CN106528680A - Identification method and device for junk information - Google Patents
Identification method and device for junk information Download PDFInfo
- Publication number
- CN106528680A CN106528680A CN201610934006.5A CN201610934006A CN106528680A CN 106528680 A CN106528680 A CN 106528680A CN 201610934006 A CN201610934006 A CN 201610934006A CN 106528680 A CN106528680 A CN 106528680A
- Authority
- CN
- China
- Prior art keywords
- junk information
- recognition strategy
- strategy
- information recognition
- junk
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
- H04L63/0227—Filtering policies
- H04L63/0236—Filtering by address, protocol, port number or service, e.g. IP-address or URL
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
- H04L63/0227—Filtering policies
- H04L63/0263—Rule management
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses an identification method and device for junk information. The method comprises the following steps of: obtaining the historical behavior data and the business data of a current user; obtaining a junk information identification strategy corresponding to the business data; and according to the junk information identification strategy and the historical behavior data, identifying the to-be-published information of a current user. By use of the embodiment of the invention, the above technical scheme is adopted, different junk information identification strategies are determined by aiming at different business data, so that junk identification exhibits better pertinence, and meanwhile, the historical behavior data of the user can be combined to enhance junk information identification accuracy.
Description
Technical field
The present embodiments relate to Internet technical field, more particularly to a kind of junk information recognition methodss and device.
Background technology
With the high speed development of the Internet, the black product industry for issuing the junk information such as fraud information and sham publicity also exists
Quickly develop, user is frequently seen these junk information when browsing information on the internet, be that user brings great being stranded
Disturb, or even the otherwise losses such as substantial amounts of economic and spirit are brought for all multi-users.
At present, part website takes certain filtering policy to eliminate junk information, however, these junk information
Existence form and to issue form varied and change continuous, and from initial small-scale crime, by now team's industry
The crime of formula, general filtering policy are difficult to identify in time the junk information of continuous upgrading, therefore, need badly a kind of timely and effective
Identify the scheme of junk information.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of junk information recognition methodss and device, to optimize existing rubbish letter
Breath identifying schemes.
On the one hand, a kind of junk information recognition methodss are embodiments provided, including:
Obtain the historical behavior data and business datum of active user;
Obtain junk information recognition strategy corresponding with the business datum;
According to the information to be released of the junk information recognition strategy and the historical behavior data to the active user
It is identified.
On the other hand, a kind of junk information identifying device is embodiments provided, including:
Data acquisition module, for obtaining the historical behavior data and business datum of active user;
Recognition strategy acquisition module, for obtaining junk information recognition strategy corresponding with the business datum;
Information identification module, for according to the junk information recognition strategy and the historical behavior data to described current
The information to be released of user is identified.
The junk information identifying schemes provided in the embodiment of the present invention, obtain the historical behavior data and business of active user
Data, according to the information to be released of junk information recognition strategy corresponding with business datum and historical behavior data to active user
It is identified.By adopting above-mentioned technical proposal, different junk information recognition strategies can be determined for different business datums,
Make rubbish identification more targetedly, the accuracy of junk information identification can be strengthened in combination with the historical behavior data of user.
Description of the drawings
Fig. 1 is a kind of schematic flow sheet of junk information recognition methodss that the embodiment of the present invention one is provided;
Fig. 2 is a kind of schematic flow sheet of junk information recognition methodss that the embodiment of the present invention two is provided;
Fig. 3 is a kind of schematic flow sheet of junk information recognition methodss that the embodiment of the present invention three is provided;
Fig. 4 is a kind of junk information recognition strategy renewal process schematic diagram that the embodiment of the present invention three is provided;
Fig. 5 is that a kind of junk information recognition strategy that the embodiment of the present invention three is provided updates schematic diagram;
Fig. 6 is a kind of structured flowchart of junk information identifying device that the embodiment of the present invention four is provided;
Fig. 7 is a kind of structural representation of anti-spam system that the embodiment of the present invention five is provided.
Specific embodiment
Technical scheme is further illustrated below in conjunction with the accompanying drawings and by specific embodiment.May be appreciated
It is that specific embodiment described herein is used only for explaining the present invention, rather than limitation of the invention.Further need exist for explanation
, for the ease of description, in accompanying drawing, illustrate only part related to the present invention rather than entire infrastructure.
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The process described as flow chart or method.Although each step to be described as flow chart the process of order, many of which
Step can by concurrently, concomitantly or while implement.Additionally, the order of each step can be rearranged.When its operation
When completing, the process can be terminated, it is also possible to have the additional step being not included in accompanying drawing.The process can be with
Corresponding to method, function, code, subroutine, subprogram etc..
Embodiment one
Fig. 1 is a kind of schematic flow sheet of junk information recognition methodss that the embodiment of the present invention one is provided, and the method can be with
Performed by junk information identifying device, wherein the device can be realized by software and/or hardware, can typically be integrated in server etc. eventually
Becoming anti-spam in end(Anti-Spam)The core of system.As shown in figure 1, the method includes:
Step 101, the historical behavior data and business datum that obtain active user.
Exemplary, can be by the identity of user(Identification, ID)Or Internet protocol(Internet
Protocol, IP)Address obtains related to active user going through according to the identity of active user confirming the identity of active user
History behavioral data.Historical behavior data may include the history accessing request information of user, history access time, historical behavior class
Content that the classification and history that type, history release news releases news etc..Business datum is may include with active user now
The data of the corresponding business correlation of website of access, for example:Hour of log-on of the user on website, the business being currently in operation
Content-data that type, operation are submitted to etc..
Optionally, before this step is carried out, user passes through webpage or application client(Web/APP)Have access to
During website, the filtration of an owl/RPC layer, wherein, owl can be first passed around(Web Ontology Language)It is that W3C recommends
Semantic Web in ontology description language standard, RPC(Remote Procedure Call Protocol, remote process
Invocation protocol)It is a kind of to ask to service the association without understanding underlying network technology by network from remote computer program
View.In this layer, by the ID in user request information, user's HTML (Hypertext Markup Language)(HyperText Transfer
Protocol, HTTP) information such as request header information and IP address does a simple rule-based filtering.Such as one hour
Interior certain IP request is more than n times(N can be set according to practical situation), just directly refusal service, prevention active user issue
Message.
Step 102, acquisition junk information recognition strategy corresponding with business datum.
Exemplary, for different business, may there is difference in the type of junk information and particular content,
Junk information that may be present in each business can be analyzed according to practical business feature, and then determine that different business is corresponding
Junk information recognition strategy, to realize targetedly junk information identification.In this step, can be according to business datum from difference
Business junk information corresponding with current business datum is obtained in the correspondence relationship information of junk information recognition strategy recognizes plan
Slightly, recognize for follow-up junk information.
Step 103, the information to be released of active user is carried out according to junk information recognition strategy and historical behavior data
Identification.
Exemplary, acquired all data can be entered row format conversion, in order to recognize.For example, data can be turned
It is changed to following reference format:[userid,userip,action_time_stamp,action_type,accept_object_
Id, content, business_data, history_data], the implication that each element is represented in the form is respectively:User's body
Part, User IP, time of the act, behavior type, content ID, content, business datum and historical behavior data.
Exemplary, according to the particular content in acquired junk information recognition strategy and above-mentioned standard form to current
The information to be released of user is identified.
The junk information recognition methodss that the embodiment of the present invention one is provided, obtain the historical behavior data and business of active user
Data, according to the information to be released of junk information recognition strategy corresponding with business datum and historical behavior data to active user
It is identified.By adopting above-mentioned technical proposal, different junk information recognition strategies can be determined for different business datums,
Make rubbish identification more targetedly, the accuracy of junk information identification can be strengthened in combination with the historical behavior data of user.
On the basis of above-described embodiment, according to junk information recognition strategy and historical behavior data to the current use
After the information to be released at family is identified, may also include:If identifying, information to be released is junk information, to letter to be released
Breath carries out delete processing, while carrying out closing process to active user.It is exemplary, identifying that active user wants what is issued
When information is junk information, in time the information can be deleted, prevent junk information from interfering to domestic consumer, while
Active user is carried out closing process, prevents the user from continuing to attempt to issue junk information.
Further, the process plan that can be also processed comprising the junk information to recognizing in junk information recognition strategy
Slightly, targetedly processed in order to be directed to different types of junk information.
Embodiment two
Fig. 2 be the embodiment of the present invention two provide a kind of junk information recognition methodss schematic flow sheet, the present embodiment with
It is optimized based on above-described embodiment, the method for the present embodiment comprises the steps:
Step 201, the historical behavior data and business datum that obtain active user.
Step 202, parsed using the eval functions of Python and obtain include in Sandbox with business datum pair
The junk information recognition strategy answered.
As the renewal of junk information is upgraded quickly, in order to meet anti-spam(Anti-Spam)The antagonism of system, needs
In time rubbish recognition strategy is updated, during renewal, in order that the continual work of Anti-Spam systems, needs
Strategy to be made Quick thread and can need not restart related service when reaching the standard grade.
Preferably, may also include before this step:Junk information recognition strategy to including in Sandbox is carried out more
Newly.
Python is a kind of OO explanation type computer programming language, using Python
The characteristic of dynamic calculation sentence(I.e. using the eval functions of Python)To send out user according to junk information recognition strategy
The information of cloth is identified, so needing eval functions to get junk information recognition strategy.In the present embodiment, one can be encapsulated
Sandbox(Sandbox), junk information recognition strategy packaging is entered, Sandbox eval is provided as into so that eval is in parsing
When stating strategy, the meaning of one's words of tactful designer can be correctly got.
Step 203, active user is treated according to junk information recognition strategy and historical behavior data using eval functions
Release news and be identified.
If step 204, identifying information to be released for junk information, treating to release news carries out delete processing, while
Active user is carried out closing process.
Exemplary, when carrying out junk information identification and processing using eval, can be realized by following sentence:
trigger:action==“QUESTION_CREATE”and len(same_text(user_same_actions
(60), 0.7))>=2
action:Freeze_user, delete_all
, on the basis of above-described embodiment, the dynamic of the Python for utilizing of novelty is special for the embodiment of the present invention two
Property, accurately identify junk information by related service need not be restarted when new rubbish recognition strategy is reached the standard grade in real time and carry out
It is corresponding to process, can help on-line user's shielding rubbish information, lift Consumer's Experience.
Embodiment three
Fig. 3 be the embodiment of the present invention three provide a kind of junk information recognition methodss schematic flow sheet, the present embodiment with
It is optimized based on above-described embodiment, will enters the step of being updated to the junk information recognition strategy included in Sandbox
Refinement is gone, the method for the present embodiment comprises the steps:
Step 301, the historical behavior data and business datum that obtain active user.
Step 302, the new junk information recognition strategy for receiving policy agent push, and the rubbish to including in Sandbox
Rubbish information recognition strategy is updated.
Wherein, the new junk information recognition strategy is automatically raw from tactical management backstage or strategy by the policy agent
Obtain at component.
Exemplary, Fig. 4 is a kind of junk information recognition strategy renewal process schematic diagram that the embodiment of the present invention three is provided,
As shown in figure 4, after tactical management backstage or strategy automatically generate component generation strategy, will request strategy agency, will
Policy data is updated in Policy Core storage, while newest policy data can be pushed to policy agent the rubbish letter of operation
Go inside breath identifying device, i.e., the junk information recognition strategy to including in Sandbox is updated, junk information identifying device
It is the latest data in the policy agent for reading every time, so now strategy i.e. newest, newest when getting
After strategy, it is possible to according to the operational mode for describing above, new strategy is come into force, this process is completely without restarting rubbish
Information recognition device and related service.
Fig. 5 is that a kind of junk information recognition strategy that the embodiment of the present invention three is provided updates schematic diagram, in Fig. 5, left side table
Show the junk information of issue, what right side represented is the explanatory note of junk information recognition strategy(The part meeting in the specific implementation
It is converted into code form to form the junk information recognition strategy described in the present embodiment), it is seen then that with junk information not
Disconnected upgrading, needs ceaselessly to update junk information recognition strategy.It should be noted that the segment word content in Fig. 5 be related to it is quick
Sense information, has done Fuzzy Processing, and the signal effect played on Fig. 5 by the content of Fuzzy Processing does not constitute impact.
Step 303, parsed using the eval functions of Python and obtain include in Sandbox with business datum pair
The junk information recognition strategy answered.
Step 304, active user is treated according to junk information recognition strategy and historical behavior data using eval functions
Release news and be identified.
If step 305, identifying information to be released for junk information, treating to release news carries out delete processing, while
Active user is carried out closing process.
The embodiment of the present invention has refined the step being updated to junk information recognition strategy on the basis of above-described embodiment
Suddenly, by policy agent come the forwarding of implementation strategy, operating junk information identifying device is enable to obtain new plan in time
Slightly.
Example IV
Fig. 6 is a kind of structured flowchart of junk information identifying device that the embodiment of the present invention four is provided, as shown in fig. 6, should
Device includes data acquisition module 601, recognition strategy acquisition module 602 and information identification module 603.
Wherein, data acquisition module 601, for obtaining the historical behavior data and business datum of active user;Identification plan
Acquisition module 602 is omited, for obtaining junk information recognition strategy corresponding with the business datum;Information identification module 603, uses
In being known to the information to be released of the active user according to the junk information recognition strategy and the historical behavior data
Not.
Junk information identifying device provided in an embodiment of the present invention, can determine different rubbish for different business datums
Information recognition strategy, makes rubbish identification more targetedly, can strengthen junk information in combination with the historical behavior data of user
The accuracy of identification.
On the basis of above-described embodiment, the recognition strategy acquisition module specifically for:Using Python
The junk information recognition strategy corresponding with the business datum that eval functions are parsed and included in obtaining sandbox Sandbox;Institute
State information identification module specifically for:Using eval functions according to the junk information recognition strategy and the historical behavior data
The information to be released of the active user is identified.
On the basis of above-described embodiment, the device also includes:Update module, for obtaining and the business datum pair
Before the junk information recognition strategy answered, the junk information recognition strategy to including in Sandbox is updated.
On the basis of above-described embodiment, the update module specifically for:Receive the new rubbish that policy agent is pushed
Information recognition strategy, and the junk information recognition strategy to including in Sandbox is updated, wherein, the new rubbish letter
Breath recognition strategy automatically generates component acquisition by the policy agent from tactical management backstage or strategy.
On the basis of above-described embodiment, the device also includes:Processing module, for recognizing according to the junk information
After tactful and described historical behavior data are identified to the information to be released of the active user, if identifying described pending
Cloth information is junk information, then carry out delete processing to the information to be released, while carrying out closing place to the active user
Reason.
Embodiment five
A kind of structural representation of anti-spam system that Fig. 7 is provided for the embodiment of the present invention five, the system(Antispam)
The junk information identifying schemes provided based on the embodiment of the present invention are realizing.
As shown in fig. 7, the system includes online detection module(owl/RPC), node(Sink), offline inspection module(Realize
Empty wukong)And memory module, wherein realize sky and can be regarded as junk information identifying device provided in an embodiment of the present invention.User is led to
When crossing Web/APP and having access to website, web or API(Application Programming Interface, application programming
Interface)Data can be filtered through owl/RPC layers, subsequent data are transferred to offline inspection module through Sink, and data exist
Analyzer is passed sequentially through in offline inspection module(Parser), distributed memory queue system(Task Queue Beanstalk)
And multiple trapping modules(Hunter)The data for receiving are converted to into following form afterwards:[userid,userip,action_
Time_stamp, action_type, accept_object_id, content, business_data, history_data],
It is easy to eval to be calculated, junk information is identified and respective handling.Subsequently data can also be entered memory module
(Storage), wherein, in memory module, contain Redis, Mysql and Tukomx document database.
Policy agent described in above-described embodiment directly can be communicated with the offline inspection module in the present embodiment, will
New junk information recognition strategy is sent to offline inspection module.
Anti-spam system provided in an embodiment of the present invention can determine different junk information for different business datums
Recognition strategy, makes rubbish identification more targetedly, can strengthen junk information identification in combination with the historical behavior data of user
Accuracy.
The junk information identifying device provided in above-described embodiment and anti-spam system can perform any embodiment of the present invention
The junk information recognition methodss for being provided, possess the corresponding functional module of execution the method and beneficial effect.Not in above-mentioned enforcement
In example, the ins and outs of detailed description, can be found in the junk information recognition methodss provided by any embodiment of the present invention.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although the present invention is carried out by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
More other Equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of junk information recognition methodss, it is characterised in that include:
Obtain the historical behavior data and business datum of active user;
Obtain junk information recognition strategy corresponding with the business datum;
The information to be released of the active user is carried out according to the junk information recognition strategy and the historical behavior data
Identification.
2. method according to claim 1, it is characterised in that obtain junk information identification corresponding with the business datum
Strategy, including:
Include in sandbox Sandbox corresponding with the business datum is parsed and is obtained using the eval functions of Python
Junk information recognition strategy;
The information to be released of the active user is carried out according to the junk information recognition strategy and the historical behavior data
Identification, including:
The active user is treated according to the junk information recognition strategy and the historical behavior data using eval functions
Release news and be identified.
3. method according to claim 2, it is characterised in that know junk information corresponding with the business datum is obtained
Not before strategy, also include:
Junk information recognition strategy to including in Sandbox is updated.
4. method according to claim 3, it is characterised in that the junk information recognition strategy to including in Sandbox enters
Row updates, including:
Receive the new junk information recognition strategy that policy agent is pushed, and the junk information identification plan to including in Sandbox
Slightly be updated, wherein, the new junk information recognition strategy by the policy agent from tactical management backstage or strategy from
Obtain at dynamic formation component.
5. method according to claim 1, it is characterised in that according to the junk information recognition strategy and the history
After behavioral data is identified to the information to be released of the active user, also include:
If identifying, the information to be released is junk information, carries out delete processing to the information to be released, while to institute
Stating active user carries out closing process.
6. a kind of junk information identifying device, it is characterised in that include:
Data acquisition module, for obtaining the historical behavior data and business datum of active user;
Recognition strategy acquisition module, for obtaining junk information recognition strategy corresponding with the business datum;
Information identification module, for according to the junk information recognition strategy and the historical behavior data to the active user
Information to be released be identified.
7. device according to claim 6, it is characterised in that the recognition strategy acquisition module specifically for:
Include in sandbox Sandbox corresponding with the business datum is parsed and is obtained using the eval functions of Python
Junk information recognition strategy;
Described information identification module specifically for:
The active user is treated according to the junk information recognition strategy and the historical behavior data using eval functions
Release news and be identified.
8. device according to claim 7, it is characterised in that also include:
Update module, for before junk information recognition strategy corresponding with the business datum is obtained, to wrapping in Sandbox
The junk information recognition strategy for containing is updated.
9. device according to claim 8, it is characterised in that the update module specifically for:
Receive the new junk information recognition strategy that policy agent is pushed, and the junk information identification plan to including in Sandbox
Slightly be updated, wherein, the new junk information recognition strategy by the policy agent from tactical management backstage or strategy from
Obtain at dynamic formation component.
10. device according to claim 6, it is characterised in that also include:
Processing module, for according to the junk information recognition strategy and the historical behavior data to the active user's
After information to be released is identified, if identifying, the information to be released is junk information, and the information to be released is entered
Row delete processing, while carry out closing process to the active user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610934006.5A CN106528680A (en) | 2016-10-25 | 2016-10-25 | Identification method and device for junk information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610934006.5A CN106528680A (en) | 2016-10-25 | 2016-10-25 | Identification method and device for junk information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106528680A true CN106528680A (en) | 2017-03-22 |
Family
ID=58292551
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610934006.5A Pending CN106528680A (en) | 2016-10-25 | 2016-10-25 | Identification method and device for junk information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106528680A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111901160A (en) * | 2020-07-15 | 2020-11-06 | 中盈优创资讯科技有限公司 | Method and device for combing network equipment garbage strategy configuration |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101415188A (en) * | 2008-11-28 | 2009-04-22 | 电子科技大学 | Supervision method for sending rubbish short message in group |
CN101534261A (en) * | 2009-04-10 | 2009-09-16 | 阿里巴巴集团控股有限公司 | A method, device and system of recognizing spam information |
US20090319480A1 (en) * | 2007-12-25 | 2009-12-24 | Fuji Xerox Co., Ltd. | Security policy management device, security policy management system, and storage medium |
CN102045271A (en) * | 2010-12-07 | 2011-05-04 | 成都市华为赛门铁克科技有限公司 | Junk mail processing method, and related device and system |
CN104348642A (en) * | 2013-07-31 | 2015-02-11 | 华为技术有限公司 | A spam information filtering method and device |
CN104980402A (en) * | 2014-04-09 | 2015-10-14 | 腾讯科技(北京)有限公司 | Method and device for recognizing malicious operation |
-
2016
- 2016-10-25 CN CN201610934006.5A patent/CN106528680A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090319480A1 (en) * | 2007-12-25 | 2009-12-24 | Fuji Xerox Co., Ltd. | Security policy management device, security policy management system, and storage medium |
CN101415188A (en) * | 2008-11-28 | 2009-04-22 | 电子科技大学 | Supervision method for sending rubbish short message in group |
CN101534261A (en) * | 2009-04-10 | 2009-09-16 | 阿里巴巴集团控股有限公司 | A method, device and system of recognizing spam information |
CN102045271A (en) * | 2010-12-07 | 2011-05-04 | 成都市华为赛门铁克科技有限公司 | Junk mail processing method, and related device and system |
CN104348642A (en) * | 2013-07-31 | 2015-02-11 | 华为技术有限公司 | A spam information filtering method and device |
CN104980402A (en) * | 2014-04-09 | 2015-10-14 | 腾讯科技(北京)有限公司 | Method and device for recognizing malicious operation |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111901160A (en) * | 2020-07-15 | 2020-11-06 | 中盈优创资讯科技有限公司 | Method and device for combing network equipment garbage strategy configuration |
CN111901160B (en) * | 2020-07-15 | 2022-09-16 | 中盈优创资讯科技有限公司 | Method and device for combing network equipment garbage strategy configuration |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11150874B2 (en) | API specification generation | |
US11151660B1 (en) | Intelligent routing control | |
US11556695B2 (en) | Combinatorial inflight analysis of multipart data | |
US20180341688A1 (en) | System and method for optimizing aggregation and analysis of data across multiple data sources | |
US10581866B1 (en) | Website verification platform | |
CN110275898A (en) | Use the integrated monitoring and communication system of the explanatory equipment management of knowledge based figure | |
EP2590113A1 (en) | On demand multi-objective network optimization | |
CN105827706A (en) | Information push device and method | |
CN102124481A (en) | Embedding macros in web pages with advertisements | |
US10453073B1 (en) | Ontology based customer support techniques | |
US8789177B1 (en) | Method and system for automatically obtaining web page content in the presence of redirects | |
CN113454621A (en) | Method, apparatus and computer program for collecting data from multiple domains | |
CN109597739A (en) | Voice log services method and system in human-computer dialogue | |
CN116457875A (en) | Method and system for automating support services | |
CN111126071B (en) | Method and device for determining questioning text data and method for processing customer service group data | |
Ali et al. | Requirement prioritization framework using case‐based reasoning: A mining‐based approach | |
JP6683681B2 (en) | Determining the contribution of various user interactions to conversions | |
Snidaro et al. | Knowledge representation for ambient security | |
CN106528680A (en) | Identification method and device for junk information | |
US20220300873A1 (en) | System and method for institutional risk identification using automated news profiling and recommendation | |
US20190347672A1 (en) | Memory augmentation in support of web interactions | |
CN106982147A (en) | The communication monitoring method and device of a kind of Web communication applications | |
CN111581533B (en) | Method and device for identifying state of target object, electronic equipment and storage medium | |
US20210288925A1 (en) | Microservice deployment in multi-tenant environments | |
US20150206075A1 (en) | Efficient Decision Making |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |