Green land intelligent management system based on cloud computing

Abstract

This invention relates to the field of green space management technology, specifically a cloud-based intelligent green space management system. The system includes a cloud-based multi-source integration module, a temporal disturbance analysis module, a disturbance chain association module, a disease trend identification module, and a management and control linkage module. Based on various green space on-site monitoring points, it determines the online status of sensing devices and the accuracy of plot numbers. This invention constructs a cloud-oriented data integration system, aggregating multi-source environmental parameters and spatial attributes into a dynamic data structure. This achieves global correlation and temporal continuity of information between plots. Data is automatically processed by the cloud platform to form parameter evolution chains, establishing multi-level characteristic criteria for monitoring objects, including coverage, temporal sequence, and trend. Abnormal evolution of disease status is directly fed back to the management and control process through linkage judgment. The system outputs control configurations based on real-time status, thereby improving the consistency of risk assessment and the pertinence of control decisions.

Description

Technical Field

[0001] This invention relates to the field of green space management technology, and in particular to a cloud-based intelligent green space management system. Background Technology

[0002] Green space management involves the construction, maintenance, and management of urban green spaces, including the planning and design of green space structures, management of vegetation growth cycles, monitoring and control of pests and diseases, water and fertilizer regulation, monitoring of environmental factors, and information management of green space resources. Traditional intelligent green space management systems refer to information systems applied to urban parks, green belts, and other green spaces to collect, schedule, and manage green space maintenance information. These systems typically rely on local server architecture for data storage and processing, collecting plant growth data and environmental information manually or through low-frequency automated equipment, and then combining this with preset rules for task management and personnel scheduling.

[0003] The existing system relies on a single-region data processing architecture, resulting in information isolation between green areas across regions. Data timeliness is limited by the collection cycle, the monitoring frequency of vegetation growth and environmental changes is low, and parameter data is difficult to form a continuous dynamic correlation. The system is mostly managed by passive task registration, and the pest and disease identification process is limited to single-point triggering, which cannot realize dynamic inference of multi-dimensional disturbances. Control measures are difficult to adapt to the real-time changes in the ecological status of green areas, resulting in lag and misjudgment in risk warning and control response. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a cloud computing-based intelligent green space management system.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a cloud computing-based intelligent green space management system, the system comprising:

[0006] The cloud-based multi-source integration module is based on various green space field monitoring points. It judges the status of sensor devices and the accuracy of plot numbers, compares the synchronization of node temperature and humidity with moisture, integrates remote sensing vegetation information, and pairs the coverage area with plot records to obtain a set of integrated green space multi-source parameters.

[0007] The temporal disturbance analysis module, based on the integrated set of multi-source parameters of the green space, filters the temperature and moisture sequences of each plot, calculates the direction of change, determines the moment of trend reversal, classifies synchronous disturbance nodes, compares the time distribution patterns, and obtains a set of temporal change nodes.

[0008] Based on the set of time-series change nodes, the disturbance chain association module analyzes the synchronization of leaf heat and soil moisture trends, determines the association order of disturbance nodes, determines the disturbance propagation process, and obtains multi-parameter disturbance association data.

[0009] Based on the multi-parameter disturbance correlation data, the disease trend identification module calculates various green space light and heat sequences, determines the disturbance chain stage interval, compares the disturbance chain stage interval with vegetation cover dynamics, identifies trend stability areas, and obtains green space abnormal evolution characteristics.

[0010] Based on the abnormal evolution characteristics of the green space, the management and control linkage module determines the area type, compares the matching relationship between irrigation and shading spray, filters and transmits key parameters, adjusts control commands, and obtains the green space management and control configuration.

[0011] The present invention improves upon the following: the integrated set of multi-source parameters for green space includes a set of plot environmental parameters, a set of vegetation spatial attributes, and a monitoring data index identifier; the set of time-series change nodes includes parameter turning point markers, coordinated fluctuation markers, and time-series location labels; the multi-parameter disturbance correlation data includes disturbance correlation units, propagation relationship identifiers, and parameter coupling structures; the abnormal evolution characteristics of green space include abnormal development types, change persistence patterns, and spatial distribution characteristics; and the green space management and control configuration includes regional control scheme identifiers, operational measure combination items, and control status configuration items.

[0012] The present invention is improved in that the cloud-based multi-source integration module includes:

[0013] The equipment status identification submodule is based on various green space on-site monitoring points. It obtains the unique identifier and signal upload status of each sensing device, retrieves the plot number information reported by each sensing node, compares the correspondence between the node identifier and the plot number, performs status classification for nodes with incorrect or missing numbers, counts the number of equipment statuses, and obtains equipment status identification information.

[0014] The data time sequence discrimination submodule collects temperature, humidity and soil moisture monitoring data uploaded by each node at a unified time period based on the device status identification information, aligns the collected data according to time tags, compares the differences in parameters between each node at the same time point, and filters the node combination with consistent time sequence to obtain parameter time sequence consistency distribution group.

[0015] The remote sensing information matching submodule acquires vegetation spectral image data uploaded by the remote sensing platform in the corresponding time period based on the parameter temporal consistency distribution group, extracts the spatial coverage boundary of the plot image and vegetation growth monitoring data, matches each data according to the spatial overlap between the plot number and the image coverage area, and calls it to the cloud platform to obtain the integrated set of green space multi-source parameters.

[0016] The present invention is improved in that the timing perturbation analysis module includes:

[0017] The monitoring sequence extraction submodule analyzes temperature and soil moisture records based on the integrated set of multi-source parameters of the green space, judges the integrity of data identifiers and time tags, compares the time order of records within the same plot, filters continuously arranged monitoring items, adjusts the order of records with conflicting identifiers, and obtains the plot monitoring time series dataset.

[0018] The change direction determination submodule analyzes the continuously arranged temperature and soil moisture sequences based on the plot monitoring time series dataset, compares the directional attributes of parameter changes at adjacent time nodes, determines whether the change direction has switched, filters the time locations where the direction switch occurs, and obtains the set of parameter change inflection nodes.

[0019] The synchronization disturbance aggregation submodule compares the arrangement of different plots' transition nodes on the time axis based on the parameter change transition node set, determines whether the nodes are in overlapping or adjacent time intervals, identifies node combinations with synchronization performance, adjusts the merging relationship between nodes and regions, and obtains a time-series change node set.

[0020] The present invention is improved in that the disturbance chain association module includes:

[0021] The key node screening submodule, based on the set of time-series change nodes, determines the direction of change of each node at each time point, compares the spatial distribution and frequency of trend reversal among nodes, and screens nodes with trend change characteristics and continuous fluctuations in monitoring data to obtain disturbance event discrimination nodes.

[0022] The time axis comparison submodule analyzes the corresponding leaf heat curve and soil moisture curve based on the disturbance event discrimination node, calculates the difference in curve changes within the same monitoring period, compares the time interval between curve change points, identifies nodes that synchronously fluctuate, and obtains a multi-parameter synchronous offset sequence.

[0023] The link structure construction submodule, based on the multi-parameter synchronous offset sequence, compares the temporal changes and spatial distribution between nodes, calculates the synchronous offset and spatial distance of sequential nodes, analyzes the propagation coupling relationship between nodes to obtain the propagation coupling strength value, filters the node chain that satisfies the coupling relationship, and obtains multi-parameter perturbation association data.

[0024] The present invention is improved in that the disease trend identification module includes:

[0025] The disturbance trend generation submodule calculates the changes in leaf heat sequence and soil moisture content sequence on the same time axis based on the multi-parameter disturbance correlation data, determines the time when the disturbance node causes a trend reversal, compares the synchronicity of light intensity and leaf heat changes, and obtains the disturbance trend synchronization index.

[0026] The disturbance chain segment identification submodule, based on the disturbance trend synchronization index, filters the intervals where light and heat change synchronously, analyzes the time intervals between continuous disturbance nodes, compares the time intervals with the fluctuation characteristics within the intervals, summarizes and classifies the duration of fluctuations, and obtains a set of continuous intervals of the disturbance chain.

[0027] The stability region extraction submodule analyzes the vegetation coverage data of the target plot within the remote sensing monitoring period based on the continuous interval set of the disturbance chain, calculates the vegetation coverage change trend in each time period, compares the synchronicity between the coverage change and the fluctuation amplitude of the disturbance chain within the segment, determines the spatial range with consistent trends, and obtains the abnormal evolution characteristics of green space.

[0028] The present invention is improved in that the management and control linkage module includes:

[0029] The regional type determination submodule determines the spatial distribution range of the plots based on the abnormal evolution characteristics of the green space, compares the plot numbers with the standard information of the preset types of urban parks and ecological protection forests, identifies the plot codes that meet the regional type conditions, adjusts the attribution relationship between the plots and the regional categories, and obtains the target regional type mapping set.

[0030] The regulation measure matching submodule, based on the target area type mapping set, determines the disturbance type label under each category, compares the adaptability between the regional disturbance performance and irrigation regulation and shading spray regulation measures, filters the measure groups associated with the response relationship, adjusts the priority order of the measures, and determines the matching result between the measures and the area, thus obtaining the regional regulation measure adaptation result.

[0031] Based on the adaptation results of the regional control measures, the command parameter linkage submodule determines the equipment control tasks that need to be triggered, compares the response of the monitoring parameters returned after the measures are executed, filters the linkage matching items between key response parameters and tasks, adjusts the order of command issuance, and obtains the green space management and control configuration.

[0032] The present invention is improved in that the plot number refers to dividing the monitoring area into several units, each of which is assigned a unique number; the coverage area refers to the spatial range that the remote sensing platform or sensing device can monitor, that is, the actual green area covered by a certain data collection point or image; and the direction of change refers to whether a certain monitoring parameter increases or decreases between adjacent time points, reflecting the trend of parameter change over time.

[0033] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0034] In this invention, by constructing a cloud-oriented data integration system, multi-source environmental parameters and spatial attributes are aggregated into a dynamic data structure, realizing global correlation and temporal continuity of information between plots. The data is automatically sorted by the cloud platform to form parameter evolution links, establishing multi-level characteristic criteria such as coverage, time series, and trend for the monitored objects. The abnormal evolution of disease status is directly fed back to the management and control process through linkage judgment. The system outputs control configuration based on real-time status, thereby improving the coherence of risk assessment and the pertinence of control decisions. Attached Figure Description

[0035] Figure 1 This is a system flowchart of the present invention;

[0036] Figure 2 This is a flowchart of the cloud-based multi-source integration module in this invention;

[0037] Figure 3 This is a flowchart of the timing perturbation analysis module in this invention;

[0038] Figure 4 This is a flowchart of the disturbance chain association module in this invention;

[0039] Figure 5 This is a flowchart of the disease trend identification module in this invention;

[0040] Figure 6 This is a flowchart of the management and control linkage module in this invention. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0042] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0043] All user-related information involved in this invention (including but not limited to biometric information, identity verification information, behavioral data, device information, and other data that can be used for identity verification and personalized services) is collected and processed with the user's full knowledge and voluntary consent. The use of data is limited to purposes necessary for providing the technical services of this invention, and reasonable technical and management measures will be taken to ensure the security and confidentiality of users' personal information in terms of information protection and privacy.

[0044] Example

[0045] Please see Figure 1 This invention provides a technical solution: a cloud-based intelligent green space management system comprising:

[0046] The cloud-based multi-source integration module is based on various green space field monitoring points. It judges the online status of the sensing devices and the accuracy of the plot number, compares the synchronization and consistency of temperature, humidity and soil moisture data of each node, integrates the vegetation information uploaded by the remote sensing platform, pairs the spatial coverage area with the plot monitoring records, and calls them to the cloud platform to obtain the integrated set of green space multi-source parameters.

[0047] The temporal disturbance analysis module is based on the integrated set of multi-source parameters of green space, filters the temperature and soil moisture monitoring sequences of each plot, calculates the direction of change of monitoring parameters in continuous time period, judges the key moment when the parameter trend reverses, classifies synchronous disturbance nodes in the same area, compares the temporal distribution pattern of each node, and collects the processing results based on the cloud platform to obtain the set of temporal change nodes.

[0048] The disturbance chain association module filters key nodes in the time-series change node set, analyzes the time axis synchronization between leaf heat monitoring and soil moisture trend, determines the sequential association order between disturbance nodes, optimizes the link layer logic, judges the change process of disturbance propagation, and obtains multi-parameter disturbance association data.

[0049] The disease trend identification module analyzes the interference trend formed by multi-parameter disturbance correlation data on the cloud platform, calculates the light and heat monitoring sequences of target plots in pocket parks and vertical greening spaces, determines the continuous stage intervals of the disturbance chain, compares the disturbance chain stages with the vegetation cover dynamics monitored by remote sensing, identifies areas with trend stability, and obtains the abnormal evolution characteristics of green spaces.

[0050] The management and control linkage module determines the target area type of urban parks and ecological protection forests based on the abnormal evolution characteristics of green spaces, analyzes the disturbance categories identified by the cloud platform, compares the applicability of irrigation regulation and shading spray measures, optimizes the control sequence at the operation end, filters key response parameters in the transmitted monitoring data, and adjusts the cloud platform control commands to obtain the green space management and control configuration.

[0051] The integrated set of multi-source parameters for green space includes a set of plot environmental parameters, a set of vegetation spatial attributes, and monitoring data index identifiers. The set of temporal change nodes includes parameter turning point markers, coordinated fluctuation markers, and time series location labels. The multi-parameter disturbance correlation data includes disturbance correlation units, propagation relationship identifiers, and parameter coupling structures. The abnormal evolution characteristics of green space include abnormal development types, change persistence patterns, and spatial distribution characteristics. The green space management and control configuration includes regional control scheme identifiers, operational measure combinations, and control status configuration items.

[0052] In the cloud-based multi-source integration module, various types of green spaces refer to different types of urban ecological green spaces such as urban parks, vertical green spaces, pocket parks, and ecological protection forests, which are the object units for system monitoring and management; sensing devices refer to various intelligent hardware terminals installed in green spaces that can automatically collect environmental and vegetation data, including temperature and humidity sensors, soil moisture sensors, and light sensors, used to continuously acquire environmental parameters; plot number refers to dividing the monitoring area into several units for easy management and data positioning, with each unit assigned a unique number (plot ID) for data identification and indexing; each node refers to all deployed sensing device nodes in the system, each node can independently collect and upload local environmental parameter data; synchronization consistency refers to the degree of synchronization... The temporal consistency of data collected by the same sensing nodes at the same time reflects the degree of temporal alignment of data from each node and the basis for data integration; remote sensing platform refers to a UAV, satellite, or ground remote sensing equipment platform equipped with multispectral sensors, which can collect image data such as spectral and coverage data of green vegetation over a large area and periodically; vegetation information refers to spatial information extracted by the remote sensing platform regarding the distribution, density, growth, and health status of vegetation within the plot; spatial coverage area refers to the spatial range that the remote sensing platform or sensing equipment can monitor, i.e., the actual green area covered by a certain data collection point or image; plot monitoring record refers to the summary of multi-source environmental and vegetation historical data collected by various sensors and remote sensing equipment within each plot after being classified and organized based on plot number.

[0053] In the temporal disturbance analysis module, the plot temperature and soil moisture monitoring sequence refers to the time series data set formed by collecting temperature and soil moisture content data at different time points within the same plot unit; the direction of change refers to whether a certain monitoring parameter (such as temperature and humidity) increases or decreases between adjacent time points, reflecting the changing trend of the parameter over time; the parameter trend refers to the summary of the overall changes of temperature, soil moisture content, etc. over time, which can be characterized by continuous increase, decrease, or stability; the critical moment refers to the time node in the monitoring sequence where the parameter trend changes significantly from increase to decrease or from decrease to increase, which is the mark moment for identifying disturbance events; synchronous disturbance nodes refer to the nodes in the same area or related parameters where different monitoring indicators show trend changes within a similar time period, indicating the coordinated fluctuation between multi-source data; the temporal distribution pattern refers to the distribution of all disturbance nodes on the time axis, which can be analyzed to determine the concentration or dispersion of disturbance events within a certain period; the cloud platform processing result refers to the processing output generated after the cloud server performs temporal alignment, trend analysis, and disturbance identification on the original data, including node screening and structured integration.

[0054] In the disturbance chain correlation module, key nodes refer to nodes that are identified as representative and important after screening in the set of time-series change nodes, usually corresponding to the occurrence points of events such as mutations, fluctuations, and anomalies; time axis synchronization refers to whether multiple monitoring parameters (such as leaf surface heat and soil moisture content) change simultaneously or nearly simultaneously in time when analyzing disturbance events, judging the temporal correlation between them; link hierarchical logic refers to classifying and organizing disturbance events of different types and time sequences in a hierarchical manner, establishing a logical relationship chain between disturbance events (such as sequential causality, synchronous influence, etc.); the change process of disturbance propagation refers to the spatiotemporal evolution process of a disturbance (such as a sudden drop in moisture) between plots and parameters, reflecting the complete trajectory of the event's impact from its starting point to its spread and development.

[0055] In the disease trend identification module, the disturbance trend refers to the comprehensive evolution of multi-parameter disturbance events (such as environmental and vegetation anomalies) in time and space, which is an early signal of subsequent risks or disease formation; the light and heat monitoring sequence refers to the continuous monitoring data related to energy metabolism, such as light intensity and leaf surface temperature difference, obtained at different time points in the target plot; the continuous stage interval refers to the continuous stage of the disturbance chain in the time series, reflecting the time range of continuous occurrence of abnormal changes; vegetation cover dynamics refers to the process of changes in vegetation distribution and density in green space over time, which can be obtained through remote sensing images or ground observations; the trend stability performance area refers to the spatial area where the disturbance trend is relatively continuous and difficult to reverse within a certain period of time by comparing various change indicators, which is usually the key focus for subsequent attention.

[0056] In the management and control linkage module, the target area type refers to determining whether a plot of land belongs to a specific green space type, such as an urban park or ecological protection forest, based on its identified location and attributes, so as to adopt appropriate management and control strategies in the future; the disturbance category refers to the type of disturbance phenomenon (such as water disturbance, light and heat imbalance, etc.) summarized by the cloud platform through analysis of previous abnormal data, which guides the selection of control measures; the applicability relationship refers to the matching assessment between different control measures (such as irrigation, spraying, shading) and the existing state of the target area to determine the most suitable management and control method; the operation terminal control sequence refers to organizing different control tasks according to priority, region, or time sequence, and reasonably arranging the execution process of each device to improve the overall response efficiency; the key response parameters refer to the parameters that are key to be observed by monitoring after the control is executed (such as soil moisture, leaf temperature, etc.), which are used to judge the control effect and system response status; the cloud platform control command refers to the instructions automatically generated by the cloud based on the type of disease or abnormality and real-time monitoring feedback, which are directly sent to the field equipment or operation terminal to guide the management and control equipment to complete the actual control actions.

[0057] Please see Figure 2 The cloud-based multi-source integration module includes:

[0058] The equipment status identification submodule is based on various green space on-site monitoring points. It obtains the unique identifier and signal upload status of each sensing device, retrieves the plot number information reported by each sensing node, compares the correspondence between the node identifier and the plot number, performs status classification for nodes with incorrect or missing numbers, counts the number of equipment statuses, and obtains equipment status identification information.

[0059] Each node's built-in sensors automatically report their unique identification code upon startup. This code typically consists of 12 characters; for example, device A's identification code is "D1F2A3B4C5E6". Upon receiving a message, the system extracts this identification code and records the current upload time, such as "2025-01-12, 10:00:00". Then, it extracts the land parcel number information attached to the message. For example, if the device reports land parcel number "000302", it compares this with the pre-defined land parcel number "000305" corresponding to "D1F2A3B4C5E6" in the database. If a discrepancy is found, it is directly determined to be an incorrect number. Another example is... If the uploaded data "C9D8E7A6B5F4" does not include any plot number field or the field is empty, it is directly marked as missing number. All nodes are divided into three categories: "correct number", "incorrect number", and "missing number". Then, the data is statistically analyzed by green space type. For example, in a vertical greening area, there are 60 sensors. 52 are marked as "correct number", 5 as "incorrect number", and 3 as "missing number". After the statistics are completed, a list is generated to record the unique identification code, current identification status, corresponding plot number, error type, and data upload time of each device. This forms a data source for subsequent time-series data identification and obtains the device status identification information.

[0060] The data time series discrimination submodule collects temperature, humidity and soil moisture monitoring data uploaded by each node at the same time period based on the device status identification information. It aligns the collected data according to the time label, compares the differences between parameters of each node at the same time point, and filters the node combination with consistent time series to obtain parameter time series consistency distribution group.

[0061] Based on the set of devices marked "correctly numbered," data upload records from nodes within a unified monitoring period were collected. Using January 1st to January 10th, 2025 as the cycle, data was collected at three fixed time points daily (6:00 AM, 2:00 PM, and 10:00 PM), totaling 30 time points. The parameters extracted at each time point were temperature, air humidity, and soil moisture. Each node's uploaded data was accompanied by a precise timestamp. Data from each node was filtered based on its timestamp, retaining only combinations of the three data items with perfectly aligned timestamps. Nodes where all three parameters (temperature, humidity, and moisture) were present at that time point were considered valid participants. Then, numerical differences were determined for similar parameters from different nodes at the same time point. For example, at 2:00 PM on January 3rd, 2025, 95 valid node data points were collected, with temperature values ​​concentrated between 13.5℃ and 16.1℃. The average temperature for this batch was calculated. With a temperature of 14.6℃ and a standard deviation of 0.7℃, the temperature difference judgment range is set to fluctuate by twice the standard deviation above and below the average value, i.e., between 13.2℃ and 16.0℃. Nodes whose temperatures fall within this range are considered to have consistent temperatures. The same method is applied to humidity and moisture data, with a fluctuation range of ±15%. The average humidity is 64%, so the consistency judgment range is 54% to 74%. The average soil moisture is 24%, and the consistency range is 20% to 28%. At this time point, if device "D1F2A3B4C5E6" reports data of 14.8℃ temperature, 67% humidity, and 23% soil moisture, all three of which fall within the consistency judgment range, this node is considered to be "time-series consistent". This judgment logic is applied to each time point, and cross-aggregation is performed through node IDs to identify a set of nodes that exhibit time-series consistency at multiple time points, i.e., the parameter time-series consistency distribution group.

[0062] The remote sensing information matching submodule acquires vegetation spectral image data uploaded by the remote sensing platform in the corresponding time period based on the parameter temporal consistency distribution group, extracts the spatial coverage boundary of the plot image and vegetation growth monitoring indicators, matches each data according to the spatial overlap of the plot number and the image coverage area, and calls it to the cloud platform to obtain the integrated set of green space multi-source parameters.

[0063] The system automatically retrieves multispectral image data of green areas acquired during the same time period from the remote sensing platform. Taking 2 PM on January 3rd as an example, it finds a set of aerial images covering plot "000305". The images contain information such as NDVI vegetation index and spectral channel reflectance. The platform records the coverage area of ​​this image as the upper left corner coordinates 117.145E, 39.081N and the lower right corner coordinates 117.148E, 39.078N. After coordinate conversion, the actual coverage area of ​​this image is 900 square meters. The overlap with the preset boundary area of ​​plot "000305" (950 square meters) is calculated, and the overlapping area is 840 square meters. Therefore, the spatial overlap rate is 840 / 900. 50% = 88.4%, which is higher than the set threshold of 80%, indicating that the remote sensing image is considered to have successfully matched the plot number. Subsequently, the average NDVI value of the image is extracted as 0.76 and the standard deviation is 0.04. The spatial vegetation distribution range and growth range of the plot are recorded. The vegetation image parameters and the monitoring data of the time-consistent nodes (such as temperature 14.8℃ and moisture 23%) are packaged together and called to the cloud platform. Combined with the upload time "2025-01-03, 14:00", a data combination with "plot number + node monitoring value + remote sensing index + spatiotemporal coverage" is generated. This process is automatically completed in batches and uniformly organized into a green space multi-source parameter integration set.

[0064] Please see Figure 3 The timing perturbation analysis module includes:

[0065] The monitoring sequence extraction submodule analyzes temperature and soil moisture records based on the integrated set of multi-source parameters of green space, judges the integrity of data identifiers and time labels, compares the time order relationship of records within the same plot, filters the continuously arranged monitoring items, adjusts the order of records with conflicting identifiers, and obtains the plot monitoring time series dataset.

[0066] Temperature and soil moisture records are categorized and extracted according to plot number. For example, the data group corresponding to plot number "000213" contains data uploaded at three time points each day from January 1, 2025 to January 10, 2025, totaling 30 groups. Each group of records includes fields such as upload time, temperature value, soil moisture value, equipment identifier, and data record number. A field integrity check is performed on each record, judging whether a field is empty or contains an illegal value. For example, if the upload time of a record is "null" or the record number appears twice, it is judged as incomplete or conflicting. The record number is generated sequentially using a six-digit number, and the time tag uses the standard time format "YYYY-MM-DDHH:MM:SS". After completing the field integrity check, the data is processed by plot. All records are sorted in ascending order by the timestamp field. After sorting, the time interval between adjacent records is checked to see if it is a fixed collection cycle. For example, with a collection frequency of 3 times per day, the interval should be 8 hours. If the interval between two time points exceeds 9 hours, it is considered a non-continuous record and is removed from the sequence. In a continuous time series, if a record has the same number as the previous one or the device identifier is different but the number is the same, it is marked as "number conflict". The conflicting records are automatically sorted later or temporarily removed to ensure that the overall records are continuous in time, unique in number and clear in source. The data of each plot after integrity verification, time order sorting and conflict handling are summarized to form a set of temperature, humidity and soil moisture records classified by plot number and arranged continuously by time label, which is the plot monitoring time series dataset.

[0067] The change direction determination submodule is based on the plot monitoring time series dataset. It analyzes the continuously arranged temperature and soil moisture sequences, compares the directional attributes of parameter changes at adjacent time nodes, determines whether the change direction has switched, filters the time locations where the direction switch occurs, and obtains the set of parameter change inflection nodes.

[0068] For each plot, the temperature and soil moisture data are analyzed by calculating the difference between adjacent nodes to determine the direction of change. The calculation method is to subtract the previous value from the later value. For example, in plot number "000213", the temperature at 14:00 on January 2, 2025 was 16.3℃, and the temperature at 18:00 was 15.8℃, with a difference of -0.5, indicating a decrease. The soil moisture was 25% and 24.2% respectively, with a difference of -0.8%, also indicating a decrease. The direction is represented by the symbols "+" for increasing, "−" for decreasing, and "0" for remaining unchanged. The direction of the difference at each time point is continuously recorded. Then, the sequence is traversed to determine whether the direction has switched from increasing to decreasing or vice versa, serving as the basis for the change in direction of change. The condition is that the signs of two consecutive adjacent changes in direction are inconsistent, which indicates a switch. For example, the consecutive appearance of "++−" indicates that a positive-to-negative switch occurred in the second and third time periods. This judgment operation is performed synchronously in the temperature and moisture records of each plot, and the specific time points with the state of change direction switching are selected. In a practical example, if the temperature at 14:00 on January 4, 2025 is 17.0℃, at 18:00 it is 17.3℃, and at 22:00 it is 16.7℃, then the direction sequence is "+−", which is judged as a turning point. "2025-01-04, 22:00" is marked as the turning point node. The execution process is repeated for each set of monitoring data to extract a series of time points with obvious change direction switching. The nodes constitute the parameter change turning point node set.

[0069] The synchronization disturbance collection submodule compares the arrangement of different plots' turning points on the time axis based on the parameter change turning point set, determines whether the nodes are in overlapping or adjacent time intervals, identifies node combinations with synchronization performance, adjusts the merging relationship between nodes and regions, and obtains a time-series change node set.

[0070] All plot turning points are sorted in ascending order by timestamp and clustered by time interval. The criterion for determining whether two or more nodes are in a state of synchronous disturbance is that the time difference does not exceed a set merging threshold. For example, adjacent time points less than or equal to 1 hour are considered adjacent intervals. If plot "000213" turns at 14:00 on January 5th and plot "000214" turns at 14:45 on January 5th, the time difference between these two nodes is 45 minutes, less than 1 hour, and they are determined to be synchronous disturbance nodes, included in the same merging group. However, if the time of plot "000215" is 15:50 on January 5th, more than 1 hour after the turning point of "000213", then it is not considered a synchronous disturbance node. If multiple plot nodes have a time interval of less than 1 hour, they are marked as nodes in the same group, and their assigned region number and node list are recorded in the structure. For example, synchronization group S1 includes “000213_2025-01-05, 14:00”, “000214_2025-01-05, 14:45”, and “000216_2025-01-05, 13:50”, and its corresponding region number is “Area A”. Synchronization group S2 is classified separately. Each node belongs to only one group. Time comparison and attribution labeling are performed on all nodes according to this rule to construct a series of disturbance node combinations with time adjacency and trend switching, forming a set of time-series changing nodes.

[0071] Please see Figure 4 The disturbance chain association module includes:

[0072] The key node screening submodule is based on the time-series change node set, determines the direction of change of each node at each time point, compares the spatial distribution and frequency of trend reversal among nodes, and screens nodes with trend change characteristics and continuous fluctuations in monitoring data to obtain disturbance event discrimination nodes.

[0073] The temporal variation data of each node is retrieved according to the plot number, and the direction of temperature change and soil moisture change within a continuous time period is extracted. The direction is determined by the sign of the difference between two adjacent time points. For example, if the temperature value of a node is 13.2℃ at 6:00 on January 10th and 14.6℃ at 12:00, the difference is +1.4, and the direction is determined to be rising. If it subsequently changes to 13.9℃ at 18:00, the difference is -0.7, and the direction is falling. This node has a direction reversal within that day, and the number of reversals and the length of the continuous direction sequence are recorded. Then, the spatial distribution between nodes is analyzed. The nodes are grouped according to the coordinates of the area to which the plot belongs, and adjacent node groups are divided with a relative distance of 10 meters. For example, the horizontal coordinate distance between nodes numbered "000120" and "000123" is 8.6 meters and the vertical coordinate distance is 3.2 meters, so they are determined to be spatially adjacent. Then, the trend reversal frequency of each node within 5 days is counted. If the continuous time... If a node experiences more than two reversals in a sequence and its fluctuation amplitude exceeds a set threshold (e.g., an absolute temperature change greater than 1.2℃ or a moisture change greater than 2%), it is marked as "volatile". Further comparison is made between the volatile node and its neighboring nodes to determine the consistency of their trends. If multiple adjacent nodes show a trend reversal on the same day, the node is categorized as a trend concentration area node. Finally, nodes with more than three consecutive days of monitoring data, more than two trend reversals, and spatial clustering are selected as key identification nodes. For example, node "000120" uploaded 18 data entries between January 3rd and January 7th, with temperature direction changes occurring on the 3rd, 4th, and 6th. Furthermore, it, along with nodes "000121" and "000123", all showed a decrease in moisture content at 14:00 on the 5th. Therefore, it is identified as a trend change node and used as a disturbance event identification node.

[0074] The time axis comparison submodule analyzes the corresponding leaf heat curve and soil moisture curve based on the disturbance event discrimination node, calculates the difference in curve changes within the same monitoring period, compares the time interval of curve inflection points, identifies nodes that synchronously fluctuate, and obtains a multi-parameter synchronous offset sequence.

[0075] Leaf surface heat data and soil moisture content data recorded by each node within the same monitoring period are extracted. Leaf surface heat is indirectly obtained by calculating the temperature difference between the leaf surface and the air using an infrared sensing module. For example, at 14:00 on January 5th, node "000120" recorded a leaf surface temperature of 32.6℃ and a corresponding air temperature of 28.4℃, resulting in a leaf surface heat value of 4.2℃. Soil moisture content was measured at the same time as 23.4%. These two types of curves are aligned by timestamps to generate a double-series curve graph of leaf surface heat and soil moisture content. Then, the variation difference of each curve within the monitoring period is calculated to determine whether there are abrupt changes or inflection points within a continuous time period. The inflection point determination logic is: the current value has a different direction sign than the values ​​before and after it, and the numerical difference exceeds a set abrupt change threshold. For example, if the leaf surface heat is 3.8℃ at 12:00 and 4.2℃ at 14:00, the leaf surface heat value is 4.2℃. If the temperature is 3.3℃ at 00, the change direction is "+−", and the difference exceeds 0.7℃, it is determined to be an inflection point on the heat curve. Similarly, the inflection point on the moisture content curve is determined by setting a sudden change threshold of 2%. If an inversion occurs between adjacent time periods and the difference is greater than 2%, it is considered an inflection point. For example, 24.8%, 23.4%, and 25.6% are considered to be inflection points. All inflection point time points of the two types of curves are extracted and the time axis differences are compared. If the time interval between the inflection points of the two curves is within 1 hour, it is considered to be synchronous fluctuation. For example, if the heat inflection point is at 14:00 on January 5th and the moisture inflection point is at 14:30 on January 5th, the difference between the two is 30 minutes, which is considered synchronous change. This node is further marked as "multi-parameter synchronous offset". The above process is repeated to select all nodes with highly similar inflection point times in the multi-parameter curves and combine them to form a multi-parameter synchronous offset sequence.

[0076] The link structure construction submodule, based on a multi-parameter synchronization offset sequence, compares the temporal changes and spatial distribution between nodes, calculates the synchronization offset and spatial distance of sequential nodes, and analyzes the propagation coupling relationship between nodes using the following formula:

[0077] ;

[0078] The propagation coupling strength value is obtained, and node chains that satisfy the coupling relationship are filtered to obtain multi-parameter perturbation correlation data. Represents a node To the node The propagation coupling strength value, Represents a node The time offset normalization amount, Represents a node With nodes The normalized measure of the path span between them Represents a node In the path chain index Path cumulative normalization quantity, Represents a node Normalized value of thermal disturbance amplitude Represents a node In the coupled link index Water content shift normalization, This represents the total number of disturbance propagation paths and coupling links;

[0079] Propagation coupling strength value This refers to the node in disturbance chain analysis based on multi-source monitoring data. To the node The overall strength of the perturbation propagation relationship between nodes is used to quantify the cumulative degree of perturbation impact and the tightness of the correlation between the two nodes; temporal and spatial coupling: it comprehensively considers the temporal offset, spatial path span, cumulative contribution of perturbation propagation, and the heat and water content trend characteristics of the perturbed nodes; normalized aggregation results: through normalization processing, data from different sources and dimensions can be uniformly used for comparison and calculation; measuring perturbation correlation: the larger the value, the stronger the node correlation. For nodes The impact on the propagation of disturbance events is more significant and the correlation is closer, reflecting the overall strength of the transmission of abnormal changes between the two nodes in the spatiotemporal link;

[0080] Extract Nodes With nodes The mutation time record, denoted as node The mutation time is 160 seconds, node The mutation time is 100 seconds, node -node The original timing offset is The time difference in seconds is calculated using the maximum-minimum normalization method, given that the system has a known minimum time difference of 0 seconds and a maximum of 75 seconds. Then, the spatial geometric distance between the two nodes was collected. The system's maximum path distance is 300 meters, normalized to... Further extract nodes The perturbation frequencies of the three connected perturbation paths are 21, 19, and 23, respectively. Normalization using the maximum perturbation frequency of 25 as the standard yields... And calculate the sum: Then extract the nodes. Original value of thermal disturbance fluctuation amplitude ℃, the maximum fluctuation value of the reference system is 6.25℃, normalized to: ; Data collection node The corresponding soil moisture content offsets in the three coupled links are 30%, 24%, and 26%, with a reference maximum of 40%. After normalization, they are: ; Substitute the normalized parameters above into the calculation process, and calculate the numerator: ; ; Calculation of the denominator: ; ; Calculate the coupling strength value : According to the system's preset coupling strength grading standard: when When the node pair is considered weakly coupled, no propagation chain is constructed; when When the coupling is moderate, it can be used to construct a basic propagation path structure; when... When the perturbation linkage between nodes is highly consistent, it falls into a strongly coupled channel and can be preferentially adopted as the main path of the perturbation chain; therefore, the calculation results in this study indicate that the perturbation linkage between nodes is highly consistent and belongs to a strongly coupled channel. This belongs to the medium coupling strength segment, indicating that the node To the node Effective perturbation connections have been established between them, and they can further participate in the process of propagation structure screening and path combination to obtain multi-parameter perturbation correlation data.

[0081] Please see Figure 5 The disease trend identification module includes:

[0082] The disturbance trend generation submodule, based on multi-parameter perturbation correlation data, calculates the changes in leaf surface heat sequence and soil moisture content sequence on the same time axis, determines the time when the trend reverses at the perturbation node, and compares the synchronicity of light intensity and leaf surface heat changes using the formula:

[0083] ;

[0084] Obtain the interference trend synchronization index ,in, This represents the total number of nodes in the perturbation chain. Indicates the first The illumination intensity of each time-series node Indicates a reference quantity for light intensity. Indicates the first Changes in leaf surface heat at each time point This represents the baseline quantity for changes in leaf surface heat. Indicates the first Changes in soil moisture content at each time point This represents the baseline quantity for changes in soil moisture content. Represents a dimensionless constant term;

[0085] Interference Trend Synchronization Index It is an index used to measure the synchronicity and coupling strength of fluctuations among light intensity, leaf heat change, and soil moisture change in a target plot over a period of time. The index quantifies the synchronous disturbance performance of light and heat fluctuations under the regulation of soil moisture change by combining the normalized product of light and heat changes at each time node of the disturbance chain with the square root of the normalized value of soil moisture change, and summing the absolute results of each node. The larger the index value, the higher the degree of joint disturbance of the three environmental factors during the monitoring period, and the more it can reflect the overall intensity of the target plot being affected by the synergistic influence of multiple parameters within a certain period.

[0086] Using farmland plots under continuous remote sensing monitoring as the target, raw monitoring values ​​of light intensity, leaf surface heat, and soil moisture content were acquired on the same time axis. The monitoring period was set to two consecutive perturbation nodes, corresponding to... The original values ​​of light intensity are respectively , The original values ​​of leaf surface heat were respectively , The original values ​​of soil moisture content were respectively , Based on the above values, the changes between adjacent disturbance nodes are calculated to obtain the change in leaf surface heat. Changes in soil moisture content Subsequently, proportional normalization was performed on the three types of physical quantities, with the light intensity calculated using the average value within the monitoring period as the baseline. The corresponding normalization result is: ; The change in leaf surface heat was calculated based on the absolute value of the change. ; The change in soil moisture content was calculated based on its absolute value. ; After normalization, substitute the values ​​into the following formula to calculate the disturbance trend synchronization index, where For a dimensionless constant term, This represents the total number of disturbed nodes. Since only the second node has an actual change, the second term is calculated: The final interference trend synchronization index is The response is compared with a preset benchmark interval to determine the degree of disturbance response it reflects. The interval range and corresponding description are as follows: When When the light intensity is low, it indicates a low level of disturbance response. At this time, the changes in light intensity and leaf heat are not synchronized, indicating that the vegetation's response to light and heat disturbance is not significant. When the disturbance response is moderate, there is a coordinated trend of change in light intensity and leaf heat at the disturbance node, but no strong response is observed; when When the time is significant, it indicates that the change in light directly drives large fluctuations in leaf surface heat, and the synchronicity with the fluctuation of soil moisture content is small.

[0087] Based on this segmentation rule, the current calculation result Satisfy interval The results show that among the analyzed disturbance nodes, the increase in light intensity and the increase in leaf heat show a consistent response, and the coupling relationship between the two is not significantly weakened by the disturbance of soil moisture content, thus reflecting a certain degree of disturbance synchronization trend. This synchronization index will be used as the output item of the disturbance trend generation submodule and passed into the subsequent disturbance chain segment identification process, and used to identify the continuous disturbance occurrence interval, thereby providing a continuity parameter basis for revealing the spatial change trend in stability region extraction.

[0088] The disturbance chain segment identification submodule uses the disturbance trend synchronization index to screen intervals where light and heat change synchronously, analyzes the time interval between continuous disturbance nodes, compares the time interval with the fluctuation characteristics within the interval, summarizes and classifies the duration of fluctuations, and obtains a set of continuous intervals of the disturbance chain.

[0089] First, records from all monitoring nodes showing simultaneous changes in light intensity and leaf heat values ​​within the same monitoring period were screened. The criteria for synchronous change were set as follows: the two parameters changed in the same direction at adjacent time points, and the magnitude of the change exceeded 10 W / m² for light intensity and 0.6℃ for leaf heat, respectively. For example, at a certain node, between 12:00 and 14:00 on January 6th, light intensity decreased from 650 W / m² to 615 W / m² (a decrease of 35 W / m²), and leaf heat decreased from 4.4℃ to 3.7℃ (a decrease of 0.7℃). Both decreased in direction, and the magnitude exceeded the set thresholds; this time period was recorded as a synchronous change interval. Then, the time intervals between all recorded synchronous change time periods were analyzed. If the interval between two intervals was less than equal... A disturbance segment is considered continuous if it lasts for 6 hours; otherwise, it is considered interrupted. In the example, if the previous segment ends at 14:00 on January 6th and the next segment starts at 18:00 on January 6th, with an interval of 4 hours, it is merged into the same continuous disturbance segment. Following this logic, the data of adjacent nodes or multiple nodes in the same area are merged, and the total magnitude and duration of changes in light and heat in each continuous segment are calculated. If the duration is greater than 12 hours and the average magnitude of change exceeds the set standard (average change in light exceeds 25W / m², average change in heat exceeds 0.5℃), it is marked as a continuous disturbance segment. After making this judgment for all plots, the time periods that meet the conditions are integrated and summarized, and structured records are formed by region, time range, and parameter type. These records are then combined to form a continuous interval set of disturbance chains.

[0090] The stability region extraction submodule analyzes vegetation coverage data within the remote sensing monitoring period of the target plot based on the continuous interval set of the disturbance chain, calculates the vegetation coverage change trend in each time period, compares the synchronicity between the coverage change and the fluctuation amplitude of the disturbance chain within the segment, determines the spatial range with consistent trends, and obtains the abnormal evolution characteristics of green space.

[0091] Remote sensing imagery data matching the time periods of each continuous disturbance interval is acquired, and vegetation cover index data for that time period is extracted. Vegetation cover is calculated based on the NDVI values ​​provided by the remote sensing platform, using a threshold conversion. For example, areas with an NDVI greater than 0.3 are considered to have vegetation. The percentage value is obtained by dividing the covered area by the total area of ​​the plot, and the daily coverage rate is recorded. For example, the coverage rates of plot "000305" from January 6th to January 8th were 76%, 72%, and 67%, respectively. Subsequently, the daily trend is calculated using a time series approach, specifically the change in coverage rate from the previous day to the next day. For example, a decrease from 76% to 72% indicates a downward trend. Record the direction and magnitude of the changes, and compare this trend with the trends of light and heat fluctuations within the disturbance chain interval. For example, if from January 6th to January 8th, the heat decreased from 4.5℃ to 3.2℃ and the light decreased from 660W / m² to 610W / m², both showing a downward trend, then the vegetation cover change trend of this plot during this period is recorded as consistent with the direction of the disturbance chain. The determination of consistent direction requires that the daily change direction of vegetation cover is consistent with the daily change direction of light, and also consistent with the daily change direction of heat. If all three directions are completely consistent within three consecutive days, the plot is determined to be consistent in direction within the disturbance interval. The area of ​​trend synchronization needs to be compared with the... Within a given region, vegetation change curves and disturbance chain change directions are used. A threshold for trend consistency is set at three consecutive days where the change directions are completely consistent, and the relative difference in magnitude does not exceed 10%. Amplitude consistency is determined for two groups: "vegetation cover and light" and "vegetation cover and heat." First, the three-day relative change rates of light, heat, and vegetation cover are calculated (all based on day 1). Then, the relative difference in magnitude is calculated, defined as the absolute value of the difference between the three-day relative change rates of the two factors divided by the absolute value of the three-day relative change rate of the disturbance chain index, multiplied by 100%. When the three-day relative change rate of the disturbance chain index is consistent over three consecutive days, the threshold is set at 10%. When the absolute value of the daily relative change rate is close to 0 (e.g., less than 0.5%), resulting in a small denominator and unstable results, the consistency of the magnitude of this indicator is not judged, or the absolute difference threshold is used instead. For example, if the light intensity decreases from 660 W / m² to 610 W / m², the three-day relative change rate is (610−660)÷660×100%≈−7.58%; if the vegetation coverage decreases from 76% to 67%, the three-day relative change rate is (67−76)÷76×100%≈−11.84%. The relative difference between the two is calculated as |−11.84%−(−7.58%)|÷7.58%×100%, which is approximately 56.The vegetation cover decreased by 2%, exceeding 10%, therefore the consistency of the "vegetation cover and light intensity" amplitude was not met. Synchronization determination requires simultaneously meeting two sets of amplitude thresholds: the relative difference between "vegetation cover and light intensity" amplitudes must not exceed 10%, and the relative difference between "vegetation cover and heat intensity" amplitudes must not exceed 10%. Based on this, and considering the condition of complete directional consistency for three consecutive days, it can be determined as synchronous. If the vegetation cover of another plot decreased from 76% to 70%, the three-day relative change rate was approximately -7.89%, and the relative difference with light intensity was approximately 4.1%, not exceeding 10%; simultaneously, the relative difference with heat intensity also did not exceed 10%. Therefore, under the premise of directional consistency for three consecutive days, it can be determined as synchronous and included in the trend-consistent area set. After traversing all areas, the spatial range records that meet the conditions are merged to obtain the green space abnormal evolution characteristics.

[0092] Please see Figure 6 The management and control linkage module includes:

[0093] The regional type determination submodule determines the spatial distribution range of the plots based on the abnormal evolution characteristics of green space, compares the plot numbers with the standard information of the preset types of urban parks and ecological protection forests, identifies the plot codes that meet the regional type conditions, adjusts the attribution relationship between plots and regional categories, and obtains the target regional type mapping set.

[0094] The system retrieves the plot number and geographic coordinates recorded in the abnormal evolution characteristics and combines them with a pre-set green space classification list in the urban management platform. This list categorizes urban green spaces according to function and construction planning into types such as urban parks, ecological protection forests, pocket parks, and vertical greening. Each type has a corresponding plot number range, coordinate boundaries, naming rules, and area thresholds in the database. The system matches the plot number with the spatial coordinates one by one. For example, the plot number "000302" recorded in the abnormal evolution characteristics has spatial center point coordinates of 117.124E, 39.067N and an area of ​​3600 square meters. The system compares whether this number falls within the pre-set urban park number range "000300-000399" and checks whether its spatial location falls within the urban park boundary. If it falls within the boundary and the area is greater than 3000 square meters, it is initially judged as an urban park. For each park, the fluctuation type, duration, and vegetation cover change range marked in the anomaly features are compared to those of the typical characteristics of the area. For example, the anomaly duration for urban parks is required to be no less than 24 hours, and the vegetation cover change range is required to be no less than 5%. If the NDVI of the park “000302” drops from 0.79 to 0.72 within two consecutive days, the decrease is 7%, and the duration is 48 hours, which meets the requirements of this type of feature. Therefore, the park is classified as an urban park. If a park number meets the basic features of multiple types, the primary type is selected according to the weight priority rule. For example, ecological protection forest has a higher priority than vertical greening, and urban park has a higher priority than pocket park. The above judgment operation is performed on each park in the anomaly evolution features, and the spatial range and classification type corresponding to each anomaly park are output to obtain the target area type mapping set.

[0095] The regulation measure matching submodule determines the disturbance type label under each category based on the target area type mapping set, compares the adaptability between regional disturbance performance and irrigation regulation and shading spray regulation measures, filters measure groups with response relationship association, adjusts the priority order of measures, and determines the matching result between measures and the region, thus obtaining the regional regulation measure adaptation result.

[0096] The disturbance type labels for each plot under each regional category are extracted. These labels are generated by the preceding identification module and include more than ten disturbance types such as "strong light fluctuations," "soil drought," and "abnormal leaf heat." Each type has a pre-defined table of corresponding control measures in the knowledge base. For example, "strong light fluctuations" prioritizes matching shading spray, "soil drought" prioritizes matching drip irrigation, and "abnormal leaf heat" prioritizes matching nighttime spray. The disturbance type of the current plot is matched with the corresponding measure group, and the attributes of each control measure in that group are called to compare the suitability of the measure with the current state of the plot. The judgment logic is as follows: if the current soil moisture content is below 22% and the disturbance type is drought, then the irrigation measure is effective; if the light intensity... If the temperature exceeds 780 W / m² and the heat change exceeds 0.7℃ during the midday period, shading measures are given priority. If multiple measures meet the conditions simultaneously, they are prioritized according to the urgency of the disturbance. The urgency is determined by whether the disturbance duration exceeds 12 hours and whether the abnormal parameter amplitude exceeds the threshold standard. For example, a decrease in soil moisture exceeding 4%, a heat increase exceeding 1.0℃, or a change in light intensity exceeding 100 W / m² are all included in the priority score. Measures with higher scores are ranked first. The combination of measures and the priority order corresponding to each plot number are output. For example, for plot "000302", "drip irrigation" is selected as the priority and "spraying" as the second priority. The order of measures is adjusted and recorded to obtain the regional control measures adaptation results.

[0097] The command parameter linkage submodule determines the equipment control tasks to be triggered based on the adaptation results of regional control measures, compares the response of monitoring parameters returned after the measures are executed, filters the linkage matching items between key response parameters and tasks, adjusts the order of command issuance, and obtains the green space management and control configuration.

[0098] First, analyze the types of on-site equipment that need to be activated for each control measure. For example, the control pumps and solenoid valves for drip irrigation are numbered "DV0001-DV0003", and the control module for the sprinkler head group for the spray system is numbered "SM001". Establish a mapping table between the measures and equipment numbers, and determine which equipment needs to trigger the control task according to the priority of the measures. Then, read the key monitoring parameter records returned by the equipment after the last execution. For example, after "DV0001" executed drip irrigation at 15:00 on January 5th, the soil moisture content of its plot increased from 20.5% to 23.1%, a change of 2.6%, indicating a valid response. Perform this parameter comparison for each group of equipment. If the change reaches the baseline value of the measure response, then... A response is considered valid, with baseline values ​​set at a moisture change of no less than 2%, a heat drop of no less than 0.5℃, and a light drop of no less than 50W / m². If the parameter change values ​​returned by the equipment do not meet the standards, the equipment is removed from this round of control tasks, but the response item is retained. Then, based on the response time requirements and coverage area of ​​each measure, the order of command issuance is adjusted, with measures with high time requirements issued first. For example, if the spray control response needs to take effect within 5 minutes, its command is placed first. At the same time, command conflicts are checked to ensure that different devices do not occupy the communication channel at the same time. After all tasks are completed, a control command list is generated, recording the command number, target equipment, execution time, and expected response parameter range, thus obtaining the green space management and control configuration.

[0099] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A cloud-based intelligent green space management system, characterized in that, The system includes: The cloud-based multi-source integration module is based on various green space field monitoring points. It judges the status of sensor devices and the accuracy of plot numbers, compares the synchronization of node temperature and humidity with moisture, integrates remote sensing vegetation information, and pairs the coverage area with plot records to obtain a set of integrated green space multi-source parameters. The temporal disturbance analysis module, based on the integrated set of multi-source parameters of the green space, filters the temperature and moisture sequences of each plot, calculates the direction of change, determines the moment of trend reversal, classifies synchronous disturbance nodes, compares the time distribution patterns, and obtains a set of temporal change nodes. Based on the set of time-series change nodes, the disturbance chain association module analyzes the synchronization of leaf heat and soil moisture trends, determines the association order of disturbance nodes, determines the disturbance propagation process, and obtains multi-parameter disturbance association data. Based on the multi-parameter disturbance correlation data, the disease trend identification module calculates various green space light and heat sequences, determines the disturbance chain stage interval, compares the disturbance chain stage interval with vegetation cover dynamics, identifies trend stability areas, and obtains green space abnormal evolution characteristics. Based on the abnormal evolution characteristics of the green space, the management and control linkage module determines the area type, compares the matching relationship between irrigation and shading spray, filters and transmits key parameters, adjusts control commands, and obtains the green space management and control configuration. The disturbance chain association module includes: The key node screening submodule, based on the set of time-series change nodes, determines the direction of change of each node at each time point, compares the spatial distribution and frequency of trend reversal among nodes, and screens nodes with trend change characteristics and continuous fluctuations in monitoring data to obtain disturbance event discrimination nodes. The time axis comparison submodule analyzes the corresponding leaf heat curve and soil moisture curve based on the disturbance event discrimination node, calculates the difference in curve changes within the same monitoring period, compares the time interval between curve change points, identifies nodes that synchronously fluctuate, and obtains a multi-parameter synchronous offset sequence. The link structure construction submodule, based on a multi-parameter synchronization offset sequence, compares the temporal changes and spatial distribution between nodes, calculates the synchronization offset and spatial distance of sequential nodes, and analyzes the propagation coupling relationship between nodes using the following formula: ； The propagation coupling strength value is obtained, and node chains that satisfy the coupling relationship are filtered to obtain multi-parameter perturbation correlation data. Represents a node To the node The propagation coupling strength value, Represents a node The time offset normalization amount, Represents a node With nodes The normalized measure of the path span between them Represents a node In the path chain index The cumulative normalized value of the path on the path, Represents a node Normalized value of thermal disturbance amplitude Represents a node In the coupled link index The normalized amount of water content shift on the surface This represents the total number of disturbance propagation paths and coupling links.

2. The cloud computing-based intelligent green space management system according to claim 1, characterized in that, The integrated set of multi-source parameters for green space includes a set of plot environmental parameters, a set of vegetation spatial attributes, and monitoring data index identifiers. The set of time-series change nodes includes parameter turning point markers, coordinated fluctuation markers, and time series location labels. The multi-parameter disturbance correlation data includes disturbance correlation units, propagation relationship identifiers, and parameter coupling structures. The abnormal evolution characteristics of green space include abnormal development types, change persistence patterns, and spatial distribution characteristics. The green space management and control configuration includes regional control scheme identifiers, operational measure combinations, and control status configuration items.

3. The cloud computing-based intelligent green space management system according to claim 1, characterized in that, The cloud-based multi-source integration module includes: The equipment status identification submodule is based on various green space on-site monitoring points. It obtains the unique identifier and signal upload status of each sensing device, retrieves the plot number information reported by each sensing node, compares the correspondence between the node identifier and the plot number, performs status classification for nodes with incorrect or missing numbers, counts the number of equipment statuses, and obtains equipment status identification information. The data time sequence discrimination submodule collects temperature, humidity and soil moisture monitoring data uploaded by each node at a unified time period based on the device status identification information, aligns the collected data according to time tags, compares the differences in parameters between each node at the same time point, and filters the node combination with consistent time sequence to obtain parameter time sequence consistency distribution group. The remote sensing information matching submodule acquires vegetation spectral image data uploaded by the remote sensing platform in the corresponding time period based on the parameter temporal consistency distribution group, extracts the spatial coverage boundary of the plot image and vegetation growth monitoring data, matches each data according to the spatial overlap between the plot number and the image coverage area, and calls it to the cloud platform to obtain the integrated set of green space multi-source parameters.

4. The cloud computing-based intelligent green space management system according to claim 1, characterized in that, The timing perturbation analysis module includes: The monitoring sequence extraction submodule analyzes temperature and soil moisture records based on the integrated set of multi-source parameters of the green space, judges the integrity of data identifiers and time tags, compares the time order of records within the same plot, filters continuously arranged monitoring items, adjusts the order of records with conflicting identifiers, and obtains the plot monitoring time series dataset. The change direction determination submodule analyzes the continuously arranged temperature and soil moisture sequences based on the plot monitoring time series dataset, compares the directional attributes of parameter changes at adjacent time nodes, determines whether the change direction has switched, filters the time locations where the direction switch occurs, and obtains the set of parameter change inflection nodes. The synchronization disturbance aggregation submodule compares the arrangement of different plots' transition nodes on the time axis based on the parameter change transition node set, determines whether the nodes are in overlapping or adjacent time intervals, identifies node combinations with synchronization performance, adjusts the merging relationship between nodes and regions, and obtains a time-series change node set.

5. The cloud computing-based intelligent green space management system according to claim 1, characterized in that, The disease trend identification module includes: The disturbance trend generation submodule calculates the changes in leaf heat sequence and soil moisture content sequence on the same time axis based on the multi-parameter disturbance correlation data, determines the time when the disturbance node causes a trend reversal, compares the synchronicity of light intensity and leaf heat changes, and obtains the disturbance trend synchronization index. The disturbance chain segment identification submodule, based on the disturbance trend synchronization index, filters the intervals where light and heat change synchronously, analyzes the time intervals between continuous disturbance nodes, compares the time intervals with the fluctuation characteristics within the intervals, summarizes and classifies the duration of fluctuations, and obtains a set of continuous intervals of the disturbance chain. The stability region extraction submodule analyzes the vegetation coverage data of the target plot within the remote sensing monitoring period based on the continuous interval set of the disturbance chain, calculates the vegetation coverage change trend in each time period, compares the synchronicity between the coverage change and the fluctuation amplitude of the disturbance chain within the segment, determines the spatial range with consistent trends, and obtains the abnormal evolution characteristics of green space.

6. The cloud computing-based intelligent green space management system according to claim 1, characterized in that, The management and control linkage module includes: The regional type determination submodule determines the spatial distribution range of the plots based on the abnormal evolution characteristics of the green space, compares the plot numbers with the standard information of the preset types of urban parks and ecological protection forests, identifies the plot codes that meet the regional type conditions, adjusts the attribution relationship between the plots and the regional categories, and obtains the target regional type mapping set. The regulation measure matching submodule, based on the target area type mapping set, determines the disturbance type label under each category, compares the adaptability between the regional disturbance performance and irrigation regulation and shading spray regulation measures, filters the measure groups associated with the response relationship, adjusts the priority order of the measures, and determines the matching result between the measures and the area, thus obtaining the regional regulation measure adaptation result. Based on the adaptation results of the regional control measures, the command parameter linkage submodule determines the equipment control tasks that need to be triggered, compares the response of the monitoring parameters returned after the measures are executed, filters the linkage matching items between key response parameters and tasks, adjusts the order of command issuance, and obtains the green space management and control configuration.

7. The cloud computing-based intelligent green space management system according to claim 1, characterized in that, The plot number refers to dividing the monitoring area into several units, with each unit assigned a unique number. The coverage area refers to the spatial range that the remote sensing platform or sensing equipment can monitor, i.e., the actual green area covered by a certain data collection point or image. The direction of change refers to whether a certain monitoring parameter increases or decreases between adjacent time points, reflecting the trend of parameter change over time.

Images