Cross-network data exchange method and system, readable storage medium and computer

Abstract

The invention provides a cross-network data exchange method and system, a readable storage medium and a computer. The method comprises the following steps: filtering, cleaning and preprocessing platform data of a plurality of cross-network data platforms to obtain preprocessed data; performing data fusion on the preprocessed data by using a feature fusion algorithm, and performing key feature extraction based on a data fusion result to obtain key feature data; performing risk point and abnormal behavior identification on the historical data and the real-time data of each cross-network data platform, and performing model construction by using a machine learning algorithm and the identified risk points and abnormal behaviors to obtain a risk early warning model; and performing model optimization on the risk early warning model by using the key feature data to obtain a risk early warning optimization model, and performing operation and maintenance monitoring on each cross-network data platform by using the risk early warning optimization model. According to the invention, the block chain technology is utilized to ensure the security of data transmission, data leakage and tampering are effectively prevented, and the security of case handling circulation is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a cross-network data exchange method, system, readable storage medium and computer. Background Art

[0002] Existing case handling and transfer systems mostly rely on manual operations and lack effective automated monitoring and data exchange mechanisms. This not only increases the workload of case handlers but also affects the timeliness and accuracy of case processing.

[0003] The existing technologies mainly have the following disadvantages: low data exchange efficiency and lack of a unified data exchange standard; data security cannot be fully guaranteed, and there is a risk of data leakage; lack of effective operation and maintenance monitoring tools, and it is impossible to achieve real-time monitoring and early warning of the case handling platform. Summary of the Invention Based on this, the purpose of the present invention is to provide a cross-network data exchange method, system, readable storage medium and computer to solve the above deficiencies in the technology.

[0004] The present invention proposes a cross-network data exchange method, including: Collecting platform data of several cross-network data platforms, and performing filtering, cleaning and preprocessing on the platform data to obtain preprocessed data; Performing data fusion on the preprocessed data by using a preset feature fusion algorithm, and extracting key features based on the data fusion result to obtain corresponding key feature data; Obtaining historical data and real-time data of each cross-network data platform, and identifying risk points and abnormal behaviors in the historical data and the real-time data. Using machine learning algorithms and the identified risk points and abnormal behaviors to construct a model to obtain a risk warning model; Using the key feature data to optimize the risk warning model to obtain an optimized risk warning model, and using the optimized risk warning model to perform operation and maintenance monitoring on each cross-network data platform.

[0005] Further, the step of performing filtering, cleaning and preprocessing on the platform data to obtain preprocessed data includes: Performing preliminary processing on the platform data to remove irrelevant data and unify the data format to obtain preliminarily processed data; Performing data review on the preliminarily processed data, and performing data processing on missing data and abnormal data to obtain preprocessed data.

[0006] Further, the step of performing data fusion on the preprocessed data by using a preset feature fusion algorithm, and extracting key features based on the data fusion result to obtain corresponding key feature data includes: Perform data fusion on the preprocessed data using a preset feature fusion algorithm, and extract core information from the data fusion result to obtain corresponding core information; Denoise the core information, and process abnormal data in the denoised core information to obtain key feature data.

[0007] Further, the steps of using a machine learning algorithm and the identified risk points and abnormal behaviors to construct a model to obtain a risk warning model include: Obtain the historical data of each of the cross-network data platforms, and perform data cleaning, data transformation, and data standardization on the historical data to obtain processed historical data; Extract features from the processed historical data, and use a preset machine learning algorithm and the extracted feature data to train a preset learning model to obtain a learning optimization model; Evaluate the learning optimization model, and optimize the parameters of the learning optimization model based on the model evaluation result to obtain a risk warning model. The present invention also proposes a cross-network data exchange system, including: A data preprocessing module, configured to collect platform data of several cross-network data platforms, and perform filtering, cleaning, and preprocessing on the platform data to obtain preprocessed data; A data fusion module, configured to perform data fusion on the preprocessed data using a preset feature fusion algorithm, and perform key feature extraction based on the data fusion result to obtain corresponding key feature data; A model construction module, configured to obtain the historical data and real-time data of each of the cross-network data platforms, identify risk points and abnormal behaviors in the historical data and the real-time data, and use a machine learning algorithm and the identified risk points and abnormal behaviors to construct a model to obtain a risk warning model; An operation and maintenance monitoring module, configured to optimize the risk warning model using the key feature data to obtain a risk warning optimized model, and use the risk warning optimized model to perform operation and maintenance monitoring on each of the cross-network data platforms.

[0008] Further, the data preprocessing module includes: A preliminary processing unit, configured to perform preliminary processing on the platform data to remove irrelevant data and unify the data format to obtain preliminary processed data; A data review unit, configured to review the preliminary processed data and perform data processing on missing data and abnormal data to obtain preprocessed data.

[0009] Further, the data fusion module includes: An information extraction unit, configured to perform data fusion on the preprocessed data by using a preset feature fusion algorithm, and extract core information from the data fusion result to obtain corresponding core information; A data denoising unit, configured to perform data denoising on the core information, and process abnormal data on the core information after data denoising to obtain key feature data.

[0010] Further, the model construction module includes: A historical data acquisition unit, configured to acquire historical data of each of the cross-network data platforms, and perform data cleaning, data conversion, and data standardization on the historical data to obtain processed historical data; A feature extraction unit, configured to extract features from the processed historical data, and perform model training on a preset learning model by using a preset machine learning algorithm and the extracted feature data to obtain a learning optimized model; A parameter optimization unit, configured to perform model evaluation on the learning optimized model, and perform parameter optimization on the learning optimized model based on the model evaluation result to obtain a risk warning model. The present invention also provides a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned cross-network data exchange method is implemented.

[0011] The present invention also provides a computer, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the above-mentioned cross-network data exchange method is implemented.

[0012] In the cross-network data exchange method, system, readable storage medium, and computer of the present invention, by performing data processing on the platform data of the cross-network data platform, the efficiency and accuracy of data exchange are improved through a unified data exchange format, the processing time caused by inconsistent formats or data redundancy is reduced, a risk warning model is obtained by constructing a model by using a machine learning algorithm and the identified risk points and abnormal behaviors, and the security of data transmission is ensured by using blockchain technology, effectively preventing data leakage and tampering, and enhancing the security of case handling circulation; by constructing a risk warning optimization model to perform operation and maintenance monitoring on the cross-network data platform, the case handling efficiency and the stability of the platform are improved. Description of the Drawings

[0013] Figure 1 It is a flowchart of the cross-network data exchange method in the first embodiment of the present invention; Figure 2 is Figure 1 a detailed flowchart of step S101 in Figure 3 isFigure 1 The detailed flowchart of step S102 in Figure 4 is Figure 1 the detailed flowchart of step S103 in Figure 5 the structural block diagram of the cross-network data exchange system in the second embodiment of the present invention; Figure 6 the structural block diagram of the computer in the third embodiment of the present invention.

[0014] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. Specific Embodiments

[0015] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0017] Embodiment 1 Please refer to Figure 1 , which shows the cross-network data exchange method in the first embodiment of the present invention. The method specifically includes steps S101 to S104: S101, collecting platform data of several cross-network data platforms, and performing filtering, cleaning, and preprocessing on the platform data to obtain preprocessed data; Further, please refer to Figure 2 , the step S101 specifically includes steps S1011~S1012: S1011, performing preliminary processing on the platform data to remove irrelevant data and unify the data format to obtain preliminarily processed data; S1012, performing data verification on the preliminarily processed data, and performing data processing on missing data and abnormal data to obtain preprocessed data.

[0018] In the specific implementation, through the professional analysis capabilities of inventorying the data of each asset, we can understand the capabilities of each asset and conduct detailed statistics and analysis of assets through multiple dimensions. This process will generate a comprehensive asset report, thereby ensuring the efficient management and rational use of assets.

[0019] Furthermore, in the cross-network area, operators’ dedicated lines, routers, firewalls, intrusion prevention systems, core switches, network gates and other equipment are purchased and deployed to realize cross-network communication, collect and process criminal case flow data of the case handling platform, heartbeat packet data of server communication, heartbeat packet data of the cross-network case handling system, network gate status data, database and middleware status data, storage host status and capacity data, application system service status data, and perform data filtering and cleaning. The algorithm used and its implementation process are as follows: 1. Data cleaning refers to the process of discovering inaccurate, incomplete or unreasonable data in a data set and repairing or removing it to improve data quality. It includes the following steps: 1. Data preprocessing: Perform preliminary processing on the collected data, remove irrelevant data, unify the data format, and lay the foundation for subsequent operations.

[0020] 2. Data review: Conduct a comprehensive review of the data to check whether the data conforms to business logic and whether there are obvious errors or unreasonableness.

[0021] 3. Missing value processing: For missing data, methods such as deletion and filling can be used to process it. For example, delete samples or variables with a large number of missing values; use statistics such as mean, median, mode, etc. to fill; use other variables for prediction and filling, etc.

[0022] 4. Outlier processing: Outliers refer to data points in a data set that deviate significantly from other observations. For outliers, you can adopt strategies such as deletion, correction, and retention. If the outlier is caused by input errors, it should be corrected; if it is caused by measurement errors, you can choose to delete or correct it according to the actual situation; if the outlier does exist and reflects a special situation, it should be retained.

[0023] 5. Duplicate value processing: Find and merge duplicate records to avoid data redundancy.

[0024] 6. Data conversion: Perform appropriate conversion on the data, such as discretizing numerical data and encoding categorical data.

[0025] 7. Standardization processing: Standardize the data to make it conform to certain specifications and standards.

[0026] Furthermore, the data filtering and cleaning adopts the following algorithm: 1. Bin method: The data to be processed is put into bins according to certain rules, and then the data in each bin is tested, and methods are adopted to process the data according to the actual situation of each bin in the data.

[0027] 2. Clustering method: Abstract objects are grouped into different sets, and outliers outside the sets are found. These outliers are noise, so the noise points can be directly discovered and then removed.

[0028] Specifically, when implementing data cleaning, ensure the consistency and repeatability of each cleaning operation. This includes: formulating clear data quality standards: clarifying the requirements for aspects such as data accuracy, integrity, consistency, and timeliness; performing data cleaning operations: processing various types of collected data according to the steps and algorithms of data cleaning; verifying the cleaning results: verifying the cleaned data to ensure data accuracy and consistency; standardization processing: performing standardization processing on the cleaned data for subsequent analysis; documentation: recording error instances and error types, and modifying the data entry program to reduce future errors; regularly conducting data quality assessments: regularly assessing the quality of the cleaned data to promptly discover problems and make adjustments.

[0029] S102, perform data fusion on the preprocessed data using a preset feature fusion algorithm, and extract key features based on the data fusion result to obtain corresponding key feature data; Further, please refer to Figure 3 , the step S102 specifically includes steps S1021~S1022: S1021, perform data fusion on the preprocessed data using a preset feature fusion algorithm, and extract core information from the data fusion result to obtain corresponding core information; S1022, perform data denoising on the core information, and perform abnormal data processing on the core information after data denoising to obtain key feature data.

[0030] In specific implementation, technologies such as Zabbix, Prometheus, Grafana, SkyWalking, API open interfaces, and Rsync Shell scripts are used to fuse data, collect data from different sources, and integrate it into a unified platform. After data fusion, it enters the preprocessing stage, where the data is initially cleaned and sorted to remove duplicate, invalid, and abnormal data. Through preprocessing, the quality of the subsequent analysis data can be ensured. Next, key features are extracted from the preprocessed data, including link operation status, traffic peaks, data exchange time consumption, and trace tracks. These features can reflect the core information and laws of the data, providing strong support for big data analysis. During the implementation process, various algorithms are used to assist in data filtering and cleaning. For example, clustering algorithms are used to identify outliers and noise in the data, and association rule mining algorithms are used to discover the relevance and dependence between data. The application of these algorithms can further improve the accuracy and efficiency of data cleaning.

[0031] S103, Obtain the historical data and real-time data of each of the cross-network data platforms, identify risk points and abnormal behaviors in the historical data and the real-time data, and use machine learning algorithms and the identified risk points and abnormal behaviors to construct a model to obtain a risk warning model; Further, please refer to Figure 4 , The step S103 specifically includes steps S1031 to S1033: S1031, Obtain the historical data of each of the cross-network data platforms, and perform data cleaning, data transformation, and data standardization on the historical data to obtain processed historical data; S1032, Extract features from the processed historical data, and use a preset machine learning algorithm and the extracted feature data to train a preset learning model to obtain a learning optimization model; S1033, Evaluate the learning optimization model, and optimize the parameters of the learning optimization model based on the model evaluation results to obtain a risk warning model.

[0032] In specific implementation, on the basis of asset management and data preprocessing, a risk warning model is further constructed. By analyzing historical data and real-time data, potential risk points and abnormal behavior patterns are identified. Machine learning algorithms, such as random forest, support vector machine, or neural network, are used to classify and score risks, so as to achieve early detection and warning of risks.

[0033] Specifically, a machine learning algorithm is used for classification and scoring. An appropriate machine learning algorithm is selected, such as random forest, support vector machine, or neural network, etc., and classification and scoring are performed according to the characteristics of the data; the selected algorithm is trained. This requires the use of labeled data, that is, a data set containing known classifications and scores. Through training, the algorithm can learn the characteristics and rules in the data, so as to classify and score new data; the trained model is applied to predict new data; the new data is input into the model, and the model will classify and score the data according to the learned characteristics and rules.

[0034] Furthermore, the process of constructing the model includes the following steps: 1. Data collection and preprocessing. Sufficient high-quality data is collected, and operations such as cleaning, transformation, and standardization are performed to meet the requirements of the model.

[0035] 2. Feature selection and extraction. Select those features from the original data that have a strong influence on the prediction target, reducing the model complexity and the risk of overfitting. This can be achieved by analyzing the importance weight coefficients of the features, and selecting the features with higher weight coefficients as input variables.

[0036] 3. Model selection and training. According to the characteristics of the problem and the nature of the data, an appropriate machine learning algorithm is selected, and the algorithm is trained using the training data set. During the training process, the parameters of the model need to be continuously adjusted to optimize the performance of the model.

[0037] 4. Model evaluation and optimization. The trained model is evaluated using the test data set to check the classification and scoring accuracy of the model. If the performance of the model is not good, optimization is required, such as adjusting parameters, adding features, or selecting other algorithms, etc.

[0038] Specifically, a risk warning model is constructed. By analyzing historical data and real-time data, potential risk points and abnormal behavior patterns are identified, and in-depth exploration and analysis of the data are carried out to discover the rules and trends in the data. Machine learning algorithms are used to classify and score risks. According to the identified risk points and abnormal behavior patterns, appropriate machine learning algorithms are selected to classify and score risks, so as to timely discover potential risk factors and take corresponding measures to reduce or avoid risks, achieving early discovery and warning of risks. By constructing a risk warning model, corresponding measures can be taken before the risk occurs, thereby avoiding or reducing the losses caused by the risk, which helps to improve the risk management level.

[0039] S104, using the key feature data to optimize the risk warning model to obtain an optimized risk warning model, and using the optimized risk warning model to perform operation and maintenance monitoring on each cross-network data platform.

[0040] In specific implementation, the results of feature extraction are combined with the risk warning model for comprehensive analysis. Through data mining techniques such as association rule mining and clustering analysis, the internal relationships and patterns between data are explored in depth. Through association rule mining, the correlations between different factors can be discovered. For example, the combination of certain specific features may indicate an increase in risk. Clustering analysis can group similar data points into one category to identify different risk groups or asset status categories. These rules can not only help to understand the asset operation status more deeply but also serve as important inputs for the risk warning model, improving the prediction accuracy and reliability of the model. In subsequent calculations, these rules can be used to optimize the risk warning model, enhancing the scientific nature and effectiveness of decision-making.

[0041] Furthermore, to ensure the accuracy and reliability of the warning system, the constructed risk warning model needs to be strictly tested and verified. First, a series of actual cases are selected as the test data set. These data sets cover various possible risk scenarios to ensure the comprehensiveness and accuracy of the verification. These actual cases are input into the constructed risk warning model for prediction. The prediction results will be compared and analyzed with the actual situations of the actual cases. The prediction ability of the model is evaluated by calculating indicators such as prediction accuracy and recall rate. During the comparison and analysis process, if there are deviations between the prediction results of the model and the actual situations, the model parameters will be adjusted and optimized according to the feedback results to improve the prediction accuracy of the model. Through the comparison and analysis with the actual cases, the prediction ability of the model is evaluated, and the model parameters are continuously adjusted and optimized according to the feedback results. In addition, in this embodiment, the system is regularly maintained and upgraded to adapt to the changing business requirements and technical environment. Through this series of strict test and verification steps, the accuracy and reliability of the risk warning model can be ensured, providing a strong guarantee for risk management.

[0042] In summary, in the cross-network data exchange method of the above embodiments of the present invention, by processing the platform data of the cross-network data platform, the efficiency and accuracy of data exchange are improved through a unified data exchange format, reducing the processing time caused by inconsistent formats or data redundancy. A risk warning model is constructed using machine learning algorithms and the identified risk points and abnormal behaviors. The blockchain technology is used to ensure the security of data transmission, effectively preventing data leakage and tampering, and enhancing the security of case handling circulation. By constructing a risk warning optimization model to monitor the operation and maintenance of the cross-network data platform, the case handling efficiency and the stability of the platform are improved.

[0043] Embodiment 2 On the other hand, the present invention also proposes a cross-network data exchange system. Please refer to Figure 5 , which shows the cross-network data exchange system in the second embodiment of the present invention. The system includes: A data preprocessing module 11, configured to collect platform data of a plurality of cross-network data platforms, and perform filtering, cleaning, and preprocessing on the platform data to obtain preprocessed data; Further, the data preprocessing module 11 includes: A preliminary processing unit, configured to perform preliminary processing on the platform data to remove irrelevant data and unify the data format to obtain preliminarily processed data; A data auditing unit, configured to perform data auditing on the preliminarily processed data, and perform data processing on missing data and abnormal data to obtain preprocessed data.

[0044] A data fusion module 12, configured to perform data fusion on the preprocessed data by using a preset feature fusion algorithm, and perform key feature extraction based on the data fusion result to obtain corresponding key feature data; Further, the data fusion module 12 includes: An information extraction unit, configured to perform data fusion on the preprocessed data by using a preset feature fusion algorithm, and perform core information extraction on the data fusion result to obtain corresponding core information; A data denoising unit, configured to perform data denoising on the core information, and perform abnormal data processing on the core information after data denoising to obtain key feature data.

[0045] A model construction module 13, configured to obtain historical data and real-time data of each of the cross-network data platforms, identify risk points and abnormal behaviors in the historical data and the real-time data, and use a machine learning algorithm and the identified risk points and abnormal behaviors to construct a model to obtain a risk warning model; Further, the model construction module 13 includes: A historical data acquisition unit, configured to obtain historical data of each of the cross-network data platforms, and perform data cleaning, data conversion, and data standardization on the historical data to obtain processed historical data; A feature extraction unit, configured to perform feature extraction on the processed historical data, and use a preset machine learning algorithm and the extracted feature data to train a preset learning model to obtain a learning optimized model; A parameter optimization unit, configured to perform model evaluation on the learning optimized model, and perform parameter optimization on the learning optimized model based on the model evaluation result to obtain a risk warning model.

[0046] An operation and maintenance monitoring module 14, configured to use the key feature data to optimize the risk warning model to obtain an optimized risk warning model, and use the optimized risk warning model to perform operation and maintenance monitoring on each of the cross-network data platforms.

[0047] The functions or operation steps realized when the above-mentioned modules and units are executed are substantially the same as those in the above method embodiment, and will not be elaborated here.

[0048] The cross-network data exchange system provided by the embodiment of the present invention has the same implementation principle and technical effects as those in the foregoing method embodiment. For a brief description, for the parts not mentioned in the system embodiment, reference may be made to the corresponding content in the foregoing method embodiment.

[0049] Embodiment III The present invention also proposes a computer. Please refer to Figure 6 , which shows the computer in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored on the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned cross-network data exchange method is realized.

[0050] Among them, the memory 10 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 10 can be an internal storage unit of the computer in some embodiments, such as the hard disk of the computer. The memory 10 can also be an external storage device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 10 can also include both an internal storage unit and an external storage device of the computer. The memory 10 can be used not only to store application software and various types of data installed in the computer, but also to temporarily store data that has been output or will be output.

[0051] Among them, the processor 20 can be an Electronic Control Unit (ECU, also known as a vehicle computer), a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments, and is used to run the program code stored in the memory 10 or process data, such as executing an access restriction program, etc.

[0052] It should be noted that Figure 6 The structure shown does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown in the figure, or combine some components, or arrange different components.

[0053] An embodiment of the present invention also provides a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the cross-network data exchange method as described above is implemented.

[0054] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0055] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0056] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following well-known technologies in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field-programmable gate arrays (FPGA), etc.

[0057] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0058] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A cross-network data exchange method, characterized in that: include: Collecting platform data from a number of cross-network data platforms, and filtering, cleaning and preprocessing the platform data to obtain preprocessed data; Using a preset feature fusion algorithm to perform data fusion on the preprocessed data, and extracting key features based on the data fusion result to obtain corresponding key feature data; Acquire historical data and real-time data of each cross-network data platform, identify risk points and abnormal behaviors of the historical data and the real-time data, and construct a model using a machine learning algorithm and the identified risk points and abnormal behaviors to obtain a risk warning model; The risk warning model is optimized using the key feature data to obtain a risk warning optimization model, and the risk warning optimization model is used to perform operation and maintenance monitoring on each of the cross-network data platforms.

2. The cross-network data exchange method according to claim 1, characterized in that: The step of filtering, cleaning and preprocessing the platform data to obtain preprocessed data includes: Preliminarily processing the platform data to remove irrelevant data and unify the data format to obtain preliminary processed data; The preliminary processed data are audited, and data processing is performed on missing data and abnormal data to obtain preprocessed data.

3. The cross-network data exchange method according to claim 1, characterized in that: The steps of fusing the preprocessed data using a preset feature fusion algorithm and extracting key features based on the data fusion result to obtain corresponding key feature data include: The pre-processed data is fused using a preset feature fusion algorithm, and core information is extracted from the data fusion result to obtain corresponding core information; The core information is subjected to data denoising, and abnormal data processing is performed on the core information after data denoising to obtain key feature data.

4. The cross-network data exchange method according to claim 1, characterized in that: The steps of using machine learning algorithms and the identified risk points and abnormal behaviors to build a model to obtain a risk warning model include: Acquire historical data from each of the cross-network data platforms, and perform data cleaning, data conversion, and data standardization on the historical data to obtain processed historical data; Extracting features from the processed historical data, and training a preset learning model using a preset machine learning algorithm and the extracted feature data to obtain a learning optimization model; A model evaluation is performed on the learning optimization model, and parameters of the learning optimization model are optimized based on the model evaluation result to obtain a risk warning model.

5. A cross-network data exchange system, characterized in that: include: A data preprocessing module is used to collect platform data of several cross-network data platforms and perform filtering, cleaning and preprocessing on the platform data to obtain preprocessed data; A data fusion module, used to perform data fusion on the pre-processed data using a preset feature fusion algorithm, and extract key features based on the data fusion result to obtain corresponding key feature data; A model building module, used to obtain historical data and real-time data of each cross-network data platform, identify risk points and abnormal behaviors of the historical data and the real-time data, and build a model using a machine learning algorithm and the identified risk points and abnormal behaviors to obtain a risk warning model; The operation and maintenance monitoring module is used to optimize the risk warning model using the key feature data to obtain a risk warning optimization model, and use the risk warning optimization model to perform operation and maintenance monitoring on each of the cross-network data platforms.

6. The inter-network data exchange system according to claim 5, characterized in that: The data preprocessing module comprises: A preliminary processing unit, used for performing preliminary processing on the platform data to remove irrelevant data and unify the data format to obtain preliminary processed data; The data review unit is used to review the preliminary processed data and process missing data and abnormal data to obtain pre-processed data.

7. The inter-network data exchange system according to claim 5, characterized in that: The data fusion module comprises: An information extraction unit, used to perform data fusion on the preprocessed data using a preset feature fusion algorithm, and extract core information from the data fusion result to obtain corresponding core information; The data denoising unit is used to perform data denoising on the core information and perform abnormal data processing on the core information after data denoising to obtain key feature data.

8. The inter-network data exchange system according to claim 5, characterized in that: The model building module includes: A historical data acquisition unit, used to acquire the historical data of each cross-network data platform, and perform data cleaning, data conversion and data standardization on the historical data to obtain processed historical data; A feature extraction unit, used to extract features from the processed historical data, and to train a preset learning model using a preset machine learning algorithm and the extracted feature data to obtain a learning optimization model; The parameter optimization unit is used to perform model evaluation on the learning optimization model and optimize the parameters of the learning optimization model based on the model evaluation result to obtain a risk warning model.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the cross-network data exchange method as described in any one of claims 1 to 4 is implemented.

10. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the cross-network data exchange method as described in any one of claims 1 to 4 is implemented.

Images