CN103491205B - The method for pushing of a kind of correlated resources address based on video search and device - Google Patents
The method for pushing of a kind of correlated resources address based on video search and device Download PDFInfo
- Publication number
- CN103491205B CN103491205B CN201310462461.6A CN201310462461A CN103491205B CN 103491205 B CN103491205 B CN 103491205B CN 201310462461 A CN201310462461 A CN 201310462461A CN 103491205 B CN103491205 B CN 103491205B
- Authority
- CN
- China
- Prior art keywords
- participle
- resource data
- video resource
- video
- text message
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000002596 correlated effect Effects 0.000 title claims abstract description 13
- 239000000284 extract Substances 0.000 claims description 70
- 230000000875 corresponding effect Effects 0.000 claims description 39
- 238000013507 mapping Methods 0.000 claims description 11
- 150000001875 compounds Chemical class 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 7
- 238000010168 coupling process Methods 0.000 claims description 7
- 238000005859 coupling reaction Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 abstract description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 26
- 230000011218 segmentation Effects 0.000 description 7
- 238000002372 labelling Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000011109 contamination Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000032696 parturition Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Abstract
The invention discloses the method for pushing of a kind of correlated resources address based on video search, including: when receiving loading or the playing request of the first video resource data, obtain this text message of feature of described first video resource data；It is one or more first participle by described feature Ben Wenben information MAP；Search be higher than predetermined threshold value with the co-occurrence rate of the one or more first participle associate the second participle；Described co-occurrence rate is current one or more first participle and the second participle common probability occurred in same video resource data；Obtain the network linking address of the second video resource data mated with the one or more first participle and described association the second participle；Push the network linking address of described second video resource data.The present invention realizes the degree of depth and excavates the high-quality resource in video library, improves the efficiency of excavating resource；Additionally, concordance list constantly can expand along with the constantly accumulation of internet video content, be conducive to expanding recall rate.
Description
Technical field
The present invention relates to the technical field of the Internet, be specifically related to a kind of association based on video search money
The method for pushing of source address and the pusher of a kind of correlated resources address based on video search.
Background technology
Video search engine is a kind of vertical search technology being different from comprehensive search.Video search draws
Hold up the result of the video class captured in the Internet and set up index, owing to it can provide to searchers
Video class result purely, such that it is able to be greatly saved netizen to find the time of video.
Relevant statistics according to video search shows, entertains, plays, video display, news, dynamic
The video of the type such as unrestrained is the major search object of user.This shows that user is for video search itself
There is the character of general demand.User often without the strongest purposiveness, Search Results not " non-that
Can not ", but with certain autgmentability, as long as target is in the category that user is liked.Cause
This, often outside Search Results, user being carried out associated recommendation is.
But, existing video search engine is made in terms of associated recommendation and is disadvantageous in that part regards
Frequently search engine does not has associated recommendation, and the video search engine having associated recommendation is according to user's
Search history data, obtained the plain mode such as association system by manual sorting and realize recommending.This
Commending system is based on user's existing search custom, and recall rate is relatively low, additionally, due to the search of user
Scope typically can be more much smaller than the scope of resource in existing the Internet, it is impossible to fully excavates the Internet
In high-quality video.
Another kind of search recommendation method is dependent on manual sorting and goes out a resource associations system or from other
Knowledge hierarchy obtains such system, is applied in commending system.Such as search at certain search engine
Rope " square dance " time, the recommendation word of " social dancing ", " belly dance ", " fitness exercise " etc. can be obtained, search
The recommendation word of " passing through live wire ", " World of Warcraft " etc. can be obtained time " dota ", but this system is recalled
Rate is relatively low, typically can not provide recommendation in the search of long-tail.
Summary of the invention
In view of the above problems, it is proposed that the present invention is to provide one to overcome the problems referred to above or at least portion
Divide method for pushing and the phase of a kind of based on video search the correlated resources address of ground solution the problems referred to above
The pusher of a kind of based on video search the correlated resources address answered.
According to one aspect of the present invention, it is provided that a kind of correlated resources address based on video search
Method for pushing, including:
When receiving loading or the playing request of the first video resource data, obtain described first video money
This text message of feature of source data；
It is one or more first participle by described feature Ben Wenben information MAP；
Search be higher than predetermined threshold value with the co-occurrence rate of the one or more first participle associate second point
Word；Described co-occurrence rate is that current one or more first participle and the second participle are in same video resource data
In the common probability occurred；
Obtain the second video mated with the one or more first participle and described association the second participle
The network linking address of resource data；
Push the network linking address of described second video resource data.
Alternatively, described when receiving loading or the playing request of the first video resource data, obtain institute
The step of this text message of feature stating the first video resource data includes:
When receiving the playing request of the first video data, receive described the first of present terminal transmission and regard
Frequently this text message of feature of resource data；
Or,
When receiving the first video data load request, extract local preset described video resource data
This text message of feature.
Alternatively, described by step that described feature Ben Wenben information MAP is one or more first participle
Suddenly include:
Extract the participle that described this text message of feature is mapped；
Or,
When this text message of feature received is compound word, described this text message of feature is split
For the sub-word of multiple search；Extract multiple participles that the sub-word of the plurality of search is mapped.
Alternatively, described lookup and the co-occurrence rate of the one or more first participle are higher than predetermined threshold value
The step of association the second participle include:
When described this text message of feature is mapped as a first participle, extract the described first participle
Corresponding preset concordance list；Wherein, described concordance list includes the video money belonging to the described first participle
The information of source data, and, all participles in described video resource data；Described video resource
All participles in data are by capturing video resource data, extracting described video resource data
Feature text message, carries out participle generation to described feature text message；
Calculate the described first participle and the co-occurrence rate of each the second participle, described co-occurrence in described concordance list
Rate is the number of times and video resource number in described concordance list that in described concordance list, each second participle occurs
According to information sum ratio；Wherein, the institute during described second participle is described video resource data
There is the participle in addition to the described first participle in participle；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
Alternatively, described lookup and the co-occurrence rate of the one or more first participle are higher than predetermined threshold value
The step of association the second participle include:
When described this text message of feature is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that the first participle is corresponding；Each concordance list includes belonging to the described first participle
The information of video resource data, and, all participles in described video resource data；Described
All participles in video resource data are by capturing video resource data, extract described video money
The feature text message of source data, carries out participle generation to described feature text message；
Extract the second participle jointly occurred with the plurality of first participle as candidate's participle；Wherein,
Described second participle be in all participles in described video resource data in addition to the described first participle
Participle；
The co-occurrence rate of the described first participle and described candidate's participle, institute is calculated respectively in each concordance list
Stating co-occurrence rate is the number of times and video resource in described concordance list that in described concordance list, candidate's participle occurs
The ratio of the information sum of data；
It is respectively the plurality of first participle and the co-occurrence rate of described candidate's participle and configures corresponding multiple
Weight；
Calculate the meansigma methods of multiple co-occurrence rate being configured with weight respectively, as the plurality of first participle
Co-occurrence rate with described candidate's participle；
Extract described co-occurrence rate candidate's participle higher than predetermined threshold value as associating the second participle.
Alternatively, described lookup and the co-occurrence rate of the one or more first participle are higher than predetermined threshold value
The step of association the second participle include:
When described this text message of feature is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that the first participle is corresponding；Wherein, each concordance list includes described first point
The information of the video resource data belonging to word, and, all participles in described video resource data；
All participles in described video resource data are by capturing video resource data, regard described in extraction
Frequently the feature text message of resource data, carries out participle generation to described feature text message；
Main participle, described main participle are the information of video resource data to use the plurality of concordance list to determine
The first participle that total most concordance list is corresponding；
Calculate the co-occurrence rate of each the second participle in the concordance list that described main participle is corresponding, described same
The number of times that during now rate is described concordance list, each second participle occurs and video resource in described concordance list
The ratio of the information sum of data；Wherein, during described second participle is described video resource data
Participle in addition to the described first participle in all participles；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
Alternatively, described feature text message includes that video title, Video Key word and/or video are retouched
State.
Alternatively, described acquisition is mated with the one or more first participle and described association the second participle
The step of network linking address of the second video resource data include:
Obtain described main participle and described association the second participle the lattice chain of the second video resource data
Ground connection location.
According to a further aspect in the invention, it is provided that a kind of correlated resources address based on video search
Pusher, including:
Feature text message acquisition module, is suitable to receiving loading or the broadcasting of the first video resource data
During request, obtain this text message of feature of described first video resource data；
First participle mapping block, being suitable to described feature Ben Wenben information MAP is one or more first
Participle；
Module searched in second participle, is suitable to search the co-occurrence rate with the one or more first participle and is higher than
Association second participle of predetermined threshold value；Described co-occurrence rate is current one or more first participle and second point
Word is the common probability occurred in same video resource data；
Network link address acquisition module, is suitable to obtain and the one or more first participle and described pass
Join the network linking address of the second video resource data of the second participle coupling；
Network link address pushing module, is suitable to push the lattice chain ground connection of described second video resource data
Location.
Alternatively, described feature text message acquisition module is further adapted for:
When receiving the playing request of the first video data, receive described the first of present terminal transmission and regard
Frequently this text message of feature of resource data；
Or,
When receiving the first video data load request, extract local preset described video resource data
This text message of feature.
Alternatively, described first participle mapping block is further adapted for:
Extract the participle that described this text message of feature is mapped；
Or,
When this text message of feature received is compound word, described this text message of feature is split
For the sub-word of multiple search；Extract multiple participles that the sub-word of the plurality of search is mapped.
Alternatively, described second participle lookup module is further adapted for:
When described this text message of feature is mapped as a first participle, extract the described first participle
Corresponding preset concordance list；Wherein, described concordance list includes the video money belonging to the described first participle
The information of source data, and, all participles in described video resource data；Described video resource
All participles in data are by capturing video resource data, extracting described video resource data
Feature text message, carries out participle generation to described feature text message；
Calculate the described first participle and the co-occurrence rate of each the second participle, described co-occurrence in described concordance list
Rate is the number of times and video resource number in described concordance list that in described concordance list, each second participle occurs
According to information sum ratio；Wherein, the institute during described second participle is described video resource data
There is the participle in addition to the described first participle in participle；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
Alternatively, described second participle lookup module is further adapted for:
When described this text message of feature is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that the first participle is corresponding；Each concordance list includes belonging to the described first participle
The information of video resource data, and, all participles in described video resource data；Described
All participles in video resource data are by capturing video resource data, extract described video money
The feature text message of source data, carries out participle generation to described feature text message；
Extract the second participle jointly occurred with the plurality of first participle as candidate's participle；Wherein,
Described second participle be in all participles in described video resource data in addition to the described first participle
Participle；
The co-occurrence rate of the described first participle and described candidate's participle, institute is calculated respectively in each concordance list
Stating co-occurrence rate is the number of times and video resource in described concordance list that in described concordance list, candidate's participle occurs
The ratio of the information sum of data；
It is respectively the plurality of first participle and the co-occurrence rate of described candidate's participle and configures corresponding multiple
Weight；
Calculate the meansigma methods of multiple co-occurrence rate being configured with weight respectively, as the plurality of first participle
Co-occurrence rate with described candidate's participle；
Extract described co-occurrence rate candidate's participle higher than predetermined threshold value as associating the second participle.
Alternatively, described second participle lookup module is further adapted for:
When described this text message of feature is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that the first participle is corresponding；Wherein, each concordance list includes described first point
The information of the video resource data belonging to word, and, all participles in described video resource data；
All participles in described video resource data are by capturing video resource data, regard described in extraction
Frequently the feature text message of resource data, carries out participle generation to described feature text message；
Main participle, described main participle are the information of video resource data to use the plurality of concordance list to determine
The first participle that total most concordance list is corresponding；
Calculate the co-occurrence rate of each the second participle in the concordance list that described main participle is corresponding, described same
The number of times that during now rate is described concordance list, each second participle occurs and video resource in described concordance list
The ratio of the information sum of data；Wherein, during described second participle is described video resource data
Participle in addition to the described first participle in all participles；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
Alternatively, described feature text message includes that video title, Video Key word and/or video are retouched
State.
Alternatively, described network link address acquisition module is further adapted for:
Obtain the network linking of the second video resource data of described main participle and described association the second participle
Address.
The present invention can push according to existing content of having issued, and makes search engine break away from and searches user
The dependence of rope custom, although that the fewer user of having searched for but video library collects the most more relevant
The video resource data-pushing of resource out, thus realizes the degree of depth and excavates the high-quality resource in video library,
Improve the efficiency of excavating resource；Additionally, concordance list can constantly amassing along with internet video content
Tiring out and constantly expand, content quantity and range that each big video station is produced can be considerably beyond users
The word number searched for, is conducive to expanding recall rate.
The present invention is by obtaining the second video resource data of the coupling of the first participle and the second participle
Network link address, user can directly carry out the acquisition of video data resource, make based on this address
User's simple search can obtain more result, it is not necessary to repeatedly submits search to, thus alleviates visit
Ask the burden of server, decrease taking of Internet resources, and improve Consumer's Experience.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the present invention
Technological means, and can be practiced according to the content of description, and the present invention's be upper in order to allow
State and can become apparent with other objects, features and advantages, below especially exemplified by the concrete reality of the present invention
Execute mode.
Accompanying drawing explanation
By reading the detailed description of hereafter preferred implementation, various other advantage and benefit pair
Will be clear from understanding in those of ordinary skill in the art.Accompanying drawing is only used for illustrating preferred implementation
Purpose, and be not considered as limitation of the present invention.And in whole accompanying drawing, with identical
Reference marks represents identical parts.In the accompanying drawings:
Fig. 1 shows a kind of correlated resources based on video search
The flow chart of steps of the method for pushing embodiment of address；And
Fig. 2 shows a kind of correlated resources based on video search
The structured flowchart of the pusher embodiment of address.
Detailed description of the invention
It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although in accompanying drawing
Show the exemplary embodiment of the disclosure, it being understood, however, that may be realized in various forms this
Disclose and should not limited by embodiments set forth here.On the contrary, it is provided that these embodiments be in order to
The disclosure can be best understood from, and complete for the scope of the present disclosure can be conveyed to ability
The technical staff in territory.
With reference to Fig. 1, it is shown that a kind of association based on video search
The flow chart of steps of the propelling movement embodiment of resource address, specifically may include steps of:
Step 101, when receiving loading or the playing request of the first video resource data, obtains described
This text message of feature of first video resource data；
It should be noted that the first video resource data may be located on terminal unit, it is also possible to position
On network, this text message of feature can be the information entrained by video resource data.
In one preferred embodiment of the invention, described step 101 specifically can include following sub-step:
Sub-step S11, when receiving the playing request of the first video data, receives present terminal and sends
This text messages of feature of described first video resource data；
When the first video resource data are positioned on terminal unit, first can be extracted by terminal unit and regard
Frequently the feature text message of resource data, then uploads to the server side of correspondence.
Or,
Sub-step S12, when receiving the first video data load request, extracts local preset described
This text message of feature of video resource data.
When the first video resource data are positioned on network, the first video money can be extracted by server side
The feature text message of source data.
In one preferred embodiment of the invention, described feature text message can include video mark
Topic, Video Key word and/or video presentation.
Such as, one section of entitled " change Venice, over thousands of car water logging throwing after [clapping visitor] Dongguan heavy rain
XX net play online by anchor, and video high definition is watched online " video resource data in, its feature
Text message can be such that
Video title (Title): becoming Venice after [clapping visitor] Dongguan heavy rain, over thousands of car water logging is cast anchor
Online broadcasting XX net, video high definition is watched online；
Video Key word (Keywords): YY reporter's living information Dongguan water logging；
Video presentation (Description) a: heavy rain of yesterday morning, allows some areas, Dongguan
Neighbour feels as having come Venice moment.Dolly in traveling suffers that in heavy rain water logging is cast anchor,
Some neighbour Jia Zhongyeshi as vast expanse of water.
In actual applications, this text message of feature can be word, i.e. includes that a semanteme is independent
Word, the such as mid-autumn, the Dragon Boat Festival, National Day etc.；This text message of feature can also be compound word,
I.e. include two or more semantic independent words, such as moon cake for the Mid-autumn Festival, Dragon Boat Festival rice tamale, National Day
Xizang road bridge etc..It is said that in general, the video resource data in terminal unit often only have video
Title (Title), the such as movie name such as " iron and steel is chivalrous ", " Spider-Man "；Video in a network
Resource data frequently includes video title (Title), Video Key word (Keywords) and video and retouches
That states in (Description) is one or more.
Step 102, is one or more first participle by described feature Ben Wenben information MAP；
It should be noted that mapped participle can pre-set, may be used for calculating not
With the co-occurrence rate between participle.
The rule mapped can also be pre-set one or more, can include that removing video searches
The dirty word of rope character, qualifier, auxiliary words of mood, wide in range word etc. are without the word of practical significance；Permissible
Including setting stop-word, i.e. some common words, the standard stopped during for splitting phrase, such as,
I, you etc.；The correspondence of incidence relation can also be included, by the multiple expression correspondence of same thing
Express for one, such as, August 15, the Mid-autumn Festival, moon cake joint etc. are associated as the mid-autumn；All right
Including other mapping rulers, this is not any limitation as by the embodiment of the present invention.
English, in units of word, is to separate by space between word and word, and Chinese is with word as list
Position, in sentence, all of word links up and could describe a meaning.Such as, english sentence I am a
Student, with Chinese be then: " I is a student ".Computer can be known simply by space very much
Student is a word, but can not be readily understood that " learning ", " giving birth to " two words the most just represent
One word.The Chinese character sequence of Chinese is cut into significant word, it is simply that Chinese word segmentation.Such as,
I is a student, and the result of participle is: I, be, one, student.
Some conventional segmenting methods are described below:
1, segmenting method based on string matching: refer to the Chinese being analysed to according to certain strategy
Entry in the machine dictionary that word string is preset with mates, if finding certain word in dictionary
Symbol string, then the match is successful (identifying a word).Actually used Words partition system, is all machinery
Participle as the section of departure at the beginning of one, also needs by utilizing other linguistic information various to carry further
The accuracy rate of high cutting.
2, feature based scanning or the segmenting method of mark cutting: refer to preferential in character string to be analyzed
Middle identification and be syncopated as some words with obvious characteristic, using these words as breakpoint, can be by former word
Symbol string is divided into less string to enter mechanical Chinese word segmentation again, thus reduces the error rate of coupling；Or will divide
Word and part-of-speech tagging combine, and utilize abundant grammatical category information to provide help to participle decision-making, and
And the most in turn word segmentation result tested in annotation process, adjust, thus improve cutting
Accuracy rate.
3, based on understand segmenting method: refer to by allow computer mould personification distich understanding,
Reach to identify the effect of word.Its basic thought carries out syntax, semantic analysis exactly while participle,
Utilize syntactic information and semantic information to process Ambiguity.It generally includes three parts: participle
Subsystem, syntactic-semantic subsystem, master control part.Under the coordination of master control part, participle subsystem
System can obtain the syntax and semantic information about word, sentence etc. and judge segmentation ambiguity,
I.e. it simulates people's understanding process to sentence.This segmenting method needs to use substantial amounts of language to know
Know and information.
4, segmenting method based on statistics: refer to, due to word co-occurrence adjacent with word in Chinese information
Frequency or probability can preferably reflect into the credibility of word, it is possible to co-occurrence adjacent in language material
The frequency of each combinatorics on words add up, calculate their information that appears alternatively, and calculate two
The adjacent co-occurrence probabilities of Chinese character X, Y.The information of appearing alternatively can embody the tight of marriage relation between Chinese character
Degree.When tightness degree is higher than some threshold value, just it is believed that this word group may constitute one
Word.Word group frequency in language material only need to be added up by this method, it is not necessary to cutting dictionary.
In one preferred embodiment of the invention, described step 102 specifically can include following son
Step:
Sub-step S21, extracts the participle that described this text message of feature is mapped；
It is the situation of word for this text message of feature, can be direct according to default mapping ruler
Extract the participle of its correspondence.Such as, this text message of feature is " Mid-autumn Festival ", " my Mid-autumn Festival "
Or " Mid-autumn Festival " etc., the first participle of mapping can be " mid-autumn ".Certainly, feature is originally
The first participle that text message can also map with it is same word, such as this text message of feature
For " mid-autumn ", the first participle of mapping can also " mid-autumn ".
Or,
Sub-step S22, when this text message of feature received is compound word, by described feature originally
Text message is split as the sub-word of multiple search；
Sub-step S23, extracts multiple participles that the sub-word of the plurality of search is mapped.
It is the situation of compound word for this text message of feature, can enter according to default mapping ruler
Row participle, obtains searching for sub-word, extracts the most respectively and search for the participle that sub-word is corresponding.Such as, connect
This text message of feature received is " moon cake in the Mid-autumn Festival ", can be split as " Mid-autumn Festival " and
" moon cake " two sub-words of search, then " Mid-autumn Festival " will be mapped as " mid-autumn ", by " moon cake "
It is mapped as " moon cake ", obtains " mid-autumn " and " moon cake " two first participles.
Step 103, searches the pass higher than predetermined threshold value of the co-occurrence rate with the one or more first participle
Join the second participle；
Described co-occurrence rate is that current one or more first participle and the second participle are at same video resource number
The common probability occurred according to；
Specifically, co-occurrence rate can be current one or more participle and the second participle regards same
Frequently the common probability occurred in the feature text message of resource data, specifically can include one first
Participle and the co-occurrence rate of the second participle, multiple participles and the co-occurrence rate of the second participle.
It should be noted that the second participle can be in the participle all preset, except the first participle
Participle in addition.Associating the second participle can be that the co-occurrence rate with the first participle is higher than predetermined threshold value
Second participle.
In actual applications, video resource data can include feature text message, this feature text
Information may be used for recording the relevant information of these video resource data, it is also possible to is used for extracting participle.
In one preferred embodiment of the invention, described step 103 specifically can include following son
Step:
Sub-step S31, when described this text message of feature is mapped as a first participle, extracts
The preset concordance list that the described first participle is corresponding；Wherein, described concordance list includes the described first participle
The information of affiliated video resource data, and, all participles in described video resource data；
All participles in described video resource data are by capturing video resource data, regard described in extraction
Frequently the feature text message of resource data, carries out participle generation to described feature text message；
In implementing, search engine can be used in advance to pass through each website platform of crawler capturing
On video resource data, then set up index database: extract the feature text envelope of video resource data
Breath carries out word segmentation processing, and sets up the concordance list that each participle is corresponding, can store in this concordance list
The information of video resource data (can be ID, internal address, outer net address etc. video labeling,
Can also be a record being made up of current participle and other participles), in video resource data
All participles (include the first participle and the second participle in addition to the first participle).
In one preferred embodiment of the invention, described feature text message can include video mark
Topic, Video Key word and/or video presentation.
Such as, the concordance list in " mid-autumn " can be such that
Wherein, the first participle is " mid-autumn ", and the information of video resource data includes video labeling.When
So, the information of video resource data can not also include video labeling, and the only first participle and
The formed record of two participles (second participle of i.e. every a line is as a record).
Certainly, above-mentioned concordance list is intended only as example, when implementing the embodiment of the present invention, and Ke Yigen
Arranging other concordance lists according to practical situation, this is not any limitation as by the embodiment of the present invention.It addition, remove
Outside above-mentioned concordance list, those skilled in the art can also use other concordance lists according to actual needs,
This is not any limitation as by the embodiment of the present invention.
It should be noted that cycle or variable interval the video resource number on each platform can be captured
According to, then update index and build storehouse, i.e. update each concordance list.
Sub-step S32, calculates the described first participle and the co-occurrence of each the second participle in described concordance list
Rate, described co-occurrence rate is the number of times and described concordance list that in described concordance list, each second participle occurs
The ratio of the information sum of middle video resource data；Wherein, described second participle is described video money
Participle in addition to the described first participle in all participles in source data；
The number of times video data data affiliated with it occurred due to each second participle in concordance list
Quantity is the same, and co-occurrence rate can also be expressed as in described concordance list each video belonging to the second participle
The quantity of data and the ratio of the information sum of video resource data in described concordance list.
Such as, the letter of a total of 100 video resource data in the concordance list of participle " square dance "
Breath, the information of a total of 200 video resource data in the concordance list of participle " Soldiers Brother " is " wide
Dance " and " Soldiers Brother " simultaneously appear in the information of the video resource data in the two concordance list
Totally 10, then, for " square dance ", " square dance " with the co-occurrence rate of " Soldiers Brother " is
10/100=10%, and for " Soldiers Brother ", the co-occurrence rate of " Soldiers Brother " and " square dance "
For 10/200=5%.
Sub-step S33, extracts the described co-occurrence rate the second participle higher than predetermined threshold value as association second
Participle.
In implementing, predetermined threshold value can be set according to practical situation by those skilled in the art
, this is not any limitation as by the embodiment of the present invention.The association second extracted in the embodiment of the present invention
Participle can be empty, it is also possible to for one or more.
In one preferred embodiment of the invention, described step 103 specifically can include following son
Step:
Sub-step S41, when described this text message of feature is mapped as multiple first participle, respectively
Extract the multiple preset concordance list that the plurality of first participle is corresponding；Each concordance list includes described
The information of the video resource data belonging to the first participle, and, the institute in described video resource data
There is participle；All participles in described video resource data are by capturing video resource data, carrying
Take the feature text message of described video resource data, described feature text message is carried out participle raw
Become；
In implementing, search engine can be used in advance to pass through on each platform of crawler capturing
Video resource data, then set up index and build storehouse: extract the feature text message of video resource data
Carry out word segmentation processing, and set up the concordance list that each participle is corresponding, this concordance list can store and regard
Frequently the information of resource data (can be ID, internal address, outer net address etc. video labeling, also
Can be a record being made up of current participle and other participles), institute in video resource data
There is participle (including the first participle and the second participle in addition to the first participle).
In one preferred embodiment of the invention, described feature text message can include video mark
Topic, Video Key word and/or video presentation.
Sub-step S42, extracts the second participle jointly occurred with the plurality of first participle as candidate
Participle；Wherein, except described in all participles during described second participle is described video resource data
Participle beyond the first participle；
Specifically, currently there is multiple first participle, i.e. have the concordance list that multiple quantity is corresponding, wait
Selecting participle to need in each concordance list to occur, i.e. candidate's participle is respectively with current each first participle all
Common occur in same concordance list.
Sub-step S43, calculates the described first participle and described candidate's participle respectively in each concordance list
Co-occurrence rate, described co-occurrence rate is number of times and the described index that in described concordance list, candidate's participle occurs
The ratio of the information sum of video resource data in table；
For example, it is possible to this text message of feature " moon cake in the Mid-autumn Festival " is mapped as the first participle " in
Autumn " and " moon cake ", being extracted one of them candidate's participle is " moon ", then can calculate respectively
Co-occurrence rate (being assumed to be 70%), " moon cake " and " moon " co-occurrence of " mid-autumn " and " moon "
Rate (is assumed to be 60%).
Sub-step S44, the most the plurality of first participle configures with the co-occurrence rate of described candidate's participle
Corresponding multiple weights；
Weight can be according to the information sum ratio of video resource data in the concordance list between each first participle
Being determined of example, wherein, in concordance list, the information sum of video resource data its weights the most are more
Greatly.Such as, in the concordance list in " mid-autumn ", the information sum of video resource data is 900, and
In the concordance list of " moon cake ", the information sum of video resource data is 100, then " mid-autumn " and " moon
Bright " the weight of co-occurrence rate can be 0.9, the weight of " moon cake " and " moon " co-occurrence rate is permissible
It is 0.1.
Certainly, above-mentioned weight is intended only as example, when implementing the embodiment of the present invention, and can basis
Practical situation arranges other weights, such as according to current social focus (news ranking, microblogging ranking
Deng) arrange correspondence weight, according to this locality of user and/or online operation behavior (video playback,
News reading etc.) weight that correspondence is set etc., this is not any limitation as by the embodiment of the present invention.Separately
Outward, in addition to above-mentioned weight, those skilled in the art can also use other to weigh according to actual needs
Weight, this is not any limitation as by the embodiment of the present invention.
Sub-step S45, calculates the meansigma methods of multiple co-occurrence rate being configured with weight, respectively as described
Multiple first participles and the co-occurrence rate of described candidate's participle；
In the embodiment of the present invention, can be using the weighted mean of multiple co-occurrence rate as final co-occurrence
Rate.
Such as, the mid-autumn ", the co-occurrence rate of " moon cake " and " moon " can be (70%*0.9+60%*0.1)
/2=34.5%。
Sub-step S46, extracts described co-occurrence rate candidate's participle higher than predetermined threshold value as association second
Participle.
In implementing, predetermined threshold value can be set according to practical situation by those skilled in the art
, this is not any limitation as by the embodiment of the present invention.The association second extracted in the embodiment of the present invention
Participle can be empty, it is also possible to for one or more.
In one preferred embodiment of the invention, described step 103 specifically can include following son
Step:
Sub-step S51, when described this text message of feature is mapped as multiple first participle, respectively
Extract the multiple preset concordance list that the plurality of first participle is corresponding；Wherein, each concordance list wraps
Include the information of video resource data belonging to the described first participle, and, described video resource data
In all participles；All participles in described video resource data are by capturing video resource number
According to, extract the feature text message of described video resource data, described feature text message is carried out
Participle generates；
In implementing, search engine can be used in advance to pass through on each platform of crawler capturing
Video resource data, then set up index and build storehouse: extract the feature text message of video resource data
Carry out word segmentation processing, and set up the concordance list that each participle is corresponding, this concordance list can store and regard
Frequently the information of resource data (can be ID, internal address, outer net address etc. video labeling, also
Can be a record being made up of current participle and other participles), institute in video resource data
There is participle (including the first participle and the second participle in addition to the first participle).
In one preferred embodiment of the invention, described feature text message can include video mark
Topic, Video Key word and/or video presentation.
Sub-step S52, main participle, described main participle are video money to use the plurality of concordance list to determine
The first participle that the total most concordance list of the information of source data is corresponding；
In order to improve Consumer's Experience, for more greatly different multiple first point of video resource data difference
Word, can ignore the first participle that the informational capacity of video resource data is few.Such as, for feature
The first participle " mid-autumn " that this text message " moon cake in the Mid-autumn Festival " is mapped and " moon cake ", " in
Autumn " concordance list in the information sum of video resource data be 900, and at the concordance list of " moon cake "
The information sum of middle video resource data is 100, then can arrange " mid-autumn " as main participle.
Sub-step S53, calculates the same of each the second participle in the concordance list that described main participle is corresponding
Now rate, described co-occurrence rate is the number of times and described index that in described concordance list, each second participle occurs
The ratio of the information sum of video resource data in table；Wherein, described second participle is described video
Participle in addition to the described first participle in all participles in resource data；
In the embodiment of the present invention, can using the co-occurrence rate of main participle as final co-occurrence rate.
Sub-step S54, extracts the described co-occurrence rate the second participle higher than predetermined threshold value as association second
Participle.
In implementing, predetermined threshold value can be set according to practical situation by those skilled in the art
, this is not any limitation as by the embodiment of the present invention.The association second extracted in the embodiment of the present invention
Participle can be empty, it is also possible to for one or more.
Step 104, acquisition is mated with the one or more first participle and described association the second participle
The network linking address of the second video resource data；
Specifically, after sub-step S33, it is possible to obtain as the previous first participle and one
Or multiple second point of contamination of association.Such as this text message of feature is " dota ", with its co-occurrence
The word that rate is higher is: " making laughs ", " egg pain ", " 2009 ", " great waves ", " the first visual angle " and " warp
Allusion quotation ", co-occurrence rate is respectively 40%, 35%, 30%, 25%, 20% and 10%, then the combination obtained
It is followed successively by " dota makes laughs ", " dota egg pain ", " dota2009 ", " dota great waves ", " dota first
Visual angle " and " dota is classical ".
After sub-step S46, it is possible to obtain current multiple first participles and one or more associations
Second point of contamination.Such as this text message of feature is " square dance Soldiers Brother ", is mapped as
The first participle " square dance " and " Soldiers Brother ", extract the simultaneously occurred with the two first participle
Two participles, the such as second participle " imparts knowledge to students ", and it the most finally can obtain as associating the second participle
Combination " square dance Soldiers Brother's teaching ".
In one preferred embodiment of the invention, step 104 specifically can include following sub-step:
Sub-step S61, obtain described main participle and described association the second participle the second video resource
The network linking address of data.
After sub-step S54, it is possible to obtain current main participle and one or more associations second point
Contamination.Such as, first point this text message of feature " moon cake in the Mid-autumn Festival " mapped
Word " mid-autumn " and " moon cake ", can arrange " mid-autumn " as main participle, obtain associating second point
Word " moon ", the most finally obtains combination " moon in the mid-autumn ".
In the embodiment of the present invention, can be based on one or more first participles and second point of contamination
Carry out the search of the video data resource mated, when searching, record its network link address, tool
Body can be internal address, it is also possible to be outer net address.
Step 105, pushes the network linking address of described second video resource data.
In actual application, the network linking address of the second video resource data can be placed on current page
Any position, it is also possible to push by embedding the mode such as icon or button, user can be by triggering
The network linking address of the second video resource data and then load described video data resource.
The present invention can push according to existing content of having issued, and makes search engine break away from user
The dependence of search custom, although that the fewer user of having searched for but video library collects existing the most heterogeneous
Close the video resource data-pushing of resource out, thus realize the high-quality money that the degree of depth is excavated in video library
Source, improves the efficiency of excavating resource；Additionally, concordance list can along with internet video content not
Disconnected accumulation and constantly expand, content quantity that each big video station is produced and range can be considerably beyond
The word number that user had searched for, is conducive to expanding recall rate.
The present invention is by obtaining the second video resource data of the coupling of the first participle and the second participle
Network link address, user can directly carry out the acquisition of video data resource, make based on this address
User's simple search can obtain more result, it is not necessary to repeatedly submits search to, thus alleviates visit
Ask the burden of server, decrease taking of Internet resources, and improve Consumer's Experience.
For embodiment of the method, in order to be briefly described, therefore it is all expressed as a series of action group
Closing, but those skilled in the art should know, the embodiment of the present invention is not by described action
The restriction of order because according to the embodiment of the present invention, some step can use other orders or
Carry out simultaneously.Secondly, those skilled in the art also should know, enforcement described in this description
Example belongs to preferred embodiment, necessary to the involved action not necessarily embodiment of the present invention.
With reference to Fig. 2, it is shown that a kind of association based on video search
The structured flowchart of the pusher embodiment of resource address, specifically can include such as lower module:
Feature text message acquisition module 201, be suitable to receive the first video resource data loading or
During playing request, obtain this text message of feature of described first video resource data；
First participle mapping block 202, it is one or more for being suitable to described feature Ben Wenben information MAP
The first participle；
Module 203 searched in second participle, is suitable to search the co-occurrence rate with the one or more first participle
Association the second participle higher than predetermined threshold value；Described co-occurrence rate is current one or more first participle and
Two participles are the common probability occurred in same video resource data；
Network link address acquisition module 204, is suitable to obtain and the one or more first participle and institute
State the network linking address of the second video resource data of association the second participle coupling；
Network link address pushing module 205, is suitable to push the lattice chain of described second video resource data
Ground connection location.
In one preferred embodiment of the invention, described feature text message acquisition module can also be fitted
In:
When receiving the playing request of the first video data, receive described the first of present terminal transmission and regard
Frequently this text message of feature of resource data；
Or,
When receiving the first video data load request, extract local preset described video resource data
This text message of feature.
In one preferred embodiment of the invention, described first participle mapping block can be adapted to:
Extract the participle that described this text message of feature is mapped；
Or,
When this text message of feature received is compound word, described this text message of feature is split
For the sub-word of multiple search；Extract multiple participles that the sub-word of the plurality of search is mapped.
In one preferred embodiment of the invention, described second participle lookup module can be adapted to:
When described this text message of feature is mapped as a first participle, extract the described first participle
Corresponding preset concordance list；Wherein, described concordance list includes the video money belonging to the described first participle
The information of source data, and, all participles in described video resource data；Described video resource
All participles in data are by capturing video resource data, extracting described video resource data
Feature text message, carries out participle generation to described feature text message；
Calculate the described first participle and the co-occurrence rate of each the second participle, described co-occurrence in described concordance list
Rate is the number of times and video resource number in described concordance list that in described concordance list, each second participle occurs
According to information sum ratio；Wherein, the institute during described second participle is described video resource data
There is the participle in addition to the described first participle in participle；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
In one preferred embodiment of the invention, described second participle lookup module can be adapted to:
When described this text message of feature is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that the first participle is corresponding；Each concordance list includes belonging to the described first participle
The information of video resource data, and, all participles in described video resource data；Described
All participles in video resource data are by capturing video resource data, extract described video money
The feature text message of source data, carries out participle generation to described feature text message；
Extract the second participle jointly occurred with the plurality of first participle as candidate's participle；Wherein,
Described second participle be in all participles in described video resource data in addition to the described first participle
Participle；
The co-occurrence rate of the described first participle and described candidate's participle, institute is calculated respectively in each concordance list
Stating co-occurrence rate is the number of times and video resource in described concordance list that in described concordance list, candidate's participle occurs
The ratio of the information sum of data；
It is respectively the plurality of first participle and the co-occurrence rate of described candidate's participle and configures corresponding multiple
Weight；
Calculate the meansigma methods of multiple co-occurrence rate being configured with weight respectively, as the plurality of first participle
Co-occurrence rate with described candidate's participle；
Extract described co-occurrence rate candidate's participle higher than predetermined threshold value as associating the second participle.
In one preferred embodiment of the invention, described second participle lookup module can be adapted to:
When described this text message of feature is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that the first participle is corresponding；Wherein, each concordance list includes described first point
The information of the video resource data belonging to word, and, all participles in described video resource data；
All participles in described video resource data are by capturing video resource data, regard described in extraction
Frequently the feature text message of resource data, carries out participle generation to described feature text message；
Main participle, described main participle are the information of video resource data to use the plurality of concordance list to determine
The first participle that total most concordance list is corresponding；
Calculate the co-occurrence rate of each the second participle in the concordance list that described main participle is corresponding, described same
The number of times that during now rate is described concordance list, each second participle occurs and video resource in described concordance list
The ratio of the information sum of data；Wherein, during described second participle is described video resource data
Participle in addition to the described first participle in all participles；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
In one preferred embodiment of the invention, described feature text message can include video mark
Topic, Video Key word and/or video presentation.
In one preferred embodiment of the invention, described network link address acquisition module can also be fitted
In:
Obtain the lattice chain of the second video resource data of described main participle and described association the second participle
Ground connection location.
For device embodiment, due to itself and embodiment of the method basic simlarity, so the comparison described
Simply, relevant part sees the part of embodiment of the method and illustrates.
Provided herein algorithm and display not with any certain computer, virtual system or other set
Standby intrinsic relevant.Various general-purpose systems can also be used together with based on teaching in this.According to upper
The description in face, constructs the structure required by this kind of system and is apparent from.Additionally, the present invention is also
It is not for any certain programmed language.It is understood that, it is possible to use various programming languages realize at this
The present disclosure described, and the description above done language-specific is to disclose this
Bright preferred forms.
In description mentioned herein, illustrate a large amount of detail.It is to be appreciated, however, that
Embodiments of the invention can be put into practice in the case of not having these details.In some instances,
It is not shown specifically known method, structure and technology, in order to do not obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand in each inventive aspect
One or more, above in the description of the exemplary embodiment of the present invention, each of the present invention
Feature is grouped together in single embodiment, figure or descriptions thereof sometimes.But, and
The method of the disclosure should be construed to reflect an intention that i.e. the present invention for required protection requirement
Than the more feature of feature being expressly recited in each claim.More precisely, it is as follows
As the claims in face are reflected, inventive aspect is less than single enforcement disclosed above
All features of example.Therefore, it then follows claims of detailed description of the invention are thus expressly incorporated in
This detailed description of the invention, the most each claim itself is as the independent embodiment of the present invention.
Those skilled in the art are appreciated that and can enter the module in the equipment in embodiment
Row adaptively changes and they is arranged on the one or more equipment different from this embodiment
In.Module in embodiment or unit or assembly can be combined into a module or unit or assembly,
And multiple submodule or subelement or sub-component can be put them in addition.Except such spy
Levy and/or outside at least some in process or unit excludes each other, any combination can be used
To all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) with
And any method or all processes of equipment or unit are combined disclosed in so.Unless additionally
It is expressly recited, every disclosed in this specification (including adjoint claim, summary and accompanying drawing)
Individual feature can be replaced by the alternative features providing identical, equivalent or similar purpose.
Although additionally, it will be appreciated by those of skill in the art that embodiment bags more described herein
Some feature included by including in other embodiments rather than further feature, but different embodiment
The combination of feature means to be within the scope of the present invention and formed different embodiments.Such as,
In the following claims, embodiment required for protection one of arbitrarily can be with arbitrarily
Compound mode use.
The all parts embodiment of the present invention can realize with hardware, or with at one or more
The software module run on processor realizes, or realizes with combinations thereof.The technology of this area
Personnel should be appreciated that and can use microprocessor or digital signal processor (DSP) in practice
Realize in the pushing equipment of correlated resources address based on video search according to embodiments of the present invention
The some or all functions of some or all parts.The present invention is also implemented as holding
Part or all equipment of row method as described herein or device program (such as, meter
Calculation machine program and computer program).The program of such present invention of realization can be stored in calculating
On machine computer-readable recording medium, or can be to have the form of one or more signal.Such signal can
Obtain to download on internet website, or provide on carrier signal, or with any other
Form provides.
The present invention will be described rather than limits the present invention to it should be noted above-described embodiment
Make, and those skilled in the art can design without departing from the scope of the appended claims
Go out alternative embodiment.In the claims, any reference marks structure between bracket should not will be located in
Cause limitations on claims.Word " comprises " not exclude the presence of and does not arranges in the claims
Element or step.Word "a" or "an" before being positioned at element do not exclude the presence of multiple this
The element of sample.The present invention can be by means of including the hardware of some different elements and by means of suitable
When the computer of programming realizes.If in the unit claim listing equipment for drying, these dresses
Several in putting can be specifically to be embodied by same hardware branch.Word first, second,
And third use does not indicates that any order.Can be title by these word explanations.
Claims (16)
1. a method for pushing for correlated resources address based on video search, including:
When receiving loading or the playing request of the first video resource data, obtain described first video money
The feature text message of source data；
Described feature text message is mapped as one or more first participle；
Search be higher than predetermined threshold value with the co-occurrence rate of the one or more first participle associate second point
Word；Described co-occurrence rate is that current one or more first participle and the second participle are in same video resource data
In the common probability occurred；
Obtain the second video mated with the one or more first participle and described association the second participle
The network linking address of resource data；
Push the network linking address of described second video resource data.
2. the method for claim 1, it is characterised in that described when receiving the first video money
When the loading of source data or playing request, obtain the feature text message of described first video resource data
Step includes:
When receiving the playing request of the first video data, receive described the first of present terminal transmission and regard
Frequently the feature text message of resource data；
Or,
When receiving the first video data load request, extract local preset described video resource data
Feature text message.
3. the method for claim 1, it is characterised in that described by described feature text envelope
Breath is mapped as the step of one or more first participle and includes:
Extract the participle that described feature text message is mapped；
Or,
When the feature text message received is compound word, described feature text message is split as many
The sub-word of individual search；Extract multiple participles that the sub-word of the plurality of search is mapped.
4. the method for claim 1, it is characterised in that described lookup and one or
The co-occurrence rate of multiple first participles includes higher than the step of association second participle of predetermined threshold value:
When described feature text message is mapped as a first participle, extract the described first participle pair
The preset concordance list answered；Wherein, described concordance list includes the video resource belonging to the described first participle
The information of data, and, all participles in described video resource data；Described video resource number
All participles according to are by capturing video resource data, extracting the spy of described video resource data
Levy text message, described feature text message is carried out participle generation；
Calculate the described first participle and the co-occurrence rate of each the second participle, described co-occurrence in described concordance list
Rate is the number of times and video resource number in described concordance list that in described concordance list, each second participle occurs
According to information sum ratio；Wherein, the institute during described second participle is described video resource data
There is the participle in addition to the described first participle in participle；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
5. the method for claim 1, it is characterised in that described lookup and one or
The co-occurrence rate of multiple first participles includes higher than the step of association second participle of predetermined threshold value:
When described feature text message is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that one participle is corresponding；Each concordance list includes belonging to the described first participle
The information of video resource data, and, all participles in described video resource data；Described regard
Frequently all participles in resource data are by capturing video resource data, extracting described video resource
The feature text message of data, carries out participle generation to described feature text message；
Extract the second participle jointly occurred with the plurality of first participle as candidate's participle；Wherein,
Described second participle be in all participles in described video resource data in addition to the described first participle
Participle；
The co-occurrence rate of the described first participle and described candidate's participle, institute is calculated respectively in each concordance list
Stating co-occurrence rate is the number of times and video resource in described concordance list that in described concordance list, candidate's participle occurs
The ratio of the information sum of data；
It is respectively the plurality of first participle and the co-occurrence rate of described candidate's participle and configures corresponding multiple
Weight；
Calculate the meansigma methods of multiple co-occurrence rate being configured with weight respectively, as the plurality of first participle
Co-occurrence rate with described candidate's participle；
Extract described co-occurrence rate candidate's participle higher than predetermined threshold value as associating the second participle.
6. the method for claim 1, it is characterised in that described lookup and one or
The co-occurrence rate of multiple first participles includes higher than the step of association second participle of predetermined threshold value:
When described feature text message is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that one participle is corresponding；Wherein, each concordance list includes the described first participle
The information of affiliated video resource data, and, all participles in described video resource data；
All participles in described video resource data are by capturing video resource data, regard described in extraction
Frequently the feature text message of resource data, carries out participle generation to described feature text message；
Main participle, described main participle are video resource data to use described preset multiple concordance lists to determine
The first participle that the total most concordance list of information is corresponding；
Calculate the co-occurrence rate of each the second participle in the concordance list that described main participle is corresponding, described same
The number of times that during now rate is described concordance list, each second participle occurs and video resource in described concordance list
The ratio of the information sum of data；Wherein, during described second participle is described video resource data
Participle in addition to the described first participle in all participles；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
7. the method as described in claim 1 or 4 or 5 or 6, it is characterised in that described feature
Text message includes video title, Video Key word and/or video presentation.
8. method as claimed in claim 6, it is characterised in that described acquisition and one or
The lattice chain ground connection of the second video resource data of multiple first participles and described association the second participle coupling
The step of location includes:
Obtain described main participle and described association the second participle the lattice chain of the second video resource data
Ground connection location.
9. a pusher for correlated resources address based on video search, including:
Feature text message acquisition module, is suitable to receiving loading or the broadcasting of the first video resource data
During request, obtain the feature text message of described first video resource data；
First participle mapping block, is suitable to described feature text message is mapped as one or more first point
Word；
Module searched in second participle, is suitable to search the co-occurrence rate with the one or more first participle and is higher than
Association second participle of predetermined threshold value；Described co-occurrence rate is current one or more first participle and second point
Word is the common probability occurred in same video resource data；
Network link address acquisition module, is suitable to obtain and the one or more first participle and described pass
Join the network linking address of the second video resource data of the second participle coupling；
Network link address pushing module, is suitable to push the lattice chain ground connection of described second video resource data
Location.
10. device as claimed in claim 9, it is characterised in that described feature text message obtains mould
Block is further adapted for:
When receiving the playing request of the first video data, receive described the first of present terminal transmission and regard
Frequently the feature text message of resource data；
Or,
When receiving the first video data load request, extract local preset described video resource data
Feature text message.
11. devices as claimed in claim 9, it is characterised in that described first participle mapping block
It is further adapted for:
Extract the participle that described feature text message is mapped；
Or,
When the feature text message received is compound word, described feature text message is split as many
The sub-word of individual search；Extract multiple participles that the sub-word of the plurality of search is mapped.
12. devices as claimed in claim 9, it is characterised in that module searched in described second participle
It is further adapted for:
When described feature text message is mapped as a first participle, extract the described first participle pair
The preset concordance list answered；Wherein, described concordance list includes the video resource belonging to the described first participle
The information of data, and, all participles in described video resource data；Described video resource number
All participles according to are by capturing video resource data, extracting the spy of described video resource data
Levy text message, described feature text message is carried out participle generation；
Calculate the described first participle and the co-occurrence rate of each the second participle, described co-occurrence in described concordance list
Rate is the number of times and video resource number in described concordance list that in described concordance list, each second participle occurs
According to information sum ratio；Wherein, the institute during described second participle is described video resource data
There is the participle in addition to the described first participle in participle；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
13. devices as claimed in claim 9, it is characterised in that module searched in described second participle
It is further adapted for:
When described feature text message is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that one participle is corresponding；Each concordance list includes belonging to the described first participle
The information of video resource data, and, all participles in described video resource data；Described regard
Frequently all participles in resource data are by capturing video resource data, extracting described video resource
The feature text message of data, carries out participle generation to described feature text message；
Extract the second participle jointly occurred with the plurality of first participle as candidate's participle；Wherein,
Described second participle be in all participles in described video resource data in addition to the described first participle
Participle；
The co-occurrence rate of the described first participle and described candidate's participle, institute is calculated respectively in each concordance list
Stating co-occurrence rate is the number of times and video resource in described concordance list that in described concordance list, candidate's participle occurs
The ratio of the information sum of data；
It is respectively the plurality of first participle and the co-occurrence rate of described candidate's participle and configures corresponding multiple
Weight；
Calculate the meansigma methods of multiple co-occurrence rate being configured with weight respectively, as the plurality of first participle
Co-occurrence rate with described candidate's participle；
Extract described co-occurrence rate candidate's participle higher than predetermined threshold value as associating the second participle.
14. devices as claimed in claim 9, it is characterised in that module searched in described second participle
It is further adapted for:
When described feature text message is mapped as multiple first participle, extract the plurality of respectively
The multiple preset concordance list that one participle is corresponding；Wherein, each concordance list includes the described first participle
The information of affiliated video resource data, and, all participles in described video resource data；
All participles in described video resource data are by capturing video resource data, regard described in extraction
Frequently the feature text message of resource data, carries out participle generation to described feature text message；
Main participle, described main participle are video resource data to use described preset multiple concordance lists to determine
The first participle that the total most concordance list of information is corresponding；
Calculate the co-occurrence rate of each the second participle in the concordance list that described main participle is corresponding, described same
The number of times that during now rate is described concordance list, each second participle occurs and video resource in described concordance list
The ratio of the information sum of data；Wherein, during described second participle is described video resource data
Participle in addition to the described first participle in all participles；
Extract the described co-occurrence rate the second participle higher than predetermined threshold value as associating the second participle.
15. devices as described in claim 9 or 12 or 13 or 14, it is characterised in that described
Feature text message includes video title, Video Key word and/or video presentation.
16. devices as claimed in claim 14, it is characterised in that described network link address obtains
Delivery block is further adapted for:
Obtain the network linking of the second video resource data of described main participle and described association the second participle
Address.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310462461.6A CN103491205B (en) | 2013-09-30 | 2013-09-30 | The method for pushing of a kind of correlated resources address based on video search and device |
| PCT/CN2014/086519 WO2015043389A1 (en) | 2013-09-30 | 2014-09-15 | Participle information push method and device based on video search |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310462461.6A CN103491205B (en) | 2013-09-30 | 2013-09-30 | The method for pushing of a kind of correlated resources address based on video search and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103491205A CN103491205A (en) | 2014-01-01 |
| CN103491205B true CN103491205B (en) | 2016-08-17 |
Family
ID=49831158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310462461.6A Active CN103491205B (en) | 2013-09-30 | 2013-09-30 | The method for pushing of a kind of correlated resources address based on video search and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103491205B (en) |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015043389A1 (en) * | 2013-09-30 | 2015-04-02 | 北京奇虎科技有限公司 | Participle information push method and device based on video search |
| CN105279172B (en) * | 2014-06-30 | 2019-07-09 | 惠州市伟乐科技股份有限公司 | Video matching method and device |
| CN105912600B (en) * | 2016-04-05 | 2019-08-16 | 上海智臻智能网络科技股份有限公司 | Question and answer knowledge base and its method for building up, intelligent answer method and system |
| RU2649793C2 (en) | 2016-08-03 | 2018-04-04 | ООО "Группа АйБи" | Method and system of detecting remote connection when working on web resource pages |
| RU2634209C1 (en) | 2016-09-19 | 2017-10-24 | Общество с ограниченной ответственностью "Группа АйБи ТДС" | System and method of autogeneration of decision rules for intrusion detection systems with feedback |
| RU2671991C2 (en) | 2016-12-29 | 2018-11-08 | Общество с ограниченной ответственностью "Траст" | System and method for collecting information for detecting phishing |
| RU2637477C1 (en) | 2016-12-29 | 2017-12-04 | Общество с ограниченной ответственностью "Траст" | System and method for detecting phishing web pages |
| RU2689816C2 (en) | 2017-11-21 | 2019-05-29 | ООО "Группа АйБи" | Method for classifying sequence of user actions (embodiments) |
| RU2677368C1 (en) | 2018-01-17 | 2019-01-16 | Общество С Ограниченной Ответственностью "Группа Айби" | Method and system for automatic determination of fuzzy duplicates of video content |
| RU2677361C1 (en) | 2018-01-17 | 2019-01-16 | Общество с ограниченной ответственностью "Траст" | Method and system of decentralized identification of malware programs |
| RU2676247C1 (en) | 2018-01-17 | 2018-12-26 | Общество С Ограниченной Ответственностью "Группа Айби" | Web resources clustering method and computer device |
| RU2680736C1 (en) | 2018-01-17 | 2019-02-26 | Общество с ограниченной ответственностью "Группа АйБи ТДС" | Malware files in network traffic detection server and method |
| RU2668710C1 (en) | 2018-01-17 | 2018-10-02 | Общество с ограниченной ответственностью "Группа АйБи ТДС" | Computing device and method for detecting malicious domain names in network traffic |
| RU2681699C1 (en) | 2018-02-13 | 2019-03-12 | Общество с ограниченной ответственностью "Траст" | Method and server for searching related network resources |
| CN110674386B (en) * | 2018-06-14 | 2022-11-01 | 北京百度网讯科技有限公司 | Resource recommendation method, device and storage medium |
| RU2708508C1 (en) | 2018-12-17 | 2019-12-09 | Общество с ограниченной ответственностью "Траст" | Method and a computing device for detecting suspicious users in messaging systems |
| RU2701040C1 (en) | 2018-12-28 | 2019-09-24 | Общество с ограниченной ответственностью "Траст" | Method and a computer for informing on malicious web resources |
| EP3842968B1 (en) | 2019-02-27 | 2024-04-24 | "Group IB" Ltd. | Method and system for identifying a user according to keystroke dynamics |
| CN110427381A (en) * | 2019-08-07 | 2019-11-08 | 北京嘉和海森健康科技有限公司 | A kind of data processing method and relevant device |
| RU2728498C1 (en) | 2019-12-05 | 2020-07-29 | Общество с ограниченной ответственностью "Группа АйБи ТДС" | Method and system for determining software belonging by its source code |
| RU2728497C1 (en) | 2019-12-05 | 2020-07-29 | Общество с ограниченной ответственностью "Группа АйБи ТДС" | Method and system for determining belonging of software by its machine code |
| RU2743974C1 (en) | 2019-12-19 | 2021-03-01 | Общество с ограниченной ответственностью "Группа АйБи ТДС" | System and method for scanning security of elements of network architecture |
| SG10202001963TA (en) | 2020-03-04 | 2021-10-28 | Group Ib Global Private Ltd | System and method for brand protection based on the search results |
| CN111400546B (en) * | 2020-03-18 | 2020-12-01 | 腾讯科技（深圳）有限公司 | Video recall method and video recommendation method and device |
| RU2743619C1 (en) | 2020-08-06 | 2021-02-20 | Общество с ограниченной ответственностью "Группа АйБи ТДС" | Method and system for generating the list of compromise indicators |
| US11947572B2 (en) | 2021-03-29 | 2024-04-02 | Group IB TDS, Ltd | Method and system for clustering executable files |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236567A (en) * | 2008-02-04 | 2008-08-06 | 上海升岳电子科技有限公司 | Method and terminal apparatus for accomplishing on-line network multimedia application |
| CN101599995A (en) * | 2009-07-13 | 2009-12-09 | 中国传媒大学 | The directory distribution method and the network architecture towards high-concurrency retrieval system |
| CN101957828A (en) * | 2009-07-20 | 2011-01-26 | 阿里巴巴集团控股有限公司 | Method and device for sequencing search results |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040064447A1 (en) * | 2002-09-27 | 2004-04-01 | Simske Steven J. | System and method for management of synonymic searching |
| CN102326144B (en) * | 2008-12-12 | 2015-06-17 | 阿迪吉欧有限责任公司 | Providing recommendations using information determined for domains of interest |
-
2013
- 2013-09-30 CN CN201310462461.6A patent/CN103491205B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236567A (en) * | 2008-02-04 | 2008-08-06 | 上海升岳电子科技有限公司 | Method and terminal apparatus for accomplishing on-line network multimedia application |
| CN101599995A (en) * | 2009-07-13 | 2009-12-09 | 中国传媒大学 | The directory distribution method and the network architecture towards high-concurrency retrieval system |
| CN101957828A (en) * | 2009-07-20 | 2011-01-26 | 阿里巴巴集团控股有限公司 | Method and device for sequencing search results |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103491205A (en) | 2014-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103491205B (en) | The method for pushing of a kind of correlated resources address based on video search and device | |
| CN111984689B (en) | Information retrieval method, device, equipment and storage medium | |
| CN103544267B (en) | Search method and device based on search recommended words | |
| CN103064956B (en) | For searching for the method for digital content, calculating system and computer-readable medium | |
| CN103488787B (en) | A kind of method for pushing and device of the online broadcasting entrance object based on video search | |
| WO2015176526A1 (en) | Superimposed-relationship-based document identification, association, search, and display system | |
| CN103853738B (en) | A kind of recognition methods of info web correlation region | |
| CN103544266B (en) | A kind of method and device for searching for suggestion word generation | |
| CN101299217B (en) | Method, apparatus and system for processing map information | |
| CN108694223A (en) | The construction method and device in a kind of user's portrait library | |
| CN103544176A (en) | Method and device for generating page structure template corresponding to multiple pages | |
| WO2015176525A1 (en) | Time-serialization-based document identification, association, search, and display system | |
| CN104978332B (en) | User-generated content label data generation method, device and correlation technique and device | |
| CN101350013A (en) | Method and system for searching geographical information | |
| CN103955529A (en) | Internet information searching and aggregating presentation method | |
| CN101794277B (en) | Method for embedding geographical labels in network character information and system | |
| CN104462553A (en) | Method and device for recommending question and answer page related questions | |
| CN111026937A (en) | Method, device and equipment for extracting POI name and computer storage medium | |
| CN102200975A (en) | Vertical search engine system and method using semantic analysis | |
| CN109492081B (en) | Text information searching and information interaction method, device, equipment and storage medium | |
| JP2022532451A (en) | How to disambiguate Chinese place name meanings based on encyclopedia knowledge base and word embedding | |
| CN104679783A (en) | Network searching method and device | |
| CN109815383A (en) | The detection of microblogging rumour and its resource base construction method based on LSTM | |
| CN103942264A (en) | Method and device for pushing webpages containing news information | |
| CN105630937A (en) | Method and device for searching answers to exam questions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220707 Address after: Room 801, 8th floor, No. 104, floors 1-19, building 2, yard 6, Jiuxianqiao Road, Chaoyang District, Beijing 100015 Patentee after: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Address before: 100088 room 112, block D, 28 new street, new street, Xicheng District, Beijing (Desheng Park) Patentee before: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Patentee before: Qizhi software (Beijing) Co.,Ltd. |
|
| TR01 | Transfer of patent right |