Water conservancy project scheduling and water resource allocation method and system based on knowledge graph

Abstract

The invention relates to the technical field of data intelligent analysis, in particular to a water conservancy project scheduling and water resource allocation method and system based on a knowledge graph, and the method comprises the steps: collecting and integrating the multi-source heterogeneous data of a water conservancy project according to a water conservancy project monitoring module; establishing a time correction model based on an operation mode of the hydraulic engineering monitoring module, and correcting time nodes of the multi-source heterogeneous data to obtain hydraulic engineering multi-source data after time correction; constructing a knowledge graph processing system of the water conservancy project data according to a knowledge graph method, and processing the water conservancy project multi-source data after time correction by using the system to obtain knowledge structure information of the water conservancy project; and analyzing a hydraulic engineering scheduling scheme and a water resource allocation condition according to the knowledge structure information so as to realize scientific regulation and efficient operation of hydraulic engineering scheduling and water resource allocation. The water conservancy project is managed and controlled based on the knowledge graph, and intelligent, efficient and sustainable development of the water conservancy project is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data intelligent analysis, and specifically to a method and system for water conservancy project scheduling and water resource allocation based on a knowledge graph. Background Art

[0002] With the development of information technology, the traditional methods for water conservancy project scheduling and water resource allocation are difficult to meet the management requirements of modern water conservancy projects. The traditional scheduling methods mainly rely on manual experience and historical data, lacking scientificity and accuracy, and are difficult to cope with the complex and changeable water conservancy project environment. At the same time, water resource allocation also faces problems such as uneven distribution of water resources, diverse water use demands, and deterioration of water environment.

[0003] With the rise of technologies such as big data and artificial intelligence, data intelligent analysis technology has gradually been applied in the field of water conservancy projects. Data intelligent analysis technology can process and analyze a large amount of multi-source heterogeneous data, extract valuable information from it, and provide decision-making support for the scheduling of water conservancy projects and water resource allocation.

[0004] Therefore, it is necessary to introduce a knowledge graph to intelligently organize and analyze the entity, attribute, and relationship information in water conservancy projects, form a water conservancy project knowledge graph and structured information, which is not only conducive to the storage and query of project data, but also can discover the potential relationships and rules between different data through knowledge reasoning and mining, conducive to solving the problems existing in the prior art, improving the scientificity and feasibility of water conservancy project scheduling and water resource allocation, and thus promoting the intelligent management and scientific allocation of water conservancy projects. Summary of the Invention

[0005] In view of the deficiencies of existing methods and the requirements of practical applications, in order to overcome the limitations of the existing technology, comprehensively analyze the influence relationships and variation laws among data in water conservancy projects, enhance the decision-making ability and implementation level of water conservancy project scheduling and water resource allocation, and accelerate the scientific adjustment and intelligent management of water conservancy projects. On the one hand, the present invention provides a method for water conservancy project scheduling and water resource allocation based on a knowledge graph. The method includes: collecting and integrating multi-source heterogeneous data of water conservancy projects according to a water conservancy project monitoring module; establishing a time correction model based on the operation mode of the water conservancy project monitoring module, and using the time correction model to correct the time nodes of the multi-source heterogeneous data to obtain multi-source data of the water conservancy project after time correction; constructing a knowledge graph processing system for water conservancy project data according to the knowledge graph method, and using the knowledge graph processing system to process the multi-source data of the water conservancy project after time correction to obtain the knowledge structure information of the water conservancy project; analyzing the water conservancy project scheduling plan and the water resource allocation status according to the knowledge structure information, and realizing scientific regulation and efficient operation of water conservancy project scheduling and water resource allocation based on the analysis results. The method of the present invention can improve the scientificity and accuracy of water conservancy project scheduling and water resource allocation plans, promote the intelligent management and scientific regulation of water conservancy projects, and provide technical support for the sustainable development of water conservancy projects.

[0006] Optionally, the collecting and integrating multi-source heterogeneous data of water conservancy projects according to the water conservancy project monitoring module includes: collecting historical data, real-time monitoring data and geographic information data of water conservancy projects through the water conservancy project monitoring module; integrating the historical data, the real-time monitoring data and the geographic information data to obtain multi-source heterogeneous data of water conservancy projects. The present invention collects and integrates multi-source heterogeneous data of water conservancy projects according to the water conservancy project monitoring module, which not only improves the comprehensiveness and complementarity of the data, helps to discover the potential relationships and laws among the data, and provides a decision-making basis for the scheduling of water conservancy projects and water resource allocation.

[0007] Optionally, the establishing a time correction model based on the operation mode of the water conservancy project monitoring module includes: analyzing the hardware operation status and software operation characteristics of the water conservancy project monitoring module based on the operation mode of the water conservancy project monitoring module; setting a hardware time correction model according to the hardware operation status; setting a software time correction model according to the software operation characteristics; and obtaining a time correction model by combining the hardware time correction model and the software time correction model. The time correction model of the present invention can correct the time deviation of different devices, ensure the temporal consistency of data from different sources, and thus improve the accuracy and reliability of system data.

[0008] Optionally, the setting a hardware time correction model according to the hardware operation status includes: the hardware time correction model satisfies the following relationship: Among them, represents the hardware calibration time of the water conservancy project monitoring module, represents the local time when the monitoring information arrives at the system database, represents the average communication delay between different time nodes, represents the average delay of receiving monitoring information at different time nodes, represents the weight coefficient of the monitoring module hardware for recording monitoring information, represents the period for the water conservancy project monitoring module to synchronize monitoring information.

[0009] The present invention provides a unified time calibration model, which helps to improve the integration and operability between different hardware devices, and further realizes the data integration and exchange of the water conservancy project monitoring system.

[0010] Optionally, the setting of the software time calibration model according to the software operation characteristics includes: the software time calibration model satisfies the following relationship: Among them, represents the time synchronization analysis model of the water conservancy project monitoring module software, represents the total number of valid time information received by the monitoring module software at different time steps, represents the total number of nodes of the time step of the water conservancy project monitoring module, represents the maximum number of faulty nodes in the water conservancy project monitoring module, represents the minimum number of valid time information required to keep the node time synchronized in the water conservancy project monitoring module.

[0011] The present invention sets the software time calibration model according to the software operation characteristics, which not only enhances the reliability of time synchronization, but also promotes the maintainability and scalability of the system, and helps to ensure the overall performance and stable operation of the water conservancy project monitoring system.

[0012] Optionally, the calibration of the time nodes of the multi-source heterogeneous data by using the time calibration model to obtain the multi-source data of the water conservancy project after time calibration includes: calibrating the time nodes of the multi-source heterogeneous data through the hardware time calibration model, and obtaining the set of time node information after calibration of the water conservancy project; adjusting the software of the water conservancy project monitoring module based on the software time calibration model and the set of time node information to obtain the multi-source data of the water conservancy project after time calibration. The present invention calibrates the time nodes of the multi-source heterogeneous data by using the time calibration model, which can not only improve the time consistency and reliability of the data, but also improve the operation efficiency of the water conservancy project monitoring system.

[0013] Optionally, the knowledge graph processing system for constructing water conservancy project data according to the knowledge graph method includes: establishing a data forgetting analysis function, an input data feature analysis function, and an information output analysis function in the knowledge graph processing system for water conservancy project data according to the knowledge graph method; combining the data forgetting analysis function, the input data feature analysis function, and the information output analysis function to form the knowledge graph processing system for water conservancy project data. The present invention establishes a data forgetting analysis function, an input data feature analysis function, and an information output analysis function according to the knowledge graph method, which can significantly improve the data processing efficiency, enhance the accuracy of data analysis, and improve the intelligent level of water conservancy project management and decision-making.

[0014] Optionally, establishing a data forgetting analysis function, an input data feature analysis function, and an information output analysis function in the knowledge graph processing system for water conservancy project data according to the knowledge graph method includes; The data forgetting analysis function satisfies the following relationship: Where, represents the output result of the data forgetting characteristic analysis, represents the sigmoid function, represents the weight matrix of the data forgetting characteristic analysis function, represents the time step corresponding data hidden state vector, represents the time step current data input vector at, represents the bias term corresponding to the data forgetting characteristic analysis function; The input data feature analysis function satisfies the following relationship: Where, represents the feature analysis result of the input information, represents the sigmoid function, represents the weight matrix corresponding to the input data retention analysis function, represents the time step corresponding data hidden state vector, represents the time step current data input vector at, represents the bias term corresponding to the input data retention analysis function; The information output analysis function satisfies the following relationship: Where, represents the information output result of the water conservancy project, represents the output result of the data forgetting characteristic analysis, Indicates the time step The control state of the data output layer Indicates the feature analysis result of the input information Indicates the weight matrix corresponding to the information output analysis function Indicates the time step The corresponding data hidden state vector Indicates the time step The current data input vector of Indicates the bias term corresponding to the information output analysis function

[0015] The present invention constructs a more perfect and practical water conservancy project data knowledge graph processing system, which helps to apply the knowledge graph technology to the field of water conservancy projects, and further improves the management effect and utilization degree of water conservancy project data.

[0016] Optionally, processing the time-corrected multi-source water conservancy project data by using the knowledge graph processing system to obtain the knowledge structure information of the water conservancy project includes: obtaining the forgotten data result of the water conservancy project through the data forgetting analysis function and the time-corrected multi-source water conservancy project data, and processing the time-corrected multi-source water conservancy project data based on the forgotten data result to obtain the first knowledge structure information of the water conservancy project; obtaining the information feature result of the water conservancy project by using the input data feature analysis function and the time-corrected multi-source water conservancy project data, and obtaining the second knowledge structure information of the water conservancy project based on the information feature result; analyzing the time-corrected multi-source water conservancy project data based on the information output analysis function, the first knowledge structure information and the second knowledge structure information, and obtaining the knowledge structure information of the water conservancy project. The present invention uses the knowledge graph processing system to process the multi-source water conservancy project data, which can improve the pertinence and accuracy of data processing, and enhance the integrity and accuracy of the knowledge structure information.

[0017] In a second aspect, in order to efficiently execute the water conservancy project scheduling and water resource allocation method based on the knowledge graph provided by the present invention, the present invention also provides a water conservancy project scheduling and water resource allocation system based on the knowledge graph. The above system includes an input device, a processor, an output device and a memory. Among them, the input device, the processor, the output device and the memory are interconnected. The memory includes the water conservancy project scheduling and water resource allocation method based on the knowledge graph as described in the first aspect of the present invention. The above memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions. The water conservancy project scheduling and water resource allocation system provided by the present invention has a compact structure and strong applicability, and greatly improves the operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Flow chart of the water conservancy project scheduling and water resource allocation method based on knowledge graph of the present invention; Figure 2 Structural diagram of the water conservancy project scheduling and water resource allocation system based on knowledge graph of the present invention. Detailed implementation manners

[0019] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described here are only for illustrative purposes and are not used to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that the present invention does not have to employ these specific details. In other instances, well-known circuits, software, or methods have not been specifically described in order to avoid obscuring the present invention.

[0020] Throughout the specification, the reference to "one embodiment", "embodiment", "one example" or "example" means that the specific features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the present invention. Thus, the phrases "in one embodiment", "in an embodiment", "one example" or "example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. In addition, the specific features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. In addition, those of ordinary skill in the art should understand that the drawings provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0021] Please refer to Figure 1 , in order to effectively analyze the internal relationships and variation laws of multi-source heterogeneous data in water conservancy projects, dynamically schedule water conservancy projects through intelligent means, improve the scientificity and feasibility of water conservancy project scheduling and water resource allocation, and promote the intelligent management and development of water conservancy projects, the present invention provides a water conservancy project scheduling and water resource allocation method based on knowledge graph. The above method includes the following steps: S1. Collect and integrate the multi-source heterogeneous data of the water conservancy project according to the water conservancy project monitoring module. The specific setting steps and implementation contents are as follows: In the embodiment, historical data, real-time monitoring data, and geographic information data of the water conservancy project are collected through the water conservancy project monitoring module, and then the historical data, real-time monitoring data, and geographic information data are integrated to obtain the multi-source heterogeneous data of the water conservancy project.

[0022] First, the relevant data of water conservancy projects are comprehensively collected through the water conservancy project monitoring module, which mainly includes historical operation records, real-time monitoring information, and geographical information data. The above steps aim to integrate the water conservancy project data from different sources and structures, and then form comprehensive and multi-dimensional multi-source heterogeneous data of water conservancy projects. The above data covers key information such as precipitation, water level changes, flow conditions, meteorological conditions, and engineering structure status of water conservancy projects, providing a data basis for subsequent water conservancy project scheduling and water resource allocation.

[0023] With the wide application of sensor technology, remote sensing technology, and Internet of Things technology, and supported by big data platform technology, it has become a reality to collect and monitor data in real time. The above water conservancy project monitoring module not only has the function of data collection, but also has a built-in self-learning mechanism. By analyzing historical scheduling cases and real-time monitoring information, it continuously optimizes the algorithms and logics of the module itself to adapt to and handle new situations and challenges that are difficult to cover by traditional modules. The dynamic adjustment ability of the module improves the intelligent level and flexibility of water conservancy project scheduling and water resource allocation methods.

[0024] Furthermore, the present invention uses the water conservancy project monitoring module to monitor various objects (such as reservoirs, sluices, rivers, dams, etc.) in water conservancy projects and their attributes and interrelationships, thereby constructing a multi-level and multi-dimensional data information framework. This framework not only includes the physical characteristics of water conservancy projects (water capacity, water level, water flow, etc.), but also reveals the interdependent relationships between different objects (such as upstream and downstream relationships, scheduling control relationships, etc.). The integration of the above multi-dimensional data not only provides data support for the formulation of scheduling rules, but also makes the optimization and adjustment of the scheme more flexible and accurate.

[0025] In addition, the water conservancy project monitoring module integrates multi-source water conservancy data, including but not limited to water conservancy facility information, meteorological data, hydrological data, and historical scheduling records. The water conservancy project monitoring module in the embodiment has the ability of dynamic integration, and can integrate multi-dimensional information such as the status of water conservancy facilities, changes in basin water conditions, and weather forecasts in real time, ensuring that scheduling decisions can quickly respond to external changes and realizing the dynamic monitoring and analysis of the water resource allocation situation. At the same time, the water conservancy project monitoring module also has a knowledge automatic update mechanism: through the self-learning mechanism, it can continuously absorb real-time data and historical experience, and continuously optimize the operation rules and algorithms of the water conservancy project monitoring module to adapt to complex and changeable hydrological, climatic conditions, and disaster situations, which is conducive to ensuring the accuracy of multi-source heterogeneous data of water conservancy projects.

[0026] Finally, the water conservancy project monitoring module of the present invention also has the ability to adjust conflicts among different scheduling objectives. Traditional monitoring modules often focus on a single objective or monitor data based on simple rules, while the water conservancy project monitoring module of the present invention can comprehensively consider multiple scheduling objectives such as water supply guarantee, flood control, irrigation, and ecological protection. Through dynamic monitoring and intelligent adjustment means, it can achieve real-time monitoring and data collection of each objective, which is beneficial to improving the scientific nature of the water conservancy project scheduling plan and providing information support for the efficient and sustainable utilization of water resources.

[0027] Furthermore, the method for obtaining multi-source heterogeneous data of water conservancy projects in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the method for obtaining multi-source heterogeneous data of water conservancy projects can be replaced and optimized according to the actual operation status of water conservancy projects and the acquisition requirements of multi-source data, which helps to select the most suitable data acquisition means and can flexibly cope with the challenges brought by environmental changes, ensuring the accuracy and practicality of water conservancy project data.

[0028] S2. Establish a time correction model based on the operation mode of the water conservancy project monitoring module, and use the time correction model to correct the time nodes of multi-source heterogeneous data to obtain the multi-source data of the water conservancy project after time correction. The specific steps and implementation contents are as follows: Analyze the hardware operation status and software operation characteristics of the water conservancy project monitoring module based on its operation mode.

[0029] I. Analysis of hardware operation status The water conservancy project monitoring module is equipped with various types of sensors, such as water level sensors, flow sensors, water quality sensors, stress sensors, etc. The above sensors are distributed in each key part of the water conservancy project to collect key data such as water level, flow, water quality, and structural stress in real time.

[0030] The data acquisition device is responsible for converting the analog signals collected by the sensors into digital signals and transmitting them to the data monitoring center of the water conservancy project monitoring module by wired or wireless means. The stability and accuracy of the hardware device directly affect the accuracy and reliability of the data acquisition results.

[0031] The integration of the water conservancy project monitoring module and the automation control system realizes the remote monitoring and control of automation equipment. Through the monitoring module, the operation status of system equipment can be understood in real time, and faults can be discovered and processed in time, which is beneficial to the normal operation of the water conservancy project.

[0032] In the hardware device management system of water conservancy projects, in order to comprehensively monitor and analyze the operating status of each device, n time acquisition nodes are set for each piece of hardware device. The above-mentioned time acquisition nodes refer to the timestamps of device operation, which record the working status and operation information of the device at different times. By combining the above time acquisition nodes, the time node information set of the water conservancy project hardware can be obtained. This time node information set not only covers the operating conditions of the device at each time point, but also meets the specific requirements of the water conservancy project for the time nodes of hardware devices, providing data support for the operation and maintenance management, fault troubleshooting, and performance optimization of water conservancy projects.

[0033] Furthermore, the time node information set of the water conservancy project hardware satisfies the following relationship; Among them, represents the time acquisition node of the hardware of the water conservancy project monitoring module, represents the 1st time acquisition node of the hardware of the water conservancy project monitoring module, represents the 2nd time acquisition node of the hardware of the water conservancy project monitoring module, represents the nth time acquisition node of the hardware of the water conservancy project monitoring module.

[0034] II. Analysis of Software Operation Characteristics The data acquisition software is responsible for real-time acquiring data from sensors and data acquisition devices and performing preliminary processing, such as data cleaning, denoising, format conversion, etc. The acquired data needs to be stored in the database of the water conservancy project monitoring module for subsequent analysis and use. The selection and management of the database directly affect the integrity and security of the data. At the same time, the water conservancy project monitoring module uses data analysis software to analyze the acquired data, extract valuable information, and visually display the multi-source heterogeneous data in the form of charts through visualization technology, facilitating managers to understand and monitor in real time.

[0035] The hardware and software in the water conservancy project monitoring module can work together.

[0036] Ensure a good interface between the hardware device and the software system, guarantee the effective transmission and interaction of the water conservancy project monitoring data, and organically combine the hardware device and the software system through module integration technology to form a complete monitoring system. At the same time, the water conservancy project monitoring module can be optimized and adjusted according to actual needs, further improving the overall performance and operation efficiency of the monitoring module.

[0037] Comprehensively analyzing the hardware operating conditions and software operation characteristics of the water conservancy project monitoring module helps to ensure the effective operation and scientific adjustment of the water conservancy project monitoring module, providing guarantee for the safe and efficient operation of water conservancy projects.

[0038] Then, a hardware time correction model was set according to the operating conditions of the hardware.

[0039] In this embodiment, a hardware time correction model was constructed based on the actual operating conditions of the hardware device. This model comprehensively considered various delay factors that the monitoring information might encounter during the transmission process, and also took into account the characteristics of the hardware device when recording the monitoring information and synchronization information, providing a benchmark for the hardware device correction of the water conservancy project monitoring module. This hardware time correction model can be used to analyze and calculate the hardware correction time of the water conservancy project monitoring module.

[0040] The above-mentioned hardware time correction model satisfies the following relationship: Where, represents the hardware correction time of the water conservancy project monitoring module, represents the local time when the monitoring information reaches the system database, represents the average communication delay between different time nodes, represents the average delay of receiving the monitoring information at different time nodes, represents the weight coefficient of the monitoring module hardware for recording the monitoring information, represents the period for the water conservancy project monitoring module to synchronize the monitoring information.

[0041] The hardware correction time is used to correct the time deviation of the monitoring information caused by factors such as hardware devices and communication delays in the water conservancy project monitoring module. Through correction, more accurate and reliable water conservancy project information can be obtained.

[0042] The local time when the monitoring information reaches the system database refers to the time point when the monitoring information actually reaches the database. The monitoring information will be affected by factors such as network delay and device processing speed during the transmission process. Therefore, the transmission and generation times of the monitoring information of different hardware devices are all different.

[0043] The average communication delay between different time nodes refers to that during the transmission process of the monitoring information, due to factors such as network conditions and device performance, there will be a certain delay in the transmission of information between different time nodes. Quantifying and analyzing the average value of the above communication delay can be used to correct the time node information of the hardware device.

[0044] The average delay of receiving the monitoring information at different time nodes refers to that when the monitoring information reaches a certain time node (such as a sensor or a collector), this node needs a certain amount of time to process and record the relevant information. In the embodiment, the average value of the processing and recording delay was quantified.

[0045] The weight coefficient for the monitoring module's hardware to record monitoring information refers to the fact that when different hardware devices record monitoring information, due to factors such as their performance, accuracy, and external conditions, there are certain errors or deviations in the recorded information. The above weight coefficient is used to adjust the impact of the error or deviation on the hardware correction time. Its size depends on factors such as the performance and accuracy of the hardware device and the importance of the monitoring information.

[0046] The period for the water conservancy project monitoring module to synchronize monitoring information refers to that in order to ensure the accuracy and real-time nature of the monitoring information, the water conservancy project monitoring module will regularly synchronize the monitoring information. In the hardware time correction model, the impact of the synchronization period on the hardware correction time is considered comprehensively through the information synchronization period and the weight coefficient.

[0047] The above hardware time correction model takes into account various delay factors during the transmission of monitoring information and the characteristics of the hardware-recorded information and synchronized information, providing an accurate and reliable basis for the hardware time correction of the water conservancy project monitoring module, and further ensuring the credibility of the water conservancy project monitoring module.

[0048] At the same time, a software time correction model is set according to the software operation characteristics.

[0049] In order to ensure that the software records or processes information to be consistent with the actual monitoring time information and improve the accuracy and reliability of the water conservancy project monitoring data, in the embodiment, the water conservancy project monitoring information recorded and processed by the software is analyzed according to the software operation characteristics, and further factors such as effective time information, node information, faulty nodes, and least significant time information are considered to evaluate and adjust the deviation between the software-recorded or processed time and the actual time, which helps to ensure that the time information of each node in the module is consistent and improve the accuracy of the water conservancy project monitoring data.

[0050] The software time correction model needs to comprehensively consider various factors to improve the accuracy of time synchronization, enhance the fault tolerance of the system, and improve the stability and reliability of the system. The above software time correction model satisfies the following relationship: Among them, represents the time synchronization analysis model of the water conservancy project monitoring module software, represents the total number of effective time information received by the monitoring module software at different time steps, represents the total number of nodes in the time step of the water conservancy project monitoring module, represents the maximum number of faulty nodes in the water conservancy project monitoring module, represents the minimum number of effective time information required to maintain node time synchronization in the water conservancy project monitoring module.

[0051] The time synchronization analysis model of the above-mentioned water conservancy project monitoring module software is used to analyze the deviation between the time recorded or processed by the software and the actual time, especially its performance in time synchronization. The time synchronization analysis model can analyze the time deviation or correction amount during the software synchronization process.

[0052] The total number of valid time information received by the monitoring module software at different time steps refers to that in the water conservancy project monitoring module, the software will receive time information from each monitoring node at different time steps (or time nodes), where the parameter is the total number of valid time information, which reflects the time information that the software can obtain at the current time step.

[0053] The total number of nodes in the time step of the water conservancy project monitoring module refers to the total number of all time steps (or time nodes) in the system, which represents the breadth and granularity of the monitoring module. In water conservancy project monitoring, the size of the total number of nodes depends on factors such as the division of the monitoring area, the layout of monitoring equipment, and the setting of monitoring frequency.

[0054] The maximum number of faulty nodes in the water conservancy project monitoring module refers to the maximum number of faulty nodes allowed in the monitoring system. Due to equipment failures, communication interruptions, etc., some monitoring nodes cannot work properly or provide valid time information. It reflects the tolerance ability of the system module to faulty nodes.

[0055] The minimum number of valid time information refers to the number of valid time information received by the system module to achieve time synchronization between different nodes. The minimum number of valid time information reflects the degree of demand of the system module for time synchronization information.

[0056] Based on the analysis of the software time correction model, when the total number of valid time information reaches or exceeds the threshold of the total number of nodes minus the maximum number of faulty nodes, and does not exceed the upper limit set by the minimum number of valid time information required to maintain time synchronization, it indicates that the number of valid time information received is sufficient, which can ensure the reliability of time synchronization and will not exceed the processing capacity range of the module software.

[0057] Based on the software analysis model to evaluate the performance of the software in time synchronization, when the number of valid time information received is sufficient and the number of system faulty nodes is within an acceptable range, the software can accurately perform time synchronization; otherwise, time correction or other measures need to be taken to ensure the accuracy of time information.

[0058] In this embodiment, the time correction model is obtained by combining the above-mentioned hardware time correction model and software time correction model.

[0059] First, the hardware time correction model is used to correct the time nodes of multi-source heterogeneous data, and the set of time node information after correction for the water conservancy project is obtained; Based on the above, the set of time node information of the water conservancy project hardware satisfies the following relationship; Among them, represents the time acquisition node of the water conservancy project monitoring module hardware, represents the first time acquisition node of the water conservancy project monitoring module hardware, represents the second time acquisition node of the water conservancy project monitoring module hardware, represents the nth time acquisition node of the water conservancy project monitoring module hardware.

[0060] Based on the hardware time correction model in the embodiment: and the set of time node information of the water conservancy project hardware, further analyze the hardware correction time of the water conservancy project monitoring module.

[0061] The hardware correction time model of the water conservancy project monitoring module can comprehensively consider the actual monitoring time, hardware system, data transmission, and hardware time deviation caused by environmental factors and hardware characteristic parameters. The hardware time correction model in the embodiment is expressed as the following relationship: , by comprehensively analyzing the set of time node information of the water conservancy project hardware, the hardware correction time of the monitoring module can be accurately calculated, thereby ensuring the accuracy and timeliness of the water conservancy project data.

[0062] The set of time node information after correction for the water conservancy project satisfies the following relationship; Among them, represents the time acquisition node of the optimized water conservancy project, represents the first time acquisition node of the water conservancy project, represents the second time acquisition node of the water conservancy project, represents the nth time acquisition node of the water conservancy project, represents the correction time of the system hardware, represents the first time acquisition node of the optimized water conservancy project, represents the second time acquisition node of the optimized water conservancy project, represents the nth time acquisition node of the optimized water conservancy project.

[0063] Calibrating the original time acquisition nodes through the hardware time calibration model can eliminate the hardware time deviation caused by the hardware system, data transmission, environmental factors, and hardware characteristic parameters, thereby ensuring the accuracy of different time acquisition nodes and improving the reliability of the monitoring data for the entire water conservancy project. At the same time, the calibrated time node information set reflects more real and accurate time information, which helps to detect and handle abnormal situations in the water conservancy project in a timely manner, and improves the response speed and timeliness of the water conservancy project monitoring module.

[0064] Then, adjust the software of the water conservancy project monitoring module based on the software time calibration model and the time node information set to obtain the multi-source data of the water conservancy project after time calibration.

[0065] Adjust and optimize the system hardware and software based on the hardware time calibration model and the software time calibration model in the time synchronization analysis model. Based on the optimized time node information set of the water conservancy project, further analyze the time step set of the optimized water conservancy project, and satisfy the following relationship: Among them, represents the time step set of the optimized water conservancy project, represents the first time step of the optimized water conservancy project, represents the second time step of the optimized water conservancy project, represents the m-th time step of the optimized water conservancy project.

[0066] The above represents the first time step of the optimized water conservancy project: Among them, represents the first time step of the optimized water conservancy project, represents the first time acquisition node of the optimized water conservancy project, represents the initial acquisition node of the water conservancy project.

[0067] represents the second time step of the optimized water conservancy project: Among them, represents the second time step of the optimized water conservancy project, represents the second time acquisition node of the optimized water conservancy project, represents the first time acquisition node of the optimized water conservancy project.

[0068] represents the m-th time step of the optimized water conservancy project: Among them, represents the m-th time step after the optimization of the water conservancy project, represents the n-th time acquisition node of the optimized water conservancy project, represents the (n - 1)-th time acquisition node of the optimized water conservancy project.

[0069] In this embodiment, the hardware time correction model and the software time correction model can eliminate the errors in time synchronization, ensure the accuracy of each time acquisition node, help obtain more accurate hydrological data, equipment operation parameters, etc., and provide a reliable basis for project operation and water resource allocation. On the other hand, the optimized system hardware and software can process time synchronization information faster, improve the response speed of the system, and can respond faster in occasions that require fast response, such as flood warning, water quality monitoring, etc., reduce losses, and thus significantly improve the operation efficiency of the water conservancy project.

[0070] Based on the time step set of the optimized water conservancy project and the multi-source heterogeneous data of the water conservancy project, the data information corresponding to different time steps can be matched, that is, the water conservancy project detection information set is obtained, and the following relationship is satisfied: Among them, represents the water conservancy project detection information set, represents the water conservancy project corresponding detection information, represents the water conservancy project corresponding detection information, represents the water conservancy project corresponding detection information.

[0071] In this embodiment, each time step is matched with the corresponding data information, so as to obtain a comprehensive water conservancy project detection information set. The above detection information set is composed of detection information corresponding to a series of time steps, that is, for each time step, there is a unique detection information corresponding to it.

[0072] Matching each time step with the corresponding detection information can form a structured data management system. The above method helps in data sorting, storage, and query, improves the efficiency and accuracy of water conservancy project data management. The matched detection information set can clearly display the information situation of each time step, making the data source, change process, and current status traceable, which is beneficial to the operation and maintenance, fault troubleshooting, and decision support of the water conservancy project.

[0073] Furthermore, the analysis method and acquisition steps of the water conservancy project detection information set in this embodiment are only an optional condition of the present invention. In one or some other embodiments, the analysis and acquisition methods of the water conservancy project detection information set can be optimized according to the actual monitoring situation of the water conservancy project and the information processing requirements of the water conservancy project detection. Optimizing the information processing method based on the characteristics and requirements of the water conservancy project can analyze the detection data more accurately, reduce errors and misjudgments, and thus ensure the feasibility of the overall water conservancy project scheduling and water resource allocation method.

[0074] S3. Construct a knowledge graph processing system for water conservancy project data according to the knowledge graph method, and use the knowledge graph processing system to process the multi-source data of the water conservancy project after time correction to obtain the knowledge structure information of the water conservancy project. The specific implementation content is as follows: First, a data forgetting analysis function, an input data feature analysis function, and an information output analysis function are established in the knowledge graph processing system of the water conservancy project data according to the knowledge graph method; and then the above data forgetting analysis function, input data feature analysis function, and information output analysis function are combined to form the knowledge graph processing system of the water conservancy project data.

[0075] Based on the memory network method, it is known that in the long short-term memory network (LSTM), the forget gate calculates a linear combination based on the previous hidden state and the current input to generate a weight vector. The above weight vector is then passed to a sigmoid function, and the forget gate function maps it to a numerical range between 0 and 1.

[0076] The vector after the above mapping is called the forget vector. Each element in it corresponds to a position information in the cell state. When the element value of the forget vector is close to 0, it means that this position information is largely forgotten; while when the element value is close to 1, it means that this position information can be retained. Through the forget gate of the long short-term memory network, it can intelligently identify and discard the information that is no longer important or has become obsolete for the current task, so as to focus on storing and processing more valuable information content.

[0077] Therefore, the forget gate in the long short-term memory network not only helps the LSTM network avoid the problem of gradient disappearance or explosion when processing long sequence data, but also improves the model's processing ability and generalization performance for time series data. By regulating the update process of the cell state, the forget gate provides a mechanism for the LSTM network to adapt to the changing data environment.

[0078] The operating principle of the forget gate in the long short-term memory network (LSTM) is combined with the multi-source data of the water conservancy project after time correction to construct a data forgetting analysis function in the knowledge graph processing system. The specific form of the function satisfies the following relationship: where represents the output result of the data forgetting characteristic analysis, represents the sigmoid function, represents the weight matrix of the data forgetting characteristic analysis function, represents the time step corresponding data hidden state vector, represents the time step current data input vector, represents the bias term corresponding to the data forgetting characteristic analysis function; According to the output result obtained from the forgetting characteristic analysis, it reflects the part of the multi-source data of the water conservancy project that is forgotten or retained at time step m. That is, at time step m of the water conservancy project, the forget gate calculates the degree of forgotten or retained information based on the previous hidden state and the current input data, and the sigmoid function determines to output a value (or vector) between 0 and 1. A value close to 0 indicates that the water conservancy project information should be forgotten, and a value close to 1 indicates that the water conservancy project information can be retained.

[0079] The sigmoid function is an activation function that maps the result of the linear combination to between 0 and 1. The data forgetting analysis function converts the result after the weight matrix and the input vector, plus the bias term, into the probability of forgotten or retained information.

[0080] The weight matrix of the data forgetting characteristic analysis function. The above weight matrix is a learned matrix that can be used to determine the relative importance of the previous hidden state and the current input data. Through the dot product with the input vector, it helps the data forgetting analysis function to adjust the degree of forgotten or retained information according to the specific characteristics of the data.

[0081] The data hidden state vector corresponding to time step m - 1 contains the hidden state at time step m - 1, and also contains the information and state of the previous time steps. As one of the inputs of the data forgetting analysis function, it helps the data forgetting analysis function to remember or forget the previous water conservancy project information The current data input vector at time step m introduces new data information to update the hidden state and cell state. The new data input into the knowledge graph processing system at the current time step m, together with the previous hidden state, serves as the input of the forget gate, which helps the function to adjust the degree of forgotten or retained previous information according to the new information.

[0082] The bias term corresponding to the data forgetting characteristic analysis function can be used to adjust the output of the data forgetting analysis function to adapt it to different water conservancy project datasets and management tasks. It is beneficial for the data forgetting analysis function to have a basic degree of forgetting or retaining information even without any input, and can be automatically fine-tuned according to the specific characteristics of water conservancy project data.

[0083] In the embodiment, the intelligent forgetting mechanism of the forgetting gate in the LSTM is fully utilized, enabling the data forgetting analysis function to adaptively adjust the degree of forgetting and retaining of water conservancy project information according to the dynamic changes of multi-source data in water conservancy projects. It can not only handle the temporal dependence and noise problems existing in water conservancy project data, but also improve the accuracy and robustness of the knowledge graph processing system. At the same time, through the input of multi-source data after time correction, a richer and more accurate information source is provided for the data forgetting analysis function, enabling it to better capture the key features and trends in the data, thereby providing technical support for the management of water conservancy projects and the allocation of water resources.

[0084] The operating mechanism of the input gate in the long short-term memory network (LSTM) is as follows: The input gate is one of the mechanisms for the LSTM to solve the long-term dependence problem. By controlling the inflow of new information, the input gate helps the network remember the previous input information and use relevant information in the current output. Based on the existing technology, it is known that the input gate consists of two parts: a sigmoid layer and a tanh layer. The sigmoid layer outputs a value between 0 and 1, which is used to determine which information is updated into the memory cell; the tanh layer generates a new candidate value vector, and the above vector contains new state information. Multiply the output of the sigmoid layer (referred to as the input gate) by the candidate value vector generated by the tanh layer, which then represents the degree to which the new information is accepted by the memory cell. A value close to 1 indicates that the information is almost completely accepted, while a value close to 0 indicates that the information is almost ignored.

[0085] In the embodiment, an input data feature analysis function in the knowledge graph processing system is constructed based on the operating principle of the input gate and the multi-source data of the water conservancy project after time correction.

[0086] By utilizing the operating principle of the input gate and fusing it with the multi-source data of the water conservancy project after time correction, an input data feature analysis function in the knowledge graph processing system is constructed, and it satisfies the following relationship: Among them, represents the feature analysis result of the input information, represents the sigmoid function, represents the weight matrix corresponding to the input data retention analysis function, represents the time step represents the corresponding data hidden state vector, Represents the time step of the current data input vector, represents the bias term corresponding to the input data retention analysis function; The feature analysis result of the input information is a value (or vector) between 0 and 1, which reflects the degree to which the features of the newly input data can be retained at the current time step m. The above value close to 1 indicates that the water conservancy project features at this time step can be retained; a value close to 0 indicates that the water conservancy project features at this time step should be retained weakly or ignored. At time step m, the input data feature analysis function calculates the degree to which new information is retained based on the previous hidden state and the current input data, and the final output is a value (or vector) between 0 and 1, where the closer to 1 indicates that the water conservancy project information at this time step can be retained, and the closer to 0 indicates that the water conservancy project information at this time step should be retained weakly or ignored.

[0087] The weight matrix corresponding to the input data retention analysis function can be obtained through the learning process, which determines the relative importance of the previous hidden state and the current input data in the input gate calculation. It is the key to judging the degree of feature retention and helps the input data retention analysis function adjust the degree of new information retention.

[0088] The bias term corresponding to the input data retention analysis function is a constant (or vector), which can adjust the output result of the input data retention analysis function, so that the knowledge graph processing system has a basic degree of new information retention even without any input, and can be adjusted and managed according to the specific characteristics of different water conservancy project data.

[0089] In the embodiment, the retention mechanism of the LSTM input gate is utilized, enabling it to adaptively adjust the retention degree of the newly input data features according to the dynamic changes of the time-corrected multi-source data of the water conservancy project. Therefore, it not only helps to handle the possible temporal dependence and noise problems in the water conservancy project data, but also improves the sensitivity and accuracy of the knowledge graph processing system to the input data. At the same time, through the input of time-corrected multi-source data, it provides a more abundant and accurate information source for the knowledge graph processing system, enabling it to better capture the key features and trends in different water conservancy project data, and providing knowledge graph information support for the decision-making and scientific management of water conservancy projects.

[0090] The operating mechanism of the output gate in the long short-term memory network (LSTM) mainly depends on the design of the gating mechanism and the cell state. LSTM effectively stores, updates, and forgets information by introducing the forget gate, input gate, output gate, and cell state, thereby being able to handle the long-term dependence relationships in long sequence data.

[0091] The output gate can determine the output of information from the cell state to the current hidden state, output a value between 0 and 1 through an activation function to control the proportion of the output information. At the same time, the cell state is processed through the tanh activation function to obtain the final hidden state output result.

[0092] In the embodiment, the output gate mechanism in the long short-term memory network (LSTM) is fused with the time-corrected multi-source data of the water conservancy project to construct an information output analysis function in the knowledge graph processing system. This analysis function can output the current hidden state at each time step, thus providing strong support for the prediction task and regulation plan of the water conservancy project. The information output analysis function in the embodiment follows a specific relational logic to ensure the accurate transmission and processing of information.

[0093] The above information output analysis function satisfies the following relationship: Wherein, represents the information output result of the water conservancy project, represents the output result of the data forgetting characteristic analysis, represents the time step the control state of the data output layer, represents the feature analysis result of the input information, represents the weight matrix corresponding to the information output analysis function, represents the time step the corresponding data hidden state vector, represents the time step the current data input vector of represents the bias term corresponding to the information output analysis function.

[0094] The information output result of the water conservancy project, that is, the output of the information output analysis function at different time steps m, provides an information representation of the water conservancy project state at the current time step, and can be used in subsequent tasks such as water conservancy project prediction, disaster analysis, and resource scheduling.

[0095] The control state of the data output layer at time step m - 1 is a factor that controls or regulates the information output analysis function, and controls the information flow at the current time step by adjusting the output state of the previous time step.

[0096] The weight matrix corresponding to the information output analysis function can perform a linear transformation on the input vector. Through the weight matrix, the function can perform weighted processing on the input data to extract the information that has an important impact on the output result.

[0097] The bias term corresponding to the information output analysis function is a constant term, which is used to adjust the average value of the output result. The bias term function can shift the output result as a whole without changing the input data, thereby adapting to the data distribution and engineering scheduling requirements of different water conservancy projects.

[0098] The information output analysis function comprehensively considers the forgetting characteristic output results, time step control state, time step input vector, weight matrix and bias term, and calculates the information output results of the water conservancy project at different time steps, providing key information for subsequent water conservancy project scheduling and water resources analysis.

[0099] Furthermore, the knowledge graph processing system is used to process the time-corrected multi-source data of water conservancy projects to obtain the knowledge structure information of water conservancy projects.

[0100] Firstly, the forgotten data results of water conservancy projects are obtained through the data forgetting analysis function and the multi-source data of water conservancy projects after time correction. Based on the above forgotten data results, the multi-source data of water conservancy projects after time correction are processed to obtain the first knowledge structure information of water conservancy projects. Then, the information feature results of the water conservancy project are obtained by using the input data feature analysis function and the multi-source data of the water conservancy project after time correction, and the second knowledge structure information of the water conservancy project is obtained based on the above information feature results; Finally, the time-corrected multi-source data of the water conservancy project are analyzed based on the information output analysis function, the first knowledge structure information and the second knowledge structure information, so as to obtain the knowledge structure information of the water conservancy project.

[0101] In an optional embodiment, the method for water conservancy project scheduling and water resources allocation based on knowledge graph systematically processes the time-corrected multi-source data of water conservancy projects in the knowledge graph processing system to extract the knowledge structure information of water conservancy projects. The relevant processing process can be divided into three main operation steps: Firstly, the data forgetting analysis function is used in combination with the multi-source data of water conservancy projects after time correction to calculate the forgotten data results of water conservancy projects. This result reflects the forgotten or ignored parts of the multi-source data of water conservancy projects in different time steps. Based on the above results, the original water conservancy project data is processed and optimized, and the corresponding part of the data information is eliminated based on the forgetting characteristic output result, thereby obtaining the first knowledge structure information of the water conservancy project.

[0102] Next, the information feature results of the water conservancy projects were analyzed by combining the input data feature analysis function with the time-corrected multi-source data of the water conservancy projects. The above results revealed the key characteristics and change patterns of the water conservancy project data. The first knowledge structure information was screened and analyzed based on the relevant characteristics, and the second knowledge structure information of the water conservancy projects was further obtained.

[0103] Finally, by combining the information output analysis function, the first knowledge structure information, and the second knowledge structure information, a comprehensive analysis of the multi-source data of the water conservancy project is carried out, and finally the complete knowledge structure information of the water conservancy project is obtained.

[0104] Furthermore, the analysis method of the water conservancy project knowledge structure information in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the analysis method of the water conservancy project knowledge structure information can be adjusted according to the time scheduling and disaster prediction requirements of the water conservancy project. The time scheduling and disaster prediction of the water conservancy project change with the actual situation, and a flexible analysis method is provided, enabling the present invention to adapt to the specific needs of different water conservancy projects and improving the flexibility and applicability of the water conservancy project scheduling and water resource allocation method.

[0105] S4. Analyze the water conservancy project scheduling plan and water resource allocation status based on the knowledge structure information, and realize the scientific regulation and efficient operation of the water conservancy project scheduling and water resource allocation based on the analysis results. The specific implementation content is as follows: The water conservancy project scheduling and water resource allocation method based on the knowledge graph further includes configuring a water conservancy project scheduling and water resource allocation module. By relying on the knowledge graph technology, the above-mentioned module can realize the scientific and precise regulation of the water conservancy project scheduling and water resource allocation, as well as the efficient and stable operation management. The relevant implementation content is as follows: I. Comprehensive evaluation and optimization of water conservancy project scheduling Conducting a comprehensive and systematic evaluation of the water conservancy project scheduling is a key step to ensure the scientificity and rationality of the scheduling strategy. During the implementation process, the water conservancy project monitoring module uses big data technology to collect and analyze multi-source data such as hydrology and meteorology in real time and accurately. The relevant data is the basis for the water conservancy project scheduling decision-making and plays an important role in grasping the operation status of the water conservancy project and predicting future trends.

[0106] To make more effective use of the multi-source data of the water conservancy project, a knowledge graph processing system is introduced in the embodiment. The above system can perform structured analysis and processing on the multi-source data of the water conservancy project, excavate the correlation and regularity between the water conservancy project data, and thus form the knowledge structure information of the water conservancy project. This information provides support for the project scheduling decision-making and enables a more comprehensive understanding of the operation status and risk situation of the water conservancy project.

[0107] In the embodiments, by integrating knowledge graph technology and a big data platform, dynamic analysis is performed on real-time data and historical disaster data of water conservancy projects. Through the monitoring and analysis of real-time data, abnormal situations or potential risk factors existing in the operation of water conservancy projects can be discovered in a timely manner. At the same time, by tracing back and analyzing historical disaster data, the occurrence laws and changing characteristics of different water conservancy project disasters can be summarized, thereby providing a reference basis for the scheduling and plan decision-making of water conservancy projects.

[0108] The method for water conservancy project scheduling and water resource allocation based on a knowledge graph not only improves the accuracy and timeliness of risk assessment but also enables the rapid formulation of emergency plans. When a disaster risk occurs, corresponding scheduling measures can be quickly taken according to the plan, reducing the impact of the disaster on water resource management. At the same time, the formulation and implementation process of the plan also provide experience and data support for post-disaster review and scheduling optimization.

[0109] Furthermore, the intelligentization of disaster risk assessment and emergency response is realized. The method for water conservancy project scheduling and water resource allocation can perceive and evaluate disaster risks such as floods and droughts in real time. According to the risk level and disaster type, corresponding scheduling plans can be quickly formulated. The relevant plans not only consider the current operation status of water conservancy projects but also can predict future disaster trends, ensuring the scientific nature and forward-looking nature of scheduling decisions.

[0110] In addition, by tracing back and analyzing historical data and emergency plans, water conservancy project scheduling and water resource allocation can also help decision-makers conduct post-disaster review and summary. The differences between the actual scheduling effect and the plan can be compared, the reasons can be analyzed, and lessons can be summarized, providing a more perfect plan and suggestions for future scheduling decisions, and further optimizing the scheduling strategy and improving the scheduling efficiency.

[0111] II. Scientific and Precise Water Resource Allocation Water resource scheduling should not only consider the quantity allocation of water resources but also take into account multiple objectives such as water quality safety, water ecological protection, and ecological restoration. These different objectives are intertwined and mutually influential, forming the complex characteristics of multiple objectives and multiple constraints. In the case of limited water resources, it is necessary to balance the conflicts between various objectives and optimize resource allocation. When dealing with extreme hydrological events such as floods, water resource scheduling needs to consider multiple objectives such as flood control, water supply, and ecological protection simultaneously, and timely and accurate adjustments must be made in water resource scheduling to ensure the balance and coordination of various objectives.

[0112] To achieve the scientific and precise water resource scheduling, it is based on the water conservancy project scheduling and water resource allocation module in the embodiments and fully relies on the knowledge graph technology. The above module utilizes the water conservancy project knowledge structure information in the knowledge graph processing system to conduct intelligent scheduling of water resources. By integrating and correlating multi-dimensional information such as water conservancy project facilities, scheduling rules, hydrological information, meteorological conditions, and historical scheduling data within the basin, a comprehensive and accurate water resource scheduling knowledge base is constructed.

[0113] The above knowledge base not only contains various basic information on water resource scheduling but also reveals various relationships and potential laws in water resource scheduling. Through the analysis and mining of different relationships and change laws, it can provide accurate and reliable knowledge support for scheduling decisions, which helps to match reasonable water resource allocation plans and adjustment measures when dealing with extreme hydrological events.

[0114] In addition, the water resource scheduling method based on the knowledge graph also has high flexibility and scalability. It can flexibly adjust scheduling strategies and evaluation parameters according to the actual needs and environmental conditions of different water conservancy projects to adapt to the water resource scheduling needs and actual environmental scenarios of different water conservancy projects. At the same time, it can continuously learn and update the content in the water conservancy project knowledge base to adapt to the changes in water resource scheduling.

[0115] In summary, the water resource allocation method based on the knowledge graph not only realizes the scientific and precise water resource scheduling but also improves the efficiency and stability of water resource scheduling, provides strong technical support and decision-making basis for water resource management, and thus promotes the continuous development and progress of water resource scheduling methods.

[0116] III. Development and Application of Intelligent Scheduling Technology The water conservancy project scheduling and water resource allocation method based on the knowledge graph further introduces digital twin and virtual simulation technologies to provide technical support for water conservancy project scheduling and water resource allocation.

[0117] Digital twin technology is an advanced digital means that can accurately reproduce the actual situations of different water conservancy projects and basin scheduling in a virtual environment. It can comprehensively, real-timely, and dynamically map different water conservancy projects and basin systems. Through digital twin technology, the scheduling effects in different scenarios can be simulated. Whether it is the emergency scheduling during a flood or the water supply guarantee during a drought period, they can be effectively reproduced and intelligently simulated in the virtual environment.

[0118] Virtual simulation technology is a powerful complement to digital twin technology. It allows decision-makers to quickly evaluate and compare different scheduling schemes without actual operation, not only greatly reducing the risks in actual operation, but also enabling decision-makers to face various scheduling scenarios more calmly. Through virtual simulation, the impact and change trends of different schemes in the real environment can be visually seen, so as to select the optimal water conservancy project scheduling scheme.

[0119] Combined with the knowledge structure information of water conservancy projects and the real-time data of modules, virtual simulation technology can monitor the operation status of water conservancy projects in real time, keep abreast of the latest developments of water conservancy projects at any time, ensure the accuracy and timeliness of scheduling decisions, contribute to the daily operation of different water conservancy projects, and can achieve emergency scheduling and timely and effective response when dealing with emergencies.

[0120] Digital twin and virtual simulation technology provide intelligent means for water conservancy project scheduling and water resource allocation methods, not only improving the scientificity and accuracy of scheduling decisions, but also greatly enhancing the operation management efficiency and stability of water conservancy projects, and contributing to the intelligent development of water conservancy project scheduling and water resource allocation.

[0121] Please refer to Figure 2 , in an optional embodiment, in order to efficiently execute the water conservancy project scheduling and water resource allocation method based on knowledge graph provided by the present invention, the present invention also provides a water conservancy project scheduling and water resource allocation system based on knowledge graph. The system includes a processor, an input device, an output device and a memory. The processor, input device, output device and memory are interconnected. Among them, the above-mentioned memory is used to store computer programs, and the computer programs include program instructions. The processor is configured to call the program instructions to execute the specific steps of the water conservancy project scheduling and water resource allocation method and related embodiments provided by the present invention. The water conservancy project scheduling and water resource allocation system based on knowledge graph of the present invention has a complete, objective and stable structure.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A method for water conservancy project scheduling and water resources allocation based on knowledge graph, characterized in that: The method comprises: Collect and integrate multi-source heterogeneous data of water conservancy projects based on the water conservancy project monitoring module; A time correction model is established based on the operation mode of the water conservancy project monitoring module, and the time nodes of the multi-source heterogeneous data are corrected by using the time correction model to obtain the water conservancy project multi-source data after time correction; Constructing a knowledge graph processing system for water conservancy project data according to a knowledge graph method, and using the knowledge graph processing system to process the time-corrected multi-source data of water conservancy projects to obtain knowledge structure information of water conservancy projects; The water conservancy project scheduling plan and water resource allocation status are analyzed according to the knowledge structure information, and the scientific regulation and efficient operation of the water conservancy project scheduling and water resource allocation are achieved based on the analysis results.

2. The method for water conservancy project scheduling and water resources allocation based on knowledge graph according to claim 1 is characterized in that: The multi-source heterogeneous data of water conservancy projects collected and integrated according to the water conservancy project monitoring module include: Collect historical data, real-time monitoring data and geographic information data of water conservancy projects through the water conservancy project monitoring module; The historical data, the real-time monitoring data and the geographic information data are integrated to obtain multi-source heterogeneous data of the water conservancy project.

3. The method for water conservancy project scheduling and water resources allocation based on knowledge graph according to claim 1 is characterized in that: The operation mode establishment time correction model based on the water conservancy project monitoring module includes: Analyze the hardware operation status and software operation characteristics of the water conservancy project monitoring module based on the operation mode of the water conservancy project monitoring module; Setting a hardware time correction model according to the hardware operating status; Setting a software time correction model according to the software operation characteristics; A time correction model is obtained by combining the hardware time correction model and the software time correction model.

4. The method for water conservancy project scheduling and water resources allocation based on knowledge graph according to claim 3 is characterized in that: The setting of the hardware time correction model according to the hardware operation status comprises: The time correction model satisfies the following relationship: in, Indicates the hardware calibration time of the water conservancy project monitoring module. Indicates the local time when the monitoring information arrives at the system database. represents the average communication delay between nodes at different time points, Indicates the average delay of receiving monitoring information at different time nodes. Indicates the weight coefficient of the monitoring module hardware recording monitoring information, Indicates the period of synchronous monitoring information of the water conservancy project monitoring module.

5. The method for water conservancy project scheduling and water resources allocation based on knowledge graph according to claim 3 is characterized in that: The setting of the software time correction model according to the software running characteristics comprises: The software time correction model satisfies the following relationship: in, Represents the time synchronization analysis model of the water conservancy project monitoring module software, Indicates the total number of valid time information received by the monitoring module software at different time steps, Represents the total number of nodes in the water conservancy project monitoring module time step, Indicates the maximum number of fault nodes in the water conservancy project monitoring module. Indicates the minimum number of valid time information required to maintain node time synchronization in the water conservancy project monitoring module.

6. The method for water conservancy project scheduling and water resources allocation based on knowledge graph according to claim 3 is characterized in that: The method of correcting the time nodes of the multi-source heterogeneous data by using the time correction model to obtain the time-corrected multi-source water conservancy project data includes: Correcting the time nodes of the multi-source heterogeneous data by using the hardware time correction model, and obtaining a corrected time node information set of the water conservancy project; The water conservancy project monitoring module software is adjusted based on the software time correction model and the time node information set to obtain time-corrected water conservancy project multi-source data.

7. The method for water conservancy project scheduling and water resources allocation based on knowledge graph according to claim 1 is characterized in that: The knowledge graph processing system for constructing water conservancy project data according to the knowledge graph method includes: Based on the knowledge graph method, a data forgetting analysis function, an input data feature analysis function and an information output analysis function are established in the knowledge graph processing system of water conservancy project data; The data forgetting analysis function, the input data feature analysis function and the information output analysis function are combined to form a knowledge graph processing system for water conservancy project data.

8. The method for water conservancy project scheduling and water resources allocation based on knowledge graph according to claim 7 is characterized in that: The method of establishing a data forgetting analysis function, an input data feature analysis function and an information output analysis function in the knowledge graph processing system of water conservancy project data based on the knowledge graph method includes: The data forgetting analysis function satisfies the following relationship: in, represents the output result of data forgetting characteristic analysis, represents the sigmoid function, Represents the weight matrix of the data forgetting characteristic analysis function, Represents the time step The corresponding data hidden state vector, Represents the time step The current data input vector, Represents the bias term corresponding to the data forgetting characteristic analysis function; The input data feature analysis function satisfies the following relationship: in, Represents the feature analysis result of the input information, represents the sigmoid function, Represents the weight matrix corresponding to the input data retention analysis function, Represents the time step The corresponding data hidden state vector, Represents the time step The current data input vector, Indicates the bias term corresponding to the input data retention analysis function; The information output analysis function satisfies the following relationship: in, It represents the information output result of water conservancy project. represents the output result of data forgetting characteristic analysis, Represents the time step The control status of the data output layer, Represents the feature analysis result of the input information, Represents the weight matrix corresponding to the information output analysis function, Represents the time step The corresponding data hidden state vector, Represents the time step The current data input vector, Represents the bias term corresponding to the information output analysis function.

9. The method for water conservancy project scheduling and water resources allocation based on knowledge graph according to claim 7 is characterized in that: The method of using the knowledge graph processing system to process the time-corrected multi-source data of water conservancy projects to obtain knowledge structure information of water conservancy projects includes: Obtaining forgotten data results of the water conservancy project through the data forgetting analysis function and the time-corrected multi-source data of the water conservancy project, and processing the time-corrected multi-source data of the water conservancy project based on the forgotten data results to obtain first knowledge structure information of the water conservancy project; Using the input data feature analysis function and the time-corrected multi-source data of the water conservancy project, an information feature result of the water conservancy project is obtained, and based on the information feature result, second knowledge structure information of the water conservancy project is obtained; Based on the information output analysis function, the first knowledge structure information and the second knowledge structure information, the time-corrected multi-source data of the water conservancy project is analyzed to obtain the knowledge structure information of the water conservancy project.

10. The water conservancy project scheduling and water resources allocation system based on knowledge graph is characterized by: The system includes a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions to execute the water conservancy project scheduling and water resources allocation method based on the knowledge graph as described in any one of claims 1 to 9.

Images