Space-air-ground-water coordinated hydrological measurement and flow mode intelligent scheduling system and method

Abstract

The application discloses a space-air-ground-water coordinated hydrological measurement flow mode intelligent scheduling system and method, relates to the related technical field of hydrological monitoring, and comprises: a water area state space deployment module used for deploying a water area state space of a target water area; a state transition graph measurement module used for developing a scheduling logic device and measuring a state transition graph through a data interface; a mode scheduling strategy determination module used for dividing the water area state into a normal state, a degraded state and a safe state, triggering the scheduling logic device to derive scheduling decision, and determining a mode scheduling strategy; and a scheduling driving management module used for being downwardly distributed to a shore-based equipment group of the target water area and performing scheduling driving management based on an information exchange protocol. The technical problems of poor collaboration of multi-source heterogeneous monitoring equipment, insufficient space-time consistency of hydrological data and low monitoring task scheduling efficiency in the prior art are solved, and the technical effects of improving space-time coverage of hydrological monitoring, collaboration of monitoring equipment and optimizing resource allocation efficiency are achieved.

Description

Technical Field

[0001] This application relates to the field of hydrological monitoring technology, specifically to an intelligent scheduling system and method for hydrological flow measurement modes that integrates air, space, and water. Background Technology

[0002] Hydrological monitoring plays a crucial role in water resource management, flood control and disaster reduction, and ecological environmental protection. Accurate and real-time hydrological data helps to achieve rational allocation of water resources and improve the ability to warn and respond to disasters such as floods. However, the hydrological environment exhibits significant dynamic complexity. The distribution of traditional hydrological monitoring points is difficult to achieve comprehensive coverage, especially in mountainous areas and remote river channels, where there are many spatial coverage blind spots. This makes it difficult to capture hydrological changes at the watershed scale, resulting in missing key data. It is also difficult to integrate data from different data sources such as satellites, drones, and ground equipment, forming a "data silo" phenomenon. At the same time, it is difficult to accurately collect data such as rainfall, water level, and soil moisture, which cannot meet the real-time monitoring needs in scenarios such as extreme weather and sudden water pollution events. Furthermore, the coordinated scheduling of different monitoring modalities in the spatiotemporal dimensions has not yet formed a standardized system, resulting in both redundancy and missing monitoring data, and unreasonable allocation of equipment resources, which affects the timeliness, accuracy, and reliability of hydrological monitoring.

[0003] Therefore, current technologies suffer from technical problems such as poor coordination among multi-source heterogeneous monitoring devices, insufficient spatiotemporal consistency of hydrological data, and low efficiency in monitoring task scheduling. Summary of the Invention

[0004] This application provides an intelligent scheduling system and method for hydrological flow measurement modes that integrates air, space, and water, solving the technical problems of poor coordination among multi-source heterogeneous monitoring equipment, insufficient spatiotemporal consistency of hydrological data, and low scheduling efficiency of monitoring tasks in the prior art. It achieves the technical effects of improving the spatiotemporal coverage of hydrological monitoring, enhancing the coordination of monitoring equipment, and optimizing resource allocation efficiency.

[0005] This application provides an intelligent scheduling system for hydrological flow measurement modalities that integrates air, space, and water. The system includes: a water state space deployment module for deploying the water state space of a target water area, wherein the water state space is updated in real time; a state transition diagram calculation module for developing a scheduling logic unit within the intelligent scheduling system and calculating a state transition diagram based on the water state space through a data interface; a modal scheduling strategy determination module for classifying the water state of the target water area into normal, degraded, and safe states, marking the state transition diagram and generating temporary agreements, triggering the scheduling logic unit to perform scheduling decision derivation, and determining the modal scheduling strategy, wherein the logic is based on state excitation state-local interaction rules and device behavior-device master-slave formation, and the formation methods include relay formation and master-slave formation; and a scheduling drive management module for decoupling and spatiotemporally aligning the modal scheduling strategy with the formation devices, delegating communication to the shore-based equipment group of the target water area, and coordinating scheduling drive management based on an information exchange protocol.

[0006] In a possible implementation, the air-space-ground-water integrated hydrological flow measurement mode intelligent scheduling system also performs the following processing: the elements of the water area state space include at least water level, meteorology, water surface environment, equipment status, and task queue, wherein the task queue is a real-time running queue, and the equipment status includes at least equipment power and location code; for each element, an element coding mode is set, wherein each element corresponds to an element coding mode; the water area state space is deployed based on the element coding mode.

[0007] In a possible implementation, the air-space-ground-water integrated hydrological flow measurement modal intelligent scheduling system further performs the following processing: retrieving hydrological record data of the target water area, performing a first clustering based on hydrological status to determine a first cluster; performing a second clustering based on the hydrological record data using a scheduling combination method to determine a second cluster; integrating the first cluster and the second cluster to determine the clustering result; and using the clustering result, classifying the target water area into a normal state, a degraded state, and a safe state.

[0008] In a possible implementation, the air-space-ground-water integrated hydrological flow measurement modal intelligent scheduling system further performs the following processing: setting state thresholds based on hydrological conditions, wherein the state thresholds include upper and lower bounds for normal state, degraded state, and safe state; mining hydrological-scheduling sequences based on the clustering results, wherein the clustering results correspond one-to-one with the hydrological-scheduling sequences; and assigning states to the hydrological-scheduling sequences according to the state thresholds, as the divided normal state, degraded state, and safe state.

[0009] In a possible implementation, the air-space-ground-water collaborative hydrological flow measurement modal intelligent scheduling system further performs the following processing: deploying a first node based on the task excitation direction of hydrological state transition, wherein the first node performs state excitation state analysis; deploying a second node based on the behavioral interaction between scheduling devices and the response of the information exchange protocol; deploying a third node with the shore-based equipment group as the target, with equipment status and task queues as constraints, and with formation methods and formation rules as the basis; cascading the first node, the second node, and the third node, and determining the scheduling logic unit through supervised learning until convergence.

[0010] In a possible implementation, the air-space-ground-water integrated hydrological flow measurement mode intelligent scheduling system also performs the following processing: setting information exchange elements, wherein the information exchange elements include at least device ID, data vector, and intent weight, wherein the intent weight is the task weight of the subject transferring from the exchanging device to the exchanged device; generating an information exchange protocol based on the information exchange elements and data modes; and performing scheduling interaction management of the shore-based equipment group based on the information exchange protocol.

[0011] In a possible implementation, the air-space-ground-water integrated hydrological flow measurement mode intelligent scheduling system also performs the following processing: the shore-based equipment group includes fixed equipment and mobile equipment, and the mobile equipment includes active mobile equipment and mounted equipment.

[0012] In a possible implementation, the air-space-ground-water collaborative hydrological flow measurement mode intelligent scheduling system also performs the following processing: the active mobile device includes a drone and an unmanned vessel, wherein the unmanned vessel uses the cross-sectional reference coordinate system as the data mode, and the drone uses the local water area projection as the data mode; the mutual conversion between the cross-sectional reference coordinate system and the local water area projection is used as the data interaction condition for the relay scheduling of drones and unmanned vessels, and is added to the information exchange protocol.

[0013] In a possible implementation, the air-space-ground-water integrated hydrological flow measurement modal intelligent scheduling system also performs the following processing: each device in the shore-based equipment group has a unique identifier; the identifier corresponding to the equipment in the formation is located, the modal scheduling strategy is decoupled, and a sub-scheduling strategy is determined, wherein the sub-scheduling strategy corresponds one-to-one with the equipment in the formation; timestamp constraints and position code constraints are introduced to collaboratively identify the sub-scheduling strategy, and strategy communication is delegated and scheduling management is performed.

[0014] This application also provides an intelligent scheduling method for hydrological flow measurement modes that integrates air, space, and water, including: deploying a water state space for a target water area, wherein the water state space is updated in real time; developing a scheduling logic unit within an intelligent scheduling system to calculate a state transition diagram based on the water state space through a data interface; dividing the water state of the target water area into normal, degraded, and safe states, marking the state transition diagram and generating a temporary agreement, triggering the scheduling logic unit to perform scheduling decision derivation, and determining a mode scheduling strategy, wherein the state excitation state-local interaction rules and equipment behavior-equipment master-slave formation are used as the baseline logic, and the formation methods include relay formation and master-slave formation; decoupling and spatiotemporally aligning the mode scheduling strategy with the formation equipment, and delegating communication to the shore-based equipment group in the target water area and coordinating scheduling-driven management based on an information exchange protocol.

[0015] This application proposes a space-air-ground-water integrated intelligent scheduling system and method for hydrological flow measurement modalities. The system comprises: a water area state space deployment module for deploying the water area state space of the target water area; a state transition diagram calculation module for developing a scheduling logic unit and calculating the state transition diagram via a data interface; a modal scheduling strategy determination module for classifying the water area state into normal, degraded, and safe states, triggering the scheduling logic unit to deduce scheduling decisions, and determining the modal scheduling strategy; and a scheduling drive management module for delegating communication to shore-based equipment groups in the target water area and coordinating scheduling drive management based on an information exchange protocol. This system addresses the technical problems of poor coordination among multi-source heterogeneous monitoring equipment, insufficient spatiotemporal consistency of hydrological data, and low efficiency in monitoring task scheduling in existing technologies. It achieves the technical effects of improving the spatiotemporal coverage of hydrological monitoring, enhancing the coordination of monitoring equipment, and optimizing resource allocation efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 A schematic diagram of the structure of the intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water, provided in the embodiments of this application.

[0018] Figure 2 A schematic diagram of the intelligent scheduling method for hydrological flow measurement modes in a space-air-ground-water collaborative manner provided in the embodiments of this application.

[0019] Figure labeling: Water area state space deployment module 10, state transition diagram calculation module 20, modal scheduling strategy determination module 30, scheduling drive management module 40. Detailed Implementation

[0020] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0023] This application provides an intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water resources. Figure 1 As shown, the system includes:

[0024] The water state space deployment module 10 is used to deploy the water state space of the target water area, wherein the water state space is updated in real time.

[0025] Preferably, a digital model is created for the physical characteristics, environmental parameters, equipment resources, and digital processes of the target water area, and a water state space is deployed for the target water area. This is a multi-dimensional dynamic database that integrates heterogeneous data from multiple sources. The core elements of the water state space include hydrological information (water level, meteorology, water surface environment), equipment status, and task queues. Specifically, water level parameters include real-time water level elevation, flow velocity profile (vertical / planar distribution), and flow angle; meteorological environmental parameters include rainfall, wind speed / direction, temperature, air pressure, solar radiation, and extreme weather warning data (such as typhoon paths and heavy precipitation forecasts); water surface environment parameters include the distribution of floating debris (type / density), algae coverage, and navigation conditions (ship position / speed); and equipment status includes air, land, and water equipment. The system includes cluster, equipment power levels, and equipment spatial coordinates. The air-ground-space-ground equipment cluster includes satellite remote sensing payloads (imaging mode / resolution), UAV endurance status, unmanned surface vessel power system parameters, underwater robot sensor calibration status, ground station instrument calibration cycle, and communication module signal strength. The equipment spatial coordinates include real-time GPS / BeiDou positioning data, motion trajectory prediction, and relative equipment positional relationships (formation parameters). The task queue includes task attribute parameters and task execution status. The task attribute parameters include task priority (emergency monitoring / routine inspection), time window constraints, and data accuracy requirements. The task execution status includes the pool of tasks to be assigned, the progress of tasks in progress, archived completed tasks, and task conflict detection (equipment resource contention conflicts, spatiotemporal coverage overlap).

[0026] Preferably, the spatial status of the water area is updated in real time. Specifically, a three-dimensional network of air, land, sea, and air is used for collaborative data collection. Satellite remote sensing acquires the status of the water surface over a wide area, drones equipped with sensors capture local details, unmanned vessels / robots perform in-situ underwater measurements, and ground stations provide reference data. Time stamp calibration and clock synchronization protocols ensure the spatiotemporal consistency of multi-source data. A hybrid communication link is constructed, such as using 5G, satellite communication, and self-organizing network wireless transmission for multi-channel redundant transmission. When the monitoring data changes exceed the threshold (e.g., water level rise ≥ 0.5m) or the equipment status is abnormal, the data is refreshed in real time to accurately capture transient processes such as flood evolution and tidal changes. This ensures that the virtual space always maintains a dynamic mapping with the physical water area, guaranteeing the timeliness of the modal scheduling strategy.

[0027] Furthermore, the specific configuration of the water area state space deployment module 10 also includes that the elements of the water area state space include at least water level, weather, water surface environment, equipment status, and task queue, wherein the task queue is a real-time running queue, and the equipment status includes at least equipment power and location code; for each element, an element coding mode is set, wherein each element corresponds to an element coding mode; and the water area state space is deployed based on the element coding mode.

[0028] Preferably, the elements of the water state space include at least water level, weather, water surface environment, equipment status, and task queue. The task queue is a real-time running queue, and the equipment status includes at least equipment battery level and location code. An element coding mode is set for each element, meaning a unique structured coding rule is designed for each element to ensure that the data is parsable, indexable, and aggregateable, and that each element's code uniquely corresponds to its physical / logical entity, with the code including classification identifiers and attribute subdivisions. Finally, the water state space is deployed based on the element coding mode. Specifically, raw data collected by air, space, and water equipment (such as UAV water level images and buoy sensor data) is converted into a unified format according to the coding rules and stored in a real-time database. The data is stored using a three-dimensional index structure of time-space-element type. High-frequency data (such as water level changes per second) is preprocessed locally through edge computing nodes and then synchronized to the cloud state space via 5G / satellite communication. When an element exceeds a threshold, a high-priority state update is immediately triggered. Example data of water state space elements is shown in Table 1.

[0029] Table 1. Spatial Data Table of Water Area Status Elements

[0030] ;

[0031] The state transition diagram calculation module 20 is used to develop a scheduling logic device within the intelligent scheduling system and calculate the state transition diagram based on the state space of the water area through a data interface.

[0032] Preferably, a scheduling logic unit is developed within the intelligent scheduling system. Utilizing real-time updated water state data, it dynamically analyzes the changing trends of the water state through data interface calculations (data differential calculation), and constructs a logical model (i.e., a state transition diagram) reflecting the transition relationships between states. The scheduling logic unit is responsible for deriving equipment scheduling strategies based on real-time data. Its core function is to analyze changes in the water state and generate corresponding control commands (such as switching equipment formation modes or adjusting task priorities). Data differential calculation identifies key changes (such as a sudden rise in water level or a sudden drop in equipment power) by comparing the current state with the state at the previous moment (or historical baseline), thereby capturing dynamic events requiring system response. The state transition diagram is a directed graph model that describes the transition conditions and rules between water states (such as normal state, degraded state, and safe state). For example, the transition condition from normal state to degraded state might be that the water level exceeds the warning line and rainfall continues to increase.

[0033] Preferably, the scheduling logic unit obtains real-time data on various elements of the water state space (water level, weather, equipment status, etc.) through standardized data interfaces (such as REST API or message queues) and performs differential calculations. This involves comparing data within a continuous time window, calculating changes (such as the difference between the current water level and the water level 10 minutes ago), identifying significant differences (such as a water level difference exceeding a threshold of ±5cm, or an abnormal rate of equipment power decline), and marking these as state transition trigger events. State transition rules are then predefined. For example, if the water level difference is >10cm and rainfall is >20mm / h, a transition from normal state to degraded state is triggered; if the equipment power is <20% and there is no backup equipment, a transition from degraded state to safe state is triggered. The differential calculation results are matched with the rule base to determine the current possible state transition path. Finally, the matched transition rules are instantiated as edges in a state transition graph, with nodes representing the current and potential water state (such as normal state and degraded state). Different weights are assigned to the transition edges based on the urgency of the differential calculation (such as the rate of water level rise), prioritizing high-risk transitions (such as edges with high weights requiring immediate response).

[0034] The modal scheduling strategy determination module 30 is used to divide the water state of the target water area into normal state, degraded state and safe state, mark the state transition diagram and generate temporary agreements, trigger the scheduling logic to perform scheduling decision deduction, and determine the modal scheduling strategy. The modal scheduling strategy is based on the state excitation state-local interaction rules and device behavior-device master-slave formation, and the formation mode includes relay formation and master-slave formation.

[0035] Preferably, the water state of the target water area is divided into normal, degraded, and safe states through dynamic state classification. At the same time, a rule-based response mechanism is used to achieve adaptive optimization of multi-device collaborative scheduling. Specifically, the water state is divided into three categories based on real-time monitoring data, each corresponding to different risk levels and response strategies. In the normal state, all hydrological parameters (water level, water quality, etc.) are within safe thresholds, the equipment operates stably, and performs tasks such as inspection and sampling according to the regular plan. The equipment formation operates in a low-power mode, such as drones patrolling along fixed routes. In the degraded state, some parameters exceed the threshold (such as a sudden rise in water level or water pollution), but have not yet reached an emergency danger level, triggering local enhanced monitoring. The equipment formation switches to a main and auxiliary formation, such as unmanned surface vessels taking the lead and underwater robots assisting in sampling key areas. In the safe state, extreme events occur (such as floods or equipment failures), requiring emergency intervention. A full-resource emergency mode is activated, and the equipment formation adopts a relay formation, such as multiple drones patrolling the dam breach point in segments and relaying data.

[0036] Preferably, the system then marks the state transition diagram and generates a temporary agreement. Specifically, based on differential calculations (such as the rate of water level change and the rate of decrease in equipment power), the system marks the current state transition path (e.g., "normal state → degraded state") in the state transition diagram and binds a preset local interaction rule to the path. For example, if "water level difference > 10cm and rainfall continues", it is marked as a degraded state and associated with the primary and secondary formation strategy. After the state transition is triggered, the system automatically generates a temporary agreement, which clarifies the task objectives, such as prioritizing the monitoring of the area with a surge in water level on the north side; equipment formation requirements, such as 1 unmanned vessel (primary) + 2 underwater robots (secondary); and timeliness, with the agreement valid until the water level returns to normal or is manually terminated. The system is based on the logic of state excitation, local interaction rules, device behavior, and device master-slave formation. Specifically, the state excitation refers to the sub-area or device that needs to be focused on in the current state (such as the degraded state), such as an abnormal water level in a certain grid. Local interaction rules are specific response strategies for the excitation state. For example, if the water quality in a certain area suddenly changes to the degraded state, the three nearest devices will automatically form a formation to go there. Master-slave formation refers to the formation of a control hierarchy among devices. The master device (such as an unmanned vessel) makes decisions, and the auxiliary device (such as an underwater robot) executes detailed tasks. Formation methods include relay formation and master-auxiliary formation. Relay formation is suitable for linear tasks (such as river patrol), with devices covering in segments and data relay transmission. Master-auxiliary formation is suitable for key area attacks (such as pollution source location), with the master device coordinating resources and the auxiliary device supplementing capabilities. Finally, the scheduling logic is triggered to perform scheduling decision deduction. That is, the scheduling logic selects the formation mode (such as degraded state → main and auxiliary formation) according to the state transition diagram, and allocates specific equipment. Combined with the real-time status of the equipment (such as power and location), unavailable equipment is eliminated, the formation combination is optimized, and then the modal scheduling strategy is determined to ensure efficient and reliable monitoring under complex hydrological conditions.

[0037] The scheduling-driven management module 40 is used to decouple and align the modal scheduling strategy with the formation equipment, and to delegate communication to the shore-based equipment group in the target water area and perform scheduling-driven management based on the information exchange protocol.

[0038] Preferably, the modal scheduling strategy is decoupled into micro-tasks that can be executed by specific devices by using formation equipment. Through spatiotemporal coordination and standardized communication protocols, it is ensured that multiple devices can perform tasks efficiently and without conflict in complex aquatic environments. Specifically, the modal scheduling strategy is decomposed into atomic tasks that can be executed independently by individual devices, while clarifying the logical relationships between tasks. For example, the main and auxiliary formation tasks can be broken down into the main device (unmanned surface vessel) sailing to the center coordinates (X, Y) of the polluted area and starting multi-parameter water quality scanning; the auxiliary device (underwater robot) following the path planned by the main device to sample the bottom sediment of the pollution source; and the communication relay UAV maintaining real-time data transmission between devices. The dependencies between tasks are also identified, that is, the task sequence is clarified (e.g., the unmanned surface vessel must arrive at the target point first before the underwater robot can start sampling) and resource dependencies (e.g., sharing the same set of meteorological data).

[0039] Preferably, spatiotemporal alignment ensures that the execution of tasks by multiple devices is conflict-free in time and space, and conforms to physical constraints (such as device movement speed and communication latency). Spatiotemporal alignment includes time alignment and spatial alignment. Specifically, time alignment allocates a precise time window for each task to avoid device waiting or resource idleness; spatial alignment plans device paths through grid-based coding (such as dividing the water area into 100m×100m grids) to avoid collisions or duplicate coverage. Then, the decoupled task instructions are efficiently transmitted to the target device through shore-based communication nodes (such as 5G base stations and satellite ground stations), rather than relying on direct control by a central server. Specifically, the cloud-based scheduling center generates modal scheduling strategies and distributes them to the shore-based master control nodes (shore-based device groups). The shore-based device groups act as regional agents, responsible for verifying device status (such as battery level and location), splitting instructions into device-level protocols (such as UAV communication messages), and monitoring execution feedback, triggering retransmission or task adjustment when necessary.

[0040] Preferably, protocol coordination refers to the interaction between devices and between devices and shore-based device groups according to predefined standardized protocols to ensure collaboration among different types of devices. Specifically, the protocol content may include task instruction formats, containing fields such as task ID, target coordinates, action type (e.g., sampling, cruise), and timeout limits; status feedback formats, such as devices periodically transmitting progress, battery level, and exception codes (e.g., low battery); and conflict negotiation rules, such as allocating resources based on priority or spatiotemporal gaps if multiple devices require the same resource (e.g., charging pile). The shore-based device group acts as a protocol intermediary, parsing and forwarding instructions, while also monitoring whether the devices execute the protocol. For example, if a drone fails to transmit data within the set time according to the protocol, the shore-based device group automatically triggers a backup link or task reassignment.

[0041] Preferably, scheduling-driven management is based on information exchange protocol coordination. Specifically, the shore-based equipment group sends the spatiotemporally aligned tasks to the formation equipment. The equipment returns its status according to the protocol. The shore-based equipment group compares the planned progress with the actual progress and makes dynamic adjustments based on the comparison results. For example, if a piece of equipment malfunctions (such as an underwater robot getting stuck), the shore-based equipment group starts a replacement device according to the information exchange protocol. In the event of a sudden weather event (such as wind speed exceeding the limit), the task is suspended and spatiotemporally aligned again. Finally, the shore-based equipment group merges the data from each device and reports it to the cloud to update the water area status space, realizing modal intelligent scheduling and refined control of hydrological flow measurement, optimizing resource allocation efficiency and improving hydrological monitoring coverage.

[0042] Furthermore, the specific configuration of the modal scheduling strategy determination module 30 also includes: retrieving hydrological record data of the target water area, performing a first clustering based on hydrological status to determine a first cluster; performing a second clustering based on the hydrological record data using a scheduling combination method to determine a second cluster; integrating the first cluster and the second cluster to determine the clustering result; and using the clustering result to divide the target water area into a normal state, a degraded state, and a safe state.

[0043] Preferably, hydrological record data (historical hydrological data of the target water area) is retrieved, including but not limited to time-series data such as water depth, river topography, sediment type, water level, flow velocity, water temperature, turbidity, and dissolved oxygen. Unsupervised learning algorithms (such as K-means and DBSCAN) are used to divide the hydrological record data into several clusters based on the similarity of hydrological states, and the first cluster is determined. For example, the distance in the three-dimensional space of water level-flow velocity-turbidity is used as a similarity measure to classify the hydrological state into "high flow velocity and low turbidity" and "low flow velocity and high turbidity". Each cluster represents a typical hydrological condition (such as rapid flow during the wet season and slow flow during the dry season). A second clustering is then performed using a scheduling combination approach. This involves using historical scheduling records as input data, such as equipment formation (primary / secondary / relay), task type (inspection, emergency response), and execution effect (success rate, time consumption). By combining hydrological data with scheduling records, the commonalities of optimal scheduling strategies under different hydrological conditions are analyzed to form a second cluster. For example, cluster M, high water level + heavy rain weather → primary / secondary formation (unmanned surface vessel + underwater robot) has the highest success rate, while cluster N, sudden water quality change + low visibility → relay formation (UAV segmented sampling) has the best efficiency.

[0044] Preferably, the first cluster (natural state) and the second cluster (scheduling strategy) are matched, and the highly correlated intersection of the two is retained to form the final clustering result. Finally, the target water area is divided into normal state, degraded state and safe state based on the clustering result. In the normal state, the hydrological parameters are within the historical normal range (e.g., the cluster center is close to the multi-year average), and the scheduling record shows that the conventional formation can meet the needs, such as water level fluctuation <±5cm, water quality meets the standards, and equipment is inspected according to the fixed route. In the degraded state, the hydrological parameters deviate from the normal but do not reach the danger threshold (e.g., the clustering result shows that the water level is rising continuously but below the warning line), and the historical scheduling requires adjustment of the formation strategy, such as the water level rising by 10cm in a single day, and the main and auxiliary formations are activated to strengthen monitoring. In the safe state, the hydrological parameters exceed the safe threshold (e.g., the extreme value range of the cluster), or the scheduling record indicates that a full-resource emergency response is required, such as the water level exceeding the warning level + equipment failure rate >30%, triggering the relay formation for emergency inspection.

[0045] Furthermore, the specific configuration of the modal scheduling strategy determination module 30 also includes: setting state thresholds based on hydrological conditions, wherein the state thresholds include upper and lower bounds for normal state, degraded state, and safe state; mining hydrological-scheduling sequences based on the clustering results, wherein the clustering results correspond one-to-one with the hydrological-scheduling sequences; and assigning states to the hydrological-scheduling sequences according to the state thresholds, as the divided normal state, degraded state, and safe state.

[0046] Preferably, by using quantitative thresholds and sequence pattern analysis, the water area status is accurately classified (normal, deteriorated, and safe), and a corresponding scheduling strategy is matched for each status. Specifically, state thresholds are set based on hydrological status. These state thresholds are dynamic threshold boundaries defined for hydrological parameters to distinguish the risk levels of different statuses, i.e., constructing multi-level threshold intervals. The state thresholds include upper and lower bounds for the normal, deteriorated, and safe states. The upper and lower bounds for the normal state are based on the statistical distribution of historical clustering results (such as 90% confidence intervals), for example, a normal water level range of 10.0. The normal dissolved oxygen range is 5.0 mg / L and 8.0 mg / L for water levels at 12.5m and 12.5m, respectively. The degraded state is a transitional range between the normal and safe states, usually corresponding to potential risks. For example, the water level degraded range is 12.5m and 13.5m (above 12.5m but below the flood warning line), and the dissolved oxygen degraded range is 3.0 mg / L and 5.0 mg / L. The safe state is a threshold for extreme danger or requiring emergency intervention. For example, the safe water level range is >13.5m (above the flood warning line), and the safe dissolved oxygen range is <3.0 mg / L (risk of fish suffocation).

[0047] Preferably, the hydrological-scheduling sequence is mined from the clustering results. That is, the spatiotemporal association rules extracted from the clustering results reflect the temporal pattern of the optimal scheduling strategy under specific hydrological conditions. Specifically, the hydrological feature clusters in the clustering results and the corresponding historical scheduling records are used as input data to perform association rule mining, determine the frequently co-occurring hydrological features and scheduling combinations, and then perform temporal pattern analysis to identify the changes in scheduling strategy before and after the state transition. Then, a set of hydrological-scheduling sequences is generated for each cluster. For example, for the degraded state cluster, the sequence is water level rise - start of main and auxiliary formations - data reporting every 2 hours. Finally, the hydrological-scheduling sequence is classified into normal, degraded, and safe states based on the state threshold. Specifically, real-time monitoring data is compared and matched with the threshold range. Based on the state of the parameter, the corresponding hydrological-scheduling sequence is invoked. For example, if the degraded state sequence requires a primary and secondary formation plus high-frequency monitoring, the strategy is directly triggered. Then, it is checked whether the current equipment state supports the scheduling combination in the sequence (such as whether the backup equipment is available). If necessary, degraded execution is performed (such as using a single UAV to replace the formation), thereby improving the system's response speed and reliability in complex water scenarios.

[0048] Furthermore, the specific configuration of the state transition graph calculation module 20 also includes: deploying a first node based on the task excitation direction of the hydrological state transition, wherein the first node performs state excitation state analysis; deploying a second node based on the behavioral interaction between scheduling devices and the response of the information exchange protocol; deploying a third node based on the shore-based equipment group as the target, the equipment status and task queue as constraints, and the formation method and formation rules as the basis; cascading the first node, the second node and the third node, and determining the scheduling logic unit through supervised learning until convergence.

[0049] Preferably, based on the task excitation direction of hydrological state transition, the first node is deployed to perform state excitation analysis. That is, based on hydrological state transition (e.g., normal state → degraded state), it identifies local excitation areas that require priority response. Specifically, it inputs real-time water state spatial data (water level, water quality, etc.) and state transition map, and locates high-risk areas (e.g., river sections with sudden water level rise) through attention mechanisms or spatial clustering. It outputs the coordinates of the excitation areas and their risk levels. For example, when the system detects that the dissolved oxygen in a certain area drops by 30% within 1 hour, it is marked as a sudden water quality excitation state. Then, based on the response of the behavioral interaction and information exchange protocol between scheduling devices, the second node is deployed. That is, based on the excitation analysis results, it plans the collaborative behavior between devices and ensures that it conforms to the information exchange protocol. It inputs the excitation area information and the status of available devices (power, location), performs behavioral interaction modeling, simulates the cooperation / competition relationship between devices based on multi-agent reinforcement learning (e.g., drones competing for charging piles), and transforms the communication protocol into constraints, outputting a set of interactive actions between devices.

[0050] Preferably, shore-based equipment groups serve as the execution terminals. Under the constraints of equipment status and task queues, an optimal formation scheme is generated, and a third node is deployed. This node takes into account the set of equipment interaction actions, task queue priorities, and a formation rule base. Integer programming is used to optimize the formation under constraints (equipment power ≥ estimated task time, high-priority tasks are prioritized for primary equipment). The formation type is matched according to the rule base, such as pollution tracking - primary-secondary formation, and specific formation instructions are output. Finally, the first, second, and third nodes are cascaded to form a decision line of state perception - behavior planning - resource allocation. This process is followed by supervised learning until convergence. Specifically, training data is constructed using historical hydrological events and manual scheduling records (labeling the optimal formation strategy) and adversarial scenarios generated in a simulated environment (such as sudden equipment failure). Real-time data is then input to the third-level node to generate a scheduling strategy. The differences between the strategy and the labeled results are compared (such as formation response delay and task completion rate). The node model parameters (such as attention weights and protocol constraint coefficients) are adjusted through gradient descent. Convergence is indicated when the strategy achieves the required accuracy on the test set. Finally, the scheduling logic is determined, realizing an intelligent mapping from complex hydrological situations to precise scheduling.

[0051] Furthermore, the specific configuration of the scheduling-driven management module 40 also includes setting information exchange elements, wherein the information exchange elements include at least device ID, data vector, and intent weight, wherein the intent weight is the task weight of the subject transferring from the exchanging device to the exchanged device; generating an information exchange protocol based on the information exchange elements and data pattern; and executing the scheduling interaction management of the shore-based device group according to the information exchange protocol.

[0052] Preferably, device ID, data vector, and intent weight are set as information exchange elements. The device ID uniquely identifies the sender and receiver; the data vector is the raw data collected by the device or the processing result, in a multi-dimensional vector format; and the intent weight is the task weight transferred from the exchanging device to the exchanged device, representing the current device's contribution to the task. It is dynamically calculated based on device capabilities and station characteristics. If device A's detection process is complex (e.g., an unmanned surface vessel requires sonar to assess underwater risks), while device B's capabilities are simple (e.g., a drone only requires visual scanning), then the intent weight for A→B is... A reduction in weight (e.g., from 0.9 to 0.4) reflects task simplification and is then used for priority allocation. For example, data from high-weight devices will account for a larger proportion during fusion. For instance, when an unmanned surface vessel (USV) detects a suspected risk point (e.g., an area with a sudden rise in water level), but its subsequent detection requires time-consuming sonar scanning, while a drone can quickly confirm it visually, the system reduces the intention weight of the ship to drone transfer (e.g., from 0.6 to 0.3) to shift the task focus to the drone. This prevents high-performance devices (e.g., USV) from being occupied by low-value tasks (e.g., simple scanning) and ensures that technical capabilities match task complexity.

[0053] Preferably, an information exchange protocol is generated based on information exchange elements and data patterns. Specifically, data from different devices is converted into a unified semantic framework. If the sender is an unmanned surface vessel (USV) with an intent weight > 0.7, the receiving UAV must prioritize processing its data. Data vectors transmitted between devices must include timestamps and confidence fields. During task handover, the receiving UAV must adjust its intent weight according to its own capabilities and send back an acknowledgment signal. Finally, the shore-based device group performs scheduling and interaction management. This involves forwarding information exchange elements based on device ID and task queue, checking whether the data vector conforms to the format (retransmission is required if coordinates are missing), and filtering conflicting requests. Weights are dynamically updated based on device status and task urgency, and tasks are then redistributed. When a device malfunctions (e.g., an underwater robot loses contact), the shore-based device group searches for a replacement device with the second-highest weight according to the protocol (e.g., calling a backup UAV). The task queues of each device are monitored. If a UAV has a backlog of tasks (queue length > 5), its low-weight tasks (< 0.3) are transferred to an idle device. This ensures task continuity in abnormal scenarios and improves the accuracy of risk identification.

[0054] Furthermore, the specific configuration of the scheduling and driving management module 40 also includes that the shore-based equipment group includes fixed equipment and mobile equipment, and the mobile equipment includes active mobile equipment and mounted equipment.

[0055] Preferably, the shore-based equipment group is a collection of hardware facilities deployed on the shore or nearshore area of ​​the target waters, responsible for data relay, protocol coordination, and scheduling execution. It includes fixed equipment and mobile equipment. Mobile equipment includes active mobile equipment and mounted equipment. Specifically, fixed equipment refers to fixed infrastructure permanently installed on the shore, usually connected to a stable power supply and communication network, such as 5G / BeiDou satellite communication base stations, data processing servers, and meteorological monitoring stations. Active mobile equipment refers to equipment with autonomous mobility that can actively change its position according to scheduling instructions, such as unmanned boats and drones. Mounted equipment refers to portable equipment without autonomous mobility that needs to be attached to other platforms (such as vehicles and drones) for transportation, such as rapid deployment buoys, foldable water quality analyzers, and modular communication repeaters.

[0056] Furthermore, the specific configuration of the scheduling-driven management module 40 also includes that the active mobile device includes a drone and an unmanned vessel, wherein the unmanned vessel uses a cross-sectional reference coordinate system as the data mode, and the drone uses a local water area projection as the data mode; the mutual conversion between the cross-sectional reference coordinate system and the local water area projection is used as the data interaction condition for relay scheduling of the drone and the unmanned vessel, and is added to the information exchange protocol.

[0057] Preferably, the active mobile devices include drones and unmanned surface vessels (USVs). Seamless cross-platform data integration is achieved through coordinate system transformation, ensuring semantic consistency and spatial accuracy during task handover. Specifically, USVs use a cross-sectional reference coordinate system as their data mode, i.e., based on the river cross-section, employing three-dimensional coordinates of longitudinal distance (along the river centerline) + lateral offset + water depth for vertical data acquisition such as underwater topographic mapping and flow velocity profile measurement. This cannot directly match the aerial observation perspective of drones. Drones use a local water area projection as their data mode, i.e., using the water surface as a two-dimensional plane, employing geographic coordinate systems (such as WGS-84 latitude and longitude) or local grid coding for planar scanning tasks such as water surface pollution diffusion monitoring and floating object identification. This is difficult to describe underwater features (such as riverbed morphology). Then, the mutual conversion between the cross-sectional reference coordinate system and the local water area projection serves as the data interaction condition for the relay scheduling of drones and USVs. That is, through a river digital elevation model, the longitudinal coordinates acquired by the USV are mapped to the planar coordinates acquired by the drone. The system uses coordinates and a water surface grid, labeled with water depth attributes. The UAV collects data on oil spills on the water surface, which are located on the grid and converted into longitudinal coordinates for the UAV's sampling. This guides the UAV's sampling. An information exchange protocol is then generated, requiring the UAV to label its coordinate system type and provide cross-section numbers and offsets in the data vector, and the UAV to label its projection type and latitude / longitude. When the UAV detects a target requiring aerial verification (such as suspected pollution), it sends the converted coordinates and intent weights. The UAV responds preferentially according to the protocol. This information is then added to the information exchange protocol to ensure that the UAV does not misinterpret the coordinates and fly into restricted areas, or that the UAV collides with underwater obstacles, thus guaranteeing the accuracy and reliability of hydrological monitoring.

[0058] Furthermore, the specific configuration of the scheduling-driven management module 40 also includes: each device in the shore-based equipment group has a unique identifier; locating the identifier corresponding to the formation equipment, decoupling the modal scheduling strategy, determining the sub-scheduling strategy, wherein the sub-scheduling strategy corresponds one-to-one with the formation equipment; introducing timestamp constraints and position code constraints, coordinating the identification of the sub-scheduling strategy, and executing strategy communication decentralization and scheduling management.

[0059] Preferably, each device within the shore-based equipment group (such as drones, unmanned surface vessels, and shore-based sensors) has a unique, non-repeatable identifier used to locate the device's status (such as battery level and current location) in the scheduling database. The identifiers corresponding to the devices in the formation are used to determine the formation's identifier list. Then, the modal scheduling strategy is decoupled to determine sub-scheduling strategies. For example, the main device is responsible for sonar scanning of the core pollution area, auxiliary devices inspect the pollution diffusion edge, and communication relay drones transmit data back to the shore-based equipment group in real time and allocate tasks according to device capabilities. Each sub-strategy includes a device identifier and action instructions (such as flight path and sampling frequency). Then, timestamp constraints and location code constraints are introduced to ensure the time synchronization or sequence of multiple device actions and to avoid spatial conflicts or coverage blind spots between devices. The sub-scheduling strategies are collaboratively identified by adding a collaborative identifier to each sub-strategy. When the shore-based equipment group tracks task progress, the collaborative relationship between multiple devices can be quickly associated. The identifier is carried when devices provide feedback data, facilitating data fusion. Finally, the strategy communication is distributed and the scheduling management is implemented. That is, the shore-based equipment group pushes the sub-strategy to the corresponding equipment through 5G / LoRa. The equipment returns the status according to the protocol. Then, the shore-based equipment group verifies the spatiotemporal constraints (such as whether there is a timeout or boundary violation), and finally completes the precise and intelligent scheduling of the hydrological flow measurement mode.

[0060] In the above text, refer to Figure 1 This paper describes in detail the intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water resources according to embodiments of the present invention. Next, reference will be made to... Figure 2 This paper describes an intelligent scheduling method for hydrological flow measurement modes that integrates air, space, and water resources, according to embodiments of the present invention. The intelligent scheduling method for hydrological flow measurement modes that integrates air, space, and water resources, such as... Figure 2 As shown, the method includes: deploying a water state space for the target water area, wherein the water state space is updated in real time; developing a scheduling logic device within an intelligent scheduling system, calculating a state transition diagram based on the water state space through a data interface; dividing the water state of the target water area into normal state, degraded state, and safe state, marking the state transition diagram and generating a temporary agreement, triggering the scheduling logic device to perform scheduling decision derivation, and determining a modal scheduling strategy, wherein the state excitation state-local interaction rules and device behavior-device master-slave formation are used as the baseline logic, and the formation methods include relay formation and master-slave formation; decoupling and spatiotemporally aligning the modal scheduling strategy with the formation devices, delegating communication to the shore-based equipment group in the target water area, and coordinating scheduling-driven management based on an information exchange protocol.

[0061] In one possible implementation, the intelligent scheduling method for hydrological flow measurement modes in a space-air-ground-water collaborative manner further includes: the elements of the water state space at least include water level, meteorology, water surface environment, equipment status, and task queue, wherein the task queue is a real-time running queue, and the equipment status at least includes equipment power and location code; for each element, an element coding mode is set, wherein each element corresponds to an element coding mode; and the water state space is deployed based on the element coding mode.

[0062] In one possible implementation, the intelligent scheduling method for hydrological flow measurement modes in a space-air-ground-water collaborative manner further includes: retrieving hydrological record data of the target water area, performing a first clustering based on hydrological status to determine a first cluster; performing a second clustering based on the hydrological record data using a scheduling combination method to determine a second cluster; integrating the first cluster and the second cluster to determine the clustering result; and using the clustering result to divide the target water area into a normal state, a degraded state, and a safe state.

[0063] In one possible implementation, the intelligent scheduling method for hydrological flow measurement modes in a space-air-ground-water collaborative manner further includes: setting state thresholds based on hydrological conditions, wherein the state thresholds include upper and lower bounds for normal state, degraded state, and safe state; mining hydrological-scheduling sequences based on the clustering results, wherein the clustering results correspond one-to-one with the hydrological-scheduling sequences; and assigning states to the hydrological-scheduling sequences according to the state thresholds, as the divided normal state, degraded state, and safe state.

[0064] In one possible implementation, the intelligent scheduling method for hydrological flow measurement modes in a space-air-ground-water collaborative manner further includes: deploying a first node based on the task excitation direction of hydrological state transition, wherein the first node performs state excitation state analysis; deploying a second node based on the behavioral interaction between scheduling devices and the response of the information exchange protocol; deploying a third node with the shore-based equipment group as the target, the equipment status and task queue as constraints, and the formation method and formation rules as the basis; cascading the first node, the second node, and the third node, and determining the scheduling logic unit through supervised learning until convergence.

[0065] In one possible implementation, the intelligent scheduling method for hydrological flow measurement modes in a space-air-ground-water collaborative manner further includes: setting information exchange elements, wherein the information exchange elements include at least a device ID, a data vector, and an intent weight, wherein the intent weight is the task weight of the subject transferring from the exchanging device to the exchanged device; generating an information exchange protocol based on the information exchange elements and the data mode; and executing the scheduling and interactive management of the shore-based equipment group according to the information exchange protocol.

[0066] In one possible implementation, the intelligent scheduling method for hydrological flow measurement modes in a space-air-ground-water collaborative manner further includes: the shore-based equipment group includes fixed equipment and mobile equipment, and the mobile equipment includes active mobile equipment and mounted equipment.

[0067] In one possible implementation, the intelligent scheduling method for hydrological flow measurement modes in a coordinated manner involving air, land, and water further includes: the active mobile device comprises a drone and an unmanned vessel, wherein the unmanned vessel uses a cross-sectional reference coordinate system as the data mode, and the drone uses a local water area projection as the data mode; the mutual conversion between the cross-sectional reference coordinate system and the local water area projection is used as a data interaction condition for relay scheduling of the drone and the unmanned vessel, and is added to the information exchange protocol.

[0068] In one possible implementation, the intelligent scheduling method for hydrological flow measurement modes in a coordinated manner involving air, land, and water further includes: each device in the shore-based equipment group has a unique identifier; the identifier corresponding to the equipment in the formation is located, the mode scheduling strategy is decoupled, and a sub-scheduling strategy is determined, wherein the sub-scheduling strategy corresponds one-to-one with the equipment in the formation; timestamp constraints and location code constraints are introduced to collaboratively identify the sub-scheduling strategies, and strategy communication is delegated and scheduling management is performed.

[0069] The intelligent scheduling system for hydrological measurement modes that integrates air, space, and water resources, provided in the embodiments of the present invention, can execute the intelligent scheduling method for hydrological measurement modes that integrates air, space, and water resources, provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0070] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. 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 each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0071] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A space-air-ground-water integrated intelligent scheduling system for hydrological flow measurement modes, characterized in that, The system includes: A water state space deployment module is used to deploy the water state space of a target water area, wherein the water state space is updated in real time; The state transition diagram calculation module is used to develop a scheduling logic device within the intelligent scheduling system and calculate the state transition diagram based on the state space of the water area through a data interface. The modal scheduling strategy determination module is used to divide the water state of the target water area into normal state, degraded state, and safe state, mark the state transition diagram and generate temporary agreements, trigger the scheduling logic to perform scheduling decision deduction, and determine the modal scheduling strategy. The module uses the state-initiated state, local interaction rules, and device behavior-device master-slave formation as the baseline logic. The formation methods include relay formation and master-slave formation. The state-initiated state refers to the sub-area or device that needs to be focused on in the current state; local interaction rules are specific response strategies for the initiated state; master-slave formation refers to the formation of a control hierarchy between devices, with the master device making decisions and the slave device executing detailed tasks. The scheduling logic selects the formation mode according to the state transition diagram, assigns specific devices, combines the real-time status of the devices, excludes unavailable devices, optimizes the formation combination, and thus determines the modal scheduling strategy. The scheduling-driven management module is used to decouple and align the modal scheduling strategy with the formation equipment, and to delegate communication to the shore-based equipment group in the target waters and perform scheduling-driven management based on the information exchange protocol. The steps performed by the modality scheduling strategy determination module include: Retrieve hydrological records of the target water area, perform a clustering based on hydrological status, and determine the first cluster. For the aforementioned hydrological record data, a second clustering is performed using a scheduling and combination method to determine the second cluster. The first cluster and the second cluster are combined to determine the clustering result; Based on the clustering results, the target water area is divided into normal state, degraded state, and safe state; The steps performed by the state transition diagram calculation module include: The first node is deployed based on the task excitation direction of hydrological state transition, wherein the first node performs state excitation state analysis; In response to the information exchange protocol and the behavioral interactions between scheduling devices, a second node is deployed; With the shore-based equipment group as the target, the equipment status and task queue as constraints, and the formation method and formation rules as the basis, a third node is deployed. The first node, the second node, and the third node are cascaded together, and the scheduling logic is determined through supervised learning until convergence.

2. The intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water as described in claim 1, characterized in that, The elements of the water area status space include at least water level, weather, water surface environment, equipment status, and task queue, wherein the task queue is a real-time running queue, and the equipment status includes at least equipment power and location code. For each element, an element coding pattern is set, where each element corresponds to one element coding pattern; Based on the aforementioned element coding pattern, the water area state space is deployed.

3. The intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water as described in claim 1, characterized in that, The steps performed by the modality scheduling strategy determination module include: Based on the hydrological conditions, state critical values ​​are set, wherein the state critical values ​​include upper and lower bounds of normal state, upper and lower bounds of degraded state, and upper and lower bounds of safe state; Based on the clustering results, hydrological-scheduling sequences are mined, wherein the clustering results correspond one-to-one with the hydrological-scheduling sequences; Based on the state threshold, the hydrological-scheduling sequence is assigned a state, which is divided into normal state, degraded state, and safe state.

4. The intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water as described in claim 1, characterized in that, The steps performed by the scheduling-driven management module include: Define information exchange elements, wherein the information exchange elements include at least device ID, data vector, and intent weight, wherein the intent weight is the task weight of the subject transferring from the exchanging device to the exchanged device; Based on the information exchange elements and data patterns, an information exchange protocol is generated; According to the information exchange protocol, the scheduling and interactive management of the shore-based equipment group is performed.

5. The intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water as described in claim 4, characterized in that, The shore-based equipment group includes fixed equipment and mobile equipment, and the mobile equipment includes active mobile equipment and mounted equipment.

6. The intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water as described in claim 5, characterized in that, The active mobile device includes drones and unmanned vessels, wherein the unmanned vessels use a cross-sectional reference coordinate system as the data mode, and the drones use a local water area projection as the data mode. The mutual conversion between the cross-sectional reference coordinate system and the local projection of the water area is used as a data interaction condition for the relay scheduling of UAVs and unmanned vessels, and is added to the information exchange protocol.

7. The intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water as described in claim 1, characterized in that, Each piece of equipment in the shore-based equipment group has a unique identification code; Locate the identification code corresponding to the formation device, decouple the modal scheduling strategy, and determine the sub-scheduling strategy, wherein the sub-scheduling strategy corresponds one-to-one with the formation device; By introducing timestamp constraints and location code constraints, the sub-scheduling strategy is collaboratively identified, and the strategy communication is delegated and the scheduling is managed.

8. A smart scheduling method for hydrological flow measurement modes that integrates air, space, and water resources, characterized in that: The method is applied to the intelligent scheduling system for hydrological flow measurement modes that integrates air, space, and water resources as described in any one of claims 1-7, and the method includes: Deploy the water state space of the target water area, wherein the water state space is updated in real time; A scheduling logic device is developed within the intelligent scheduling system to calculate the state transition diagram based on the state space of the water area through a data interface. The water state of the target water area is divided into normal state, degraded state and safe state. The state transition diagram is marked and a temporary contract is generated. The scheduling logic is triggered to perform scheduling decision deduction and determine the modal scheduling strategy. The state excitation state-local interaction rules and device behavior-device master-slave formation are used as the basis logic. The formation mode includes relay formation and master-slave formation. The mode scheduling strategy is decoupled and spatiotemporally aligned by the formation equipment, and communication is decentralized to the shore-based equipment group in the target waters and scheduling-driven management is carried out in cooperation with the information exchange protocol.

Images