A multi-service data integration method, system, medium and device

Abstract

The present application provides a multi-service data integration method, system, medium and device, relating to the technical field of data integration. The method includes: obtaining multi-service data of a target water conservancy project, where the multi-service data includes original service data of multiple different dimensions; sequentially performing data preprocessing and normalization processing on each of the original service data to obtain each standard service data; classifying according to the data characteristics of each of the standard service data to obtain a classification result; establishing a water conservancy data correlation network based on the classification result, and performing data correlation analysis based on the water conservancy data correlation network to generate a multi-dimensional correlation view including early warning information, operation status and performance evaluation. Implementing the technical solution provided by the present application can achieve the overall correlation analysis of multi-dimensional service data, thereby enhancing the accuracy of the status assessment of water conservancy projects.

Description

Technical Field

[0001] This application relates to the technical field of data integration, and specifically relates to a multi-service data integration method, system, medium and device. Background Art

[0002] With the development of water conservancy projects towards large-scale and complexity, their operation and management face increasing challenges. Water conservancy projects involve multiple subsystems such as hydraulic structures, mechanical and electrical equipment, and control systems, and there are complex interaction relationships between these subsystems. To ensure the safe operation of the project, it is necessary to collect and analyze various types of monitoring data in real time.

[0003] Currently, the collection and analysis of business data for water conservancy projects mainly adopt a decentralized management mode. Each subsystem independently collects and processes data, forming relatively independent business data sets. These data sets include information in multiple dimensions such as hydrological monitoring data, equipment operation data, and safety monitoring data. In practical applications, operation and maintenance personnel need to view the data of different systems separately and make decisions based on empirical judgments. Due to the lack of overall correlation analysis of multi-dimensional business data, it is difficult to achieve refined data management, resulting in inaccurate state assessment of water conservancy projects. Summary of the Invention

[0004] This application provides a multi-service data integration method, system, medium and device, which can realize the overall correlation analysis of multi-dimensional business data, thereby enhancing the accuracy of the state assessment of water conservancy projects.

[0005] In the first aspect, this application provides a multi-service data integration method, and the method includes:

[0006] Obtain the multi-service data of the target water conservancy project, where the multi-service data includes original business data in multiple different dimensions;

[0007] Perform data preprocessing and normalization processing on each of the original business data in sequence to obtain each standard business data;

[0008] Classify according to the data characteristics of each of the standard business data to obtain a classification result;

[0009] Based on the classification result, establish a water conservancy data correlation network, and perform data correlation analysis based on the water conservancy data correlation network to generate a multi-dimensional correlation view including early warning information, operation status and performance evaluation.

[0010] By adopting the above technical solutions, by obtaining multi-source business data including multiple different-dimensional original business data, and performing preprocessing and normalization processing on these original business data to obtain standard business data, the unified management of data in each subsystem of the water conservancy project is realized. Then, by classifying the standard business data according to data characteristics and establishing a water conservancy data correlation network based on the classification results, the scattered business data is effectively associated. Finally, based on this water conservancy data correlation network, data correlation analysis is carried out to generate a multi-dimensional correlation view including early warning information, operation status and performance evaluation, enabling the operation and maintenance personnel to intuitively grasp the interaction relationship between the various systems of the project, breaking through the limitations of the traditional decentralized management mode, realizing the overall correlation analysis of multi-dimensional business data, and thus significantly improving the accuracy of the water conservancy project status assessment.

[0011] In the second aspect of the present application, a multi-source business data integration system is provided, and the system includes:

[0012] A data acquisition module, configured to acquire multi-source business data of a target water conservancy project, where the multi-source business data includes multiple different-dimensional original business data;

[0013] A data processing module, configured to sequentially perform data preprocessing and normalization processing on each of the original business data to obtain each standard business data;

[0014] A data classification module, configured to classify according to the data characteristics of each of the standard business data to obtain a classification result;

[0015] A data integration module, configured to establish a water conservancy data correlation network based on the classification result, and perform data correlation analysis based on the water conservancy data correlation network to generate a multi-dimensional correlation view including early warning information, operation status and performance evaluation.

[0016] In the third aspect of the present application, a computer storage medium is provided, and the computer storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the above method steps.

[0017] In the fourth aspect of the present application, an electronic device is provided, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is suitable for being loaded and executed by the processor to perform the above method steps.

[0018] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0019] This application realizes the unified management of data for each subsystem of the water conservancy project by obtaining multi-source business data including multiple different-dimensional original business data, and performing preprocessing and normalization on these original business data to obtain standard business data. Then, by classifying the standard business data according to data characteristics and establishing a water conservancy data correlation network based on the classification results, the scattered business data is effectively correlated. Finally, based on this water conservancy data correlation network, data correlation analysis is carried out to generate a multi-dimensional correlation view including early warning information, operating status, and performance evaluation, enabling operation and maintenance personnel to intuitively grasp the interaction relationships between various systems of the project, breaking through the limitations of the traditional decentralized management mode, realizing the overall correlation analysis of multi-dimensional business data, and thus significantly improving the accuracy of the water conservancy project status assessment. Description of the Drawings

[0020] Figure 1 is a schematic flowchart of a multi-source business data integration method provided by an embodiment of this application;

[0021] Figure 2 is a schematic block diagram of a multi-source business data integration system provided by an embodiment of this application;

[0022] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of this application.

[0023] Description of the reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Embodiments

[0024] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments.

[0025] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly, the use of words such as "for example" or "for instance" is intended to present relevant concepts in a specific manner.

[0026] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the technical features indicated. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0027] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0028] Please refer to Figure 1 , and a flow schematic diagram of a multi-service data integration method is specifically proposed. This method can be implemented depending on a computer program, can be implemented depending on a single-chip microcomputer, or can run on a multi-service data integration system. This computer program can be integrated in a computer device or can run as an independent tool-type application. Specifically, this method includes steps 10 to 40, and the above steps are as follows:

[0029] Step 10: Obtain the multi-service data of the target water conservancy project, and the multi-service data includes multiple original service data in different dimensions.

[0030] In the embodiments of the present application, the target water conservancy project refers to a large water conservancy facility with multiple functional subsystems. For example, it can be a reservoir dam, a hydropower station, a sluice pump station, etc., which are water conservancy projects with multiple subsystems such as hydraulic structures, electromechanical equipment, and control systems. These engineering projects usually have complex hydraulic characteristics and system interaction relationships.

[0031] In the embodiments of the present application, the multi-service data refers to various monitoring data and service data related to the operation of the target water conservancy project, including but not limited to: structural monitoring data of hydraulic structures (such as displacement, stress, seepage, etc.), hydrological monitoring data (such as water level, flow rate, water quality, etc.), operation data of electromechanical equipment (such as rotational speed, vibration, temperature, etc.), status data of control systems (such as opening degree, pressure, current, etc.), and other service data related to project operation management. These data come from different subsystems and have different data characteristics and collection frequencies.

[0032] Specifically, since a large amount of different types of data will be generated during the operation of each subsystem of the water conservancy project, and these data are scattered and stored in different business systems, in order to achieve a comprehensive assessment of the project status, it is necessary to first obtain this multi-source business data. First, based on the historical operation data of the target water conservancy project, analyze the data change rules of the key parts of the project under different operating conditions, and extract data change characteristics such as data fluctuation range and change rate, so as to obtain data characteristic indicators that can represent the operation characteristics of the project. Then, according to these data characteristic indicators, determine the optimal acquisition frequency of different types of data. After determining the acquisition frequency, deploy distributed data acquisition nodes at the key monitoring points of the project. These acquisition nodes perform data interaction through the edge computing network and collect the original business data of different dimensions in real time, including the structural monitoring data of hydraulic structures, hydrological monitoring data, and the operation data of electromechanical equipment. Finally, uniformly convert the collected various original business data into a preset standard data format to form a standardized multi-source business data set.

[0033] Based on the above embodiments, as an optional embodiment, the step of obtaining the multi-source business data of the target water conservancy project may further include the following steps:

[0034] Step 101: Based on the historical operation data of the target water conservancy project, extract the data change characteristics of the key parts of the project to obtain data characteristic indicators.

[0035] Specifically, since each key part of the water conservancy project exhibits different data characteristics under different operating conditions, in order to accurately grasp these characteristics and determine a reasonable data acquisition strategy, it is necessary to conduct an in-depth analysis of the historical operation data. First, retrieve the historical operation data of the target water conservancy project in the past five years from the project operation management system. These data include dam deformation monitoring data, gate opening and closing process data, pump operation data, etc. For each key part, select the data sequence under its typical operating conditions, such as the water level change data during the flood season and non-flood season, and the equipment parameter change data during the start-up and shutdown process of the unit. Then, use the sliding time window method to segment these data sequences and calculate the data statistical characteristics within each time window, including mean, standard deviation, change rate, etc. By comparing the statistical characteristics under different operating conditions, determine the change rules of various types of data, such as the periodicity, mutation characteristics, and correlation of the data. Based on these change rules, construct a feature vector that reflects the dynamic characteristics of the data. This feature vector contains information such as the data fluctuation range, change rate, and trend, so as to obtain data characteristic indicators that can quantitatively describe the data change characteristics of each key part. In this way, not only the change rules of various types of data are clarified, but also a scientific basis is provided for determining the data acquisition frequency later, which helps to improve the pertinence and efficiency of data acquisition.

[0036] Step 102: Determine the data acquisition frequency based on the data characteristic indicators. Using the distributed data acquisition nodes and based on the data acquisition frequency, obtain the original business data of different dimensions. The distributed data acquisition nodes perform data interaction through the edge computing network.

[0037] Specifically, according to the fluctuation range and change rate information in the data characteristic indicators, use the Nyquist sampling theorem to calculate the minimum sampling frequency, and adjust it in combination with the actual engineering situation. For example, for parameters that change rapidly such as equipment vibration, a sampling frequency of 100 Hz is adopted, while for slowly changing parameters such as water level and temperature, a sampling frequency of 1 Hz is adopted. After determining the sampling frequency, deploy distributed data acquisition nodes at key engineering positions. These nodes include strain acquisition nodes set at different elevations of the dam, vibration acquisition nodes installed on the bearing seats of the units, water level acquisition nodes arranged upstream and downstream, etc. Each acquisition node is equipped with an edge computing unit, which can perform local data preprocessing and caching. Adjacent acquisition nodes communicate through the edge computing network, use the time synchronization protocol to ensure the timing consistency of the data, and achieve data complementarity and redundant backup between nodes through the data sharing mechanism. When an abnormal data is detected by a certain node, it can quickly notify the relevant nodes to increase the sampling frequency through the edge network, realizing the adaptive adjustment of data acquisition.

[0038] Step 103: Convert each original business data into a preset standard data format to obtain the multi-source business data of the target water conservancy project.

[0039] Specifically, the collected original business data includes different data formats, such as binary data streams, text data, analog data, etc., and needs to be uniformly converted into a preset standard data format. During the conversion process, first extract the key fields such as the timestamp, measurement point information, and numerical value of the data, and then perform formatting processing according to the predefined data template to generate a standardized data set containing a unified metadata structure. In this way, both the real-time and reliability of data acquisition are ensured, and the unified management of data formats is realized.

[0040] Step 20: Perform data preprocessing and normalization processing on each original business data in sequence to obtain each standard business data.

[0041] Specifically, in order to eliminate the noise interference in the original business data and unify the data scales of different dimensions, it is necessary to preprocess and normalize the obtained original business data. First, preprocess the original business data, including two steps: data cleaning and data smoothing. During the data cleaning process, an outlier detection method based on the 3σ criterion is used to identify outliers. For the detected outliers, if the deviation from the adjacent data points exceeds the preset threshold, they are marked as invalid data; for the case of missing data, according to the time continuity characteristics of the data, linear interpolation or spline interpolation methods are used for data repair. Then, an adaptive filtering algorithm based on wavelet transform is used to smooth the data. By threshold processing the wavelet coefficients of different scales, the influence of random noise is effectively suppressed while retaining the mutation characteristics of the data. After the preprocessing is completed, corresponding normalization methods are adopted for different types of data. For parameters with a definite range of variation (such as water level, pressure, etc.), the maximum-minimum normalization method is used to map the data to the interval [0, 1]; for parameters that may have large fluctuations (such as vibration, flow rate, etc.), the method based on Z-score standardization is used to convert the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. Through this data preprocessing and normalization, not only the quality and reliability of the data are improved, but also the scale unification of data in different dimensions is achieved, creating conditions for subsequent data classification and correlation analysis.

[0042] Based on the above embodiments, as an optional embodiment, the step of preprocessing and normalizing each original business data in sequence to obtain each standard business data may further include the following steps:

[0043] Step 201: Extract the time series features of each original business data and segment the data based on the time series features.

[0044] Specifically, since the original business data generated during the operation of water conservancy projects is uneven in the time dimension, with sparse data in some periods and redundant data in some periods, in order to ensure the accuracy of data analysis, it is necessary to extract the time series features of the data and perform segmented balancing processing. Specifically, during implementation, first, the sliding time window method is used to extract the time series features of each original business data, calculate the statistical features within each time window, including mean, variance, kurtosis, skewness, etc., and determine the periodic and trend characteristics of the data in combination with autocorrelation analysis. Based on the extracted time series features, a segmentation algorithm based on change point detection is used to segment the data. This algorithm sets segmentation points at the positions where the features change significantly by calculating the distance metric of adjacent time window features, thereby dividing the entire time series into multiple data segments with relatively stable features.

[0045] Step 202: Calculate the data density of each segmented data segment, interpolate and supplement the data segments with data density not higher than the density threshold, and downsample the data segments with data density higher than the density threshold to obtain the first service data set.

[0046] Specifically, for each data segment, calculate its data density, that is, the number of data points per unit time. Set a density threshold based on engineering experience. For example, for water level data, it can be set to 10 points / minute. For data segments with data density lower than the density threshold, use an interpolation method considering the physical characteristics of the data for supplementation. For data with periodic characteristics, use Fourier interpolation, and for data with monotonic characteristics, use cubic spline interpolation to ensure that the interpolation results conform to the physical meaning of the data. For data segments with data density higher than the density threshold, adopt a downsampling strategy based on data importance. By calculating the information entropy of the data points, retain the key data points with large amounts of information and eliminate redundant information to achieve data dimensionality reduction. Through this segmented balancing process, a first service data set with a reasonable time resolution is formed, which not only ensures the integrity of the data but also avoids data redundancy and improves the efficiency of subsequent analysis.

[0047] Step 203: Determine different filtering parameters based on the time span of each data segment, and filter each data segment in the first service data set according to the filtering parameters to obtain the second service data set.

[0048] Specifically, since data segments with different time spans may contain noise with different frequency characteristics, an adaptive filtering strategy needs to be adopted to improve data quality. First, design adaptive filtering parameters based on the time span of each data segment. For data segments with a short time span (such as hourly), use a higher cut-off frequency to retain the effective information of rapid changes; for data segments with a long time span (such as daily), use a lower cut-off frequency to filter out the interference in the long-term trend. After determining the filtering parameters, use a multi-scale filtering method based on wavelet transform to process each data segment in the first service data set. By selecting an appropriate wavelet basis function (such as db4 wavelet) to decompose the data into multiple layers, perform threshold processing on the wavelet coefficients according to the corresponding filtering parameters at different decomposition levels, and then obtain the filtered data segment through wavelet reconstruction, thus forming the second service data set.

[0049] Step 204: Re - splice each data segment in the second service data set and perform data smoothing to obtain the pre - processed data.

[0050] Specifically, in order to eliminate the splicing breakpoints between data segments, the data segments in the second service dataset are combined using an overlapping splicing method, and a weighted average method is used to achieve smooth transition in the overlapping area of adjacent data segments. The spliced data is then globally smoothed using the LOESS algorithm based on local regression. By adjusting the window size of local regression, local fluctuations are suppressed while maintaining the overall trend of the data, and preprocessed data is obtained.

[0051] Step 205: Group and normalize the preprocessed data according to data characteristic indicators to obtain each standard service data.

[0052] Specifically, the preprocessed data is grouped according to data characteristic indicators. For example, data with the same physical quantity or similar variation rules are divided into one group, and appropriate normalization methods are used for each group of data: for data with a fixed range, maximum-minimum normalization is used; for data with a normal distribution characteristic, Z-score standardization is used; for data with obvious skewness, logarithmic transformation is used followed by standardization. Thus, each standard service data with unified dimension and consistent scale is obtained. Through this multi-step data processing, not only is the data quality effectively improved, but also the physical characteristics of the data are maintained, providing a reliable basis for subsequent data analysis.

[0053] Step 30: Classify according to the data characteristics of each standard service data to obtain a classification result.

[0054] Specifically, first, a multi-dimensional feature vector is constructed to characterize the characteristics of each standard service data. This feature vector includes statistical features (mean, variance, kurtosis, skewness, etc.), time-domain features (periodicity, trend, mutation, etc.), and frequency-domain features (main frequency, energy distribution, etc.). The principal component analysis method is used to reduce the dimension of the feature vector, and the principal components with a cumulative contribution rate reaching 85% are retained to reduce the dimension of the feature space and eliminate the correlation between features. Then, a clustering method based on the improved K-means algorithm is used to classify the reduced-dimensional features. The optimal number of clusters is determined by calculating the silhouette coefficient, and a density-based initial cluster center selection strategy is adopted to improve the clustering effect. During the clustering process, an adaptive distance metric mechanism is introduced to assign dynamic weights to different-dimensional features, making the clustering result more in line with the physical attributes of the data. For example, vibration data representing equipment status, displacement data reflecting engineering safety, and process parameters describing operating conditions are classified into different categories according to their feature similarities. Through this data classification method, not only is the scientific classification of service data achieved, but also a clear data organizational structure is provided for subsequent data analysis and applications, helping to improve the efficiency of data management and utilization.

[0055] Based on the above embodiments, as another alternative embodiment, the step of classifying according to the data characteristics of each standard business data to obtain a classification result may further include the following steps:

[0056] Step 301: Extract the hydraulic characteristic parameters of each standard business data and generate a feature description matrix.

[0057] Specifically, first extract the hydraulic characteristic parameters of each standard business data. These parameters include hydraulic characteristics (such as flow velocity, head loss, Reynolds number, etc.), structural characteristics (such as stress distribution, deformation amount, vibration frequency, etc.), and operation characteristics (such as equipment efficiency, energy consumption index, operation condition, etc.). For each data sequence, calculate its characteristic values under different working conditions, and combine expert experience to determine the weight coefficients of the characteristic parameters. Organize the extracted characteristic parameters into a feature description matrix. The rows of the matrix represent different standard business data, the columns represent different hydraulic characteristic parameters, and the matrix elements are the corresponding characteristic values.

[0058] Step 302: Calculate the similarity between each standard business data based on the feature description matrix, and divide the data with a similarity greater than the first threshold into the same category to obtain a first classification result.

[0059] Specifically, use the cosine similarity algorithm to calculate the similarity between the row vectors in the feature description matrix, and introduce parameter weights during the calculation process so that the characteristic parameters with a greater impact on hydraulic performance have higher weights. Set the first threshold according to the actual engineering requirements. For example, set the first threshold to 0.85. When the similarity between two data sequences is greater than this threshold, divide them into the same category. Through this classification method based on hydraulic characteristics, data with similar hydraulic performance, structural response, or operation characteristics are aggregated together to form a first classification result. This classification method not only considers the statistical characteristics of the data, but more importantly, reflects the professional characteristics of hydraulic engineering, helps to discover the physical associations between data, and provides a scientific basis for subsequent engineering analysis and decision-making.

[0060] Step 303: Calculate the hydraulic correlation degree between different category data in the first classification result, and merge the data categories with a hydraulic correlation degree greater than the second threshold to obtain a second classification result.

[0061] Specifically, a hydraulic correlation calculation model is constructed based on the principles of hydraulics, which comprehensively considers factors such as hydraulic connectivity, flow balance, and energy transfer. For different categories in the first classification result, by analyzing the spatial relationships of their monitoring locations in the hydraulic system, a hydraulic correlation matrix between categories is established. When calculating the hydraulic correlation degree, a network analysis method based on graph theory is adopted, with each monitoring point as a network node and the hydraulic connection relationship as an edge. By calculating indicators such as the shortest path, connectivity, and flow transfer coefficient between nodes, the hydraulic correlation strength between different category data is quantified. A second threshold based on engineering experience is set. For example, the second threshold is set to 0.75. When the hydraulic correlation degree between two data categories exceeds this threshold, it indicates that they have a close functional correlation in the hydraulic system, and these categories need to be merged into a new category. The merging process adopts the idea of hierarchical clustering, preferentially merging the categories with the highest correlation degree until the correlation degree between all categories is lower than the second threshold, thus obtaining the second classification result.

[0062] Step 304: Extract the common features and differential features of each category of data in the second classification result, and determine the attribute labels of each category of data based on the common features and differential features.

[0063] Specifically, a multi-dimensional feature analysis method is used to extract the common features of each category of data. By calculating the statistical moments of each category of data, including the mean vector, covariance matrix, etc., the characteristic patterns commonly possessed by this category of data are identified; at the same time, information theory indicators such as information entropy and mutual information are used to quantify the correlation and information redundancy of the data within the category, so as to discover the common laws between the data. On the basis of extracting the common features, a feature contrast analysis method is further used to extract the differential features. By calculating the Mahalanobis distance between the data of different categories, the significant distinguishing features between different category data are identified; combined with time-frequency analysis methods such as wavelet transform and empirical mode decomposition, the feature differences of each category of data at different scales are extracted. Based on the extracted common features and differential features, a feature importance evaluation index system is constructed, and the fuzzy comprehensive evaluation method is used to determine the weights of each feature, and the features are physically interpreted in combination with the professional knowledge of hydraulic engineering. For example, for data categories with obvious periodic and steady-state characteristics, they can be labeled as "steady-state operation data"; for data categories showing mutation characteristics and non-linear correlations, they can be labeled as "transition condition data"; for data categories with obvious spatial distribution characteristics, they can be labeled as "hydraulic spatial distribution data".

[0064] Step 305: Take the second classification result and the corresponding attribute labels of each category as the classification result.

[0065] Specifically, associate the second classification result with the attribute tags of the corresponding category and use it as the classification result. This method of defining attribute tags based on feature analysis assigns clear physical meanings and engineering attributes to various types of data in the second classification result, forming the final classification result. This classification result not only reflects the internal characteristics of the data but also reflects the functional positioning of the data in the water conservancy project system.

[0066] Step 40: Establish a water conservancy data connection network based on the classification result, and perform data association analysis based on the water conservancy data connection network to generate a multi-dimensional association view including early warning information, operation status, and performance evaluation.

[0067] Specifically, in order to comprehensively understand the complex association relationships among various types of data in the water conservancy project system and achieve comprehensive analysis and visual display of the data, it is necessary to construct a water conservancy data connection network and perform multi-dimensional analysis. In specific implementation, first, construct a water conservancy data connection network based on the classification result, use different types of data as network nodes, and establish network connections according to the physical association, causal relationship, and temporal correlation among the data. Use a weighted directed graph to represent the data connection network, where the weight of the edge reflects the association strength, and the direction of the edge represents the causal relationship or the direction of influence transmission. During the network construction process, introduce a time-varying weight mechanism, calculate the dynamic correlation coefficient through a sliding time window, so that the connection network can reflect the time-varying characteristics of the data relationship. Based on the constructed connection network, use complex network analysis methods to perform data association analysis, including calculating node importance, clustering coefficient, and path analysis, etc., to identify key data nodes and important association paths. By tracking the abnormal propagation paths in the connection network and combining the set early warning thresholds, generate early warning information such as equipment anomalies and parameter overlimits; by analyzing the state transition characteristics in the connection network, identify the system operation mode and judge the current operation status; by evaluating the overall topological characteristics and local structural characteristics of the connection network and combining the performance index calculation model, generate the performance evaluation results of the equipment and the system. Integrate these analysis results into a multi-dimensional association view, adopt a hierarchical visualization scheme, display the overall situation of the system at the macroscopic level, display the status of key equipment groups at the mesoscopic level, present specific equipment parameters at the microscopic level, and achieve flexible switching between different dimensions through interactive operations. This analysis method based on the connection network not only realizes the systematic management of water conservancy project data but also provides intuitive decision-making support information, effectively improving the intelligent level of system operation management.

[0068] On the basis of the above embodiments, as another optional embodiment, the step of establishing a water conservancy data connection network based on the classification result and performing data association analysis based on the water conservancy data connection network may further include the following steps:

[0069] Step 4011: Connect the data nodes with the same classification result attribute labels, calculate the association strength between the nodes based on the common features, and construct an initial data sub-network.

[0070] Specifically, first connect the data nodes with the same attribute labels to construct an initial data sub-network. Adopt an association strength calculation method based on common features, and quantify the association degree between the nodes by analyzing the time series correlation, spectrum characteristics, and statistical characteristics of the data. When calculating the association strength, introduce an adaptive weight mechanism to dynamically adjust the weight coefficients according to the importance of different features under different working conditions, so that the association strength can accurately reflect the actual association degree between the data. For each initial data sub-network, use the minimum spanning tree algorithm in graph theory to optimize the network connection structure, retain the key connections with higher association strength, and eliminate redundant connections to form a stable sub-network structure.

[0071] Step 4012: Analyze the hydraulic association degree of each node in the initial data sub-network, establish cross-network connections between different sub-networks based on the difference features, and generate a hierarchical association structure.

[0072] Specifically, analyze the hydraulic association degree of the nodes in different initial data sub-networks, identify the node pairs with significant hydraulic association by calculating the upstream and downstream relationships, energy transfer paths, and flow balance relationships of the nodes in the hydraulic system. When establishing cross-network connections based on the difference features, use the analytic hierarchy process to determine the weights of different features, and focus on the features that can reflect the dynamic characteristics and engineering mechanisms of the system, such as equipment response characteristics, system damping characteristics, and control parameter sensitivity. Through the establishment of cross-network connections, a hierarchical structure including local sub-networks and global associations is formed. This structure not only maintains the close association of the same type of data but also reflects the system association between different types of data.

[0073] Step 4013: Calculate the hydraulic transfer characteristics between the connected nodes in the hierarchical association structure, and determine the directionality of the network connection based on the hydraulic transfer characteristics.

[0074] Specifically, first, a calculation model for hydraulic transmission characteristics is established. This model is based on the basic principles of fluid mechanics and takes into account factors such as water flow direction, pressure gradient, and energy transfer. For each pair of connected nodes in the hierarchical association structure, by analyzing the temporal characteristics of their monitoring data, the time-delay relationship and causal relationship between the nodes are calculated, and the Granger causality test method is used to determine the order of data changes. In the analysis of hydraulic transmission characteristics, a hydraulic response function is introduced. By solving the transfer function and impulse response between nodes, the propagation characteristics of hydraulic disturbances are quantified. For nodes with obvious physical connections, such as the inlet and outlet of a pumping station, the upstream and downstream of a canal system, etc., the connection direction is directly determined according to the hydraulic flow direction; for nodes without direct physical connections but with statistical correlations, by calculating the mutual information entropy and conditional entropy, the directionality of information transfer is evaluated. Based on the calculated hydraulic transmission characteristics, a direction attribute is assigned to each connection in the network, and the undirected hierarchical association structure is transformed into a directed network.

[0075] Step 4014: Integrate the hierarchical association structure and the directionality of the corresponding network connections into a water conservancy data association network.

[0076] Specifically, a weighted directed graph representation method is adopted. The weight of the edge reflects the hydraulic association strength, and the direction of the edge represents the direction of hydraulic influence transmission, forming a complete water conservancy data association network. This association network considering directionality not only reflects the causal relationship and influence transmission path in the system, but also provides a scientific basis for the dynamic characteristic analysis and fault propagation prediction of the system.

[0077] Based on the above embodiments, as another alternative embodiment, the step of generating a multi-dimensional association view including warning information, operating status, and performance evaluation based on the water conservancy data association network may further include the following steps:

[0078] Step 4021: Calculate the hydraulic mutation index of each node in the water conservancy data association network, and trace the mutation propagation path based on the transfer direction between nodes. An early warning information trigger chain is constructed based on the mutation index and the mutation propagation path.

[0079] Specifically, a calculation model for hydraulic mutation indicators is constructed, which comprehensively considers characteristics such as the jump amplitude, change rate, and duration of data. By performing wavelet transform and singular spectrum analysis on node data, mutation points in the data are identified, and the mutation intensity index is calculated; at the same time, an adaptive threshold mechanism is introduced to dynamically adjust the mutation determination criteria according to different working conditions and seasonal characteristics. After determining the mutation characteristics of the nodes, based on the transmission direction in the correlation network, a graph traversal algorithm is used to trace the propagation path of the mutation. By analyzing the spatio-temporal evolution law of the mutation characteristics, the source nodes and affected nodes of the mutation are identified. Combining the mutation indicators with the propagation path information, an early warning information trigger chain is constructed, which includes links such as mutation detection, impact assessment, and early warning level determination, and can realize the early detection of mutation events and the prediction of chain reactions.

[0080] Step 4022: Extract the operation parameter combinations of the nodes in the hydraulic data correlation network, analyze the change characteristics of the parameter combinations, and obtain the operation state intervals of each part of the project.

[0081] Specifically, the operation parameter combinations of the nodes are extracted from the correlation network. These parameters include physical quantities such as flow rate, water level, and pressure, as well as equipment operation parameters such as rotation speed and power. Multidimensional data analysis methods are used to reduce the parameter space dimension through principal component analysis and extract key feature combinations; clustering analysis methods, such as fuzzy C-means clustering, are used to divide the change characteristics of the parameter combinations into different operation modes. For each operation mode, the normal fluctuation range of the parameters is determined through statistical analysis, and combined with the equipment operation regulations and engineering experience, different operation state intervals are defined. For example, the change characteristics of the parameter combinations are divided into a normal operation interval, a transition operation interval, and a warning operation interval, etc. By establishing the mapping relationship between the parameter combinations and the operation states, the real-time assessment of the operation states of each part of the project is realized. This analysis method based on the data correlation network can not only detect system anomalies in a timely manner, but also accurately judge the operation states, providing a reliable basis for operation management decisions.

[0082] Step 4023: Calculate the performance transmission chain based on the hierarchical structure of the hydraulic data correlation network, and generate a performance evaluation result based on the performance transmission chain.

[0083] Specifically, a performance transfer chain calculation model is constructed based on the hierarchical structure of the water conservancy data correlation network, which considers the transfer relationship between equipment performance indicators and system effectiveness indicators. By analyzing indicators such as the energy transfer efficiency, equipment operation efficiency, and system coordination among nodes in the correlation network, a performance evaluation index system is established; the fuzzy comprehensive evaluation method is adopted to weight and integrate performance indicators at different levels to obtain the overall system performance evaluation value. In the performance transfer analysis, a performance decay function is introduced to quantify the loss characteristics of performance indicators during the transfer process and identify the location of performance bottlenecks. Based on the calculated performance transfer chain, a multi-level evaluation method is used to generate performance evaluation results, including the operation efficiency evaluation at the equipment level, the collaborative performance evaluation at the system level, and the economic performance evaluation at the overall level.

[0084] Step 4024: Map the warning information trigger chain, the operating state interval, and the performance evaluation result to the preset engineering structure layout to obtain a multi-dimensional correlation view.

[0085] Specifically, the warning information trigger chain, the operating state interval, and the performance evaluation result are integrated into the preset engineering structure layout. The hierarchical display technology is adopted to overlay multi-dimensional information layers on the engineering structure diagram, and different dimensions of information are expressed through different visual coding methods. For example, the operating state interval is represented by color coding, the warning information is displayed by flashing marks, and the performance evaluation result is shown by numerical labels. In the process of visualization implementation, an interactive operation mechanism is introduced to support functions such as the switching of information layers, the drill-down analysis of data, and the playback of the time dimension. By establishing a unified visualization framework, the collaborative display of multi-dimensional information such as warnings, states, and performances is realized, forming an intuitive multi-dimensional correlation view. This visualization solution based on the engineering structure layout not only facilitates managers to quickly grasp the system operation situation but also helps to discover the correlation characteristics between different dimensions of information, providing comprehensive information support for system optimization and decision-making.

[0086] Based on the above embodiments, as another alternative embodiment, the multi-service data integration method may further include the following steps:

[0087] Specifically, in order to actively prevent and control the risks of the water conservancy project system, it is necessary to deeply analyze the early warning information in the multi-dimensional association view and establish a corresponding emergency response mechanism. During the specific implementation, first, extract the propagation characteristics of the early warning information from the multi-dimensional association view. By analyzing the spatio-temporal distribution law, propagation speed, and influence range of the early warning events and other characteristics, establish a risk propagation model. Adopt the network analysis method, based on the association relationship and propagation path of the early warning information, calculate the possible paths of risk diffusion, including direct propagation paths and indirect propagation paths. In the risk path analysis, introduce the risk transfer probability matrix to quantify the possibility of risk transfer between different nodes, and predict the dynamic process of risk diffusion through the Monte Carlo simulation method. Finally, form a risk prevention and control network including risk source identification, propagation path, and impact assessment.

[0088] Based on the constructed risk prevention and control network, use the analytic hierarchy process to evaluate the risk levels of various parts of the project. Considering factors such as equipment importance, failure impact, and maintenance difficulty, establish a risk level assessment index system. By analyzing historical failure cases and expert experience, determine the discrimination criteria and thresholds for different risk levels to achieve dynamic assessment of risk levels. For different risk levels, formulate corresponding emergency response plans, including emergency response processes, disposal measures, and resource allocation strategies. During the formulation of the emergency plan, adopt the case-based reasoning method. Based on historical disposal experience and the current system status, generate targeted disposal suggestions, and evaluate the effects of different disposal measures through the plan optimization algorithm.

[0089] Integrate the generated emergency response plan into the multi-dimensional association view, adopt a hierarchical display method, and add a risk prevention and control information layer on the basis of the original view. Through visual encoding, use different graphic symbols and colors to identify the risk levels, use dynamic arrows to represent the risk propagation direction, and use pop-up windows to display the detailed content of the disposal plan. In the interaction design, support the quick call of the emergency plan and the real-time tracking of the plan execution progress to achieve visual management of the risk prevention and control process. This multi-dimensional association view integrated with risk prevention and control functions can not only help managers timely discover and evaluate risks, but also guide the orderly development of emergency response work, realizing the active prevention and control and efficient disposal of project risks.

[0090] Please refer to Figure 2 , which is a schematic diagram of the modules of a multi-service data integration system provided by an embodiment of the present application. The multi-service data integration system may include: a data acquisition module, a data processing module, a data classification module, and a data integration module, where:

[0091] The data acquisition module is used to acquire multi-service data of the target water conservancy project, and the multi-service data includes original service data of multiple different dimensions;

[0092] A data processing module, which is used to perform data preprocessing and normalization processing on each of the original service data in sequence to obtain each standard service data;

[0093] A data classification module, which is used to classify according to the data characteristics of each of the standard service data to obtain a classification result;

[0094] A data integration module, which is used to establish a water conservancy data correlation network based on the classification result, and perform data correlation analysis based on the water conservancy data correlation network to generate a multi-dimensional correlation view including early warning information, operation status and performance evaluation.

[0095] Optionally, the data acquisition module is further used to extract the data change characteristics of the key parts of the project based on the historical operation data of the target water conservancy project to obtain data characteristic indicators;

[0096] Determine the data acquisition frequency based on the data characteristic indicators, and use distributed data acquisition nodes to obtain original service data of different dimensions based on the data acquisition frequency. The distributed data acquisition nodes perform data interaction through an edge computing network;

[0097] Convert each of the original service data into a preset standard data format to obtain multi-service data of the target water conservancy project.

[0098] Optionally, the data processing module is further used to extract the time series characteristics of each of the original service data, and perform segmentation processing on the data based on the time series characteristics;

[0099] Calculate the data density of each segmented data segment, interpolate and supplement the data segments with data density not higher than the density threshold, and downsample the data segments with data density higher than the density threshold to obtain a first service data set;

[0100] Determine different filtering parameters based on the time span of each of the data segments, and filter each data segment in the first service data set according to the filtering parameters to obtain a second service data set;

[0101] Re-splice each data segment in the second service data set, and perform data smoothing processing to obtain preprocessed data;

[0102] Perform grouped normalization processing on the preprocessed data according to the data characteristic indicators to obtain each standard service data.

[0103] Optionally, the data classification module is further used to extract the hydraulic characteristic parameters of each of the standard service data and generate a characteristic description matrix;

[0104] Calculate the similarity between each of the standard business data based on the feature description matrix, divide the data with similarity greater than the first threshold into the same category, and obtain the first classification result;

[0105] Calculate the hydraulic correlation degree between different categories of data in the first classification result, and merge the data categories with hydraulic correlation degree greater than the second threshold to obtain the second classification result;

[0106] Extract the common features and different features of each category of data in the second classification result, and determine the attribute labels of each category of data based on the common features and different features;

[0107] Take the second classification result and the corresponding category attribute labels as the classification result.

[0108] Optionally, the data integration module is further configured to connect the data nodes with the same attribute labels in the classification result, calculate the association strength between the nodes based on the common features, and construct an initial data subnet;

[0109] Analyze the hydraulic correlation degree of each node in the initial data subnet, establish cross-network connections between different subnets based on the different features, and generate a hierarchical association structure;

[0110] Calculate the hydraulic transmission characteristics between the connected nodes in the hierarchical association structure, and determine the directionality of the network connection based on the hydraulic transmission characteristics;

[0111] Integrate the hierarchical association structure and the directionality of the corresponding network connection into a water conservancy data correlation network.

[0112] Optionally, the data integration module is further configured to calculate the hydraulic mutation index of each node in the water conservancy data correlation network, track the mutation propagation path based on the transmission direction between the nodes, and construct an early warning information trigger chain based on the mutation index and the mutation propagation path;

[0113] Extract the operation parameter combinations of the nodes in the water conservancy data correlation network, analyze the change characteristics of the parameter combinations, and obtain the operation state intervals of each part of the project;

[0114] Calculate the performance transmission chain based on the hierarchical structure of the water conservancy data correlation network, and generate a performance evaluation result based on the performance transmission chain;

[0115] Map the early warning information trigger chain, operation state interval and performance evaluation result to the preset project structure layout to obtain a multi-dimensional association view.

[0116] Optionally, the data integration module extracts the propagation characteristics of the early warning information in the multi-dimensional association view, and calculates the risk diffusion path to obtain a risk prevention and control network;

[0117] Generate an emergency response plan based on the risk levels of various parts of the risk prevention and control network analysis project;

[0118] Integrate the emergency response plan into the multi-dimensional association view to achieve active prevention and control of project risks.

[0119] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above-mentioned functional modules is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be seen in the method embodiment, which will not be repeated here.

[0120] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded and executed by a processor to perform a multi-service data integration method in the above embodiment. The specific execution process can refer to the specific description in the above embodiment, and will not be repeated here.

[0121] Please refer to Figure 3 The present application also discloses an electronic device. Figure 3 It is a schematic structural diagram of an electronic device disclosed in the embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0122] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0123] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0124] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0125] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by invoking the data stored in the memory 305, it performs various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0126] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , in the memory 305, as a computer storage medium, there may be included an operating system, a network communication module, a user interface module, and an application program of a multi-service data integration method.

[0127] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a multi-service data integration method. When executed by one or more processors 301, the electronic device 300 is caused to execute one or more of the methods as described in the above embodiments. It should be noted that for the foregoing method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0128] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] In several implementation manners provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0130] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, the functional units in the respective embodiments of the present application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0132] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard disks, magnetic disks, or optical discs.

[0133] The foregoing are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will readily think of other embodiments of the present disclosure after considering the specification and the practice of the disclosed truth.

[0134] The present application aims to cover any variations, uses, or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for integrating multiple business data, characterized in that: The method comprises: Acquire multiple business data of a target water conservancy project, wherein the multiple business data includes original business data of multiple different dimensions; Performing data preprocessing and normalization processing on each of the original business data in turn to obtain each standard business data; Classify the standard business data according to the data characteristics of each of the standard business data to obtain a classification result; Establishing a water conservancy data association network based on the classification results; A hydraulic mutation index calculation model is constructed, which comprehensively considers the jump amplitude, change rate and duration of the data, identifies the mutation points in the data by performing wavelet transform and singular spectrum analysis on the node data, and calculates the hydraulic mutation index of each node in the water conservancy data association network; at the same time, an adaptive threshold mechanism is introduced to dynamically adjust the mutation judgment standard according to different working conditions and seasonal characteristics; after determining the node mutation characteristics, a graph traversal algorithm is used to track the propagation path of the mutation based on the transmission direction in the water conservancy data association network, and the source node and affected node of the mutation are identified by analyzing the spatiotemporal evolution law of the mutation characteristics; the mutation index is combined with the propagation path information to construct an early warning information trigger chain, which includes mutation detection, impact assessment and early warning level determination, so as to realize the early detection of mutation events and chain reaction prediction; the operating parameter combination of the nodes in the water conservancy data association network is extracted, the change characteristics of the parameter combination are analyzed, and the operating status interval of each part of the project is obtained; Calculating a performance transfer chain based on the hierarchical structure of the water conservancy data association network, and generating a performance evaluation result based on the performance transfer chain; The warning information trigger chain, operating status interval and performance evaluation result are mapped to a preset engineering structure layout to obtain a multi-dimensional correlation view.

2. The multi-business data integration method according to claim 1, characterized in that: The obtaining of the multi-business data of the target water conservancy project includes: Based on the historical operation data of the target water conservancy project, extract the data change characteristics of key parts of the project to obtain data characteristic indicators; Determine the data collection frequency based on the data characteristic index, and acquire original business data of different dimensions based on the data collection frequency and using distributed data collection nodes, wherein the distributed data collection nodes exchange data through an edge computing network; Each of the original business data is converted into a preset standard data format to obtain the multivariate business data of the target water conservancy project.

3. The multi-business data integration method according to claim 1, characterized in that: The data preprocessing and normalization processing are performed on each of the original business data in sequence to obtain each standard business data, including: Extracting time series features of each of the original business data, and performing segmentation processing on the data based on the time series features; Calculate the data density of each data segment after segmentation processing, interpolate and supplement the data segment whose data density is not higher than the density threshold, and downsample the data segment whose data density is higher than the density threshold to obtain a first business data set; Determining different filtering parameters based on the time span of each of the data segments, and filtering each of the data segments in the first business data set according to the filtering parameters to obtain a second business data set; Rejoining the data segments in the second business data set and performing data smoothing processing to obtain preprocessed data; The pre-processed data are grouped and normalized according to data characteristic indicators to obtain various standard business data.

4. The multi-business data integration method according to claim 1, characterized in that: The classification is performed according to the data features of each of the standard business data to obtain the classification results, including: Extracting hydraulic characteristic parameters of each of the standard business data and generating a characteristic description matrix; Calculating the similarity between each of the standard business data based on the feature description matrix, classifying the standard business data with a similarity greater than a first threshold into the same category, and obtaining a first classification result; In the first classification result, the hydraulic correlation between different categories of data is calculated, and the data categories with hydraulic correlation greater than the second threshold are merged to obtain a second classification result; Extracting common features and difference features of each type of data in the second classification result, and determining attribute labels of each type of data based on the common features and difference features; The second classification result and the attribute label of the corresponding category are used as the classification result.

5. The multi-business data integration method according to claim 4, characterized in that: The step of establishing a water conservancy data association network based on the classification results includes: Connecting the data nodes with the same attribute labels in the classification results, calculating the association strength between the nodes based on the common features, and constructing an initial data subnet; Analyze the hydraulic correlation of each node in the initial data subnet, establish cross-network connections between different subnets based on the difference characteristics, and generate a hierarchical correlation structure; Calculating the hydraulic transmission characteristics between each connection node in the hierarchical association structure, and determining the directionality of the network connection based on the hydraulic transmission characteristics; The hierarchical association structure and the directionality of the corresponding network connections are integrated into a water conservancy data association network.

6. The multi-business data integration method according to claim 1, characterized in that: The method further comprises: Extracting the propagation characteristics of the warning information in the multi-dimensional correlation view, and calculating the risk diffusion path to obtain a risk prevention and control network; Analyze the risk level of each part of the project based on the risk prevention and control network and generate an emergency response plan; The emergency response plan is integrated into the multi-dimensional association view to achieve active prevention and control of engineering risks.

7. A multi-business data integration system, characterized in that: The system comprises: A data acquisition module is used to acquire multiple business data of a target water conservancy project, wherein the multiple business data includes original business data of multiple different dimensions; A data processing module, used to perform data preprocessing and normalization processing on each of the original business data in turn to obtain each standard business data; A data classification module, used to classify the standard business data according to the data characteristics of each of the standard business data to obtain a classification result; A data integration module, used for establishing a water conservancy data association network based on the classification results; A hydraulic mutation index calculation model is constructed. The model comprehensively considers the jump amplitude, change rate and duration of the data. By performing wavelet transform and singular spectrum analysis on the node data, the mutation points in the data are identified, and the hydraulic mutation index of each node in the water conservancy data association network is calculated. At the same time, an adaptive threshold mechanism is introduced to dynamically adjust the mutation judgment criteria according to different working conditions and seasonal characteristics. After determining the node mutation characteristics, a graph traversal algorithm is used to track the propagation path of the mutation based on the transmission direction in the water conservancy data association network. By analyzing the spatiotemporal evolution of the mutation characteristics, the source node and the affected node of the mutation are identified. The mutation index Combined with the propagation path information, a warning information trigger chain is constructed, which includes mutation detection, impact assessment and warning level determination, so as to realize early detection of mutation events and chain reaction prediction; extract the operating parameter combination of the nodes in the water conservancy data association network, analyze the change characteristics of the parameter combination, and obtain the operating status range of each part of the project; calculate the performance transfer chain based on the hierarchical structure of the water conservancy data association network, and generate performance evaluation results based on the performance transfer chain; map the warning information trigger chain, operating status range and performance evaluation results to the preset project structure layout to obtain a multi-dimensional association view.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-6.

Images