CN105095508A - Multimedia content recommendation method and multimedia content recommendation apparatus - Google Patents
Multimedia content recommendation method and multimedia content recommendation apparatus Download PDFInfo
- Publication number
- CN105095508A CN105095508A CN201510549931.1A CN201510549931A CN105095508A CN 105095508 A CN105095508 A CN 105095508A CN 201510549931 A CN201510549931 A CN 201510549931A CN 105095508 A CN105095508 A CN 105095508A
- Authority
- CN
- China
- Prior art keywords
- emotion
- weighted value
- user
- content
- affective tag
- 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.)
- Granted
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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9562—Bookmark management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
-
- 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
- G06F16/951—Indexing; Web crawling techniques
Abstract
The embodiment of the present invention provides a multimedia content recommendation method and apparatus. The method comprises: acquiring an evaluation content input by a user; according to the evaluation content, establishing an emotion model of the user; and according to the established emotion model of the user, recommending a multimedia content to the user.
Description
Technical field
The present invention relates to communication technology application, particularly relate to a kind of content of multimedia recommend method and content of multimedia recommendation apparatus.
Background technology
Along with the development of the communication technology and the universal of mobile terminal, the user obtaining content of multimedia on mobile terminals gets more and more.
At present, mostly user, to the obtain manner of content of multimedia, is directly to search the content of wishing viewing or the content selecting self hope viewing according to the recommendation page that multimedia content provider provides.
Obviously, this mode can not meet the diversity of user preferences.
Therefore, for multimedia content provider, content of multimedia propelling movement (comprising video recommendations, advertisement putting or other resource supplyings etc.) can bring better viewing experience to user in real time and accurately, also can improve the viewing number of times, loyalty etc. of user.
The working method of present content of multimedia commending system descends Modling model often online, then watches behavior as parameters input using the user on line, by the calculating of model, draws recommendation list.Also having the improvement of some real-time recommendation algorithms, is carry out dynamic adjustment model according to statisticss such as the broadcasting records watched mostly.But, cannot perception user emotion at that time and interest-degree with upper type, also cannot the change of perception user interest.Thus cannot analyze more accurately user interest according to the change of user interest, and carry out the recommendation of content of multimedia based on this.
Summary of the invention
In order to solve the technical matters of existing existence, the embodiment of the present invention is expected to provide a kind of content of multimedia recommend method and device.
Embodiments provide a kind of content of multimedia recommend method, comprising:
Obtain the evaluation content of user's input;
The emotion model of user is set up according to described evaluation content;
Emotion model according to the user set up recommends content of multimedia to user.
In such scheme, described evaluation content comprises: user carries out the comment evaluated and/or barrage.
In such scheme, the described emotion model setting up user according to described evaluation content, comprising: determine the affective tag list of user in different emotions dimension according to described evaluation content; Wherein, described emotion dimension at least comprises: like dimension; Described affective tag list comprises: affective tag and weighted value corresponding to described affective tag.
In such scheme, describedly determine the affective tag list of user in different emotions dimension according to described evaluation content, comprising:
The content that emotion descriptor in extraction user evaluation content and described emotion descriptor describe;
Described emotion descriptor can be emotion adjective or emotion adjective and emotion adverbial word;
Affective tag in the corresponding affective tag list of the content that described emotion descriptor describes, the weighted value of the corresponding described affective tag of weighted value of described emotion descriptor.
In such scheme, the weighted value of described emotion descriptor is determined by the following method:
When described emotion descriptor only comprises emotion adjective, determine the first weighted value, and described the first weighted value determined is defined as weighted value corresponding to described affective tag; When described emotion descriptor comprises emotion adjective and emotion adverbial word, determine the first weighted value and the second weighted value, using the product of described first weighted words and described second weighted value as weighted value corresponding to described affective tag; Described first weighted value refers to the weighted value that described emotion adjective is corresponding, and described second weighted value refers to the weighted value that described emotion adverbial word is corresponding.
In such scheme, when the product of described first weighted value and described second weighted value is greater than the max-thresholds of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described max-thresholds; When the product of described first weighted value and described second weighted value is less than the minimum threshold of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described minimum threshold.
In such scheme, before determining the weighted value of described emotion descriptor, described method also comprises:
Pre-set the weighted value that weighted value corresponding to emotion adjective in described emotion descriptor or the emotion adjective pre-set in described emotion descriptor and emotion adverbial word are corresponding.
In such scheme, the emotion model of the described user according to setting up recommends content of multimedia to user, comprising:
Determine the affective tag list of user;
Determine the list of labels of content of multimedia to be recommended;
Determine the similarity of the list of labels of content of multimedia to be recommended and the affective tag list of described user;
One or more content of multimedia the highest with the affective tag list similarity of described user in content of multimedia to be recommended are recommended user.
Embodiments provide a kind of content of multimedia recommendation apparatus, comprising:
Evaluation content acquisition module, emotion model set up module and content of multimedia recommending module; Wherein
Described evaluation content acquisition module, for obtaining the evaluation content of user's input;
Described emotion model sets up module, for setting up the emotion model of user according to described evaluation content;
Described content of multimedia recommending module, for recommending content of multimedia according to the emotion model of the user set up to user.
In such scheme, described evaluation content comprises: user carries out the comment evaluated and/or barrage.
In such scheme, described emotion model sets up module, for determining the affective tag list of user in different emotions dimension according to described evaluation content; Wherein, described emotion dimension at least comprises: like dimension; Described affective tag list comprises: affective tag and weighted value corresponding to described affective tag.
In such scheme, described emotion model sets up module, comprises and extracts submodule and arrange submodule; Wherein,
Described extraction submodule, for extracting the content that emotion descriptor in user's evaluation content and described emotion descriptor describe; Described emotion descriptor can be emotion adjective or emotion adjective and emotion adverbial word;
Describedly arrange submodule, the curriculum offering for being described by described emotion descriptor is the affective tag in affective tag list, and the weighted value of described emotion descriptor is set to the weighted value of described affective tag.
In such scheme, described emotion model is set up module and is also comprised first and determine submodule, for only comprising emotion adjective when described emotion descriptor, determining the first weighted value, and described first weighted value is defined as weighted value corresponding to described affective tag; When described emotion descriptor comprises emotion adjective and emotion adverbial word, determine the first weighted value and the second weighted value, the product of described first weighted words and the second weighted value is defined as weighted value corresponding to described affective tag; Described first weighted value refers to the weighted value that described emotion adjective is corresponding, and described second weighted value refers to the weighted value that described emotion adverbial word is corresponding.
In such scheme, described emotion model sets up module, and for when the product of described first weighted value and described second weighted value is greater than the max-thresholds of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described max-thresholds; When the product of described first weighted value and described second weighted value is less than the minimum threshold of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described minimum threshold.
In such scheme, described device also comprises: weighted value arranges module, determine the weighted value of described emotion descriptor for setting up module at emotion model before, pre-set the weighted value that weighted value corresponding to emotion adjective in described emotion descriptor or the emotion adjective pre-set in described emotion descriptor and emotion adverbial word are corresponding.
In such scheme, described content of multimedia pushing module, comprising: second determines submodule and recommend submodule; Wherein,
Described second determines submodule, for determining the affective tag list of user; Determine the list of labels of content of multimedia to be recommended; Determine the similarity of the affective tag list that the list of labels of content of multimedia to be recommended and described user like;
Described recommendation submodule, for recommending user by one or more content of multimedia the highest with the affective tag list similarity of described user in content of multimedia to be recommended.
The embodiment of the present invention at least possesses following advantage:
A kind of content of multimedia recommend method that the embodiment of the present invention provides and device, obtain the evaluation content of user's input; The emotion model of user is set up according to described evaluation content; Emotion model according to the user set up recommends content of multimedia to user.According to the content of multimedia recommend method that the embodiment of the present invention provides, the emotion model of user can be set up according to user's evaluation content, and according to the emotion model set up for user for user recommends content of multimedia, relative in prior art according to watching record of user for user recommends the method for content of multimedia.The content of multimedia recommend method that the embodiment of the present invention provides more can reflect the true hobby of user, and the hobby that energy track user changes at any time, constantly adjust the content of multimedia recommended to user, adding users content of multimedia views and admires interest in process and satisfaction.
Accompanying drawing explanation
Fig. 1 shows the flow chart of steps of a kind of content of multimedia recommend method embodiment that the embodiment of the present invention one provides;
Fig. 2 shows the flow chart of steps of a kind of content of multimedia recommend method embodiment that the embodiment of the present invention two provides;
Fig. 3 shows the basic structure block diagram in a kind of content of multimedia recommendation apparatus of the present invention;
Fig. 4 shows the exemplary process diagram based on a kind of content of multimedia recommend method of the present invention.
Embodiment
For enabling above-mentioned purpose of the present invention, feature and advantage become apparent more, and below in conjunction with the drawings and specific embodiments, the present invention is further detailed explanation.
Embodiment of the method one
With reference to Fig. 1, show the flow chart of steps of a kind of content of multimedia recommend method embodiment of the present invention, specifically can comprise:
The evaluation content of step 101, acquisition user input;
Concrete, by multimedia supplier in this step, especially video providing system gathers the evaluation content of user's input, and it can be the comment that user delivers for video that user mentioned here evaluates, or the barrage delivered in video display process.
Step 102, set up the emotion model of user according to described evaluation content;
Concrete, the emotion model of described user, be made up of the affective tag list of user in different emotions dimension, different emotions dimension mentioned here at least comprises: like dimension;
Further, described different emotions dimension also can comprise disagreeable dimension, also or further comprises noninductive dimension etc.
Described affective tag list is made up of one or more affective tag and weighted value corresponding to affective tag.
As its name suggests, like affective tag list in dimension can affective tag interested to characterizing consumer, and the weighted value of this affective tag; The weighted value of each different emotions label embodies this affective tag proportion shared in the context that user likes, and embodies user to the favorable rating of the content that this affective tag identifies.
In practical application, in video playback field, described affective tag can comprise following element: name (name of the celebrity such as performer, singer), movie and television play name, character's name, movie and television play type etc.; Here only provide some Usual examples of affective tag element, the protection domain be not intended to limit the present invention, in practical application, various affective tag element can be set according to actual needs.
It should be noted that, for the affective tag list of same user, above all elements can be comprised in label wherein, as name (name of the celebrity such as performer, singer), movie and television play name, character's name, movie and television play type wherein at least one item, and one or more affective tag can be comprised for each element.
Step 103, recommend content of multimedia according to the emotion model of user set up to user.
Concrete, emotion model according to the user set up recommends content of multimedia to user, be specifically as follows and recommend content of multimedia to user according to user liking the list of labels in dimension, like this, the content of multimedia recommended to user in this way more can meet the hobby of user's current time.And along with inputting the tracking of evaluation content to user and analyzing, can the change of real-time perception user preferences, and adapt to the content of multimedia that this change adjustment pushes to user, like this, that more can bring for user views and admires experience.
To sum up, the content of multimedia recommend method provided according to the embodiment of the present invention, can set up the emotion model of user according to user's evaluation content, and according to the emotion model set up for user for user recommends content of multimedia.Relative in prior art according to watching record of user for user recommends the method for content of multimedia, the content of multimedia recommend method that the embodiment of the present invention provides more can reflect the true hobby of user, and the hobby that energy track user changes at any time, constantly adjust the content of multimedia recommended to user, adding users content of multimedia views and admires interest in process and satisfaction.
Embodiment of the method two
With reference to Fig. 2, show the flow chart of steps of a kind of content of multimedia recommend method embodiment of the present invention, specifically can comprise:
The evaluation content of step 201, acquisition user input;
Concrete, by multimedia supplier in this step, especially video providing system gathers the evaluation content of user's input, and it can be the comment that user delivers for video that user mentioned here evaluates, and/or the barrage delivered in video display process.
Step 202, determine the affective tag list of user in different emotions dimension according to the evaluation content of user; Wherein, described emotion dimension at least comprises: like dimension, and described list of labels comprises: label and weighted value corresponding to described label;
Described affective tag list is made up of one or more affective tag and weighted value corresponding to affective tag.
Further, described different emotions dimension also can comprise disagreeable dimension, also or further comprises noninductive dimension etc.
As its name suggests, like affective tag list in dimension can the weighted value of affective tag interested to characterizing consumer and corresponding affective tag; The weighted value of each different emotions label embodies this affective tag proportion shared in the context that user likes, and embodies user to the favorable rating of this label.Accordingly, the affective tag list in disagreeable dimension can be used for characterizing consumer the weighted value of the affective tag disliked and corresponding affective tag; The weighted value of each different emotions label embody this affective tag user proportion shared in the context disliked, embody user to the disagreeable degree of this affective tag.
In practical application, in video playback field, described affective tag can comprise following element: name (name of the celebrity such as performer, singer), movie and television play name, character's name, movie and television play type etc.; Here only provide some Usual examples of affective tag element, the protection domain be not intended to limit the present invention, in practical application, various affective tag element can be set according to actual needs.
It should be noted that, for the affective tag list of same user, above all elements can be comprised in affective tag wherein, as name (name of the celebrity such as performer, singer), movie and television play name, character's name, movie and television play type wherein at least one item, and one or more affective tag can be comprised for each element.
Concrete, the described evaluation content according to user sets up the affective tag list for described user, comprising:
The content that emotion descriptor in extraction user evaluation content and described emotion descriptor describe;
Described emotion descriptor can be emotion adjective or emotion adjective and emotion adverbial word;
Affective tag in the corresponding affective tag list of the content that described emotion descriptor describes, the weighted value of the corresponding described affective tag of weighted value of described emotion descriptor; Namely, be the affective tag in affective tag list by the curriculum offering that described emotion descriptor describes, the weighted value of described emotion descriptor be set to the weighted value of described affective tag.
In such scheme, common emotion adjective and the keyword of emotion adverbial word can be set, thus according to keyword, user comment be retrieved, extract the description meeting described keyword in user comment and also analyzed; Such as, the adjectival keyword of common emotion can comprise: like, like, interesting, good-looking, make laughs, boring, disagreeable, nauseating, not laughable, plain, do not like etc.; The keyword of common emotion adverbial word can comprise: very, very, good, special, a bit etc.And the difference of emotion described by emotion adjective and emotion adverbial word also needs the emotion adjective that is divided into by emotion adjective under different emotion dimension; Such as, liking in upper example, like, interesting, good-looking etc. be the emotion adjective liked under dimension, and boring, disagreeable, nauseating, plain etc. the emotion adjective be under disagreeable dimension.
It should be noted that, the emotion adjective more than enumerated is not the adjective on verbal meaning entirely, and the specific vocabulary just in order to define the accuracy of user's emotion identification, comprises and the adjective be not limited on verbal meaning and verb etc.
Concrete, the weighted value of described emotion descriptor is determined by the following method:
When described emotion descriptor only comprises emotion adjective, determine the weighted value (hereinafter referred to as the first weighted value) that described emotion adjective is corresponding, and described the first weighted value determined is defined as weighted value corresponding to described label;
When described emotion descriptor comprises emotion adjective and emotion adverbial word, determine the weighted value (hereinafter referred to as the second weighted value) that emotion adverbial word in the weighted value (hereinafter referred to as the first weighted value) that emotion adjective in described emotion descriptor is corresponding and described emotion descriptor is corresponding, using the product of described first weighted words and the second weighted value as weighted value corresponding to described label.
Concrete, when the product of described first weighted value and the second weighted value is greater than the max-thresholds of weighted value corresponding to described label, getting weighted value corresponding to described label is described max-thresholds; When the product of described first weighted value and the second weighted value is less than the minimum threshold of weighted value corresponding to described label, getting weighted value corresponding to described label is described minimum threshold.
Concrete, before determining the weighted value of described emotion descriptor, described method also comprises:
Pre-set the weighted value that weighted value corresponding to emotion adjective in described emotion descriptor or the emotion adjective pre-set in described emotion descriptor and emotion adverbial word are corresponding.
The weighted value plan of establishment that exemplary emotion adjective is corresponding is as shown in table 1, wherein, the weighted value representing the emotion adjective liked corresponding is positive number, and the weighted value representing disagreeable emotion adjective corresponding is negative, and according to liking or disagreeable degree difference, the value size of the weighted value that different emotions adjective is corresponding is different; Represent the degree liked or dislike darker, then the absolute value of weighted value is larger.
| Emotion adjective | Weighted value |
| Like | 0.8 |
| Interesting | 0.6 |
| Disagreeable | -0.6 |
| Feel sick | -0.9 |
Table 1
The weighted value plan of establishment that exemplary emotion adverbial word is corresponding is as shown in table 2, according to shown in table 2, when emotion adverbial word and emotion adjective occur and darker to the adjectival degree of modification of emotion simultaneously, then this weighted value corresponding to emotion adverbial word is larger, and the minimum value of weighted value is 1.0.
| Emotion adverbial word | Weighted value |
| Very | 1.3 |
| Very | 1.2 |
| A bit | 1.1 |
Table 2
Step 203, recommend content of multimedia according to the affective tag list of user to user.
Concrete, the affective tag list according to user recommends content of multimedia to user, comprising:
Determine the affective tag list of user;
Determine the list of labels of content of multimedia to be recommended;
Determine the similarity of the list of labels of content of multimedia to be recommended and the affective tag list of described user;
One or more content of multimedia the highest with the affective tag list similarity of described user in content of multimedia to be recommended are recommended user.
Like this, the content of multimedia recommended to user in this way more can meet the hobby of user's current time, and along with inputting the tracking of evaluation content to user and analyzing, can the change of real-time perception user preferences, and adapt to the content of multimedia of this change adjustment to user's propelling movement, therefore, that more can bring for user views and admires experience.
Device embodiment
With reference to Fig. 3, show the structured flowchart of a kind of content of multimedia recommendation apparatus of the present invention embodiment, described device comprises: evaluation content acquisition module 31, emotion model set up module 32 and content of multimedia recommending module 33; Wherein
Described evaluation content acquisition module 31, for obtaining the evaluation content of user's input;
Described emotion model sets up module 32, for setting up the emotion model of user according to described evaluation content;
Described content of multimedia recommending module 33, for recommending content of multimedia according to the emotion model of the user set up to user.
Concrete, described evaluation content can be the comment that user delivers for video, and/or the barrage delivered in video display process.
Concrete, described emotion model sets up module 32, for determining the affective tag list of described user in different emotions dimension according to the evaluation content of user; Wherein, described emotion dimension at least comprises: like dimension; Described affective tag list comprises: affective tag and weighted value corresponding to described affective tag.
Concrete, described emotion model sets up module 32, comprises and extracts submodule and arrange submodule; Wherein,
Described extraction submodule, for extracting the content that emotion descriptor in user's evaluation content and described emotion descriptor describe; Described emotion descriptor can be emotion adjective or emotion adjective and emotion adverbial word;
Describedly arrange submodule, the curriculum offering for being described by described emotion descriptor is the affective tag in affective tag list, and the weighted value of described emotion descriptor is set to the weighted value of described affective tag.
More specifically, described emotion model sets up module 32, also comprises first and determines submodule, for when described emotion descriptor only comprises emotion adjective, determines the first weighted value, and described first weighted value is defined as weighted value corresponding to described affective tag;
When described emotion descriptor comprises emotion adjective and emotion adverbial word, determine the first weighted value and the second weighted value, using the product of described first weighted words and the second weighted value as weighted value corresponding to described label;
In such scheme, described first weighted value refers to the weighted value that described emotion adjective is corresponding, and described second weighted value refers to the weighted value that described emotion adverbial word is corresponding.
Concrete, described emotion model sets up module 32, and for when the product of described first weighted value and described second weighted value is greater than the max-thresholds of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described max-thresholds; When the product of described first weighted value and described second weighted value is less than the minimum threshold of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described minimum threshold.
In another embodiment of the invention, described device also comprises: weighted value arranges module 34, determine the weighted value of described emotion descriptor for setting up module 32 at emotion model before, pre-set the weighted value that weighted value corresponding to emotion adjective in described emotion descriptor or the emotion adjective pre-set in described emotion descriptor and emotion adverbial word are corresponding.
Concrete, described content of multimedia pushing module 33, comprising: second determines submodule and recommend submodule; Wherein,
Described second determines submodule, for determining the affective tag list of user; Determine the list of labels of content of multimedia to be recommended; Determine the similarity of the list of labels of content of multimedia to be recommended and the affective tag list of described user;
Described recommendation submodule, for recommending user by one or more content of multimedia the highest with the affective tag list similarity of described user in content of multimedia to be recommended.
In specific implementation process, above-mentioned evaluation content acquisition module 31, emotion model is set up module 32 and content of multimedia recommending module 33 and weighted value and is arranged module 34, extract submodule, submodule is set, first determines submodule, second determines that submodule and recommendation submodule all can by the central processing unit (CPU in content of multimedia recommendation apparatus, CentralProcessingUnit), microprocessor (MPU, MicroProcessingUnit), digital signal processor (DSP, or programmable logic array (FPGA DigitalSignalProcessor), Field-ProgrammableGateArray) at least one of them realizes.
Application example
With reference to Fig. 4, show based on a kind of content of multimedia recommend method process flow diagram of the present invention, specifically can comprise:
Step 401: content of multimedia list of labels management to be recommended;
Concrete, for adding list of labels by recommended content of multimedia (video, advertisement, commodity), described list of labels can be produced by human-edited, also automatically can generate according to the attribute of content of multimedia to be recommended.Such as, automatically generate according to the performer, subject matter, age, region, background etc. of content of multimedia to be recommended, can also from user to extracting keyword the related commentary of corresponding content of multimedia thus generating labels list.Meanwhile, a weighted value is set for label each in list of labels, is used for representing the degree of correlation of respective labels and corresponding content of multimedia, so often portion's slice, thin piece has a tag set.For example, having a film M1, is the romance movie that star A, B, C perform together, and wherein star A and B is leading role, and the scene of A is very heavy, and C is supporting role, and so the list of labels tag (M1) of this film can be:
Tag (M1)=(star A:1), (star B:0.8), (star C:0.3), (romance movie: 1) };
In superincumbent list of labels, the content bracketed in each bracket is the weighted value of a label and this label, separates between respective labels and weighted value with colon.
It should be noted that the label that can have much larger number in the list of labels of a usual content of multimedia, here in order to example is convenient, only list 4 labels.In above-mentioned list of labels, the value of the weighted value of label between [0,1], when the value of a label more level off to 1 time, the degree of correlation representing this label and corresponding content of multimedia is higher; Accordingly, when the value of a label more level off to 0 time, the degree of correlation representing this label and corresponding content of multimedia is lower.
Step 402: obtain user's evaluation content, and set up the emotion model of user;
In this step, suppose that an exemplary emotion adjective weighted value list is as shown in table 3, the weighted value list that exemplary emotion adverbial word is corresponding is as shown in table 4:
| Emotion adjective | Weighted value |
| Like | 0.8 |
| Interesting | 0.6 |
| Disagreeable | -0.6 |
| Feel sick | -0.9 |
| Do not like | -0.8 |
Table 3
| Emotion adverbial word | Weighted value |
| Very | 1.4 |
| Especially | 1.3 |
| Very | 1.2 |
| A bit | 1.1 |
Table 4
At this moment, obtain user A in a period of time, such as, intraday evaluation content, suppose after the intraday evaluation content extraction of this user, find that user A mentioned " enjoying a lot star A ", " not liking star B ", " liking romance movie ", then can determine that the affective tag of user is feelingtag (A) and is according to above information:
Feelingtag (A)=(star A:0.96), (star B:-0.8), (romance movie: 0.8) }.
Step 403: content of multimedia mates.
Because the affective tag list of user and the list of labels of content of multimedia to be recommended are vector set, and the similarity of vector set can adopt a variety of mode to calculate, such as Euclidean distance, cosine similarity etc.Be described with an example below:
For the affective tag list of user A, now, suppose there are two films: film M1 and M2, its list of labels respectively:
Tag (M1)=(star A:1), (star B:0.2), (romance movie: 1) }
Tag (M1)=(star A:1), (star B:0.8), (romance movie: 0) }
The similarity calculating the list of labels of film M1 and film M2 and the affective tag list of user A according to Euclidean distance is respectively as follows, if the similarity of the affective tag list of film M1 and user A is Similarity (M, M1), set the similarity of the affective tag list of film M2 and user A as Similarity (M, M2), then result of calculation is as follows:
Similarity(M，M1)＝1.021；
Similarity(M，M2)＝1.789；
Can find out that the similarity of the affective tag list of film M1 and user A is lower, therefore, film M1 can be recommended user A.
Implement for embodiment for device, due to itself and embodiment of the method basic simlarity, so description is fairly simple, relevant part illustrates see the part of embodiment of the method.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar part mutually see.
Those skilled in the art should understand, the embodiment of the embodiment of the present invention can be provided as method, device or computer program.Therefore, the embodiment of the present invention can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the embodiment of the present invention can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disk memory, CD-ROM, optical memory etc.) of computer usable program code.
The embodiment of the present invention describes with reference to according to the process flow diagram of the method for the embodiment of the present invention, terminal device (system) and computer program and/or block scheme.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or square frame.These computer program instructions can being provided to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminal equipment to produce a machine, making the instruction performed by the processor of computing machine or other programmable data processing terminal equipment produce device for realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing terminal equipment, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be loaded on computing machine or other programmable data processing terminal equipment, make to perform sequence of operations step to produce computer implemented process on computing machine or other programmable terminal equipment, thus the instruction performed on computing machine or other programmable terminal equipment is provided for the step realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
Although described the preferred embodiment of the embodiment of the present invention, those skilled in the art once obtain the basic creative concept of cicada, then can make other change and amendment to these embodiments.So claims are intended to be interpreted as comprising preferred embodiment and falling into all changes and the amendment of embodiment of the present invention scope.
Finally, also it should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or terminal device and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or terminal device.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the terminal device comprising described key element and also there is other identical element.
Above to a kind of content of multimedia recommend method provided by the present invention and device, be described in detail, apply specific case herein to set forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping; Meanwhile, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (16)
1. a content of multimedia recommend method, is characterized in that, described method comprises:
Obtain the evaluation content of user's input;
The emotion model of user is set up according to described evaluation content;
Emotion model according to the user set up recommends content of multimedia to user.
2. method according to claim 1, is characterized in that, described evaluation content comprises: user carries out the comment evaluated and/or barrage.
3. method according to claim 2, is characterized in that, the described emotion model setting up user according to described evaluation content, comprising: determine the affective tag list of user in different emotions dimension according to described evaluation content; Wherein, described emotion dimension at least comprises: like dimension; Described affective tag list comprises: affective tag and weighted value corresponding to described affective tag.
4. method according to claim 3, is characterized in that, describedly determines the affective tag list of user in different emotions dimension according to described evaluation content, comprising:
The content that emotion descriptor in extraction user evaluation content and described emotion descriptor describe;
Described emotion descriptor can be emotion adjective or emotion adjective and emotion adverbial word;
Affective tag in the corresponding affective tag list of the content that described emotion descriptor describes, the weighted value of the corresponding described affective tag of weighted value of described emotion descriptor.
5. method according to claim 4, is characterized in that, the weighted value of described emotion descriptor is determined by the following method:
When described emotion descriptor only comprises emotion adjective, determine the first weighted value, and described the first weighted value determined is defined as weighted value corresponding to described affective tag; When described emotion descriptor comprises emotion adjective and emotion adverbial word, determine the first weighted value and the second weighted value, using the product of described first weighted words and described second weighted value as weighted value corresponding to described affective tag; Described first weighted value refers to the weighted value that described emotion adjective is corresponding, and described second weighted value refers to the weighted value that described emotion adverbial word is corresponding.
6. method according to claim 5, is characterized in that, when the product of described first weighted value and described second weighted value is greater than the max-thresholds of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described max-thresholds; When the product of described first weighted value and described second weighted value is less than the minimum threshold of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described minimum threshold.
7. method according to claim 5, is characterized in that, before determining the weighted value of described emotion descriptor, described method also comprises:
Pre-set the weighted value that weighted value corresponding to emotion adjective in described emotion descriptor or the emotion adjective pre-set in described emotion descriptor and emotion adverbial word are corresponding.
8. according to the method for claim 3 to 7 according to any one of it, it is characterized in that, the emotion model of the described user according to setting up recommends content of multimedia to user, comprising:
Determine the affective tag list of user;
Determine the list of labels of content of multimedia to be recommended;
Determine the similarity of the list of labels of content of multimedia to be recommended and the affective tag list of described user;
One or more content of multimedia the highest with the affective tag list similarity of described user in content of multimedia to be recommended are recommended user.
9. a content of multimedia recommendation apparatus, is characterized in that, described device comprises: evaluation content acquisition module, emotion model set up module and content of multimedia recommending module; Wherein
Described evaluation content acquisition module, for obtaining the evaluation content of user's input;
Described emotion model sets up module, for setting up the emotion model of user according to described evaluation content;
Described content of multimedia recommending module, for recommending content of multimedia according to the emotion model of the user set up to user.
10. device according to claim 9, is characterized in that, described evaluation content comprises: user carries out the comment evaluated and/or barrage.
11. devices according to claim 10, is characterized in that, described emotion model sets up module, for determining the affective tag list of user in different emotions dimension according to described evaluation content; Wherein, described emotion dimension at least comprises: like dimension; Described affective tag list comprises: affective tag and weighted value corresponding to described affective tag.
12. methods according to claim 11, is characterized in that, described emotion model sets up module, comprise and extract submodule and arrange submodule; Wherein,
Described extraction submodule, for extracting the content that emotion descriptor in user's evaluation content and described emotion descriptor describe; Described emotion descriptor can be emotion adjective or emotion adjective and emotion adverbial word;
Describedly arrange submodule, the curriculum offering for being described by described emotion descriptor is the affective tag in affective tag list, and the weighted value of described emotion descriptor is set to the weighted value of described affective tag.
13. devices according to claim 12, it is characterized in that, described emotion model is set up module and is also comprised first and determine submodule, for only comprising emotion adjective when described emotion descriptor, determine the first weighted value, and described first weighted value is defined as weighted value corresponding to described affective tag; When described emotion descriptor comprises emotion adjective and emotion adverbial word, determine the first weighted value and the second weighted value, the product of described first weighted words and the second weighted value is defined as weighted value corresponding to described affective tag; Described first weighted value refers to the weighted value that described emotion adjective is corresponding, and described second weighted value refers to the weighted value that described emotion adverbial word is corresponding.
14. devices according to claim 13, it is characterized in that, described emotion model sets up module, for when the product of described first weighted value and described second weighted value is greater than the max-thresholds of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described max-thresholds; When the product of described first weighted value and described second weighted value is less than the minimum threshold of weighted value corresponding to described affective tag, getting weighted value corresponding to described affective tag is described minimum threshold.
15. devices according to claim 13, it is characterized in that, described device also comprises: weighted value arranges module, determine the weighted value of described emotion descriptor for setting up module at emotion model before, pre-set the weighted value that weighted value corresponding to emotion adjective in described emotion descriptor or the emotion adjective pre-set in described emotion descriptor and emotion adverbial word are corresponding.
16. according to claim 11 to 15 devices according to any one of it, and it is characterized in that, described content of multimedia pushing module, comprising: second determines submodule and recommend submodule; Wherein,
Described second determines submodule, for determining the affective tag list of user; Determine the list of labels of content of multimedia to be recommended; Determine the similarity of the affective tag list that the list of labels of content of multimedia to be recommended and described user like;
Described recommendation submodule, for recommending user by one or more content of multimedia the highest with the affective tag list similarity of described user in content of multimedia to be recommended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510549931.1A CN105095508B (en) | 2015-08-31 | 2015-08-31 | A kind of multimedia content recommended method and multimedia content recommendation apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510549931.1A CN105095508B (en) | 2015-08-31 | 2015-08-31 | A kind of multimedia content recommended method and multimedia content recommendation apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105095508A true CN105095508A (en) | 2015-11-25 |
| CN105095508B CN105095508B (en) | 2019-11-08 |
Family
ID=54575943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510549931.1A Active CN105095508B (en) | 2015-08-31 | 2015-08-31 | A kind of multimedia content recommended method and multimedia content recommendation apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105095508B (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205699A (en) * | 2015-09-17 | 2015-12-30 | 北京众荟信息技术有限公司 | User label and hotel label matching method and device based on hotel comments |
| CN105574132A (en) * | 2015-12-15 | 2016-05-11 | 海信集团有限公司 | Multimedia file recommendation method and terminal |
| CN105824923A (en) * | 2016-03-17 | 2016-08-03 | 海信集团有限公司 | Movie and video resource recommendation method and device |
| CN105843922A (en) * | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Multimedia classification recommendation method, apparatus and system |
| CN105979338A (en) * | 2016-05-16 | 2016-09-28 | 武汉斗鱼网络科技有限公司 | System and method for matching colors according to emotions of bullet screen contents |
| CN106231428A (en) * | 2016-07-29 | 2016-12-14 | 乐视控股（北京）有限公司 | A kind of video recommendation method and device |
| CN106303675A (en) * | 2016-08-24 | 2017-01-04 | 北京奇艺世纪科技有限公司 | A kind of video segment extracting method and device |
| CN106572399A (en) * | 2016-11-18 | 2017-04-19 | 广州爱九游信息技术有限公司 | Information recommendation method and device, server and user terminal |
| CN106792208A (en) * | 2016-11-24 | 2017-05-31 | 武汉斗鱼网络科技有限公司 | Video preference information processing method, apparatus and system |
| CN106792014A (en) * | 2016-11-25 | 2017-05-31 | 广州酷狗计算机科技有限公司 | A kind of method of recommendation of audio, apparatus and system |
| WO2017101424A1 (en) * | 2015-12-14 | 2017-06-22 | 乐视控股（北京）有限公司 | Single-account multi-preference recommendation method and apparatus for video website |
| CN107197368A (en) * | 2017-05-05 | 2017-09-22 | 中广热点云科技有限公司 | Determine method and system of the user to multimedia content degree of concern |
| CN107509116A (en) * | 2017-09-08 | 2017-12-22 | 咪咕互动娱乐有限公司 | A kind of information-pushing method, device and storage medium |
| CN107547922A (en) * | 2016-10-28 | 2018-01-05 | 腾讯科技（深圳）有限公司 | Information processing method, apparatus and system |
| CN108475388A (en) * | 2015-12-31 | 2018-08-31 | 电子湾有限公司 | The user interface of forward attribute for identification |
| CN108737859A (en) * | 2018-05-07 | 2018-11-02 | 华东师范大学 | Video recommendation method based on barrage and device |
| CN109271423A (en) * | 2018-09-29 | 2019-01-25 | 深圳市轱辘汽车维修技术有限公司 | A kind of object recommendation method, apparatus, terminal and computer readable storage medium |
| CN109284403A (en) * | 2018-11-12 | 2019-01-29 | 珠海格力电器股份有限公司 | The processing method and processing device of media information, storage medium, electronic device |
| CN109862397A (en) * | 2019-02-02 | 2019-06-07 | 广州虎牙信息科技有限公司 | A kind of video analysis method, apparatus, equipment and storage medium |
| 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 |
| CN110267111A (en) * | 2019-05-24 | 2019-09-20 | 平安科技（深圳）有限公司 | Video barrage analysis method, device and storage medium, computer equipment |
| WO2019184054A1 (en) * | 2018-03-29 | 2019-10-03 | 网宿科技股份有限公司 | Method and system for processing on-screen comment information |
| WO2019214336A1 (en) * | 2018-05-10 | 2019-11-14 | 苏州跃盟信息科技有限公司 | Content pushing method and apparatus, and machine readable storage medium |
| CN113704630A (en) * | 2021-10-27 | 2021-11-26 | 武汉卓尔数字传媒科技有限公司 | Information pushing method and device, readable storage medium and electronic equipment |
| CN113766281A (en) * | 2021-09-10 | 2021-12-07 | 北京快来文化传播集团有限公司 | Short video recommendation method, electronic device and computer-readable storage medium |
| CN117312658A (en) * | 2023-09-08 | 2023-12-29 | 广州风腾网络科技有限公司 | Popularization method and system based on big data analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102387207A (en) * | 2011-10-21 | 2012-03-21 | 华为技术有限公司 | Push method and system based on user feedback information |
| US20120179751A1 (en) * | 2011-01-06 | 2012-07-12 | International Business Machines Corporation | Computer system and method for sentiment-based recommendations of discussion topics in social media |
| CN102611785A (en) * | 2011-01-20 | 2012-07-25 | 北京邮电大学 | Personalized active news recommending service system and method for mobile phone user |
| CN103678329A (en) * | 2012-09-04 | 2014-03-26 | 中兴通讯股份有限公司 | Recommendation method and device |
| CN103714071A (en) * | 2012-09-29 | 2014-04-09 | 株式会社日立制作所 | Label emotional tendency quantifying method and label emotional tendency quantifying system |
| CN104331451A (en) * | 2014-10-30 | 2015-02-04 | 南京大学 | Recommendation level scoring method for theme-based network user comments |
-
2015
- 2015-08-31 CN CN201510549931.1A patent/CN105095508B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120179751A1 (en) * | 2011-01-06 | 2012-07-12 | International Business Machines Corporation | Computer system and method for sentiment-based recommendations of discussion topics in social media |
| CN102611785A (en) * | 2011-01-20 | 2012-07-25 | 北京邮电大学 | Personalized active news recommending service system and method for mobile phone user |
| CN102387207A (en) * | 2011-10-21 | 2012-03-21 | 华为技术有限公司 | Push method and system based on user feedback information |
| CN103678329A (en) * | 2012-09-04 | 2014-03-26 | 中兴通讯股份有限公司 | Recommendation method and device |
| CN103714071A (en) * | 2012-09-29 | 2014-04-09 | 株式会社日立制作所 | Label emotional tendency quantifying method and label emotional tendency quantifying system |
| CN104331451A (en) * | 2014-10-30 | 2015-02-04 | 南京大学 | Recommendation level scoring method for theme-based network user comments |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205699A (en) * | 2015-09-17 | 2015-12-30 | 北京众荟信息技术有限公司 | User label and hotel label matching method and device based on hotel comments |
| WO2017101424A1 (en) * | 2015-12-14 | 2017-06-22 | 乐视控股（北京）有限公司 | Single-account multi-preference recommendation method and apparatus for video website |
| CN105574132A (en) * | 2015-12-15 | 2016-05-11 | 海信集团有限公司 | Multimedia file recommendation method and terminal |
| CN108475388A (en) * | 2015-12-31 | 2018-08-31 | 电子湾有限公司 | The user interface of forward attribute for identification |
| US11544776B2 (en) | 2015-12-31 | 2023-01-03 | Ebay Inc. | System, method, and media for identifying top attributes |
| CN105824923A (en) * | 2016-03-17 | 2016-08-03 | 海信集团有限公司 | Movie and video resource recommendation method and device |
| CN105843922A (en) * | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Multimedia classification recommendation method, apparatus and system |
| CN105979338A (en) * | 2016-05-16 | 2016-09-28 | 武汉斗鱼网络科技有限公司 | System and method for matching colors according to emotions of bullet screen contents |
| CN105979338B (en) * | 2016-05-16 | 2019-07-09 | 武汉斗鱼网络科技有限公司 | A kind of system and method according to barrage content mood matching color |
| CN106231428A (en) * | 2016-07-29 | 2016-12-14 | 乐视控股（北京）有限公司 | A kind of video recommendation method and device |
| CN106303675B (en) * | 2016-08-24 | 2019-11-15 | 北京奇艺世纪科技有限公司 | A kind of video clip extracting method and device |
| CN106303675A (en) * | 2016-08-24 | 2017-01-04 | 北京奇艺世纪科技有限公司 | A kind of video segment extracting method and device |
| CN107547922A (en) * | 2016-10-28 | 2018-01-05 | 腾讯科技（深圳）有限公司 | Information processing method, apparatus and system |
| CN106572399A (en) * | 2016-11-18 | 2017-04-19 | 广州爱九游信息技术有限公司 | Information recommendation method and device, server and user terminal |
| CN106792208A (en) * | 2016-11-24 | 2017-05-31 | 武汉斗鱼网络科技有限公司 | Video preference information processing method, apparatus and system |
| CN106792014A (en) * | 2016-11-25 | 2017-05-31 | 广州酷狗计算机科技有限公司 | A kind of method of recommendation of audio, apparatus and system |
| CN106792014B (en) * | 2016-11-25 | 2019-02-26 | 广州酷狗计算机科技有限公司 | A kind of method, apparatus and system of recommendation of audio |
| CN107197368B (en) * | 2017-05-05 | 2019-10-18 | 中广热点云科技有限公司 | Determine user to the method and system of multimedia content degree of concern |
| CN107197368A (en) * | 2017-05-05 | 2017-09-22 | 中广热点云科技有限公司 | Determine method and system of the user to multimedia content degree of concern |
| CN107509116A (en) * | 2017-09-08 | 2017-12-22 | 咪咕互动娱乐有限公司 | A kind of information-pushing method, device and storage medium |
| WO2019184054A1 (en) * | 2018-03-29 | 2019-10-03 | 网宿科技股份有限公司 | Method and system for processing on-screen comment information |
| CN108737859A (en) * | 2018-05-07 | 2018-11-02 | 华东师范大学 | Video recommendation method based on barrage and device |
| WO2019214336A1 (en) * | 2018-05-10 | 2019-11-14 | 苏州跃盟信息科技有限公司 | Content pushing method and apparatus, and machine readable storage medium |
| 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 |
| CN109271423A (en) * | 2018-09-29 | 2019-01-25 | 深圳市轱辘汽车维修技术有限公司 | A kind of object recommendation method, apparatus, terminal and computer readable storage medium |
| CN109284403A (en) * | 2018-11-12 | 2019-01-29 | 珠海格力电器股份有限公司 | The processing method and processing device of media information, storage medium, electronic device |
| CN109862397B (en) * | 2019-02-02 | 2021-11-09 | 广州虎牙信息科技有限公司 | Video analysis method, device, equipment and storage medium |
| CN109862397A (en) * | 2019-02-02 | 2019-06-07 | 广州虎牙信息科技有限公司 | A kind of video analysis method, apparatus, equipment and storage medium |
| CN110267111A (en) * | 2019-05-24 | 2019-09-20 | 平安科技（深圳）有限公司 | Video barrage analysis method, device and storage medium, computer equipment |
| CN113766281A (en) * | 2021-09-10 | 2021-12-07 | 北京快来文化传播集团有限公司 | Short video recommendation method, electronic device and computer-readable storage medium |
| CN113704630A (en) * | 2021-10-27 | 2021-11-26 | 武汉卓尔数字传媒科技有限公司 | Information pushing method and device, readable storage medium and electronic equipment |
| CN117312658A (en) * | 2023-09-08 | 2023-12-29 | 广州风腾网络科技有限公司 | Popularization method and system based on big data analysis |
| CN117312658B (en) * | 2023-09-08 | 2024-04-09 | 广州风腾网络科技有限公司 | Popularization method and system based on big data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105095508B (en) | 2019-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105095508A (en) | Multimedia content recommendation method and multimedia content recommendation apparatus | |
| JP6855595B2 (en) | Using machine learning to recommend live stream content | |
| CN106331778B (en) | Video recommendation method and device | |
| CN109033149B (en) | Information recommendation method and device, server and storage medium | |
| CN104199896A (en) | Video similarity determining method and video recommendation method based on feature classification | |
| CN105975472A (en) | Method and device for recommendation | |
| CN104504059A (en) | Multimedia resource recommending method | |
| CN103929653A (en) | Enhanced real video generator and player, generating method of generator and playing method of player | |
| CN104636371A (en) | Information recommendation method and device | |
| CN112511854A (en) | Live video highlight generation method, device, medium and equipment | |
| US11907817B2 (en) | System and methods for machine learning training data selection | |
| CN112507163A (en) | Duration prediction model training method, recommendation method, device, equipment and medium | |
| López-Nores et al. | Cloud-based personalization of new advertising and e-commerce models for video consumption | |
| CN103942247A (en) | Information providing method and device of multimedia resources | |
| CN107948755B (en) | Video content recommendation method and system combining user watching duration | |
| CN112015736B (en) | Multi-functional recommendation method and device based on Spark Mllib | |
| Daneshi et al. | Eigennews: Generating and delivering personalized news video | |
| CN113627983A (en) | Network advertisement promotion method and system based on video creativity | |
| Wang et al. | Exploiting content relevance and social relevance for personalized ad recommendation on internet TV | |
| WO2021025681A1 (en) | Event progress detection in media items | |
| US20230105830A1 (en) | Matching video content to podcast episodes | |
| US11488042B1 (en) | Dynamic determination of media consumption | |
| US11948172B2 (en) | Rendering a dynamic endemic banner on streaming platforms using content recommendation systems and content affinity modeling | |
| Scurtu et al. | Audiovisual descriptors for a linguistic educational engine | |
| CN110909206B (en) | Method and device for outputting information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |