CN118101344B - Transmission security identification system, method and medium for 5G message - Google Patents
Transmission security identification system, method and medium for 5G message Download PDFInfo
- Publication number
- CN118101344B CN118101344B CN202410496594.3A CN202410496594A CN118101344B CN 118101344 B CN118101344 B CN 118101344B CN 202410496594 A CN202410496594 A CN 202410496594A CN 118101344 B CN118101344 B CN 118101344B
- Authority
- CN
- China
- Prior art keywords
- data
- message
- real
- time
- safety
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000005070 sampling Methods 0.000 claims abstract description 161
- 238000009826 distribution Methods 0.000 claims abstract description 36
- 230000002776 aggregation Effects 0.000 claims abstract description 30
- 238000004220 aggregation Methods 0.000 claims abstract description 30
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 230000010354 integration Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 73
- 238000004422 calculation algorithm Methods 0.000 claims description 38
- 238000004140 cleaning Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims 6
- 238000005516 engineering process Methods 0.000 abstract description 14
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 description 20
- 238000004458 analytical method Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000007405 data analysis Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005111 flow chemistry technique Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000004904 shortening Methods 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to artificial intelligence technology, and discloses a transmission safety recognition system, method and medium for 5G messages, wherein the system comprises a feature extraction module, a flow sampling module, a data aggregation module, a node distribution module, a parallel recognition module and a result integration module, wherein the feature extraction module can be used for extracting the historical flow data of the 5G messages to obtain the historical flow characteristics of the historical flow data, a dynamic sampling parameter set of the 5G messages is generated according to the historical flow characteristics, the flow sampling is carried out on the 5G messages in transmission according to the dynamic sampling parameter set, the data aggregation is carried out on the real-time flow data obtained by sampling to obtain the data blocks of the 5G messages, a distributed computing architecture is constructed, the node distribution is carried out on the data blocks by utilizing the computing nodes of the distributed computing architecture, the parallel safety recognition is carried out on the data blocks according to the distributed nodes, the safety recognition result of the 5G messages is obtained, and the recognition efficiency of the transmission safety recognition of the 5G messages is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a transmission safety identification system, method and medium for 5G messages.
Background
The application of 5G technology relates to many business fields such as internet of things, smart cities, autopilot, etc. The requirements of the fields on network security are extremely high, any security hole can cause serious economic loss and trust crisis, the trust degree of enterprises and users on the network can be improved by identifying and enhancing the transmission security of the information, and the healthy development of digital economy is promoted.
At present, the existing transmission safety identification aiming at the 5G message has the problems that a sampling strategy is not intelligent enough, a large amount of redundant information is reserved in the transmission process, the safety identification process can only be carried out in series, a plurality of data blocks cannot be processed at the same time, and the like, so that the identification efficiency of the transmission safety identification aiming at the 5G message is lower.
Disclosure of Invention
The invention provides a transmission safety identification system, a method and a medium for 5G messages, and mainly aims to solve the problem of low identification efficiency of transmission safety identification for 5G messages.
In order to achieve the above objective, the present invention provides a transmission security identification system for 5G messages, which is characterized in that the system includes a feature extraction module, a traffic sampling module, a data aggregation module, a node allocation module, a parallel identification module, and a result integration module, wherein:
The feature extraction module is used for carrying out feature extraction on the historical flow data of the 5G message to obtain the historical flow feature of the historical flow data, and generating a dynamic sampling parameter set of the 5G message according to the historical flow feature;
The flow sampling module is used for sampling the flow of the 5G message in transmission according to the dynamic sampling parameter set to obtain real-time flow data of the 5G message;
the data aggregation module is used for carrying out data aggregation on the real-time flow data according to the data similarity of the real-time flow data to obtain a data block of the 5G message;
the node allocation module is used for constructing a distributed computing architecture of the 5G message, and performing node allocation on the data blocks by using computing nodes of the distributed computing architecture to obtain allocation nodes of the data blocks;
The parallel identification module is configured to determine a data set to be identified according to the allocation node and the data block, and perform parallel security identification on the data set by using a preset initial feature and a preset security identification algorithm to obtain a parallel identification result of the data block, where the preset security identification algorithm is: Wherein/> Is in the dataset/>Above, using a preset initial feature/>Gain of information obtained by dividing,/>Is the dataset/>Entropy of/>Is a preset initial feature/>Value set of (1)/>Is the dataset/>Preset initial feature/>Take the value of/>Subset of/>Is a dataset,/>Is a subset/>Entropy of (2);
and the result integration module is used for integrating the parallel recognition results to obtain the safety recognition result of the 5G message.
Optionally, when performing feature extraction on the historical traffic data of the 5G message, the feature extraction module obtains a historical traffic feature of the historical traffic data, including:
Performing data cleaning on the historical flow data of the 5G message to obtain cleaning data of the historical flow data;
generating time sequence characteristics and distribution characteristics of the historical flow data according to the cleaning data;
And collecting the time sequence characteristic and the distribution characteristic as the historical flow characteristic of the historical flow data.
Optionally, the feature extraction module, when executing the dynamic sampling parameter set for generating the 5G message according to the historical traffic feature, includes:
Generating a dynamic sampling proportion of the 5G message according to the historical flow characteristics;
generating a dynamic sampling frequency of the 5G message according to the historical flow characteristics;
and generating a dynamic sampling parameter set of the 5G message according to the dynamic sampling proportion and the dynamic sampling frequency.
Optionally, when performing traffic sampling on the 5G message in transmission according to the dynamic sampling parameter set, the traffic sampling module obtains real-time traffic data of the 5G message, including:
Determining the real-time sampling proportion and the real-time sampling frequency of the 5G message in transmission according to the dynamic sampling array;
and adaptively sampling the 5G message in the transmission according to the real-time sampling proportion and the real-time sampling frequency to obtain the real-time flow data of the 5G message.
Optionally, the data aggregation module performs data aggregation on the real-time traffic data according to the data similarity of the real-time traffic data to obtain the data block of the 5G message, and includes:
Generating data similarity of the real-time flow data by using a preset similarity algorithm, wherein the preset similarity algorithm is as follows: Wherein/> Is the data similarity of the real-time traffic data,/>Is the target flow data in the real-time flow data,/>Is the comparison flow data in the real-time flow data,/>Is the total number of data features of the real-time traffic data,/>Is a data characteristic identification of the real-time traffic data,/>Is the/>, of the target traffic dataData characteristics,/>Is the/>, of the control traffic dataData characteristics;
and carrying out data aggregation on the real-time flow data according to the data similarity and a preset similarity threshold value to obtain a data block of the 5G message.
Optionally, the node allocation module, when executing node allocation to the data block by using the computing node of the distributed computing architecture, obtains an allocation node of the data block, includes:
generating the processing complexity and the data size of the data block;
Distributing the data blocks to computing nodes of the distributed computing architecture according to the processing complexity and the data size;
And carrying out resource verification on the computing nodes, and determining the computing nodes passing the resource verification as the distribution nodes of the data blocks.
Optionally, the parallel identification module performs parallel security identification on the data set by using a preset initial feature and a preset security identification algorithm, so as to obtain a parallel identification result of the data block, and the parallel identification module includes:
Dividing the data sets in parallel according to preset initial characteristics to obtain subsets of the data sets;
Generating a feature value of the subset;
Calculating information gains of the subset by using the preset safety recognition algorithm and the characteristic value;
Generating a safety value of the subset according to the information gain, and carrying out safety marking on the subset according to the safety value and a preset safety threshold value to obtain a marking set of the subset;
and carrying out reliability check on the mark set, and generating a parallel identification result of the data block according to the check result of the reliability check and the mark set.
Optionally, the result integrating module performs result integration on the parallel recognition result to obtain a secure recognition result of the 5G message, and includes:
generating a safety probability value of the parallel recognition result;
carrying out weighted average processing on the safety probability value to obtain a weighted average value of the safety probability value;
And generating a safety identification result of the 5G message according to the weighted average value and a preset safety level.
In order to solve the above problem, the present invention further provides a transmission security identification method for a 5G message, the method comprising:
extracting the characteristics of the historical flow data of the 5G message to obtain the historical flow characteristics of the historical flow data, and generating a dynamic sampling parameter set of the 5G message according to the historical flow characteristics;
Performing flow sampling on the 5G message in transmission according to the dynamic sampling parameter set to obtain real-time flow data of the 5G message;
Performing data aggregation on the real-time flow data according to the data similarity of the real-time flow data to obtain a data block of the 5G message;
Constructing a distributed computing architecture of the 5G message, and performing node distribution on the data blocks by utilizing computing nodes of the distributed computing architecture to obtain distribution nodes of the data blocks;
Carrying out parallel safety recognition on the data blocks according to the distribution nodes and a preset safety recognition algorithm to obtain a parallel recognition result of the data blocks;
and integrating the parallel recognition results to obtain the safety recognition result of the 5G message.
In order to solve the above-mentioned problems, the present invention also provides a storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-mentioned transmission security identification method for 5G messages.
The invention can dynamically adjust the sampling proportion and frequency according to the characteristics of the historical flow data by using an intelligent sampling technology, so that the sampled data can fully represent the integral flow characteristics, thereby more accurately extracting the required information from the real-time flow data, reducing unnecessary resource waste, and through a high-efficiency data aggregation algorithm, similar data can be combined and processed, redundant information is reduced, thus reducing the burden of subsequent processing, improving the integral processing efficiency, simultaneously reducing the resources required by storage and transmission, ensuring that the data blocks can be quickly and effectively distributed to each computing node, fully utilizing the processing capacity of each node, improving the integral processing speed and efficiency when processing a large amount of data, adopting advanced parallel processing technology such as multi-thread, multi-core processing and the like, enabling the safety recognition process to be simultaneously carried out on different data blocks, remarkably improving the processing speed, shortening the recognition time, and improving the integral transmission safety recognition efficiency, therefore, the transmission safety recognition system and method for the 5G message and the transmission safety recognition method for the 5G message can improve the safety recognition efficiency for the medium.
Drawings
Fig. 1 is a system architecture diagram of a transmission security identification system for 5G messages according to an embodiment of the present invention;
fig. 2 is a flow chart of a method for identifying transmission security of 5G messages according to an embodiment of the present invention;
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in embodiments of the present invention, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" typically includes at least two.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.
In addition, the sequence of steps in the method embodiments described below is only an example and is not strictly limited.
In an implementation form, the transmission security identification system for the 5G message and the user side are mutually adapted. Namely, the transmission security identification system aiming at the 5G message is used as an application installed on the cloud service platform, and the user side is used as a client side for establishing communication connection with the application; or realizing the transmission safety identification system aiming at the 5G message as a website, and realizing the user side as a webpage; and then or the transmission security identification system aiming at the 5G message is realized as a cloud service platform, and the user side is realized as an applet in the instant messaging application.
Fig. 1 is a system architecture diagram of a transmission security identification system for 5G messages according to an embodiment of the present invention.
The transmission security identification system 100 for 5G messages of the present invention may be disposed in a cloud server, and in implementation form, may be used as one or more service devices, may also be used as an application installed on the cloud (e.g. a server of a mobile service operator, a server cluster, etc.), or may also be developed as a website. Depending on the implemented functionality, the transmission security identification system 100 for 5G messages may include a feature extraction module 101, a traffic sampling module 102, a data aggregation module 103, a node allocation module 104, a parallel identification module 105, and a result integration module 106.
In the embodiment of the invention, in the transmission safety identification system for the 5G message, each module can be independently realized and called with other modules. A call herein is understood to mean that a module may connect to a plurality of modules of another type and provide corresponding services to the plurality of modules to which it is connected. For example, the sharing evaluation module can call the same information acquisition module to acquire the information acquired by the information acquisition module based on the characteristics, and in the transmission safety identification system for the 5G message provided by the embodiment of the invention, the application range of the transmission safety identification system architecture for the 5G message can be adjusted by adding the module and directly calling the module without modifying the program code, so that the cluster type horizontal expansion is realized, and the purpose of rapidly and flexibly expanding the transmission safety identification system for the 5G message is achieved. In practical applications, the modules may be disposed in the same device or different devices, or may be service instances disposed in virtual devices, for example, in a cloud server.
The following description is directed to respective components of a transmission security identification system for 5G messages and specific workflows, respectively, in conjunction with specific embodiments:
The feature extraction module 101 is configured to perform feature extraction on historical flow data of a 5G message, obtain a historical flow feature of the historical flow data, and generate a dynamic sampling parameter set of the 5G message according to the historical flow feature.
In the embodiment of the present invention, when performing feature extraction on the historical traffic data of the 5G message to obtain the historical traffic feature of the historical traffic data, the feature extraction module 101 includes:
Performing data cleaning on the historical flow data of the 5G message to obtain cleaning data of the historical flow data;
generating time sequence characteristics and distribution characteristics of the historical flow data according to the cleaning data;
And collecting the time sequence characteristic and the distribution characteristic as the historical flow characteristic of the historical flow data.
In detail, the 5G message refers to a new type of communication service based on a 5G network, which aims to provide a more efficient and reliable messaging experience, and support a wider variety of message formats and functions, such as multimedia message, location information sharing, etc.
In detail, the data cleaning refers to processing the original data to remove errors, incomplete, repeated or improper data, so as to ensure that the data quality meets the analysis requirement; the time sequence features refer to time-related features in the data, such as trends, periodicity, etc. in the time sequence data; the distribution characteristics are distribution conditions of data in different value ranges, such as mean value, variance, quantile and the like of the data.
Further, processing the historical flow data of the 5G message to remove the data which does not meet the requirements; extracting time sequence features and distribution features from the cleaned data; and collecting the extracted time sequence characteristics and the distribution characteristics to form characteristic representation of the historical flow data.
In detail, the data cleansing may utilize data preprocessing techniques including missing value processing, outlier detection and processing, de-duplication, etc., and common methods include interpolation padding, de-outlier, de-duplication, etc.
In detail, the data cleaning is to ensure the accuracy and the integrity of the data and improve the credibility and the accuracy of the subsequent analysis.
In detail, the extraction of the time series features may utilize a time series analysis technique such as trend analysis, periodicity analysis, sliding window method, and the like.
In detail, the extraction of the distribution features may utilize statistical methods, such as calculating means, variances, quantiles, etc.
In detail, time-dependent features and data distribution features are extracted from historical flow data, which provide a basis for subsequent analysis and modeling.
In detail, the feature collection can simply combine the extracted time sequence features and the distribution features to form a feature representation of the historical flow data, and the complete historical flow features are constructed by integrating different types of features together to provide input data for subsequent analysis and modeling.
In general, by performing data cleaning and feature extraction on historical flow data, more representative and analyzable data features can be obtained, supporting subsequent data analysis and safety recognition.
In the embodiment of the present invention, the feature extraction module 101, when executing the generation of the dynamic sampling parameter set of the 5G message according to the historical traffic feature, includes:
Generating a dynamic sampling proportion of the 5G message according to the historical flow characteristics;
generating a dynamic sampling frequency of the 5G message according to the historical flow characteristics;
and generating a dynamic sampling parameter set of the 5G message according to the dynamic sampling proportion and the dynamic sampling frequency.
In detail, the dynamic sampling parameter set includes two important parameters of sampling proportion and sampling frequency, which play a key role in real-time flow monitoring and safety recognition.
In detail, the sampling ratio refers to a ratio of the amount of data sampled from the original traffic to the total amount of data. For example, if the sampling ratio is 10%, 1 out of every 10 data packets is sampled, the remaining 9 are discarded, and the sampling ratio is selected to balance the accuracy of real-time monitoring with the consumption of system resources.
In detail, the sampling ratio refers to a ratio of the amount of data sampled from the original traffic to the total amount of data. For example, if dynamic adjustment of the sampling rate is performed in response to changes in network traffic, the sampling rate may be reduced to reduce processing pressure when network loading is high, and increased to increase monitoring sensitivity when abnormal traffic occurs in the network.
In detail, the sampling frequency refers to a time interval or frequency of sampling, i.e., how often traffic is sampled. The sampling frequency is selected depending on the real-time requirements of the monitoring and may be typically set in milliseconds or seconds.
In detail, the dynamic adjustment of the sampling frequency can be performed according to the change of the network traffic and the monitoring requirement, for example, the sampling frequency can be reduced to reduce the amount of sampling data when the network traffic is stable, and the sampling frequency can be increased to respond more quickly and perform safety recognition when abnormal traffic is found.
In detail, by reasonably adjusting and dynamically optimizing the sampling proportion and the sampling frequency, the system resource can be effectively managed while the time-lapse monitoring precision is ensured, and the safety recognition efficiency and accuracy are improved.
In detail, a sampling parameter set is dynamically generated according to historical flow characteristics and monitoring requirements. This can be achieved by the following steps:
An initial sampling rate is determined based on characteristics of the historical traffic data, such as traffic size, traffic distribution, etc., e.g., if there are a large number of small traffic packets in the historical traffic, then the sampling rate may be considered reduced to reduce sampling of the small traffic, while for large traffic the sampling rate may be increased appropriately.
An initial sampling frequency is determined based on the trend of the historical flow data and the monitoring requirements, for example, if there is periodic variation in the historical flow, the sampling frequency can be determined based on the periodic variation to ensure real-time monitoring.
Dynamic adjustment strategies are formulated, and sampling parameter sets are adaptively adjusted according to the change condition of real-time flow data and monitoring requirements, for example, if abnormal flow or security threat is detected, sampling proportion and frequency can be increased to improve monitoring precision, and sampling parameters can be properly reduced to reduce system resource consumption when network flow is stable.
By the method, the dynamic sampling parameter set adapting to the real-time monitoring requirement can be generated according to the historical flow characteristics, so that the monitoring efficiency and accuracy of the 5G message transmission safety are improved.
Further, the generated dynamic sampling ratio and dynamic sampling frequency are combined into a parameter set as input parameters for the control message sampling. The sampling proportion and the sampling frequency can be integrated into a parameter set by using a data processing and integration technology, and the dynamically adjusted sampling proportion and the dynamically adjusted sampling frequency are combined in a parameter form, so that the configuration and the application in an actual system are facilitated, and the dynamic control of the 5G message sampling is realized.
In detail, the dynamic sampling parameter set can be dynamically adjusted according to the historical flow characteristics so as to adapt to the flow change in different time periods and network environments. This can be achieved by monitoring network traffic in real time and automatically adjusting parameters to ensure the validity and accuracy of the sampling.
The flow sampling module 102 is configured to sample a flow of the 5G message in transmission according to the dynamic sampling parameter set, so as to obtain real-time flow data of the 5G message.
In the embodiment of the present invention, when the flow sampling module 102 performs flow sampling on the 5G message in transmission according to the dynamic sampling parameter set to obtain real-time flow data of the 5G message, the flow sampling module includes:
Determining the real-time sampling proportion and the real-time sampling frequency of the 5G message in transmission according to the dynamic sampling array;
and adaptively sampling the 5G message in the transmission according to the real-time sampling proportion and the real-time sampling frequency to obtain the real-time flow data of the 5G message.
In detail, the real-time sampling ratio refers to a ratio determined according to a dynamic sampling parameter set during transmission, and is used for determining a ratio between the number of messages sampled in real time and the total number of messages; the real-time sampling frequency refers to a frequency determined according to a dynamic sampling parameter set in a transmission process, and is used for determining a time interval of message sampling or periodicity of sampling.
In detail, the real-time sampling proportion is dynamically calculated according to the information in the dynamic sampling parameter set so as to adapt to the network flow change in the transmission process.
In detail, the real-time sampling frequency is dynamically calculated according to the information in the dynamic sampling parameter set to adapt to the network traffic variation in the transmission process.
In detail, according to the real-time sampling proportion and the real-time sampling frequency, the 5G message in transmission is adaptively sampled to obtain real-time flow data, namely, the sampling strategy is dynamically adjusted according to the current network flow condition.
In detail, the real-time flow monitoring and analyzing technology can be utilized, the historical flow characteristics and the current network flow state in the dynamic sampling parameter set are combined, an algorithm (such as dynamic programming, greedy algorithm and the like) is adopted to dynamically calculate the real-time sampling proportion, and the accuracy of network load and data analysis can be considered in sampling under different network flow loads by dynamically adjusting the real-time sampling proportion, so that the sampling efficiency and the data reliability are improved.
In detail, by combining the historical flow characteristics and the real-time flow data in the dynamic sampling parameter set, a time sequence analysis or a machine learning algorithm (such as a random forest, a neural network and the like) is adopted to dynamically calculate the real-time sampling frequency, and the sampling frequency is dynamically adjusted according to the current network flow condition and the message transmission rate, so that the sampling interval is ensured to be properly increased under high load, the excessive influence on the network performance is avoided, and meanwhile, the sampling frequency of key data is ensured to be high enough to meet the requirements of real-time monitoring and analysis.
In detail, the dynamic sampling proportion and the real-time sampling frequency are utilized to carry out self-adaptive sampling on the 5G messages in transmission, the messages meeting the conditions can be screened out for sampling according to the sampling proportion and the sampling frequency through the real-time flow control and data filtering technology, the message sampling strategy is adaptively adjusted according to the current network flow condition and the guidance of the dynamic sampling parameter set, the timely and accurate sampling of key data is ensured, meanwhile, unnecessary waste of network resources is avoided, and therefore the efficiency and the accuracy of data acquisition are improved.
Further, through reasonable sampling proportion and frequency, the collected data can accurately reflect the flow characteristics of the 5G message; the self-adaptive sampling can reasonably allocate calculation and storage resources according to actual needs, so that the overall resource consumption of the system is reduced; by dynamically adjusting the sampling rate, unnecessary data processing work is reduced, and the data analysis speed is increased.
In summary, by dynamically calculating the real-time sampling proportion and the real-time sampling frequency and combining with the adaptive sampling strategy, the message sampling can be effectively controlled in the transmission process, the real-time flow data can be obtained, and the accuracy and the efficiency of data acquisition can be ensured.
The data aggregation module 103 is configured to perform data aggregation on the real-time traffic data according to the data similarity of the real-time traffic data, so as to obtain a data block of the 5G message.
In the embodiment of the present invention, when executing data aggregation on the real-time traffic data according to the data similarity of the real-time traffic data, the data aggregation module 103 includes:
Generating data similarity of the real-time flow data by using a preset similarity algorithm, wherein the preset similarity algorithm is as follows: Wherein/> Is the data similarity of the real-time traffic data,/>Is the target flow data in the real-time flow data,/>Is the comparison flow data in the real-time flow data,/>Is the total number of data features of the real-time traffic data,/>Is a data characteristic identification of the real-time traffic data,/>Is the/>, of the target traffic dataData characteristics,/>Is the/>, of the control traffic dataData characteristics;
and carrying out data aggregation on the real-time flow data according to the data similarity and a preset similarity threshold value to obtain a data block of the 5G message.
In detail, the data similarity represents the degree of similarity between two sets of data, and is generally represented by a numerical value, wherein the closer the numerical value is to 1, the more similar the data is, and the closer the numerical value is to 0, the more dissimilar the data is; the target flow data refers to a group of real-time flow data which needs to be subjected to similarity comparison; the control flow data refers to another set of real-time flow data as a reference for comparison with the target flow data; the total number of data features refers to the number of features contained in the real-time traffic data that describe various aspects or attributes of the data.
In detail, data aggregation refers to a process of combining a plurality of data sets into one data set, and may be performed by various methods, such as weighted average, cluster analysis, and the like.
In detail, a preset similarity algorithm is utilized to compare characteristic values of the target flow data and the comparison flow data, the similarity between the target flow data and the comparison flow data is calculated, and the similarity degree between the target flow data and the comparison flow data can be quantified through calculating the data similarity, so that a basis is provided for subsequent data aggregation.
In detail, according to a preset similarity threshold value, similarity comparison is carried out on each data block in the real-time flow data, and data aggregation is carried out according to a similarity result. The data blocks with higher similarity can be aggregated into one data block by adopting methods such as cluster analysis, weighted average and the like.
In detail, through data aggregation, similar data blocks in the real-time flow data can be combined into one data block, so that data redundancy is reduced, data processing efficiency is improved, and meanwhile, important information is reserved for subsequent data analysis and application.
For example: assume that there are two sets of real-time traffic data, each set of data containing 5 data features (n=5), representing different attributes of the traffic, respectively. It is now necessary to calculate the similarity between them and to aggregate the data according to a similarity threshold.
Assuming target flow dataControl traffic data/>Calculating according to a preset similarity algorithm to obtain that the similarity of the two is approximately equal to/>Assuming that the preset similarity threshold is 0.9, it can be seen from the calculation result that the similarity between the target traffic data and the reference traffic data is higher than the threshold, so that they can be aggregated into one data block.
In detail, when performing data aggregation on the real-time traffic data according to the data similarity and a preset similarity threshold, the data aggregation module 103 obtains a data block of the 5G message, including:
and when the data similarity is larger than a preset similarity threshold, carrying out data aggregation on the real-time flow data to obtain a data block of the 5G message.
The node allocation module 104 is configured to construct a distributed computing architecture of the 5G message, and allocate nodes to the data blocks by using computing nodes of the distributed computing architecture to obtain allocation nodes of the data blocks.
In the embodiment of the present invention, the node allocation module 104, when executing a distributed computing architecture for constructing the 5G message, includes:
In detail, a distributed computing architecture is a system architecture that distributes computing tasks to multiple nodes or computing resources for parallel processing, with the aim of improving computing efficiency, flexibility, and reliability.
In detail, through researching and analyzing the requirements and application scenes of the 5G message service, the characteristics of the user requirements, the data volume, the instantaneity and the like are known, the architecture design is ensured to meet the actual application requirements, and the communication requirements of the user are met.
Further, the basic components of the distributed computing architecture are determined, and by selecting appropriate distributed computing frameworks and components, e.g., APACHE KAFKA, APACHE SPARK, etc., for distribution, processing, and storage of data, it is ensured that the architecture has the basic functionality and features required for distributed computing, e.g., high availability, fault tolerance, etc.
Further, the data flow and the processing flow are designed, and the flow processing technology such as APACHE FLINK, apache Storm and the like is used for designing the data flow processing flow, including the receiving, analyzing, processing and distributing of the messages, so that the efficient processing and the distributing of the real-time messages are realized, and the real-time performance and the reliability of the messages are ensured.
Further, the distributed computing nodes are deployed, a proper cloud computing platform or server cluster is selected, the distributed computing nodes are deployed, corresponding software environments and resources are configured, and the sufficient and stable computing resources are ensured so as to support the requirements of large-scale message processing and distribution.
Further, a distributed storage system such as Apache Hadoop and Cassandra is used for storing the processed information in a lasting mode, and a proper retrieval mechanism is designed to ensure the safety and reliability of information data and the support of subsequent data analysis and mining.
In the embodiment of the present invention, when executing node allocation on the data block by using the computing node of the distributed computing architecture, the node allocation module 104 includes:
generating the processing complexity and the data size of the data block;
Distributing the data blocks to computing nodes of the distributed computing architecture according to the processing complexity and the data size;
And carrying out resource verification on the computing nodes, and determining the computing nodes passing the resource verification as the distribution nodes of the data blocks.
In detail, the processing complexity refers to the computing resources and time required for processing the data blocks in the distributed computing architecture; the data size refers to the size of the data block to be processed, typically measured in bytes or bits.
In detail, the data blocks to be processed are distributed to the respective computing nodes of the distributed computing architecture for parallel processing.
In detail, the computing nodes are validated, confirming that they possess sufficient computing resources and capabilities to process the allocated data blocks, determining the appropriate computing nodes, and allocating the data blocks to those nodes for processing.
In detail, the processing complexity and the data size of the generated data block can be analyzed by using an algorithm and a data analysis tool, and the processing complexity and the processing size of the data block to be processed are determined so as to know the characteristics of the data block and provide basis for subsequent distribution and processing.
In detail, the distributed message queue or the distributed file system can be used for distributing the data blocks to the computing nodes of the distributed computing architecture, so that the parallel processing of the data is realized, and the processing efficiency and the performance are improved.
In detail, the resource management tool or the monitoring system is used for monitoring the conditions of computing resources, memory, network bandwidth and the like of the computing nodes, ensuring that the computing nodes have enough resources to process the distributed data blocks, and avoiding the reduction of processing performance or task failure caused by insufficient resources.
In detail, according to the resource condition of the computing node and the processing requirement of the data block, a proper computing node is selected as a processing node of the data block, so that the data block can be efficiently processed on the node with enough computing resources, and the processing efficiency and the processing performance are improved.
For example, a distributed computing architecture requires processing a batch of data blocks containing data of varying sizes and processing complexity. The following are examples of architectural designs:
Analyzing the data blocks by using a data analysis tool to determine the processing complexity and the size of each data block, for example, the size of the data block A is 1GB, the processing complexity is higher, the size of the data block B is 100MB, and the processing complexity is lower; distributing the data blocks A and B to different computing nodes by using a distributed message queue so as to realize parallel processing; monitoring the resource condition of each computing node by using a monitoring system, for example, the computing node X has enough CPU and memory resources, and the computing node Y has shortage of resources; data block a is allocated to compute node X for processing and data block B is allocated to compute node Y for processing to ensure reasonable utilization of resources and maximization of processing performance.
Through the steps, the data blocks with different sizes and processing complexity can be distributed and processed efficiently, and the processing efficiency and performance of the distributed computing architecture are improved.
The parallel recognition module 105 is configured to determine a data set to be recognized according to the distribution node and the data block, and perform parallel security recognition on the data set by using a preset initial feature and a preset security recognition algorithm, so as to obtain a parallel recognition result of the data block.
In the embodiment of the present invention, the preset security identification algorithm is: Wherein, Is in the dataset/>Above, using a preset initial feature/>The gain of the information obtained by the division is performed,Is the dataset/>Entropy of/>Is a preset initial feature/>Value set of (1)/>Is the dataset/>Preset initial feature/>Take the value of/>Subset of/>Is a dataset,/>Is a subset/>Is a function of the entropy of (a).
In detail, the information gain refers to the degree of entropy reduction obtained after the data set is divided by using a preset initial feature, and is used for measuring the effect of the division feature; entropy refers to the degree of uncertainty or confusion of a data set, with higher entropy indicating that the data set is more unordered; the preset initial features are initial features selected during data set partitioning and are used for constructing models such as decision trees.
In detail, the data set is segmented according to preset initial characteristics to improve the purity of the data set or reduce uncertainty, and entropy calculation is performed on the data set and subsets thereof to evaluate the uncertainty degree of the data set.
In detail, according to a preset initial feature a, a data set is divided into a plurality of subsets, entropy of each subset is calculated, information gain is calculated, effect of each division is evaluated, and division with the maximum information gain is selected as an optimal division.
In detail, assuming a two-classification task, data set D contains 100 samples, 60 of which belong to class A and 40 of which belong to class B. Now, the division is performed according to a feature, which has two values: yes and No, the entropy of the data set D is calculated as: entropy (D) ≡0.971.
Further, the data set is divided and the information gain is calculated, and assuming that the division is performed according to the feature "whether safe" or not, the two subsets after the division are respectively d_yes (safe) and d_no (unsafe), and the entropy after the division is respectively: entropy (d_yes) ≡0.918, entropy (d_no) =1.0, information gain is calculated: gain (D, security) ≡0.124, by calculation, it is possible to obtain an information Gain of about 0.124 for division according to the feature "security", and a larger information Gain indicates a better division effect, and thus can be used as a basis for dividing a data set.
In detail, the parallel identification module 105 performs parallel security identification on the data set by using a preset initial feature and a preset security identification algorithm, so as to obtain a parallel identification result of the data block, and includes:
Dividing the data sets in parallel according to preset initial characteristics to obtain subsets of the data sets;
Generating a feature value of the subset;
Calculating information gains of the subset by using the preset safety recognition algorithm and the characteristic value;
Generating a safety value of the subset according to the information gain, and carrying out safety marking on the subset according to the safety value and a preset safety threshold value to obtain a marking set of the subset;
and carrying out reliability check on the mark set, and generating a parallel identification result of the data block according to the check result of the reliability check and the mark set.
In detail, the preset initial characteristics are initial characteristics selected when data set classification is performed, and are used for constructing basic characteristics of the parallel recognition model; the information gain refers to the degree of entropy reduction obtained after the data set is divided by using the preset initial characteristics, and is used for measuring the effect of the division characteristics.
In detail, the security value is a security evaluation value of the subset calculated from the security recognition algorithm and the feature value; the security threshold refers to a preset threshold for judging the security of the data set, and is used for deciding whether the subset is marked as safe or unsafe.
In detail, the data set is segmented according to preset initial characteristics so as to perform parallel identification and safety evaluation; calculating the security value and the information gain of the subset according to the characteristic value and the security identification algorithm of the subset; carrying out quantization evaluation on the security and information gain of the subset by using a security identification algorithm and formulas in the information theory; the subset is marked as safe or unsafe according to the safety value and the safety threshold value of the subset so as to generate the subsequent credibility checking and identification result.
In detail, the data set is divided according to the preset initial characteristics by using a parallel computing technology, a parallel computing framework such as Spark and the like can be adopted, so that the data set dividing efficiency is improved, and preparation is made for subsequent parallel identification and security evaluation.
In detail, the features of each subset are extracted and calculated by using a parallel computing technology, and a distributed computing framework or GPU acceleration and the like can be used for acquiring the feature information of the subset, so that a data basis is provided for subsequent safety identification and information gain calculation.
In detail, according to the safety recognition algorithm and the formulas in the information theory, the safety evaluation and the information gain calculation are carried out on the subsets, the calculation efficiency can be improved by adopting a distributed calculation technology, the safety and the division effect of the subsets are evaluated, and the basis is provided for the subsequent safety marks.
In detail, the subset is marked as safe or unsafe according to a preset safety threshold, the safety of the subset is determined, and a mark is provided for the subsequent credibility checking and recognition result generation.
In detail, a threshold may be set, for example, if the information gain is greater than a certain threshold, the subset is marked as "safe", otherwise it is marked as "unsafe".
Further, outputting the results of the security identification, each subset being marked as "safe" or "unsafe", the results may be output in the form of a data tag, e.g. with 1 for "safe", 0 for "unsafe", or a probability score for the subset directly.
In detail, assuming that there is one data set D, the data set is divided into a plurality of subsets in parallel according to a preset initial feature of "whether there is a security hole", and each subset represents a security state. Then, a security identification algorithm is used to evaluate the security of each subset and calculate the information gain. Assuming a security threshold of 0.8, i.e. a subset with a security value greater than 0.8 is marked as secure and a subset less than or equal to 0.8 is marked as unsafe.
In detail, the information gain of each subset is calculated, the security of the subset is evaluated according to the magnitude of the information gain, the larger the information gain, the higher the degree of purity improvement of the subset under a given characteristic, and therefore the safer the subset.
In detail, the performing the reliability check on the label set, and generating the parallel recognition result of the data block according to the check result of the reliability check and the label set means that, besides the label or the probability score, a corresponding reliability evaluation, that is, a confidence level of the result, which may be a probability value, a confidence level indicating the result, or a confidence interval, indicating an uncertainty range of the result, may also be output.
In detail, the results of the security identification may be used directly to make decisions or take action. For example, in the field of network security, the security recognition result may be used to decide whether to allow a certain network traffic to pass through, or whether to take further defensive measures, if there are multiple subsets marked as "secure", one or more of which may be selected as the final recognition result according to specific needs, or further refined analysis may be performed, through such output result, the user may clearly understand the security of each subset, and make corresponding decisions or processes as needed.
And the result integration module 106 is configured to integrate the parallel recognition results to obtain a secure recognition result of the 5G message.
In the embodiment of the present invention, when executing the result integration on the parallel recognition result to obtain the secure recognition result of the 5G message, the result integration module 106 includes:
generating a safety probability value of the parallel recognition result;
carrying out weighted average processing on the safety probability value to obtain a weighted average value of the safety probability value;
And generating a safety identification result of the 5G message according to the weighted average value and a preset safety level.
In detail, the security probability value refers to a security probability value calculated by using a security recognition algorithm for each parallel recognition result when performing security recognition; the weighted average processing refers to an operation of performing weighted summation on a plurality of safety probability values and dividing the weighted summation by the weighted summation, and is used for obtaining an average value of the safety probability values; the security level refers to a preset level for indicating the security level, and is used for determining the security of the 5G message.
In detail, according to the safety probability value of each parallel recognition result, the safety probability value of each result is calculated, and all the safety probability values are subjected to weighted average processing to obtain a comprehensive safety probability value.
In detail, the security recognition result of the 5G message is determined according to the weighted average value and the preset security level.
In detail, a weighted average algorithm is used to perform weighted summation on a plurality of safety probability values and divide the weighted summation, the common weight can be determined according to the importance of the parallel recognition results, and the safety of the plurality of parallel recognition results is comprehensively considered to obtain a more reliable safety probability value.
In detail, the security of the 5G message is determined according to the weighted average and the preset security level, and logic judgment or probability threshold may be used to determine whether the message is secure or not, and a final security recognition result is given according to the comprehensive security probability value and the preset security level to determine whether the message is secure or not.
In detail, assuming that there are three parallel recognition results, the security probability values obtained respectively are 0.9, 0.85 and 0.8, and weighted average processing is performed on the three security probability values, wherein weights are 0.4, 0.3 and 0.3 respectively.
In detail, the security evaluation is performed on each parallel recognition result to obtain security probability values of 0.9, 0.85 and 0.8, and the weighted average processing is performed on the security probability values to obtain a weighted average value of 0.87.
In detail, according to the weighted average and the preset security level, the preset security level is assumed to be 0.8, so that 0.87 is greater than 0.8, and the 5G message is determined to be safe and reliable.
Through the steps, the safety probability values of a plurality of parallel recognition results are comprehensively considered, and the final safety recognition result is obtained and is used for judging the safety of the 5G message.
Referring to fig. 2, a flow chart of a transmission security identification method for a 5G message according to an embodiment of the invention is shown. In this embodiment, the transmission security identification method for a 5G message includes:
S1, extracting characteristics of historical flow data of a 5G message to obtain historical flow characteristics of the historical flow data, and generating a dynamic sampling parameter set of the 5G message according to the historical flow characteristics;
s2, carrying out flow sampling on the 5G message in transmission according to the dynamic sampling parameter set to obtain real-time flow data of the 5G message;
s3, data aggregation is carried out on the real-time flow data according to the data similarity of the real-time flow data, and a data block of the 5G message is obtained;
s4, constructing a distributed computing architecture of the 5G message, and performing node distribution on the data blocks by utilizing computing nodes of the distributed computing architecture to obtain distribution nodes of the data blocks;
S5, carrying out parallel safety recognition on the data blocks according to the distribution nodes and a preset safety recognition algorithm to obtain a parallel recognition result of the data blocks;
and S6, carrying out result integration on the parallel recognition results to obtain the safety recognition result of the 5G message.
The invention can dynamically adjust the sampling proportion and frequency according to the characteristics of the historical flow data by using an intelligent sampling technology, so that the sampled data can fully represent the integral flow characteristics, thereby more accurately extracting the required information from the real-time flow data, reducing unnecessary resource waste, and reducing redundant information by combining and processing similar data through a high-efficiency data aggregation algorithm, thereby reducing the burden of subsequent processing, improving the integral processing efficiency, reducing the resources required by storage and transmission, ensuring that the data blocks can be quickly and effectively distributed to each computing node by using a distributed computing architecture with reasonable design, improving the integral processing speed and efficiency when processing a large amount of data, adopting advanced parallel processing technology such as multi-thread and multi-core processing, enabling the safety recognition process to be simultaneously carried out on different data blocks, remarkably improving the processing speed, shortening the recognition time, and improving the integral transmission safety recognition efficiency, therefore, the safety recognition method for the 5G message can improve the safety recognition efficiency for the 5G message.
The present invention also provides a storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
extracting the characteristics of the historical flow data of the 5G message to obtain the historical flow characteristics of the historical flow data, and generating a dynamic sampling parameter set of the 5G message according to the historical flow characteristics;
Performing flow sampling on the 5G message in transmission according to the dynamic sampling parameter set to obtain real-time flow data of the 5G message;
Performing data aggregation on the real-time flow data according to the data similarity of the real-time flow data to obtain a data block of the 5G message;
Constructing a distributed computing architecture of the 5G message, and performing node distribution on the data blocks by utilizing computing nodes of the distributed computing architecture to obtain distribution nodes of the data blocks;
Carrying out parallel safety recognition on the data blocks according to the distribution nodes and a preset safety recognition algorithm to obtain a parallel recognition result of the data blocks;
and integrating the parallel recognition results to obtain the safety recognition result of the 5G message.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (3)
1. The system for identifying the transmission safety of the 5G message is characterized by comprising a feature extraction module, a flow sampling module, a data aggregation module, a node distribution module, a parallel identification module and a result integration module, wherein:
the characteristic extraction module is used for carrying out data cleaning on historical flow data of the 5G message to obtain cleaning data of the historical flow data, generating time sequence characteristics and distribution characteristics of the historical flow data according to the cleaning data, collecting the time sequence characteristics and the distribution characteristics as the historical flow characteristics of the historical flow data, generating dynamic sampling proportion of the 5G message according to the historical flow characteristics, generating dynamic sampling frequency of the 5G message according to the historical flow characteristics, and generating a dynamic sampling parameter set of the 5G message according to the dynamic sampling proportion and the dynamic sampling frequency;
The flow sampling module is used for determining the real-time sampling proportion and the real-time sampling frequency of the 5G message in transmission according to the dynamic sampling parameter set, and carrying out self-adaptive sampling on the 5G message in transmission according to the real-time sampling proportion and the real-time sampling frequency to obtain the real-time flow data of the 5G message;
The data aggregation module is configured to generate data similarity of the real-time traffic data by using a preset similarity algorithm, where the preset similarity algorithm is: Wherein, Is the data similarity of the real-time traffic data,/>Is the target flow data in the real-time flow data,/>Is the comparison flow data in the real-time flow data,/>Is the total number of data features of the real-time traffic data,Is a data characteristic identification of the real-time traffic data,/>Is the/>, of the target traffic dataData characteristics,/>Is the/>, of the control traffic dataData characteristics, namely carrying out data aggregation on the real-time flow data according to the data similarity and a preset similarity threshold value to obtain a data block of the 5G message;
The node allocation module is used for constructing a distributed computing architecture of the 5G message, generating processing complexity and data size of the data block, distributing the data block to computing nodes of the distributed computing architecture according to the processing complexity and the data size, performing resource verification on the computing nodes, and determining the computing nodes passing the resource verification as allocation nodes of the data block;
The parallel identification module is configured to determine a data set to be identified according to the allocation node and the data block, divide the data set in parallel according to a preset initial feature, obtain a subset of the data set, generate a feature value of the subset, calculate an information gain of the subset by using the preset security identification algorithm and the feature value, generate a security value of the subset according to the information gain, perform security marking on the subset according to the security value and a preset security threshold, obtain a marking set of the subset, perform reliability inspection on the marking set, and generate a parallel identification result of the data block according to an inspection result of the reliability inspection and the marking set, where the preset security identification algorithm is: Wherein/> Is in the dataset/>Above, using a preset initial feature/>Gain of information obtained by dividing,/>Is the dataset/>Entropy of/>Is a preset initial feature/>Value set of (1)/>Is the dataset/>Preset initial feature/>Take the value ofSubset of/>Is a dataset,/>Is a subset/>Entropy of (2);
The result integration module is used for generating a safety probability value of the parallel recognition result, carrying out weighted average processing on the safety probability value to obtain a weighted average value of the safety probability value, and generating a safety recognition result of the 5G message according to the weighted average value and a preset safety level.
2. A transmission security identification method for a 5G message, the method comprising:
Performing data cleaning on historical flow data of a 5G message to obtain cleaning data of the historical flow data, generating time sequence characteristics and distribution characteristics of the historical flow data according to the cleaning data, collecting the time sequence characteristics and the distribution characteristics as historical flow characteristics of the historical flow data, generating a dynamic sampling proportion of the 5G message according to the historical flow characteristics, generating a dynamic sampling frequency of the 5G message according to the historical flow characteristics, and generating a dynamic sampling parameter set of the 5G message according to the dynamic sampling proportion and the dynamic sampling frequency;
Determining a real-time sampling proportion and a real-time sampling frequency of the 5G message in transmission according to the dynamic sampling parameter set, and carrying out self-adaptive sampling on the 5G message in transmission according to the real-time sampling proportion and the real-time sampling frequency to obtain real-time flow data of the 5G message;
Generating data similarity of the real-time flow data by using a preset similarity algorithm, wherein the preset similarity algorithm is as follows: Wherein/> Is the data similarity of the real-time traffic data,/>Is the target flow data in the real-time flow data,/>Is the comparison flow data in the real-time flow data,/>Is the total number of data features of the real-time traffic data,/>Is a data characteristic identification of the real-time traffic data,/>Is the/>, of the target traffic dataData characteristics,/>Is the/>, of the control traffic dataData characteristics, namely carrying out data aggregation on the real-time flow data according to the data similarity and a preset similarity threshold value to obtain a data block of the 5G message;
Constructing a distributed computing architecture of the 5G message, generating processing complexity and data size of the data block, distributing the data block to computing nodes of the distributed computing architecture according to the processing complexity and the data size, performing resource verification on the computing nodes, and determining the computing nodes passing the resource verification as distribution nodes of the data block;
Determining a data set to be identified according to the distribution node and the data block, carrying out parallel division on the data set according to preset initial characteristics to obtain a subset of the data set, generating a characteristic value of the subset, calculating an information gain of the subset by utilizing the preset safety identification algorithm and the characteristic value, generating a safety value of the subset according to the information gain, carrying out safety marking on the subset according to the safety value and a preset safety threshold to obtain a mark set of the subset, carrying out reliability inspection on the mark set, and generating a parallel identification result of the data block according to an inspection result of the reliability inspection and the mark set, wherein the preset safety identification algorithm is as follows: Wherein/> Is in the data setAbove, using a preset initial feature/>Gain of information obtained by dividing,/>Is the dataset/>Is used as a reference to the entropy of (a),Is a preset initial feature/>Value set of (1)/>Is the dataset/>Preset initial feature/>Take the value of/>Subset of/>Is a dataset,/>Is a subset/>Entropy of (2);
and generating a safety probability value of the parallel recognition result, carrying out weighted average processing on the safety probability value to obtain a weighted average value of the safety probability value, and generating a safety recognition result of the 5G message according to the weighted average value and a preset safety level.
3. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the transmission security identification method for 5G messages according to claim 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410496594.3A CN118101344B (en) | 2024-04-24 | 2024-04-24 | Transmission security identification system, method and medium for 5G message |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410496594.3A CN118101344B (en) | 2024-04-24 | 2024-04-24 | Transmission security identification system, method and medium for 5G message |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118101344A CN118101344A (en) | 2024-05-28 |
| CN118101344B true CN118101344B (en) | 2024-06-25 |
Family
ID=91155392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410496594.3A Active CN118101344B (en) | 2024-04-24 | 2024-04-24 | Transmission security identification system, method and medium for 5G message |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118101344B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115314294A (en) * | 2022-08-09 | 2022-11-08 | 微栈科技(浙江)有限公司 | Identification system and method for flow safety characteristics |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102293773B1 (en) * | 2020-01-16 | 2021-08-26 | 주식회사 윈스 | Apparatus and method for analyzing network traffic using artificial intelligence |
| CN117061198B (en) * | 2023-08-30 | 2024-02-02 | 广东励通信息技术有限公司 | Network security early warning system and method based on big data |
-
2024
- 2024-04-24 CN CN202410496594.3A patent/CN118101344B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115314294A (en) * | 2022-08-09 | 2022-11-08 | 微栈科技(浙江)有限公司 | Identification system and method for flow safety characteristics |
Non-Patent Citations (1)
| Title |
|---|
| 面向流量识别系统的聚类算法的比较与分析;苏欣;杨建华;张大方;谢高岗;;计算技术与自动化;20080915(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118101344A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109981744B (en) | Data distribution method and device, storage medium and electronic equipment | |
| CN107872457B (en) | Method and system for network operation based on network flow prediction | |
| CN111930526B (en) | Load prediction method, load prediction device, computer equipment and storage medium | |
| CN111552570B (en) | Self-adaptive distribution method of data processing resources of Internet of things and cloud computing server | |
| CN108696486B (en) | Abnormal operation behavior detection processing method and device | |
| CN114513470B (en) | Network flow control method, device, equipment and computer readable storage medium | |
| CN112398700B (en) | Service degradation method and device, storage medium and computer equipment | |
| CN110399268A (en) | A kind of method, device and equipment of anomaly data detection | |
| CN112527448A (en) | Openstack-based dynamic load adjustment method and system | |
| CN108390793A (en) | A kind of method and device of analysis system stability | |
| CN110896357A (en) | Flow prediction method, device and computer readable storage medium | |
| CN111639902A (en) | Data auditing method based on kafka, control device, computer equipment and storage medium | |
| CN117078048A (en) | Digital twinning-based intelligent city resource management method and system | |
| CN113568759B (en) | Cloud computing-based big data processing method and system | |
| CN111339052A (en) | Unstructured log data processing method and device | |
| CN118101344B (en) | Transmission security identification system, method and medium for 5G message | |
| CN112925964A (en) | Big data acquisition method based on cloud computing service and big data acquisition service system | |
| CN101022370A (en) | Automatic clustering method for multi-particle size network under G bit flow rate | |
| CN115529315B (en) | Cloud edge cooperative system | |
| CN115883392A (en) | Data perception method and device of computing power network, electronic equipment and storage medium | |
| CN112860763B (en) | Real-time streaming data processing method and device, computer equipment and storage medium | |
| CN115314400A (en) | Network system anomaly detection method and device, electronic equipment and storage medium | |
| CN113837481A (en) | Financial big data management system based on block chain | |
| CN111598390A (en) | Server high availability evaluation method, device, equipment and readable storage medium | |
| CN111783487A (en) | Fault early warning method and device for card reader equipment |
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 |