CN114116921A - Simplification method for mining network asset graph based on equivalent structure - Google Patents
Simplification method for mining network asset graph based on equivalent structure Download PDFInfo
- Publication number
- CN114116921A CN114116921A CN202111436047.9A CN202111436047A CN114116921A CN 114116921 A CN114116921 A CN 114116921A CN 202111436047 A CN202111436047 A CN 202111436047A CN 114116921 A CN114116921 A CN 114116921A
- Authority
- CN
- China
- Prior art keywords
- equivalent structure
- simplification
- equivalent
- independent
- weak
- 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
- G06F16/28—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
- 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
- G06F16/287—Visualization; Browsing
Abstract
The invention discloses a simplification method for excavating a network asset graph based on an equivalent structure, which comprises the following steps: s01, classifying and defining equivalent structures: classifying the equivalent structures and defining various discrimination methods; s02, counting and labeling equivalent structure nodes: counting the original data according to the equivalent structure and the discrimination method defined in the step S01, identifying a specific label for the node corresponding to the equivalent structure, and then classifying; s03, design simplification scheme: according to the classification and statistical result of the step S02, carrying out simplification of the non-independent equivalent structure through a simplification proportion calculation function, and simplifying the independent weak equivalent structure through a fixed simplification scheme; and S04, simplifying the proportion processing data according to the equivalent structure. The method and the device can effectively solve the problem of visual redundancy in the asset map, can keep the consistency of the whole topological structure before and after simplification, and are suitable for popularization and application.
Description
Technical Field
The invention belongs to the technical field of data visualization, and particularly relates to a simplification method for mining a network asset graph based on an equivalent structure.
Background
In the network asset map, rich assets are associated in various modes, and an intricate and complex asset map topological structure is formed. The high-complexity asset map with point and edge dual heterogeneity contains abundant and diverse local structures, and has certain significance in the service level, the topological structure level and the like. In particular, among these local structures, there are some equivalent structures that show a high degree of similarity, topologically, traffic, and visually, and can also be considered redundant. For example, in a graph of network assets, a clustered structure (or star structure) is very common. In the network black (grey) map, the structure is likely to be a group from the service perspective, and the structure is often large in size and consistent inside (as shown in fig. 2) from the topology perspective, so that visual redundancy is easily caused. Because the internal structures of the system are similar, the service logic of the system cannot be influenced by simplifying the topological structure to a certain extent. As another example, bridge-type structures are also very common in network asset maps. In the network black (grey) map, the structure is likely to contact two groups from the service aspect, and the interior of the structure is basically consistent from the topology aspect (as shown in figure 3), so that the visual redundancy is easily caused.
Disclosure of Invention
In order to solve the defects and shortcomings of the prior art, the invention aims to provide a simplification method for mining a network asset graph based on an equivalent structure. The simplification method effectively solves the problem of visual redundancy in the asset map, and meanwhile, the consistency of the whole topological structure before and after simplification can be kept, so that the method helps people to research and visually analyze the network asset map, and is suitable for popularization and application.
The purpose of the invention is realized by the following technical scheme:
a simplification method for mining a network asset graph based on an equivalent structure comprises the following steps:
s01, classifying and defining equivalent structures: classifying the equivalent structures into a primary cluster level structure, a bridge level structure, a cluster bridge structure, a multi-level cluster structure and an independent weak equivalent structure, and defining a judging method of the primary cluster level structure, the bridge level structure, the cluster bridge structure, the multi-level cluster structure and the independent weak equivalent structure;
s02, counting and labeling equivalent structure nodes: counting the original data according to the equivalent structure and the discrimination method defined in the step S01, identifying a specific label for the node corresponding to the equivalent structure, and then classifying;
s03, design simplification scheme: according to the classification and statistical result of the step S02, carrying out simplification of the non-independent equivalent structure through a simplification proportion calculation function, and simplifying the independent weak equivalent structure through a fixed simplification scheme;
and S04, processing the simplified data according to the equivalent structure simplified proportion.
Further, the simplification method for mining the network asset graph based on the equivalent structure further comprises the following steps: s05, iteration optimization simplification scheme: and according to the simplification effect of the map, comparing and evaluating the influence degree of the simplification effect on the whole topological structure and the service logic, and performing an iterative optimization simplification scheme.
Further, in step S01,
the first-level cluster-level structure, the bridge-level structure, the cluster bridge structure and the multi-level cluster structure are non-independent equivalent structures; the first-level cluster level structure is a node group with the degree of 1 and the number of nodes connected with the cluster center nodes being more than 3.
In the present application, the separation of equivalent structures is based on local feature rules for classification. The nodes in the original data already carry a label of whether the node is a cluster center node.
Further, in step S03,
the general formula of the reduction ratio calculation function is as follows:
wherein e isiAll equivalent structures in case i are in proportion; sigma is a recommended simplification coefficient which is set according to an empirical value, has a good simplification effect and can keep the visual effect of the before-and-after-simplification graph (the value is 1.2 under the default condition); siThe equivalent structure simplification scale for case i.
The simplification of the non-independent equivalent structure includes: according to the reduction ratio calculation function, when the equivalent structure ratio of case i is not more than 50% (i.e. e)iLess than or equal to 0.5), adopting a linear function to carry out simplification proportion calculation; when the equivalent structure ratio of case i exceeds 50% (i.e. 0.5 < e)iLess than or equal to 1), a quadratic function is adopted to carry out simplification proportion calculation.
Due to eiWhen the value is less than or equal to 0.5, the relatively serious visual influence can not be brought to the asset map, so that the equivalent structure simplification is carried out to a small extent, and a relatively smooth linear function is used as a simplified proportion calculation function of the segment。
Since 0.5 < eiAt 1 or less, the method brings great visual influence to the asset map, and simultaneously causes the asset map of the case to have very serious visual redundancy, thereby carrying out great equivalent structural simplification. According to the empirical value of the application, when the simplification rate exceeds 60%, the simplified asset map is greatly changed, the change possibly changes the understanding of a user on the asset map, and even changes the original topological structure characteristics of the asset map, so that a quadratic function which is gradually gentle in the increase of the simplification rate along with the increase of the proportion of equivalent structures is adopted.
The simplification of the independent weak equivalent structure through the fixed simplification scheme comprises the following steps: dividing the independent weak equivalent structure into an important independent weak equivalent structure, a common independent weak equivalent structure and a non-important independent weak equivalent structure; firstly, important 'independent weak equivalent structures' are not simplified; then, for a common independent weak equivalent structure, discarding 40% of nodes randomly; then, for the non-significant "independent weak equivalence structure", 60% of the nodes are randomly discarded.
In the application, according to the evaluation of network security experts, an independent weak equivalent structure is divided into an important independent weak equivalent structure, a common independent weak equivalent structure and a non-important independent weak equivalent structure; then, based on the business logic consideration, firstly, for an important independent weak equivalence structure, directly skipping the structure without simplifying the structure; then, for a common independent weak equivalent structure, discarding 40% of nodes randomly; finally, for the non-significant "independent weak equivalence structure", 60% of the nodes are randomly discarded. Therefore, the group number of other independent weak equivalent structures can be effectively reduced while the important independent weak equivalent structures are reserved, interference nodes in the asset map analysis process can be reduced to a certain extent, and the purpose of simplifying the equivalent structures in the network asset map is achieved.
Further, in step S04, the processing simplification data includes:
s04.1, simplifying the 'non-independent equivalent structure': according to the equivalent structure simplification proportion, nodes in each equivalent structure are deleted randomly, so that the data meet the requirement of the equivalent structure simplification proportion; in this way, the reasonability of the data and the relative stability of the topology of each equivalent structure in the map can be maintained.
Further, in step S04, the processing simplified data further includes:
s04.2, simplifying the independent weak equivalent structure: dividing the independent weak equivalent structure into an important independent weak equivalent structure, a common independent weak equivalent structure and a non-important independent weak equivalent structure; then, the equivalent structure simplification ratios of the important independent weak equivalent structure, the common independent weak equivalent structure and the non-important independent weak equivalent structure are respectively set, and the important independent weak equivalent structure, the common independent weak equivalent structure and the non-important independent weak equivalent structure are respectively simplified according to the corresponding equivalent structure simplification ratios.
Compared with the prior art, the invention has the following advantages and effects: by the method, the equivalent structure mining can be applied to simplification of the network asset map, the problem of visual redundancy in the asset map is effectively solved, meanwhile, the consistency of the whole topological structure before and after simplification can be kept, people can be helped to research and visually analyze the network asset map, an accurate and rapid method is provided for mining, counting and analyzing the equivalent structure in the checking chart, the network asset map can be simplified on the premise of keeping business logic, the attractiveness and the simplicity of the view are improved, and the method is suitable for popularization and application.
Drawings
FIG. 1 is a flow chart diagram of a network asset graph reduction method based on equivalent structure mining according to an embodiment of the present invention;
FIG. 2 is an example of a network black (gray) clustering structure;
FIG. 3 is an example of a network black (grey) bridge architecture;
FIG. 4 is a network black grey map with simplified sub-domain names;
FIG. 5 is a graph of network black gray yield after mining using equivalent structures (where non-equivalent structures are gray);
FIG. 6 is a graph of network black gray product after equivalent structure simplification;
FIG. 7 is a highlight map of the equivalent structure after the equivalent structure is simplified.
Detailed Description
The present invention will be described in further detail with reference to examples, but the embodiments of the present invention are not limited thereto.
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.
As used herein, the term "comprising" or "includes" can be open, semi-closed, and closed. In other words, the term also includes "consisting essentially of …," or "consisting of ….
According to the method, firstly, feature analysis is carried out on original data (such as point and edge data), time overhead of subsequent traversal is reduced, then, equivalent structures are mined, counted and analyzed, the equivalent structures in a map are manually identified by observation, logic judgment standards of all equivalent structures are made, code tests are written according to the judgment standards, and repeated iteration is carried out to achieve a better identification rate; after each equivalent structure is correctly identified, a simplification rate formula with the equivalent structure ratio as an independent variable is counted and formulated, a random simplification method is adopted, and parameters in the formula are iteratively tested and modified, so that the visual redundancy in the asset map is effectively reduced, and the consistency of the whole topological structure before and after simplification can be maintained.
By the method, the equivalent structure mining can be applied to simplification of the network asset map, the problem of visual redundancy in the asset map is effectively solved, meanwhile, the consistency of the whole topological structure before and after simplification can be kept, people can be helped to research and visually analyze the network asset map, an accurate and rapid method is provided for mining, counting and analyzing the equivalent structure in the checking chart, the network asset map can be simplified on the premise of keeping business logic, the attractiveness and the simplicity of the view are improved, and the method is suitable for popularization and application.
Specifically, as shown in fig. 1, taking simplification processing of crawled DNS data as an example, an embodiment of the present invention provides a simplification method for mining a network asset graph based on an equivalent structure, including the following steps:
s01, classifying and defining equivalent structures: classifying the equivalent structures into a primary cluster level structure, a bridge level structure, a cluster bridge structure, a multi-level cluster structure and an independent weak equivalent structure, and defining a judging method of the primary cluster level structure, the bridge level structure, the cluster bridge structure, the multi-level cluster structure and the independent weak equivalent structure;
s02, counting and labeling equivalent structure nodes: counting the original data according to the equivalent structure and the discrimination method defined in the step S01, identifying a specific label for the node corresponding to the equivalent structure, and then classifying;
s03, design simplification scheme: according to the classification and statistical result of the step S02, carrying out simplification of the non-independent equivalent structure through a simplification proportion calculation function, and simplifying the independent weak equivalent structure through a fixed simplification scheme;
and S04, processing the simplified data according to the equivalent structure simplified proportion.
Further, the simplification method for mining the network asset graph based on the equivalent structure further comprises the following steps: s05, iteration optimization simplification scheme: and according to the simplification effect of the map, comparing and evaluating the influence degree of the simplification effect on the whole topological structure and the service logic, and performing an iterative optimization simplification scheme.
Further, in step S01,
the first-level cluster-level structure, the bridge-level structure, the cluster bridge structure and the multi-level cluster structure are non-independent equivalent structures; the first-level cluster level structure is a node group with the degree of 1 and the number of nodes connected with the cluster center nodes being more than 3.
In the present application, the separation of equivalent structures is based on local feature rules for classification. The nodes in the original data already carry a label of whether the node is a cluster center node.
Further, in step S03,
the general formula of the reduction ratio calculation function is as follows:
wherein e isiAll equivalent structures in case i are in proportion; sigma is a recommended simplification coefficient which is set according to an empirical value, has a good simplification effect and can keep the visual effect of the before-and-after-simplification graph (the value is 1.2 under the default condition); siThe equivalent structure simplification scale for case i.
The simplification of the non-independent equivalent structure includes: according to the reduction ratio calculation function, when the equivalent structure ratio of case i is not more than 50% (i.e. e)iLess than or equal to 0.5), adopting a linear function to carry out simplification proportion calculation; when the equivalent structure ratio of case i exceeds 50% (i.e. 0.5 < e)iLess than or equal to 1), a quadratic function is adopted to carry out simplification proportion calculation.
Due to eiAnd when the value is less than or equal to 0.5, the relatively serious visual influence can not be brought to the asset map, so that the equivalent structure is simplified to a small extent, and a relatively smooth linear function is used as a simplified proportion calculation function of the segment.
Since 0.5 < eiAt 1 or less, the method brings great visual influence to the asset map, and simultaneously causes the asset map of the case to have very serious visual redundancy, thereby carrying out great equivalent structural simplification. According to the empirical value of the application, when the simplification rate exceeds 60%, the simplified asset map is greatly changed, the change possibly changes the understanding of a user on the asset map, and even changes the original topological structure characteristics of the asset map, so that a quadratic function which is gradually gentle in the increase of the simplification rate along with the increase of the proportion of equivalent structures is adopted.
The simplification of the independent weak equivalent structure through the fixed simplification scheme comprises the following steps: dividing the independent weak equivalent structure into an important independent weak equivalent structure, a common independent weak equivalent structure and a non-important independent weak equivalent structure; firstly, important 'independent weak equivalent structures' are not simplified; then, for a common independent weak equivalent structure, discarding 40% of nodes randomly; then, for the non-significant "independent weak equivalence structure", 60% of the nodes are randomly discarded.
In the application, according to the evaluation of network security experts, an independent weak equivalent structure is divided into an important independent weak equivalent structure, a common independent weak equivalent structure and a non-important independent weak equivalent structure; then, based on the business logic consideration, firstly, for an important independent weak equivalence structure, directly skipping the structure without simplifying the structure; then, for a common independent weak equivalent structure, discarding 40% of nodes randomly; finally, for the non-significant "independent weak equivalence structure", 60% of the nodes are randomly discarded. Therefore, the group number of other independent weak equivalent structures can be effectively reduced while the important independent weak equivalent structures are reserved, interference nodes in the asset map analysis process can be reduced to a certain extent, and the purpose of simplifying the equivalent structures in the network asset map is achieved.
Further, in step S04, the processing simplification data includes:
s04.1, simplifying the 'non-independent equivalent structure': according to the equivalent structure simplification proportion, nodes in each equivalent structure are deleted randomly, so that the data meet the requirement of the equivalent structure simplification proportion; in this way, the reasonability of the data and the relative stability of the topology of each equivalent structure in the map can be maintained.
Further, in step S04, the processing simplified data further includes:
s04.2, simplifying the independent weak equivalent structure: dividing the independent weak equivalent structure into an important independent weak equivalent structure, a common independent weak equivalent structure and a non-important independent weak equivalent structure; then, the equivalent structure simplification ratios of the important independent weak equivalent structure, the common independent weak equivalent structure and the non-important independent weak equivalent structure are respectively set, and the important independent weak equivalent structure, the common independent weak equivalent structure and the non-important independent weak equivalent structure are respectively simplified according to the corresponding equivalent structure simplification ratios.
The method of the invention is adopted to simplify the crawled DNS data, and the result is shown in fig. 4 to 7, wherein fig. 4 is a network black grey map with simplified sub-domain names; FIG. 5 is a graph of network black gray yield after mining using equivalent structures (where non-equivalent structures are gray); FIG. 6 is a graph of network black gray product after equivalent structure simplification; FIG. 7 is a highlight map of the equivalent structure after the equivalent structure has been simplified; as can be seen from fig. 4 to 7, the method of the present invention effectively solves the problem of visual redundancy in the asset map, and simultaneously, the method can maintain the consistency of the overall topology before and after simplification, can help people to research and visually analyze the network asset map, and can also simplify the network asset map on the premise of maintaining business logic, and improve the aesthetic property and the simplicity of the view.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (8)
1. A simplification method for mining a network asset graph based on an equivalent structure is characterized by comprising the following steps:
s01, classifying and defining equivalent structures: classifying the equivalent structures into a primary cluster level structure, a bridge level structure, a cluster bridge structure, a multi-level cluster structure and an independent weak equivalent structure, and defining a judging method of the primary cluster level structure, the bridge level structure, the cluster bridge structure, the multi-level cluster structure and the independent weak equivalent structure;
s02, counting and labeling equivalent structure nodes: counting the original data according to the equivalent structure and the discrimination method defined in the step S01, identifying a specific label for the node corresponding to the equivalent structure, and then classifying;
s03, design simplification scheme: according to the classification and statistical result of the step S02, carrying out simplification of the non-independent equivalent structure through a simplification proportion calculation function, and simplifying the independent weak equivalent structure through a fixed simplification scheme;
and S04, processing the simplified data according to the equivalent structure simplified proportion.
2. The method for simplifying the equivalent structure-based mining network asset graph according to claim 1, wherein the method for simplifying the equivalent structure-based mining network asset graph further comprises the following steps: s05, iteration optimization simplification scheme: and according to the simplification effect of the map, comparing and evaluating the influence degree of the simplification effect on the whole topological structure and the service logic, and performing an iterative optimization simplification scheme.
3. The method for simplifying equivalent structure-based mining network asset graph according to claim 1, wherein in step S01, the primary cluster-level structure, the bridge-level structure, the cluster-bridge structure and the multi-level cluster structure are non-independent equivalent structures; the first-level cluster level structure is a node group with the degree of 1 and the number of nodes connected with the cluster center nodes being more than 3.
4. The method for simplifying equivalent structure-based mining network asset graph according to claim 3, wherein in step S03, the general formula of the reduction proportion calculation function is as follows:
wherein e isiAll equivalent structures in case i are in proportion; sigma is a recommended simplification coefficient which is set according to an empirical value, has a good simplification effect and can keep the visual effect of the before and after simplification; siThe equivalent structure simplification scale for case i.
5. The method for simplifying network asset graph mining based on equivalence structure according to claim 4, wherein the simplification of the non-independent equivalence structure comprises: according to the simplification proportion calculation function, when the equivalent structure proportion of the case i is not more than 50%, adopting a linear function to calculate the simplification proportion; and when the equivalent structure proportion of the case i exceeds 50%, carrying out reduction proportion calculation by adopting a quadratic function.
6. The method for simplifying the asset graph of the equivalent structure-based mining network according to claim 5, wherein the reducing the independent weak equivalent structure through a fixed reduction scheme comprises: dividing the independent weak equivalent structure into an important independent weak equivalent structure, a common independent weak equivalent structure and a non-important independent weak equivalent structure; firstly, important 'independent weak equivalent structures' are not simplified; then, for a common independent weak equivalent structure, discarding 40% of nodes randomly; then, for the non-significant "independent weak equivalence structure", 60% of the nodes are randomly discarded.
7. The method for simplifying network asset graph mining based on equivalent structure as claimed in claim 6, wherein in step S04, the processing the simplification data includes:
s04.1, simplifying the 'non-independent equivalent structure': according to the equivalent structure simplification proportion, nodes in each equivalent structure are deleted randomly, so that the data meet the requirement of the equivalent structure simplification proportion; in this way, the reasonability of the data and the relative stability of the topology of each equivalent structure in the map can be maintained.
8. The method for simplifying network asset graph mining based on equivalent structure as claimed in claim 7, wherein in step S04, the processing the simplification data further comprises:
s04.2, simplifying the independent weak equivalent structure: dividing the independent weak equivalent structure into an important independent weak equivalent structure, a common independent weak equivalent structure and a non-important independent weak equivalent structure; then, the equivalent structure simplification ratios of the important independent weak equivalent structure, the common independent weak equivalent structure and the non-important independent weak equivalent structure are respectively set, and the important independent weak equivalent structure, the common independent weak equivalent structure and the non-important independent weak equivalent structure are respectively simplified according to the corresponding equivalent structure simplification ratios.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111436047.9A CN114116921A (en) | 2021-11-29 | 2021-11-29 | Simplification method for mining network asset graph based on equivalent structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111436047.9A CN114116921A (en) | 2021-11-29 | 2021-11-29 | Simplification method for mining network asset graph based on equivalent structure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114116921A true CN114116921A (en) | 2022-03-01 |
Family
ID=80367687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111436047.9A Pending CN114116921A (en) | 2021-11-29 | 2021-11-29 | Simplification method for mining network asset graph based on equivalent structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114116921A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023246165A1 (en) * | 2022-06-24 | 2023-12-28 | 华为云计算技术有限公司 | Data asset display method and apparatus, and device and storage medium |
-
2021
- 2021-11-29 CN CN202111436047.9A patent/CN114116921A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023246165A1 (en) * | 2022-06-24 | 2023-12-28 | 华为云计算技术有限公司 | Data asset display method and apparatus, and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110519128B (en) | Random forest based operating system identification method | |
| CN102289522B (en) | Method of intelligently classifying texts | |
| CN103077720B (en) | Speaker identification method and system | |
| CN108959474B (en) | Entity relation extraction method | |
| CN110210431A (en) | A kind of point cloud classifications method based on cloud semantic tagger and optimization | |
| CN110705298B (en) | Improved prefix tree and cyclic neural network combined field classification method | |
| CN110990718A (en) | Social network model building module of company image improving system | |
| CN114154570A (en) | Sample screening method and system and neural network model training method | |
| CN114116921A (en) | Simplification method for mining network asset graph based on equivalent structure | |
| CN110830291B (en) | Node classification method of heterogeneous information network based on meta-path | |
| CN111061923A (en) | Graph data entity identification method and system based on graph dependence rule and supervised learning | |
| CN111984790B (en) | Entity relation extraction method | |
| CN106815320B (en) | Investigation big data visual modeling method and system based on expanded three-dimensional histogram | |
| CN112463974A (en) | Method and device for establishing knowledge graph | |
| CN109447833A (en) | A kind of extensive microblog users community of interest discovery method | |
| CN113449403B (en) | Complex network node evaluation method based on hierarchical network division | |
| CN115374859A (en) | Method for classifying unbalanced and multi-class complex industrial data | |
| CN104468276A (en) | Network traffic identification method based on random sampling multiple classifiers | |
| Hanna | Spectral comparison of large urban graphs | |
| CN113742488A (en) | Embedded knowledge graph completion method and device based on multitask learning | |
| CN112632284A (en) | Information extraction method and system for unlabeled text data set | |
| Luo et al. | Network attack classification and recognition using hmm and improved evidence theory | |
| CN114387118B (en) | Character social network theme identification method and system based on pellet calculation | |
| US20230012041A1 (en) | Identity Graphing for Network Genomes | |
| CN116452841A (en) | Hierarchical-based improved DBSCAN clustering algorithm suitable for mass point clouds |
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 |