Big data transaction security management and control method and system
By using AES-256 encryption algorithm and blockchain platform in big data transactions, combined with the risk identification technology of XGBoost and LR models, the security threat problem in big data transactions has been solved, and the security and user trust has been significantly improved, and the security and user trust has been achieved. Maximize the use of data value.
Patent Information
- Application Number
- CN202410996916.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
There are serious security threats in big data transactions, such as data breaches, privacy infringement and illegal transactions, resulting in the abuse of data resources and the destruction of market order. It is difficult for existing technology to effectively solve these problems.
The AES-256 encryption algorithm is used to encrypt the big data transaction data and upload it to the blockchain trading platform. It combines the XGBoost extreme gradient enhancement algorithm and the LR binary classification model to establish a transaction risk identification model, monitor and warning in real time to prevent abnormal transactions model.
It significantly improves the security of big data transactions, reduces the risk of data leakage, enhances user trust, ensures the security of data during transmission and storage, realizes the maximum utilization of data value and the protection of personal privacy, and is for digital The sustainable economic growth provides technical support.
Smart Images

Figure CN118982355A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of big data analysis, and in particular to a big data transaction security management and control method and system thereof. Background Art
[0002] With the rapid development and popularization of information technology, big data has become an important engine to promote the sustainable progress of modern social economy. Big data not only provides unprecedented insights for business decisions, but also shows great potential and value in many fields such as medical care, education, and transportation. However, at the same time, security issues in big data transactions have gradually been exposed, becoming a bottleneck restricting the effective use and legal circulation of data resources. In the process of big data transactions, security threats such as data leakage, privacy infringement, and illegal transactions are becoming increasingly serious. Data leakage may cause sensitive information to be used by criminals to conduct illegal activities such as fraud and extortion, posing a serious threat to the property security of individuals and enterprises. Privacy infringement may infringe on the privacy rights of individuals and damage their legitimate rights and interests. Illegal transactions may lead to the abuse and waste of data resources, disrupting market order and fair competition. Therefore, how to ensure the security of big data transactions and conduct risk prediction, real-time monitoring and early warning are technical issues that need to be solved at this stage. Summary of the invention
[0003] The purpose of the present invention is to solve the above problems and to design a big data transaction security management and control method and system.
[0004] To achieve the above object, the technical solution of the present invention is that, further, in the above-mentioned big data transaction security management and control method, the big data transaction security management and control method comprises the following steps:
[0005] Acquire big data transaction data, and encrypt the big data transaction data using an AES-256 encryption algorithm to obtain encrypted big data transaction data;
[0006] Establishing a blockchain transaction platform, and uploading the encrypted big data transaction data to the blockchain transaction platform;
[0007] Acquire real-time transaction information data in the blockchain transaction platform, and perform data processing on the real-time transaction information data;
[0008] The XGBoost transaction risk identification model is established based on the XGBoost extreme gradient boosting algorithm, and the LR binary classification model is combined with the XGBoost transaction risk identification model to obtain the XGBoost-LR transaction risk identification model; the processed access information data is transmitted to the XGBoost-LR transaction risk identification model for identification to obtain the transaction risk results;
[0009] If the transaction risk result is an abnormal transaction mode, an early warning is issued to the server terminal, and the early warning information is transmitted to the mobile terminal.
[0010] Furthermore, in the above-mentioned big data transaction security management and control method, the obtaining of big data transaction data, and encrypting the big data transaction data using the AES-256 encryption algorithm to obtain encrypted big data transaction data include:
[0011] Generate a 256-bit key that meets the requirements of AES-256, and segment the big data transaction data to obtain segmented big data transaction data;
[0012] Implementing a segmented encryption strategy of a key, applying an AES-256 algorithm to encrypt the segmented big data transaction data to obtain initial big data transaction data;
[0013] According to the structure of the original data, the initial big data transaction data is reorganized into a format suitable for storage and transmission to obtain reorganized big data transaction data;
[0014] By calculating the hash value of the data before and after encryption and adding verification information to the data packet, the verification big data transaction data is obtained;
[0015] The verification big data transaction data is transmitted using a secure storage medium or through an encrypted SSL protocol to obtain encrypted big data transaction data.
[0016] Furthermore, in the above-mentioned big data transaction security management and control method, uploading the encrypted big data transaction data to the blockchain transaction platform includes:
[0017] Design the architecture of the blockchain platform using the public blockchain type to obtain a blockchain trading platform;
[0018] Define the rules for data uploading, storage, querying and trading of the blockchain trading platform, and upload the encrypted big data transaction data to the blockchain trading platform.
[0019] Furthermore, in the above-mentioned big data transaction security management and control method, the real-time transaction information data in the blockchain transaction platform is obtained, and the real-time transaction information data is processed, including:
[0020] Acquire real-time transaction information data in the blockchain transaction platform, remove invalid or incomplete data packets in the real-time transaction information, and obtain complete real-time transaction information data;
[0021] The complete real-time transaction information data is converted and standardized into a unified format according to preset rules to obtain unique real-time transaction information data;
[0022] Identify the unique real-time transaction information data through key fields such as transaction ID, and remove duplicate transaction records to obtain deduplicated real-time transaction information data;
[0023] Outlier values are deleted and missing values are filled in the deduplicated real-time transaction information data to obtain target real-time transaction information data.
[0024] Furthermore, in the above-mentioned big data transaction security management and control method, an XGBoost transaction risk identification model is established according to the XGBoost extreme gradient boosting algorithm, and the LR binary classification model is combined with the XGBoost transaction risk identification model to obtain an XGBoost-LR transaction risk identification model; the processed access information data is transmitted to the XGBoost-LR transaction risk identification model for identification, and a transaction risk result is obtained, including:
[0025] An XGBoost transaction risk identification model is established according to the XGBoost extreme gradient boosting algorithm. The XGBoost transaction risk identification model consists of two decision trees, where tree 1 has three leaf nodes and tree 2 has two leaf nodes, and each leaf node is regarded as a new feature.
[0026] The target real-time transaction information data output value is input into the XGBoost transaction risk identification model, and the output result is a one-hot encoded data set; wherein the node value of the input data set falling into the decision tree is 1, and the node value of the input data set not falling into the decision tree is 0;
[0027] Extracting features of the one-hot encoded data set to obtain a feature one-hot encoded data set;
[0028] The feature one-hot encoding dataset is input into the LR binary classification model for training and testing to obtain the transaction risk results.
[0029] Furthermore, in the above-mentioned big data transaction security management and control method, if the transaction risk result is an abnormal transaction mode, an early warning is issued to the server terminal, and the early warning information is transmitted to the mobile terminal, including:
[0030] If the transaction risk result is an abnormal transaction mode, an early warning is sent to the server terminal, and an emergency response mechanism is automatically triggered, and the emergency response mechanism at least includes temporarily freezing the transaction rights of the relevant account;
[0031] Establish an early warning log system to record information such as warning time, warning level, accounts involved and processing status;
[0032] Relevant managers and users involved will be notified instantly through mobile application push, SMS, email, etc.
[0033] Furthermore, in a big data transaction security management and control system, the big data transaction security management and control system includes the following modules:
[0034] A data encryption module is used to obtain big data transaction data, and encrypt the big data transaction data using an AES-256 encryption algorithm to obtain encrypted big data transaction data;
[0035] A platform establishment module, used to establish a blockchain transaction platform and upload the encrypted big data transaction data to the blockchain transaction platform;
[0036] A data processing module, used to obtain real-time transaction information data in the blockchain transaction platform and perform data processing on the real-time transaction information data;
[0037] The model building module is used to build an XGBoost transaction risk identification model based on the XGBoost extreme gradient boosting algorithm, and combine the LR binary classification model with the XGBoost transaction risk identification model to obtain the XGBoost-LR transaction risk identification model;
[0038] The information identification module is used to transmit the processed access information data to the XGBoost-LR transaction risk identification model for identification to obtain the transaction risk results;
[0039] The security warning module is used to warn the server terminal if the transaction risk result is an abnormal transaction mode, and transmit the warning information to the mobile terminal.
[0040] Furthermore, in a big data transaction security management and control system, the data encryption module includes the following submodules:
[0041] A generating submodule, used for generating a 256-bit key that meets the requirements of AES-256, and segmenting the big data transaction data to obtain segmented big data transaction data;
[0042] An encryption submodule, used for implementing a segmented encryption strategy of a key, encrypting the segmented big data transaction data using an AES-256 algorithm to obtain initial big data transaction data;
[0043] An integration submodule, used to reorganize the initial big data transaction data into a format suitable for storage and transmission according to the structure of the original data, to obtain reorganized big data transaction data;
[0044] The verification submodule is used to obtain the verification big data transaction data by calculating the hash value of the data before and after encryption and adding the verification information to the data packet;
[0045] The transmission submodule is used to transmit the verification big data transaction data using a secure storage medium or through an encrypted SSL protocol to obtain encrypted big data transaction data.
[0046] Furthermore, in a big data transaction security management and control system, the data processing module includes the following submodules:
[0047] An acquisition submodule is used to acquire real-time transaction information data in the blockchain transaction platform, remove invalid or incomplete data packets in the real-time transaction information, and obtain complete real-time transaction information data;
[0048] A standardization submodule, used to convert and standardize the complete real-time transaction information data into a unified format according to preset rules to obtain unique real-time transaction information data;
[0049] A removal submodule, used to identify the unique real-time transaction information data through key fields such as transaction ID, and remove duplicate transaction records to obtain deduplicated real-time transaction information data;
[0050] The filling submodule is used to delete abnormal values and fill missing values in the deduplicated real-time transaction information data to obtain target real-time transaction information data.
[0051] Its beneficial effects are that by obtaining big data transaction data, the big data transaction data is encrypted by using the AES-256 encryption algorithm to obtain encrypted big data transaction data; a blockchain transaction platform is established, and the encrypted big data transaction data is uploaded to the blockchain transaction platform; real-time transaction information data in the blockchain transaction platform is obtained, and data processing is performed on the real-time transaction information data; an XGBoost transaction risk identification model is established according to the XGBoost extreme gradient boosting algorithm, and the LR binary classification model is combined with the XGBoost transaction risk identification model to obtain the XGBoost-LR transaction risk identification model; the processed access information data is transmitted to the XGBoost-LR transaction risk identification model for identification to obtain a transaction risk result; if the transaction risk result is an abnormal transaction mode, the server terminal is warned, and the warning information is transmitted to the mobile terminal. It will significantly improve the security of big data transactions, reduce the risk of data leakage, enhance user trust, and promote the healthy development of the data market. Through technological innovation, the maximum utilization of data value is achieved, while personal privacy and corporate information security are guaranteed, providing solid technical support for the sustainable growth of the digital economy. It has data encryption and desensitization technology to ensure the security of data during transmission and storage. Secondly, it should establish a complete identity authentication and access control mechanism to prevent unauthorized access and data tampering. In addition, it should also have real-time monitoring and early warning functions to promptly detect and respond to potential security threats. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the following detailed description of the preferred embodiment.The drawings are only for the purpose of illustrating the preferred embodiments and are not to be construed as limiting the invention.
[0053] Figure 1 This is a schematic diagram of a first embodiment of a method for security management and control of big data transactions in an embodiment of the present invention;
[0054] Figure 2 This is a schematic diagram of a second embodiment of a method for security management and control of big data transactions in an embodiment of the present invention;
[0055] Figure 3 This is a schematic diagram of a first embodiment of a big data transaction security management and control system in an embodiment of the present invention. DETAILED DESCRIPTION
[0056] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0057] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.
[0058] The present invention will be described in detail below in conjunction with the accompanying drawings. Figure 1 As shown, a big data transaction security management method includes the following steps:
[0059] Step 101: Obtain big data transaction data, and encrypt the big data transaction data using the AES-256 encryption algorithm to obtain encrypted big data transaction data;
[0060] Specifically, in this embodiment, a 256-bit key that meets the requirements of AES-256 is generated, and the big data transaction data is segmented to obtain segmented big data transaction data; a segmented encryption strategy of the key is implemented, and the segmented big data transaction data is encrypted using the AES-256 algorithm to obtain initial big data transaction data; according to the structure of the original data, the initial big data transaction data is reintegrated into a format suitable for storage and transmission to obtain reorganized big data transaction data; by calculating the hash value of the data before and after encryption, and adding verification information to the data packet, the verified big data transaction data is obtained; the verified big data transaction data is transmitted using a secure storage medium or through an encrypted SSL protocol to obtain encrypted big data transaction data.
[0061] Step 102: Establish a blockchain transaction platform and upload the encrypted big data transaction data to the blockchain transaction platform;
[0062] Specifically, in this embodiment, the architecture of the blockchain platform is designed using the public chain blockchain type to obtain a blockchain trading platform; the rules for data uploading, storage, querying and trading of the blockchain trading platform are defined, and the encrypted big data transaction data is uploaded to the blockchain trading platform.
[0063] Step 103: Acquire real-time transaction information data in the blockchain transaction platform and process the real-time transaction information data;
[0064] Specifically, in this embodiment, real-time transaction information data in the blockchain transaction platform is obtained, invalid or incomplete data packets in the real-time transaction information are eliminated, and complete real-time transaction information data is obtained; the complete real-time transaction information data is converted and standardized into a unified format according to preset rules to obtain unique real-time transaction information data; unique real-time transaction information data is identified through key fields such as transaction ID, and duplicate transaction records are removed to obtain deduplicated real-time transaction information data; outliers are deleted and missing values are filled in the deduplicated real-time transaction information data to obtain target real-time transaction information data.
[0065] Step 104: Establish an XGBoost transaction risk identification model based on the XGBoost extreme gradient boosting algorithm, combine the LR binary classification model with the XGBoost transaction risk identification model to obtain an XGBoost-LR transaction risk identification model; transmit the processed access information data to the XGBoost-LR transaction risk identification model for identification to obtain a transaction risk result;
[0066] Specifically, in this embodiment, an XGBoost transaction risk identification model is established according to the XGBoost extreme gradient boosting algorithm. The XGBoost transaction risk identification model consists of two decision trees, tree 1 has three leaf nodes, and tree 2 has two leaf nodes, and each leaf node is regarded as a new feature; the target real-time transaction information data is output to the XGBoost transaction risk identification model, and the output result is a one-hot encoded data set; wherein, the node value of the input data set falling into the decision tree is 1, and the node value of the input data set not falling into the decision tree is 0; the features of the one-hot encoded data set are extracted to obtain a feature one-hot encoded data set; the feature one-hot encoded data set is input into the LR binary classification model for training and testing to obtain a transaction risk result.
[0067] Specifically, in this embodiment, the XGBoost (Extreme Gradient Boosting) extreme gradient boosting algorithm is an efficient, flexible and powerful machine learning algorithm, especially showing excellent performance when processing large-scale data sets. The following is a detailed introduction to the XGBoost algorithm:
[0068] Algorithm principle:
[0069] Basics: XGBoost is an ensemble learning algorithm based on gradient boosting, which combines the prediction results of multiple weak learners (usually decision trees) to form a strong learner, thereby improving the overall performance of the model. Optimization: Compared with the traditional gradient boosting algorithm, XGBoost has been optimized in many aspects, such as introducing second-order derivative information to more accurately approximate the loss function, adding regularization terms to prevent overfitting, and using Block storage structure to achieve parallel computing.
[0070] Algorithm Features
[0071] Efficiency: XGBoost can maintain efficient performance when processing large-scale data sets through parallel computing and distributed computing. Flexibility: XGBoost supports multiple types of objective functions and loss functions, which can adapt to different learning tasks and data types. Robustness: By introducing mechanisms such as regularization terms and automatic training stop, XGBoost can automatically stop training before the model overfits, improving the robustness of the model.
[0072] Algorithm Application
[0073] Data mining: In the field of data mining, XGBoost has attracted much attention due to its high performance and wide application, and has become the preferred algorithm for many data competitions and practical applications. Recommendation system: In the recommendation system, XGBoost can recommend products or content of interest to users by analyzing their behavior and preferences. Other fields: XGBoost can also be applied to finance, medical care, transportation and other fields to solve various complex prediction and classification problems.
[0074] Algorithm parameters
[0075] The XGBoost algorithm contains multiple adjustable parameters that can affect the performance and effectiveness of the model. Here are some common parameters and their functions:eta (learning rate): a parameter that controls the learning speed of the model. A smaller learning rate can make the model more robust, but may require more iterations. max_depth (maximum depth of the tree): controls the maximum depth of the decision tree. Deeper trees can improve the expressiveness of the model, but may also lead to overfitting. min_child_weight (minimum child weight): controls the threshold of the child node sample weight to prevent overfitting. subset (sample sampling rate): controls the proportion of the data subset used for training in each round of iteration, which helps prevent overfitting. col sample_bytree (feature sampling rate): controls the proportion of the feature subset used when building each tree, which helps prevent overfitting and reduces the amount of computation.
[0076] Specifically, in this embodiment, LR (Logistic Regression) is a statistical learning method for binary classification problems. Although its name contains "regression", it is actually mainly used for classification tasks, especially binary classification problems.
[0077] Step 105: If the transaction risk result is an abnormal transaction mode, an early warning is issued to the server terminal, and the early warning information is transmitted to the mobile terminal.
[0078] Specifically, in this embodiment, if the transaction risk result is an abnormal transaction mode, an early warning is sent to the server terminal and an emergency response mechanism is automatically triggered. The emergency response mechanism at least includes temporarily freezing the transaction permissions of relevant accounts; establishing an early warning log system to record information such as the warning time, warning level, accounts involved and processing status; and immediately notifying relevant managers and users involved through mobile application push, SMS, email, etc.
[0079] Its beneficial effects are that by obtaining big data transaction data, the big data transaction data is encrypted using the AES-256 encryption algorithm to obtain encrypted big data transaction data; a blockchain transaction platform is established, and the encrypted big data transaction data is uploaded to the blockchain transaction platform; real-time transaction information data in the blockchain transaction platform is obtained, and data processing is performed on the real-time transaction information data; an XGBoost transaction risk identification model is established according to the XGBoost extreme gradient boosting algorithm, and the LR binary classification model is combined with the XGBoost transaction risk identification model to obtain the XGBoost-LR transaction risk identification model; the processed access information data is transmitted to the XGBoost-LR transaction risk identification model for identification to obtain the transaction risk result; if the transaction risk result is an abnormal transaction mode, the server terminal is warned, and the warning information is transmitted to the mobile terminal. It will significantly improve the security of big data transactions, reduce the risk of data leakage, enhance user trust, and promote the healthy development of the data market. Through technological innovation, the maximum utilization of data value is achieved, while personal privacy and corporate information security are guaranteed, providing solid technical support for the sustainable growth of the digital economy. It has data encryption and desensitization technology to ensure the security of data during transmission and storage. Secondly, it should establish a complete identity authentication and access control mechanism to prevent unauthorized access and data tampering. In addition, it should also have real-time monitoring and early warning functions to promptly detect and respond to potential security threats.
[0080] See also Figure 2 In a big data transaction security management method, obtaining big data transaction data, encrypting the big data transaction data using an AES-256 encryption algorithm, and obtaining the encrypted big data transaction data include the following steps:
[0081] Step 201: Generate a 256-bit key that meets the requirements of AES-256, and segment the big data transaction data to obtain segmented big data transaction data;
[0082] Step 202: Implement the key segment encryption strategy, apply the AES-256 algorithm to encrypt the segmented big data transaction data, and obtain the initial big data transaction data;
[0083] Step 203: According to the structure of the original data, the initial big data transaction data is reorganized into a format suitable for storage and transmission to obtain reorganized big data transaction data;
[0084] Step 204: Calculate the hash value of the data before and after encryption and add verification information to the data packet to obtain verification big data transaction data;
[0085] Step 205: Use a secure storage medium or transmit the verification big data transaction data through an encrypted SSL protocol to obtain encrypted big data transaction data.
[0086] The above is an introduction to an embodiment of a method for security management and control of big data transactions of the present invention. Figure 3 In a big data transaction security management and control system, the big data transaction security management and control system includes the following modules:
[0087] A data encryption module is used to obtain big data transaction data, encrypt the big data transaction data using an AES-256 encryption algorithm, and obtain encrypted big data transaction data;
[0088] The platform establishment module is used to establish a blockchain trading platform and upload encrypted big data transaction data to the blockchain trading platform;
[0089] The data processing module is used to obtain real-time transaction information data in the blockchain transaction platform and perform data processing on the real-time transaction information data;
[0090] The model building module is used to build an XGBoost transaction risk identification model based on the XGBoost extreme gradient boosting algorithm, and combine the LR binary classification model with the XGBoost transaction risk identification model to obtain the XGBoost-LR transaction risk identification model;
[0091] The information identification module is used to transmit the processed access information data to the XGBoost-LR transaction risk identification model for identification to obtain the transaction risk results;
[0092] The security warning module is used to warn the server terminal if the transaction risk result is an abnormal transaction mode, and transmit the warning information to the mobile terminal.
[0093] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A method for security management and control of big data transactions, characterized in that: The big data transaction security management and control method comprises the following steps: Acquire big data transaction data, and encrypt the big data transaction data using an AES-256 encryption algorithm to obtain encrypted big data transaction data; Establishing a blockchain transaction platform, and uploading the encrypted big data transaction data to the blockchain transaction platform; Acquire real-time transaction information data in the blockchain transaction platform, and perform data processing on the real-time transaction information data; The XGBoost transaction risk identification model is established based on the XGBoost extreme gradient boosting algorithm, and the LR binary classification model is combined with the XGBoost transaction risk identification model to obtain the XGBoost-LR transaction risk identification model; the processed access information data is transmitted to the XGBoost-LR transaction risk identification model for identification to obtain the transaction risk results; If the transaction risk result is an abnormal transaction mode, an early warning is issued to the server terminal, and the early warning information is transmitted to the mobile terminal.
2. A method for security management and control of big data transactions as claimed in claim 1, characterized in that: The obtaining of the big data transaction data and encrypting the big data transaction data using the AES-256 encryption algorithm to obtain the encrypted big data transaction data includes: Generate a 256-bit key that meets the requirements of AES-256, and split the big data transaction data to obtain split big data transaction data; Implementing a segmented encryption strategy of a key, applying an AES-256 algorithm to encrypt the segmented big data transaction data to obtain initial big data transaction data; According to the structure of the original data, the initial big data transaction data is reorganized into a format suitable for storage and transmission to obtain reorganized big data transaction data; By calculating the hash value of the data before and after encryption and adding verification information to the data packet, the verification big data transaction data is obtained; The verification big data transaction data is transmitted using a secure storage medium or through an encrypted SSL protocol to obtain encrypted big data transaction data.
3. A method for security management and control of big data transactions as claimed in claim 1, characterized in that: The step of establishing a blockchain transaction platform and uploading the encrypted big data transaction data to the blockchain transaction platform includes: Design the architecture of the blockchain platform using the public blockchain type to obtain a blockchain trading platform; Define the rules for data uploading, storage, querying and trading of the blockchain trading platform, and upload the encrypted big data transaction data to the blockchain trading platform.
4. A method for security management and control of big data transactions as claimed in claim 1, characterized in that: The obtaining of real-time transaction information data in the blockchain transaction platform and processing the real-time transaction information data includes: Acquire real-time transaction information data in the blockchain transaction platform, remove invalid or incomplete data packets in the real-time transaction information, and obtain complete real-time transaction information data; The complete real-time transaction information data is converted and standardized into a unified format according to preset rules to obtain unique real-time transaction information data; Identify the unique real-time transaction information data through key fields such as transaction ID, and remove duplicate transaction records to obtain deduplicated real-time transaction information data; Outlier values are deleted and missing values are filled in the deduplicated real-time transaction information data to obtain target real-time transaction information data.
5. A method for security management and control of big data transactions as claimed in claim 4, characterized in that: The XGBoost transaction risk identification model is established according to the XGBoost extreme gradient boosting algorithm, and the LR binary classification model is combined with the XGBoost transaction risk identification model to obtain the XGBoost-LR transaction risk identification model; The processed access information data is transmitted to the XGBoost-LR transaction risk identification model for identification, and the transaction risk results are obtained, including: An XGBoost transaction risk identification model is established according to the XGBoost extreme gradient boosting algorithm. The XGBoost transaction risk identification model consists of two decision trees, where tree 1 has three leaf nodes and tree 2 has two leaf nodes, and each leaf node is regarded as a new feature. The target real-time transaction information data output value is input into the XGBoost transaction risk identification model, and the output result is a one-hot encoded data set; wherein the node value of the input data set falling into the decision tree is 1, and the node value of the input data set not falling into the decision tree is 0; Extracting features of the one-hot encoded data set to obtain a feature one-hot encoded data set; The feature one-hot encoding dataset is input into the LR binary classification model for training and testing to obtain the transaction risk results.
6. A method for security management and control of big data transactions as claimed in claim 1, characterized in that: If the transaction risk result is an abnormal transaction mode, an early warning is issued to the server terminal, and the early warning information is transmitted to the mobile terminal, including: If the transaction risk result is an abnormal transaction mode, an early warning is sent to the server terminal, and an emergency response mechanism is automatically triggered, and the emergency response mechanism at least includes temporarily freezing the transaction rights of the relevant account; Establish an early warning log system to record information such as warning time, warning level, accounts involved and processing status; Relevant managers and users involved will be notified instantly through mobile application push, SMS, email, etc.
7. A big data transaction security management and control system, characterized in that: The big data transaction security management and control system includes the following modules: A data encryption module is used to obtain big data transaction data, and encrypt the big data transaction data using an AES-256 encryption algorithm to obtain encrypted big data transaction data; A platform establishment module, used to establish a blockchain transaction platform and upload the encrypted big data transaction data to the blockchain transaction platform; A data processing module, used to obtain real-time transaction information data in the blockchain transaction platform and perform data processing on the real-time transaction information data; The model building module is used to build an XGBoost transaction risk identification model based on the XGBoost extreme gradient boosting algorithm, and combine the LR binary classification model with the XGBoost transaction risk identification model to obtain the XGBoost-LR transaction risk identification model; The information identification module is used to transmit the processed access information data to the XGBoost-LR transaction risk identification model for identification to obtain the transaction risk results; The security warning module is used to warn the server terminal if the transaction risk result is an abnormal transaction mode, and transmit the warning information to the mobile terminal.
8. A big data transaction security management and control system as claimed in claim 7, characterized in that: The data encryption module includes the following submodules: A generating submodule, used for generating a 256-bit key that meets the requirements of AES-256, and segmenting the big data transaction data to obtain segmented big data transaction data; An encryption submodule, used for implementing a segmented encryption strategy of a key, encrypting the segmented big data transaction data using an AES-256 algorithm to obtain initial big data transaction data; An integration submodule, used to reorganize the initial big data transaction data into a format suitable for storage and transmission according to the structure of the original data, to obtain reorganized big data transaction data; The verification submodule is used to obtain the verification big data transaction data by calculating the hash value of the data before and after encryption and adding the verification information to the data packet; The transmission submodule is used to transmit the verification big data transaction data using a secure storage medium or through an encrypted SSL protocol to obtain encrypted big data transaction data.
9. A big data transaction security management and control system as claimed in claim 7, characterized in that: The data processing module includes the following submodules: An acquisition submodule is used to acquire real-time transaction information data in the blockchain transaction platform, remove invalid or incomplete data packets in the real-time transaction information, and obtain complete real-time transaction information data; A standardization submodule, used to convert and standardize the complete real-time transaction information data into a unified format according to preset rules to obtain unique real-time transaction information data; A removal submodule, used to identify the unique real-time transaction information data through key fields such as transaction ID, and remove duplicate transaction records to obtain deduplicated real-time transaction information data; The filling submodule is used to delete abnormal values and fill missing values in the deduplicated real-time transaction information data to obtain target real-time transaction information data.
Citation Information
Cited By
Big data secure transmission method combining block chain and machine learning
CN120434045A
Big data transaction security control method and system
CN120672341A
