Water resource fine management method and system integrated with water consumption behavior recognition

Abstract

The invention discloses a water resource fine management method and system integrated with water consumption behavior recognition, and relates to the technical field of water resource management, and the method comprises the steps: calling a water consumption event record, mining time-space water consumption characteristics, and constructing a dynamic water consumption portrait; reconstructing a fog computing topology according to the resource request condition, and establishing a resource field to determine a resource scene; deploying a user-defined scheduler according to the dynamic water consumption portrait, and executing a game to determine a water consumption strategy; and performing standardized reconstruction on a water consumption strategy, and executing scheduling and control management according to a water resource management system. The technical problems that a traditional water resource management mode does not make full use of a big data processing technology and is difficult to deal with complex water use scenes are solved, and the purposes that the big data processing technology is applied, various water use behaviors are accurately recognized, real-time dynamic resource scheduling is achieved, multi-region water use data are efficiently integrated and analyzed, the fine water resource management level is improved, and the water resource management efficiency is improved are achieved. And the technical effect of effectively dealing with complex water use scenes is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of water resource management, and in particular to a method and system for refined water resource management integrating water use behavior identification. Background Art

[0002] In the field of water resources management, accurate analysis of water use behavior and efficient resource allocation are crucial. As the demand for refined water resource management increases, traditional management methods have exposed many shortcomings.

[0003] Existing water resource management relies heavily on simple rules or manual experience, and underutilizes big data processing technology. Traditional methods struggle to deeply mine and analyze massive amounts of water use data, and are unable to accurately identify complex water use behaviors such as regular, irregular, and flexible water use. Furthermore, there is a lack of dynamic resource scheduling models based on big data processing, making it impossible to adjust resource allocation in real time based on spatiotemporal changes in water use behavior. Furthermore, in a multi-region, multi-scenario mixed water use environment, traditional methods are unable to leverage big data to fully integrate and analyze water use data from different regions, resulting in inefficient resource scheduling and a failure to meet the demands of refined modern water resource management. Summary of the Invention

[0004] This application provides a refined water resource management method and system that integrates water use behavior identification, which is used to solve the technical problem that traditional water resource management methods do not fully utilize big data processing technology and are difficult to cope with complex water use scenarios.

[0005] The first aspect of the present application provides a method for refined water resource management that integrates water use behavior identification, the method comprising: retrieving water use event records in a water use area, mining spatiotemporal water use characteristics and performing behavioral deconstruction, and constructing a dynamic water use portrait, wherein regularity, irregularity, and elastic scales are used as construction constraints; according to resource request conditions and reconstruction of the fog computing topology in the cloud, a resource field based on the water use area is established and dynamic resource isolation and elastic scaling constraints are performed to determine the resource scenario; according to the dynamic water use portrait, a custom scheduler is deployed in the cloud, and a first-layer partitioning game and a second-layer refined game are executed based on the resource scenario to determine the water use strategy; the water use strategy is standardized and reconstructed, and resource scheduling and infrastructure control management of the water use area are executed according to the water resource management system.

[0006] The second aspect of the present application provides a refined water resource management system that integrates water use behavior identification, and the system includes: a water use profile construction module, which is used to retrieve water use event records in water use areas, mine spatiotemporal water use characteristics and perform behavioral deconstruction, and construct a dynamic water use profile, wherein regularity, irregularity, and elastic scales are used as construction constraints; a resource scenario determination module, which is used to reconstruct the fog computing topology in the cloud based on resource request conditions, establish a resource field based on water use areas, and perform dynamic resource isolation and elastic scaling constraints to determine resource scenarios; a water use strategy determination module, which is used to deploy a custom scheduler in the cloud based on the dynamic water use profile, execute a first-layer partitioning game and a second-layer refined game based on the resource scenario, and determine the water use strategy; a water use strategy reconstruction module, which is used to standardize the water use strategy and execute resource scheduling and infrastructure control management of water use areas according to the water resource management system.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] This application retrieves the water use event records of the water use area, mines the spatiotemporal water use characteristics and deconstructs the behavior, and constructs a dynamic water use portrait constrained by regular, irregular, and elastic scales; reconstructs the cloud fog computing topology based on the resource request conditions, establishes a resource field including spatial three-dimensional, temporal and entropy dimensions, and implements dynamic resource isolation and elastic scaling constraints to determine resource scenarios; deploys a custom scheduler based on the dynamic water use portrait, executes a first-layer partitioning game and a second-layer refined game to determine the water use strategy; after the standardized reconstruction of the water use strategy, the water resources management system performs resource scheduling and infrastructure control management, and forms a closed loop through synchronous monitoring, anomaly tracing and feedback adjustment. This solution realizes the refined analysis of water use behavior and the spatiotemporal coordinated scheduling of resources, improves the efficiency of water resource allocation and the adaptability of the system, and achieves the technical effect of using big data processing technology to accurately identify various water use behaviors, realize real-time dynamic resource scheduling, efficiently integrate and analyze water use data in multiple regions, improve the level of refined water resource management, and effectively respond to complex water use scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 This is a flow chart of a refined water resource management method that integrates water use behavior identification provided in an embodiment of the present application.

[0011] Figure 2This is a structural diagram of a refined water resource management system that integrates water use behavior identification provided in an embodiment of the present application.

[0012] Description of the accompanying drawings: water use portrait construction module 1, resource scenario determination module 2, water use strategy determination module 3, water use strategy reconstruction module 4. DETAILED DESCRIPTION

[0013] This application provides a refined water resource management method and system that integrates water use behavior identification, which is used to solve the technical problem that traditional water resource management methods do not fully utilize big data processing technology and are difficult to cope with complex water use scenarios.

[0014] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0016] Example 1, as Figure 1 As shown, a method for refined water resource management integrating water use behavior identification is provided, wherein the method includes:

[0017] Step A100: Retrieve water use event records in the water use area, mine spatiotemporal water use characteristics, perform behavioral deconstruction, and construct a dynamic water use portrait, where regularity, irregularity, and elasticity are used as construction constraints.

[0018] In the embodiments of the present application, a water use event record refers to a digital record of water use-related events occurring within a water use area, including information such as time dimensions (e.g., the specific time period and periodic characteristics of water use), spatial dimensions (e.g., water use location and regional distribution), and water use values ​​(e.g., quantitative data such as flow rate and frequency). Spatiotemporal water use characteristics are derived by periodically clustering water use event records, traversing each event class, and mining spatial and temporal dimensional features under inter-class periodic mapping at a preset frequency. Dynamic water use profiling deconstructs the water use feature structure in three spatial and temporal dimensions, using regular, irregular, and elastic scales as constraints, to establish a dynamic model of its time series mapping.

[0019] Specifically, after retrieving the water use event records of the water use area, the technical personnel in this field perform periodic clustering on the water use event records to determine N event classes, traverse the N event classes to perform spatiotemporal water use feature mining under inter-class periodic mapping at a preset frequency to determine the water use feature structure, and then construct a dynamic water use portrait through behavioral deconstruction analysis. The specific steps are described in detail in A110-A130.

[0020] Step A200: Reconstruct the fog computing topology in the cloud based on the resource request conditions, establish a resource field based on the water usage area, perform dynamic resource isolation and elastic scaling constraints, and determine the resource scenario.

[0021] In the embodiments of the present application, resource request conditions refer to the water resource requirements of a water-using area, such as water volume, water use period, and water use type. Fog computing topology refers to a cloud-based distributed computing architecture that dynamically partitions water-using areas and reconstructs node connections, i.e., reconstructs fog nodes.

[0022] Optionally, first, the water use area is dynamically partitioned according to the resource request conditions to determine the water use partitions; then, the fog computing topology is reconstructed based on the water use partitions to determine the reconstructed fog nodes. The specific steps are described in detail in A210-A220.

[0023] Next, the resource field includes three spatial dimensions, time dimensions, and entropy dimensions. Dynamic resource isolation is performed on the resource field based on water use zoning to determine the isolated resource field. Then, the elastic scale is combined to constrain the isolated resource field, determine the requested resource field, and establish an association between the reconstructed fog node and the requested resource field to determine the resource scenario. The specific steps are detailed in A230-A260.

[0024] Step A300: Deploy a custom scheduler in the cloud based on the dynamic water usage profile, execute a first-layer partitioning game and a second-layer refinement game based on the resource scenario, and determine the water usage strategy.

[0025] In an embodiment of the present application, a custom scheduler is constructed based on dynamic water use profiling and performs sample-driven supervised training under resource scenario switching. It can be split into a logically related upper scheduler and an autonomous scheduler and deployed in the cloud.

[0026] In one embodiment of the present application, first, a custom scheduler is constructed by performing sample-driven supervised training based on the dynamic water usage profile, which is then split into an upper-level scheduler and an autonomous scheduler and deployed in the cloud. An association is then established between the autonomous scheduler and the fog computing topology. The specific steps are described in detail in A310-A330.

[0027] Next, the total amount of water resources based on the time slice is determined as the resource pool, triggering the upper scheduler to execute the resource game between water-using partitions to determine the partition resource pool, and then triggering the autonomous scheduler to execute the refined water use game within the area to determine the water use strategy. The specific steps are described in detail in A340-A360.

[0028] Step A400: Standardize and reconstruct the water use strategy, and execute resource scheduling and infrastructure control management of the water use area according to the water resource management system.

[0029] In the embodiment of the present application, the water resource management system is a system for executing resource scheduling and infrastructure control management of water-using areas, and can identify and respond to standard water use strategies converted according to their standardized dimensions.

[0030] Specifically, the water use strategy is executed based on the aggregation and splicing of water use areas to determine the regional water use strategy, which is converted into a standard water use strategy according to the standardized dimension of the water resources management system, and is recognized and responded to by the system. The specific steps are detailed in A410-A430.

[0031] Furthermore, step A100 in the method provided in the embodiment of the present application includes:

[0032] A110: Perform periodic clustering on the water use event records to determine N event classes, where N is the number of periodic cycles.

[0033] A120: Traverse the N event classes, perform spatiotemporal water usage feature mining under inter-class periodic mapping, and determine a water usage feature structure, wherein a preset frequency is used as a mining constraint.

[0034] A130: Based on the water usage characteristic structure, a dynamic water usage profile is constructed by performing behavioral deconstruction analysis.

[0035] In this embodiment, periodic clustering involves clustering water use event records by time period, classifying them into N event classes to extract periodic patterns. Inter-class periodic mapping involves performing a comparative analysis of the spatiotemporal characteristics of the same event class within different periods at a preset frequency while traversing the N event classes, thereby exploring differences and correlations in spatiotemporal water use characteristics between classes (between different periods).

[0036] Specifically, first, water use event records are periodically clustered to determine N event classes. Specifically, based on the timestamp characteristics of historical water use data, a k-means clustering algorithm is used to divide water use events into N categories based on natural cycles such as days, weeks, and months. The algorithm process is as follows:

[0037] First, based on the timestamp features of water use event records, such as the specific date and time, the cyclical attributes of the time dimension are extracted. For example, for a daily period, the number of hours is extracted; for a weekly period, the combination of the day of the week and the hour is extracted. This is converted into a numerical feature vector, such as a two-dimensional vector [day of week, hour]. The k-means algorithm is then used, with the number of clusters k set to the number of periodic cycles N (e.g., N = 14 for a biweekly model). N centroids are randomly initialized to represent N potential time period categories. The algorithm calculates the Euclidean distance between each water use event's feature vector and each centroid, assigning the event to the category to which the nearest centroid belongs. The centroid position is then updated based on the mean of the feature vectors of all events within the category. This assignment and updating process is repeated until the centroid position no longer changes significantly or the preset number of iterations is reached. Finally, water use events are classified into N event categories, each corresponding to a specific water use pattern within a specific time period, such as the weekday morning peak or the weekend midday flat period (i.e., a stable state of water demand, neither peak nor trough). This enables the automated extraction and grouping of cyclical patterns in water use events.

[0038] Next, N event classes are traversed at a preset frequency (e.g., 15 minutes / time) to conduct spatiotemporal water usage feature mining under inter-class periodic mapping. In the spatial dimension, GIS gridding technology is used to subdivide the water use area into several spatial units, such as Workshop A and Workshop B in a factory. Data such as water flow rate and equipment start / stop times within the corresponding event class time interval are then counted for each unit. In the temporal dimension, temporal fluctuations within the same event class within adjacent periods are analyzed, such as the difference in water use between Monday this week and the same period last week. This creates a three-dimensional feature matrix consisting of spatial points, time slices, and water use values. For example, mining a certain industrial area revealed that, in the event class between 9:00 AM and 11:00 AM on weekdays, the average water flow rate for Workshop A was 20 m³ / h. This data fluctuation was less than 5% for the same period for three consecutive weeks, confirming that this period exhibited a stable, high-frequency water use feature structure.

[0039] Finally, the water use characteristic structure is deconstructed in the three spatial and temporal dimensions to determine regular, irregular, and elastic structures. An overall water use portrait is constructed based on the water use characteristic structure. Three sub-order water use portraits are constructed using the three structures (the elastic structure is determined based on the spatiotemporal tensor of water use events). A time series mapping of the overall and sub-order water use portraits is established as a dynamic water use portrait. The specific steps are described in detail in A131-A133.

[0040] Through a progressive processing flow of periodic clustering event classification, high-frequency spatiotemporal feature mining, and multi-dimensional behavior deconstruction, the original water use data is converted into a structured and dynamic digital model, achieving accurate identification of regular / irregular / elastic water use behaviors, providing a refined underlying basis for subsequent resource field construction and game scheduling.

[0041] Furthermore, step A100 in the method provided in the embodiment of the present application includes:

[0042] A131: Deconstruct the water use characteristic structure in three spatial dimensions and time dimensions to determine regular structure, irregular structure and elastic structure.

[0043] A132: Construct an overall water use portrait based on the water use characteristic structure, and construct a sub-level water use portrait based on the regular structure, irregular structure and elastic structure, wherein the sub-level water use portrait includes three items, and the elastic structure is determined based on the spatiotemporal tensor of the water use event.

[0044] A133: Establish a time series mapping between the assembly water usage profile and the sub-level water usage profile as the dynamic water usage profile.

[0045] Optionally, first, use the three-dimensional spatial X, Y, Z coordinates or regional grid coding and the time dimension (such as minute-level time periods, daily / weekly / monthly cycles) as the analysis framework to perform a multi-dimensional deconstruction of the water use characteristic structure. Using the aforementioned spatial grid division technology, such as dividing the water use area into 100m×100m grid cells, combined with a time series decomposition algorithm (such as STL seasonal decomposition), the water use characteristic structure can be decomposed into:

[0046] Regular structure: water use patterns that recur within fixed time and space units, such as the average water flow rate of 5 m³ / h in each unit of a residential community from 7:00 to 9:00 every day, with a fluctuation coefficient of less than 8% for 30 consecutive days; irregular structure: sudden water use events that deviate from the normal pattern, such as equipment cleaning in a factory causing the flow rate to suddenly increase to three times the average level during a certain period, with no historical record for the same period; elastic structure: flexible water use patterns determined based on the space-time tensor, that is, the rate of change of water consumption with respect to space-time variables, such as ΔQ / ΔT (temperature change) and ΔQ / ΔS (spatial distance), such as the seasonal fluctuation characteristic that water consumption in a certain area increases by 1.5% for every 1°C increase in summer temperature.

[0047] Secondly, a two-layer water use portrait system is constructed based on the deconstructed feature structure. The process of modeling the water use portrait of the assembly is as follows:

[0048] The overall water use profile constructs a global feature model using a spatiotemporal data aggregation algorithm. First, the spatiotemporal data of the water use area is standardized, using spatial grids (e.g., 100m×100m cells) and time slices (e.g., one hour per slice) as basic units. Statistics such as total water use and average flow within each cell are summarized. Time series analysis (e.g., moving average and seasonal decomposition) is used to extract trends in total water use across the entire region, generating fluctuation curves at monthly, weekly, and daily scales. For example, polynomial functions are fitted to identify increasing or decreasing trends in water use over time. Spatially, spatial interpolation techniques (e.g., kriging) are used to convert discrete water use data into continuous thermal distribution maps, annotating high-water-consuming areas (e.g., industrial plants and commercial centers) and their spatiotemporal distribution characteristics. Finally, the overall profile is presented as a spatiotemporal matrix and statistical charts, visually reflecting global water use patterns. For example, it demonstrates a seasonal trend where a park's total summer water use is 20% higher than its winter use, or a diurnal difference where nighttime water use accounts for less than 15% of daytime water use in a particular area.

[0049] During the modeling process of the sub-level water use profile, the sub-level water use profile is modeled based on three types of deconstruction features:

[0050] Regular structure profiling: Based on periodic clustering results, such as N = 14 event types, template modeling is performed on the spatiotemporal data within each periodic cluster. For example, for the weekday morning rush hour event class, the mean and standard deviation of water flow for each spatial unit during that period are calculated to form a standardized water use sequence template. If the average flow rate on a certain floor from 7:00 to 9:00 is 3 m³ / h with a fluctuation of less than 5%, this pattern is defined as a regular structure feature.

[0051] Irregular Structure Profiling: First, anomaly detection algorithms, such as the Isolation Forest algorithm, are used to identify outliers in high-dimensional water use data. This algorithm constructs multiple random forests and uses the path length of sample points within the forest to determine the degree of anomaly, effectively capturing sudden water use events. A dynamic threshold method is also employed. Based on the statistical characteristics of historical water use data (such as mean and standard deviation), threshold intervals are set that adjust dynamically over time. When real-time monitored indicators such as water flow and frequency exceed the threshold range, an abnormal event detection mechanism is triggered. After identifying an abnormal event, spatiotemporal trajectory tracking techniques, such as the Kalman filter algorithm, are used to recursively filter the spatiotemporal data of the event, predicting and updating the event's start time, spatial location (such as pipe network node coordinates), and diffusion path parameters. The event's dynamics are tracked by iteratively calculating optimal estimates. Finally, combined with the spatial analysis capabilities of GIS maps, the spatiotemporal trajectory data of the abnormal event is converted into a visual leak diffusion heat map. Color gradients and contour lines are used to indicate the impact area and water flow direction, enabling precise location and dynamic display of irregular water use events.

[0052] Elastic Structural Profiling: Based on the random forest learning algorithm, a correlation model between water usage variables and environmental factors is established. First, feature engineering is performed on external variables such as temperature, humidity, and holidays, converting them into numerical features (e.g., temperature numeric values ​​and holiday binary identifiers). These features, along with water usage data (e.g., flow rate and time of day), form a training dataset. Supervised learning is performed on the training dataset using the random forest algorithm, leveraging the ensemble learning capabilities of multiple decision trees to capture nonlinear relationships. For example, by calculating the feature importance scores of each environmental factor, it is determined that temperature has the highest weight on water usage. After model training is complete, real-time environmental variables are input to output predicted water usage values. The coefficient of deviation is calculated by comparing these values ​​with the actual values. For example, a linear relationship is established, indicating a 1.5% increase in water usage for every 1°C increase in temperature. The goodness of fit of the model is measured using a coefficient of determination (R²) of 0.82. To cope with seasonal and sudden changes, an elastic scale constraint mechanism is introduced. A calibration threshold is set based on the fluctuation range of historical water use data (such as the ±20% range of water use in the same period of the past three years). When the prediction deviation exceeds the threshold, the model output weight is automatically adjusted to ensure that the prediction results are consistent with real-time environmental changes and do not deviate from historical statistical laws, ultimately achieving accurate characterization and dynamic response to elastic water use patterns.

[0053] Finally, a time series mapping relationship is established between the overall profile and its sub-level profiles. Using timestamp alignment technology, detailed features of the sub-level profiles (such as irregular water usage peaks during a certain period) are embedded in the corresponding time nodes of the overall profile. Dynamic refresh of the profile is achieved through a sliding window algorithm (e.g., daily updates of the previous seven days' data). For example, if a region experiences a surge in water usage due to elastic structures for three consecutive days, the overall profile will automatically adjust its baseline for that period based on forecasted rising temperatures, triggering an increase in the weight of the elastic features in the sub-level profiles.

[0054] Through the technical path of cross-analysis of spatiotemporal dimensions, extraction of three types of structural features, two-layer portrait modeling and dynamic association of time series, abstract water use data is transformed into a behavioral model with physical significance, realizing a regular-irregular-elastic hierarchical analysis of water use behavior, achieving the technical effect of improving the accuracy of water use portraits and supporting differentiated resource scheduling strategies.

[0055] Furthermore, step A200 in the method provided in the embodiment of the present application includes:

[0056] A210: Dynamically partition the water use area according to the resource request condition to determine the water use partition.

[0057] A220: Reconstruct the fog computing topology according to the water usage partition and determine the reconstructed fog nodes.

[0058] In the embodiment of the present application, the reconstructed fog node refers to a node formed after adjusting and reconstructing the fog computing topology of the cloud based on the result of dynamic partitioning of the water use area (determining the water use partition).

[0059] Specifically, first, water use areas are dynamically partitioned based on resource request conditions. The system collects real-time resource request data from water use areas, such as water demand characteristics at different time periods (e.g., a certain time span at night) and for different functional areas (commercial areas, residential areas, factory areas, mixed areas), such as peak flow, duration, and spatial distribution. Using GIS spatial analysis algorithms, the water use area is divided into several water use zones with similar demand patterns. The specific process is as follows:

[0060] First, spatiotemporal water usage data for each water-using area is collected, including water flow, timestamps, and geographic coordinates at each point. This data is preprocessed to remove outliers and redundant information, forming a structured dataset. Subsequently, temporal features (such as time period and cycle) and spatial features (such as latitude and longitude, and regional functional attributes) are extracted to construct a multidimensional feature matrix. Spatial clustering algorithms (such as DBSCAN density clustering) are used to group water-using points. Water-using areas are then divided into clusters based on a set spatial distance threshold (e.g., 500 meters) and temporal pattern similarity (e.g., >80% overlap between peak water use periods).

[0061] On this basis, using the spatial overlay analysis function of GIS, the clustering results were overlaid with regional land use data (such as the distribution of commercial land, residential land, and industrial land). Each cluster was assigned clear functional attributes, forming water use zones such as central business districts, residential areas, and industrial parks. For example, due to the high concentration of water-using activities such as office and restaurant use during the daytime on weekdays, the commercial district's clusters exhibited a mean daytime water flow rate greater than 20 m³ / h and a concentrated spatial distribution. Residential areas, on the other hand, exhibited a peak water use rate between 7:00 PM and 10:00 PM in the evening, with a flow fluctuation coefficient less than 15%.

[0062] Finally, the rationality of the zoning is verified through GIS spatiotemporal analysis tools (such as time series animation and thermal distribution evolution) to ensure that the water use patterns of each zone are consistent with actual needs.

[0063] Secondly, the fog computing topology is reconstructed based on the water use partitioning results. The fog computing topology is based on a cloud-based distributed architecture, and each water use partition corresponds to one or more reconstructed fog nodes. The system dynamically adjusts the node's computing power resource configuration based on the complexity of the partition's resource requirements (such as the computational workload and real-time requirements of the water use scheduling strategy): partitions with high demand and complex structures (such as commercial areas) are allocated more computing nodes or higher-performance resources, while partitions with low demand and simple patterns (such as residential areas at night) optimize node configuration to save resources. For example, the storage and computing power of the nodes are redistributed through a load balancing algorithm so that the processing pressure of each reconstructed fog node matches the partition requirements, forming a dynamic mapping relationship between partitions and nodes. The specific process is as follows:

[0064] During the load balancing process for reconstructing fog nodes, the algorithm first quantifies the resource demand weights of each water-using zone by monitoring water data flow and the computational complexity of the scheduling strategy in real time. For example, a commercial zone with a high water-intensiveness is assigned a weight of 0.8, while a residential zone is assigned a weight of 0.3. Subsequently, a dynamic load balancing algorithm is employed to allocate resources to each reconstructed fog node that match the zone's demand based on the fog node's current load, including CPU utilization, memory usage, and task queue length. For example, upon detecting a surge in water scheduling requests for a central business district, the algorithm automatically increases the computing resource share of the fog node corresponding to that zone from 30% to 50%. Simultaneously, 20% of idle resources are dynamically migrated from nodes in low-loaded zones (such as residential zones at night) to supplement the allocated resources. By establishing a dynamic mapping model between zone demand weights and node resource availability, the algorithm continuously iteratively optimizes task allocation between nodes, ensuring a dynamic balance between the processing pressure of each reconstructed fog node and the zone's demand, avoiding resource overload or idleness. Ultimately, a partition-node elastic resource allocation mechanism that adapts to fluctuating water demand is established, improving the overall scheduling efficiency and stability of the cloud-based fog computing topology.

[0065] Through the technical path of demand-driven dynamic partitioning, topology reconstruction and elastic resource configuration, a precise match between fog computing resources and water demand is achieved, achieving the effect of improving resource utilization efficiency and supporting real-time refined scheduling.

[0066] Furthermore, step A200 in the method provided in the embodiment of the present application includes:

[0067] A230: The resource field includes three spatial dimensions, a time dimension, and an entropy dimension, wherein the entropy dimension includes structural entropy and resource entropy.

[0068] A240: Dynamically isolate the resource field according to the water use zoning to determine the isolated resource field.

[0069] A250: Constrain the isolated resource farm based on the elastic scale to determine the requested resource farm.

[0070] A260: Establish an association between the reconstruction fog node and the requested resource field, and determine the resource scenario.

[0071] In this embodiment, the entropy dimension is one of the dimensions of the resource field, which includes structural entropy and resource entropy. A greater structural entropy indicates a more complex resource scheduling execution and setup. Greater resource fluctuations within a partition and a more complex water usage architecture correspond to greater resource entropy.

[0072] Specifically, first, a multidimensional resource field is constructed, encompassing three dimensions: spatial, temporal, and entropy. The spatial dimension corresponds to the geographic coordinates or grid partitions of the water use area, such as three-dimensional spatial units divided by the X, Y, and Z axes. The temporal dimension encompasses time series at all scales, from seconds to monthly / seasonal periods. The entropy dimension quantifies system complexity through structural entropy and resource entropy. Structural entropy reflects the execution complexity of resource scheduling strategies, such as the connectivity complexity of the pipe network topology; larger values ​​indicate more complex scheduling logic. Resource entropy characterizes the degree of resource fluctuation and the complexity of the water use architecture within a partition. For example, when the daily fluctuation coefficient of water consumption exceeds 20%, the resource entropy value increases. For example, in an industrial park, the structural entropy value reaches 0.8 (range 0-1) due to the interlaced production lines, while the resource entropy value of a residential area is only 0.3 due to the stable water use patterns.

[0073] Secondly, dynamic resource isolation is implemented based on water use zoning. Based on the dynamic zoning results, such as commercial, industrial, residential, and mixed areas, IoT devices like smart valves and flow meters are used to divide each zone's water resources into independent, isolated resource fields to prevent cross-regional interference. For example, during peak water use periods, the isolated resource fields in commercial areas can be physically separated from those in industrial areas to ensure that emergency water needs in commercial areas are met first.

[0074] Then, elastic scaling constraints are introduced to optimize the isolated resource field. Based on sub-order features in the dynamic water use profile, such as the spatiotemporal tensor threshold corresponding to the elastic structure, the elastic scaling flexibly adjusts the boundaries and capacity of the isolated resource field. For example, when the summer temperature exceeds 35°C, based on the correlation model in the elastic structure profile that water consumption increases by 1.5% for every 1°C increase in temperature, the upper limit of the isolated resource field in the residential area is increased by 10%. Simultaneously, real-time pipeline flow is monitored using pressure sensors to ensure that it does not exceed the elastic scaling threshold, such as 120% of the historical maximum flow, thus forming a requested resource field.

[0075] Finally, a dynamic association is established between the reconstructed fog nodes and the requested resource fields. Each node in the fog computing topology corresponds to the requested resource field of a specific partition. Edge computing matches resource demands within the field in real time, such as matching node computing power with the complexity of the partition's water scheduling. For example, due to the high structural entropy of commercial areas, dual nodes are assigned to parallelize scheduling tasks, while residential areas can meet demand with a single node. This ultimately creates a three-in-one resource scenario: partition, resource field, and fog node, enabling precise mapping of water demand.

[0076] Through the technical chain of multi-dimensional resource field construction, dynamic isolation, elastic constraints and node association, static resource management is upgraded to a dynamic adaptive mode, achieving the effect of improving resource allocation accuracy and enhancing system robustness in complex scenarios.

[0077] Furthermore, step A300 in the method provided in the embodiment of the present application includes:

[0078] A310: Based on the dynamic water usage profile, sample-driven supervised training is performed under resource scenario switching to build the custom scheduler.

[0079] A320: The custom scheduler is split into partition scheduling and intra-area autonomous scheduling, and a logically associated upper scheduler and autonomous scheduler are determined.

[0080] A330: Deploy the upper scheduler and the autonomous scheduler in the cloud, and establish an association between the autonomous scheduler and the fog computing topology.

[0081] In this embodiment, the upper-level scheduler is a split from a custom scheduler built based on dynamic water usage profiling. It is responsible for executing resource negotiations between water zones based on resource scenarios and determining the partition resource pools. This logically associated upper-level scheduling component is deployed in the cloud. The autonomous scheduler is a lower-level scheduling component logically associated with the upper-level scheduler after the custom scheduler is split. Based on the partition resource pools and reconstructed fog nodes, it executes refined intra-zone water usage negotiations to determine water usage strategies. It also establishes an association with the fog computing topology to achieve autonomous scheduling within the zone.

[0082] Specifically, first, when building a custom scheduler based on the dynamic water use profile, the spatiotemporal feature data is first extracted from the dynamic water use profile, including the regular structure periodic water use template reflected by N event classes determined by periodic clustering, irregular structure abnormal event characteristics (such as the spatiotemporal trajectory of pipe network leakage), and the elastic structure based on the spatiotemporal tensor environmental correlation model (such as the correlation coefficient between temperature and water consumption), forming a training sample set containing time (such as time period, cycle), space (such as regional grid coordinates), and entropy dimensions (structural entropy, resource entropy).

[0083] Then, through sample-driven supervised training, the gradient boosting tree learning algorithm is used to train the samples, enabling the scheduling model to learn the optimal scheduling strategy for different resource scenarios. Specifically, the samples are fed into the gradient boosting tree algorithm for supervised training. Multiple decision trees are iteratively constructed, with each tree learning the residuals of the previous model, gradually optimizing the scheduling strategy predictions for different resource scenarios (peak, flat, and off-peak). For example, for the weekday morning rush hour scenario, the model takes the spatiotemporal distribution of residential water use (e.g., a mean flow rate of 5 m³ / h between 7:00 and 9:00 AM in residential areas) and industrial water use characteristics (e.g., a flow fluctuation coefficient greater than 20% in factory areas during the same period) as inputs, and outputs policy rules that prioritize residential water use and stagger industrial water use to the nighttime. By adjusting hyperparameters such as tree depth and learning rate through cross-validation, the model achieves over 90% accuracy in predicting scheduling strategies for various scenarios on the test set, ultimately building a custom scheduler that dynamically responds to water use patterns.

[0084] Next, the custom scheduler is split into a higher-level scheduler and an autonomous scheduler. The higher-level scheduler is responsible for global resource coordination across partitions and performs inter-partition scheduling based on resource scenarios, such as water allocation between commercial and residential areas. The autonomous scheduler performs refined scheduling within a single partition, combining real-time data from the fog computing topology (such as pipe network pressure and equipment status). By utilizing a hierarchical control architecture and decoupling global and local scheduling logic, the system's response speed is improved. For example, when a sudden surge in water consumption is detected in an industrial area, the autonomous scheduler can trigger a local emergency scheduling strategy within 50ms and synchronize information with the higher-level scheduler to adjust the global resource pool.

[0085] Finally, both types of schedulers are deployed in the cloud, and the autonomous scheduler is associated with the fog computing topology. Cloud-based containerized deployment technologies (such as Kubernetes) enable elastic scalability of the scheduler. Edge computing interfaces are used to connect the autonomous scheduler to fog nodes (such as edge servers deployed in industrial parks) in real time, forming a collaborative cloud-based decision-making and edge-based execution mechanism. For example, the upper-level scheduler issues zone resource pool quotas via a cloud-based API. Upon receiving these instructions, the autonomous scheduler, combined with real-time water usage data collected by fog nodes, such as minute-by-minute flow sensor data, dynamically adjusts valve openings and equipment startups and shutdowns within the zone, achieving precise water resource allocation.

[0086] Through the technical paths of dynamic portrait training, scheduler hierarchical splitting and cloud-edge collaborative deployment, the scheduling strategy is deeply bound to real-time water use behavior. By utilizing data-driven intelligent scheduling models and distributed computing architecture, the real-time performance of water resource scheduling is improved and the efficiency of resource allocation is optimized.

[0087] Furthermore, step A300 in the method provided in the embodiment of the present application includes:

[0088] A340: Determine a resource pool, wherein the resource pool is the total amount of water resources based on a time slice.

[0089] A350: Based on the resource pool, trigger the upper scheduler to execute resource game between water-using partitions based on the resource scenario, and determine the partition resource pool.

[0090] A360: Using the partition resource pool and the reconstructed fog node, trigger the autonomous scheduler to execute the refined water use game within the area and determine the water use strategy.

[0091] In one embodiment, a time-slice-based resource pool is first determined. Water resources are divided into fixed-length time slices (e.g., 1 hour per slice) based on the time dimension. Based on historical water usage statistics and real-time monitoring, the total amount of water resources within each time slice is calculated as the global resource pool. For example, a city's daily water supply is 100,000 tons. After being divided into 24 time slices, the initial resource pool value for each time slice is approximately 4,167 tons. This resource pool is dynamically adjusted based on real-time rainfall, pipe network pressure, and other data. For example, during heavy rain, the resource pool capacity is temporarily reduced by 20% during a certain period.

[0092] Secondly, when executing a first-level zone-based game, the upper-level dispatcher first triggers a resource game between water zones based on resource scenarios (such as weekday morning peak hours and weekend flat periods). Each water zone (e.g., commercial, industrial, and residential) acts as the game agent and submits a resource allocation request to the system based on its own water demand (e.g., a commercial zone requesting 30% of the resource pool between 9:00 AM and 11:00 AM) and global constraints (e.g., the upper limit of the total resource pool). The system performs a global optimization using a game algorithm (e.g., Nash equilibrium). This algorithm aims to maximize overall resource utilization efficiency and incorporates historical water efficiency data (e.g., industrial water consumption per unit of output value and residential water consumption peak patterns) as weighting parameters to calculate the optimal allocation for each zone. For example, if both a commercial zone and an industrial zone request resources during peak hours, the upper-level dispatcher sets the zone resource pool ratio to 40% for the commercial zone and 50% for the industrial zone based on historical data showing that industrial water efficiency is higher, e.g., water consumption per unit of output value is 30% lower than that of the commercial zone. The remaining 10% is reserved as an emergency reserve to ensure the ability to adjust to unexpected water use events. This process achieves a reasonable allocation of global resources through dynamic game theory, balancing the water demand of different partitions with the overall stability of the system.

[0093] Finally, a second-level refined game is implemented. The autonomous scheduler combines the zone resource pool quota with real-time data from reconstructed fog nodes (such as flow and pressure sensor data from each pipe network node within the zone) to implement refined water allocation within the zone. For example, based on user profiles, if high-priority users account for 15%, the autonomous scheduler in a residential area will allocate 60% of the zone resource pool to high-priority users, 30% to regular users, and 10% as a dynamic adjustment. Fuzzy control algorithms are used to adjust valve openings in real time to ensure stable water pressure at each user end within a ±5% error range while preventing pipe network overload.

[0094] Through the steps of time-slice resource pool modeling, inter-partition game optimization, and real-time refined control within the zone, global resource balance is combined with local dynamic response. Finally, through the two-layer game strategy and fog computing real-time data drive, the effect of improving the fairness of water resource allocation, reducing system energy consumption, and enhancing emergency response capabilities is achieved.

[0095] Furthermore, step A400 in the method provided in the embodiment of the present application includes:

[0096] A410: Perform aggregation and splicing based on the water use area on the water use strategy to determine the regional water use strategy.

[0097] A420: Convert the regional water use strategy according to the standardized dimensions of the water resources management system to determine the standard water use strategy.

[0098] A430: The water resource management system recognizes and responds to the standard water use strategy.

[0099] Optionally, first, perform an aggregation and splicing based on water use zones. Collect the independent water use strategies for each water use zone (e.g., commercial, residential, and industrial areas), extract key parameters such as water consumption, scheduling period, and priority, and use spatial data fusion techniques (e.g., vector overlay) to integrate the zone strategies into a regional overall strategy. For example, a strategy that prioritizes 200 m³ / h of water supply during peak hours in the commercial area and 150 m³ / h of water supply during off-peak hours in the residential area can be spliced ​​together in a time series to form a 24-hour continuous water supply plan for the region. Conflict detection algorithms (e.g., intersection analysis) can be used to eliminate conflicts between the zones' strategies and ensure the spatiotemporal continuity of the regional strategy.

[0100] Secondly, a standardized water use strategy is converted based on standardized dimensions. A unified dimension conversion model is established for heterogeneous dimensions, such as cubic meters per second and tons per hour, across different infrastructure (e.g., pipeline networks, reservoirs) and water use types (e.g., industrial water, domestic water). For example, the cooling flow rate of 10 tons per minute for industrial water equipment is converted to a standardized dimension of 600 cubic meters per hour. At the same time, strategy parameters (e.g., priority level) are encoded as system-recognizable numerical variables, such as setting high priority to 1 and medium priority to 2. Through standardization, a standard strategy file is generated that complies with the interface specifications of the water resources management system, such as the JSON format, to ensure data format consistency.

[0101] Finally, the water resources management system identifies and responds to the standard policy. The system reads the standard policy file through an API interface, parses the scheduling instructions contained therein, such as increasing the pressure of the commercial area pipeline network to 0.4 MPa from 8:00 to 10:00, and converts them into control signals for the underlying equipment, such as starting the booster pump and adjusting the valve opening. At the same time, integrated real-time monitoring modules (such as pressure sensors and flow meters) provide feedback on the execution status, forming a policy formulation-execution-feedback closed loop. For example, when the system recognizes the nighttime pressure reduction water supply instruction in the standard policy, it automatically adjusts the speed of the variable frequency pump to reduce the pipeline pressure from 0.35 MPa to 0.25 MPa, and transmits pressure data in real time through the IoT terminal to ensure that the policy execution accuracy error is less than 2%.

[0102] Through the technical paths of regional strategy aggregation, dimensional standardization conversion and seamless system integration, the policy processing efficiency is improved and the execution error rate is reduced. Ultimately, through the unified dimensional system and data format standardization technology, the effect of enhancing system compatibility and improving global scheduling coordination is achieved.

[0103] Furthermore, step A500 in the method provided in the embodiment of the present application includes:

[0104] A510: Conduct water resource management monitoring simultaneously and determine management response data.

[0105] A520: Identify the management response data, locate the abnormal management data and perform tracing processing to determine the cause of the abnormality.

[0106] A530: Conduct feedback adjustments to water resource management based on the causes of the abnormality.

[0107] In one embodiment, water resource management and monitoring are first performed simultaneously. IoT sensor networks deployed in water-using areas, such as ultrasonic flow meters, pressure transmitters, and water quality monitors, collect real-time data on pipe network flow, water pressure, water quality parameters, and equipment status at a frequency of seconds or minutes, generating a multi-dimensional management response dataset. For example, pressure sensors deployed in a residential community pipe network upload pressure values ​​(in MPa) every 10 seconds. If pressure fluctuations exceed ±5% during peak water consumption periods (e.g., between 6:00 PM and 8:00 PM), the data automatically triggers an abnormality warning.

[0108] Secondly, the system identifies abnormal data and performs traceability processing. The system uses an isolation forest learning algorithm to compare real-time data with historical baseline values, identifying abnormal points that exceed preset thresholds (the algorithm process is the same as step A132). Through the data traceability engine, the abnormal data is traced back along the pipeline network topology to the devices (such as valves and pumps) and water use events (such as firefighting water and industrial water emergencies) associated with the abnormal data, locating the cause of the abnormality. For example, at 2 a.m., water consumption in an industrial zone suddenly reached twice the daily peak. By analyzing the equipment operation logs during this period, the system determined that a cooling water leak was caused by a fault in a production line.

[0109] Finally, feedback regulation is implemented. Based on the cause of the anomaly, the system automatically triggers an adjustment strategy. If it's a device failure, such as an abnormal valve opening, a command is sent via the cloud to the edge controller, remotely adjusting device parameters or activating backup equipment. If it's due to uneven resource allocation, the elastic resource pool (reserving 10%-15% of emergency water) is used for secondary scheduling, and the allocation of district resource pools is reallocated using an optimization algorithm. For example, if a fire drill causes a sudden drop in water pressure in a commercial area, the system temporarily allocates 5% of the water from the idle resource pool in a neighboring residential area, restoring normal water supply within 30 minutes.

[0110] Through the closed-loop mechanism of dynamic monitoring-intelligent tracing-elastic adjustment, refined and adaptive water resource management is achieved, effectively reducing the leakage rate and improving the system's anti-interference ability.

[0111] In summary, the water resource refined management method integrated with water use behavior identification provided by the embodiments of the present application has the following technical effects:

[0112] This application retrieves water use event records in water use areas, obtains dynamic water use portraits through spatiotemporal water use feature mining and behavior deconstruction, calculates resource scenarios and water use strategies, and makes adjustments based on dynamic isolation and elastic constraints of resource fields, zoning games, and refined game results, thereby achieving refined management of water resources. Resource scheduling and infrastructure control management in water use areas are more accurate and efficient, achieving the technical effect of using big data processing technology to accurately identify various water use behaviors, realize real-time dynamic scheduling of resources, efficiently integrate and analyze water use data in multiple regions, improve the level of refined management of water resources, and effectively respond to complex water use scenarios.

[0113] Example 2, as Figure 2 As shown, based on the same inventive concept as the aforementioned embodiment 1, the embodiment of the present application provides a refined water resource management system integrating water use behavior identification, the system comprising:

[0114] The water use portrait construction module 1 is used to retrieve water use event records in the water use area, mine spatiotemporal water use characteristics and perform behavioral deconstruction, and construct a dynamic water use portrait, wherein regularity, irregularity, and elastic scales are used as construction constraints.

[0115] The resource scenario determination module 2 is used to reconstruct the fog computing topology of the cloud according to the resource request conditions, establish a resource field based on the water use area, and perform dynamic resource isolation and elastic scaling constraints to determine the resource scenario.

[0116] The water use strategy determination module 3 is used to deploy a custom scheduler in the cloud according to the dynamic water use profile, perform a first-layer partitioning game and a second-layer refinement game based on the resource scenario, and determine the water use strategy.

[0117] The water use strategy reconstruction module 4 is used to standardize the reconstruction of the water use strategy and execute resource scheduling and infrastructure control management of the water use area according to the water resource management system.

[0118] Furthermore, the water usage profile building module 1 is used to perform the following steps:

[0119] Perform periodic clustering on the water use event records to determine N event classes, where N is the number of periodic cycles; traverse the N event classes, perform spatiotemporal water use feature mining under inter-class periodic mapping, and determine the water use feature structure, where the preset frequency is used as the mining constraint; and construct a dynamic water use profile based on the water use feature structure by performing behavioral deconstruction analysis.

[0120] Furthermore, the water usage profile building module 1 is used to perform the following steps:

[0121] The water use characteristic structure is deconstructed in three spatial and temporal dimensions to determine regular structure, irregular structure and elastic structure; an overall water use portrait is constructed based on the water use characteristic structure, and a sub-level water use portrait is constructed based on the regular structure, irregular structure and elastic structure, wherein the sub-level water use portrait includes three items, and the elastic structure is determined based on the spatiotemporal tensor of water use events; a time series mapping of the overall water use portrait and the sub-level water use portrait is established as the dynamic water use portrait.

[0122] Furthermore, the resource scenario determination module 2 is configured to perform the following steps:

[0123] According to the resource request condition, the water use area is dynamically partitioned to determine the water use partition; according to the water use partition, the fog computing topology is reconstructed to determine the reconstructed fog node.

[0124] Furthermore, the resource scenario determination module 2 is configured to perform the following steps:

[0125] The resource field includes three spatial dimensions, a temporal dimension, and an entropy dimension, wherein the entropy dimension includes structural entropy and resource entropy. According to the water use partition, the resource field is dynamically isolated to determine the isolated resource field. In combination with the elastic scale, the isolated resource field is constrained to determine the requested resource field. An association is established between the reconstructed fog node and the requested resource field to determine the resource scenario.

[0126] Furthermore, the water use strategy determination module 3 is configured to perform the following steps:

[0127] Based on the dynamic water usage profile, sample-driven supervised training is performed under resource scenario switching to construct the custom scheduler; the custom scheduler is split into partition scheduling and intra-area autonomous scheduling to determine the logically associated upper scheduler and autonomous scheduler; the upper scheduler and the autonomous scheduler are deployed in the cloud, and an association is established between the autonomous scheduler and the fog computing topology.

[0128] Furthermore, the water use strategy determination module 3 is configured to perform the following steps:

[0129] Determine a resource pool, wherein the resource pool is the total amount of water resources based on a time slice; based on the resource pool, trigger the upper scheduler to execute a resource game between water use partitions based on the resource scenario to determine the partition resource pool; use the partition resource pool and the reconstructed fog node to trigger the autonomous scheduler to execute a refined water use game within the area to determine the water use strategy.

[0130] Furthermore, the water use strategy reconstruction module 4 is used to perform the following steps:

[0131] The water use strategy is aggregated and spliced ​​based on the water use area to determine the regional water use strategy; the regional water use strategy is converted according to the standardized dimension of the water resources management system to determine the standard water use strategy; the water resources management system identifies and responds to the standard water use strategy.

[0132] Furthermore, the water use strategy reconstruction module 4 is used to perform the following steps:

[0133] Water resource management monitoring is carried out simultaneously to determine management response data; the management response data is identified, abnormal management data is located and traceability processing is performed to determine the cause of the abnormality; and feedback adjustment of water resource management is carried out based on the cause of the abnormality.

[0134] The water resource refined management system with integrated water use behavior identification provided in the embodiment of the present invention can execute the water resource refined management method with integrated water use behavior identification provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0135] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0136] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A refined water resource management method integrating water use behavior identification, characterized in that: The method comprises: Retrieve water use event records in water-using areas, explore spatiotemporal water use characteristics, deconstruct behavior, and construct a dynamic water use portrait, using regularity, irregularity, and elasticity as construction constraints; Based on resource request conditions, the cloud-based fog computing topology is reconstructed, a resource field based on water use areas is established, and dynamic resource isolation and elastic scaling constraints are implemented to determine resource scenarios. Deploy a custom scheduler in the cloud based on the dynamic water use profile, execute a first-layer partitioning game and a second-layer refinement game based on the resource scenario, and determine the water use strategy; The water use strategy is standardized and reconstructed, and resource scheduling and infrastructure control management of the water use area are executed according to the water resource management system.

2. The method for refined water resource management integrating water use behavior identification according to claim 1, characterized in that: Mining spatiotemporal water use characteristics and analyzing behaviors to build a dynamic water use profile, including: Performing periodic clustering on the water use event records to determine N event classes, where N is the number of periodic cycles; Traversing the N event classes, mining spatiotemporal water use characteristics under inter-class periodic mapping to determine the water use characteristic structure, wherein a preset frequency is used as a mining constraint; Based on the water use characteristic structure, a dynamic water use profile is constructed by performing behavioral deconstruction analysis.

3. The method for refined water resource management integrating water use behavior identification according to claim 2, characterized in that: By conducting behavioral deconstruction analysis, a dynamic water use profile is constructed, including: Deconstruct the water use characteristic structure in three dimensions of space and time to determine regular structure, irregular structure and elastic structure; An overall water use profile is constructed based on the water use characteristic structure, and a sub-level water use profile is constructed based on the regular structure, irregular structure, and elastic structure, wherein the sub-level water use profile includes three items, and the elastic structure is determined based on the spatiotemporal tensor of water use events; A time series mapping of the assembly water usage profile and the sub-level water usage profile is established as the dynamic water usage profile.

4. The method for refined water resource management integrating water use behavior identification according to claim 1, characterized in that: Reconstruct the fog computing topology in the cloud, including: Dynamically partitioning the water use area according to the resource request condition to determine the water use partition; The fog computing topology is reconstructed according to the water usage partitions, and a reconstructed fog node is determined.

5. The method for refined water resource management integrating water use behavior identification according to claim 4, characterized in that: The resource field includes three dimensions of space, time and entropy, wherein the entropy dimension includes structural entropy and resource entropy; Dynamically isolate the resource field according to the water use zoning to determine the isolated resource field; In combination with the elastic scale, constraining the isolated resource farm to determine the requested resource farm; An association is established between the reconstruction fog node and the requested resource field, and the resource scenario is determined.

6. The method for refined water resource management integrating water use behavior identification according to claim 4, characterized in that: Deploy a custom scheduler in the cloud based on the dynamic water usage profile, including: Based on the dynamic water usage profile, sample-driven supervised training is performed under resource scenario switching to build the custom scheduler; The custom scheduler is split according to partition scheduling and autonomous scheduling within the zone, and the upper scheduler and autonomous scheduler with logical association are determined; The upper scheduler and the autonomous scheduler are deployed in the cloud, and an association between the autonomous scheduler and the fog computing topology is established.

7. The method for refined water resource management integrating water use behavior identification according to claim 6, characterized in that: Based on the resource scenario, a first-layer partitioning game and a second-layer refinement game are executed to determine the water use strategy, including: Determine a resource pool, wherein the resource pool is the total amount of water resources based on time slices; Based on the resource pool, trigger the upper scheduler to perform resource game between water use partitions based on the resource scenario to determine the partition resource pool; The autonomous scheduler is triggered by the partition resource pool and the reconstructed fog node to execute a refined water use game within the area and determine the water use strategy.

8. The method for refined water resource management integrating water use behavior identification according to claim 1, characterized in that: The water use strategy is standardized and reconstructed, including: Performing aggregation and splicing based on the water use areas on the water use strategy to determine a regional water use strategy; According to the standardized dimensions of the water resources management system, the regional water use strategy is converted to determine the standard water use strategy; The water resource management system recognizes and responds to the standard water use policy.

9. The method for refined water resource management integrating water use behavior identification according to claim 1, characterized in that: After executing resource dispatch and infrastructure control management in water-using areas, including: Conduct water resource management monitoring simultaneously to determine management response data; Identify the management response data, locate the abnormal management data and perform source tracing to determine the cause of the abnormality; Feedback adjustment of water resource management is performed based on the abnormal causes.

10. A refined water resource management system that integrates water use behavior identification is characterized by: A method for fine-grained water resource management with integrated water use behavior identification according to any one of claims 1 to 9, the system comprising: The water use profile construction module is used to retrieve water use event records in water use areas, mine spatiotemporal water use characteristics, deconstruct behavior, and construct a dynamic water use profile, using regularity, irregularity, and elasticity as construction constraints. The resource scenario determination module is used to reconstruct the fog computing topology in the cloud based on resource request conditions, establish resource fields based on water use areas, and perform dynamic resource isolation and elastic scaling constraints to determine resource scenarios. A water use strategy determination module is used to deploy a custom scheduler in the cloud based on the dynamic water use profile, perform a first-layer partitioning game and a second-layer refinement game based on the resource scenario, and determine the water use strategy; The water use strategy reconstruction module is used to standardize the water use strategy and execute resource scheduling and infrastructure control management of the water use area according to the water resource management system.

Images