopy width. The basic vegetation information 110-1 can be obtained in various ways, such as user input, acquisition through third-party platforms, or collection by drones.

[0021] In some embodiments, population density information 110-2 may be data related to the population size of the area. Population density information 110-2 may be obtained based on urban heat maps or similar data from third-party platforms.

[0022] In some embodiments, traffic flow information 110-3 may be information related to traffic flow data in a region. Traffic flow information 110-3 may be obtained based on third-party platforms such as traffic big data platforms.

[0023] The memory 130 can be used to store data, instructions, and / or any other information. In some embodiments, the memory 130 may be part of the processing device 140.

[0024] The processing device 140 can process information and / or data related to the application scenario 100 of the smart city greening management system to perform one or more functions described in this specification. For example, the processing device 140 can determine the priority of vegetation greening treatment based on basic vegetation information, population density, and traffic flow.

[0025] Terminal 150 may refer to one or more terminals or software used by a user. In some embodiments, the user (e.g., a municipal road management department, a landscaping department, a traffic management department, etc.) may be the owner of terminal 150. In some embodiments, terminal 150 may be a device with data acquisition capabilities. For example, terminal 150 may be a device used by urban greening management personnel to acquire geographic location information of abnormal vegetation.

[0026] It should be noted that the application scenario 100 based on the smart city greening management system is provided for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can make various modifications or variations based on the description in this specification. However, such modifications and variations will not depart from the scope of this specification.

[0027] Figure 2 This is a block diagram of a smart city greening management system according to some embodiments of this specification. In some embodiments, the smart city greening management system 200 may include a user platform 210, a service platform 220, a management platform 230, a sensor network platform 240, and an object platform 250.

[0028] User platform 210 can be a user-facing service interface. In some embodiments, user platform 210 can receive information from users and / or service platforms. For example, user platform 210 can receive input from users. As another example, user platform 210 can receive feedback information from the service platform, such as basic information about abnormal vegetation. In some embodiments, user platform 210 can be configured to feed information back to users. User platform 210 can also send information to the service platform.

[0029] Service platform 220 can be a platform for preliminary processing of information. In some embodiments, service platform 220 can transmit information obtained from the user platform to the management platform. For example, vegetation information can be transmitted to the management platform. In some embodiments, service platform 220 can receive information sent by the management platform. For example, basic vegetation information, population density, and priority for processing green vegetation.

[0030] The management platform 230 can refer to an IoT platform that coordinates and integrates the connections and collaborations between various functional platforms, providing sensing management and control management.

[0031] In some embodiments, the management platform 230 can identify vegetation anomaly information, predict air quality, and send the vegetation anomaly information and predicted air quality to the service platform. In some embodiments, the management platform 230 can be configured as a stand-alone structure. A stand-alone structure means that the management platform includes multiple management sub-platforms, each corresponding to a different region, and can store, process, and / or transmit data from different regions uploaded by the sensor network platform based on the corresponding management sub-platform.

[0032] In some embodiments, the management platform 230 may be further configured to: acquire vegetation data for the corresponding monitoring area. The vegetation data includes at least one of the following: species information, climate information, soil information, maintenance information, and actual growth parameters.

[0033] In some embodiments, the management platform 230 is further configured to: obtain vegetation anomaly information of the monitored area based on vegetation data. The vegetation anomaly information includes the location and amount of vegetation anomalies.

[0034] In some embodiments, the management platform 230 is further configured to: obtain the predicted air quality of the monitored area based on vegetation anomaly information, combined with traffic flow and population density in the monitored area. In some embodiments, the management platform 230 is further configured to: determine the priority of greening treatment in the monitored area based on the predicted air quality and vegetation anomaly information of the monitored area. See details below. Figure 3 Related explanations.

[0035] The sensor network platform 240 can be a platform that enables interaction between the management platform and the object platform. In some embodiments, the sensor network platform 240 can receive instructions from the management platform to acquire monitoring data of each area and send the instructions to the object platform, and the sensor network platform 240 can upload the monitoring data acquired by the object platform to the management platform.

[0036] In some embodiments, the sensor network platform 240 can be configured as a stand-alone structure. A stand-alone structure means that the sensor network platform includes multiple sensor network sub-platforms, each corresponding to a different region. The corresponding regional sensor network sub-platform can process the monitoring data uploaded by the object platform collecting monitoring data for that region, upload the corresponding monitoring data to the management sub-platform for that region, and transmit data collection instructions issued by the management sub-platform to the object platform corresponding to that region.

[0037] The object platform 250 can be a functional platform for generating sensing information and ultimately executing control information. The object platform 250 can acquire monitoring data based on monitoring equipment. For example, vegetation growth parameters can be acquired based on drone sensors. In some embodiments, the object platform 250 may include object sub-platforms corresponding to different regions, each of which can be implemented by a monitoring device or a sensing device. The object sub-platforms corresponding to different regions can upload the collected data to the corresponding sensor network sub-platform, which then uploads it to the management sub-platform for processing. Different management sub-platforms can issue instructions to the object sub-platforms to collect corresponding data for that region based on the corresponding sensor network sub-platform, and the corresponding object sub-platforms will execute these instructions.

[0038] It should be noted that the above description of the smart city greening management system 200 is for convenience only and should not be construed as limiting this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principles of this system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles.

[0039] Figure 3 This is an exemplary flowchart of a smart city greening management method according to some embodiments of this specification. In some embodiments, process 300 may be executed by a management platform. Figure 3 As shown, process 300 includes the following steps:

[0040] Step 310: Obtain vegetation data of the monitoring area corresponding to the object platform through the sensor network platform. The vegetation data includes at least one of the following: species information, climate information, soil information, maintenance information, and actual growth parameters.

[0041] A monitoring area refers to an area where the status of green spaces needs to be monitored. The size of the monitoring area can be determined based on the actual situation. For example, a monitoring area could be a district or street within a city.

[0042] Vegetation data can be data related to vegetation. For example, vegetation data includes at least one of the following: species information, climate information, soil information, maintenance information, and actual growth parameters.

[0043] Vegetation data can be obtained by monitoring equipment such as drones, or through third-party platforms.

[0044] The vegetation species information can be the plant community type to which the vegetation belongs. For example, ginkgo trees belong to the tree family. In some embodiments, the vegetation species information can be pre-entered by the user.

[0045] Climate information can be data reflecting the current climate conditions of the vegetation growth environment. For example, climate information can be information such as current weather temperature. In some embodiments, climate information can be obtained through third-party platforms such as meteorological platforms.

[0046] Soil information can be related to the soil in which the current vegetation is located. For example, soil information can include soil moisture, soil type, etc. In some embodiments, soil information can be obtained through drones or user input.

[0047] Maintenance information can be recorded data on vegetation maintenance. For example, maintenance information may include irrigation and fertilization information, pruning and shaping information, pest and disease control information, and information on the number of times frost protection was applied. In some embodiments, maintenance information can be obtained from the greening work records of the landscaping department.

[0048] Actual growth parameters can be data on the actual growth of vegetation. For example, actual growth parameters may include data such as plant height and crown width. In some embodiments, actual growth parameters can be obtained by taking pictures with a drone. For example, actual growth parameters of vegetation can be obtained based on image analysis of vegetation images taken by a drone. When taking vegetation images, the drone can take pictures from directly above the plant and use the same flight altitude and shooting precision.

[0049] Step 320: Obtain vegetation anomaly information in the monitored area based on vegetation data. The vegetation anomaly information includes the location and amount of vegetation anomalies.

[0050] Vegetation anomaly information can be data related to vegetation that has not met growth standards. For example, vegetation anomaly information can include the location and quantity of vegetation that has not met growth standards; that is, vegetation anomaly information can include abnormal vegetation location and abnormal vegetation quantity.

[0051] Anomaly in vegetation location can refer to the planting location of vegetation that has not met the growth standards. Anomaly in vegetation location can take many forms; for example, it can be identified by the street where the vegetation is located, or by the latitude and longitude coordinates of the vegetation.

[0052] Vegetation anomaly is information related to the number of plants in a monitored area that do not meet growth standards. Vegetation anomaly can be expressed in several ways; for example, it can be represented by the number of plants in the monitored area that do not meet growth standards, or it can be represented by the percentage of such plants in the total vegetation area. For example, if there are 100 plants in a monitored area, and 20 of them do not meet growth standards, then the vegetation anomaly is 20%.

[0053] In some embodiments, the management platform can obtain vegetation anomaly information of a region based on vegetation data in various ways. For example, based on the monitoring area corresponding to the device acquiring the vegetation data, the location of vegetation anomalies can be determined. Furthermore, based on image recognition of the vegetation images corresponding to the monitoring area, the amount of vegetation anomalies in the monitoring area can be statistically analyzed.

[0054] In other embodiments, vegetation anomaly information can be obtained by combining it with historical data; see details below. Figure 4 And its related descriptions.

[0055] Step 330: Based on the abnormal vegetation information in the monitored area, combined with the traffic flow and population density in the monitored area, the predicted air quality of the monitored area is obtained.

[0056] Traffic flow can be defined as the number of vehicles passing through a point on a highway within a certain time period. For example, if 50 vehicles pass through a point on Highway 1 within one hour, then the traffic flow of that highway is 50 vehicles per hour.

[0057] Population density can be defined as the number of people per unit area of ​​land. For example, if there are 10,000 people in 10 square kilometers of land, then the population density of that area is 1,000 people per square kilometer.

[0058] Predicted air quality refers to data related to air conditions, such as the predicted level of air pollution. In some embodiments, predicted air quality can be represented by an air quality score, with a higher score indicating worse air quality. For example, a predicted air quality score of 40 indicates a level four air quality.

[0059] In some embodiments, the predicted air quality of a monitored area can be obtained based on vegetation anomaly information, combined with traffic flow and population density. For example, the greater the vegetation anomaly, the higher the traffic flow, and the greater the population density, the worse the predicted air quality will be.

[0060] In some embodiments, a preset air quality table can be used to query the predicted air quality under different conditions. The air quality table can record the air quality corresponding to different vegetation anomalies, traffic flow, and population density based on historical experience. For example, when the vegetation anomaly is 10%, the traffic flow is 200 vehicles / hour, and the population density is 1000 people / square kilometer, the predicted air quality can be found to be level three by looking up the table.

[0061] In other embodiments, air quality can be predicted based on machine learning models, see details below. Figure 5 And its related descriptions.

[0062] Step 340: Based on the predicted air quality and vegetation anomaly information of the monitored area, determine the priority of greening treatment in the monitored area.

[0063] Greening priority can refer to the order in which abnormal vegetation is addressed through greening measures. For example, areas with higher greening priority should be addressed earlier. Greening measures can include irrigating and fertilizing the vegetation within the monitored area, and treating pests.

[0064] In some embodiments, the management platform can determine the priority of greening treatment in a monitored area based on multiple methods. For example, in monitored areas where traffic flow and population density are similar or within a certain range, greening treatment with poor air quality has a higher priority.

[0065] In some embodiments, the priority of greening treatment can be determined based on a weighted sum of air quality score and vegetation anomaly amount, with the weight values ​​preset. In some embodiments, the management platform can determine the priority of greening treatment for a region by referring to a preset table relating traffic flow, population density, and priority. In some embodiments, the priority of greening treatment can also be determined based on historical data. For example, the historical greening treatment priority of a certain historical region that has the same or different air quality and vegetation anomaly information as the current prediction can be used as the greening treatment priority of the monitored area.

[0066] For more details on determining the priority of greening treatment in the monitored area, please see [link / details]. Figure 6 And its related descriptions.

[0067] In some embodiments of this specification, by acquiring information such as vegetation image information, basic vegetation information and vegetation anomaly information are obtained. Then, combined with traffic flow, population density, and vegetation anomaly information, predicted air quality is obtained. In this way, the priority of vegetation greening treatment in the monitored area can be comprehensively determined, which can make the priority determination more reasonable, ensure timely greening treatment of the corresponding monitored area, avoid interference caused by environmental degradation, and further beautify the urban environment.

[0068] Figure 4This is an exemplary flowchart illustrating the determination of vegetation anomalies in a smart city greening management method according to some embodiments of this specification. In some embodiments, process 400 may be executed by processing device 140 or a management platform. Figure 4 As shown, process 400 includes the following steps:

[0069] Step 410: Construct vegetation feature vectors based on vegetation data of the monitored area.

[0070] A vegetation feature vector is a vector that reflects information about the vegetation species and the vegetation's growing environment in a monitored area. For example, a vegetation feature vector can reflect information about vegetation species, climate, soil, and maintenance conditions.

[0071] In some embodiments, the management platform can construct a vegetation feature vector based on vegetation data of the monitored area. This vegetation data includes vegetation type information, climate information of the monitored area, soil information of the monitored area, and vegetation maintenance information. In some embodiments, the management platform can assign values ​​to different vegetation data and construct a feature vector based on these assigned values. For example, the management platform can assign values ​​1, 2, 3, 4, ..., n to different vegetation types; assign values ​​1, 2, 3, 4, ..., m to different climate information; assign values ​​1, 2, 3, 4, ..., i to different soil information; and assign values ​​1, 2, 3, 4, ..., j to different maintenance information. The constructed vegetation feature vector can then be represented as (n, m, i, j). For example, the vegetation feature vector (1, 1, 1, 1) represents vegetation type 1, climate type 1, soil type 1, and vegetation maintenance type 1.

[0072] Step 420: Retrieve reference feature vectors from the vegetation vector database based on vegetation feature vectors.

[0073] In some embodiments, feature vectors can be constructed based on vegetation data of multiple vegetation types to form a vector database. A vegetation vector database refers to a set of vectors composed of multiple feature vectors, where each feature vector corresponds to the vegetation data of one plant. More information about vegetation data can be found in [link to relevant documentation]. Figure 3 And its description.

[0074] In some embodiments, the vegetation data corresponding to the feature vectors in the vegetation vector database are vegetation data of plants whose growth parameters in all aspects meet preset standards. Each feature vector is associated with its corresponding vegetation growth parameter and stored in the database.

[0075] A reference feature vector refers to a feature vector retrieved from a vegetation vector database that meets preset conditions, where the preset conditions can be a preset similarity threshold. For example, a reference feature vector may include one or more feature vectors retrieved from the vegetation vector database that meet the similarity threshold with the constructed vegetation feature vector.

[0076] In some embodiments, the management platform can search a vegetation vector database based on vegetation feature vectors and determine feature vectors whose vector similarity to the vegetation feature vectors is greater than or equal to a similarity threshold as reference feature vectors. Vector similarity may include cosine similarity, etc. The similarity threshold can be preset in advance, for example, setting the similarity threshold to a cosine similarity of 0.95. In some embodiments, the management platform can retrieve one or more reference feature vectors from the vegetation vector database based on the vegetation feature vectors.

[0077] Step 430: Determine the reference growth parameters based on the reference feature vector.

[0078] Reference growth parameters refer to the actual growth parameters of the vegetation corresponding to the reference feature vector. For example, reference growth parameters could be the actual height and crown width of an osmanthus tree corresponding to the reference feature vector.

[0079] In some embodiments, the management platform can determine reference growth parameters based on reference feature vectors, wherein the reference growth parameters are stored in a vector database in association with the reference feature vectors.

[0080] In some embodiments, when only one reference feature vector is retrieved, the management platform can directly determine the growth parameter corresponding to that reference feature vector as the reference growth parameter. In some embodiments, when multiple reference feature vectors are retrieved, the management platform can calculate the average of the multiple reference growth parameters to obtain the average reference growth parameter, which is then used as the final reference growth parameter.

[0081] Step 440: Determine abnormal vegetation based on actual growth parameters and reference growth parameters.

[0082] Abnormal vegetation refers to vegetation with abnormal growth parameters. For example, abnormal vegetation is vegetation whose plant height, crown width, or any other growth parameter does not meet the preset relationship with the reference growth parameters.

[0083] In some embodiments, the management platform can identify abnormal vegetation based on actual growth parameters and reference growth parameters. For example, the management platform can identify vegetation as abnormal vegetation if the actual growth parameters and reference growth parameters do not meet a preset relationship. The preset relationship refers to a pre-defined relationship between the actual growth parameters and the reference growth parameters. For example, the preset relationship may include actual plant height not being less than 90% of the reference plant height, actual crown width not being less than 90% of the reference crown width, etc.

[0084] In some embodiments, the management platform can identify vegetation as abnormal vegetation based on any one of the preset relationships between the actual growth parameters and the reference growth parameters. For example, when the height or crown width of a certain Chinese arborvitae tree is lower than the reference height or crown width, the Chinese arborvitae tree is identified as abnormal vegetation.

[0085] Step 450: Statistically monitor the amount of vegetation anomalies in the monitored area based on abnormal vegetation.

[0086] In some embodiments, the management platform can statistically analyze the amount of vegetation anomalies in a monitored area based on abnormal vegetation. In some embodiments, the management platform can count the number of abnormal plants whose locations correspond to the monitored area, based on the abnormal vegetation and its location, to determine the amount of vegetation anomalies in the monitored area. For example, the total number of abnormal plants located in the monitored area can be summed, and this total number can be used as the amount of vegetation anomalies in the monitored area. In some embodiments, the management platform can determine the type of abnormal vegetation and its corresponding amount of vegetation anomalies in the monitored area based on the type and location of the abnormal vegetation.

[0087] Some embodiments in this specification use vector retrieval to determine reference growth parameters for vegetation, and then compare the actual growth parameters with the reference growth parameters to identify abnormal vegetation. This takes into account the influence of growth environment and maintenance conditions on vegetation growth, making the results more consistent with the actual situation and the statistical anomaly of vegetation more accurate.

[0088] It should be noted that the above description of process 400 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to process 400 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, process 400 may also include determining anomaly handling methods based on vegetation anomaly levels.

[0089] Figure 5 This is a schematic diagram of a process 500 for predicting regional air quality based on a predictive model, according to some embodiments of the smart city greening management method shown in this specification.

[0090] In some embodiments, air quality predictions can be obtained based on a prediction model, wherein the prediction model is a machine learning model.

[0091] In some embodiments, the input to the prediction model may be vegetation data, traffic flow, and population density of the monitored area, and the output may be the predicted air quality of the monitored area.

[0092] In some embodiments, the prediction model can be trained using multiple labeled training samples. For example, multiple labeled training samples can be input into an initial prediction model, and a loss function can be constructed using the labels and the results of the initial prediction model. Based on the loss function, the parameters of the initial prediction model are iteratively updated using gradient descent or other methods. The model training is complete when preset conditions are met, resulting in a trained prediction model. These preset conditions may include loss function convergence, the number of iterations reaching a threshold, etc.

[0093] In some embodiments, the training samples may include at least a large amount of historical vegetation data, traffic flow, and population density data for the monitored and other areas. Labels may be the actual air quality corresponding to each area, and may be manually labeled or obtained based on web data.

[0094] In some embodiments, the prediction model structure can be a combination of a graph neural network (GNN) and a deep neural network (DNN). Predicting air quality includes: constructing a regional map based on regional vegetation anomaly information, combined with regional traffic flow and population density; processing the regional map based on the GNN to obtain a regional feature vector, wherein the regional feature vector is output by the nodes of the regional map; and processing the regional feature vector based on the DNN to obtain the predicted air quality.

[0095] In some embodiments, the process 500 for predicting regional air quality is executed by a management platform. For example... Figure 5 As shown, process 500 includes the following steps:

[0096] Step 510: Based on the vegetation anomaly information of the region, and combined with the region's traffic flow and population density, construct a regional map. The nodes of the regional map include residential nodes and road intersection nodes, and the edges of the regional map are used to connect two nodes connected by roads. The attributes of the residential nodes include population density and vegetation anomaly amount; the attributes of the road intersection nodes include traffic flow; and the attributes of the edges include vegetation anomaly amount along the road.

[0097] A regional map is a graphical structure that can reflect information on vegetation anomalies, traffic flow, population density and their distribution in a monitored area.

[0098] In some embodiments, the management platform can construct a regional map based on vegetation anomaly information, combined with regional traffic flow and population density. For example, the management platform can construct a regional map based on the population density and vegetation anomaly information of each residential area within the region, the traffic flow at each road intersection within the region, and the vegetation anomaly information along each road within the region.

[0099] A residential node refers to a data point within a single residential area. For example, such as... Figure 5 As shown, a residential node can be "Residential Area 1".

[0100] In some embodiments, the attributes of a residential node may include the population density of the residential area and the amount of vegetation anomalies in the residential area. For example, the attributes of a residential node may be "population density 300 people / km², vegetation anomaly rate 40%".

[0101] A road intersection node refers to a data point at a single road intersection. For example, ... Figure 5 As shown, the road intersection node can be "road intersection 1".

[0102] In some embodiments, the attributes of a road intersection node may include traffic flow. For example, the attribute of a road intersection node may be "500 vehicles / hour".

[0103] Edges in a region graph are used to connect two nodes that share a road connection. For example, as shown... Figure 5 As shown, the edges of the area graph can be edges used to connect road intersection nodes and residential nodes, or edges used to connect one road intersection node to another road intersection node. In some embodiments, the edges of the area graph can be roads representing connecting nodes. For example, a road connecting two road intersection nodes.

[0104] In some embodiments, the edge attributes of an edge in a region map may include the amount of vegetation anomaly along the road corresponding to that edge. For example, the edge attribute of an edge in a region map may be "30% of vegetation anomaly".

[0105] Step 520: Obtain the predicted air quality based on the prediction model.

[0106] In some embodiments, the prediction model may include an embedding layer and a prediction layer. In some embodiments, the embedding layer may be a graph neural network (GNN), and the prediction layer may be a deep neural network (DNN).

[0107] In some embodiments, step 520 is implemented by steps 522 and 524:

[0108] Step 522: Based on the GNN processing of the region graph, the region feature vector is obtained, and the region feature vector is output by the node.

[0109] A regional feature vector can refer to a vector that reflects the data affecting air quality in a regional map. For example, a regional feature vector could be a vector that reflects vegetation anomalies, traffic flow, and population density at various nodes and edges in a regional map.

[0110] In some embodiments, the region graph can be processed based on a GNN to obtain a region feature vector, which is output by the nodes of the region graph. In some embodiments, the input to the GNN can be the region graph, and the output can be the region feature vector.

[0111] Step 524: Based on the processing of regional feature vectors by DNN, the predicted air quality is obtained.

[0112] In some embodiments, the input to the DNN can be a region feature vector, such as the region feature vector output by the GNN; the output of the DNN can be the predicted regional air quality corresponding to the region map. In some embodiments, the regional air quality output by the DNN can be an air quality level. For example, Level 1, Level 2, Level 3, etc., each level representing a different air quality condition.

[0113] In some embodiments, the parameters of the GNN and DNN can be obtained through joint training. Training sample data, i.e., region maps of multiple regions, can be input into the GNN to obtain the region feature vectors output by the GNN. Then, these region feature vectors are used as training sample data and input into the DNN to obtain the predicted air quality output by the DNN. The actual air quality of the samples is used to validate the output of the DNN. Utilizing the backpropagation characteristics of the neural network model, validation data of the region feature vectors output by the GNN is obtained, and this validation data is used as labels to train the GNN.

[0114] As an example only, an initial DNN and an initial GNN can be trained based on a large number of labeled training samples. Specifically, the region maps of each area are input into the initial GNN, and the output of the initial GNN is used as the input to the initial DNN. A loss function is established based on the actual air quality of the samples and the output of the initial GNN to update the parameters of the initial DNN and initial GNN. The parameters of the DNN and GNN are iteratively updated simultaneously based on the loss function until a preset condition is met to complete the training. The preset condition can be that the loss function is less than a threshold, convergence, or the training cycle reaches a threshold.

[0115] The parameters of the GNN obtained through the above training method can help solve the problem of difficulty in obtaining labels when training the GNN alone in some cases. It can also enable the GNN to obtain embedding vectors that better reflect the region map of each region.

[0116] By processing the regional map to obtain regional feature vectors before making air quality predictions, the data processing steps can be optimized, and the accuracy and efficiency of predictions can be improved.

[0117] By using models to predict regional air quality, the self-learning capabilities of machine learning models can be leveraged to find patterns in large amounts of regional data, thereby predicting the air quality of the region in the future and improving the efficiency and accuracy of predictions.

[0118] Figure 6 This is an exemplary flowchart illustrating the method for determining the priority of vegetation anomaly handling in a smart city greening management system according to some embodiments of this specification.

[0119] In some embodiments, the worse the predicted air quality in the monitored area, the higher the priority of greening treatment.

[0120] The priority of greening treatment refers to the order in which abnormal vegetation is addressed, and this priority is negatively correlated with air quality. Abnormal vegetation treatment includes replanting and enhanced maintenance of the affected vegetation. Determining the priority of greening treatment by comparing it with air quality conditions takes into account the impact of air quality on people's lives and health, and is more in line with practical needs.

[0121] In some embodiments, air quality prediction can be based on air quality scores, and greening priority can be determined based on a weighted sum of air quality scores and vegetation anomalies.

[0122] An air quality score is a score that measures the predicted air quality. In some embodiments, the better the predicted air quality, the lower the air quality score. In some embodiments, the management platform can preset air quality scores for each level of predicted air quality. For example, when the air quality level is Level 1, the preset air quality score is 10 points; when the air quality level is Level 2, the preset air quality score is 20 points, where Level 1 air quality is better than Level 2 air quality.

[0123] In some embodiments, the weights corresponding to air quality scores and vegetation anomalies can be preset based on actual conditions. For example, the weights can be determined based on the degree of impact of air quality and vegetation anomalies on people's lives, with greater impacts receiving relatively larger weights. The degree of impact can be determined through methods such as survey reports. The sum of the weights is 1.

[0124] In some embodiments, the management platform can perform a weighted summation of air quality score and vegetation anomaly, and determine the priority of greening treatment based on the summation result. For example, if the air quality score is n points and the corresponding weight is q1; and the vegetation anomaly is m and the corresponding weight is q2; then the weighted summation value is n×q1+m×q2.

[0125] In some embodiments, the management platform can determine the priority of greening treatment based on the magnitude of the weighted sum, with a higher weighted sum indicating a higher priority. For example, if the weighted sum of area A is greater than that of area B, then the greening treatment priority of area A is higher than that of area B.

[0126] In some embodiments of this specification, the priority of greening treatment is determined based on the weighted sum of regional vegetation anomalies and air quality scores, taking into account the impact of vegetation anomalies and air quality on people's lives, making the determined priority of greening treatment more reasonable.

[0127] In some embodiments, the management platform may first identify areas with similar traffic flow and population density, and then determine the priority of greening treatment based on the air quality of the area.

[0128] In some embodiments, the process 600 for determining the priority of greening treatment based on air quality can be executed by a management platform. For example... Figure 6 As shown, process 600 includes the following steps:

[0129] Step 610: Based on the embedding layer, embed the traffic flow and population density of the region to obtain the embedding vector; the embedding layer is obtained through joint training with the prediction model.

[0130] An embedding vector is a vector that reflects population density and traffic flow information within a monitored area. For example, an embedding vector can reflect the population density of various residential areas and traffic flow information at road intersections within area A.

[0131] In some embodiments, the management platform can embed traffic flow and population density within a region based on the embedding layer to obtain an embedding vector.

[0132] In some embodiments, the embedding layer can be obtained through joint training with the prediction model. For example, the embedding layer can be obtained through joint training with a GNN in the prediction model.

[0133] As an example only, the management platform can use regional maps constructed based on vegetation data, traffic flow, and population density of multiple monitoring areas as training samples, input them into the GNN of the prediction model, obtain the feature vectors corresponding to each regional map, use the feature vectors as labels for training the embedding layer, and use the traffic flow and population density of multiple monitoring areas as training samples to train the embedding layer.

[0134] Step 620: Obtain the vector distance between the embedding vectors corresponding to each region, and classify the embedding vectors whose distances meet the preset conditions as a class.

[0135] Vector distance refers to the distance between various embedding vectors. Examples include Euclidean distance and Manhattan distance.

[0136] A preset condition refers to a pre-defined relationship between vector distance and a threshold. For example, a preset condition could be that the vector distance does not exceed a vector distance threshold. In some embodiments, the vector distance threshold can be determined based on computational requirements. For example, a preset condition could be that the Euclidean distance between vectors is less than or equal to 0.2.

[0137] In some embodiments, the management platform can classify embedded vectors that meet preset conditions into one class based on the vector distance between the embedded vectors corresponding to each region. For example, if the vector distance between embedded vector a and embedded vector b is less than or equal to 0.2, then embedded vector a and embedded vector b are classified into one class.

[0138] Step 630: Compare the predicted air quality corresponding to the same type of embedding vector. Among the same type of embedding vector, the worse the predicted air quality, the higher the priority of greening treatment.

[0139] In some embodiments, the management platform can compare the predicted air quality corresponding to the same type of embedding vectors. Among the same type of embedding vectors, the worse the predicted air quality, the higher the priority of greening treatment. For example, among the same type of embedding vectors a and b, if the predicted air quality of the monitoring area corresponding to embedding vector a is worse than the air quality of the monitoring area corresponding to embedding vector b, then the greening treatment priority of the area corresponding to embedding vector a is higher than the greening treatment priority of the area corresponding to embedding vector b.

[0140] In some embodiments of this specification, embedding is performed based on regional population density and traffic flow characteristics. Areas with the same population density and traffic flow characteristics are filtered out and then the priority of greening treatment is determined. Different greening treatment priorities can be determined for areas with the same traffic flow and population density but different air quality, prioritizing the health of the residents before beautifying the environment.

[0141] In some embodiments, when the air quality of the monitoring areas corresponding to the feature vectors of the same category is the same or meets the preset range, the greening treatment of the monitoring area with the large amount of vegetation anomaly has a higher priority.

[0142] A preset range refers to the range of differences in air quality scores between predicted air quality in different regions. For example, a preset range could be a range where the difference in air quality scores does not exceed 5 points.

[0143] In some embodiments, if the predicted air quality corresponding to the same type of embedding vector is the same or meets a preset range, then the greening treatment priority for areas with larger vegetation anomalies corresponding to the embedding vector is higher than that for areas with smaller vegetation anomalies. For example, if the air quality corresponding to the same type of embedding vector a and embedding vector b is the same, or the difference in air quality scores does not exceed 5 points, and the vegetation anomaly rate in area A corresponding to embedding vector a is 40%, while the vegetation anomaly rate in area B corresponding to embedding vector b is 30%, then the greening treatment priority for area A is higher than that for area B.

[0144] In some embodiments of this specification, the amount of vegetation anomalies is compared in areas with the same air quality to determine the priority of greening treatment. The urgency of greening treatment under different conditions of air quality and vegetation anomalies is taken into account, making the determined priority more reasonable.

[0145] In some embodiments of this specification, the priority of greening treatment is determined based on air quality, taking into account the impact of air quality on people's lives and health, which meets practical needs.

[0146] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0147] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0148] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0149] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0150] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0151] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0152] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A smart city greening management method, characterized in that, The method is executed by the management platform and includes: The vegetation data of the monitoring area corresponding to the object platform is obtained through the sensor network platform. The vegetation data includes at least one of the following: species information, climate information, soil information, maintenance information, and actual growth parameters. Based on the vegetation data, vegetation anomaly information of the monitored area is obtained, including the location and amount of vegetation anomaly. Based on the vegetation anomaly information in the monitored area, combined with the traffic flow and population density in the monitored area, the predicted air quality of the monitored area is obtained based on a prediction model, wherein the prediction model is a machine learning model. Based on the predicted air quality and vegetation anomaly information of the monitored area, the priority of greening treatment in the monitored area is determined, whereby the greening treatment priority indicates the order in which abnormal vegetation is treated; wherein, the prediction model includes graph neural networks and deep neural networks; and the prediction of air quality in the monitored area based on the prediction model includes: Based on the vegetation anomaly information in the monitored area, combined with the traffic flow and population density in the monitored area, a regional map is constructed. The nodes of the regional map include residential nodes and road intersection nodes. The edges of the regional map are used to connect two nodes with roads. The attributes of the residential nodes include the population density and the amount of vegetation anomaly. The attributes of the road intersection nodes include the traffic flow. The attributes of the edges include the amount of vegetation anomaly next to the road. The region graph is processed based on the graph neural network to obtain a region feature vector, wherein the region feature vector is output by the nodes of the region graph; The predicted air quality is obtained by processing the feature vector of the region based on the deep neural network.

2. The method according to claim 1, characterized in that, The sensor network platform includes several sensor network sub-platforms corresponding to different monitoring areas; The management platform includes several management sub-platforms corresponding to different monitoring areas; The vegetation anomaly information and the predicted air quality in the monitored area are determined by the corresponding management sub-platform of the monitored area.

3. The method of claim 1, wherein, The method for determining the abnormal vegetation amount in the monitored area includes: A vegetation feature vector is constructed based on the vegetation data of the monitored area; A reference feature vector is obtained by retrieving it from the vegetation vector database based on the vegetation feature vector. Based on the reference feature vector, determine the reference growth parameters; Abnormal vegetation is determined based on the actual growth parameters and the reference growth parameters; The abnormal vegetation is used to calculate the amount of vegetation abnormality in the monitored area.

4. The method of claim 1, wherein, The worse the predicted air quality, the higher the priority of the greening treatment.

5. An Internet of Things (IoT) system for smart city greening management, characterized in that, Includes an object platform, a sensor network platform, and a management platform: the management platform is configured to perform the following operations: The vegetation data of the monitoring area corresponding to the object platform is obtained through the sensor network platform. The vegetation data includes at least one of the following: species information, climate information, soil information, maintenance information, and actual growth parameters. Based on the vegetation data, vegetation anomaly information of the monitored area is obtained, including the location and amount of vegetation anomaly. Based on the vegetation anomaly information in the monitored area, combined with the traffic flow and population density in the monitored area, the predicted air quality of the monitored area is obtained based on a prediction model, wherein the prediction model is a machine learning model. Based on the predicted air quality and vegetation anomaly information of the monitored area, the priority of greening treatment in the monitored area is determined, and the greening treatment priority indicates the order in which abnormal vegetation is treated; wherein, the prediction model includes graph neural networks and deep neural networks. The management platform is also configured to perform the following operations: Based on the vegetation anomaly information in the monitored area, combined with the traffic flow and population density in the monitored area, a regional map is constructed. The nodes of the regional map include residential nodes and road intersection nodes. The edges of the regional map are used to connect two nodes with roads. The attributes of the residential nodes include the population density and the amount of vegetation anomaly. The attributes of the road intersection nodes include the traffic flow. The attributes of the edges include the amount of vegetation anomaly next to the road. The region graph is processed based on the graph neural network to obtain a region feature vector, wherein the region feature vector is output by the nodes of the region graph; The predicted air quality is obtained by processing the feature vector of the region based on the deep neural network.

6. The system according to claim 5, characterized in that, The sensor network platform includes several sensor network sub-platforms corresponding to different monitoring areas; The management platform includes several management sub-platforms corresponding to different monitoring areas; The vegetation anomaly information and the predicted air quality in the monitored area are determined by the corresponding management sub-platform of the monitored area.

7. The system according to claim 5, characterized in that, The management platform is further used for: A vegetation feature vector is constructed based on the vegetation data of the monitored area; A reference feature vector is obtained by retrieving it from the vegetation vector database based on the vegetation feature vector. Based on the reference feature vector, determine the reference growth parameters; Abnormal vegetation is determined based on the actual growth parameters and the reference growth parameters; The abnormal vegetation is used to calculate the amount of vegetation abnormality in the monitored area.

8. The system according to claim 5, characterized in that, The worse the predicted air quality, the higher the priority of the greening treatment.

9. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes a smart city greening management method as described in any one of claims 1-4.

10. A smart city greening management device, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least a portion of the computer instructions to implement a smart city greening management method as described in any one of claims 1 to 4.

Images