CN112487033A - Service visualization method and system for data flow and network topology construction - Google Patents
Service visualization method and system for data flow and network topology construction Download PDFInfo
- Publication number
- CN112487033A CN112487033A CN202011375135.8A CN202011375135A CN112487033A CN 112487033 A CN112487033 A CN 112487033A CN 202011375135 A CN202011375135 A CN 202011375135A CN 112487033 A CN112487033 A CN 112487033A
- Authority
- CN
- China
- Prior art keywords
- service
- data
- data flow
- network topology
- decision tree
- 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.)
- Pending
Links
Images
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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24568—Data stream processing; Continuous queries
-
- 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
- G06F16/26—Visual data mining; Browsing structured data
-
- 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
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Abstract
The invention belongs to the field of service visualization, and provides a service visualization method and system for data flow and network topology construction. The service visualization method for the data flow and the network topology construction comprises the steps of preprocessing the service data flow and extracting features; judging a service mode of service data stream characteristics by using a decision tree, and generating a plurality of classification nodes with the same level to form a service topological graph; and visually displaying the service topological graph. The visualization method can rapidly extract the characteristics of the data stream, classify and predict the service mode of the data stream examples according to the characteristics, automatically and orderly establish the service domain, and finally visually display the service topological graph, thereby further improving the automation level of the technology.
Description
Technical Field
The invention belongs to the field of service visualization, and particularly relates to a service visualization method and system for data flow and network topology construction.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
In the big data era, a lot of big data information exists in the form of data stream, which contains a lot of useful information, but it is difficult to store it based on the characteristics of massive and high-speed flow, so that it is required to process the data stream in real time and obtain useful information from it. The data flow model is widely applied to various fields of social production and life, is a main trend of future data development, and has become a current research hotspot.
In the era of computer internet, the related technologies of computers and internet are continuously updated, the development is changing day by day, the use of networks and computers is spreading to the aspects of family life and work, because the number of the users of the networks and computers is getting larger and higher, the use frequency is getting higher and higher, various malicious applications such as various network viruses, trojans, network eavesdropping and various hacker attacks and crawler accesses are full of the network and the malicious applications occupy limited network resources, so that the use of normal applications is seriously hindered, and the security of application services normally used by people is greatly threatened. The traditional identification technology based on the fixed port computer network has a good effect, and mainly utilizes the data flow of the port to analyze, and obtains related information from the data flow so as to monitor and supervise. In recent years, as the most flow identification technology is integrated with advanced technologies in other fields such as machine learning, pattern recognition and data mining, the feasibility and efficiency of service identification based on data flow are improved.
The inventor finds that how the result obtained by the data flow analysis is displayed intuitively is also a very important problem, the result of the data flow analysis is expressed in the form of network topology information, the network topology information plays a significant role in network management, network security research, network performance analysis, network model research and the like, and how to acquire, analyze and utilize the network topology information is also a hotspot concerned by a plurality of researches.
Disclosure of Invention
In order to solve at least one technical problem in the background art, the invention provides a service visualization method and system for data flow and network topology construction, and the service identification of network flow based on a decision tree has good analysis and detection effects, so that a means for monitoring network services can be provided for a network service provider, the safety and reliability of the network services can be improved, and positive significance is provided for the development of internet services.
In order to achieve the purpose, the invention adopts the following technical scheme:
the first aspect of the present invention provides a service visualization method for data flow and network topology construction, which includes:
preprocessing a service data stream and extracting characteristics;
judging a service mode of service data stream characteristics by using a decision tree, and generating a plurality of classification nodes with the same level to form a service topological graph;
and visually displaying the service topological graph.
A second aspect of the present invention provides a service visualization system for data flow and network topology construction, which includes:
the service data flow preprocessing module is used for preprocessing the service data flow and extracting characteristics;
the decision tree analysis and prediction module is used for judging the service mode of the service data stream characteristics by using the decision tree and generating a plurality of classification nodes with the same level to form a service topological graph;
and the business topological graph visualization module is used for visually displaying the business topological graph.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method for traffic visualization oriented towards data flows and building a network topology as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method for visualizing services oriented to data flows and building a network topology as described above when executing the program.
Compared with the prior art, the invention has the beneficial effects that:
(1) the invention preprocesses the service data stream and extracts the characteristics so as to be convenient for later analysis and prediction; generating a decision tree by using a decision tree algorithm, judging a service mode of the processed data flow example by using the decision tree, and automatically and orderly establishing a service domain; and the service topological graph is visually displayed, so that the automation level of the technology is further improved.
(2) The decision tree and business network topology visualization method provided by the invention can rapidly extract the characteristics of the data stream, classify and predict the business mode of the data stream examples according to the characteristics, automatically and orderly establish business domains, and finally visually display the business topological graph, thereby further improving the automation level of the technology: the data preprocessing can eliminate the noise and incompleteness of the data, and improve the data quality and the classification accuracy; the decision tree is very suitable for massive and high-speed flowing data streams based on the rapid classification of main characteristics; the visualization of the service topology enables the classification process and the result to be displayed more clearly and clearly, and is helpful for users to know and understand clearly.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow chart of a data flow oriented service visualization method for constructing a network topology according to an embodiment of the present invention;
FIG. 2 is a flow chart of a business data stream preprocessing according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a decision tree according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a service visualization method for data flow oriented and network topology construction according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
The network topology visualization is an important auxiliary means for analyzing and utilizing network topology information, and the main aim of the network topology visualization is to completely and clearly display the node and connection condition of a target network in front of people, so that intuitive materials and an operation platform are provided for people to know and analyze the overall condition of the target network. This not only helps people to observe and analyze it, but more importantly, it will help people to discover the underlying laws that exist in the network topology.
In order to solve the problem of intuitively displaying a result obtained by analyzing a data flow in the background art, the embodiment provides a service visualization method for data flow and network topology construction, and with reference to fig. 1, the method includes:
s101: the traffic data stream is preprocessed and features are extracted.
The preprocessing of the data can improve the quality of the later decision tree analysis and prediction. The system firstly extracts required data from massive original data according to different tasks, and corresponding preprocessing is required to be carried out on incomplete data. The result of preprocessing the data directly affects the result of the later analysis, and the later statistical analysis result can obtain better effect only through data preprocessing. Therefore, data preprocessing is the key to ensure the statistical analysis results and the data mining quality. The data preprocessing process mainly includes data cleaning, attribute selection, and data summarization, as shown in fig. 2.
The specific implementation of data preprocessing is given below:
firstly, data cleaning is performed, and at this stage, a series of processing is performed on a data stream, because real data is often noisy, incomplete or even inconsistent, data cleaning is required: this stage mainly deals with two problems: default values and noise data. Default values can be determined by inference based tools, predicting the most likely value to fill in missing values; and noise data may be excluded by clustering.
And secondly, selecting attributes, namely obtaining a structural data stream example after a series of processing in the previous data acquisition stage, wherein the attributes of the data stream example can be easily extracted and used as a characteristic candidate set for judgment in decision tree classification in the subsequent stage.
And finally, the data collecting part collects the main attributes obtained in the previous stage and performs overall general description on the overall data set, wherein the general description comprises the size, the characteristic information, the characteristic quantity, the service mode label and other information of the data set for subsequent decision tree training and prediction.
After data preprocessing, a data stream is changed into a structural data example from a series of irregular and inconsistent data, main characteristic information and data set general description are obtained, and the information is used for decision tree training and prediction of the next stage.
S102: and judging the service mode of the service data stream characteristics by using the decision tree, and generating a plurality of classification nodes with the same hierarchy to form a service topological graph.
And after the business data flow data is subjected to a data preprocessing step, the main attributes and the characteristics are extracted, and the module analyzes and predicts according to the attributes and the characteristics. The decision tree is a tree-like decision graph of additional probability results, and the module uses classification and regression trees (CART), which is one of the widely applied decision tree learning methods. CART consists of feature selection, tree generation and pruning, and can be used for both classification and regression. The following is an example of the CART decision tree classification: the CART decision tree classification mainly comprises the following steps:
(1) and (3) generating a decision tree: in the data preprocessing part, the characteristics of the data set are selected, and the aim of the stage is to recursively construct a binary decision tree based on the training data set and the characteristics thereof, wherein the generated decision tree is as large as possible.
The step of decision tree generation is to establish nodes from top to bottom from the root, and each node needs to select a best characteristic attribute to split, so that the training sets of the left and right child nodes are as pure as possible. And the characteristic attribute which is best to judge and can separate the data set as much as possible is used for the Gini index, the Gini coefficient represents the purity of the model, and the smaller the Gini coefficient is, the lower the purity is, and the better the characteristic is.
Assuming K classes, the probability of the kth class is PkThe expression for the kini coefficient of the probability distribution is:
for sample D, the number is | D |, assuming K classes, the number of kth classes is | CkIf the coefficient of kini of sample D is expressed as:
for sample D, the number is | D |, and D is divided into | D | according to a certain value a of the characteristic A1I and I D2If the characteristic a is satisfied, the expression of the kini coefficient of the sample D is:
in the process of generating the decision tree, starting from a root node, calculating the kini coefficients of all the remaining features to a sample set in each step, taking the feature with the minimum kini coefficient as the root node of the current subtree, dividing the data set into two parts by using the feature, and then recursively calling the above steps in the left and right subtrees until the kini index or the number of samples of the sample set is less than a certain specified threshold value, and finishing the generation of the decision tree.
(2) Pruning the decision tree: pruning the generated decision tree by using a verification set and selecting an optimal sub-tree, wherein the minimum loss function is used as a pruning standard.
Decision trees are easily over-fitted to the training set, resulting in poor generalization capability, so the CART decision tree is pruned, i.e. regularization similar to linear regression. The CART adopts a post-pruning method, namely, a decision tree is generated firstly, then all the pruned CART trees are generated, then cross validation is used for testing the pruning effect, and a pruning strategy with the best generalization capability is selected.
The pruning loss function is as follows:
Ca(Tt)＝C(Tt)+a|Tt|
where a is the regularization parameter (as in the regularization of linear regression), C (T)t) For training dataPrediction error, | TtAnd | is the number of leaf nodes of the subtree T and the complexity of the subtree. The penalty function is understood as the prediction error and the complexity of the sub-tree, which is only small if both the prediction error and the complexity of the sub-tree are small.
Each internal node has a value a, when the loss function value of the node pruning is the same as that of the node without pruning, the value a is as follows:
the value a can be understood as the influence of pruning on the prediction error, the larger the value a is, the larger the prediction error after pruning is, that is, the smaller the value a is, the smaller the influence after pruning is, so that a node with a small value a should be found as much as possible for pruning, and the value a can be taken from 0 to infinity.
The decision tree pruning process is that the value a of each internal node is calculated from bottom to top every time, then the point with the minimum value a is selected for pruning to obtain a pruned tree, and the operation is repeatedly carried out on the tree until only the root node is left. In the process, a series of subtree sequences can be obtained, then a test set is used for carrying out cross validation on each subtree, and finally the optimal tree is obtained.
After the decision tree generation and pruning, a decision tree as shown in fig. 3 is obtained, where P1-3 is a service feature that can be used to determine a service mode in a data stream, and the input data is determined at these branch points according to the feature and finally flows into different leaf nodes, i.e., different service modes.
After the data stream is subjected to the preprocessing step, a data stream example containing a plurality of characteristics is obtained. And in the prediction stage, the processed data stream is input into a decision tree to sequentially judge the characteristics from top to bottom, and if the characteristics meet the conditions, the data stream flows into the left branch, otherwise, the data stream flows into the right branch. Finally, after the decision of the plurality of feature branches, the data stream instance arrives at a leaf node, and each leaf node represents a class of traffic patterns, i.e., the data stream instance is classified into the class of traffic patterns.
S103: and visually displaying the service topological graph.
The visualization of the network topology is used as an important auxiliary means for analyzing and utilizing the network topology information, and the service topology is not only beneficial to observation and analysis of people, but also beneficial to finding potential rules existing in the network topology. In the previous process, the service data flow in the server is subjected to preliminary pretreatment, and the decision tree algorithm automatically identifies and classifies the service modes, so that the service domains are automatically and orderly established. The module can visually display the service topological graph, and the automation level of the technology is further improved.
The service topological graph to be constructed in the embodiment is a top-down, hierarchical and flow picture. The visualization steps of the service topological graph are described from top to bottom in sequence as follows:
(a) the source of the whole data stream is a server, so a server node needs to be generated at the top, which also represents the source node of the data stream flow, and is taken as the first layer of the topology map.
(b) The data stream from the server is subjected to a series of pre-processing including data cleansing, attribute selection and data summarization. The second layer of the topology is a node that preprocesses the data stream.
(c) The preprocessed data stream will flow into the next stage, which classifies the traffic pattern of the data stream by training the spanning decision tree. In this part, a particularly complex decision tree may be generated according to the feature information of the data stream, but in the visualization link, we do not care about the structure of the decision tree itself, and we only care about the classification result of the data stream. Therefore, the present embodiment classifies the whole decision tree into one node, and puts the classification results of different decision trees into the next layer.
(d) Through decision tree classification, the data streams are classified into different business modes. At this last level, a plurality of classification nodes with the same level are generated, which respectively represent different results corresponding to the decision tree classification.
The decision tree and service network topology visualization method provided by this embodiment can quickly extract the features of the data stream, classify and predict the service mode of the data stream instance according to the features, automatically and orderly establish the service domain, and finally visually display the service topology map, thereby further improving the automation level of the technology: the data preprocessing can eliminate the noise and incompleteness of the data, and improve the data quality and the classification accuracy; the decision tree is very suitable for massive and high-speed flowing data streams based on the rapid classification of main characteristics; the visualization of the service topology enables the classification process and the result to be displayed more clearly and clearly, and is helpful for users to know and understand clearly.
It should be noted here that the practical scope of the present embodiment includes a server side supporting data stream transmission and companies and enterprises including business models, and uses them for data stream business identification classification at any time. The data flow-oriented service visualization method for constructing the network topology has a very wide application prospect.
Example two
The embodiment provides a service visualization system for data flow and network topology construction, which includes:
the service data flow preprocessing module is used for preprocessing the service data flow and extracting characteristics;
the decision tree analysis and prediction module is used for judging the service mode of the service data stream characteristics by using the decision tree and generating a plurality of classification nodes with the same level to form a service topological graph;
and the business topological graph visualization module is used for visually displaying the business topological graph.
Each module in the service visualization system for data flow and network topology construction of the embodiment corresponds to each step in the service visualization method for data flow and network topology construction of the first embodiment one by one, and will not be described again here.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the traffic visualization method for data flow oriented and network topology construction as described in the first embodiment.
Example four
The present embodiment provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps in the service visualization method for data flow and network topology construction according to the first embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A service visualization method for data flow and network topology construction is characterized by comprising the following steps:
preprocessing a service data stream and extracting characteristics;
judging a service mode of service data stream characteristics by using a decision tree, and generating a plurality of classification nodes with the same level to form a service topological graph;
and visually displaying the service topological graph.
2. The business visualization method for data flow oriented and network topology built according to claim 1, wherein the operations for preprocessing the business data flow include data cleansing, attribute selection and data summarization.
3. The business visualization method for data flow oriented and network topology construction as recited in claim 1, wherein the decision tree model selects classification and regression trees.
4. The traffic visualization method oriented to data flow and constructing network topology according to claim 1, wherein the step of generating the decision tree is to establish nodes from top to bottom from the root, and each node should select a best feature attribute to split, so that the training sets of the left and right child nodes are as pure as possible.
5. The business visualization method oriented to data flow and constructing network topology as recited in claim 4, wherein the kini coefficient represents the impurity degree of the decision tree model, and the smaller the kini coefficient, the lower the impurity degree, the better the feature.
6. The business visualization method for data flow oriented and network topology construction as claimed in claim 5, wherein in the process of generating the decision tree, starting from the root node, each step is to calculate the kini coefficients of all the remaining features to the sample set, and the feature with the minimum kini coefficient is used as the root node of the current sub-tree, and the data set is divided into two by using the feature, and then recursion is performed on the left and right sub-trees until the kini index or the number of samples of the sample set is less than a certain specified threshold, and the generation of the decision tree is completed.
7. The traffic visualization method oriented to data flow and constructing network topology according to claim 1, characterized in that the generated decision tree is pruned by verification set and the optimal sub-tree is selected, and the least loss function is used as the pruning criterion.
8. A service visualization system for data flow and network topology construction is characterized by comprising:
the service data flow preprocessing module is used for preprocessing the service data flow and extracting characteristics;
the decision tree analysis and prediction module is used for judging the service mode of the service data stream characteristics by using the decision tree and generating a plurality of classification nodes with the same level to form a service topological graph;
and the business topological graph visualization module is used for visually displaying the business topological graph.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the method for visualizing services oriented towards data flows and building a network topology as set forth in any one of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for visualizing services oriented to data flows and structured network topologies according to any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011375135.8A CN112487033A (en) | 2020-11-30 | 2020-11-30 | Service visualization method and system for data flow and network topology construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011375135.8A CN112487033A (en) | 2020-11-30 | 2020-11-30 | Service visualization method and system for data flow and network topology construction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112487033A true CN112487033A (en) | 2021-03-12 |
Family
ID=74937489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011375135.8A Pending CN112487033A (en) | 2020-11-30 | 2020-11-30 | Service visualization method and system for data flow and network topology construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112487033A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052505A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Cross-border travel recommendation method, device and equipment based on artificial intelligence |
| CN113342861A (en) * | 2021-07-06 | 2021-09-03 | 云南中烟工业有限责任公司 | Data management method and device in business scene |
| CN114567569A (en) * | 2022-02-25 | 2022-05-31 | 西安微电子技术研究所 | PCIe simulation data visualization method, system, device and medium |
| CN114827272A (en) * | 2022-03-22 | 2022-07-29 | 深圳智芯微电子科技有限公司 | Power business management method and device, transformer substation equipment and storage medium |
| CN115102871A (en) * | 2022-05-20 | 2022-09-23 | 浙江大学 | Energy internet control terminal service processing method based on service feature vector |
| WO2023035190A1 (en) * | 2021-09-09 | 2023-03-16 | Siemens Aktiengesellschaft | Network topology visualization method and apparatus, and computer-readable medium |
| CN116562769A (en) * | 2023-06-15 | 2023-08-08 | 深圳爱巧网络有限公司 | Cargo data analysis method and system based on cargo attribute classification |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107516104A (en) * | 2017-07-11 | 2017-12-26 | 合肥工业大学 | A kind of optimization CART decision tree generation methods and its device based on dichotomy |
| CN108446384A (en) * | 2018-03-21 | 2018-08-24 | 中国信息通信研究院 | A kind of network topology visualization system and data visualization method based on WebGL |
| CN109410074A (en) * | 2018-10-18 | 2019-03-01 | 广州市勤思网络科技有限公司 | Intelligent core protects method and system |
| CN109858886A (en) * | 2019-02-18 | 2019-06-07 | 国网吉林省电力有限公司电力科学研究院 | It is a kind of that control success rate promotion analysis method is taken based on integrated study |
| CN110363347A (en) * | 2019-07-12 | 2019-10-22 | 江苏天长环保科技有限公司 | The method of neural network prediction air quality based on decision tree index |
| CN110691073A (en) * | 2019-09-19 | 2020-01-14 | 中国电子科技网络信息安全有限公司 | Industrial control network brute force cracking flow detection method based on random forest |
| CN110909786A (en) * | 2019-11-19 | 2020-03-24 | 江苏方天电力技术有限公司 | New user load identification method based on characteristic index and decision tree model |
| CN111291097A (en) * | 2020-05-08 | 2020-06-16 | 西南石油大学 | Drilling leaking layer position real-time prediction method based on decision tree data mining |
| CN111783840A (en) * | 2020-06-09 | 2020-10-16 | 苏宁金融科技(南京)有限公司 | Visualization method and device for random forest model and storage medium |
| CN111783904A (en) * | 2020-09-04 | 2020-10-16 | 平安国际智慧城市科技股份有限公司 | Data anomaly analysis method, device, equipment and medium based on environmental data |
| CN111782900A (en) * | 2020-08-06 | 2020-10-16 | 平安银行股份有限公司 | Abnormal service detection method and device, electronic equipment and storage medium |
| CN111861256A (en) * | 2020-07-30 | 2020-10-30 | 国网经济技术研究院有限公司 | Active power distribution network reconstruction decision method and system |
-
2020
- 2020-11-30 CN CN202011375135.8A patent/CN112487033A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107516104A (en) * | 2017-07-11 | 2017-12-26 | 合肥工业大学 | A kind of optimization CART decision tree generation methods and its device based on dichotomy |
| CN108446384A (en) * | 2018-03-21 | 2018-08-24 | 中国信息通信研究院 | A kind of network topology visualization system and data visualization method based on WebGL |
| CN109410074A (en) * | 2018-10-18 | 2019-03-01 | 广州市勤思网络科技有限公司 | Intelligent core protects method and system |
| CN109858886A (en) * | 2019-02-18 | 2019-06-07 | 国网吉林省电力有限公司电力科学研究院 | It is a kind of that control success rate promotion analysis method is taken based on integrated study |
| CN110363347A (en) * | 2019-07-12 | 2019-10-22 | 江苏天长环保科技有限公司 | The method of neural network prediction air quality based on decision tree index |
| CN110691073A (en) * | 2019-09-19 | 2020-01-14 | 中国电子科技网络信息安全有限公司 | Industrial control network brute force cracking flow detection method based on random forest |
| CN110909786A (en) * | 2019-11-19 | 2020-03-24 | 江苏方天电力技术有限公司 | New user load identification method based on characteristic index and decision tree model |
| CN111291097A (en) * | 2020-05-08 | 2020-06-16 | 西南石油大学 | Drilling leaking layer position real-time prediction method based on decision tree data mining |
| CN111783840A (en) * | 2020-06-09 | 2020-10-16 | 苏宁金融科技(南京)有限公司 | Visualization method and device for random forest model and storage medium |
| CN111861256A (en) * | 2020-07-30 | 2020-10-30 | 国网经济技术研究院有限公司 | Active power distribution network reconstruction decision method and system |
| CN111782900A (en) * | 2020-08-06 | 2020-10-16 | 平安银行股份有限公司 | Abnormal service detection method and device, electronic equipment and storage medium |
| CN111783904A (en) * | 2020-09-04 | 2020-10-16 | 平安国际智慧城市科技股份有限公司 | Data anomaly analysis method, device, equipment and medium based on environmental data |
Non-Patent Citations (1)
| Title |
|---|
| 张赫: "汽车螺栓打紧质量大数据分析", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052505A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Cross-border travel recommendation method, device and equipment based on artificial intelligence |
| CN113342861A (en) * | 2021-07-06 | 2021-09-03 | 云南中烟工业有限责任公司 | Data management method and device in business scene |
| CN113342861B (en) * | 2021-07-06 | 2022-11-11 | 云南中烟工业有限责任公司 | Data management method and device in service scene |
| WO2023035190A1 (en) * | 2021-09-09 | 2023-03-16 | Siemens Aktiengesellschaft | Network topology visualization method and apparatus, and computer-readable medium |
| CN114567569A (en) * | 2022-02-25 | 2022-05-31 | 西安微电子技术研究所 | PCIe simulation data visualization method, system, device and medium |
| CN114567569B (en) * | 2022-02-25 | 2023-10-20 | 西安微电子技术研究所 | PCIe simulation data visualization method, system, equipment and medium |
| CN114827272A (en) * | 2022-03-22 | 2022-07-29 | 深圳智芯微电子科技有限公司 | Power business management method and device, transformer substation equipment and storage medium |
| CN115102871A (en) * | 2022-05-20 | 2022-09-23 | 浙江大学 | Energy internet control terminal service processing method based on service feature vector |
| CN115102871B (en) * | 2022-05-20 | 2023-10-03 | 浙江大学 | Service feature vector-based energy internet control terminal service processing method |
| CN116562769A (en) * | 2023-06-15 | 2023-08-08 | 深圳爱巧网络有限公司 | Cargo data analysis method and system based on cargo attribute classification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112487033A (en) | Service visualization method and system for data flow and network topology construction | |
| Greene et al. | Tracking the evolution of communities in dynamic social networks | |
| Park et al. | Graph transplant: Node saliency-guided graph mixup with local structure preservation | |
| CN103870751A (en) | Method and system for intrusion detection | |
| CN110704846B (en) | Intelligent human-in-loop security vulnerability discovery method | |
| CN113259176B (en) | Alarm event analysis method and device | |
| CN105630797B (en) | Data processing method and system | |
| Nuiaa et al. | Evolving Dynamic Fuzzy Clustering (EDFC) to Enhance DRDoS_DNS Attacks Detection Mechnism. | |
| CN103793589B (en) | High-speed train fault handling method | |
| CN109656898A (en) | Distributed large-scale complex community detection method and device based on node degree | |
| CN106845990B (en) | Rule processing method and equipment | |
| Xie et al. | Logm: Log analysis for multiple components of hadoop platform | |
| CN110287237B (en) | Social network structure analysis based community data mining method | |
| Danilchenko et al. | Opinion spam detection: A new approach using machine learning and network-based algorithms | |
| CN112039907A (en) | Automatic testing method and system based on Internet of things terminal evaluation platform | |
| Yasir et al. | TRICE: Mining frequent itemsets by iterative TRimmed transaction LattICE in sparse big data | |
| binti Oseman et al. | Data mining in churn analysis model for telecommunication industry | |
| Chadokar et al. | Optimizing network traffic by generating association rules using hybrid apriori-genetic algorithm | |
| CN112905845B (en) | Multi-source unstructured data cleaning method for discrete intelligent manufacturing application | |
| CN112181952B (en) | Method, system, device and storage medium for constructing data model | |
| Mohammed et al. | Degree-based random walk approach for graph embedding | |
| Liu et al. | A Web Back-End Database Leakage Incident Reconstruction Framework Over Unlabeled Logs | |
| Thanasekaran | A Robust and Efficient Real Time Network Intrusion Detection System Using Artificial Neural Network In Data Mining | |
| CN115617698B (en) | Software defect measurement element selection method based on association rule network | |
| Hao | Design of ID3 Decision Tree Algorithm In Network Data Public Management System |
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 |