CN107241237B - A kind of method and calculating equipment of the identification affiliated component of message - Google Patents
A kind of method and calculating equipment of the identification affiliated component of message Download PDFInfo
- Publication number
- CN107241237B CN107241237B CN201710363681.1A CN201710363681A CN107241237B CN 107241237 B CN107241237 B CN 107241237B CN 201710363681 A CN201710363681 A CN 201710363681A CN 107241237 B CN107241237 B CN 107241237B
- Authority
- CN
- China
- Prior art keywords
- message
- critical field
- screenshot
- identified
- similar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/06—Generation of reports
- H04L43/062—Generation of reports related to network traffic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of methods for identifying the affiliated component of message, and suitable for executing in calculating equipment, the method comprising the steps of: at least one critical field is extracted from message to be identified;For an extracted critical field, using the search engine inquiry critical field, to obtain multiple including the message of the critical field and the IP address for returning to the message;The screenshot for the Web content that each IP address inquired is directed toward is obtained respectively;Judge whether the critical field is effective according to the screenshot of acquired multiple Web contents;For each message obtained based on effective critical field, message difference similar to message to be identified is calculated;It chooses the wherein the smallest predetermined number message of similar difference and the module information of message to be identified is obtained using the deep learning model pre-established according to the predetermined number message;And according to module information determine message to be identified belonging to component.The invention also discloses a kind of calculating equipment and computer readable storage mediums.
Description
Technical field
The present invention relates to technical field of network security more particularly to a kind of method for identifying the affiliated component of message and calculating to set
It is standby.
Background technique
As the rapid development of network communication technology, carried information become increasingly abundant, internet has become human society
Important infrastructure, more and more enterprises or it is personal by the various assemblies of network server and server to user
Web content and service are provided.
The various assemblies of network server also give network security management while bringing various facilitate to people's lives
Problem of some sternnesses, such as component possibility loophole safe to carry, virus, wooden horse etc. are brought, privacy of user leakage, network are caused
Security risk.Therefore component is identified very crucial.
Normally, its affiliated component can be determined by identification message, but at present this process mainly by being accomplished manually,
Need to be extracted effective critical field from message by identification personnel, then by search engine determination component type, affiliated company
And model, since message is many kinds of, complexity is higher, and whole process expends great manpower and time.
Therefore, there is an urgent need to a kind of schemes of more advanced identification affiliated component of message.
Summary of the invention
For this purpose, the present invention provides a kind of scheme for identifying the affiliated component of message, to try hard to solve or at least alleviate above
At least one existing problem.
According to an aspect of the invention, there is provided a kind of method for identifying the affiliated component of message, is suitable for calculating equipment
Middle execution, the method comprising the steps of: at least one critical field is extracted from message to be identified;For an extracted key
Field, using the search engine inquiry critical field, to obtain multiple including the message of the critical field and returning to the report
The IP address of text;The screenshot for the Web content that each IP address inquired is directed toward is obtained respectively;According to acquired multiple nets
The screenshot of network content judges whether the critical field is effective;For in each network for being obtained based on effective critical field
Hold screenshot, calculates the similarity of message and message to be identified that IP address inquiring, being directed toward the Web content returns;It chooses
The wherein screenshot of Web content corresponding to the highest message of similarity, according to the screenshot, using the deep learning pre-established
Model obtains the module information of message to be identified;And according to the module information determine message to be identified belonging to component.
According to another aspect of the present invention, a kind of calculating equipment is provided, comprising: one or more processors;Memory;
And one or more programs, wherein one or more programs store in memory and are configured as being handled by one or more
Device execute, one or more programs include for execute it is according to the present invention identification the affiliated component of message method in either
The instruction of method.
According to the present invention there are one aspects, provide a kind of readable storage medium storing program for executing for storing program, program includes referring to
Enable, the instruction when executed by a computing apparatus so that calculate equipment execute it is according to the present invention identification the affiliated component of message side
Method either in method.
The scheme of the identification affiliated component of message according to the present invention, includes from message to be identified by obtaining its message
Multiple messages of the critical field of extraction, and obtain using deep learning model the module information of message to be identified, last root
Component is determined according to module information, is realized the automatic identification of the affiliated component of message, is dramatically saved manpower and time cost.
Wherein, key is judged also according to the screenshot of the Web content for the multiple IP address direction for returning to acquired message
Whether field is effective, so as to avoid the redundancy process identified using invalid key section, improves recognition efficiency.
Detailed description of the invention
To the accomplishment of the foregoing and related purposes, certain illustrative sides are described herein in conjunction with following description and drawings
Face, these aspects indicate the various modes that can practice principles disclosed herein, and all aspects and its equivalent aspect
It is intended to fall in the range of theme claimed.Read following detailed description in conjunction with the accompanying drawings, the disclosure it is above-mentioned
And other purposes, feature and advantage will be apparent.Throughout the disclosure, identical appended drawing reference generally refers to identical
Component or element.
Fig. 1 shows the structural block diagram of the calculating equipment 100 of an illustrative embodiments according to the present invention;
Fig. 2 shows the methods 200 of the identification affiliated component of message of an illustrative embodiments according to the present invention
Flow chart;And
Fig. 3 shows the page of the query result of cyberspace search engine according to one exemplary embodiment
Face screenshot.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Fig. 1 shows the structural block diagram of calculating equipment 100 according to an illustrative embodiment of the invention.The calculating equipment
100 can be implemented as server, such as file server, database server, apps server and network server etc.,
Also can be implemented as include desktop computer and notebook computer configuration personal computer.May be used also in addition, calculating equipment 100
To be embodied as a part of portable (or mobile) electronic equipment of small size, these electronic equipments can be such as cellular phone,
Personal digital assistant (PDA), personal media player device, wireless network browsing apparatus, personal helmet, application specific are set
Mixing apparatus that is standby or may include any of the above function.
In basic configuration 102, calculate equipment 100 typically comprise system storage 106 and one or more at
Manage device 104.Memory bus 108 can be used for the communication between processor 104 and system storage 106.
Depending on desired configuration, processor 104 can be any kind of processing, including but not limited to: microprocessor
((μ P), microcontroller (μ C), digital information processor (DSP) or any combination of them.Processor 104 may include all
Cache, processor core such as one or more rank of on-chip cache 110 and second level cache 112 etc
114 and register 116.Exemplary processor core 114 may include arithmetic and logical unit (ALU), floating-point unit (FPU),
Digital signal processing core (DSP core) or any combination of them.Exemplary Memory Controller 118 can be with processor
104 are used together, or in some implementations, and Memory Controller 218 can be an interior section of processor 104.
Depending on desired configuration, system storage 106 can be any type of memory, including but not limited to: easily
The property lost memory (RAM), nonvolatile memory (ROM, flash memory etc.) or any combination of them.System storage
Device 106 may include operating system 120, one or more program 122 and program data 124.In some embodiments,
Program 122 can be configured as to be referred to by one or more processor 104 using the execution of program data 124 on an operating system
It enables.
Calculating equipment 100 can also include facilitating from various interface equipments (for example, output equipment 142, Peripheral Interface
144 and communication equipment 146) to basic configuration 102 via the communication of bus/interface controller 130 interface bus 140.Example
Output equipment 142 include graphics processing unit 148 and audio treatment unit 150.They can be configured as facilitate via
One or more port A/V 152 is communicated with the various external equipments of such as display or loudspeaker etc.Outside example
If interface 144 may include serial interface controller 154 and parallel interface controller 156, they, which can be configured as, facilitates
Via one or more port I/O 158 and such as input equipment (for example, keyboard, mouse, pen, voice-input device, touch
Input equipment) or the external equipment of other peripheral hardwares (such as printer, scanner etc.) etc communicated.Exemplary communication is set
Standby 146 may include network controller 160, can be arranged to convenient for via one or more communication port 164 and one
A or multiple other calculate communication of the equipment 162 by network communication link.
Network communication link can be an example of communication media.Communication media can be usually presented as in such as carrier wave
Or computer readable instructions, data structure, program module in the modulated data signal of other transmission mechanisms etc, and can
To include any information delivery media." modulated data signal " can such signal, one in its data set or more
It is a or it change can the mode of encoded information in the signal carry out.As unrestricted example, communication media can be with
Wired medium including such as cable network or private line network etc, and it is such as sound, radio frequency (RF), microwave, infrared
(IR) the various wireless mediums or including other wireless mediums.Term computer-readable medium used herein may include depositing
Both storage media and communication media.
Wherein, the one or more programs 122 for calculating equipment 100 include for executing identification message according to the present invention institute
Belong to the instruction of any one of method of component.The method of the identification affiliated component of message according to the present invention, by obtaining its report
Text includes the multiple messages for the critical field extracted from message to be identified, and is obtained using deep learning model to be identified
The module information of message, finally determines component according to module information, realizes the automatic identification of the affiliated component of message, greatly
Save manpower and time cost.
Fig. 2 shows the streams of the method 200 of the identification affiliated component of message according to one exemplary embodiment
Cheng Tu.The method 200 of the identification affiliated component of message is suitable for executing in calculating equipment 100, and starts from step S210.
In step S210, at least one critical field is extracted from message to be identified.It specifically, can be according to preset
Set of keywords obtains at least one critical field by string matching in message to be identified.For example, report to be identified
Text can be such that
Preset set of keywords can be server:| WWW-Authenticate:Basic realm=| location
=|<title>, then the critical field finally obtained is WWW-Authenticate:Basic according to the set of keywords
Realm=" CAMERA_AUTHENTICATE1 ".
Normally, the critical field extracted is multiple, then sequentially for extracted one of critical field, In
In step S220, using the search engine inquiry critical field, to obtain multiple including the message of the critical field and returning
Return the IP address of the message.
Here search engine can be the cyberspace search engine of such as ZoomEye and Shadon etc, Duo Geke
To be such as 5 etc fixed numbers.Fig. 3 shows the search of cyberspace according to one exemplary embodiment
The page screenshot of the query result of engine, in an embodiment as illustrated in figure 3, in cyberspace search engine ZoomEye with
Server Apache be search term inquired, the query result of return includes multiple include Server Apache report
Text and the IP address for returning to the message.Renewal time newer fixed number of message can wherein randomly selected and returned
The IP address of the message is returned, to carry out subsequent processing.
In step S230, the screenshot for the Web content that each IP address inquired is directed toward is obtained respectively.Specifically, it passes through
The IP address each inquired, and the Web content screenshot being displayed on browser are accessed by browser.
After obtaining screenshot, in step S240, which is judged according to the screenshot of acquired multiple Web contents
Whether field is effective.Specifically, for the screenshot of acquired multiple Web contents, judge section of wherein every two Web content
Whether figure is similar, for example, the screenshot of acquired multiple Web contents is screenshot 1~3, then judges wherein screenshot 1 respectively and cuts
Whether Fig. 2, screenshot 1 and screenshot 3, screenshot 2 and screenshot 3 are similar.
According to one embodiment of present invention, SIFT algorithm can be used to judge whether two screenshots are similar.Specifically,
The SIFT feature that SIFT algorithm extracts two screenshots respectively can be used, matched by the SIFT feature to two screenshots,
To judge whether two screenshots are similar.Wherein it is possible to whether be more than scheduled similar proportion come really to quantity by characteristic matching
Whether fixed two screenshots are similar.
After carrying out similar judgement to the screenshot of every two Web content, available multiple judging results.If obtained
Dissimilar number is not above predetermined ratio in multiple judging results, it is determined that the critical field is effective, if multiple judgements are tied
Dissimilar number is more than that predetermined ratio determines that the critical field is invalid in fruit.For example, acquired multiple Web contents are cut
Figure is screenshot 1~3, and the judging result of screenshot 1 and screenshot 2, screenshot 1 and screenshot 3, screenshot 2 and screenshot 3 is respectively dissimilar, no
It is similar, similar, wherein dissimilar number accounting is 2/3, it has been more than predetermined ratio 1/2, it is thus determined that corresponding critical field
In vain.In this way, avoiding the redundancy process identified using invalid key section, recognition efficiency is improved.
It is to be appreciated that whether similar its corresponding message that can reflect of Web content screenshot is similar, therefore works as and look into
Ask multiple message majorities that some critical field obtains it is all similar when, then it is considered that all messages comprising the critical field
There are certain rule, then message to be identified also natural component similar to these messages, therefore being extracted by these messages
Information may be considered the module information of message to be identified.
And when inquiring multiple messages most all dissmilarities each other that some critical field obtains, it is believed that include
The message of the critical field can not extract with typicalness, general module information there is no rule by these messages,
Thus it is considered that the critical field is invalid.
After determining that a critical field is invalid, it is also necessary to continue to repeat extracted other invalid fields above-mentioned
It inquires, obtain, judging the whether effective step of the critical field, until determining that some critical field is effectively or all crucial
Until field is invalid.If whole critical fielies are invalid, it may be considered that the message to be identified is unrecognized message, no
It is identified again.
If it is determined that a critical field is effective, then in step s 250, for being obtained based on the effective critical field
Each of include the critical field message, calculate message difference similar to message to be identified.
Specifically, the temporal information that two messages are included can be deleted, Levenshtein algorithm is recycled to calculate two
Similar difference between message.
It is assumed that message to be identified is as follows:
HTTP/1.1 505 HTTP Version Not Supported\nServer:HP HTTP Server;HP HP
Officejet Pro X551dw Printer-CV037A;Serial Number:CN584KJ0C2;Built:Fri Jan
09,2015 02:58:26PM{BZP1CN1502AR}
It is deleted as follows after temporal information:
HTTP/1.1 505 HTTP Version Not Supported\nServer:HP HTTP Server;HP HP
Officejet Pro X551dw Printer-CV037A;Serial Number:CN584KJ0C2;Built:
{BZP1CN1502AR}
Again it is assumed that the message inquired is as follows:
HTTP/1.1 505 HTTP Version Not Supported\nServer:HP HTTP Server;HP HP
Officejet Pro X476dw MFP-CN461A;Serial Number:CN45KIK01V;Built:Tue Nov 24,
2015 03:37:44PM{LWP1CN1548AR}
It is deleted as follows after temporal information:
HTTP/1.1 505 HTTP Version Not Supported\nServer:HP HTTP Server;HP HP
Officejet Pro X476dw MFP-CN461A;Serial Number:CN45KIK01V;Built:{LWP1CN1548AR}
Finally, the similar difference between two messages being calculated using Levenshtein algorithm is 26, i.e., it is to be identified
Message transforms to the number of words modified required for the message inquired.
In step S260, choose wherein the smallest predetermined number message of similar difference (i.e. with message to be identified most phase
As message), and the module information of message to be identified is obtained according to these messages using the deep learning model that pre-establishes.
In this way, can be further improved the accuracy of the component finally identified.
Specifically, selected predetermined number message can be input in the deep learning neural network, to obtain it
The module information of output.Wherein, deep learning model is that deep learning neural network according to one embodiment of present invention can
With by TensorFlow framework establishment deep learning neural network, the case where according to input information, by deep learning nerve net
The number of plies of network is set as 5~9 layers, and each layer is convolutional layer, and each layer of design parameter needs to adjust in the training process.In
After each layer of convolutional layer calculates, using ELU function as activation primitive, connect being accessed after the activation of the last layer convolutional layer entirely
Layer is connect, and is input to Softmax function and is handled, to construct the first deep learning neural network and the second deep learning
Neural network.In subsequent training process, using the prediction result of Softmax function and true label value as input, utilize
Cross-entropy algorithm calculates corresponding loss value, and loss value is input to Momentum optimization method and calculates gradient, and more
The model parameter of new deep learning neural network.Furthermore it is possible to using the different message of the predetermined number for belonging to same components and
Common module information is trained the deep learning neural network as sample.
For example, a message to be identified is as follows:
The effective critical field extracted is as follows:
<title>BitNami:Open Source.Simplified</title>
It is as follows in the smallest 3 messages of the similar difference that cyberspace search engine inquiry arrives:
After this 3 message input deep learning models, the module information of available output are as follows: Bitnami.Obtain group
After part information, finally in step S270, component belonging to message to be identified can be determined according to the module information.For example,
Obtained module information is Tomcat, according to the common sense sex experience in the field, it can be determined that component Apache.It can also utilize
The search engine of such as Google, Baidu etc search for Tomcat, so that the search result according to return determines component.
It should be appreciated that various technologies described herein are realized together in combination with hardware or software or their combination.From
And some aspects or part of the process and apparatus of the present invention or the process and apparatus of the present invention can take the tangible matchmaker of insertion
It is situated between, such as the program code in floppy disk, CD-ROM, hard disk drive or other any machine readable storage mediums (refers to
Enable) form, wherein when program is loaded into the machine of such as computer etc, and when being executed by the machine, which becomes real
Trample equipment of the invention.
In the case where program code executes on programmable computers, calculates equipment and generally comprise processor, processor
Readable storage medium (including volatile and non-volatile memory and or memory element), at least one input unit, and extremely
A few output device.Wherein, memory is configured for storage program code;Processor is configured for according to the memory
Instruction in the program code of middle storage executes various methods of the invention.
By way of example and not limitation, computer-readable medium includes computer storage media and communication media.It calculates
Machine readable medium includes computer storage media and communication media.Computer storage medium storage such as computer-readable instruction,
The information such as data structure, program module or other data.Communication media is generally modulated with carrier wave or other transmission mechanisms etc.
Data-signal processed passes to embody computer readable instructions, data structure, program module or other data including any information
Pass medium.Above any combination is also included within the scope of computer-readable medium.
It should be appreciated that in order to simplify the disclosure and help to understand one or more of the various inventive aspects, it is right above
In the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure or
In person's descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. claimed hair
Bright requirement is than feature more features expressly recited in each claim.More precisely, as the following claims
As book reflects, inventive aspect is all features less than single embodiment disclosed above.Therefore, it then follows specific real
Thus the claims for applying mode are expressly incorporated in the specific embodiment, wherein each claim itself is used as this hair
Bright separate embodiments.
Those skilled in the art should understand that the module of the equipment in example disclosed herein or unit or groups
Part can be arranged in equipment as depicted in this embodiment, or alternatively can be positioned at and the equipment in the example
In different one or more equipment.Module in aforementioned exemplary can be combined into a module or furthermore be segmented into multiple
Submodule.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
In addition, be described as herein can be by the processor of computer system or by executing by some in the embodiment
The combination of method or method element that other devices of the function are implemented.Therefore, have for implementing the method or method
The processor of the necessary instruction of element forms the device for implementing this method or method element.In addition, Installation practice
Element described in this is the example of following device: the device be used for implement as in order to implement the purpose of the invention element performed by
Function.
As used in this, unless specifically stated, come using ordinal number " first ", " second ", " third " etc.
Description plain objects, which are merely representative of, is related to the different instances of similar object, and is not intended to imply that the object being described in this way must
Must have the time it is upper, spatially, sequence aspect or given sequence in any other manner.
Although the embodiment according to limited quantity describes the present invention, above description, the art are benefited from
It is interior it is clear for the skilled person that in the scope of the present invention thus described, it can be envisaged that other embodiments.Additionally, it should be noted that
Language used in this specification primarily to readable and introduction purpose and select, rather than in order to explain or limit
Determine subject of the present invention and selects.Therefore, without departing from the scope and spirit of the appended claims, for this
Many modifications and changes are obvious for the those of ordinary skill of technical field.For the scope of the present invention, to this
Invent done disclosure be it is illustrative and not restrictive, it is intended that the scope of the present invention be defined by the claims appended hereto.
Claims (10)
1. a kind of method for identifying the affiliated component of message, suitable for executing in calculating equipment, the method comprising the steps of:
At least one critical field is extracted from message to be identified;
For an extracted critical field,
Using the search engine inquiry critical field, it is somebody's turn to do with obtaining multiple messages for including the critical field and return
The IP address of message;
The screenshot for the Web content that each IP address inquired is directed toward is obtained respectively, and the screenshot is via browser access IP
The Web content screenshot being displayed on browser behind location obtains;
Judge whether the critical field is effective according to the screenshot of acquired multiple Web contents;
For each message obtained based on effective critical field, message difference similar to message to be identified is calculated
Value;
The wherein the smallest predetermined number message of similar difference is chosen, according to the predetermined number message, using what is pre-established
Deep learning model obtains the module information of message to be identified;And
According to the module information determine the message to be identified belonging to component.
2. the method for claim 1, wherein the step of described at least one critical field of extraction includes:
According to preset set of keywords, at least one critical field is obtained by string matching in message to be identified.
3. the method for claim 1, wherein described search engine includes ZoomEye and Shadon search engine.
4. the method for claim 1, wherein the step for judging whether critical field is effective includes:
For the screenshot of acquired multiple Web contents, judge whether the screenshot of wherein every two Web content is similar;
If dissimilar number is not above predetermined ratio in obtained multiple judging results, it is determined that the critical field has
Effect, otherwise determines that the critical field is invalid.
5. method as claimed in claim 4, wherein further comprise the steps of:
After determining that a critical field is invalid, continues to repeat other invalid fields above-mentioned inquiry, obtain, judge whether
Effective step, until determining that some critical field is effective or whole critical fielies are invalid.
6. the method for claim 1, wherein judging that the whether similar step of the screenshot of two Web contents includes:
Extract the SIFT feature of two screenshots respectively using SIFT algorithm;
It is matched by the SIFT feature to two screenshots, to judge whether two screenshots are similar.
7. the step of the method for claim 1, wherein calculating the similar difference between two messages includes:
Delete the temporal information that two messages are included;
The similar difference between two messages is calculated using Levenshtein algorithm.
8. the method as described in any of claim 1-7, wherein the deep learning model is deep learning nerve net
Network.
9. a kind of calculating equipment, comprising:
One or more processors;
Memory;And
One or more programs, wherein one or more of programs are stored in the memory and are configured as by described one
A or multiple processors execute, and one or more of programs include for executing in method according to claims 1-8
The instruction of either method.
10. a kind of readable storage medium storing program for executing for storing program, described program includes instruction, and described instruction is worked as to be executed by calculating equipment
When, so that the method for calculating equipment execution as described in any of claim 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710363681.1A CN107241237B (en) | 2017-05-22 | 2017-05-22 | A kind of method and calculating equipment of the identification affiliated component of message |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710363681.1A CN107241237B (en) | 2017-05-22 | 2017-05-22 | A kind of method and calculating equipment of the identification affiliated component of message |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107241237A CN107241237A (en) | 2017-10-10 |
CN107241237B true CN107241237B (en) | 2019-11-12 |
Family
ID=59985582
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710363681.1A Active CN107241237B (en) | 2017-05-22 | 2017-05-22 | A kind of method and calculating equipment of the identification affiliated component of message |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107241237B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108156034B (en) * | 2017-12-22 | 2021-10-01 | 武汉噢易云计算股份有限公司 | Message forwarding method and message forwarding system based on deep neural network assistance |
CN108173716B (en) * | 2018-01-09 | 2020-03-17 | 北京知道创宇信息技术股份有限公司 | Method for identifying network equipment manufacturer and computing equipment |
CN109302381B (en) * | 2018-08-21 | 2022-05-10 | 新华三大数据技术有限公司 | Radius attribute extension method, device, electronic equipment and computer readable medium |
CN114697273A (en) * | 2022-03-29 | 2022-07-01 | 杭州安恒信息技术股份有限公司 | Flow identification method and device, computer equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101867578B (en) * | 2010-05-27 | 2013-05-29 | 北京星网锐捷网络技术有限公司 | Method and device for detecting counterfeit network equipment |
CN103414596A (en) * | 2013-08-28 | 2013-11-27 | 上海斐讯数据通信技术有限公司 | Method for recognizing and processing all manufacturer Traps based on simple network management protocol |
CN105329236A (en) * | 2015-11-17 | 2016-02-17 | 潍柴动力股份有限公司 | Power assembly control method, power assembly control device and power assembly control system |
-
2017
- 2017-05-22 CN CN201710363681.1A patent/CN107241237B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101867578B (en) * | 2010-05-27 | 2013-05-29 | 北京星网锐捷网络技术有限公司 | Method and device for detecting counterfeit network equipment |
CN103414596A (en) * | 2013-08-28 | 2013-11-27 | 上海斐讯数据通信技术有限公司 | Method for recognizing and processing all manufacturer Traps based on simple network management protocol |
CN105329236A (en) * | 2015-11-17 | 2016-02-17 | 潍柴动力股份有限公司 | Power assembly control method, power assembly control device and power assembly control system |
Also Published As
Publication number | Publication date |
---|---|
CN107241237A (en) | 2017-10-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107241237B (en) | A kind of method and calculating equipment of the identification affiliated component of message | |
US10621509B2 (en) | Method, system and computer program product for learning classification model | |
US10678822B2 (en) | Query expansion using a graph of question and answer vocabulary | |
US8380680B2 (en) | Piecemeal list prefetch | |
CN107729532A (en) | A kind of resume matching process and computing device | |
US11888855B2 (en) | Website verification platform | |
US20150309981A1 (en) | Methods, systems, and devices for outcome prediction of text submission to network based on corpora analysis | |
US11423307B2 (en) | Taxonomy construction via graph-based cross-domain knowledge transfer | |
US11640540B2 (en) | Interpretable knowledge contextualization by re-weighting knowledge graphs | |
CN107341233A (en) | A kind of position recommends method and computing device | |
CN110427453B (en) | Data similarity calculation method, device, computer equipment and storage medium | |
US20160180218A1 (en) | Automated opinion prediction based on indirect information | |
US20230388261A1 (en) | Determining topic cohesion between posted and linked content | |
CN107832300A (en) | Towards minimally invasive medical field text snippet generation method and device | |
JP2017532655A (en) | Compress cascading style sheet files | |
CN116324804A (en) | Training a question-answer dialog system to avoid challenge-resistance attacks | |
CN111241843B (en) | Semantic relation inference system and method based on composite neural network | |
US10884996B1 (en) | Systems and methods for optimizing automatic schema-based metadata generation | |
CN104580109A (en) | Method and device for generating click verification code | |
CN109660612A (en) | A kind of request processing method and server | |
WO2021139076A1 (en) | Intelligent text dialogue generation method and apparatus, and computer-readable storage medium | |
US20150310079A1 (en) | Methods, systems, and devices for machines and machine states that analyze and modify documents and various corpora | |
US20080109435A1 (en) | Determining Sort Order by Traffic Volume | |
US11157532B2 (en) | Hierarchical target centric pattern generation | |
CN108683749A (en) | A kind of judgment method, equipment and the medium of random email address |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 311501, Unit 1, Building 5, Courtyard 1, Futong East Street, Chaoyang District, Beijing 100102 Applicant after: Beijing Zhichuangyu Information Technology Co., Ltd. Address before: 100097 Jinwei Building 803, 55 Lanindichang South Road, Haidian District, Beijing Applicant before: Beijing Knows Chuangyu Information Technology Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |