Cloud edge collaboration based small watershed water flow parameter monitoring system and method

Abstract

The application relates to the technical field of data processing, in particular to a small watershed water flow parameter monitoring system and method based on cloud edge cooperation. The system comprises an edge module, the edge module comprises a plurality of edge node modules, the plurality of edge node modules are arranged near each target watershed respectively, and are used for acquiring water flow parameters of each target watershed; the edge node module comprises a computing unit and an information acquisition unit; the information acquisition unit is used for measuring characteristic information of the target watershed; the computing unit is used for calculating the water flow parameters based on the characteristic information; the water flow parameters comprise water level height and flow speed; a cloud end module, the cloud end module comprises: a meteorological module, which is used for acquiring meteorological information in a future predetermined time period; a management and scheduling module, which is used for determining the priority of characteristic information acquisition of each watershed in the future predetermined time period according to the meteorological information; by adopting the system provided by the application, the problem that a small watershed area water flow safety hidden danger is not found in time can be solved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a small watershed flow parameter monitoring system and method based on cloud-edge collaboration. Background Technology

[0002] In hydrological monitoring systems, small watershed monitoring cameras are typically widely distributed, with numerous data nodes but limited computing resources. Usually, all data needs to be aggregated and transmitted to a cloud server for centralized processing. In this scenario, the data processing task is concentrated in the background, leading to a heavy processing burden on the central cloud server and delays in data feedback to application terminals. This makes it difficult to issue timely and accurate alarm information in emergencies. For example, during heavy rains, the tides in small watersheds typically rise rapidly. If water flow data collection and analysis are not timely, residents near the watershed may not receive timely alarm information when the water level exceeds the warning line, potentially threatening their property and personal safety. Therefore, there is an urgent need to design a small watershed water flow parameter monitoring system to address the problem of untimely detection of water flow safety hazards in small watershed areas. Summary of the Invention

[0003] The purpose of this application is to provide a cloud-edge collaborative small watershed flow parameter monitoring system and method to solve the problem of untimely detection of water flow safety hazards in small watershed areas.

[0004] To achieve the above objectives, the first aspect of this application provides a small watershed flow parameter monitoring system based on cloud-edge collaboration. The system includes: an edge module comprising multiple edge node modules, each located near a target watershed, for acquiring flow parameters of each target watershed; each edge node module includes a computing unit and an information acquisition unit; the information acquisition unit is used to measure characteristic information of the target watershed; the computing unit is used to calculate flow parameters based on the characteristic information; the flow parameters include water level and flow velocity; and a cloud module comprising: a meteorological module for acquiring meteorological information for a predetermined future time period; and a management and scheduling module for determining the priority of characteristic information acquisition for each watershed within the predetermined future time period based on the meteorological information; and also for calling the computing unit to prioritize the acquisition of priority characteristic information; wherein, within the predetermined future time period, the higher the priority of characteristic information acquisition, the higher the frequency of characteristic information acquisition for the corresponding watershed.

[0005] Based on the first aspect, in this embodiment of the application, the cloud module further includes: a status monitoring module, used to monitor whether the operating status of each information collection unit is normal; if so, the calculation unit uses a first algorithm model to calculate the water flow parameters, otherwise it uses a second algorithm model to calculate the water flow parameters.

[0006] Based on the first aspect, in the embodiments of this application, the information acquisition unit includes a video acquisition device, and the feature information includes image information; the first algorithm model is a pre-trained image-based water flow parameter prediction model.

[0007] Based on the first aspect, in the embodiments of this application, the second algorithm model is an empirical calculation model based on the upstream and downstream flow correlation method and the rainfall-runoff empirical correlation method.

[0008] Based on the first aspect, in this embodiment of the application, the cloud module further includes: a status monitoring module, used to monitor the load status of each computing unit; the load status includes light load and overload; the management and scheduling module is also used to call computing units with a light load status to assist computing units with an overload status in processing data.

[0009] Based on the first aspect, in this embodiment of the application, the cloud module further includes: an early warning module, used to determine whether there are safety hazards in the target watershed based on the water flow parameters; if so, to estimate the scope of the disaster impact and send early warning information to residents within the scope of the disaster impact.

[0010] Based on the first aspect, in the embodiments of this application, the information acquisition unit includes a video acquisition device, the feature information includes image information, and the cloud module further includes a streaming media display module, which is used to render the acquired image information and push the rendered result to the user terminal via the WebRTC protocol.

[0011] A second aspect of this application provides a method for monitoring water flow parameters in small watersheds based on cloud-edge collaboration. The method includes: S1, measuring characteristic information of the target watershed; S2, calculating water flow parameters based on the characteristic information; the water flow parameters include water level and flow velocity; S3, acquiring meteorological information for a predetermined future time period; S4, determining the priority of characteristic information collection for each watershed within the predetermined future time period based on the meteorological information, and prioritizing the processing of the prioritized characteristic information; wherein, within the predetermined future time period, the higher the priority of characteristic information collection, the higher the frequency of characteristic information collection for the corresponding watershed.

[0012] Based on the second aspect, in this embodiment of the application, the meteorological information includes rainfall; the step of determining the priority of collecting feature information of each watershed within a predetermined time period based on the meteorological information includes: setting watersheds with rainfall R in the range of 0 ≤ R < a as non-priority collection watersheds; setting watersheds with rainfall R in the range of a ≤ R < b as Level I priority collection watersheds; and setting watersheds with rainfall R in the range of b ≤ R as Level II priority collection watersheds; wherein, the collection frequency of feature information of Level II priority collection watersheds is higher than that of Level I priority collection watersheds, and the collection frequency of feature information of Level I priority collection watersheds is higher than that of non-priority collection watersheds.

[0013] Based on the second aspect, in this embodiment of the application, the method further includes: monitoring whether the operating status of each information acquisition unit is normal; if so, calculating the water flow parameters using a first algorithm model; otherwise, calculating the water flow parameters using a second algorithm model. Monitoring the load status of each computing unit; the load status includes light load and overload; calling the computing unit with a light load status to assist the computing unit with an overload status in processing data.

[0014] The solution provided in this application has at least the following beneficial effects:

[0015] The cloud-edge collaborative small watershed flow parameter monitoring system provided in this application relies on the division of labor and cooperation between edge computing and cloud computing. It fully utilizes the edge analysis capabilities of edge devices and the efficient storage and task scheduling capabilities of the cloud to construct a low-latency, high-precision data processing and real-time monitoring platform. This platform can solve the problem of untimely detection of potential water flow safety (flood) hazards caused by the rapid tidal rise in small watershed areas. Furthermore, through the edge deployment of lightweight algorithm models, the system can achieve real-time monitoring and data acquisition of water level and flow velocity; combined with cloud-based streaming media proxy rendering, it provides users with intuitive and real-time hydrological data display effects.

[0016] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0018] Figure 1 This diagram illustrates the structure of a small watershed flow parameter monitoring system based on cloud-edge collaboration.

[0019] Figure 2 The schematic diagram illustrates the process flow of a small watershed flow parameter monitoring method based on cloud-edge collaboration.

[0020] Explanation of reference numerals in the attached figures

[0021] 1-Edge Node Module; 11-Computing Unit; 12-Information Acquisition Unit; 13-Loading and Update Unit; 2-Meteorological Module; 3-Management and Scheduling Module; 4-Early Warning Module; 5-Streaming Media Display Module; 6-Data Storage Module; 7-User Interaction Module; 8-Status Monitoring Module. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0023] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0024] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0025] Example 1

[0026] like Figure 1 As shown, this embodiment provides a small watershed flow parameter monitoring system based on cloud-edge collaboration. The system includes:

[0027] An edge module, the edge module comprising:

[0028] Multiple edge node modules 1 are respectively located near each target watershed to obtain the water flow parameters of each target watershed;

[0029] The edge node module 1 includes a computing unit 11 and an information acquisition unit 12 (e.g., a video acquisition device); the information acquisition unit 12 is used to measure the characteristic information of the target watershed; the computing unit 11 is used to calculate water flow parameters based on the characteristic information; the water flow parameters include water level and flow velocity;

[0030] For example, the feature information includes image information of the target watershed. Real-time video (images) related to water level and flow velocity are acquired through the information acquisition unit 12. The computing unit 11 and the information acquisition unit 12 are connected via video protocols such as RTSP / RTMP. The computing unit 11 performs real-time water level and flow velocity analysis on the acquired video frames using a preset hydraulic algorithm analysis model, providing multi-flow input data support to adapt to the needs of multi-scenario hydraulic monitoring. Specifically, it includes two parts: water flow velocity monitoring and water level monitoring.

[0031] In addition, the information acquisition unit 12 also includes multiple water level sensors and flow velocity sensors evenly spaced along the watershed. However, due to the significant fluctuations in water flow, the following calculation method can be used to calculate the water level at a local location in the target watershed: Count the time t within a time period T when the water surface reaches or exceeds the height of the water level sensor, and calculate the ratio t / T. If this ratio is less than 30%, the water level is considered to be lower than the height of the water level sensor; if the ratio is between 30% and 50%, the water level is considered to be equal to the height of the water level sensor; and if the ratio is not less than 50%, the water level is considered to be higher than the height of the water level sensor. The water flow velocity at a local location in the target watershed can be directly measured by the flow velocity sensor.

[0032] A cloud module, comprising:

[0033] Meteorological module 2 is used to obtain meteorological information for a future predetermined time period (which can be obtained directly from the Internet).

[0034] The management and scheduling module 3 is used to determine the priority of feature information collection for each watershed within a predetermined time period in the future based on the meteorological information; it is also used to call the computing unit 11 to prioritize the feature information to be collected; wherein, within the predetermined time period in the future, the higher the priority of feature information collection, the higher the frequency of feature information collection for the corresponding watershed.

[0035] For example, the meteorological information includes rainfall; determining the priority of collecting feature information of each watershed within a predetermined time period based on the meteorological information includes: designating watersheds with rainfall R within the range of 0 ≤ R < a (for example, a can be set to 20 mm) as non-priority collection watersheds; designating watersheds with rainfall R within the range of a ≤ R < b (for example, b can be set to 50 mm) as Level I priority collection watersheds; and designating watersheds with rainfall R within the range of b ≤ R as Level II priority collection watersheds; wherein, the collection frequency of feature information in Level II priority collection watersheds is higher than that in Level I priority collection watersheds, and the collection frequency of feature information in Level I priority collection watersheds is higher than that in non-priority collection watersheds. That is, the higher the rainfall, the higher the frequency of feature information collection. In cases of high rainfall, the water level and flow velocity in small watersheds can easily rise rapidly in a short period of time. Therefore, extra attention needs to be paid to the water level and flow velocity in small watersheds during heavy rainfall to prevent water from overflowing the riverbanks or causing a rapid rise in downstream water levels due to high flow velocity, which may go undetected in time.

[0036] For the Level I and Level II priority collection basins, the increased frequency of feature information collection necessitates improving the processing efficiency of the corresponding edge node module 1's computing unit 11. This obviously increases the burden on the corresponding computing unit 11. Therefore, to address this issue, in this embodiment, the cloud module further includes: a status monitoring module 8, used to monitor the load status of each computing unit 11; the load status includes light load and overload; the management and scheduling module 3 is also used to call upon computing units 11 with a light load status to assist computing units 11 with an overload status in processing data, ensuring reliable task execution.

[0037] Furthermore, the cloud module also includes:

[0038] The early warning module 4 is used to determine whether there are safety hazards in the target watershed based on the water flow parameters. If there are, it estimates the scope of the disaster impact and sends early warning information to residents within the disaster impact area to protect the lives and property of nearby residents.

[0039] The streaming media display module 5 is used to render the acquired image information and push the rendered result to the user terminal via the WebRTC protocol. Specifically, its display content includes: water body segmentation information, water level coordinates, flow velocity visualization, and other information;

[0040] Data storage module 6 uses a PostgreSQL relational database to persistently store structured data such as user information, task information, algorithm exception information, and system configuration; for video data and image data, a distributed file system NFS is used for storage management to ensure data storage security and avoid data loss.

[0041] User Interaction Module 7: The user interface is built using the Vue front-end framework and communicates with the back-end using a RESTful API. The back-end uses the OATPP framework, employs Bearer for user authentication and authorization, and uses ORM to manage the database model. It supports real-time monitoring, historical data querying, and system parameter configuration, and displays real-time water conservancy monitoring information and historical data trend charts through the interface.

[0042] Example 2

[0043] Since the information acquisition unit 12 typically operates outdoors, human or non-human factors may inevitably cause it to malfunction or collect inaccurate information. For example, heavy rainfall may result in unclear images acquired by the image acquisition module. To address this issue, this embodiment provides two sets of calculation models for water flow parameters: a first algorithm model and a second algorithm model.

[0044] Specifically, the cloud module also includes a status monitoring module 8, used to monitor whether the operating status of each information acquisition unit 12 is normal; if so, the computing unit 11 uses a first algorithm model to calculate the water flow parameters; otherwise, it uses a second algorithm model to calculate the water flow parameters. That is, when the information acquisition unit 12 is working normally (when the acquired image information is accurate), the first algorithm model is used. The information acquisition unit 12 includes a video acquisition device, and the feature information includes image information; the first algorithm model is a pre-trained image-based water flow parameter prediction model, which improves the efficiency and accuracy of water flow parameter acquisition. Furthermore, through deep learning model pruning and quantization techniques, the water flow parameter detection algorithm is optimized into a lightweight version model to adapt to the computing power of the computing unit 11, ensuring operating efficiency and performance stability on different edge node modules 1. Also, because the geographical environments of different watersheds are different, different models need to be trained separately for acquiring water flow parameters in different watersheds. In the aforementioned embodiment 1, before calling the lightly loaded computing unit 11 to assist the overloaded computing unit 11 in processing data, the lightly loaded computing unit 11 needs to load and switch to a new algorithm model (a prediction model corresponding to the target watershed). Preferably, the edge node module 1 further includes a loading and updating unit 13, used to load, update, and switch the water flow parameter prediction model, and to establish a persistent connection with the cloud via the HTTP protocol to receive the latest algorithm module from the cloud and dynamically update the algorithm model. When the information acquisition unit 12 cannot work properly (when the live image information is inaccurate), a second algorithm model needs to be used. The second algorithm model is an empirical calculation model based on the upstream and downstream flow correlation method and the rainfall-runoff empirical correlation method. For example, the water level and flow rate, flow velocity, and water propagation time of the upstream watershed can be used to estimate the downstream water level and flow rate. Specific methods include the corresponding water level method and the synthetic flow method, which establish an empirical relationship model by analyzing the water level change law when the water flow and water waves propagate from upstream to downstream. Furthermore, by establishing the correlation between rainfall and flow in the basin through historical data, the basin's runoff can be predicted using rainfall data. Based on the theory of rainfall runoff and confluence in the basin, measured rainfall data can be used to predict the runoff at the basin's outlet section, i.e., the flow velocity.

[0045] Example 3

[0046] The specific design and deployment steps of the above system are as follows:

[0047] Step 1: Deploy cloud-based services. Select the performance configuration of the central Linux server according to actual needs. Deploy the management and scheduling module 3, configure the scheduling task parameters for water level monitoring and water flow velocity monitoring algorithms, and configure task priorities and load balancing rules. Deploy the data storage module 6, build an efficient and reliable PostgreSQL database, and configure data persistence functions to store real-time analysis results and historical monitoring data. Deploy the streaming media display module 5, build a streaming media server, and realize real-time rendering of cloud video data. Deploy the user interaction module 7, and use Nginx service to deploy the system client interface.

[0048] Step 2: Deploy edge layer services. Deploy and configure the network parameters and physical monitoring locations of the computing power cameras (including computing unit 11 and information acquisition unit 12) to ensure that the monitoring range covers the designated hydrological area. Deploy the edge box algorithm monitoring service, configure the central registration IP, port, and authentication key of the edge devices to ensure normal interaction between the edge devices and the computing power cameras in the future.

[0049] Step 3: Lightweight Algorithm Model Deployment. Model pruning and quantization techniques are used to lightweight the PidNet water level detection model and the FusionUnet flow velocity detection model, ensuring that the generated lightweight versions are adapted to the computing power and storage space of edge devices and computing cameras. This ensures that the lightweight models meet the application scenario requirements in terms of inference accuracy and performance, while significantly reducing the model's computational overhead. The optimized lightweight models are pushed to edge devices through the central task management module, achieving rapid deployment at the edge layer.

[0050] Step 4: Cloud-edge task collaboration begins. A real-time, stable, bidirectional connection is established between the central endpoint and edge devices via HTTP. The cloud allocates water level detection and flow rate monitoring tasks to each edge device based on task priority and the load status of the edge devices. Upon receiving the task, the edge device initiates the video acquisition task according to the task configuration and simultaneously loads the corresponding lightweight algorithm model for data processing. During task execution, the cloud can reallocate tasks based on the edge device status (analysis latency, device load data) to improve resource utilization and processing efficiency.

[0051] Step 5: Edge Data Calculation and Result Reporting. The algorithm analysis module in the edge device processes the collected video data in real time, analyzes water level and flow velocity information, and generates key result data (such as water level height, real-time flow velocity, and flow velocity change trend). The processed results are pushed to the central end via HTTP transmission protocol. The central end aggregates the data and persists it through the storage module. The data to be rendered is then updated and pushed to the streaming media server.

[0052] Step 6: Streaming media proxy rendering and display. The cloud streaming media display module 5 receives data from the edge device and, by pulling the original video stream data from the camera itself, overlays the real-time water level and flow rate results that need to be updated onto the video stream.

[0053] Step 7: Cloud-based model iteration and updates. Regularly collect data returned from edge devices and video image data from actual analysis scenarios. Through local model iterative training, generate new lightweight model versions to adapt to constantly changing hydrological environments and new scenario requirements. The updated algorithm model is pushed to edge devices via HTTP through the cloud task management module, ensuring continuous optimization and operation of the entire system.

[0054] Through the above steps, a small-basin water flow parameter monitoring system based on cloud-edge collaboration can be finally realized. This system relies on the division of labor and cooperation between edge computing and cloud computing, fully utilizing the edge analysis capabilities of edge devices and the efficient storage and task scheduling capabilities of the cloud to build a low-latency, high-precision data processing and real-time monitoring platform. The system achieves real-time monitoring and data acquisition of water levels and flow velocities through the edge deployment of lightweight algorithm models; combined with cloud-based streaming media proxy rendering, it provides users with intuitive and real-time hydrological data display effects. Simultaneously, the cloud-based model iteration and update mechanism enables the system to continuously learn and adapt to new environments, meeting the real-time, reliability, and scalability requirements of water conservancy monitoring scenarios.

[0055] Example 4

[0056] like Figure 2 As shown, this embodiment provides a method for monitoring water flow parameters in small watersheds based on cloud-edge collaboration. The method includes: S1, measuring characteristic information of the target watershed; S2, calculating water flow parameters based on the characteristic information; the water flow parameters include water level and flow velocity; S3, acquiring meteorological information for a predetermined future time period; S4, determining the priority of characteristic information collection for each watershed within the predetermined future time period based on the meteorological information, and prioritizing the processing of the prioritized characteristic information; wherein, within the predetermined future time period, the higher the priority of characteristic information collection, the higher the frequency of characteristic information collection for the corresponding watershed.

[0057] Furthermore, the meteorological information includes rainfall; determining the priority of collecting feature information of each watershed within a predetermined future time period based on the meteorological information includes: setting watersheds with rainfall R in the range of 0 ≤ R < a as non-priority collection watersheds; setting watersheds with rainfall R in the range of a ≤ R < b as Level I priority collection watersheds; and setting watersheds with rainfall R in the range of b ≤ R as Level II priority collection watersheds; wherein, the collection frequency of feature information of Level II priority collection watersheds is higher than that of Level I priority collection watersheds, and the collection frequency of feature information of Level I priority collection watersheds is higher than that of non-priority collection watersheds.

[0058] Furthermore, the method also includes: monitoring whether the operating status of each information acquisition unit 12 is normal; if so, the first algorithm model is used to calculate the water flow parameters; otherwise, the second algorithm model is used to calculate the water flow parameters. Monitoring the load status of each calculation unit 11; the load status includes light load and overload; calling the calculation unit 11 with a light load status to assist the calculation unit 11 with an overload status in processing data.

[0059] The method provided in this embodiment is applicable to the systems in Embodiments 1 and 2 above, as detailed in Embodiments 1 and 2, and will not be repeated here.

[0060] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0062] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0064] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0065] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0066] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0067] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0068] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A small watershed flow parameter monitoring system based on cloud-edge collaboration, characterized in that, The system includes: An edge module, comprising multiple edge node modules, is positioned near each target watershed to acquire water flow parameters for each target watershed. Each edge node module includes a computing unit and an information acquisition unit. The information acquisition unit measures characteristic information of the target watershed. The computing unit calculates water flow parameters based on the characteristic information. The water flow parameters include water level and flow velocity. A cloud module, comprising: The meteorological module is used to obtain meteorological information for a future scheduled time period; The management and scheduling module is used to determine the priority of feature information collection for each watershed within a predetermined time period based on the meteorological information; it is also used to call the computing unit to prioritize the feature information to be collected; wherein, within the predetermined time period, the higher the priority of feature information collection, the higher the frequency of feature information collection for the corresponding watershed.

2. The small watershed flow parameter monitoring system based on cloud-edge collaboration according to claim 1, characterized in that, The cloud module also includes: The status monitoring module is used to monitor whether the operating status of each information acquisition unit is normal. If so, the calculation unit uses the first algorithm model to calculate the water flow parameters; otherwise, it uses the second algorithm model to calculate the water flow parameters.

3. The small watershed flow parameter monitoring system based on cloud-edge collaboration according to claim 2, characterized in that, The information acquisition unit includes a video acquisition device, and the feature information includes image information; the first algorithm model is a pre-trained image-based water flow parameter prediction model.

4. The small watershed flow parameter monitoring system based on cloud-edge collaboration according to claim 2, characterized in that, The second algorithm model is an empirical calculation model based on the upstream and downstream flow correlation method and the rainfall-runoff empirical correlation method.

5. The small watershed flow parameter monitoring system based on cloud-edge collaboration according to claim 1, characterized in that, The cloud module also includes: The status monitoring module is used to monitor the load status of each computing unit; the load status includes light load and overload. The management and scheduling module is also used to call computing units with a light load status to assist computing units with an overload status in processing data.

6. The small watershed flow parameter monitoring system based on cloud-edge collaboration according to claim 1, characterized in that, The cloud module also includes: The early warning module is used to determine whether there are any safety hazards in the target watershed based on the water flow parameters. If so, it estimates the scope of the disaster impact and sends early warning information to residents within the disaster impact area.

7. The small watershed flow parameter monitoring system based on cloud-edge collaboration according to claim 1, characterized in that, The information acquisition unit includes a video acquisition device, the feature information includes image information, and the cloud module further includes: The streaming media display module is used to render the acquired image information and push the rendered result to the user terminal via the WebRTC protocol.

8. A method for monitoring water flow parameters in a small watershed based on cloud-edge collaboration, characterized in that, The method includes: To acquire characteristic information of the target watershed; The water flow parameters are calculated based on the aforementioned feature information; the water flow parameters include water level height and flow velocity. Obtain weather information for a future scheduled time period; Based on the meteorological information, the priority of collecting feature information of each river basin within a predetermined time period in the future is determined, and the feature information collected first is processed first; wherein, within the predetermined time period in the future, the higher the priority of feature information collection, the higher the frequency of feature information collection for the corresponding river basin.

9. The method for monitoring small watershed flow parameters based on cloud-edge collaboration according to claim 8, characterized in that, The meteorological information includes rainfall; the step of determining the priority of collecting characteristic information of each river basin within a predetermined future time period based on the meteorological information includes: Watersheds with rainfall R within the range of 0 ≤ R < a are designated as non-priority watersheds for data collection. Watersheds with rainfall R within the range of a≤R<b are designated as Level I priority watersheds for data collection. Watersheds with rainfall R within the range of b≤R are designated as Level II priority watersheds for data collection. Among them, the collection frequency of feature information of the Class II priority collection basin is higher than that of the Class I priority collection basin, and the collection frequency of feature information of the Class I priority collection basin is higher than that of the non-priority collection basin.

10. The method for monitoring small watershed flow parameters based on cloud-edge collaboration according to claim 8, characterized in that, The method further includes: Monitor the operational status of each information collection unit to ensure it is functioning properly; If so, the first algorithm model is used to calculate the flow parameters; otherwise, the second algorithm model is used to calculate the flow parameters. Monitor the load status of each computing unit; the load status includes light load and overload. The computing unit with a light load status is invoked to assist the computing unit with an overload status in processing data.

Images