CN104156389A - Deep packet detecting system and method based on Hadoop platform - Google Patents
Deep packet detecting system and method based on Hadoop platform Download PDFInfo
- Publication number
- CN104156389A CN104156389A CN201410317160.9A CN201410317160A CN104156389A CN 104156389 A CN104156389 A CN 104156389A CN 201410317160 A CN201410317160 A CN 201410317160A CN 104156389 A CN104156389 A CN 104156389A
- Authority
- CN
- China
- Prior art keywords
- module
- dpi
- tuple
- key
- stream
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Abstract
The invention discloses a deep packet detecting system and method based on a Hadoop platform, and relates to the data mining technology. The deep packet detecting system comprises a web crawler part and a deep packet detecting part, a web crawler unit grabs pages from the internet, a file analysis unit analyzes the pages and obtains the mapping relation between a URL and webpage classification content, and a mapping relation library in a database is iterated and updated continuously. The deep packet detecting part analyzes original data into quintuple flow which is input into a TC module, service flow marks are made, specific service flow is generated, the specific service flow is converted into a DPI event, the DPI event is matched with the mapping relation library, and DPI event statistics is completed. The deep packet detecting technology is integrated with the Hadoop platform, and the needs for big data storage and flow depth analysis are met.
Description
Technical field
The present invention relates to the analysis of mass network data, relate in particular to a kind of deep-packet detection system.
Background technology
Deep packet inspection technical is that DPI technology is a kind of flow detection and control technology based on application layer, deep packet inspection technical is widely used in the analysis of packet application type, user behavior analysis, and the aspect such as intrusion detection, virus/worm detection, be the important means of data mining.
The arrival of large data age has brought new impact to legacy network flow analysis method, particularly at network flow monitoring, safety management, content auditing, and have higher requirement for flow analysis and challenge in the aspect such as the classification charging of telecom operators, the marketing and intelligent pipeline construction.
Legacy network flow analysis method mainly comprises the analysis based on host-host protocol port, feature, traffic characteristic statistics, and above-mentioned analytical approach can not meet traffic classification and the multi-functional demand of depth analysis.Flow identification advantage based on deep packet inspection technical is to resolve more profound procotol, there is higher matching accuracy rate, but because DPI need to resolve each packet, the explosion type that is accompanied by network traffics rises, and processing speed has become the bottleneck of analyzing based on DPI flux deepness.Need to adopt that new method solves that large data depth analysis faces accurately, the challenge of speed and cost.
Summary of the invention
Based on above problem, the present invention make full use of the increasing income of Hadoop Distributed Computing Platform, efficiently, the advantage such as stable, fault-tolerance is high, deep packet inspection technical is integrated into Hadoop platform, meet the demand that large data storage and flux deepness are analyzed.
The technical scheme that the present invention solves the problems of the technologies described above is: propose a kind of based on Hadoop (distributed system architecture) platform deep-packet detection system, described system comprises web crawlers and deep-packet detection part, web crawlers is partly by capturing and analyzing web page, constantly iteration is upgraded mapping relations storehouse, for deep-packet detection, partly mate, this part comprises webcrawler module and web page analysis module, webcrawler module captures specific website web page files, for web page analysis module provides input; Web page analysis module analysis web page files, obtains the mapping relations of URL (URL(uniform resource locator)) and webpage classification contents, for DPI module, mates.According to capturing the more mapping relations storehouse in new database of the continuous iteration of the page; Deep-packet detection partly comprises packet parsing PA module, traffic classification TC module, deep-packet detection DPI module, PA module resolves to five-tuple stream by raw data, input TC module, TC module is done traffic marking by the five-tuple stream of input, generate given traffic streams input DPI module, DPI module changes into DPI event by given traffic streams, and DPI event is mated with mapping relations storehouse, completes DPI event statistics.
PA module resolves to five-tuple stream by raw data, input TC module specifically comprises, PA module reads original data stream in HDFS, using packet side-play amount as the input of Key, the packet content key-value pair form that is Value as MapReduce, result output be take five-tuple as the form that Key, five-tuple stream and stream characteristic statistics are Value, stores in HDFS.TC module is done traffic marking by the five-tuple stream of input, generating given traffic streams input DPI module specifically comprises, TC module reads five-tuple stream in HDFS, using five-tuple as the input of Key, the five-tuple stream key-value pair form that is Value as MapReduce, result output be take five-tuple/service marker as the form that Key, service marker stream are Value, stores in HDFS.DPI module changes into DPI event by given traffic streams and specifically comprises, DPI module reads given traffic streams in HDFS, five-tuple/the service marker of usining is inputted as MapReduce as the key-value pair form that Key, given traffic streams are characterized as Value, and the form that five-tuple/service marker is Value as Key, DPI event is take in result output.
The present invention also proposes a kind of based on Hadoop platform deep packet inspection method, comprise step: webcrawler module constantly circulates and captures specific website web page files, document analysis module is analyzed web page files, obtain the mapping relations of URL and webpage classification contents, store database into, according to capturing the more mapping relations storehouse in new database of the continuous iteration of the page; PA module resolves to five-tuple stream input TC module by raw data, TC module is done traffic marking by the five-tuple stream of input, generates given traffic streams input DPI module, and DPI module changes into DPI event by given traffic streams, DPI event is mated with mapping relations storehouse, complete DPI event statistics.
The present invention make full use of the increasing income of Hadoop Distributed Computing Platform, efficiently, the advantage such as stable, fault-tolerance is high, the deep packet inspection technical of reptile Network Based is integrated into Hadoop platform, reach the object that efficient flux deepness is analyzed.The present invention can resolve more profound procotol, has higher matching accuracy rate, and processing speed is fast, has solved accurate, speed issue in large data depth analysis.
Accompanying drawing explanation
Accompanying drawing 1 the present invention is based on Hadoop platform deep-packet detection system framework schematic diagram;
Accompanying drawing 2 the present invention is based on Hadoop platform deep-packet detection system web crawlers part process flow diagram;
Accompanying drawing 3 the present invention is based on Hadoop platform deep-packet detection system deep-packet detection part process flow diagram.
Embodiment
Deep-packet detection is partly based upon on Hadoop platform, finishing service flow label and given traffic streams (mainly referring to Web Business Stream) change into the function of DPI event, DPI event to the profound recognition result of network event (is for example, user A has browsed a certain video website sometime), be the output of DPI module.This part comprises packet parsing PA module, traffic classification TC module, deep-packet detection DPI module.PA module mainly completes packet analytical capabilities, raw data is resolved to five-tuple stream (five-tuple comprises: source IP address, source port, object IP address, destination interface, transport layer protocol number), output to TC module, TC module is done traffic marking by the five-tuple stream of input, for DPI module provides input; DPI module completes given traffic streams and changes into DPI event, and DPI event is mated with mapping relations storehouse, according to DPI event, adds up with the DPI event of having mated of information in mapping relations storehouse.
Below in conjunction with accompanying drawing, the present invention will be further described with concrete enforcement, specific as follows:
Be illustrated in figure 1 and the present invention is based on Hadoop platform deep-packet detection system framework schematic diagram, described system comprises web crawlers and two parts of deep-packet detection.
Web crawlers partly comprises webcrawler module, document analysis module, database, web crawlers unit captures the page from internet, document analysis unit obtains the mapping relations of uniform resource position mark URL and webpage classification contents to webpage analysis, according to capturing the more mapping relations storehouse in new database of the continuous iteration of the page, for deep-packet detection part DPI module, mate.
Deep-packet detection is partly based upon on Hadoop platform, and finishing service flow label and given traffic streams change into DPI event.This part comprises packet parsing PA, traffic classification TC, tri-modules of deep-packet detection DPI.PA module completes packet and resolves, and raw data is resolved to five-tuple stream, for TC module provides input; TC module completes flow label function, and the five-tuple stream of input is done to traffic marking, generates given traffic streams, input DPI module; DPI module changes into deep-packet detection DPI event by given traffic streams, and DPI event is mated with mapping relations storehouse, completes DPI event statistics.The major function of IO Format is the Data Segmentation of modules input and output and reads.HDFS is as the distributed memory system of Hadoop, and its major function is the storage to raw data and modules data processed result.
Be illustrated in figure 2 and the present invention is based on Hadoop platform deep-packet detection system web crawlers part process flow diagram.Web crawlers is partly divided into webpage and captures and two stages of web page analysis, by following steps, completes:
Webcrawler module constantly circulates and captures specific website web page files; Document analysis module is analyzed web page files, obtains the mapping relations of URL and webpage classification contents, stores database into, for DPI module;
Be illustrated in figure 3 deep-packet detection part process flow diagram.Deep-packet detection comprises parsing, traffic classification mark and deep-packet detection three phases, specifically comprises the steps:
Step 1, webcrawler module circulation captures specific website web page files;
Step 2, web page analysis module is analyzed the web page files capturing, and obtains the mapping relations of URL and webpage classification contents, stores mapping relations storehouse into, for deep-packet detection DPI module, carries out deep-packet detection;
Deep-packet detection module comprises packet parsing, traffic classification mark and deep-packet detection three phases, and concrete steps comprise:
Step 3, data acquisition unit captures network raw data stream, stores distributed memory system HDFS (Hadoop Distributed File System, Hadoop) into;
Step 4, packet parsing module PA reads original data stream in HDFS, using packet side-play amount as the input of Key (being good for), the packet content key-value pair form that is Value (value) as programming paradigm unit MapReduce, result output be take five-tuple as the form that Key, five-tuple stream and stream characteristic statistics are Value, stores in HDFS; Step 5, traffic classification mark module TC reads five-tuple stream in HDFS, using five-tuple as the input of Key, the five-tuple stream key-value pair form that is Value as MapReduce, and the form that five-tuple/service marker is Value as Key, service marker stream is take in result output, and result store is in HDFS;
Step 6, deep-packet detection module DPI reads specific transactions mark stream in HDFS, the key-value pair form that the five-tuple/service marker of usining is Value as Key, given traffic streams feature field is inputted as MapReduce, and the form that five-tuple/service marker is Value as Key, DPI event is take in result output;
Step 7, mates DPI event and obtains DPI statistics with mapping relations storehouse, store DPI statistics into database, for inquiry; Based on DPI event (comprising user, time, action), complete the depth data of network traffics is excavated.
Data acquisition unit captures network data, stores the distributed memory system HDFS of Hadoop platform as original data stream into; PA module reads original data stream in HDFS, using packet side-play amount as the input of Key, the packet content key-value pair form that is Value as MapReduce, result output be take five-tuple as Key, five-tuple stream and is flowed the form that characteristic statistics is Value, result store in HDFS, PA module end-of-job; TC module reads five-tuple stream in HDFS, using five-tuple as the input of Key, the five-tuple stream key-value pair form that is Value as MapReduce, the form that five-tuple/service marker is Value as Key, service marker stream is take in result output, and result store is in HDFS; DPI module reads given traffic streams in HDFS, the key-value pair form that the five-tuple/traffic marking of usining is Value as Key, given traffic streams is inputted as MapReduce, the form that five-tuple/service marker is Value as Key, DPI event is take in result output, mate in the mapping relations storehouse of partly setting up with web crawlers by the feature field of DPI event, based on DPI event (comprising user, time, action), complete the depth data of network traffics is excavated.
Claims (8)
1. the deep-packet detection system based on Hadoop platform, it is characterized in that, described system comprises web crawlers part and deep-packet detection part, web crawlers partly comprises webcrawler module, document analysis module, database, web crawlers unit captures the page from internet, document analysis unit obtains the mapping relations of uniform resource position mark URL and webpage classification contents to webpage analysis, according to capturing the more mapping relations storehouse in new database of the continuous iteration of the page; Deep-packet detection partly comprises packet parsing PA module, traffic classification TC module, deep-packet detection DPI module, PA module resolves to five-tuple stream by raw data, input TC module, TC module is done traffic marking by the five-tuple stream of input, generate given traffic streams input DPI module, DPI module changes into DPI event by given traffic streams, and DPI event is mated with mapping relations storehouse, completes DPI event statistics.
2. system according to claim 1, it is characterized in that, PA module resolves to five-tuple stream by raw data, input TC module specifically comprises, PA module reads original data stream in HDFS, using packet side-play amount as the input of Key, the packet content key-value pair form that is Value as MapReduce, and result output be take five-tuple as the form that Key, five-tuple stream and stream characteristic statistics are Value, stores in HDFS.
3. system according to claim 1, it is characterized in that, TC module is done traffic marking by the five-tuple stream of input, generating given traffic streams input DPI module specifically comprises, TC module reads five-tuple stream in HDFS, using five-tuple as the input of Key, the five-tuple stream key-value pair form that is Value as MapReduce, and result output be take five-tuple/service marker as the form that Key, service marker stream are Value, stores in HDFS.
4. system according to claim 1, it is characterized in that, DPI module changes into DPI event by given traffic streams and specifically comprises, DPI module reads given traffic streams in HDFS, five-tuple/the service marker of usining is inputted as MapReduce as the key-value pair form that Key, given traffic streams are characterized as Value, and the form that five-tuple/service marker is Value as Key, DPI event is take in result output.
5. one kind based on Hadoop platform deep packet inspection method, it is characterized in that, comprise step: webcrawler module constantly circulates and captures specific website web page files, document analysis module is analyzed web page files, obtain the mapping relations of URL and webpage classification contents, store database into, according to capturing the more mapping relations storehouse in new database of the continuous iteration of the page; PA module resolves to five-tuple stream input TC module by raw data, TC module is done traffic marking by the five-tuple stream of input, generates given traffic streams input DPI module, and DPI module changes into DPI event by given traffic streams, DPI event is mated with mapping relations storehouse, complete DPI event statistics.
6. method according to claim 5, it is characterized in that, PA module resolves to five-tuple stream by raw data, input TC module specifically comprises, PA module reads original data stream in HDFS, using packet side-play amount as the input of Key, the packet content key-value pair form that is Value as MapReduce, and result output be take five-tuple as the form that Key, five-tuple stream and stream characteristic statistics are Value, stores in HDFS.
7. method according to claim 5, it is characterized in that, TC module is done traffic marking by the five-tuple stream of input, generating given traffic streams input DPI module specifically comprises, TC module reads five-tuple stream in HDFS, using five-tuple as the input of Key, the five-tuple stream key-value pair form that is Value as MapReduce, and result output be take five-tuple/service marker as the form that Key, service marker stream are Value, stores in HDFS.
8. method according to claim 5, it is characterized in that, DPI module changes into DPI event by given traffic streams and specifically comprises, DPI module reads given traffic streams in HDFS, five-tuple/the service marker of usining is inputted as MapReduce as the key-value pair form that Key, given traffic streams are characterized as Value, and the form that five-tuple/service marker is Value as Key, DPI event is take in result output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410317160.9A CN104156389B (en) | 2014-07-04 | 2014-07-04 | Deep-packet detection system and method based on Hadoop platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410317160.9A CN104156389B (en) | 2014-07-04 | 2014-07-04 | Deep-packet detection system and method based on Hadoop platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104156389A true CN104156389A (en) | 2014-11-19 |
| CN104156389B CN104156389B (en) | 2017-12-26 |
Family
ID=51881893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410317160.9A Active CN104156389B (en) | 2014-07-04 | 2014-07-04 | Deep-packet detection system and method based on Hadoop platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104156389B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104486157A (en) * | 2014-12-16 | 2015-04-01 | 国家电网公司 | Information system performance detecting method based on deep packet analysis |
| CN104486116A (en) * | 2014-12-12 | 2015-04-01 | 北京百度网讯科技有限公司 | Multidimensional query method and multidimensional query system of flow data |
| CN104636434A (en) * | 2014-12-31 | 2015-05-20 | 百度在线网络技术（北京）有限公司 | Search result processing method and device |
| CN105117649A (en) * | 2015-07-30 | 2015-12-02 | 中国科学院计算技术研究所 | Anti-virus method and anti-virus system for virtual machine |
| CN105812324A (en) * | 2014-12-30 | 2016-07-27 | 华为技术有限公司 | Method, device and system for IDC information safety management |
| CN106303751A (en) * | 2015-05-18 | 2017-01-04 | 中兴通讯股份有限公司 | A kind of realization method and system orienting flow bag |
| CN107948266A (en) * | 2017-11-17 | 2018-04-20 | 武汉绿色网络信息服务有限责任公司 | The processing method and system of HTTP uplink traffics in asymmetric routed environment |
| CN108171887A (en) * | 2017-12-20 | 2018-06-15 | 新华三技术有限公司 | A kind of method and device of electric energy tariff |
| CN109829094A (en) * | 2019-01-23 | 2019-05-31 | 钟祥博谦信息科技有限公司 | Distributed reptile system |
| CN110990669A (en) * | 2019-10-16 | 2020-04-10 | 广州丰石科技有限公司 | DPI (deep packet inspection) analysis method and system based on rule generation |
| CN111641531A (en) * | 2020-05-12 | 2020-09-08 | 国家计算机网络与信息安全管理中心 | DPDK-based data packet distribution and feature extraction method |
| CN112272123A (en) * | 2020-10-16 | 2021-01-26 | 北京锐安科技有限公司 | Network traffic analysis method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101414939A (en) * | 2008-11-28 | 2009-04-22 | 武汉虹旭信息技术有限责任公司 | Internet application recognition method based on dynamical depth package detection |
| CN101741744A (en) * | 2009-12-17 | 2010-06-16 | 东南大学 | Network flow identification method |
| US20120182891A1 (en) * | 2011-01-19 | 2012-07-19 | Youngseok Lee | Packet analysis system and method using hadoop based parallel computation |
-
2014
- 2014-07-04 CN CN201410317160.9A patent/CN104156389B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101414939A (en) * | 2008-11-28 | 2009-04-22 | 武汉虹旭信息技术有限责任公司 | Internet application recognition method based on dynamical depth package detection |
| CN101741744A (en) * | 2009-12-17 | 2010-06-16 | 东南大学 | Network flow identification method |
| US20120182891A1 (en) * | 2011-01-19 | 2012-07-19 | Youngseok Lee | Packet analysis system and method using hadoop based parallel computation |
Non-Patent Citations (2)
| Title |
|---|
| 胡国良: "基于并行Bloom过滤器组的深度包检测研究", 《中国优秀硕士学位论文全文数据库》 * |
| 魏军: "基于Hadoop的深度包检测技术的研究", 《中国优秀硕士学位论文全文数据包》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104486116A (en) * | 2014-12-12 | 2015-04-01 | 北京百度网讯科技有限公司 | Multidimensional query method and multidimensional query system of flow data |
| CN104486157A (en) * | 2014-12-16 | 2015-04-01 | 国家电网公司 | Information system performance detecting method based on deep packet analysis |
| CN105812324B (en) * | 2014-12-30 | 2019-04-05 | 华为技术有限公司 | The method, apparatus and system of IDC information security management |
| CN105812324A (en) * | 2014-12-30 | 2016-07-27 | 华为技术有限公司 | Method, device and system for IDC information safety management |
| CN104636434A (en) * | 2014-12-31 | 2015-05-20 | 百度在线网络技术（北京）有限公司 | Search result processing method and device |
| CN106303751B (en) * | 2015-05-18 | 2020-06-30 | 中兴通讯股份有限公司 | Method and system for realizing directional flow packet |
| CN106303751A (en) * | 2015-05-18 | 2017-01-04 | 中兴通讯股份有限公司 | A kind of realization method and system orienting flow bag |
| CN105117649B (en) * | 2015-07-30 | 2018-11-30 | 中国科学院计算技术研究所 | A kind of anti-virus method and system for virtual machine |
| CN105117649A (en) * | 2015-07-30 | 2015-12-02 | 中国科学院计算技术研究所 | Anti-virus method and anti-virus system for virtual machine |
| CN107948266A (en) * | 2017-11-17 | 2018-04-20 | 武汉绿色网络信息服务有限责任公司 | The processing method and system of HTTP uplink traffics in asymmetric routed environment |
| CN108171887A (en) * | 2017-12-20 | 2018-06-15 | 新华三技术有限公司 | A kind of method and device of electric energy tariff |
| CN109829094A (en) * | 2019-01-23 | 2019-05-31 | 钟祥博谦信息科技有限公司 | Distributed reptile system |
| CN110990669A (en) * | 2019-10-16 | 2020-04-10 | 广州丰石科技有限公司 | DPI (deep packet inspection) analysis method and system based on rule generation |
| CN111641531A (en) * | 2020-05-12 | 2020-09-08 | 国家计算机网络与信息安全管理中心 | DPDK-based data packet distribution and feature extraction method |
| CN111641531B (en) * | 2020-05-12 | 2021-08-17 | 国家计算机网络与信息安全管理中心 | DPDK-based data packet distribution and feature extraction method |
| CN112272123A (en) * | 2020-10-16 | 2021-01-26 | 北京锐安科技有限公司 | Network traffic analysis method and device, electronic equipment and storage medium |
| CN112272123B (en) * | 2020-10-16 | 2022-04-15 | 北京锐安科技有限公司 | Network traffic analysis method, system, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104156389B (en) | 2017-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104156389A (en) | Deep packet detecting system and method based on Hadoop platform | |
| EP2955686A9 (en) | Automatic article enrichment by social media trends | |
| US11055373B2 (en) | Method and apparatus for generating information | |
| CN104504081A (en) | Intelligent analysis system for all-media detection and monitoring big data behaviors | |
| CN107563725A (en) | A kind of recruitment system for optimizing cumbersome personnel recruitment process | |
| CN101916285A (en) | Method and device for analyzing internet web page contents | |
| CN102420813A (en) | Method and device for providing target information according to terminal attributes of user equipment | |
| CN104731906A (en) | Automatic recruiting website resume pushing method | |
| CN102402589A (en) | Method and equipment for providing reference research information related to research request | |
| CN104618132A (en) | Generation method and generation device for application program recognition rule | |
| CN105808722A (en) | Information discrimination method and system | |
| CN103491089A (en) | Transcoding method and system of data recovery based on HTTP | |
| Patil et al. | Bisecting K-means for clustering web log data | |
| US20240095170A1 (en) | Multi-cache based digital output generation | |
| CN103036910A (en) | Method and device for controlling user web access behaviors | |
| CN103235821A (en) | Original content searching method and searching server | |
| CN104598536A (en) | Structured processing method of distributed network information | |
| US11334592B2 (en) | Self-orchestrated system for extraction, analysis, and presentation of entity data | |
| CN112749360A (en) | Webpage classification method and device | |
| CN101420356A (en) | Network content classified processing method and apparatus | |
| CN108287831B (en) | URL classification method and system and data processing method and system | |
| CN104079450A (en) | Method and device for generating characteristic pattern set | |
| Jiang et al. | Seq2Path: a sequence-to-path-based flow feature fusion approach for encrypted traffic classification | |
| CN106503253A (en) | The framework that a kind of web crawlers for picture format extracts URL and indexes and map | |
| US20150127624A1 (en) | Framework for removing non-authored content documents from an authored-content database |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |