A method and system for intelligent data collection and secure storage based on blockchain

Abstract

The present invention discloses a method and system for intelligent data collection and secure storage based on blockchain. The data platform and user terminal are connected through a network, user interaction data is collected within a specific time period, and converted into a text-formatted behavior data set with behavior labels. Subsequently, the Word2Vec technology is used to perform semantic analysis on these data, define multiple behavior feature patterns, construct a user behavior knowledge graph, and set the security level according to each pattern. For the newly collected current behavior data, the Word2Vec technology is also used to analyze its characteristics, generate corresponding nodes and import them into the knowledge graph to determine its security level. Finally, based on the security assessment results, the data is asymmetrically encrypted and uploaded to the blockchain for secure storage. Automated security perception and on-chain storage of interactive data are realized, and at the same time, intelligent processing and protection of user behavior data are realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent data collection and secure encryption, and more specifically, to a method and system for intelligent data collection and secure storage based on blockchain. Background Art

[0002] With the rapid development of user interaction platforms, data platforms have accumulated a large amount of user behavior data. This data not only includes various user records, but also sensitive data. By mining and analyzing these user behavior data, companies can understand user needs more accurately, optimize products and services, and enhance market competitiveness. However, the collection, storage, and analysis of user behavior data also face many challenges, such as data privacy protection, data security storage, and efficient data classification.

[0003] As a distributed ledger technology, blockchain technology has the characteristics of decentralization, immutability, transparency and traceability, and provides a new solution for the secure storage and sharing of data. Through blockchain technology, distributed storage and encryption protection of user behavior data can be achieved to ensure the security and privacy of data. However, most of the existing blockchain-based data storage methods focus on data storage and transaction security, and there is relatively little research on intelligent data collection, preprocessing and analysis. There is a lack of methods for automatic perception and rapid sensitivity analysis of user interaction data, and a lack of methods for correlation analysis and efficient identification of user sensitive data using existing user behavior characteristics and behavior knowledge information. As a result, the platform needs to perform secondary analysis of user data or encrypt and analyze each data packet, which is inefficient and difficult to apply to multi-user situations and big data platforms. In addition, due to the inefficiency of the encrypted storage platform, it is difficult to improve the ability and efficiency of data collection and processing. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and proposes a method and system for intelligent data collection and secure storage based on blockchain.

[0005] The first aspect of the present invention provides a method for intelligent data collection and secure storage based on blockchain, comprising:

[0006] Establishing a data network connection between the data platform and the user terminal, and collecting user interaction data through the user terminal within a preset time period;

[0007] Conduct behavioral pattern analysis on user interaction data, classify interactive behaviors and convert them into behavioral labels, generate corresponding behavioral labels, convert behavioral labels into keywords and generate behavioral data sets in text format;

[0008] Obtain user behavior big data in text format from the system database, perform semantic analysis on the user behavior big data through Word2Vec word analysis technology and set multiple behavior feature patterns. Based on the semantic perspective, analyze the correlation between multiple behavior feature patterns, use each behavior feature pattern as node data to build a user behavior knowledge graph, and set corresponding data security levels for multiple behavior feature patterns.

[0009] Based on a current user, current behavior data is extracted from the behavior data set, and behavior characteristics are analyzed on the current behavior data based on Word2Vec word analysis technology, and the current behavior characteristic pattern is generated. The current behavior characteristic pattern is imported into the user behavior knowledge graph to generate a current node data, and the corresponding associated node data is analyzed based on the current node data, and the security level of the current node data is determined;

[0010] Based on the security level, it is determined whether the current behavior data is stored on the chain. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network.

[0011] In this solution, the data platform establishes a data network connection with the user terminal, and collects user interaction data through the user terminal within a preset time period, specifically:

[0012] Set up a dedicated network channel to establish a dedicated data network for the data platform and user terminals;

[0013] Within a preset time period, user interaction data is collected through user terminals, pre-processed by data cleaning and outlier removal, and uploaded to the data platform.

[0014] In this solution, the behavior pattern analysis of user interaction data is performed, and the interaction behaviors are classified and converted into behavior labels, corresponding behavior labels are generated, and the behavior labels are converted into keywords and a text-based behavior data set is generated, specifically:

[0015] Conduct behavioral pattern analysis on user interaction data, classify and transform user interaction data according to preset behavioral labels, and obtain multiple groups of behavioral labels;

[0016] Generate keywords for multiple groups of behavior tags based on text-based behavior datasets.

[0017] In this solution, the user behavior big data in text format is obtained from the system database, and the user behavior big data is semantically analyzed through Word2Vec word analysis technology to set multiple behavior feature patterns. Based on the semantic perspective, the correlation between multiple behavior feature patterns is analyzed, and each behavior feature pattern is used as node data to construct a user behavior knowledge graph, and corresponding data security levels are set for multiple behavior feature patterns, specifically:

[0018] Obtain user behavior big data in text format from the system database;

[0019] Convert user behavior big data into keywords to obtain text big data;

[0020] Based on Word2Vec word analysis technology, we set up a vector space, perform word vector conversion and semantic similarity analysis on text big data, and generate corresponding user behavior features based on each unit user using word vectors as raw data. We then set the corresponding behavior feature pattern for each unit user based on the user behavior features.

[0021] Based on the semantic similarity between the behavior feature patterns, the behavior feature patterns within a preset similarity range are merged to obtain a plurality of merged behavior feature patterns;

[0022] Each behavior feature pattern is used as node data, and relationship data is set through semantic similarity between multiple behavior feature patterns. For each behavior feature pattern, corresponding user information is obtained and a corresponding data security level is set, and the user information and security level are used as attribute data of the node;

[0023] A user behavior knowledge graph is constructed through the node data, relationship data and attribute data.

[0024] In this solution, the current behavior data is extracted from the behavior data set based on a current user, the behavior characteristics of the current behavior data are analyzed based on the Word2Vec word analysis technology, and the current behavior characteristic pattern is generated, and the current behavior characteristic pattern is imported into the user behavior knowledge graph to generate a current node data, and the corresponding associated node data is analyzed based on the current node data, and the security level of the current node data is determined, specifically:

[0025] Select a current user and extract the current behavior data from the behavior data set;

[0026] Based on Word2Vec word analysis technology, the current behavior data is analyzed for semantics and behavior characteristics, and the current behavior feature pattern is generated through word vector conversion;

[0027] Import the current behavior feature pattern into the user behavior knowledge graph to generate a current node and the corresponding current node data. Through the knowledge graph, analyze the node position of the current node data in the graph, filter out the node data with associated relationships, mark them as associated nodes, set corresponding weights based on the strength of the association between each associated node and the current node, obtain the security levels corresponding to all associated nodes, and perform weighted average based on the corresponding weights to obtain the weighted level;

[0028] The obtained weighted level is used as the security level for real-time analysis of current behavior data.

[0029] In this solution, the security level is used to determine whether the current behavior data is stored on the chain. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network. Specifically:

[0030] Determine whether the security level of the current behavior data is greater than the preset level. If so, generate a data packet with the current node data and the current behavior data, encrypt the data packet in an asymmetric encryption form, upload it to the current network node, and broadcast it to the data platform;

[0031] The data platform receives the broadcast message to synchronize the data of the blockchain network. After data verification, the data packet is synchronously uploaded to the blockchain network.

[0032] In this solution, the user terminal includes a computer terminal and a mobile terminal.

[0033] The second aspect of the present invention further provides a blockchain-based data intelligent collection and secure storage system, the system comprising: a memory, a processor, the memory comprising a blockchain-based data intelligent collection and secure storage program, the blockchain-based data intelligent collection and secure storage program when executed by the processor to implement the following steps:

[0034] Establishing a data network connection between the data platform and the user terminal, and collecting user interaction data through the user terminal within a preset time period;

[0035] Conduct behavioral pattern analysis on user interaction data, classify interactive behaviors and convert them into behavioral labels, generate corresponding behavioral labels, convert behavioral labels into keywords and generate behavioral data sets in text format;

[0036] Obtain user behavior big data in text format from the system database, perform semantic analysis on the user behavior big data through Word2Vec word analysis technology and set multiple behavior feature patterns. Based on the semantic perspective, analyze the correlation between multiple behavior feature patterns, use each behavior feature pattern as node data to build a user behavior knowledge graph, and set corresponding data security levels for multiple behavior feature patterns.

[0037] Based on a current user, current behavior data is extracted from the behavior data set, and behavior characteristics are analyzed on the current behavior data based on Word2Vec word analysis technology, and the current behavior characteristic pattern is generated. The current behavior characteristic pattern is imported into the user behavior knowledge graph to generate a current node data, and the corresponding associated node data is analyzed based on the current node data, and the security level of the current node data is determined;

[0038] Based on the security level, it is determined whether the current behavior data is stored on the chain. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network.

[0039] The third aspect of the present invention also provides a computer-readable storage medium, which includes a blockchain-based data intelligent collection and secure storage program. When the blockchain-based data intelligent collection and secure storage program is executed by a processor, the steps of the blockchain-based data intelligent collection and secure storage method as described in any one of the above items are implemented.

[0040] The present invention discloses a method and system for intelligent data collection and secure storage based on blockchain. The data platform and user terminal are connected through a network, user interaction data is collected within a specific time period, and converted into a text-formatted behavior data set with behavior labels. Subsequently, the Word2Vec technology is used to perform semantic analysis on these data, define multiple behavior feature patterns, construct a user behavior knowledge graph, and set the security level according to each pattern. For the newly collected current behavior data, the Word2Vec technology is also used to analyze its characteristics, generate corresponding nodes and import them into the knowledge graph to determine its security level. Finally, based on the security assessment results, the data is asymmetrically encrypted and uploaded to the blockchain for secure storage. Automated security perception and on-chain storage of interactive data are realized, and at the same time, intelligent processing and protection of user behavior data are realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a method for intelligent data collection and secure storage based on blockchain is shown in the present invention;

[0042] Figure 2 A block diagram of a data intelligent collection and secure storage system based on blockchain of the present invention is shown. DETAILED DESCRIPTION

[0043] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0044] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0045] Figure 1 A flow chart of a method for intelligent data collection and secure storage based on blockchain of the present invention is shown.

[0046] like Figure 1 As shown, the first aspect of the present invention provides a method for intelligent data collection and secure storage based on blockchain, comprising:

[0047] S102, establishing a data network connection between the data platform and the user terminal, and collecting user interaction data through the user terminal within a preset time period;

[0048] S104, analyzing the behavior patterns of the user interaction data, classifying the interaction behaviors and converting them into behavior labels, generating corresponding behavior labels, converting the behavior labels into keywords and generating a behavior data set based on a text format;

[0049] S106, obtaining user behavior big data in text format from the system database, performing semantic analysis on the user behavior big data through Word2Vec word analysis technology and setting multiple behavior feature patterns, analyzing the correlation between the multiple behavior feature patterns from a semantic perspective, constructing a user behavior knowledge graph with each behavior feature pattern as node data, and setting corresponding data security levels for the multiple behavior feature patterns;

[0050] S108, extracting current behavior data from a behavior data set based on a current user, performing behavior feature analysis on the current behavior data based on Word2Vec word analysis technology, and generating a current behavior feature pattern, importing the current behavior feature pattern into a user behavior knowledge graph to generate a current node data, analyzing the corresponding associated node data based on the current node data, and determining the security level of the current node data;

[0051] S110, based on the security level, determine whether the current behavior data is to be stored on the chain. If so, asymmetrically encrypt the current behavior data and upload it to the blockchain network.

[0052] According to an embodiment of the present invention, the data platform and the user terminal are connected to a data network, and user interaction data is collected through the user terminal within a preset time period, specifically:

[0053] Set up a dedicated network channel to establish a dedicated data network for the data platform and user terminals;

[0054] Within a preset time period, user interaction data is collected through user terminals, pre-processed by data cleaning and outlier removal, and uploaded to the data platform.

[0055] It should be noted that user interaction data includes multi-dimensional data. For example, in e-commerce platforms, it includes interactive data such as browsing, clicking on products, searching for keywords, collecting products, adding to shopping carts, setting order quantities, searching for item types, and order time, from which the corresponding user behavior characteristics can be identified.

[0056] It is worth mentioning that for network user interaction platforms (such as e-commerce, warehousing and other platforms), it is often necessary to analyze the security of the corresponding interactive data and encrypt sensitive data. However, in the prior art, there is a lack of methods for automatic perception and rapid sensitivity analysis of user interaction data, and a lack of methods for using existing user behavior characteristics and behavior knowledge information for correlation analysis and efficient identification of user sensitive data, which results in the platform needing to perform secondary analysis of user data or encrypt and analyze each data packet, which is inefficient and difficult to apply to multi-user situations and big data platforms. In addition, due to the inefficiency of the encrypted storage platform, it is difficult to improve the ability and efficiency of collecting and processing data. Based on this, the present invention can effectively solve the above problems.

[0057] According to an embodiment of the present invention, the behavior pattern analysis of user interaction data, the classification of interaction behaviors and the conversion of behavior labels, the generation of corresponding behavior labels, the conversion of behavior labels into keywords and the generation of a behavior data set based on a text format are specifically as follows:

[0058] Conduct behavioral pattern analysis on user interaction data, classify and transform user interaction data according to preset behavioral labels, and obtain multiple groups of behavioral labels;

[0059] Generate keywords for multiple groups of behavior tags based on text-based behavior datasets.

[0060] It should be noted that each group of behavior tags may correspond to one user. Keywords are keywords based on text format and are used for semantic analysis of behavior features.

[0061] According to an embodiment of the present invention, the user behavior big data in text format is obtained from the system database, the user behavior big data is semantically analyzed by Word2Vec word analysis technology and multiple behavior feature patterns are set, the correlation between multiple behavior feature patterns is analyzed from a semantic perspective, each behavior feature pattern is used as node data to construct a user behavior knowledge graph, and corresponding data security levels are set for multiple behavior feature patterns, specifically:

[0062] Obtain user behavior big data in text format from the system database;

[0063] Convert user behavior big data into keywords to obtain text big data;

[0064] Based on Word2Vec word analysis technology, we set up a vector space, perform word vector conversion and semantic similarity analysis on text big data, and generate corresponding user behavior features based on each unit user using word vectors as raw data. We then set the corresponding behavior feature pattern for each unit user based on the user behavior features.

[0065] Based on the semantic similarity between the behavior feature patterns, the behavior feature patterns within a preset similarity range are merged to obtain a plurality of merged behavior feature patterns;

[0066] Each behavior feature pattern is used as node data, and relationship data is set through semantic similarity between multiple behavior feature patterns. For each behavior feature pattern, corresponding user information is obtained and a corresponding data security level is set, and the user information and security level are used as attribute data of the node;

[0067] A user behavior knowledge graph is constructed through the node data, relationship data and attribute data.

[0068] It should be noted that the Word2Vec word analysis technology can use the bag of words model (CBOW) for semantic analysis. The behavior feature pattern uses the behavior features of semantic analysis as a pattern identifier, and then compares the behavior patterns. The semantic similarity between the behavior feature patterns is analyzed by word vectors. The relationship pattern includes strong and weak relationship information. The merge operation is an optional operation used to simplify the types of behavior patterns. In the user behavior knowledge graph constructed with each behavior feature pattern as node data, each behavior feature pattern corresponds to a node, and each node stores the corresponding node data. User behavior big data is the existing historical user interaction data.

[0069] According to an embodiment of the present invention, the current behavior data is extracted from the behavior data set based on a current user, the behavior feature analysis is performed on the current behavior data based on the Word2Vec word analysis technology, and the current behavior feature pattern is generated, the current behavior feature pattern is imported into the user behavior knowledge graph to generate a current node data, the corresponding associated node data is analyzed based on the current node data, and the security level of the current node data is determined, specifically:

[0070] Select a current user and extract the current behavior data from the behavior data set;

[0071] Based on Word2Vec word analysis technology, the current behavior data is analyzed for semantics and behavior characteristics, and the current behavior feature pattern is generated through word vector conversion;

[0072] Import the current behavior feature pattern into the user behavior knowledge graph to generate a current node and the corresponding current node data. Through the knowledge graph, analyze the node position of the current node data in the graph, filter out the node data with associated relationships, mark them as associated nodes, set corresponding weights based on the strength of the association between each associated node and the current node, obtain the security levels corresponding to all associated nodes, and perform weighted average based on the corresponding weights to obtain the weighted level;

[0073] The obtained weighted level is used as the security level for real-time analysis of current behavior data.

[0074] It should be noted that the current behavior feature pattern is consistent with the behavior feature process method of user behavior big data analysis. The security level is specifically a numerical value. Nodes and node data correspond to entities and entity data in the knowledge graph. The strength of the relationship between each associated node and the current node can be obtained based on the relationship data between the nodes in the knowledge graph, which is generally determined by the distance between the edges of the two nodes. The stronger the relationship, the smaller the shortest distance between the two nodes in the graph, and the greater the similarity and association. In setting the corresponding weights, each associated node corresponds to a weight, and the greater the degree of association, the greater the weight.

[0075] According to an embodiment of the present invention, the security level is used to determine whether the current behavior data is to be stored on the chain. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network. Specifically,

[0076] Determine whether the security level of the current behavior data is greater than the preset level. If so, generate a data packet with the current node data and the current behavior data, encrypt the data packet in an asymmetric encryption form, upload it to the current network node, and broadcast it to the data platform;

[0077] The data platform receives the broadcast message to synchronize the data of the blockchain network. After data verification, the data packet is synchronously uploaded to the blockchain network.

[0078] It should be noted that the real-time perceived user sensitive data is further encrypted and stored on the chain through the blockchain network to improve data security.

[0079] According to an embodiment of the present invention, the user terminal includes a computer terminal and a mobile terminal.

[0080] According to an embodiment of the present invention, it also includes:

[0081] In one analysis cycle, real-time interaction data of multiple users is collected;

[0082] Conduct behavioral pattern analysis and semantic analysis on real-time interactive data, and combine it with Word2Vec word analysis technology to generate real-time behavioral features based on word vectors;

[0083] Based on the time dimension, the real-time behavior features are serialized to obtain feature sequence data;

[0084] Through the LSTM model, the feature sequence data is predicted to generate the corresponding predicted sequence data;

[0085] Perform data analysis on the predicted sequence data to obtain the corresponding predicted behavior features;

[0086] By predicting the behavior characteristics, setting behavior patterns for the multiple users to obtain predicted behavior characteristic patterns;

[0087] By predicting the behavior feature pattern, the data security level of multiple users is set to obtain the corresponding predicted security level, the predicted security levels of multiple users are sorted and a cache priority table of users is generated;

[0088] In the cache priority table, the higher the predicted security level, the higher the user priority.

[0089] It should be noted that the real-time behavior features are word vectors based on semantic analysis as features of the original data.

[0090] It is worth mentioning that in the prior art, interactive platforms with encryption requirements often lack classified cache settings for users, which makes it difficult for system resources to match users with different needs and different behavior patterns, which in turn leads to low efficiency in secure on-chain storage of user data and lack of a comprehensive platform suitable for different user characteristics. Based on this, the embodiment of the present invention serializes the user behavior characteristics of semantic analysis, and implements the prediction process of sequence data through the LSTM model. The prediction process is used to simulate the user behavior pattern after the analysis period, and the corresponding data cache priority is set for the users within the analysis period through the predicted user behavior pattern. When storing interactive data and data on the chain, the interactive data generated by different users can be cached based on the cache priority table, effectively improving the data transmission efficiency between the interactive platform and the blockchain network and the storage and extraction efficiency of interactive data.

[0091] According to an embodiment of the present invention, it also includes:

[0092] In the selected analysis cycle, a data packet of a preset data volume is screened out from the blockchain network, the data packet is extracted and decrypted to obtain the first interaction data, and the data extraction record is saved;

[0093] Mark multiple analysis users according to user information corresponding to the first interaction data, perform behavioral semantic analysis on the first interaction data, and obtain corresponding multiple first behavioral features by combining Word2Vec word analysis technology;

[0094] Determining whether the security levels of the behavior feature patterns corresponding to the plurality of first behavior features are all greater than a preset level;

[0095] If they are not all greater than the preset level, generating multiple node data based on the user behavior knowledge graph according to the multiple first behavior features, and generating relationship data between the multiple nodes based on the semantic similarity between the multiple first behavior features;

[0096] Generate association rules based on relational data, combine the existing association rules in the user behavior knowledge graph, infer and expand the rules based on the AMIE+ algorithm, and generate extended rules;

[0097] Import the extension rules into the user behavior knowledge graph, expand new node relationship data, and update the user behavior knowledge graph;

[0098] The new node relationship data and data extraction records are used as query record data, and the query record data is encrypted and uploaded to the blockchain network.

[0099] It should be noted that each first behavior feature corresponds to an analysis user. The semantic similarity between multiple first behavior features represents the strength of the relationship between the corresponding nodes. It is worth mentioning here that in the long-term multi-cycle data chain storage, some non-sensitive data may be stored on the chain, resulting in redundant blockchain data storage, and the existing technology is difficult to query and correct efficiently. Based on this, the present invention conducts security judgment on the interactive data that has been chained by spot-checking the analysis cycle. If it is judged to be non-security data, nodes are generated for the interactive data of the corresponding period, and rule reasoning is performed on the knowledge graph, and the knowledge graph rules and relationships are updated, so that the knowledge graph can more accurately judge the security level of the user interaction mode in the future. This process can dynamically update the knowledge graph, and it has high applicability and practicality for the security storage requirements of interactive big data, and improves the efficiency of secure storage.

[0100] Figure 2 A block diagram of a data intelligent collection and secure storage system based on blockchain of the present invention is shown.

[0101] The second aspect of the present invention further provides a blockchain-based data intelligent collection and secure storage system 2, the system comprising: a memory 21, a processor 22, the memory 21 comprising a blockchain-based data intelligent collection and secure storage program, the blockchain-based data intelligent collection and secure storage program when executed by the processor 22 to implement the following steps:

[0102] Establishing a data network connection between the data platform and the user terminal, and collecting user interaction data through the user terminal within a preset time period;

[0103] Conduct behavioral pattern analysis on user interaction data, classify interactive behaviors and convert them into behavioral labels, generate corresponding behavioral labels, convert behavioral labels into keywords and generate behavioral data sets in text format;

[0104] Obtain user behavior big data in text format from the system database, perform semantic analysis on the user behavior big data through Word2Vec word analysis technology and set multiple behavior feature patterns. Based on the semantic perspective, analyze the correlation between multiple behavior feature patterns, use each behavior feature pattern as node data to build a user behavior knowledge graph, and set corresponding data security levels for multiple behavior feature patterns.

[0105] Based on a current user, current behavior data is extracted from the behavior data set, and behavior characteristics are analyzed on the current behavior data based on Word2Vec word analysis technology, and the current behavior characteristic pattern is generated. The current behavior characteristic pattern is imported into the user behavior knowledge graph to generate a current node data, and the corresponding associated node data is analyzed based on the current node data, and the security level of the current node data is determined;

[0106] Based on the security level, it is determined whether the current behavior data is stored on the chain. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network.

[0107] According to an embodiment of the present invention, the data platform and the user terminal are connected to a data network, and user interaction data is collected through the user terminal within a preset time period, specifically:

[0108] Set up a dedicated network channel to establish a dedicated data network for the data platform and user terminals;

[0109] Within a preset time period, user interaction data is collected through user terminals, pre-processed by data cleaning and outlier removal, and uploaded to the data platform.

[0110] It should be noted that user interaction data includes multi-dimensional data. For example, in e-commerce platforms, it includes interactive data such as browsing, clicking on products, searching for keywords, collecting products, adding to shopping carts, setting order quantities, searching for item types, and order time, from which the corresponding user behavior characteristics can be identified.

[0111] It is worth mentioning that for network user interaction platforms (such as e-commerce, warehousing and other platforms), it is often necessary to analyze the security of the corresponding interactive data and encrypt sensitive data. However, in the prior art, there is a lack of methods for automatic perception and rapid sensitivity analysis of user interaction data, and a lack of methods for using existing user behavior characteristics and behavior knowledge information for correlation analysis and efficient identification of user sensitive data, which results in the platform needing to perform secondary analysis of user data or encrypt and analyze each data packet, which is inefficient and difficult to apply to multi-user situations and big data platforms. In addition, due to the inefficiency of the encrypted storage platform, it is difficult to improve the ability and efficiency of collecting and processing data. Based on this, the present invention can effectively solve the above problems.

[0112] According to an embodiment of the present invention, the behavior pattern analysis of user interaction data, the classification of interaction behaviors and the conversion of behavior labels, the generation of corresponding behavior labels, the conversion of behavior labels into keywords and the generation of a behavior data set based on a text format are specifically as follows:

[0113] Conduct behavioral pattern analysis on user interaction data, classify and transform user interaction data according to preset behavioral labels, and obtain multiple groups of behavioral labels;

[0114] Generate keywords for multiple groups of behavior tags based on text-based behavior datasets.

[0115] It should be noted that each group of behavior tags may correspond to one user. Keywords are keywords based on text format and are used for semantic analysis of behavior features.

[0116] According to an embodiment of the present invention, the user behavior big data in text format is obtained from the system database, the user behavior big data is semantically analyzed by Word2Vec word analysis technology and multiple behavior feature patterns are set, the correlation between multiple behavior feature patterns is analyzed from a semantic perspective, each behavior feature pattern is used as node data to construct a user behavior knowledge graph, and corresponding data security levels are set for multiple behavior feature patterns, specifically:

[0117] Obtain user behavior big data in text format from the system database;

[0118] Convert user behavior big data into keywords to obtain text big data;

[0119] Based on Word2Vec word analysis technology, we set up a vector space, perform word vector conversion and semantic similarity analysis on text big data, and generate corresponding user behavior features based on each unit user using word vectors as raw data. We then set the corresponding behavior feature pattern for each unit user based on the user behavior features.

[0120] Based on the semantic similarity between the behavior feature patterns, the behavior feature patterns within a preset similarity range are merged to obtain a plurality of merged behavior feature patterns;

[0121] Each behavior feature pattern is used as node data, and relationship data is set through semantic similarity between multiple behavior feature patterns. For each behavior feature pattern, corresponding user information is obtained and a corresponding data security level is set, and the user information and security level are used as attribute data of the node;

[0122] A user behavior knowledge graph is constructed through the node data, relationship data and attribute data.

[0123] It should be noted that the Word2Vec word analysis technology can use the bag of words model (CBOW) for semantic analysis. The behavior feature pattern uses the behavior features of semantic analysis as a pattern identifier, and then compares the behavior patterns. The semantic similarity between the behavior feature patterns is analyzed by word vectors. The relationship pattern includes strong and weak relationship information. The merge operation is an optional operation used to simplify the types of behavior patterns. In the user behavior knowledge graph constructed with each behavior feature pattern as node data, each behavior feature pattern corresponds to a node, and each node stores the corresponding node data. User behavior big data is the existing historical user interaction data.

[0124] According to an embodiment of the present invention, the current behavior data is extracted from the behavior data set based on a current user, the behavior feature analysis is performed on the current behavior data based on the Word2Vec word analysis technology, and the current behavior feature pattern is generated, the current behavior feature pattern is imported into the user behavior knowledge graph to generate a current node data, the corresponding associated node data is analyzed based on the current node data, and the security level of the current node data is determined, specifically:

[0125] Select a current user and extract the current behavior data from the behavior data set;

[0126] Based on Word2Vec word analysis technology, the current behavior data is analyzed for semantics and behavior characteristics, and the current behavior feature pattern is generated through word vector conversion;

[0127] Import the current behavior feature pattern into the user behavior knowledge graph to generate a current node and the corresponding current node data. Through the knowledge graph, analyze the node position of the current node data in the graph, filter out the node data with associated relationships, mark them as associated nodes, set corresponding weights based on the strength of the association between each associated node and the current node, obtain the security levels corresponding to all associated nodes, and perform weighted average based on the corresponding weights to obtain the weighted level;

[0128] The obtained weighted level is used as the security level for real-time analysis of current behavior data.

[0129] It should be noted that the current behavior feature pattern is consistent with the behavior feature process method of user behavior big data analysis. The security level is specifically a numerical value. Nodes and node data correspond to entities and entity data in the knowledge graph. The strength of the relationship between each associated node and the current node can be obtained based on the relationship data between the nodes in the knowledge graph, which is generally determined by the distance between the edges of the two nodes. The stronger the relationship, the smaller the shortest distance between the two nodes in the graph, and the greater the similarity and association. In setting the corresponding weights, each associated node corresponds to a weight, and the greater the degree of association, the greater the weight.

[0130] According to an embodiment of the present invention, the security level is used to determine whether the current behavior data is to be stored on the chain. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network. Specifically,

[0131] Determine whether the security level of the current behavior data is greater than the preset level. If so, generate a data packet with the current node data and the current behavior data, encrypt the data packet in an asymmetric encryption form, upload it to the current network node, and broadcast it to the data platform;

[0132] The data platform receives the broadcast message to synchronize the data of the blockchain network. After data verification, the data packet is synchronously uploaded to the blockchain network.

[0133] It should be noted that the real-time perceived user sensitive data is further encrypted and stored on the chain through the blockchain network to improve data security.

[0134] According to an embodiment of the present invention, the user terminal includes a computer terminal and a mobile terminal.

[0135] The third aspect of the present invention also provides a computer-readable storage medium, which includes a blockchain-based data intelligent collection and secure storage program. When the blockchain-based data intelligent collection and secure storage program is executed by a processor, the steps of the blockchain-based data intelligent collection and secure storage method as described in any one of the above items are implemented.

[0136] The present invention discloses a method and system for intelligent data collection and secure storage based on blockchain. The data platform and user terminal are connected through a network, user interaction data is collected within a specific time period, and converted into a text-formatted behavior data set with behavior labels. Subsequently, the Word2Vec technology is used to perform semantic analysis on these data, define multiple behavior feature patterns, construct a user behavior knowledge graph, and set the security level according to each pattern. For the newly collected current behavior data, the Word2Vec technology is also used to analyze its characteristics, generate corresponding nodes and import them into the knowledge graph to determine its security level. Finally, based on the security assessment results, the data is asymmetrically encrypted and uploaded to the blockchain for secure storage. Automated security perception and on-chain storage of interactive data are realized, and at the same time, intelligent processing and protection of user behavior data are realized.

[0137] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0138] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0139] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0140] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0141] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0142] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for intelligent data collection and secure storage based on blockchain, characterized in that: include: Establishing a data network connection between the data platform and the user terminal, and collecting user interaction data through the user terminal within a preset time period; Conduct behavioral pattern analysis on user interaction data, classify interactive behaviors and convert them into behavioral labels, generate corresponding behavioral labels, convert behavioral labels into keywords and generate behavioral data sets in text format; Obtain user behavior big data in text format from the system database, perform semantic analysis on the user behavior big data through Word2Vec word analysis technology and set multiple behavior feature patterns. Based on the semantic perspective, analyze the correlation between multiple behavior feature patterns, use each behavior feature pattern as node data to build a user behavior knowledge graph, and set corresponding data security levels for multiple behavior feature patterns. Based on a current user, current behavior data is extracted from the behavior data set, and behavior characteristics are analyzed on the current behavior data based on Word2Vec word analysis technology, and the current behavior characteristic pattern is generated. The current behavior characteristic pattern is imported into the user behavior knowledge graph to generate a current node data, and the corresponding associated node data is analyzed based on the current node data, and the security level of the current node data is determined; Determine whether the current behavior data is stored on the chain based on the security level. If so, asymmetrically encrypt the current behavior data and upload it to the blockchain network; The user behavior knowledge graph is constructed by taking each behavior feature pattern as node data, and corresponding data security levels are set for multiple behavior feature patterns. Specifically, each behavior feature pattern is taken as node data, relationship data is set by semantic similarity between multiple behavior feature patterns, corresponding user information is obtained for each behavior feature pattern and corresponding data security level is set, and user information and security level are taken as attribute data of the node; Constructing a user behavior knowledge graph through the node data, relationship data and attribute data; The method of importing the current behavior feature pattern into the user behavior knowledge graph to generate a current node data, analyzing the corresponding associated node data based on the current node data, and determining the security level of the current node data, specifically, importing the current behavior feature pattern into the user behavior knowledge graph to generate a current node and the corresponding current node data, analyzing the node position of the current node data in the graph through the knowledge graph, screening out the node data with an associated relationship, marking them as associated nodes, setting corresponding weights based on the strength of the association between each associated node and the current node, obtaining the security levels corresponding to all associated nodes, and performing weighted averaging in combination with the corresponding weights to obtain a weighted level; The obtained weighted level is used as the security level for real-time analysis of current behavior data; The method determines whether the current behavior data is to be stored on the chain based on the security level. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network. Specifically, it determines whether the security level of the current behavior data is greater than the preset level. If so, the current node data and the current behavior data are generated into a data packet, which is encrypted in the form of asymmetric encryption and uploaded to the current network node, and broadcast to the data platform.

2. According to claim 1, a method for intelligent data collection and secure storage based on blockchain is characterized in that: The data platform and the user terminal are connected to a data network, and user interaction data is collected through the user terminal within a preset time period, specifically: Set up a dedicated network channel to establish a dedicated data network for the data platform and user terminals; Within a preset time period, user interaction data is collected through user terminals, pre-processed by data cleaning and outlier removal, and uploaded to the data platform.

3. According to claim 1, a method for intelligent data collection and secure storage based on blockchain is characterized in that: The behavior pattern analysis of user interaction data is performed, and the interaction behaviors are classified and converted into behavior labels, corresponding behavior labels are generated, and the behavior labels are converted into keywords and a behavior data set based on text format is generated, specifically: Conduct behavioral pattern analysis on user interaction data, classify and transform user interaction data according to preset behavioral labels, and obtain multiple groups of behavioral labels; Generate keywords for multiple groups of behavior tags based on text-based behavior datasets.

4. According to the method of claim 1, the method is characterized in that: The user behavior big data in text format is obtained from the system database, and semantic analysis is performed on the user behavior big data through Word2Vec word analysis technology to set multiple behavior feature patterns. Based on the semantic perspective, the correlation between multiple behavior feature patterns is analyzed, and each behavior feature pattern is used as node data to construct a user behavior knowledge graph, and corresponding data security levels are set for multiple behavior feature patterns, specifically: Obtain user behavior big data in text format from the system database; Convert user behavior big data into keywords to obtain text big data; Based on Word2Vec word analysis technology, we set up a vector space, perform word vector conversion and semantic similarity analysis on text big data, and generate corresponding user behavior features based on each unit user using word vectors as raw data. We then set the corresponding behavior feature pattern for each unit user based on the user behavior features. Through the semantic similarity between the behavior feature patterns, the behavior feature patterns within a preset similarity range are merged to obtain a plurality of merged behavior feature patterns.

5. According to claim 4, a method for intelligent data collection and secure storage based on blockchain is characterized in that: The method extracts current behavior data from a behavior data set based on a current user, performs behavior feature analysis on the current behavior data based on Word2Vec word analysis technology, generates a current behavior feature pattern, imports the current behavior feature pattern into the user behavior knowledge graph to generate a current node data, analyzes the corresponding associated node data based on the current node data, and determines the security level of the current node data, specifically: Select a current user and extract the current behavior data from the behavior data set; Based on Word2Vec word analysis technology, semantic analysis and behavioral feature analysis are performed on the current behavior data, and the current behavior feature pattern is generated through word vector conversion.

6. According to a blockchain-based data intelligent collection and secure storage method according to claim 1, it is characterized in that: The security level is used to determine whether the current behavior data is to be stored on the chain. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network. Specifically: The data platform receives the broadcast message to synchronize the data of the blockchain network. After data verification, the data packet is synchronously uploaded to the blockchain network.

7. According to claim 1, a method for intelligent data collection and secure storage based on blockchain is characterized in that: The user terminal includes a computer terminal and a mobile terminal.

8. A data intelligent collection and secure storage system based on blockchain, characterized in that: The system includes: a memory and a processor, wherein the memory includes a data intelligent collection and secure storage program based on blockchain, and when the data intelligent collection and secure storage program based on blockchain is executed by the processor, the following steps are implemented: Establishing a data network connection between the data platform and the user terminal, and collecting user interaction data through the user terminal within a preset time period; Conduct behavioral pattern analysis on user interaction data, classify interactive behaviors and convert them into behavioral labels, generate corresponding behavioral labels, convert behavioral labels into keywords and generate behavioral data sets in text format; Obtain user behavior big data in text format from the system database, perform semantic analysis on the user behavior big data through Word2Vec word analysis technology and set multiple behavior feature patterns. Based on the semantic perspective, analyze the correlation between multiple behavior feature patterns, use each behavior feature pattern as node data to build a user behavior knowledge graph, and set corresponding data security levels for multiple behavior feature patterns. Based on a current user, current behavior data is extracted from the behavior data set, and behavior characteristics are analyzed on the current behavior data based on Word2Vec word analysis technology, and the current behavior characteristic pattern is generated. The current behavior characteristic pattern is imported into the user behavior knowledge graph to generate a current node data, and the corresponding associated node data is analyzed based on the current node data, and the security level of the current node data is determined; Determine whether the current behavior data is stored on the chain based on the security level. If so, asymmetrically encrypt the current behavior data and upload it to the blockchain network; The user behavior knowledge graph is constructed by taking each behavior feature pattern as node data, and corresponding data security levels are set for multiple behavior feature patterns. Specifically, each behavior feature pattern is taken as node data, relationship data is set by semantic similarity between multiple behavior feature patterns, corresponding user information is obtained for each behavior feature pattern and corresponding data security level is set, and user information and security level are taken as attribute data of the node; Constructing a user behavior knowledge graph through the node data, relationship data and attribute data; The method of importing the current behavior feature pattern into the user behavior knowledge graph to generate a current node data, analyzing the corresponding associated node data based on the current node data, and determining the security level of the current node data, specifically, importing the current behavior feature pattern into the user behavior knowledge graph to generate a current node and the corresponding current node data, analyzing the node position of the current node data in the graph through the knowledge graph, screening out the node data with an associated relationship, marking them as associated nodes, setting corresponding weights based on the strength of the association between each associated node and the current node, obtaining the security levels corresponding to all associated nodes, and performing weighted averaging in combination with the corresponding weights to obtain a weighted level; The obtained weighted level is used as the security level for real-time analysis of current behavior data; The method determines whether the current behavior data is to be stored on the chain based on the security level. If so, the current behavior data is asymmetrically encrypted and uploaded to the blockchain network. Specifically, it determines whether the security level of the current behavior data is greater than the preset level. If so, the current node data and the current behavior data are generated into a data packet, which is encrypted in the form of asymmetric encryption and uploaded to the current network node, and broadcast to the data platform.

9. According to claim 8, a blockchain-based data intelligent collection and secure storage system is characterized in that: The data platform and the user terminal are connected to a data network, and user interaction data is collected through the user terminal within a preset time period, specifically: Set up a dedicated network channel to establish a dedicated data network for the data platform and user terminals; Within a preset time period, user interaction data is collected through user terminals, pre-processed by data cleaning and outlier removal, and uploaded to the data platform.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a blockchain-based data intelligent collection and secure storage program. When the blockchain-based data intelligent collection and secure storage program is executed by a processor, the steps of the blockchain-based data intelligent collection and secure storage method as described in any one of claims 1 to 7 are implemented.

Images