CN106294536A - A kind of method and device of anti-cheating video - Google Patents
A kind of method and device of anti-cheating video Download PDFInfo
- Publication number
- CN106294536A CN106294536A CN201610575419.9A CN201610575419A CN106294536A CN 106294536 A CN106294536 A CN 106294536A CN 201610575419 A CN201610575419 A CN 201610575419A CN 106294536 A CN106294536 A CN 106294536A
- Authority
- CN
- China
- Prior art keywords
- video
- cheating
- user
- daily record
- record data
- 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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses the method and device of a kind of anti-cheating video, to solve prior art affects, owing to cannot evade cheating video, the problem that normal video is demonstrated.Wherein, the method for anti-cheating video includes: obtain the daily record data of video；Use default cheating video identification rule that the daily record data of described video is screened, determine cheating video；Reducing the searching order of described cheating video and recommend sequence, the program has evaded the cheating video impact on normal video so that normal video can obtain rational display machine meeting.
Description
Technical field
The present invention relates to video search engine technical field, particularly relate to the method and device of a kind of anti-cheating video.
Background technology
Nowadays, video, as important online Streaming Media product, occupies important in daily life is entertained
Position.Encourage user to make video, uploaded videos, and to obtain exposing also be the basic principle of video website.Each video website
Results for video will be shown in Search Results or commending system.Its algorithm behind is typically to make use of video title, retouches
State, playback volume, the data such as upload user information.Normal video is generally of rational title, describes, and playback volume, and
Interbehavior with user.Normal user also can comprise normal video, and has a certain amount of vermicelli.But the Internet regards
Frequently there is substantial amounts of cheating video and cheating user in website.
Cheating video and cheating user can produce inequitable impact to normal video and user.In industrial quarters and science
Boundary, people are not about cheating video and the strict difinition of cheating user.Common cheating video and cheating user have as follows
Feature: video title has a large amount of word to pile up, such as " what Gui of happy base camp that makes progress every day thanks to Na video ", " horse cloud Ma Huateng
The foundation treasured book of Wang Jian Lin Liyanhong thunder army Chen An ".Video content and video title not the biggest association, or carry agency's secretly
Promotion message.Such as the video content of " what Gui of happy base camp that makes progress every day thanks to Na video " is about starting an undertaking,
Cheating video has bigger playback volume.But, the video of non-popular program and personage does not have up to million broadcast
High-volume, the vermicelli of cheating user is little, and this situation does not meets normal " broadcast and the turn powder " efficiency in website.
Regular traffic is carried out by cheating video and cheating user is and disadvantageous.Cheating video and cheating user due to
False playback volume and title, generally can gain all advantage so that oneself can come before results for video in sort algorithm,
It is easy to expose, so that real video does not has chance for exposure in search and recommendation.
Summary of the invention
Present invention is primarily targeted at the method and device that a kind of anti-cheating video is provided, with solve in prior art by
In cannot evade cheating video and affect the problem that normal video is demonstrated.
A kind of method of anti-cheating video, including:
Obtain the daily record data of video；
Use default cheating video identification rule that the daily record data of described video is screened, determine that cheating regards
Frequently；
Reduce the searching order of described cheating video and recommend sequence.
Preferably, described cheating video identification rule, including:
Judge that whether the meeting of popular key word that video title comprises presets popular key word number, it is judged that video is in advance
If whether the playback volume in the time period meets presets broadcasting time, it is judged that the user that video obtains in described preset time period hands over
Whether behavior is less than the second preset times mutually, it is judged that whether the title of video meets first is preset rule；
Use described cheating video identification rule that the daily record data of described video is screened, determine cheating video,
Including:
It is defined as the daily record data of described video at least meets the video of in described cheating video identification rule
Cheating video.
Preferably, described method also includes:
Using the cheating video identification preset rule that the daily record data of described video is screened, determining that cheating regards
After Pin, obtain the daily record data of user, use default cheating user's recognition rule that the daily record data of described user is carried out
Screening, determines cheating user；
Reduce the searching order of the video that described cheating user uploads and recommended sequence.
Preferably, described cheating user's recognition rule includes:
Judge whether the user's name in the daily record data of described user meets second and preset rule, it is judged that described user's
In daily record data, whether the playback volume of video meets default broadcasting time, it is judged that the user in the daily record data of described user regards
Whether frequency mesh is less than presetting video number, it is judged that comprise in the title of the video of the user in the daily record data of described user
Whether the number of popular key word meets is preset popular key word number, it is judged that the vermicelli number of user in described user journal data
Whether less than presetting vermicelli number；
The described daily record data obtaining user, uses default cheating user's recognition rule daily record data to described user
Screen, determine cheating user, including:
It is defined as the daily record data of described user at least meets the user of in described cheating user's recognition rule
Cheating user.
Preferably, described method also includes:
Receive title and/or the identity of cheating user of the cheating video of outside input, by described cheating video
The identity of title and/or cheating user is sent to video cache district, so that cheating video and cheating user regard described
Frequently identified in buffer area, described cheating video identification is regular and described cheating user's recognition rule is pre-stored in described video and delays
Deposit in district.
A kind of device of anti-cheating video, including:
First acquisition module, for obtaining the daily record data of video；
First screening module, for using default cheating video identification rule to sieve the daily record data of described video
Choosing, determines cheating video；
First fall power module, for reducing the searching order of described cheating video and recommending sequence.
Preferably, described cheating video identification rule, including:
Judge that whether the meeting of popular key word that video title comprises presets popular key word number, it is judged that video is in advance
If whether the playback volume in the time period meets presets broadcasting time, it is judged that the user that video obtains in described preset time period hands over
Whether behavior is less than the second preset times mutually, it is judged that whether the title of video meets first is preset rule；
Described first screening module specifically for:
It is defined as the daily record data of described video at least meets the video of in described cheating video identification rule
Cheating video.
Preferably, described device also includes:
Second screening module, for using the cheating video identification preset rule to carry out the daily record data of described video
Screening, after determining cheating video, obtains the daily record data of user, uses default cheating user's recognition rule to described use
The daily record data at family screens, and determines cheating user；
Second fall power module, for reducing the searching order of the video that described cheating user uploads and recommended row
Sequence.
Preferably, described cheating user's recognition rule includes:
Judge whether the user's name in the daily record data of described user meets second and preset rule, it is judged that described user's
In daily record data, whether the playback volume of video meets default broadcasting time, it is judged that the user in the daily record data of described user regards
Whether frequency mesh is less than presetting video number, it is judged that comprise in the title of the video of the user in the daily record data of described user
Whether the number of popular key word meets is preset popular key word number, it is judged that the vermicelli number of user in described user journal data
Whether less than presetting vermicelli number；
Described second screening module specifically for:
It is defined as the daily record data of described user at least meets the user of in described cheating user's recognition rule
Cheating user.
Preferably, described device also includes:
Receiver module, for receiving title and/or the identity of cheating user of the cheating video of outside input；
Sending module, delays for the identity of the title of described cheating video and/or cheating user is sent to video
Deposit district so that cheating video and cheating user are identified in described video cache district, described cheating video identification rule with
And described cheating user's recognition rule be pre-stored in described video cache district.
The present invention has the beneficial effect that:
The scheme that present example the provides cheating video to identifying uses fall power to process, and improves video search and recommendation
The ranking results of the video in algorithm so that cheating user and cheating video are in very big inferior position in sequence, have evaded cheating
The video impact on normal video display so that normal video can obtain rational display machine meeting.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this
Bright schematic description and description is used for explaining the present invention, is not intended that inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the method for the anti-cheating video that the embodiment of the present invention 1 provides；
Fig. 2 is the structured flowchart of the device of the anti-cheating video that the embodiment of the present invention 2 provides；
Fig. 3 is the structured flowchart of the device of the anti-cheating video that the embodiment of the present invention 3 provides.
Detailed description of the invention
In order to solve that prior art affects, owing to cannot evade cheating video, the problem that normal video is demonstrated, this
The bright method and device providing a kind of anti-cheating video, below in conjunction with accompanying drawing and embodiment, is carried out the present invention further
Describe in detail.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, does not limit the present invention.
Embodiment 1
A kind of method present embodiments providing anti-cheating video, Fig. 1 is the flow chart of the method, as it is shown in figure 1, the party
Method includes processing as follows:
Step 101: obtain the daily record data of video；
Step 102: use the cheating video identification preset rule that the daily record data of video is screened, determine cheating
Video；
Cheating video identification rule specifically can include each in the daily record data of the video got in the present embodiment
Item video data makes the following judgment:
Judge that whether the meeting of popular key word that video title comprises presets popular key word number, it is judged that video is in advance
If whether the playback volume in the time period meets presets broadcasting time, it is judged that the mutual row of user that video obtains in preset time period
For whether less than the second preset times, it is judged that whether the title of video meets first is preset rule；Based on this, use cheating video
The daily record data of video is screened by recognition rule, determines that the step of cheating video specifically may include that the day of video
Will data at least meet the video of in cheating video identification rule and is defined as video of practising fraud.
Step 103: reduce the searching order of cheating video and recommend sequence.
Further, the method that the present embodiment provides can also comprise the following steps:
Using the cheating video identification preset rule that the daily record data of video is screened, determine practise fraud video it
After, obtain the daily record data of user, use default cheating user's recognition rule that the daily record data of user is screened, determine
Go out the user that practises fraud；Reduce the searching order of the video that cheating user uploads and recommended sequence.
Wherein, whether cheating user's recognition rule specifically may include that the user's name in the daily record data judging user
Meet second and preset rule, it is judged that in the daily record data of user, whether the playback volume of video meets default broadcasting time, it is judged that use
Whether the video number of the user in the daily record data at family is less than presetting video number, it is judged that the user in the daily record data of user
Video title in the number of popular key word that comprises whether meet and preset popular key word number, it is judged that user journal number
Whether it is less than according to the vermicelli number of middle user and presets vermicelli number；Obtain the daily record data of user, use default cheating user to identify
The daily record data of user is screened by rule, determines cheating user, including: make the daily record data of user at least meets
In fraud user's recognition rule, the user of is defined as the user that practises fraud.
Preferably, the present embodiment provides method to include: receive title and/or the work of the cheating video of outside input
The identity of fraud user, is sent to video cache district by the title of cheating video and/or the identity of cheating user, so that
Cheating video and cheating user are identified in video cache district.Preferably, in the present embodiment, cheating video identification rule
And cheating user's recognition rule can be pre-stored in video cache district.
Embodiment 2
Present embodiments providing the anti-video system of practising fraud of one, the present embodiment is for SEO (Search Engine
Optimization, search engine optimization) the line that technology designs suppression cheating video and cheating user exposes on framework, this
Embodiment mainly proposes two kinds of frameworks, i.e. basic framework and manual intervention framework, and these two frameworks come into force simultaneously, and suppression cheating regards
Frequency exposes with cheating user's.Wherein, basic framework is used for realizing identifying that function and suppression are exposed automatically；Manual intervention framework
It is responsible for cheating video and the user manually added, and comes into force in time, in case urgent need.
In the present embodiment, the basic data for the anti-video of practising fraud of video website can comprise two parts: cheating video
With cheating user.
Identification to cheating video and cheating user illustrates individually below:
Cheating video it is generally desirable to obtain on the platform of video website and higher exposes probability and attention rate.Such as, exist
In search engine, cheating video it is generally desirable to come the homepage of search results pages, the most former positions；In video recommendation system
In, cheating video also is intended to obtain more recommendation；Cheating video also it is generally desirable to more user collection or reprinted
Oneself, so on third-party platform, cheating video also has any opportunity for more people and sees.
The present embodiment, by the statistical analysis to SEO technology and video, finds that cheating video has a characteristic that
The title of cheating video generally comprises multiple popular word, or the popular word of association area, i.e. popular pass
Keyword.Such as, hot broadcast TV play and variety, the program names of field of finance and economics and famous person, start an undertaking or sell directly to households field program names and
Famous persons etc., such as, common are in nearest network: happy comedy people, the descendant of the sun, youth's eye finance and economics, Ma Yun, Chen An it, peace
Profit etc..
Improving playback volume owing to cheating video has special SEO instrument to come extremely, therefore, the playback volume of cheating video is usual
Reach improper high value within a short period of time.By statistics it is found that a normal domestic consumer is in one day
Video playback amount generally not over 10000, but cheating video playback volume can reach hundreds of thousands very at several hours
To up to a million.
User's interbehaviors such as cheating video is stepped on almost without top, collection.Rather than cheating video is in the highest playback volume
Under premise, user's interbehaviors such as the top of video is stepped on, collection can reach certain level.But cheating video is usually not
These behaviors, i.e. although the playback volume of cheating video is enhanced, but the most real user comes mutual.
The user's name of cheating video has certain rule, owing to the SEO modes using software automation now are entered more
Row name, therefore user is before uploaded videos, will not manually arrange user name.Only can simply rely on software according to certain rule
Rule generates user name.Common are: game_XXXXXX, QQYYYYYYYY, wherein X represents alphabetical or digital, and Y represents number
Word.
According to the above feature of cheating video, it is identified passing through manual sorting to cheating video, it is also possible to pass through
The These characteristics of cheating video is learnt by machine, thus draws the rule identifying cheating video.
Cheating user is the carrying platform of cheating video, according to the current attribute of user, it can be determined that whether it is cheating
User.Cheating user is accurately identified, significantly more efficient can suppress cheating video, especially for the work that will release
Fraud video, can suppress in advance.Feature extraction for user, it is also desirable to set up and the feature of contained video is being considered
On.According to the cheating SEO technology of user and the statistical analysis of video, find that cheating user has a characteristic that
The title of cheating user has certain rule, this point and the feature similarity of a lot of video of practising fraud.Owing to SEO is existing
In the modes using software automation, therefore user creates user, will not manually arrange user name more.Only can simply rely on soft
Part generates user name according to certain rule.Common are: game_XXXXXX, wherein X represents alphabetical or digital.
Owing to cheating user has special SEO instrument to improve video playback amount, the video playback amount pretending fraud user is led to
The highest.Can obtain based on statistics, the video playback amount of a domestic consumer is not over 100000, but cheating the broadcasting of user
High-volume the most up to ten million up to up to a million.
The number of videos of cheating user is all little, owing to SEO technology is provided convenience to user's establishment, therefore to improve
Video exposes chance, and cribber repeats to create user generally for similar video content.So video under each user
Number is the most few.At present, generally, the video number of cheating user is no more than 5.
The video title of cheating user usually contains substantial amounts of hot word, due to the probability of video of practising fraud in cheating user
The highest, the video title of the user that therefore practises fraud also has piled up substantial amounts of hot word.
The vermicelli number of cheating user is the lowest, and cheating user is due to video content quality, and the people of concern is the most few,
Even if under the biggest playback volume, vermicelli number does not still reach rational level.Typically, the non-cheating video of video website is used
Family, every 5000 broadcastings can be converted to a vermicelli, and the user that practises fraud then is typically not capable of such vermicelli conversion ratio.
In the present embodiment, according to the above feature of cheating user, being identified cheating user can be carefully and neatly done by people
Reason, it is also possible to the These characteristics of cheating user is learnt by machine, thus draw the rule identifying cheating user.
The present embodiment feature based on above-mentioned cheating video and the feature of cheating user, it is proposed that user identifies that cheating regards
Frequency and the system of cheating user, the system that the present embodiment proposes is responsible for practise fraud user and the identification of cheating video, and intervention line
Upper effect, comes into force.The basic framework of native system should be before not affecting video searching system or video recommendation system
Put and intervene.
It should be noted that the system of the present embodiment depends on the search of backstage log system and recommends business module, meeting
Update cycle timing according to daily record is identified computing.Owing to business system is the hugest, inevitably there is day in backstage
The nonsynchronous situation of will.Such as, the video of user comes into force the most on line, this video also already recorded in video daily record, but
Being not record in user journal, this is by unfavorable to the judgement of user.For this situation, can preferentially carry out cheating and regard
The identification of frequency.
It addition, uploading of cheating video is likely short than the daily record cycle with the cheating cycle.The such as daily record cycle is 3
My god, but the cheating cycle is 1 day.This situation can cause no matter how recognizer judges, all can have new cheating video or
Person user has an opportunity to expose.In view of the situation, can be in operation system near the module of front end (user), such as, in caching
Add judgment rule (that is, above-mentioned cheating video identification rule and cheating user's recognition rule), cheating video can be carried out
Judging in time, the feature of caching is the most in time, but can not undertake huge task amount.Therefore the rule added at this should
Logic is simple, it is easy to process.
Based on above-mentioned analysis, as in figure 2 it is shown, the system that the present embodiment provides specifically can include following ingredient: make
Fraud video identification module: include log acquisition module, computing module and data communication module.Wherein, log acquisition module is used for
Obtain the daily record data of video；Computing module is for automatically identifying whether video is cheating video, and its internal algorithm is for instruct in advance
The machine learning algorithm practiced；Data communication module is for being transferred to conversational traffic module the id of cheating video, and it is right to wait
Cheating video carries out fall power process.
Cheating subscriber identification module: include log acquisition module, computing module and data communication module.Log acquisition module
For obtaining the daily record data of user；Computing module is for automatically identifying whether user is cheating user, and its internal algorithm is pre-
The machine learning algorithm first trained；Data communication module is used for the id of cheating user to be transferred to conversational traffic module, etc.
Treat cheating video is carried out fall power process.
Fast regular processing module: simple by realizing logic, the decision logic that business understands, these decision logics are direct
Realize in the buffer, the quick intervention to final search or recommendation results can be supported.
The system that the present embodiment provides achieves the effect of the most anti-compacting of practising fraud of machine, but for emergency,
Remaining a need for input cheating video and cheating user id, based on this, the present embodiment additionally provides manual intervention framework,
Manual intervention framework needs to carry out quickly identifying timely to cheating video and user, can be placed on operation system and lean on
The module of front end (user), such as in caching.Manual intervention framework be typically required for special module be responsible for access user defeated
Entering, based on this, in the present embodiment, the framework of manual intervention module is as follows:
Manual intervention module: include inputting receiver module and data communication module.Input receiver module, generally by a use
The inputting interface realization that family is friendly, it allows user to be manually entered or receive cheating video and the cheating that other modules send over
The id of user, data communication module is responsible for the data received to be transferred to caching, is used for final video search or regards
Frequently recommendation results is quickly intervened.
In the present embodiment, basic system framework and manual intervention framework are generally combined and are come into force, just can be to cheating
Suppress, it may be assumed that use basic system framework in normal conditions, use manual intervention framework under emergency conditions.
In the present embodiment, fall power is being used to process at search engine the cheating video identified and cheating user,
Improve the ranking results in search and proposed algorithm so that these users and video are in very big inferior position, for mistake in sequence
The video of high playback volume and suspicious title carries out the process of secondary logic, it is ensured that exposing of normal video, meanwhile, monitors suspicious use
The video at family uploads behavior, contained video carries out early warning and intervention targetedly, and reminds this user, help it
Improve video quality；Shielding cheating video and the invalid broadcasting behavior of cheating user, obtain true playback volume, for being divided into system
Important role.
Embodiment 3
Present embodiments providing the device of a kind of anti-cheating video, this device can be the anti-of offer in above-described embodiment 2
Cheating video system an ingredient, or this device can include in above-described embodiment 2 provide anti-video system of practising fraud,
Fig. 3 is the structured flowchart of this device, as it is shown on figure 3, this device 30 includes following ingredient:
First acquisition module 31, for obtaining the daily record data of video；
First screening module 32, for using default cheating video identification rule to sieve the daily record data of video
Choosing, determines cheating video；
First fall power module 33, for reducing the searching order of cheating video and recommending sequence.
Wherein, the rule of the cheating video identification in the present embodiment specifically may include that the hot topic judging that video title comprises
Popular key word number is preset in whether meeting of key word, it is judged that whether video playback volume in preset time period meets is preset
Broadcasting time, it is judged that whether user's interbehavior that video obtains in preset time period is less than the second preset times, it is judged that regard
Whether the title of frequency meets first is preset rule；Based on this, above-mentioned first screening module 31 specifically for: by the daily record number of video
At least meet the video of in cheating video identification rule according to and be defined as video of practising fraud.
Further, above-mentioned, device 30 can also include:
Second screening module, for using the cheating video identification preset rule to sieve the daily record data of video
Choosing, after determining cheating video, obtains the daily record data of user, uses default cheating user's recognition rule day to user
Will data are screened, and determine cheating user；Second fall power module, for reducing the search row of the video that cheating user uploads
Sequence and recommended sequence.
Wherein, cheating user's recognition rule includes: judge whether the user's name in the daily record data of user meets second
Preset rule, it is judged that in the daily record data of user, whether the playback volume of video meets default broadcasting time, it is judged that the daily record of user
Whether the video number of the user in data is less than presetting video number, it is judged that the video of the user in the daily record data of user
Whether the number of the popular key word comprised in title meets is preset popular key word number, it is judged that user in user journal data
Vermicelli number whether less than presetting vermicelli number；Based on this, above-mentioned second screening module specifically for: by the daily record data of user
At least meet the user of in cheating user's recognition rule and be defined as the user that practises fraud.
Optionally, the device 30 in the present embodiment can also include: receiver module, regards for receiving the cheating of outside input
The title of frequency and/or the identity of cheating user；Sending module, for by the title of cheating video and/or cheating user
Identity is sent to video cache district, so that cheating video and cheating user are identified in video cache district, cheating regards
Frequently recognition rule and cheating user's recognition rule are pre-stored in video cache district.
The foregoing is only embodiments of the invention, be not limited to the present invention, for those skilled in the art
For Yuan, the present invention can have various modifications and variations.All within the spirit and principles in the present invention, any amendment of being made,
Equivalent, improvement etc., within should be included in scope of the presently claimed invention.
Claims (10)
1. the method for an anti-cheating video, it is characterised in that including:
Obtain the daily record data of video；
Use default cheating video identification rule that the daily record data of described video is screened, determine cheating video；
Reduce the searching order of described cheating video and recommend sequence.
Method the most according to claim 1, it is characterised in that described cheating video identification rule, including:
Judge that whether the meeting of popular key word that video title comprises presets popular key word number, it is judged that video is when default
Between playback volume in section whether meet and preset broadcasting time, it is judged that the mutual row of user that video obtains in described preset time period
For whether less than the second preset times, it is judged that whether the title of video meets first is preset rule；
Use described cheating video identification rule that the daily record data of described video is screened, determine cheating video, including:
It is defined as cheating by the daily record data of described video at least meets the video of in described cheating video identification rule
Video.
Method the most according to claim 1, it is characterised in that described method also includes:
Using the cheating video identification preset rule that the daily record data of described video is screened, determine practise fraud video it
After, obtain the daily record data of user, use default cheating user's recognition rule that the daily record data of described user is screened,
Determine cheating user；
Reduce the searching order of the video that described cheating user uploads and recommended sequence.
Method the most according to claim 3, it is characterised in that described cheating user's recognition rule includes:
Judge whether the user's name in the daily record data of described user meets second and preset rule, it is judged that the daily record of described user
In data, whether the playback volume of video meets default broadcasting time, it is judged that the video counts of the user in the daily record data of described user
Whether mesh is less than presetting video number, it is judged that the hot topic comprised in the title of the video of the user in the daily record data of described user
Whether the number of key word meets is preset popular key word number, it is judged that in described user journal data, whether the vermicelli number of user
Less than presetting vermicelli number；
The described daily record data obtaining user, uses default cheating user's recognition rule to carry out the daily record data of described user
Screening, determines cheating user, including:
It is defined as cheating by the daily record data of described user at least meets the user of in described cheating user's recognition rule
User.
5. according to the method according to any one of claim 1-4, it is characterised in that described method also includes:
Receive title and/or the identity of cheating user of the cheating video of outside input, by the title of described cheating video
And/or the identity of cheating user is sent to video cache district, so that cheating video and cheating user delay at described video
Depositing in district identified, described cheating video identification is regular and described cheating user's recognition rule is pre-stored in described video cache district
In.
6. the device of an anti-cheating video, it is characterised in that including:
First acquisition module, for obtaining the daily record data of video；
First screening module, for using default cheating video identification rule that the daily record data of described video is screened,
Determine cheating video；
First fall power module, for reducing the searching order of described cheating video and recommending sequence.
Device the most according to claim 6, it is characterised in that described cheating video identification rule, including:
Judge that whether the meeting of popular key word that video title comprises presets popular key word number, it is judged that video is when default
Between playback volume in section whether meet and preset broadcasting time, it is judged that the mutual row of user that video obtains in described preset time period
For whether less than the second preset times, it is judged that whether the title of video meets first is preset rule；
Described first screening module specifically for:
It is defined as cheating by the daily record data of described video at least meets the video of in described cheating video identification rule
Video.
Device the most according to claim 6, it is characterised in that described device also includes:
Second screening module, for using the cheating video identification preset rule to sieve the daily record data of described video
Choosing, after determining cheating video, obtains the daily record data of user, uses default cheating user's recognition rule to described user
Daily record data screen, determine cheating user；
Second fall power module, for reducing the searching order of the video that described cheating user uploads and recommended sequence.
Device the most according to claim 8, it is characterised in that described cheating user's recognition rule includes:
Judge whether the user's name in the daily record data of described user meets second and preset rule, it is judged that the daily record of described user
In data, whether the playback volume of video meets default broadcasting time, it is judged that the video counts of the user in the daily record data of described user
Whether mesh is less than presetting video number, it is judged that the hot topic comprised in the title of the video of the user in the daily record data of described user
Whether the number of key word meets is preset popular key word number, it is judged that in described user journal data, whether the vermicelli number of user
Less than presetting vermicelli number；
Described second screening module specifically for:
It is defined as cheating by the daily record data of described user at least meets the user of in described cheating user's recognition rule
User.
10. according to the device according to any one of claim 6-9, it is characterised in that described device also includes:
Receiver module, for receiving title and/or the identity of cheating user of the cheating video of outside input；
Sending module, for the identity of the title of described cheating video and/or cheating user is sent to video cache district,
So that cheating video and cheating user are identified in described video cache district, described cheating video identification is regular and described
Cheating user's recognition rule is pre-stored in described video cache district.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610575419.9A CN106294536A (en) | 2016-07-20 | 2016-07-20 | A kind of method and device of anti-cheating video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610575419.9A CN106294536A (en) | 2016-07-20 | 2016-07-20 | A kind of method and device of anti-cheating video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106294536A true CN106294536A (en) | 2017-01-04 |
Family
ID=57652712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610575419.9A Pending CN106294536A (en) | 2016-07-20 | 2016-07-20 | A kind of method and device of anti-cheating video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106294536A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107529093A (en) * | 2017-09-05 | 2017-12-29 | 北京奇艺世纪科技有限公司 | A kind of detection method and system of video file playback volume |
| CN108595513A (en) * | 2018-03-23 | 2018-09-28 | 北京奇艺世纪科技有限公司 | A kind of video search cheating processing method and processing device |
| CN108764021A (en) * | 2018-04-04 | 2018-11-06 | 北京奇艺世纪科技有限公司 | A kind of cheating video frequency identifying method and device |
| CN110290400A (en) * | 2019-07-29 | 2019-09-27 | 北京奇艺世纪科技有限公司 | The recognition methods of suspicious brush amount video, true playback volume predictor method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101777053A (en) * | 2009-01-08 | 2010-07-14 | 北京搜狗科技发展有限公司 | Method and system for identifying cheating webpages |
| CN103294686A (en) * | 2012-02-24 | 2013-09-11 | 腾讯科技（深圳）有限公司 | Method and system for identifying webpage spam user and spam webpage |
| CN103390027A (en) * | 2013-06-25 | 2013-11-13 | 亿赞普(北京)科技有限公司 | Internet advertisement anti-spamming method and system |
| CN103593791A (en) * | 2013-11-07 | 2014-02-19 | 广州优蜜信息科技有限公司 | Mobile advertisement putting method and system |
| CN103714057A (en) * | 2012-09-28 | 2014-04-09 | 北京亿赞普网络技术有限公司 | Real-time monitoring method and device for online web information |
| CN105183897A (en) * | 2015-09-29 | 2015-12-23 | 北京奇艺世纪科技有限公司 | Method and system for ranking video retrieval |
| CN105677869A (en) * | 2016-01-06 | 2016-06-15 | 广州神马移动信息科技有限公司 | Multidimensional search log anti-cheating method, system and computing equipment |
-
2016
- 2016-07-20 CN CN201610575419.9A patent/CN106294536A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101777053A (en) * | 2009-01-08 | 2010-07-14 | 北京搜狗科技发展有限公司 | Method and system for identifying cheating webpages |
| CN103294686A (en) * | 2012-02-24 | 2013-09-11 | 腾讯科技（深圳）有限公司 | Method and system for identifying webpage spam user and spam webpage |
| CN103714057A (en) * | 2012-09-28 | 2014-04-09 | 北京亿赞普网络技术有限公司 | Real-time monitoring method and device for online web information |
| CN103390027A (en) * | 2013-06-25 | 2013-11-13 | 亿赞普(北京)科技有限公司 | Internet advertisement anti-spamming method and system |
| CN103593791A (en) * | 2013-11-07 | 2014-02-19 | 广州优蜜信息科技有限公司 | Mobile advertisement putting method and system |
| CN105183897A (en) * | 2015-09-29 | 2015-12-23 | 北京奇艺世纪科技有限公司 | Method and system for ranking video retrieval |
| CN105677869A (en) * | 2016-01-06 | 2016-06-15 | 广州神马移动信息科技有限公司 | Multidimensional search log anti-cheating method, system and computing equipment |
Non-Patent Citations (1)
| Title |
|---|
| 乔辉、曹雨: "常见的违规SEO", 《网络营销》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107529093A (en) * | 2017-09-05 | 2017-12-29 | 北京奇艺世纪科技有限公司 | A kind of detection method and system of video file playback volume |
| CN107529093B (en) * | 2017-09-05 | 2020-05-22 | 北京奇艺世纪科技有限公司 | Method and system for detecting playing amount of video file |
| CN108595513A (en) * | 2018-03-23 | 2018-09-28 | 北京奇艺世纪科技有限公司 | A kind of video search cheating processing method and processing device |
| CN108764021A (en) * | 2018-04-04 | 2018-11-06 | 北京奇艺世纪科技有限公司 | A kind of cheating video frequency identifying method and device |
| CN108764021B (en) * | 2018-04-04 | 2021-03-26 | 北京奇艺世纪科技有限公司 | Cheating video identification method and device |
| CN110290400A (en) * | 2019-07-29 | 2019-09-27 | 北京奇艺世纪科技有限公司 | The recognition methods of suspicious brush amount video, true playback volume predictor method and device |
| CN110290400B (en) * | 2019-07-29 | 2022-06-03 | 北京奇艺世纪科技有限公司 | Suspicious brushing amount video identification method, real playing amount estimation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109327714B (en) | Method and system for supplementing live broadcast | |
| US20200372089A1 (en) | Content sharing management | |
| CN110996116B (en) | Anchor information pushing method and device, computer equipment and storage medium | |
| US10664872B2 (en) | Systems and methods for generating network intelligence through real-time analytics | |
| Ghosh et al. | On sampling the wisdom of crowds: Random vs. expert sampling of the twitter stream | |
| CN104063521B (en) | Searching service implementation method and device | |
| CN109684513B (en) | Low-quality video identification method and device | |
| CN106294536A (en) | A kind of method and device of anti-cheating video | |
| CN103686375B (en) | Video sharing method and device | |
| WO2017096832A1 (en) | Media data recommendation method and server | |
| US20170188102A1 (en) | Method and electronic device for video content recommendation | |
| CN104850550B (en) | A kind of sort method and device of prompting message | |
| US8554910B2 (en) | Method and device for pushing data | |
| CN109769128A (en) | Video recommendation method, video recommendations device and computer readable storage medium | |
| CN103838814B (en) | Method for dynamically displaying contacts diagram relationship | |
| CN102750299B (en) | A kind of method of network information convergence | |
| EP3873065B1 (en) | Content recommendation method, mobile terminal, and server | |
| CN104133820A (en) | Content recommending method and content recommending device | |
| CN102033929A (en) | Hot video set displaying method and device | |
| CN102855256A (en) | Method, device and equipment for determining evaluation information of websites | |
| CN102750346A (en) | Method, system and terminal device for recommending software | |
| US8983942B2 (en) | Method and apparatus for providing time machine service based on social network service | |
| CN107368549B (en) | Personalized government affair service recommendation method and system based on deep learning | |
| US20070016642A1 (en) | Automated moderation of discussion lists | |
| CN111984787A (en) | Public opinion hotspot obtaining method and system based on internet data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100080 A 5 C, block A, China International Steel Plaza, 8 Haidian Avenue, Haidian District, Beijing. Applicant after: Youku network technology (Beijing) Co., Ltd. Address before: 100080 A 5 C, block A, China International Steel Plaza, 8 Haidian Avenue, Haidian District, Beijing. Applicant before: 1Verge Inc. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170104 |