CN116070111B - Auxiliary decision method and system for big data mining based on AI - Google Patents
Auxiliary decision method and system for big data mining based on AI Download PDFInfo
- Publication number
- CN116070111B CN116070111B CN202211438379.5A CN202211438379A CN116070111B CN 116070111 B CN116070111 B CN 116070111B CN 202211438379 A CN202211438379 A CN 202211438379A CN 116070111 B CN116070111 B CN 116070111B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- mined
- decision
- service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/57—Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
- G06F21/577—Assessing vulnerabilities and evaluating computer system security
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
- G06F8/42—Syntactic analysis
- G06F8/427—Parsing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an AI-based big data mining auxiliary decision-making method and system, wherein the method comprises the following steps: acquiring a business decision requirement, and determining a data mining purpose based on the business decision requirement; determining a data type to be mined based on business decision requirements, locking a data set to be mined from a preset data warehouse based on the data type to be mined, and mining the data set to be mined based on data mining purposes to obtain a target data set; preprocessing the target data set, and optimizing a decision mechanism corresponding to the business decision requirement based on the preprocessed target data set. The data mining purpose is determined according to the service decision requirement, the data set to be mined in the preset data warehouse is mined according to the data mining purpose, the accuracy and the reliability of data mining are guaranteed, the decision mechanism corresponding to the service decision requirement is optimized according to the mined data, the timely discovery of loopholes and abnormal nodes is guaranteed, and the timeliness and the accuracy of response are improved.
Description
Technical Field
The invention relates to the technical field of big data, in particular to an auxiliary decision method and system for big data mining based on AI.
Background
At present, with the rapid development of artificial intelligence technology, the artificial intelligence technology has demonstrated its application potential in some fields, for example, the application of the artificial intelligence technology in vulnerability mining can greatly improve the problem of low mining efficiency caused by the current mode of relying on rule matching and manually searching for vulnerabilities;
the characteristic of vulnerability expression can be reflected to a certain extent on the abnormal log data generated in the service operation process, so that the method has very obvious value on vulnerability excavation and the tracing of the late abnormal nodes by learning the vulnerability excavation on the abnormal log data, is convenient for improving the quality and efficiency of the system operation, and is convenient for reducing the maintenance cost of the system by timely excavating the vulnerability;
Therefore, the invention provides an auxiliary decision making method and system for large data mining based on AI.
Disclosure of Invention
The invention provides an AI-based big data mining auxiliary decision making method and system, which are used for effectively confirming the aim of data mining by determining service decision making requirements, mining a data set to be mined in a preset data warehouse by the aim of data mining, guaranteeing the accuracy and reliability of data mining, and finally optimizing decision making mechanisms corresponding to the service decision making requirements by the mined data, ensuring timely discovery of loopholes and abnormal nodes, improving the timeliness and accuracy of response, and guaranteeing the quality and efficiency of system operation.
The invention provides an AI-based big data mining auxiliary decision-making method, which comprises the following steps:
step 1: acquiring a business decision requirement, and determining a data mining purpose based on the business decision requirement;
step 2: determining a data type to be mined based on business decision requirements, locking a data set to be mined from a preset data warehouse based on the data type to be mined, and mining the data set to be mined based on data mining purposes to obtain a target data set;
Step 3: preprocessing the target data set, and optimizing a decision mechanism corresponding to the business decision requirement based on the preprocessed target data set.
Preferably, in step 1, a method for assisting in big data mining based on AI, the method for acquiring service decision requirement includes:
acquiring a service decision instruction sent by a management terminal, and sending a service information acquisition request to a server based on the service decision instruction;
analyzing the service information acquisition request, determining information characteristics to be acquired, and matching service execution behavior information corresponding to the service information acquisition request from a server based on the information characteristics to be acquired;
extracting key fields in service execution behavior information, determining target loopholes existing in service operation based on the key fields, determining attribute values of the key fields, and evaluating abnormal grades of the target loopholes based on the attribute values to obtain the abnormal grades;
and determining the final business decision requirement based on the abnormal grade.
Preferably, an auxiliary decision method for big data mining based on AI evaluates an abnormality grade of a target vulnerability based on an attribute value to obtain the abnormality grade, including:
acquiring the obtained target vulnerability and determining target sub-information corresponding to the target vulnerability based on service execution behavior information;
Extracting data characteristics of target sub-information, determining service item types contained in target vulnerabilities based on the data characteristics, and determining item weight values of different service items based on target proportions of the different service items corresponding to the item types in a service operation process;
and constructing an influence evaluation model based on the project weight value, inputting target sub-information corresponding to the target vulnerability and the corresponding target value into the influence evaluation model for analysis to obtain the influence degree of the target vulnerability on the service, and matching the influence degree with a preset grading threshold value to obtain the abnormal grade of the target vulnerability.
Preferably, in step 1, determining a data mining objective based on a service decision requirement, the method comprises:
acquiring a script file corresponding to a service, and analyzing the script file to obtain service characteristics of the service;
determining a node identification of a target node contained in a service operation process based on the service characteristics, and determining a service dimension corresponding to a service scene based on the node identification;
acquiring the obtained business decision requirement, and matching the business decision requirement with a business dimension to obtain a target business dimension corresponding to the business decision requirement;
And determining a service function corresponding to the target service dimension, and determining the data mining purpose based on the service function.
Preferably, in step 2, a data type to be mined is determined based on a service decision requirement, a data set to be mined is locked from a preset data warehouse based on the data type to be mined, and the data set to be mined is mined based on a data mining purpose, so as to obtain a target data set, which comprises:
analyzing the business decision requirement, acquiring a target feature vector corresponding to the business decision requirement, determining a target access data identifier based on the target feature vector, and matching the target access data identifier with each preset data file identifier of a preset data warehouse based on the target access data identifier to lock a data set to be mined;
determining the width of a data interval of a data set to be mined, determining the mining precision of the data set to be mined based on the data mining purpose, and determining the stepping length of the data set to be mined based on the precision;
performing first traversal on a data set to be mined based on the stepping length, determining behavior feature vectors of all data to be mined in the data set to be mined based on a first traversal result, and determining distribution features of all data to be mined, which meet the data mining purpose, in the data set to be mined based on the behavior feature vectors;
And determining a data mining distribution diagram of the data set to be mined based on the distribution characteristics, and performing second traversal on the data to be mined based on the data mining distribution diagram.
Preferably, an auxiliary decision method for large data mining based on AI, performs a second traversal of data to be mined based on a data mining distribution diagram, including:
acquiring a data mining distribution diagram of a data set to be mined, and determining the data amount to be mined of different data fragments in the data set to be mined based on the data mining distribution diagram;
carrying out serialization processing on different data fragments in the data to be mined based on the data amount to be mined to obtain a data sequence to be mined, determining characteristic vectors corresponding to all the data fragments in the data sequence to be mined, and determining data mining conditions based on the data mining purpose;
and matching the characteristic vector with the data mining condition, obtaining a target data segment meeting the data mining condition based on a matching result, and associating the target data segment based on the target position of the target data segment in the data set to be mined to obtain a target data set.
Preferably, an auxiliary decision method for large data mining based on AI, after obtaining a target data set, includes:
Acquiring an obtained target data set, determining a data mining dimension of the data set to be mined based on the data mining purpose, and performing first verification on data types in the target data set based on the data mining dimension;
meanwhile, determining an attribute value of target data in a target data set, determining a target offset of the target data relative to a data mining condition based on the attribute value, comparing the target offset with a preset threshold value, and performing second verification on data content in the target data set based on a comparison result;
when the first verification and the second verification are passed, judging that the mining of the data set to be mined is completed;
otherwise, judging that the mining of the data set to be mined is abnormal.
Preferably, in step 3, preprocessing a target data set, and optimizing a decision mechanism corresponding to a service decision requirement based on the preprocessed target data set, where the decision mechanism includes:
the method comprises the steps of obtaining a target data set, carrying out clustering treatment on the target data set based on a preset classification index to obtain sub-target data sets, determining the value of target data in each sub-target data set, and determining the abnormal type of abnormal data in each sub-target data set based on the value;
Matching a target processing rule from a preset data processing rule base based on the abnormal type, and processing the target data set based on the target processing rule to obtain a standard target data set;
acquiring execution characteristics of a decision mechanism corresponding to service decision requirements, and searching sample data which has strong association with the decision mechanism from a standard target data set through a preset association rule based on the execution characteristics;
training and correcting abnormal nodes in the decision mechanism based on the sample data to finish optimization of the decision mechanism.
Preferably, the auxiliary decision-making method for large data mining based on AI trains and corrects the decision-making mechanism based on sample data, and after completing the optimization of the decision-making mechanism, the method comprises the following steps:
acquiring real-time operation data of a decision mechanism, constructing a state prediction model, and inputting the real-time operation data of the decision mechanism into the state prediction model to obtain a state development trend prediction curve of a service corresponding to the decision mechanism;
determining the operation characteristics of each node in the decision mechanism, and correcting the state development trend prediction curve based on the operation characteristics and the standard target data set to obtain a target state development trend prediction curve;
Predicting the target probability of abnormality of the business corresponding to the decision mechanism in the running process based on the target state development trend prediction curve, and determining the position information and the abnormality type of the abnormal node when the target probability is greater than a preset probability threshold;
and matching an overhaul strategy based on the position information of the predicted abnormal node and the abnormal type, and overhauling each node based on the overhaul strategy to finish auxiliary decision.
The invention provides an AI-based big data mining auxiliary decision system, which comprises:
the objective determining module is used for acquiring service decision requirements and determining data mining objectives based on the service decision requirements;
the data mining module is used for determining the type of data to be mined based on the business decision requirement, locking the data set to be mined from a preset data warehouse based on the type of the data to be mined, and mining the data set to be mined based on the data mining purpose to obtain a target data set;
the auxiliary decision-making module is used for preprocessing the target data set and optimizing a decision mechanism corresponding to the business decision-making requirement based on the preprocessed target data set.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of an auxiliary decision making method for AI-based big data mining in an embodiment of the invention;
FIG. 2 is a flowchart of step 1 in an auxiliary decision method for AI-based big data mining in an embodiment of the invention;
fig. 3 is a block diagram of an assistant decision making system based on AI big data mining in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
the embodiment provides an auxiliary decision method for large data mining based on AI, as shown in FIG. 1, comprising the following steps:
step 1: acquiring a business decision requirement, and determining a data mining purpose based on the business decision requirement;
step 2: determining a data type to be mined based on business decision requirements, locking a data set to be mined from a preset data warehouse based on the data type to be mined, and mining the data set to be mined based on data mining purposes to obtain a target data set;
Step 3: preprocessing the target data set, and optimizing a decision mechanism corresponding to the business decision requirement based on the preprocessed target data set.
In this embodiment, the service decision requirement refers to the kind and direction of the service to be checked or optimized, and specifically may be a maintenance scheme of the system, an optimization scheme of data processing, and the like.
In this embodiment, the data mining purpose refers to the type, the number, and the like of data to be mined by the AI technology, which are determined according to the service decision requirement, that is, valuable data related to the service decision is mined, so that effective auxiliary decision is facilitated.
In this embodiment, the data types to be mined refer to data types that need to be mined by AI, and the data types to be mined are at least one.
In this embodiment, the preset data warehouse is known in advance, and a plurality of different service data are stored therein, which may be specifically a cloud server or the like.
In this embodiment, the data set to be mined refers to a plurality of data sets that are consistent with the data type to be mined, which are determined from a preset data warehouse.
In this embodiment, the target data set refers to a data set obtained after mining the data set to be mined according to the type of data to be mined, and is a part of the data set to be mined.
In this embodiment, preprocessing refers to performing operations such as denoising, verification, filling in a lost domain, and deleting invalid data on the obtained target data set.
In this embodiment, the decision mechanism refers to a decision scheme corresponding to the service decision requirement.
In this embodiment, the objective of optimizing the decision mechanism corresponding to the business decision requirement based on the preprocessed target data set is to adjust the defects or flaws in the decision mechanism through the target data set obtained by mining, so as to effectively avoid the occurrence of vulnerabilities.
The beneficial effects of the technical scheme are as follows: through determining the service decision requirement, the aim of effectively confirming the data mining is achieved, secondly, the data set to be mined in the preset data warehouse is mined through the data mining aim, the accuracy and the reliability of the data mining are guaranteed, and finally, decision mechanisms corresponding to the service decision requirement are optimized through the mined data, so that loopholes and abnormal nodes are guaranteed to be found in time, the timeliness and the accuracy of response are improved, and the quality and the efficiency of system operation are guaranteed.
Example 2:
on the basis of embodiment 1, this embodiment provides an auxiliary decision method for large data mining based on AI, as shown in fig. 2, in step 1, the obtaining of a service decision requirement includes:
Step 101: acquiring a service decision instruction sent by a management terminal, and sending a service information acquisition request to a server based on the service decision instruction;
step 102: analyzing the service information acquisition request, determining information characteristics to be acquired, and matching service execution behavior information corresponding to the service information acquisition request from a server based on the information characteristics to be acquired;
step 103: extracting key fields in service execution behavior information, determining target loopholes existing in service operation based on the key fields, determining attribute values of the key fields, and evaluating abnormal grades of the target loopholes based on the attribute values to obtain the abnormal grades;
step 104: and determining the final business decision requirement based on the abnormal grade.
In this embodiment, the service decision instruction is sent by the management terminal, and is used to send a service information acquisition request to the server, so as to implement the retrieval of the log data related to the service from the server.
In this embodiment, the service information acquisition request carries an information type identifier of the information to be acquired, so that the server can analyze the service information acquisition request conveniently and determine the data to be accessed finally.
In this embodiment, the information to be acquired is characterized by parameters such as the type of data to be acquired, the value range, and the like.
In this embodiment, the service execution behavior information refers to log data generated in the service operation process, and specifically may be an operation link of the service in the operation process, an operation result corresponding to the working content of each link, and the like.
In this embodiment, the key field refers to a piece of data capable of characterizing the gist content of the service execution behavior information.
In this embodiment, the target vulnerability refers to a defect or drawback existing in the service running process.
In this embodiment, the attribute value of the key field refers to a specific value condition corresponding to the key field.
In this embodiment, the anomaly level characterizes the severity of the target vulnerability that exists during the business operation.
The beneficial effects of the technical scheme are as follows: the method has the advantages that the service execution behavior information is acquired from the server, the service execution behavior information is analyzed, the target loopholes existing in the service operation process are accurately and effectively acquired, the abnormal grades of the target loopholes are evaluated, the accurate and reliable judgment of the service decision requirement through the abnormal grades of the target loopholes is finally realized, convenience is brought to large data mining, and the accuracy of data mining is guaranteed.
Example 3:
on the basis of embodiment 2, the present embodiment provides an auxiliary decision method for big data mining based on AI, and evaluates an anomaly level of a target vulnerability based on an attribute value to obtain the anomaly level, including:
acquiring the obtained target vulnerability and determining target sub-information corresponding to the target vulnerability based on service execution behavior information;
extracting data characteristics of target sub-information, determining service item types contained in target vulnerabilities based on the data characteristics, and determining item weight values of different service items based on target proportions of the different service items corresponding to the item types in a service operation process;
and constructing an influence evaluation model based on the project weight value, inputting target sub-information corresponding to the target vulnerability and the corresponding target value into the influence evaluation model for analysis to obtain the influence degree of the target vulnerability on the service, and matching the influence degree with a preset grading threshold value to obtain the abnormal grade of the target vulnerability.
In this embodiment, the target sub-information refers to partial service execution behavior information corresponding to the target.
In this embodiment, the data features refer to the data value characteristics of the target sub-information, the association relationship between the data, and the like, so as to realize the judgment of the service item types related to the target sub-information through the data features.
In this embodiment, the service item type refers to a type of a service item related to a target vulnerability in a service operation process, specifically may be a problem department or the like existing in an enterprise operation process, and the service item type is at least one.
In this embodiment, the target proportion refers to the running time of different business items in the whole business running process and the ratio of the workload to the total time and the total workload.
In this embodiment, the term weights are used to characterize how large and small different business terms are acting throughout the business operation.
In this embodiment, the preset classification threshold is set in advance, and is used to provide a reference for determining the abnormal level of the target vulnerability.
The beneficial effects of the technical scheme are as follows: the method comprises the steps of determining target sub-information corresponding to the target loophole, analyzing the target sub-information, accurately acquiring the business item types related to the target loophole, and simultaneously determining the weight values of different business item types in the business operation process, so that the abnormal grade of the target loophole is effectively confirmed, a reliable basis is provided for accurately confirming the data mining purpose, and the accuracy of data mining is conveniently realized.
Example 4:
on the basis of embodiment 1, the present embodiment provides an auxiliary decision method for large data mining based on AI, in step 1, determining a data mining purpose based on a service decision requirement, including:
acquiring a script file corresponding to a service, and analyzing the script file to obtain service characteristics of the service;
determining a node identification of a target node contained in a service operation process based on the service characteristics, and determining a service dimension corresponding to a service scene based on the node identification;
acquiring the obtained business decision requirement, and matching the business decision requirement with a business dimension to obtain a target business dimension corresponding to the business decision requirement;
and determining a service function corresponding to the target service dimension, and determining the data mining purpose based on the service function.
In this embodiment, the script file refers to a business process and specific text content corresponding to a business step.
In this embodiment, the service features refer to the operation mode of the service in the operation process, the related operation range, and the like.
In this embodiment, the target node refers to a node involved in the service in the running process and interacting with different applications or clients.
In this embodiment, the node identification is a type of marking tag used to mark different target node types.
In this embodiment, the service scenario refers to the scope of service application, application specific content, and the like.
In this embodiment, the target service dimension refers to a range related to a service or different related data processing and service management types, and the data mining purposes corresponding to different target service dimensions are confirmed, so that operation instructions and efficiency of the system are conveniently ensured according to mining results.
The beneficial effects of the technical scheme are as follows: by acquiring the script file of the service, the service dimension corresponding to the service is accurately and effectively determined, the service dimension is finally analyzed according to the service decision requirement, the service dimension which is finally required to be decided is determined, and the purpose of data mining is accurately and effectively judged according to the service function of the service dimension, so that the data are conveniently and pointedly mined, the accuracy and the reliability of the data mining are ensured, and the quality and the efficiency of the system operation are conveniently ensured.
Example 5:
on the basis of embodiment 1, the present embodiment provides an auxiliary decision method for large data mining based on AI, in step 2, a data type to be mined is determined based on a service decision requirement, a data set to be mined is locked from a preset data warehouse based on the data type to be mined, and the data set to be mined is mined based on a data mining purpose, so as to obtain a target data set, including:
Analyzing the business decision requirement, acquiring a target feature vector corresponding to the business decision requirement, determining a target access data identifier based on the target feature vector, and matching the target access data identifier with each preset data file identifier of a preset data warehouse based on the target access data identifier to lock a data set to be mined;
determining the width of a data interval of a data set to be mined, determining the mining precision of the data set to be mined based on the data mining purpose, and determining the stepping length of the data set to be mined based on the precision;
performing first traversal on a data set to be mined based on the stepping length, determining behavior feature vectors of all data to be mined in the data set to be mined based on a first traversal result, and determining distribution features of all data to be mined, which meet the data mining purpose, in the data set to be mined based on the behavior feature vectors;
and determining a data mining distribution diagram of the data set to be mined based on the distribution characteristics, and performing second traversal on the data to be mined based on the data mining distribution diagram.
In this embodiment, the target feature vector refers to the type of defect or vulnerability that needs to be overcome by the business decision requirement, and the degree to which repair or optimization needs to be performed, etc.
In this embodiment, the target access data identifier is a tag for marking a data type that needs to be relied on to solve the business decision requirement, and may specifically be a set special symbol or the like.
In this embodiment, the preset data file identifier is a tag for marking the type of preset data file in the preset data store.
In this embodiment, locking the data set to be mined refers to determining a preset data file corresponding to the service decision requirement according to the matching degree between the target access data identifier and the preset data file identifier, where the preset data file with the largest matching degree is determined as the data set to be mined.
In this embodiment, the data interval width refers to how much data the data set to be mined contains.
In this embodiment, the mining precision refers to the need to mine the data set to be mined, and when the higher the mining precision is, the smaller the data amount to be mined is, otherwise, the larger the data amount to be mined is.
In this embodiment, the step length refers to the amount of data that can be analyzed per mining, i.e., the single maximum amount of analysis data at the time of mining.
In this embodiment, the first traversal refers to coarse mining of the data set to be mined according to the step length, and mining of the coarse data set, which has a relation with the data mining purpose, in the data set to be mined.
In this embodiment, the behavior feature vector refers to the value size of each piece of data to be mined in the data set to be mined, the corresponding data type, and the like.
In this embodiment, the distribution feature refers to a situation where data satisfying the purpose of data mining in the data set to be mined is located in the data set to be mined.
In this embodiment, the data mining profile is a chart for marking the situation of a position in the data set to be mined that satisfies the data mining purpose.
In this embodiment, the second traversal refers to performing secondary mining on data to be mined, which satisfies the purpose of data mining, so as to mine out accurate data.
The beneficial effects of the technical scheme are as follows: by analyzing the service decision requirement, the data set to be mined is accurately locked from the preset data warehouse according to the service decision requirement, meanwhile, the width of a data interval and the stepping length of the data set to be mined are determined, the data set to be mined is rapidly and accurately mined according to the stepping length, useful data related to the current service decision is conveniently mined, and convenience and guarantee are provided for auxiliary decision making.
Example 6:
on the basis of embodiment 5, the present embodiment provides an auxiliary decision method for large data mining based on AI, and the second traversal of the data to be mined based on the data mining distribution diagram includes:
Acquiring a data mining distribution diagram of a data set to be mined, and determining the data amount to be mined of different data fragments in the data set to be mined based on the data mining distribution diagram;
carrying out serialization processing on different data fragments in the data to be mined based on the data amount to be mined to obtain a data sequence to be mined, determining characteristic vectors corresponding to all the data fragments in the data sequence to be mined, and determining data mining conditions based on the data mining purpose;
and matching the characteristic vector with the data mining condition, obtaining a target data segment meeting the data mining condition based on a matching result, and associating the target data segment based on the target position of the target data segment in the data set to be mined to obtain a target data set.
In this embodiment, the amount of data to be mined refers to how much of the data is contained in the different pieces of data to be mined.
In this embodiment, a data fragment refers to a data block in a set of data to be mined that meets the purpose of data mining.
In this embodiment, the serialization processing refers to splitting the data segment, so as to accurately and effectively determine the data content of the single data in the data segment.
In this embodiment, the data sequence to be mined refers to data obtained by performing serialization processing on the data segment.
In this embodiment, the feature vector refers to a specific value size corresponding to the data segment and a corresponding content feature.
In this embodiment, the data mining condition refers to a requirement that data mined during data mining must meet, and specifically may be a type of data, a value range of the data, and the like.
In this embodiment, the target data segment refers to data in the data set to be mined that eventually satisfies the purpose of data mining.
In this embodiment, the target position refers to an original arrangement position of the target data fragment in the data set to be mined.
The beneficial effects of the technical scheme are as follows: the data fragments needing deep mining and the data quantity to be mined corresponding to the data fragments are accurately and effectively confirmed according to the data mining distribution diagram of the data set to be mined, then, the characteristic vectors of the data needing mining are accurately and effectively judged according to the data quantity to be mined, and the characteristic vectors are matched with the data mining conditions corresponding to the data mining purpose, so that the data needing to be finally mined is accurately and effectively mined, data support is provided for auxiliary decision making, and the accuracy and reliability of the auxiliary decision making are guaranteed.
Example 7:
on the basis of embodiment 6, the present embodiment provides an auxiliary decision method for large data mining based on AI, which includes, after obtaining a target data set:
acquiring an obtained target data set, determining a data mining dimension of the data set to be mined based on the data mining purpose, and performing first verification on data types in the target data set based on the data mining dimension;
meanwhile, determining an attribute value of target data in a target data set, determining a target offset of the target data relative to a data mining condition based on the attribute value, comparing the target offset with a preset threshold value, and performing second verification on data content in the target data set based on a comparison result;
when the first verification and the second verification are passed, judging that the mining of the data set to be mined is completed;
otherwise, judging that the mining of the data set to be mined is abnormal.
In this embodiment, the data mining dimension refers to the kind of data to be mined from the data set to be mined, the amount of data to be mined, and the like.
In this embodiment, the first verification refers to verifying the data type contained in the mined target data set.
In this embodiment, the attribute value refers to the value condition of the target data contained in the target data set.
In this embodiment, the target data refers to data contained in the target data set, that is, data satisfying the purpose of data mining is mined from the data set to be mined.
In this embodiment, the target offset refers to the extent to which the target data does not satisfy the data mining condition.
In this embodiment, the preset threshold is set in advance, and is used to measure whether the offset of the target data relative to the data mining condition exceeds the highest requirement.
The beneficial effects of the technical scheme are as follows: the data mining dimension and the data mining condition are accurately and effectively judged according to the data mining purpose, and the mined target data set is verified according to the data mining dimension and the data mining condition, so that the reliability and the accuracy of the target data set are ensured, a decision mechanism corresponding to the business decision requirement is conveniently optimized through the mined data, and the timely discovery of loopholes and abnormal nodes is ensured.
Example 8:
on the basis of embodiment 1, the present embodiment provides an auxiliary decision method for large data mining based on AI, in step 3, a target data set is preprocessed, and a decision mechanism corresponding to a service decision requirement is optimized based on the preprocessed target data set, including:
The method comprises the steps of obtaining a target data set, carrying out clustering treatment on the target data set based on a preset classification index to obtain sub-target data sets, determining the value of target data in each sub-target data set, and determining the abnormal type of abnormal data in each sub-target data set based on the value;
matching a target processing rule from a preset data processing rule base based on the abnormal type, and processing the target data set based on the target processing rule to obtain a standard target data set;
acquiring execution characteristics of a decision mechanism corresponding to service decision requirements, and searching sample data which has strong association with the decision mechanism from a standard target data set through a preset association rule based on the execution characteristics;
training and correcting abnormal nodes in the decision mechanism based on the sample data to finish optimization of the decision mechanism.
In this embodiment, the predetermined classification index is known in advance for characterizing the data types contained in the target data set.
In this embodiment, the sub-target data set refers to each type of data obtained by classifying the obtained target data set.
In this embodiment, the abnormal data refers to a data missing piece, invalid data, and the like contained in each sub-target data set.
In this embodiment, the preset data processing rule base is set in advance, and is used for storing different data processing rules.
In this embodiment, the target processing rule refers to a rule applicable to processing current abnormal data, and specifically may be that when the data abnormality type is that the data value is missing, the missing data segment is filled, so as to complete processing of the abnormal data, and so on.
In this embodiment, the standard target data set refers to a final data set obtained by processing each sub-target data set according to a target processing rule.
In this embodiment, the execution feature refers to the operation mode or the operation purpose of the decision mechanism in the operation process.
In this embodiment, the preset association rule is set in advance, so that each piece of target data in the mined standard target data set corresponds to each node in the decision mechanism, and thus the decision mechanism is convenient to optimize.
In this embodiment, the sample data refers to data with a strong association relationship with the decision mechanism in the mined standard target data set.
The beneficial effects of the technical scheme are as follows: the analysis of the obtained target data set is carried out to determine the abnormal data and the corresponding abnormal types in the target data set, so that the abnormal data can be conveniently and correspondingly processed according to the abnormal types, the accuracy and the reliability of the finally obtained target data set can be conveniently ensured, finally, the determination of sample data which are strongly related with the decision mechanism from the finally obtained standard target data set can be realized by determining the execution characteristics of the decision mechanism corresponding to the service decision requirement, the training and the optimization of the decision mechanism can be carried out through the sample data, the reliability of auxiliary decision can be ensured, the loopholes and abnormal nodes can be conveniently found in time, and the normal operation of the service can be ensured.
Example 9:
on the basis of embodiment 8, this embodiment provides an auxiliary decision method for large data mining based on AI, which trains and corrects a decision mechanism based on sample data, and after completing optimization of the decision mechanism, includes:
acquiring real-time operation data of a decision mechanism, constructing a state prediction model, and inputting the real-time operation data of the decision mechanism into the state prediction model to obtain a state development trend prediction curve of a service corresponding to the decision mechanism;
determining the operation characteristics of each node in the decision mechanism, and correcting the state development trend prediction curve based on the operation characteristics and the standard target data set to obtain a target state development trend prediction curve;
predicting the target probability of abnormality of the business corresponding to the decision mechanism in the running process based on the target state development trend prediction curve;
calculating the target probability of abnormal business corresponding to the decision mechanism in the operation process according to the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,the target probability of abnormal business corresponding to the decision mechanism in the running process is represented, and the value range is (0, 1); mu represents an error factor, and the value range is 0.01,0.03; m represents the number of abnormal nodes in the service corresponding to the decision mechanism; m represents the total number of nodes contained in the service corresponding to the decision mechanism; i represents the number of times of abnormality of the service corresponding to the decision mechanism and the value range is [1, n ] ]The method comprises the steps of carrying out a first treatment on the surface of the n represents the total number of abnormal times of the business corresponding to the decision mechanism in the operation process; t is t i Indicating the reason that the business corresponding to the decision mechanism is abnormal at the ith timeA barrier time length value; t represents the total time length value of the service operation corresponding to the decision mechanism; omega represents the accuracy rate of abnormal prediction of the business corresponding to the decision mechanism in the running process, and the value range is 0.85,0.95;
when the target probability is larger than a preset probability threshold, determining the position information and the anomaly type of the predicted anomaly node;
and matching an overhaul strategy based on the position information of the predicted abnormal node and the abnormal type, and overhauling each node based on the overhaul strategy to finish auxiliary decision.
In this embodiment, the real-time operational data refers to real-time data generated by the decision mechanism during operation.
In this embodiment, the state development trend prediction curve is used to characterize the running condition of the service corresponding to the decision mechanism in a future period of time.
In this embodiment, the operation features refer to the function types of the node included in the decision mechanism and the mode features of the operation.
In this embodiment, the target state development trend prediction curve refers to a final prediction curve obtained by correcting the state development trend prediction curve through the mined standard target data set.
In this embodiment, the target probability is a probability size for characterizing an anomaly of the traffic corresponding to the decision mechanism in a future period of time.
In this embodiment, the preset probability threshold is set in advance, and is used to measure whether the probability of occurrence of an abnormality exceeds an expected value.
In this embodiment, the predicted abnormal node refers to a node that may malfunction when an abnormality occurs.
The beneficial effects of the technical scheme are as follows: the state prediction model is constructed, the state development trend prediction curve of the service corresponding to the decision mechanism is accurately judged according to the real-time operation data of the decision mechanism, the obtained state development trend prediction curve is corrected according to the mined standard target data set, the abnormal target probability of the service corresponding to the decision mechanism in the operation process is analyzed according to the correction result, and the node information and the position which are possibly abnormal are accurately locked when the target probability is greater than a preset probability threshold value, so that the overhaul strategy is matched, all nodes are timely overhauled, the accurate and reliable assistance to the decision through the mined data is realized, and the reliability of the auxiliary decision is ensured.
Example 10:
the embodiment provides an auxiliary decision system for large data mining based on AI, as shown in FIG. 3, comprising:
the objective determining module is used for acquiring service decision requirements and determining data mining objectives based on the service decision requirements;
the data mining module is used for determining the type of data to be mined based on the business decision requirement, locking the data set to be mined from a preset data warehouse based on the type of the data to be mined, and mining the data set to be mined based on the data mining purpose to obtain a target data set;
the auxiliary decision-making module is used for preprocessing the target data set and optimizing a decision mechanism corresponding to the business decision-making requirement based on the preprocessed target data set.
The beneficial effects of the technical scheme are as follows: through determining the service decision requirement, the aim of effectively confirming the data mining is achieved, secondly, the data set to be mined in the preset data warehouse is mined through the data mining aim, the accuracy and the reliability of the data mining are guaranteed, and finally, decision mechanisms corresponding to the service decision requirement are optimized through the mined data, so that loopholes and abnormal nodes are guaranteed to be found in time, and the timeliness and the accuracy of response are improved.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. An auxiliary decision making method for large data mining based on AI, which is characterized by comprising the following steps:
step 1: acquiring a business decision requirement, and determining a data mining purpose based on the business decision requirement;
step 2: determining a data type to be mined based on business decision requirements, locking a data set to be mined from a preset data warehouse based on the data type to be mined, and mining the data set to be mined based on data mining purposes to obtain a target data set;
step 3: preprocessing a target data set, and optimizing a decision mechanism corresponding to the business decision requirement based on the preprocessed target data set;
wherein obtaining the business decision requirement comprises:
acquiring a service decision instruction sent by a management terminal, and sending a service information acquisition request to a server based on the service decision instruction;
analyzing the service information acquisition request, determining information characteristics to be acquired, and matching service execution behavior information corresponding to the service information acquisition request from a server based on the information characteristics to be acquired;
Extracting key fields in service execution behavior information, determining target loopholes existing in service operation based on the key fields, determining attribute values of the key fields, and evaluating abnormal grades of the target loopholes based on the attribute values to obtain the abnormal grades;
and determining the final business decision requirement based on the abnormal grade.
2. The AI-based big data mining aid decision making method of claim 1, wherein evaluating the anomaly class of the target vulnerability based on the attribute value to obtain the anomaly class comprises:
acquiring the obtained target vulnerability and determining target sub-information corresponding to the target vulnerability based on service execution behavior information;
extracting data characteristics of target sub-information, determining service item types contained in target vulnerabilities based on the data characteristics, and determining item weight values of different service items based on target proportions of the different service items corresponding to the item types in a service operation process;
and constructing an influence evaluation model based on the project weight value, inputting target sub-information corresponding to the target vulnerability and the corresponding target value into the influence evaluation model for analysis to obtain the influence degree of the target vulnerability on the service, and matching the influence degree with a preset grading threshold value to obtain the abnormal grade of the target vulnerability.
3. The AI-based big data mining aid decision making method according to claim 1, wherein in step 1, determining a data mining objective based on a business decision requirement comprises:
acquiring a script file corresponding to a service, and analyzing the script file to obtain service characteristics of the service;
determining a node identification of a target node contained in a service operation process based on the service characteristics, and determining a service dimension corresponding to a service scene based on the node identification;
acquiring the obtained business decision requirement, and matching the business decision requirement with a business dimension to obtain a target business dimension corresponding to the business decision requirement;
and determining a service function corresponding to the target service dimension, and determining the data mining purpose based on the service function.
4. The AI-based big data mining assistant decision-making method according to claim 1, wherein in step 2, the data type to be mined is determined based on the service decision requirement, the data set to be mined is locked from a preset data warehouse based on the data type to be mined, and the data set to be mined is mined based on the data mining purpose, so as to obtain the target data set, and the method comprises the following steps:
analyzing the business decision requirement, acquiring a target feature vector corresponding to the business decision requirement, determining a target access data identifier based on the target feature vector, and matching the target access data identifier with each preset data file identifier of a preset data warehouse based on the target access data identifier to lock a data set to be mined;
Determining the width of a data interval of a data set to be mined, determining the mining precision of the data set to be mined based on the data mining purpose, and determining the stepping length of the data set to be mined based on the precision;
performing first traversal on a data set to be mined based on the stepping length, determining behavior feature vectors of all data to be mined in the data set to be mined based on a first traversal result, and determining distribution features of all data to be mined, which meet the data mining purpose, in the data set to be mined based on the behavior feature vectors;
and determining a data mining distribution diagram of the data set to be mined based on the distribution characteristics, and performing second traversal on the data to be mined based on the data mining distribution diagram.
5. The AI-based big data mining aid decision making method of claim 4, wherein performing a second traversal of the data to be mined based on the data mining profile comprises:
acquiring a data mining distribution diagram of a data set to be mined, and determining the data amount to be mined of different data fragments in the data set to be mined based on the data mining distribution diagram;
carrying out serialization processing on different data fragments in the data to be mined based on the data amount to be mined to obtain a data sequence to be mined, determining characteristic vectors corresponding to all the data fragments in the data sequence to be mined, and determining data mining conditions based on the data mining purpose;
And matching the characteristic vector with the data mining condition, obtaining a target data segment meeting the data mining condition based on a matching result, and associating the target data segment based on the target position of the target data segment in the data set to be mined to obtain a target data set.
6. The AI-based big data mining aid decision making method of claim 5, wherein after obtaining the target data set, comprising:
acquiring an obtained target data set, determining a data mining dimension of the data set to be mined based on the data mining purpose, and performing first verification on data types in the target data set based on the data mining dimension;
meanwhile, determining an attribute value of target data in a target data set, determining a target offset of the target data relative to a data mining condition based on the attribute value, comparing the target offset with a preset threshold value, and performing second verification on data content in the target data set based on a comparison result;
when the first verification and the second verification are passed, judging that the mining of the data set to be mined is completed;
otherwise, judging that the mining of the data set to be mined is abnormal.
7. The AI-based big data mining assistant decision making method according to claim 1, wherein in step 3, preprocessing a target data set, and optimizing a decision mechanism corresponding to a service decision requirement based on the preprocessed target data set, includes:
The method comprises the steps of obtaining a target data set, carrying out clustering treatment on the target data set based on a preset classification index to obtain sub-target data sets, determining the value of target data in each sub-target data set, and determining the abnormal type of abnormal data in each sub-target data set based on the value;
matching a target processing rule from a preset data processing rule base based on the abnormal type, and processing the target data set based on the target processing rule to obtain a standard target data set;
acquiring execution characteristics of a decision mechanism corresponding to service decision requirements, and searching sample data which has strong association with the decision mechanism from a standard target data set through a preset association rule based on the execution characteristics;
training and correcting abnormal nodes in the decision mechanism based on the sample data to finish optimization of the decision mechanism.
8. The AI-based big data mining aided decision-making method of claim 7, wherein training and correcting the decision-making mechanism based on the sample data, after completing the optimization of the decision-making mechanism, comprises:
acquiring real-time operation data of a decision mechanism, constructing a state prediction model, and inputting the real-time operation data of the decision mechanism into the state prediction model to obtain a state development trend prediction curve of a service corresponding to the decision mechanism;
Determining the operation characteristics of each node in the decision mechanism, and correcting the state development trend prediction curve based on the operation characteristics and the standard target data set to obtain a target state development trend prediction curve;
predicting the target probability of abnormality of the business corresponding to the decision mechanism in the running process based on the target state development trend prediction curve, and determining the position information and the abnormality type of the abnormal node when the target probability is greater than a preset probability threshold;
and matching an overhaul strategy based on the position information of the predicted abnormal node and the abnormal type, and overhauling each node based on the overhaul strategy to finish auxiliary decision.
9. An AI-based big data mining aid decision making system, comprising:
the objective determining module is used for acquiring service decision requirements and determining data mining objectives based on the service decision requirements;
the data mining module is used for determining the type of data to be mined based on the business decision requirement, locking the data set to be mined from a preset data warehouse based on the type of the data to be mined, and mining the data set to be mined based on the data mining purpose to obtain a target data set;
the auxiliary decision-making module is used for preprocessing the target data set and optimizing a decision-making mechanism corresponding to the business decision-making requirement based on the preprocessed target data set;
Wherein obtaining the business decision requirement comprises:
acquiring a service decision instruction sent by a management terminal, and sending a service information acquisition request to a server based on the service decision instruction;
analyzing the service information acquisition request, determining information characteristics to be acquired, and matching service execution behavior information corresponding to the service information acquisition request from a server based on the information characteristics to be acquired;
extracting key fields in service execution behavior information, determining target loopholes existing in service operation based on the key fields, determining attribute values of the key fields, and evaluating abnormal grades of the target loopholes based on the attribute values to obtain the abnormal grades;
and determining the final business decision requirement based on the abnormal grade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211438379.5A CN116070111B (en) | 2022-11-17 | 2022-11-17 | Auxiliary decision method and system for big data mining based on AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211438379.5A CN116070111B (en) | 2022-11-17 | 2022-11-17 | Auxiliary decision method and system for big data mining based on AI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116070111A CN116070111A (en) | 2023-05-05 |
| CN116070111B true CN116070111B (en) | 2023-08-04 |
Family
ID=86168989
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211438379.5A Active CN116070111B (en) | 2022-11-17 | 2022-11-17 | Auxiliary decision method and system for big data mining based on AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116070111B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116956130B (en) * | 2023-07-25 | 2024-06-14 | 北京安联通科技有限公司 | Intelligent data processing method and system based on associated feature carding model |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256257A (en) * | 2017-06-12 | 2017-10-17 | 上海携程商务有限公司 | Abnormal user generation content identification method and system based on business datum |
| CN112015618A (en) * | 2020-08-17 | 2020-12-01 | 杭州指令集智能科技有限公司 | Abnormity warning method and device |
| WO2021135532A1 (en) * | 2020-07-21 | 2021-07-08 | 平安科技（深圳）有限公司 | Cloud network vulnerability discovery method, apparatus, electronic device, and medium |
| CN113592035A (en) * | 2021-08-23 | 2021-11-02 | 广州梦源信息科技有限公司 | Big data mining method based on AI auxiliary decision and AI auxiliary decision system |
| CN113590601A (en) * | 2020-12-30 | 2021-11-02 | 陈静 | Big data mining method and system for cloud computing service |
| CN113704751A (en) * | 2021-08-31 | 2021-11-26 | 姜虎 | Vulnerability repairing method based on artificial intelligence decision and big data mining system |
| CN113961615A (en) * | 2021-09-27 | 2022-01-21 | 北京东方通科技股份有限公司 | Multi-layer service fusion decision method and system |
| CN115225336A (en) * | 2022-06-24 | 2022-10-21 | 中国人民解放军国防科技大学 | Vulnerability availability calculation method and device for network environment |
| CN115329204A (en) * | 2022-03-08 | 2022-11-11 | 张伟斌 | Cloud business service pushing method and pushing processing system based on big data mining |
-
2022
- 2022-11-17 CN CN202211438379.5A patent/CN116070111B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256257A (en) * | 2017-06-12 | 2017-10-17 | 上海携程商务有限公司 | Abnormal user generation content identification method and system based on business datum |
| WO2021135532A1 (en) * | 2020-07-21 | 2021-07-08 | 平安科技（深圳）有限公司 | Cloud network vulnerability discovery method, apparatus, electronic device, and medium |
| CN112015618A (en) * | 2020-08-17 | 2020-12-01 | 杭州指令集智能科技有限公司 | Abnormity warning method and device |
| CN113590601A (en) * | 2020-12-30 | 2021-11-02 | 陈静 | Big data mining method and system for cloud computing service |
| CN113592035A (en) * | 2021-08-23 | 2021-11-02 | 广州梦源信息科技有限公司 | Big data mining method based on AI auxiliary decision and AI auxiliary decision system |
| CN113704751A (en) * | 2021-08-31 | 2021-11-26 | 姜虎 | Vulnerability repairing method based on artificial intelligence decision and big data mining system |
| CN113961615A (en) * | 2021-09-27 | 2022-01-21 | 北京东方通科技股份有限公司 | Multi-layer service fusion decision method and system |
| CN115329204A (en) * | 2022-03-08 | 2022-11-11 | 张伟斌 | Cloud business service pushing method and pushing processing system based on big data mining |
| CN115225336A (en) * | 2022-06-24 | 2022-10-21 | 中国人民解放军国防科技大学 | Vulnerability availability calculation method and device for network environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116070111A (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112528519A (en) | Method, system, readable medium and electronic device for engine quality early warning service | |
| CN111259947A (en) | Power system fault early warning method and system based on multi-mode learning | |
| CN110874744B (en) | Data anomaly detection method and device | |
| CN116070111B (en) | Auxiliary decision method and system for big data mining based on AI | |
| CN113704328B (en) | User behavior big data mining method and system based on artificial intelligence | |
| CN111190832A (en) | Method, device and system for positioning and optimizing performance bottleneck | |
| CN116861446A (en) | Data security assessment method and system | |
| CN113987504A (en) | Vulnerability detection method for network asset management | |
| CN113687972A (en) | Method, device and equipment for processing abnormal data of business system and storage medium | |
| CN114036531A (en) | Multi-scale code measurement-based software security vulnerability detection method | |
| CN115357906A (en) | Intelligent auxiliary evaluation method and system for network security level protection 2.0 | |
| CN116150191A (en) | Data operation acceleration method and system for cloud data architecture | |
| CN115225336A (en) | Vulnerability availability calculation method and device for network environment | |
| CN113704772B (en) | Safety protection processing method and system based on user behavior big data mining | |
| CN112632330A (en) | Method and device for routing inspection of ATM equipment, computer equipment and storage medium | |
| CN110825725A (en) | Data quality checking method and system based on double helix management | |
| CN113962331A (en) | ETC portal system fault reason identification method and system | |
| CN112712423A (en) | Suspected illegal fundraising item judgment method and device, computer equipment and storage medium | |
| Yazdi et al. | An optimization model for designing acceptance sampling plan based on cumulative count of conforming run length using minimum angle method | |
| CN110175200A (en) | A kind of abnormal energy analysis method and system based on intelligent algorithm | |
| CN114913670B (en) | Personnel going out of sea safety management system based on safety code management | |
| CN117240527B (en) | Network security risk prevention system and method | |
| CN112307090B (en) | Detection method and system based on tunnel security data | |
| CN117556187B (en) | Cloud data restoration method and system based on deep learning and readable storage medium | |
| CN112528293B (en) | Security vulnerability early warning method, device, equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |