CN105824923A - Movie and video resource recommendation method and device - Google Patents
Movie and video resource recommendation method and device Download PDFInfo
- Publication number
- CN105824923A CN105824923A CN201610152332.0A CN201610152332A CN105824923A CN 105824923 A CN105824923 A CN 105824923A CN 201610152332 A CN201610152332 A CN 201610152332A CN 105824923 A CN105824923 A CN 105824923A
- Authority
- CN
- China
- Prior art keywords
- movie
- resources
- video display
- display label
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Abstract
The embodiment of the invention provides a movie and video resource recommendation method and device. The method comprises the following steps of obtaining an interestingness tag of a target user; matching at least one movie and video tag according to the interestingness tag, wherein the movie and video tag at least includes a nominal tag extracted from a scenario text of the movie and video resource or an adjective tag extracted from a comment text of the movie and video resource; according to the at least one movie and video tag, obtaining at least one part of corresponding movie and video resource; recommending the at least one movie and video resource to the target user. The method and the device provided by the invention have the advantages that the nominal movie and video tag can show the liking contents of movie and video resources of the user; the adjective movie and video tag can better show the subjective feeling of the movie and video resource; the nominal movie and video tag and the adjective movie and video tag are combined for performing movie and video resource matching; the interestingness of the user can be met in multiple aspects and multiple angles; the movie and video resource recommendation accuracy is improved.
Description
Technical field
The present invention relates to communication technology, particularly relate to a kind of the resources of movie & TV and recommend method and device.
Background technology
Along with emerging in an endless stream of various the resources of movie & TVs, the resources of movie & TVs such as various film, TV play, variety show all can be had every day to occur in the visual field of user.User, in the face of too much the resources of movie & TV, is difficult to quickly find the film oneself liked, thus is highly desirable to rational the resources of movie & TV recommendation mechanisms.
In prior art, being based primarily upon the common key words such as director, protagonist, films types and recommend film to user, such as user likes certain to direct, and will recommend other film of this director.
But, use the existing this way of recommendation, the most rough to the hobby of user and the division of film, cause the film limitation recommended for user bigger, it is impossible to meet the hobby of user in many aspects.
Summary of the invention
The present invention provides a kind of the resources of movie & TV to recommend method and device, is used for solving existing the resources of movie & TV and recommends method limitation bigger, it is impossible to the problem meeting the hobby of user in many aspects.
First aspect present invention provides a kind of the resources of movie & TV to recommend method, including:
Obtain the interest tags of targeted customer；
Mating at least one video display label according to described interest tags, wherein, described video display label is at least included in the story of a play or opera text of the resources of movie & TV the nominal label extracted, or extract in the comment text of the resources of movie & TV describe part of speech label；
According at least one video display label described, obtain at least one corresponding the resources of movie & TV, and described at least one corresponding the resources of movie & TV is recommended described targeted customer.
Second aspect present invention provides a kind of the resources of movie & TV recommendation apparatus, including:
First acquisition module, for obtaining the interest tags of targeted customer；
Matching module, for mating at least one video display label according to described interest tags, wherein, described video display label is at least included in the story of a play or opera text of the resources of movie & TV the nominal label extracted, or extract in the comment text of the resources of movie & TV describe part of speech label；
Recommending module, for according at least one video display label described, obtains at least one corresponding the resources of movie & TV, and described at least one corresponding the resources of movie & TV is recommended described targeted customer.
The resources of movie & TV that the present invention provides is recommended in method and device, obtain the interest tags of targeted customer, and mate video display label according to the interest tags of targeted customer, and the resources of movie & TV of video display tag match is recommended user, wherein, video display label is at least included in the story of a play or opera text of the resources of movie & TV the nominal label extracted, or in the comment text of the resources of movie & TV extract describe part of speech label, can be seen that nominal video display label can embody the content of the resources of movie & TV that user likes, describe that part of speech video display label can preferably embody user's subjective feeling of the resources of movie & TV, both combine the coupling carrying out the resources of movie & TV, can be many-sided, meet the interest of user with multi-angle, improve the accuracy that the resources of movie & TV is recommended.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in describing below is some embodiments of the present invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 recommends the schematic flow sheet of embodiment of the method one for the resources of movie & TV that the present invention provides；
Fig. 2 recommends the schematic flow sheet of embodiment of the method two for the resources of movie & TV that the present invention provides；
The structural representation of the resources of movie & TV recommendation apparatus embodiment one that Fig. 3 provides for the present invention；
The structural representation of the resources of movie & TV recommendation apparatus embodiment two that Fig. 4 provides for the present invention；
The structural representation of the resources of movie & TV recommendation apparatus embodiment three that Fig. 5 provides for the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art are obtained under not making creative work premise, broadly fall into the scope of protection of the invention.
Fig. 1 recommends the schematic flow sheet of embodiment of the method one for the resources of movie & TV that the present invention provides, as it is shown in figure 1, the method includes:
S101, the interest tags of acquisition targeted customer.
This interest tags includes: at least one nominal interest tags, or at least one describes part of speech interest tags.
Certainly, interest tags can also include: at least one nominal interest tags, and at least one describes part of speech interest tags, and this is not restricted.
The type of the resources of movie & TV that each user is liked may there are differences, and more specifically can be identified the resources of movie & TV that user likes in more detail by interest tags.
Nominal interest tags typically may include that eponym, place name noun, time noun, mechanism/organization name noun, proper noun etc., these nominal interest tags can embody the content of the resources of movie & TV that user likes, such as certain user likes comedy class video display, and his nominal interest tags potentially includes: Zhou Xingchi, Chaplin, France, handou sir, three stupidly create an uproar in BOLLYWOOD etc..
Describe that part of speech interest tags is generally used to describe the subjective experience of user, the impression of the film of user can also be reflected, such as certain user likes comedy class video display, and he describes that part of speech interest tags potentially includes: humour, make laughs, spectacular, touching, laughable, make us fresh and new, artistic skills are pretty good, vivid, be difficult to forget.
Alternatively, obtain the interest tags of targeted customer, can be the interest tags obtaining user's active upload, such as, can input oneself video display label interested interest tags as oneself under the account of oneself correspondence of certain website.And then nominal interest tags can also be extracted from the interest tags of user's active upload and describe part of speech interest tags.
Or, watch the resources of movie & TV and the scoring to history viewing the resources of movie & TV according to the history of user, analyze the interest tags obtaining user.Such as, user is the highest to the scoring of certain the resources of movie & TV, illustrates that user likes this resources of movie & TV, then can extract the video display label interest tags as user of this resources of movie & TV.Specifically, when extracting the interest tags of user from user's history viewing the resources of movie & TV, can be in the story of a play or opera text of history viewing the resources of movie & TV, to extract nominal key word and extract in the comment text of history viewing the resources of movie & TV and describe the part of speech key word interest tags as user.
Certainly it is not limited with the method for above-mentioned acquisition interest tags.
S102, mating at least one video display label according to above-mentioned interest tags, wherein, this video display label is at least included in the nominal label of the story of a play or opera Text Feature Extraction of the resources of movie & TV, or extract in the comment text of the resources of movie & TV describe part of speech label.
Certainly, corresponding with interest tags, it is also possible to be simultaneously included in the nominal label of the story of a play or opera Text Feature Extraction of the resources of movie & TV, and extract in the comment text of the resources of movie & TV describe part of speech label, this is not restricted.
Specifically, matching process can mate video display label identical, relevant or close, the such as interest tags of certain user of user is " Beijing ", so during coupling video display label, in addition to " Beijing " that coupling is identical, can also match " Beijing ", " capital ", " capital " of synonym etc., and can mate relevant " Tian An-men ", " Wangfujing ", this is not restricted.
Owing to nominal video display label can embody the content of the resources of movie & TV that user likes, describing that part of speech video display label can preferably embody user's subjective feeling of the resources of movie & TV, both combinations carry out the coupling of the resources of movie & TV, the actual demand of the user that can more fit.
S103, according at least one video display label above-mentioned, obtain at least one corresponding the resources of movie & TV, and the resources of movie & TV that this at least is corresponding recommended above-mentioned targeted customer.
Each the resources of movie & TV has at least one video display label, uses the above-mentioned video display label matched according to interest tags to mate the resources of movie & TV of correspondence in the resources of movie & TV storehouse, and then recommends targeted customer again.In concrete matching process, can search and comprise the resources of movie & TV of one or more video display labels at least one video display label above-mentioned, and the resources of movie & TV found is recommended.
The video display label such as matched according to the interest tags " Huai-Hai Campaign " of targeted customer comprises " war of liberation ", the video display label finding film " foundation great cause " in search procedure also includes " war of liberation ", then just " foundation great cause " can be recommended user.
In the present embodiment, obtain the interest tags of targeted customer, and mate video display label according to the interest tags of targeted customer, and the resources of movie & TV of video display tag match is recommended user, wherein, video display label is at least included in the story of a play or opera text of the resources of movie & TV the nominal label extracted, or in the comment text of the resources of movie & TV extract describe part of speech label, can be seen that nominal video display label can embody the content of the resources of movie & TV that user likes, describe that part of speech video display label can preferably embody user's subjective feeling of the resources of movie & TV, both combine the coupling carrying out the resources of movie & TV, can be many-sided, meet the interest of user with multi-angle, improve the accuracy that the resources of movie & TV is recommended.
In concrete recommendation process, the recommendation of the resources of movie & TV can be carried out using the type information of the resources of movie & TV as retrievable attribute, specifically, the scope of the resources of movie & TV to be recommended can be reduced by the type of the resources of movie & TV.
According at least one video display label above-mentioned, obtain at least one corresponding the resources of movie & TV, and before the resources of movie & TV that this at least corresponding is recommended above-mentioned targeted customer, targeted customer's video display interest-degree to each the resources of movie & TV type can also be obtained, this video display interest-degree size mark user's interest size to this resources of movie & TV type.
And then according to video display interest-degree, obtain at least one to be recommended the resources of movie & TV type corresponding more than the video display interest-degree of the first predetermined threshold value.
Correspondingly, according at least one video display label above-mentioned, in the resources of movie & TV included by least one the resources of movie & TV type to be recommended above-mentioned, coupling comprises the target the resources of movie & TV of at least one above-mentioned video display label, and with described target the resources of movie & TV similarity more than the alternative the resources of movie & TV of the second predetermined threshold value, described target the resources of movie & TV and described alternative the resources of movie & TV are recommended above-mentioned targeted customer.Specifically, the method calculating the resources of movie & TV similarity is a lot, and this is not restricted, such as, can compare the video display label overlapping between the resources of movie & TV or approximating, or use other similarity algorithm to carry out calculating etc..
For video display interest-degree, alternatively, it is assumed that data base has M portion the resources of movie & TV, it is recommended that platform has N number of user, and wherein M portion the resources of movie & TV includes R kind the resources of movie & TV type, and wherein M, N, R are the integer more than 0.
The resources of movie & TV type matrix of M*R can be obtained according to the resources of movie & TV type.
And then the concrete each user scoring situation to each the resources of movie & TV can be obtained, it is expressed as { a with M dimensional vector1,a2,……,am, wherein, amRepresent certain user scoring to m-th the resources of movie & TV, m is the integer less than or equal to M, scoring record according to wherein non-NULL calculates scoring meansigma methods avg, if i.e. certain the resources of movie & TV is not scored, then neglect, only calculate the scoring of the resources of movie & TV marked by certain user add and, and divided by total scoring number, obtain scoring meansigma methods avg of certain user.
It is possible to further according to formula Ui=(∑ xi-avg)/niCalculate the targeted customer video display interest-degree U to i-th kind of the resources of movie & TV typei, wherein, ∑ xiRepresent targeted customer comment in i-th kind of the resources of movie & TV type the scoring of undue the resources of movie & TV add and, niRepresent targeted customer to i-th kind of the resources of movie & TV type is commented the number of undue the resources of movie & TV, avg represents the meansigma methods of the scoring record of the non-NULL of targeted customer.I is the positive integer less than or equal to R, can obtain the targeted customer R dimensional vector { x to the resources of movie & TV type1,x2,......xr, r is the positive integer less than or equal to R.After the same method, the N*R interests matrix of N number of user can be obtained.
And then can be according to video display interest-degree UiObtain the resources of movie & TV type that targeted customer likes, such as by UiThe resources of movie & TV type liked as targeted customer more than the resources of movie & TV type of the 3rd predetermined threshold value.
Video display interest-degree according to user, can mate the to be recommended the resources of movie & TV higher with user's matching degree that the high the resources of movie & TV type of video display interest-degree is comprised further.Specifically, formula can be usedCalculate matching degree cos (U, I) of user U and the resources of movie & TV I.Wherein, UsRepresent the user U video display interest-degree to s the resources of movie & TV type, IsRepresent whether the resources of movie & TV I belongs to s the resources of movie & TV type.Can therefrom choose the resources of movie & TV higher for cos (U, I) as the resources of movie & TV to be recommended, such as using matching degree more than the resources of movie & TV of the 4th predetermined threshold value as the resources of movie & TV to be recommended.
Further, then use user interest tag match to video display label in the resources of movie & TV to be recommended, mate target the resources of movie & TV.
It should be noted that, above-mentioned the resources of movie & TV type can be that the story of a play or opera attribute previously according to the resources of movie & TV divides, such as can be divided into comedy, patriotic, history, war etc., can also divide is more careful, such as ancient war, science fiction war, ancient costume comedy, city love etc., this is not restricted.
Illustrate certain user's conception of history and seen " X fights alert ", nominal label is extracted from the story of a play or opera text of " X fights alert ", and part of speech label is described in extraction from the comment text of " X fights alert ", get " U.S. ", " war ", " save ", the interest tags of users such as " fierce ", and then it is higher to the video display interest-degree of " science fiction war " class the resources of movie & TV to get this user, in " science fiction war " class the resources of movie & TV, coupling comprises video display label " U.S. ", " war ", " save ", the film of at least one in " fierce ", finally give film " terminator ", then this film is recommended user as target the resources of movie & TV.
The most such as user's conception of history has seen " nine grades of rank in the feudal regimes sesame official ", nominal key word is extracted from the story of a play or opera text of " nine grades of rank in the feudal regimes sesame official ", and part of speech key word is described in extraction from the comment text of " nine grades of rank in the feudal regimes sesame official ", get " ancient costume ", " Zhou Xingchi ", the key word interest tags as user such as " make laughs ", and then it is higher to the video display interest-degree of " ancient costume comedy " class the resources of movie & TV to get this user, in " ancient costume comedy " class the resources of movie & TV, coupling comprises video display label " ancient costume ", " Zhou Xingchi ", the film of at least one in " making laughs ", finally give film " Flirting Scholar ", then this film is recommended user as target the resources of movie & TV.
Certainly, it is not limited with above-mentioned example, multiple the resources of movie & TV can be recommended, specifically, the resources of movie & TV directly matched can be recommended, it is also possible to the similar the resources of movie & TV of the resources of movie & TV that will match to is recommended.
Alternatively, above-mentioned mate at least one video display label according to interest tags before, in addition it is also necessary to set up video display tag library.This video display tag library is for storing the mark of the resources of movie & TV, and the video display label of the mark correspondence of each the resources of movie & TV.Specifically, each the resources of movie & TV can be corresponding with multiple video display labels, can set up the resources of movie & TV and the mapping relations of multiple video display label in video display tag library.
Fig. 2 recommends the schematic flow sheet of embodiment of the method two for the resources of movie & TV that the present invention provides, as in figure 2 it is shown, above-mentioned video display tag library of setting up specifically includes:
S201, the story of a play or opera text at least obtaining target the resources of movie & TV or comment text.
Goal the resources of movie & TV can refer to any one the resources of movie & TV.Story of a play or opera text and the comment text of target the resources of movie & TV can certainly be obtained simultaneously.
Alternatively, by story of a play or opera text and the comment text of Network Capture target the resources of movie & TV.Specifically, can be from the recommendation platform of some the resources of movie & TVs, social networks first-class acquisition story of a play or opera text and comment text, such as Semen Sojae Preparatum, microblogging, Baidupedia, TIME dotCom etc..
Story of a play or opera text can be the brief introduction of the resources of movie & TV or detailed situation introduction etc., and normal words more specification is neat, and comment text can be all kinds of comments for certain the resources of movie & TV, long, short does not limits.
S202, story of a play or opera text or comment text are carried out word segmentation, and each word after cutting is marked part of speech.
Here part of speech may include that noun, verb, adjective, preposition etc..
It is online that the story of a play or opera text obtained or comment text are the most all that user uploads to, may form chaotic or be mingled with the symbol etc. of some pictures, None-identified.Before carrying out word segmentation, story of a play or opera text and comment text can also be carried out pretreatment, tentatively to arrange, specifically, pretreatment includes deleting the forbidden character in story of a play or opera text and comment text, the complex form of Chinese characters, picture etc., or the complex form of Chinese characters can also be converted to simplified Chinese character in preprocessing process.
S203, part of speech according to above-mentioned each word, at least extract the noun in story of a play or opera text or the adjective in the above-mentioned comment text video display label as above-mentioned target the resources of movie & TV.
Usually, the noun in story of a play or opera text includes: eponym, place name noun, time noun, mechanism/organization name noun, proper noun etc., these nouns can objectively embody the particular content of the resources of movie & TV, in order to preferably matches type the resources of movie & TV.
And comment text embodies the subjective assessment of user more, adjective therein can embody user's description to the resources of movie & TV, such as: exciting, grand, realistic, moved, sentimental etc..
In conjunction with the noun in story of a play or opera text and the adjective of comment text, the resources of movie & TV can be described more fully with and bring the impression of user.
S204, the video display label of above-mentioned target the resources of movie & TV and the mark of this target the resources of movie & TV are set up associate after be stored in above-mentioned video display tag library.
Specifically, mapping relations can be set up between video display label and the resources of movie & TV.
Alternatively, above-mentioned S203 can be particularly as follows: according to the part of speech of each word, at least extract the noun in story of a play or opera text or the adjective in above-mentioned comment text, then according to database of synonyms, noun in story of a play or opera text or the adjective in comment text are carried out synonym duplicate removal, and using the word after duplicate removal as the video display label of above-mentioned target the resources of movie & TV.Such as " like ", " liking ", the next one can be stayed at random, delete one.
By synonym duplicate removal, it is possible to reduce the total amount of video display label, save memory space resource.
Alternatively, in another embodiment, can also be according to the meaning of a word of the video display label of target the resources of movie & TV, obtain video display label relevant to the video display label meaning of a word of above-mentioned target the resources of movie & TV in above-mentioned video display tag library, and video display label relevant to the above-mentioned meaning of a word for the video display label of above-mentioned target the resources of movie & TV is set up association.Wherein, the meaning of a word of the video display label that the meaning of a word is relevant comprises or by inclusion relation with the meaning of a word existence of the video display label of above-mentioned target the resources of movie & TV.
Specifically, meaning of a word analysis can be used, analyze the meaning of a word of all video display labels in video display tag library, set up incidence relation between which, when carrying out the resources of movie & TV coupling, except the resources of movie & TV of video display label oneself coupling, it is also possible to recommend the resources of movie & TV of associated video display tag match.
Such as between " Tian An-men " and " Beijing ", " Beijing " contains " Tian An-men ", association can be set up, the interest tags of user is Beijing, after so matching " Beijing " this video display label, " Tian An-men " associated with " Beijing " can also be matched, then can also recommend to comprise the resources of movie & TV of " Tian An-men " this video display label to this user.
The most such as between " documentary film " and " realistic ", " documentary film " comprises " realistic ", association can be set up, the interest tags of user is documentary film, after so matching " documentary film " this video display label, " realistic " associated with " documentary film " can also be matched, then can also recommend to comprise the resources of movie & TV of " realistic " this video display label to this user.
In order to preferably recommend the resources of movie & TV for user, after video display tag library has been set up, manager can also artificially be adjusted, such as by unclear for some meaning of a word or there is the word of ambiguity and carry out deleting or replacement etc., or be not set up association by the meaning of a word and but itself there is the word manager of certain association can also set up association, such as can set up association etc. between " Bruce Lee " and " wushu ".
Alternatively, multiple label theme can also be preset, video display label is divided under different label themes, can comprise under above-mentioned each the resources of movie & TV type and can comprise multiple label themes such as " Zhou Xingchi ", " French ", " Hong Kong " under this resources of movie & TV type of multiple label theme, such as " comedy ".When carrying out the resources of movie & TV recommendation, can be first according to the video display interest-degree of user, determine the resources of movie & TV type that user likes, interest tags according further to user determines several label theme, then mate in the video display label that these label themes are comprised, and finally determine target the resources of movie & TV.So can reduce the scope of coupling video display label further, improve efficiency.
The structural representation of the resources of movie & TV recommendation apparatus embodiment one that Fig. 3 provides for the present invention, as it is shown on figure 3, this device includes: the first acquisition module 301, matching module 302 and recommending module 303, wherein,
First acquisition module 301, for obtaining the interest tags of targeted customer.
Matching module 302, for mating at least one video display label according to described interest tags, wherein, described video display label is at least included in the story of a play or opera text of the resources of movie & TV the nominal label extracted, or extract in the comment text of the resources of movie & TV describe part of speech label.
Recommending module 303, for according at least one video display label described, obtains at least one corresponding the resources of movie & TV, and described at least one corresponding the resources of movie & TV is recommended described targeted customer.
In the present embodiment, obtain the interest tags of targeted customer, and mate video display label according to the interest tags of targeted customer, and the resources of movie & TV of video display tag match is recommended user, wherein, video display label is at least included in the story of a play or opera text of the resources of movie & TV the nominal label extracted, or in the comment text of the resources of movie & TV extract describe part of speech label, can be seen that nominal video display label can embody the content of the resources of movie & TV that user likes, describe that part of speech video display label can preferably embody user's subjective feeling of the resources of movie & TV, both combine the coupling carrying out the resources of movie & TV, can be many-sided, meet the interest of user with multi-angle, improve the accuracy that the resources of movie & TV is recommended.
The structural representation of the resources of movie & TV recommendation apparatus embodiment two that Fig. 4 provides for the present invention, as shown in Figure 4, on the basis of Fig. 3, this device also includes: set up module 401, is used for setting up video display tag library.
Specifically, set up module 401 and at least obtain story of a play or opera text or the comment text of target the resources of movie & TV；Described story of a play or opera text or described comment text are carried out word segmentation, and each word after cutting is marked part of speech；According to the part of speech of described each word, at least extract the noun in described story of a play or opera text or the adjective in the described comment text video display label as described target the resources of movie & TV；The video display label of described target the resources of movie & TV is set up with the mark of described target the resources of movie & TV and is stored in described video display tag library after associating.
Wherein, set up the module 401 part of speech according to described each word, at least extract the noun in described story of a play or opera text or the adjective in described comment text and may include that the part of speech according to described each word as the video display label of described target the resources of movie & TV, at least extract the noun in described story of a play or opera text or the adjective in described comment text；According to database of synonyms, the noun in described story of a play or opera text or the adjective in described comment text are carried out synonym duplicate removal, and using the word after duplicate removal as the video display label of described target the resources of movie & TV.
Alternatively, set up module 401 and be additionally operable to the meaning of a word of the video display label according to described target the resources of movie & TV, obtain video display label relevant to the video display label meaning of a word of described target the resources of movie & TV in described video display tag library；Video display label relevant to the described meaning of a word for the video display label of described target the resources of movie & TV is set up association, and wherein, the meaning of a word of the video display label that the described meaning of a word is relevant comprises or by inclusion relation with the meaning of a word existence of the video display label of described target the resources of movie & TV.
The structural representation of the resources of movie & TV recommendation apparatus embodiment three that Fig. 5 provides for the present invention, as it is shown in figure 5, on the basis of Fig. 3, this device also includes: the second acquisition module 501, for obtaining the described targeted customer video display interest-degree to each the resources of movie & TV type.
Correspondingly, above-mentioned recommending module 303, according to described video display interest-degree, obtain at least one to be recommended the resources of movie & TV type corresponding more than the described video display interest-degree of the first predetermined threshold value；According at least one video display label described, the resources of movie & TV included by least one the resources of movie & TV type to be recommended described mates the target the resources of movie & TV comprising at least one described video display label and is more than the alternative the resources of movie & TV of the second predetermined threshold value with described target the resources of movie & TV similarity；Described target the resources of movie & TV and described alternative the resources of movie & TV are recommended described targeted customer.
In several embodiments provided by the present invention, it should be understood that disclosed apparatus and method, can realize by another way.Such as, device embodiment described above is only schematically, such as, the division of described unit, be only a kind of logic function to divide, actual can have when realizing other dividing mode, the most multiple unit or assembly can in conjunction with or be desirably integrated into another system, or some features can ignore, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be the INDIRECT COUPLING by some interfaces, device or unit or communication connection, can be electrical, machinery or other form.
The described unit illustrated as separating component can be or may not be physically separate, and the parts shown as unit can be or may not be physical location, i.e. may be located at a place, or can also be distributed on multiple NE.Some or all of unit therein can be selected according to the actual needs to realize the purpose of the present embodiment scheme.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it is also possible to be that unit is individually physically present, it is also possible to two or more unit are integrated in a unit.Above-mentioned integrated unit both can realize to use the form of hardware, it would however also be possible to employ hardware adds the form of SFU software functional unit and realizes.
The above-mentioned integrated unit realized with the form of SFU software functional unit, can be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions with so that a computer equipment (can be personal computer, server, or the network equipment etc.) or processor (English: processor) perform the part steps of method described in each embodiment of the present invention.And aforesaid storage medium includes: USB flash disk, portable hard drive, read only memory are (English: Read-OnlyMemory, be called for short: ROM), random access memory (English: RandomAccessMemory, RAM), the various media that can store program code such as magnetic disc or CD be called for short:.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, it is not intended to limit；Although the present invention being described in detail with reference to foregoing embodiments, it will be understood by those within the art that: the technical scheme described in foregoing embodiments still can be modified by it, or the most some or all of technical characteristic is carried out equivalent；And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (9)
1. a resources of movie & TV recommends method, it is characterised in that including:
Obtain the interest tags of targeted customer；
Mating at least one video display label according to described interest tags, wherein, described video display label is at least included in the story of a play or opera text of the resources of movie & TV the nominal label extracted, or extract in the comment text of the resources of movie & TV describe part of speech label；
According at least one video display label described, obtain at least one corresponding the resources of movie & TV, and described at least one corresponding the resources of movie & TV is recommended described targeted customer.
Method the most according to claim 1, it is characterised in that described mate at least one video display label according to described interest tags before, also include:
At least obtain story of a play or opera text or the comment text of target the resources of movie & TV；
Described story of a play or opera text or described comment text are carried out word segmentation, and each word after cutting is marked part of speech；
According to the part of speech of described each word, at least extract the noun in described story of a play or opera text or the adjective in the described comment text video display label as described target the resources of movie & TV；
The video display label of described target the resources of movie & TV is set up with the mark of described target the resources of movie & TV and is stored in described video display tag library after associating.
Method the most according to claim 2, it is characterised in that the described part of speech according to described each word, at least extracts the noun in described story of a play or opera text or the adjective in the described comment text video display label as described target the resources of movie & TV, including:
According to the part of speech of described each word, at least extract the noun in described story of a play or opera text or the adjective in described comment text；
According to database of synonyms, the noun in described story of a play or opera text or the adjective in described comment text are carried out synonym duplicate removal, and using the word after duplicate removal as the video display label of described target the resources of movie & TV.
Method the most according to claim 3, it is characterised in that described method also includes:
The meaning of a word of the video display label according to described target the resources of movie & TV, obtains video display label relevant to the video display label meaning of a word of described target the resources of movie & TV in described video display tag library；
Video display label relevant to the described meaning of a word for the video display label of described target the resources of movie & TV is set up association, and wherein, the meaning of a word of the video display label that the described meaning of a word is relevant comprises or by inclusion relation with the meaning of a word existence of the video display label of described target the resources of movie & TV.
Method the most according to claim 1, it is characterised in that at least one video display label described in described basis, obtains at least one corresponding the resources of movie & TV, and before described at least one corresponding the resources of movie & TV is recommended described targeted customer, also includes:
Obtain the described targeted customer video display interest-degree to each the resources of movie & TV type.
Method the most according to claim 5, it is characterised in that at least one video display label described in described basis, obtains at least one corresponding the resources of movie & TV, and described at least one corresponding the resources of movie & TV is recommended described targeted customer, including:
According to described video display interest-degree, obtain at least one to be recommended the resources of movie & TV type corresponding more than the described video display interest-degree of the first predetermined threshold value；
According at least one video display label described, the resources of movie & TV included by least one the resources of movie & TV type to be recommended described mates the target the resources of movie & TV comprising at least one described video display label and is more than the alternative the resources of movie & TV of the second predetermined threshold value with described target the resources of movie & TV similarity；
Described target the resources of movie & TV and described alternative the resources of movie & TV are recommended described targeted customer.
7. a resources of movie & TV recommendation apparatus, it is characterised in that including:
First acquisition module, for obtaining the interest tags of targeted customer；
Matching module, for mating at least one video display label according to described interest tags, wherein, described video display label is at least included in the story of a play or opera text of the resources of movie & TV the nominal label extracted, or extract in the comment text of the resources of movie & TV describe part of speech label；
Recommending module, for according at least one video display label described, obtains at least one corresponding the resources of movie & TV, and described at least one corresponding the resources of movie & TV is recommended described targeted customer.
Device the most according to claim 7, it is characterised in that also include:
Set up module, at least obtaining story of a play or opera text or the comment text of target the resources of movie & TV；Described story of a play or opera text or described comment text are carried out word segmentation, and each word after cutting is marked part of speech；According to the part of speech of described each word, at least extract the noun in described story of a play or opera text or the adjective in the described comment text video display label as described target the resources of movie & TV；The video display label of described target the resources of movie & TV is set up with the mark of described target the resources of movie & TV and is stored in described video display tag library after associating.
Device the most according to claim 7, it is characterised in that also include:
Second acquisition module, for obtaining the described targeted customer video display interest-degree to each the resources of movie & TV type；
Correspondingly,
Described recommending module, specifically for according to described video display interest-degree, obtaining at least one to be recommended the resources of movie & TV type corresponding more than the described video display interest-degree of the first predetermined threshold value；According at least one video display label described, the resources of movie & TV included by least one the resources of movie & TV type to be recommended described mates the target the resources of movie & TV comprising at least one described video display label and is more than the alternative the resources of movie & TV of the second predetermined threshold value with described target the resources of movie & TV similarity；Described target the resources of movie & TV and described alternative the resources of movie & TV are recommended described targeted customer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610152332.0A CN105824923A (en) | 2016-03-17 | 2016-03-17 | Movie and video resource recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610152332.0A CN105824923A (en) | 2016-03-17 | 2016-03-17 | Movie and video resource recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105824923A true CN105824923A (en) | 2016-08-03 |
Family
ID=56523828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610152332.0A Pending CN105824923A (en) | 2016-03-17 | 2016-03-17 | Movie and video resource recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105824923A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407420A (en) * | 2016-09-23 | 2017-02-15 | 广州视源电子科技股份有限公司 | A multimedia resource recommendation method and system |
| CN106815364A (en) * | 2017-01-24 | 2017-06-09 | 百度在线网络技术（北京）有限公司 | Content delivery method and device |
| CN106909635A (en) * | 2017-02-09 | 2017-06-30 | 苏州亮磊知识产权运营有限公司 | Data mining and processing method and system based on the comment of multimedia digital image |
| CN106909634A (en) * | 2017-02-09 | 2017-06-30 | 苏州亮磊知识产权运营有限公司 | Multimedia image comment data based on condition is excavated and processing method and system |
| CN107436934A (en) * | 2017-07-21 | 2017-12-05 | 上海斐讯数据通信技术有限公司 | It is a kind of to orient the system and method for subscribing to the story of a play or opera |
| CN107577672A (en) * | 2017-09-19 | 2018-01-12 | 网智天元科技集团股份有限公司 | Method and apparatus based on public sentiment setting drama |
| WO2018023666A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Patent information pushing method in video recommendation and video recommendation system |
| CN107730313A (en) * | 2017-09-30 | 2018-02-23 | 口碑(上海)信息技术有限公司 | Recommend method and device in shop based on rationale for the recommendation |
| CN108038446A (en) * | 2017-12-11 | 2018-05-15 | 周飞燕 | Information collecting method |
| CN108256024A (en) * | 2018-01-10 | 2018-07-06 | 链家网（北京）科技有限公司 | A kind of source of houses recommends method |
| CN108519991A (en) * | 2018-02-28 | 2018-09-11 | 北京奇艺世纪科技有限公司 | A kind of method and apparatus of main broadcaster's account recommendation |
| CN109033167A (en) * | 2018-06-20 | 2018-12-18 | 新华网股份有限公司 | Separated film method and system |
| CN110020192A (en) * | 2018-07-31 | 2019-07-16 | 北京微播视界科技有限公司 | A kind of information content method for pushing and device, server device |
| CN110019958A (en) * | 2017-12-28 | 2019-07-16 | Tcl集团股份有限公司 | A kind of generation method, device and the terminal device of films and television programs label |
| CN110019935A (en) * | 2017-10-17 | 2019-07-16 | 飞狐信息技术（天津）有限公司 | A kind of video set creation method and device based on theme |
| CN110209921A (en) * | 2018-05-10 | 2019-09-06 | 腾讯科技（深圳）有限公司 | The method for pushing and device and storage medium and electronic device of media resource |
| CN111625704A (en) * | 2020-05-11 | 2020-09-04 | 镇江纵陌阡横信息科技有限公司 | Non-personalized recommendation algorithm model based on user intention and data cooperation |
| CN111708901A (en) * | 2020-06-19 | 2020-09-25 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901450A (en) * | 2010-07-14 | 2010-12-01 | 中兴通讯股份有限公司 | Media content recommendation method and media content recommendation system |
| CN103744849A (en) * | 2011-12-27 | 2014-04-23 | 北京奇虎科技有限公司 | Method and device for automatic recommendation application |
| CN103973754A (en) * | 2013-02-06 | 2014-08-06 | 上海华师京城高新技术开发有限公司 | Resource push method and system |
| CN105095508A (en) * | 2015-08-31 | 2015-11-25 | 北京奇艺世纪科技有限公司 | Multimedia content recommendation method and multimedia content recommendation apparatus |
| US20150370907A1 (en) * | 2014-06-19 | 2015-12-24 | BrightSky Labs, Inc. | Systems and methods for intelligent filter application |
-
2016
- 2016-03-17 CN CN201610152332.0A patent/CN105824923A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901450A (en) * | 2010-07-14 | 2010-12-01 | 中兴通讯股份有限公司 | Media content recommendation method and media content recommendation system |
| CN103744849A (en) * | 2011-12-27 | 2014-04-23 | 北京奇虎科技有限公司 | Method and device for automatic recommendation application |
| CN103973754A (en) * | 2013-02-06 | 2014-08-06 | 上海华师京城高新技术开发有限公司 | Resource push method and system |
| US20150370907A1 (en) * | 2014-06-19 | 2015-12-24 | BrightSky Labs, Inc. | Systems and methods for intelligent filter application |
| CN105095508A (en) * | 2015-08-31 | 2015-11-25 | 北京奇艺世纪科技有限公司 | Multimedia content recommendation method and multimedia content recommendation apparatus |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018023666A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Patent information pushing method in video recommendation and video recommendation system |
| CN106407420A (en) * | 2016-09-23 | 2017-02-15 | 广州视源电子科技股份有限公司 | A multimedia resource recommendation method and system |
| CN106407420B (en) * | 2016-09-23 | 2020-04-21 | 广州视源电子科技股份有限公司 | Multimedia resource recommendation method and system |
| CN106815364A (en) * | 2017-01-24 | 2017-06-09 | 百度在线网络技术（北京）有限公司 | Content delivery method and device |
| CN106909635B (en) * | 2017-02-09 | 2020-05-19 | 深圳市瑞迪兴智能科技有限公司 | Data mining and processing method and system based on multimedia digital image comments |
| CN106909635A (en) * | 2017-02-09 | 2017-06-30 | 苏州亮磊知识产权运营有限公司 | Data mining and processing method and system based on the comment of multimedia digital image |
| CN106909634B (en) * | 2017-02-09 | 2020-04-28 | 江苏睿泰数字传媒有限公司 | Multimedia image comment data mining and processing method and system based on conditions |
| CN106909634A (en) * | 2017-02-09 | 2017-06-30 | 苏州亮磊知识产权运营有限公司 | Multimedia image comment data based on condition is excavated and processing method and system |
| CN107436934A (en) * | 2017-07-21 | 2017-12-05 | 上海斐讯数据通信技术有限公司 | It is a kind of to orient the system and method for subscribing to the story of a play or opera |
| CN107436934B (en) * | 2017-07-21 | 2023-09-08 | 杭州吉吉知识产权运营有限公司 | System and method for directionally subscribing to scenario |
| CN107577672B (en) * | 2017-09-19 | 2021-07-06 | 网智天元科技集团股份有限公司 | Public opinion-based script setting method and device |
| CN107577672A (en) * | 2017-09-19 | 2018-01-12 | 网智天元科技集团股份有限公司 | Method and apparatus based on public sentiment setting drama |
| CN107730313B (en) * | 2017-09-30 | 2020-11-03 | 口碑(上海)信息技术有限公司 | Shop recommendation method and device based on recommendation reason |
| CN107730313A (en) * | 2017-09-30 | 2018-02-23 | 口碑(上海)信息技术有限公司 | Recommend method and device in shop based on rationale for the recommendation |
| CN110019935A (en) * | 2017-10-17 | 2019-07-16 | 飞狐信息技术（天津）有限公司 | A kind of video set creation method and device based on theme |
| CN108038446B (en) * | 2017-12-11 | 2021-11-02 | 周飞燕 | Information acquisition method |
| CN108038446A (en) * | 2017-12-11 | 2018-05-15 | 周飞燕 | Information collecting method |
| CN110019958A (en) * | 2017-12-28 | 2019-07-16 | Tcl集团股份有限公司 | A kind of generation method, device and the terminal device of films and television programs label |
| CN108256024A (en) * | 2018-01-10 | 2018-07-06 | 链家网（北京）科技有限公司 | A kind of source of houses recommends method |
| CN108519991A (en) * | 2018-02-28 | 2018-09-11 | 北京奇艺世纪科技有限公司 | A kind of method and apparatus of main broadcaster's account recommendation |
| CN110209921A (en) * | 2018-05-10 | 2019-09-06 | 腾讯科技（深圳）有限公司 | The method for pushing and device and storage medium and electronic device of media resource |
| CN110209921B (en) * | 2018-05-10 | 2023-04-11 | 深圳市雅阅科技有限公司 | Method and device for pushing media resource, storage medium and electronic device |
| CN109033167A (en) * | 2018-06-20 | 2018-12-18 | 新华网股份有限公司 | Separated film method and system |
| CN110020192A (en) * | 2018-07-31 | 2019-07-16 | 北京微播视界科技有限公司 | A kind of information content method for pushing and device, server device |
| CN111625704A (en) * | 2020-05-11 | 2020-09-04 | 镇江纵陌阡横信息科技有限公司 | Non-personalized recommendation algorithm model based on user intention and data cooperation |
| CN111708901A (en) * | 2020-06-19 | 2020-09-25 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
| CN111708901B (en) * | 2020-06-19 | 2023-10-13 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105824923A (en) | Movie and video resource recommendation method and device | |
| Nie et al. | Multimedia answering: enriching text QA with media information | |
| Jakob et al. | Beyond the stars: exploiting free-text user reviews to improve the accuracy of movie recommendations | |
| US20140164507A1 (en) | Media content portions recommended | |
| CN108595660A (en) | Label information generation method, device, storage medium and the equipment of multimedia resource | |
| JP5714702B2 (en) | Analysis of product information randomness | |
| US20160321355A1 (en) | Media content recommendation method and apparatus | |
| CN106156157B (en) | Electronic book navigation system and method | |
| US9720978B1 (en) | Fingerprint-based literary works recommendation system | |
| US20220138474A1 (en) | Personalizing videos with nonlinear playback | |
| JP2015529901A (en) | Information classification based on product recognition | |
| US20180067935A1 (en) | Systems and methods for digital media content search and recommendation | |
| Zhang et al. | Snap-and-ask: Answering multimodal question by naming visual instance | |
| CN111813993A (en) | Video content expanding method and device, terminal equipment and storage medium | |
| CN107368489A (en) | A kind of information data processing method and device | |
| Akula et al. | Metaclue: Towards comprehensive visual metaphors research | |
| Bednarek | Language and Characterisation in Television Series | |
| Dubuisson Duplessis et al. | Utterance retrieval based on recurrent surface text patterns | |
| Vimieiro | The digital productivity of football supporters: Formats, motivations and styles | |
| Bhatt et al. | Multimodal reranking of content-based recommendations for hyperlinking video snippets | |
| CN110929035B (en) | Information prediction method and system for film and television works | |
| Choi et al. | Consento: a new framework for opinion based entity search and summarization | |
| CN107203621A (en) | A kind of querying method based on first letter of pinyin | |
| Liu et al. | Automatic suggestion of presentation image for storytelling | |
| Inoue et al. | Retrieving lightly annotated images using image similarities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160803 |