CN109558500A - Multimedia sequence generation method, medium, device and calculating equipment - Google Patents
Multimedia sequence generation method, medium, device and calculating equipment Download PDFInfo
- Publication number
- CN109558500A CN109558500A CN201811393179.6A CN201811393179A CN109558500A CN 109558500 A CN109558500 A CN 109558500A CN 201811393179 A CN201811393179 A CN 201811393179A CN 109558500 A CN109558500 A CN 109558500A
- Authority
- CN
- China
- Prior art keywords
- multimedia
- candidate
- sequence
- label
- user
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Embodiments of the present invention provide a kind of multimedia sequence generation method, device, medium and electronic equipment.The multimedia sequence generation method includes: to obtain the first label for referring to multimedia sequence；Calculate the first similarity of candidate multimedia second label and first label；The first minor sort is carried out to the candidate multimedia according to first similarity and obtains candidate collection；The second minor sort is carried out to the candidate collection according to the preference data of user and obtains destination multimedia sequence.Destination multimedia sequence is generated by reference to multimedia sequence, method of the invention quickly can recommend multimedia to user, to improve the efficiency of Multimedia Recommendation significantly, bring better experience for user.
Description
Technical field
Embodiments of the present invention are related to communication and field of computer technology, more specifically, embodiments of the present invention relate to
And a kind of multimedia sequence generation method, storage medium, multimedia sequence generating means and calculating equipment.
Background technique
Background that this section is intended to provide an explanation of the embodiments of the present invention set forth in the claims or context.Herein
Description recognizes it is the prior art not because not being included in this section.
With the fast development of internet, the form of multimedia messages is more and more abundant, such as music, animation, video etc.
Deng.
Currently, having had already appeared with the client for playing multimedia messages function.By taking music class client as an example, user
When playing music on the client, client can collect the music that user has played, thus the happiness listened to music according to user
It is good to recommend song to user.However, the hobby of user needs long-term accumulation that could generate, such user must be in a certain client
End keeps listening the habit of song, and client can obtain the hobby data that user listens song.Also, the user of new registration is come
It says, also the not no hobby data of user, can not generate and song is recommended to recommend to user.
Summary of the invention
But for collecting the reason of user preference data needs the plenty of time, the prior art can not quickly generate more matchmakers
Body is recommended to user.
Thus, it is also very desirable to a kind of improved multimedia sequence generation method, so as to be pushed away according to multimedia sequence to user
Recommend multimedia.
In the present context, embodiments of the present invention be intended to provide a kind of multimedia sequence generation method, storage medium,
Multimedia sequence generating means and calculating equipment.
In the first aspect of embodiment of the present invention, a kind of multimedia sequence generation method is provided, comprising: obtain ginseng
Examine the first label of multimedia sequence；Calculate the first similarity of candidate multimedia second label and first label；Root
The first minor sort is carried out to candidate multimedia according to the first similarity and obtains candidate collection；According to the preference data of user to Candidate Set
It closes the second minor sort of progress and obtains destination multimedia sequence.
Optionally, candidate multimedia is carried out the first minor sort to obtain candidate collection including: basis according to the first similarity
The result of first minor sort chooses the candidate multimedia of the first quantity and forms candidate collection, wherein the candidate in candidate collection is more
Media are arranged according to the result of the first minor sort.
Optionally, the second minor sort is carried out to candidate collection according to the preference data of user and obtains destination multimedia sequence packet
It includes: the candidate multimedia composition destination multimedia sequence of the second quantity being chosen according to the result of the second minor sort, wherein the second number
Amount is less than or equal to the first quantity.
Optionally, the first label includes multiple first subtabs, and the second label includes multiple second subtabs；It calculates candidate
First similarity of multimedia second label and the first label may include: by multiple second subtabs respectively with multiple first
Subtab carries out first time matching；First is obtained according to matched result and multiple respective weighted values of second subtab for the first time
Similarity.
Optionally, the preference data of user includes multiple third subtabs；According to the preference data of user to the candidate
Set carry out the second minor sort obtain destination multimedia sequence include: by multiple third subtabs respectively with matchmakers more in candidate collection
Second subtab of body carries out second and matches；Multimedia in candidate collection is arranged in first time according to second of matched result
Precedence in sequence is promoted, reduced or is remained unchanged.
Optionally, multiple first subtabs include: at least one first subtab being directed to reference to multimedia sequence, and/
Or for reference at least one each multimedia first subtab in multimedia sequence.
Optionally, the first subtab or the second subtab include at least one of: style information, type information, languages
Information, temporal information, author information.
It optionally, can also include: that destination multimedia sequence is saved as into multimedia after obtaining destination multimedia sequence
Set, for selection by the user；Or playlist is generated according to destination multimedia sequence and is played out.
Optionally, above-mentioned multimedia may include: one of image, text, animation, video, music or a variety of.
It optionally, can also include: in reference multimedia sequence before obtaining the first label with reference to multimedia sequence
Displaying interface in show the first control；When detecting the first operation for the first control, start obtain with reference to more
The step of first label of media sequence.
In the second aspect of embodiment of the present invention, a kind of storage medium is provided, program is stored thereon with, the program
Above-mentioned multimedia sequence generation method may be implemented when being executed by processor.
In the third aspect of embodiment of the present invention, a kind of multimedia sequence generating means are provided, comprising: multimedia
Acquiring unit, for obtaining the first label for referring to multimedia sequence；Similarity calculated, it is candidate multimedia for calculating
First similarity of the second label and the first label；Sequencing unit, for carrying out the to candidate multimedia according to the first similarity
One minor sort obtains candidate collection；Multimedia sequence determination unit, for being carried out according to the preference data of user to candidate collection
Second minor sort obtains destination multimedia sequence.
In the fourth aspect of the invention, a kind of calculating equipment, including processor and memory, memory storage are provided
There is executable instruction, the executable instruction that processor is used to that memory to be called to store executes such as above-mentioned multimedia sequence generation side
Method.
Optionally, sequencing unit includes: the first sequencing unit, for choosing the first quantity according to the result of the first minor sort
A candidate's multimedia forms candidate collection, wherein the candidate multimedia in candidate collection is carried out according to the result of the first minor sort
Arrangement.
Optionally, multimedia sequence determination unit includes: the second sequencing unit, for the knot according to second minor sort
Fruit chooses the described candidate multimedia of the second quantity and forms the destination multimedia sequence, wherein second quantity be less than or
Equal to first quantity.
Optionally, the first label may include multiple first subtabs, and the second label may include multiple second subtabs；
Thus similarity calculated may include: the first matching unit, for multiple second subtabs are sub with multiple first respectively
Label carries out first time matching；Similarity acquiring unit, for each according to matched result and multiple second subtabs for the first time
From weighted value obtain the first similarity.
Optionally, the preference data of user may include multiple third subtabs；Thus multimedia sequence determination unit can
To include: the second matching unit, for by multiple third subtabs respectively with the second subtab multimedia in candidate collection into
Second of matching of row；Sequence adjustment unit, for second of matched result of basis to multimedia in candidate collection for the first time
Precedence in sequence is promoted, reduced or is remained unchanged.
Optionally, multimedia acquiring unit may include: subtab determination unit, for determining for reference to multimedia sequence
At least one first subtab of column, and/or for reference at least one each multimedia first subtab in multimedia sequence.
Optionally, similarity calculated can be also used for: determine the first subtab or the second subtab include with down toward
It is one of few: style information, type information, language information, temporal information, author information.
Optionally, multimedia sequence determination unit can also include: recommendation unit, for saving destination multimedia sequence
For multimedia collections, for selection by the user；Or playlist is generated according to destination multimedia sequence and is played out.
Optionally, above-mentioned multimedia sequence generating means can also include: page presentation unit, in reference multimedia
The first control is shown in the displaying interface of sequence；Trigger unit, for opening when detecting the first operation for the first control
The step of beginning obtain the first label for referring to multimedia sequence.
Optionally, the multimedia in above-mentioned multimedia sequence generating means may include: image, text, animation, video,
One of music is a variety of.
The destination multimedia sequence that embodiment generates according to the present invention can recommend multimedia to user, thus significantly
Ground improves the efficiency of Multimedia Recommendation, brings better experience for user.
Detailed description of the invention
The following detailed description is read with reference to the accompanying drawings, above-mentioned and other mesh of exemplary embodiment of the invention
, feature and advantage will become prone to understand.In the accompanying drawings, if showing by way of example rather than limitation of the invention
Dry embodiment, in which:
Fig. 1 schematically shows first process of the multimedia sequence generation method of embodiment according to the present invention
Figure；
Fig. 2 schematically shows second processes of the multimedia sequence generation method of embodiment according to the present invention
Figure；
Fig. 3 schematically shows one in the multimedia sequence generation method implementation process of embodiment according to the present invention
Kind interactive interface figure；
Fig. 4 schematically shows another in the multimedia sequence generation method implementation process of embodiment according to the present invention
A kind of interactive interface figure；
Fig. 5 diagrammatically illustrates the third flow chart of the multimedia sequence generation method of embodiment according to the present invention；
Fig. 6 diagrammatically illustrates the 4th flow chart of the multimedia sequence generation method of embodiment according to the present invention；
Fig. 7 schematically shows the block diagram of the multimedia sequence generating means of embodiment according to the present invention.
In the accompanying drawings, identical or corresponding label indicates identical or corresponding part.
Specific embodiment
The principle and spirit of the invention are described below with reference to several illustrative embodiments.It should be appreciated that providing this
A little embodiments are used for the purpose of making those skilled in the art can better understand that realizing the present invention in turn, and be not with any
Mode limits the scope of the invention.On the contrary, thesing embodiments are provided so that the present invention is more thorough and complete, and energy
It enough will fully convey the scope of the invention to those skilled in the art.
One skilled in the art will appreciate that embodiments of the present invention can be implemented as a kind of system, device, equipment, method
Or computer program product.Therefore, the present invention can be with specific implementation is as follows, it may be assumed that complete hardware, complete software
The form that (including firmware, resident software, microcode etc.) or hardware and software combine.
Embodiment according to the present invention proposes a kind of method and apparatus that multimedia sequence generates.
Herein, it is to be understood that related term client indicates the application operated in operating system, example
Such as the application of music class, video class application.User opens some interface in client, and client can transmit a request to server,
Server returned data and presentation user interface.User carries out input operation on the interface of client, and client can be sent
Data are to server, product servers storing data.
Related multimedia sequence can indicate multiple multimedia combinations.It can be with certain between these multimedias
Sequence is combined, such as the list etc. that multiple multimedias are formed；Alternatively, these multimedias can also be with random combine shape together
At set.For example, multimedia sequence can be song list, book list, video album, playlist etc..
The single set that can be indicated song sequence combination and be formed of related term song, the side that can be combined according to song
Formula assigns different themes to song is single, such as song list, " popular song " song of " Chinese songster " theme are single, " heat song list " song is single
Etc..
Related term list of songs can indicate a kind of form that song is organized using table as container, and song can be with
It is arranged according to certain linear precedence.
The label of related song or song list can indicate when song or song are singly saved into database by operation personnel institute
The label done.The song label can be used to categorizing songs, and a song may include one or more labels, and a song is single
Also one or more labels be may include.Label can indicate that song languages, song style, types of songs, song writer etc. believe
Breath, such as: Guangdong language prevalence, rock and roll, new era, rural area, Chinese musical telling hip-hop, world music, test, light music, the American-European popular, people
Ballad, atypical independence, thunder ghost, Blues, jazz, metal, Latin, Chinese prevalence, ancient customs, allusion, electric sound, Chinese, English, Zhou Jielun
Etc..
In addition, any number of elements in attached drawing is used to example rather than limitation and any name are only used for distinguishing,
Without any restrictions meaning.
Below with reference to several representative embodiments of the invention, the principle and spirit of the present invention are explained in detail.
Summary of the invention
The inventors discovered that user, in client terminal playing music, client can listen song habit to generate use according to user
The hobby data at family recommend other resources to user by the hobby data of user.It is needed according to this mode user at present
A very long time keeps using client, and client just can determine that the hobby data of user, recommends song to user, causes to give birth to
It is longer at the time needed for song recommended to the user.
Therefore, embodiments of the present invention provide a kind of multimedia sequence generation method, storage medium, multimedia sequence
Generating means and calculate equipment, thus reduce significantly generate recommend song time, improve the efficiency of song recommendations.
After introduced the basic principles of the present invention, lower mask body introduces various non-limiting embodiment party of the invention
Formula.
Application scenarios overview
It should be noted which is shown only for the purpose of facilitating an understanding of the spirit and principles of the present invention for following application scenarios, this
The embodiment of invention is unrestricted in this regard.On the contrary, embodiments of the present invention can be applied to it is applicable any
Scene.
User in client terminal playing multimedia messages needs that a very long time is spent to be maintained at same client progress
It plays, which could collect the hobby data of user, to recommend other multimedias to user according to the hobby of user, supply
User selects to play.
Illustrative methods
Below with reference to above-mentioned application scenarios, the more of illustrative embodiments according to the present invention are described referring to figs. 1 to Fig. 6
Media sequence generation method.
Firstly, Fig. 1 diagrammatically illustrates first stream of the multimedia sequence generation method of embodiment according to the present invention
Cheng Tu.
Shown in referring to Fig.1, the multimedia sequence generation method of embodiment of the present invention may include:
Step S11. obtains the first label for referring to multimedia sequence；
Step S12. calculates the first similarity of candidate multimedia second label and first label；
Step S13. carries out the first minor sort to the candidate multimedia according to first similarity and obtains candidate collection；
Step S14. carries out the second minor sort to the candidate collection according to the preference data of user and obtains destination multimedia
Sequence.
Multimedia sequence production method shown in FIG. 1 can calculate first according to the first label of reference multimedia sequence
First similarity of label and candidate multimedia second label, and candidate multimedia is ranked up according to the first similarity
To candidate collection, the candidate collection of destination multimedia sequence is obtained according to the first similarity to realize, saves and collects user
The time for liking data improves the efficiency of multimedia generation；And it can be when there is user preference data further to candidate
Multimedia sequence is adjusted, and obtains destination multimedia sequence, improves user experience.
The realization details of each step shown in Fig. 1 is described in detail below:
In step s 11, the first label for referring to multimedia sequence is obtained.
It may include multiple multimedias with reference to multimedia sequence, or may include a variety of in this illustrative embodiment
Multimedia of type, such as music, video etc..Also, it can also be according to certain with reference to the multimedia in multimedia sequence
Sequence arranges, for example, can be arranged in order according to the time order and function that user plays with reference to the multimedia in multimedia sequence；?
Can be arranged according to frequency size order of the user to each multimedia broadcasting etc..It certainly, can also be only with reference to multimedia sequence
It is some multimedia set, does not put in order explicitly.The multimedia sequence can also be a variety of multimedia combinations, example
Such as, a variety of multimedias are formed together list, a variety of multimedia set etc..This example embodiment does not do special limit to this
It is fixed.Wherein, multimedia may include various forms of information, such as image, text, animation, video, music, audiobook, radio station
Broadcast etc..
The first label with reference to multimedia sequence may include the label being directed to reference to multimedia sequence, such as song list
Label, theme of video intersection etc.；It also may include the multimedia label being directed to reference to including in multimedia sequence, such as
Label, label of video of song etc..Also, the first label may include multiple first subtabs.First subtab can be with
Mark multimedia feature, such as style, the languages of song, the corresponding singer of song, the type of song of song etc.；It can also
To mark the feature of multimedia sequence, such as sing the theme etc. of single theme, animated series.That is, first label
It may include being directed to the first subtab with reference to multimedia sequence and being directed to reference in multimedia sequence multimedia first
Subtab；Alternatively, first label can only include the first subtab being directed to reference to multimedia sequence, or only include needle
For the first subtab multimedia in reference multimedia sequence；This example embodiment does not do particular determination to this.
It in some embodiments of the invention, can also include a displaying interface, it can be by this with reference to multimedia sequence
Show that interface is shown, so that user is checked and played with reference to the multimedia in multimedia sequence.Optionally, it is obtaining
Before the first label with reference to multimedia sequence, the present embodiment can also include step S21 and step S22, as shown in Figure 2.
Fig. 2 diagrammatically illustrates second flow chart of the multimedia sequence generation method of embodiment according to the present invention.
In the step s 21, the first control can be shown in the displaying interface of reference multimedia sequence.First control can be with
Including the virtual control added in the displaying interface, such as virtual push button etc.；Or it is also possible to a virtual region, this implementation
Example does not do particular determination to this.In step S22, when detecting the first operation for the first control, it can start to carry out
The step of obtaining the first label for referring to multimedia sequence.Specifically, monitoring event can be added for the first control, in the prison
When event being listened to detect the first operation, the operation for obtaining the first label can be triggered.First operation can be user and set in display
Standby upper interactive operation, such as press the button, click screen etc.；Or it is also possible to other interactive operations, such as interactive voice
Operation etc..
Fig. 3 diagrammatically illustrates one of multimedia sequence generation method implementation process of embodiment according to the present invention
Interactive interface figure.
Fig. 4 diagrammatically illustrates another in the multimedia sequence generation method implementation process of embodiment according to the present invention
Kind interactive interface figure.
As shown in figure 3, in an alternate embodiment of the invention, the first control may be displayed on the displaying interface with reference to multimedia sequence
Top, the position as shown in N in Fig. 3, user can by click N, select triggered multimedia recommend function, and then start
It executes and obtains with reference to the step of multimedia first label.Wherein, N can be used as the first control, and user can pass through various friendships
The monitoring event of interoperability triggering N, the interactive operation can be used as the first operation, such as finger clicks the position etc. of N.In addition,
First control can otherwise be shown, such as M shown in Fig. 4, and user can be obtained by the first operation of M to trigger
With reference to multimedia first label etc.；This example embodiment does not do particular determination to this.
Optionally, triggering, which obtains the first label, can first carry out control N's by control N shown in Fig. 3, user
Operation shows control M in showing interface, as shown in Figure 4 after detecting the operation of N.User can further trigger M's
Operation, so that the step of obtaining the first label starts to execute.It is of course also possible to start to obtain the first label by other means,
Such as showing interface long-pressing control N, into displayings interface shown in Fig. 4 after click M and can start to obtain first label etc.,
Example embodiment does not do particular determination to this.It is understood that the displaying interface may include other interaction effects, such as
Display is distinguished, when detecting the first operation to the first control progress color, is shown showing that a certain region highlight by interface
Show etc., this example embodiment does not do particular determination to this.
With reference to Fig. 1, in step s 12, it is similar to the first of the first label that candidate multimedia second label can be calculated
Degree.
Candidate multimedia may include various types of multimedias, such as animation, music etc..Candidate multimedia can also be
It is not included in reference to other multimedias in multimedia.Multimedia can be stored in multimedia database or multimedia clothes
It is engaged in device, when playing multimedia client request acquisition multimedia resource, can be obtained from the server or database
Take corresponding multimedia resource.When saving multimedia, operation personnel can be marked multimedia, in order to distinguish, because
This each multimedia can have multiple labels.As the first tag class, the second label can also have multiple second subtabs.
Perhaps the second subtab can indicate multimedia various features or or indicate each of multimedia sequence first subtab
Kind feature；For example, the first subtab or the second subtab can indicate that the style of multimedia or multimedia sequence (is such as shaken
Roll, pursue a goal with determination, express one's emotion), type (such as popular, classics), languages (such as Chinese, English, Japanese), temporal information (such as deliver
Time, play time etc.) and author (such as creator, singer) etc..In addition, the first subtab or the second subtab may be used also
To indicate other information, such as multimedia or evaluation information, the propagation quantity of multimedia sequence etc..
The first similarity for calculating the first label and the second label can be by being by the first label and second are label converting
Feature vector, to calculate the similarity between feature vector to calculate.Similarity between feature vector can pass through cosine
Similarity algorithm calculates.Alternatively, similarity, such as Pearson correlation coefficients algorithm etc. can also be calculated by other algorithms.And
And the similarity between them can also be indicated with the distance between feature vector, thus the calculating of similarity can also lead to
Cross the algorithm progress for calculating distance, such as Euclidean distance etc..Optionally, calculating the first similarity can also be calculated by machine learning
Method carries out, this example embodiment does not do particular determination to this.
Fig. 5 diagrammatically illustrates the third flow chart of the multimedia sequence generation method of embodiment according to the present invention.
In some embodiments of the invention, the first similarity of candidate multimedia second label and the first label is calculated
It may include step S51 to step S52, as shown in Figure 5.
In step s 51, multiple second subtabs can be subjected to first time matching with multiple first subtabs respectively.It is logical
It crosses and is compared the second subtab and the first subtab one by one, can determine every one second subtab and every one first subtab
First time matched result.The first time matched result can indicate the matching journey of the first subtab and the second subtab
Degree or similarity degree.Therefore, first time can be obtained by calculating the similarity of the first subtab and the second subtab
The result matched.Also, candidate multimedia can also be handled according to matched result for the first time.For example, it can incite somebody to action
Second subtab is filtered with the completely unmatched candidate multimedia of the first subtab, reduces subsequent calculation amount；Or it presses
Candidate multimedia is ranked up according to matching result.
Then, in step S52, first can be obtained according to the weighted value of matched result and the second subtab for the first time
Similarity.For example, if the weight of certain the second subtab is 1.2, the first of second subtab and certain the first subtab
Secondary matching result is 0.5, then can be by the product of calculating 1.2 and 0.5, using obtained result as the first similarity.When
So, the first similarity can also be obtained by other means, such as there are can match to first time when multiple first subtabs
Result also determine a weight, and then by the product of matched result for the first time and the weight again with the weight phase of the second subtab
Multiply, using obtained result as the first similarity.
It continues to refer to figure 1, in step s 13, the first minor sort can be carried out to candidate multimedia according to the first similarity
Obtain candidate collection.
It, can be according to the size of the first similarity to candidate after obtaining the first similarity in this example embodiment
Multimedia carries out the first minor sort.Candidate multimedia can be ranked up from big to small with similarity, or with similarity from small
To being ranked up greatly.After the sequence of candidate multimedia, a certain number of candidate multimedias can be chosen from ranking results and are obtained
To candidate collection.It therefore, may include the biggish candidate multimedia of similarity in the candidate collection, and then when user needs
Time extracts the biggish candidate Multimedia Recommendation of similarity to user, to improve recommendation efficiency from this collection.Alternatively, can also
To obtain candidate collection by other means, such as screening similarity is greater than the candidate multimedia of preset threshold to obtain candidate
Set etc..
Optionally, the candidate multimedia composition candidate collection of the first quantity can be chosen according to the result of the first minor sort,
And the candidate multimedia in candidate collection can be arranged according to the result of the first minor sort.Wherein, candidate multimedia can
To arrange according to the size order of similarity, and then top n candidate's Multimedia Combination candidate collection can be chosen.Alternatively, can also
With candidate Multimedia Combination candidate collection N number of after selection.Also, the candidate multimedia in candidate collection can be still according to first
The result of sequence is ranked up, that is, the multimedia in candidate collection can be arranged according to the size order of the first similarity.It obtains
After candidate collection, candidate collection can be recommended into user, user is allowed to play the multimedia in candidate collection；Alternatively,
Playlist can also be generated according to candidate collection, and then plays candidate multimedia.In addition, the first quantity can according to need and set
It is fixed, such as 100,50 etc.；Or it is also possible to other numerical value, such as 20 etc., this example embodiment is not spy to this
It is different to limit.
In step S14, the second minor sort can be carried out to candidate collection according to the preference data of user, it is more to obtain target
Media sequence.
In the exemplary embodiment, the multimedia that can be played according to user determines the preference data of user.In detail
For, if the frequency of the multimedia of certain label is higher in the multimedia that user plays, user can be determined to this
The multimedia of label compares preference.It therefore may include multiple third subtabs in the preference data of user.And then it can basis
The preference data of user carries out the second minor sort to candidate collection, that is, the multimedia in candidate collection is according to the first minor sort
Sequence arrangement after, the sequence can be adjusted to form a new sequence by user preference data, to obtain
Destination multimedia sequence.Multimedia in destination multimedia sequence can be arranged in a certain order, such as similarity
The sequence of size；It can also carry out random alignment, that is, destination multimedia sequence can be used as a set.
In some embodiments, step can be passed through by carrying out the second minor sort to candidate collection according to the preference data of user
S61 and step S62, as shown in fig. 6, Fig. 6 diagrammatically illustrates the multimedia sequence generation method of embodiment according to the present invention
The 4th flow chart.
With reference to Fig. 6, in step S61, can by the multiple third subtabs for including in user preference data respectively with time
Multimedia second subtab carries out second of matching in selected works conjunction.Wherein, third subtab can be carried out with the second subtab
Match one by one, thus obtain second it is matched as a result, the matching result can indicate the second subtab and third subtab it
Between matching degree or similarity degree.Therefore, the second phase of calculating each second subtab and each third subtab can be passed through
Like degree, using second similarity as matching result.However, it is also possible to the matching result is calculated in other ways, such as
Machine learning algorithm, CF algorithm etc. can be passed through.
In turn, in step S62, can according to second matched result to the multimedia in candidate collection for the first time
Precedence in sequence is promoted, reduced or is remained unchanged.Specifically, if the matching of the second subtab and third subtab
As a result more than the first matching threshold, then can by precedence of the candidate multimedia comprising the second subtab in candidate collection into
Row is promoted, other corresponding candidate multimedia precedences can reduce accordingly, or remain unchanged.The precedence grade promoted every time
Number determines according to actual conditions, such as can promote 1,2,5 etc. every time, this example embodiment does not do special limit to this
It is fixed.Such as can promote the 10th candidate multimedia to the 5th, then the multimedia of original serial number 5 to 9 moves backward 1,
Originally the multimedia precedence after serial number 11 and 11 remains unchanged.Also, if second of matching result is lower than second
Matching threshold, then precedence of the corresponding candidate multimedia in candidate collection can be reduced；If second of matching result
Between the first matching threshold and the second matching threshold, then position of the corresponding candidate multimedia in candidate collection can be determined
It is secondary to remain unchanged.
It in some embodiments, can be according to the result of the second minor sort after carrying out the second minor sort to candidate collection
The candidate multimedia composition destination multimedia sequence of the second quantity is chosen, and the second quantity can be less than or equal to the first number
Amount.For example, the top n multimedia composition destination multimedia sequence in second of ranking results can be chosen.Wherein, the second quantity
It can be the numerical value less than the first quantity, for example, if the first quantity is 50, then the second quantity can be 45,30 etc.；Also,
Second quantity can also be equal to the first quantity, that is, can be no longer after carrying out the second minor sort for the multimedia in candidate collection
It is filtered, all candidate multimedias in candidate collection is retained into destination multimedia sequence.
Optionally, after obtaining destination multimedia sequence, destination multimedia sequence can also be saved as multimedia collections,
For selection by the user；It is played out alternatively, generating playlist according to destination multimedia sequence.Wherein, by destination multimedia sequence
Multimedia in column saves as multimedia collections, which can save in the database or in server, in turn
It is shown in client to user and recommends the multimedia collections.Recommend destination multimedia sequence to user for convenience, it can be with root
It is that the multimedia collections are named according to multimedia label each in the multimedia collections, in order to recommend to user.Citing
For, if multimedia in the multimedia collections is music, and languages are Chinese, author is male, style be it is lyric, that
The multimedia collections can be named as " Chinese songster lyric song ".Alternatively, can be to more in destination multimedia sequence
Media carry out arrangement according to the sequence of the second minor sort and generate a playlist, thus to more matchmakers in the destination multimedia sequence
Body plays out.And then the multimedia collections or multimedia list can be shown on a user interface.
From the foregoing, it will be observed that user client can be obtained when user triggers the control in Fig. 3 or Fig. 4 by interactive operation
On multimedia collections perhaps multimedia list can be used as the multimedia collections or multimedia list with reference to multimedia sequence
Column；Alternatively, the multimedia that can also be added the user in playlist is used as with reference to multimedia sequence.And then it is more to obtain target
Media sequence can regenerate a recommendation multimedia collections according to destination multimedia sequence, or recommend multimedia list, into
And showing the displaying of boundary's user oriented.For example, obtaining destination multimedia sequence according to the playlist in user client, then
Another playlist is generated to user's displaying etc. according to destination multimedia sequence.User can play this and push away showing interface selection
The multimedia in multimedia collections or the recommendation multimedia list is recommended, to improve recommendation efficiency.
Exemplary media
After describing the method for exemplary embodiment of the invention, next, to exemplary embodiment of the invention
Medium be illustrated.
In some possible embodiments, various aspects of the invention are also implemented as a kind of medium, store thereon
There is program code, it is above-mentioned " illustrative methods " for realizing this specification when said program code is executed by the processor of equipment
Step in the multimedia sequence generation method of various illustrative embodiments according to the present invention described in part.
Specifically, for realizing following steps when the processor of the equipment executes said program code: obtaining with reference to more
First label of media sequence；Calculate the first similarity of candidate multimedia second label and first label；According to
One similarity carries out the first minor sort to candidate multimedia and obtains candidate collection；According to the preference data of user to candidate collection into
The second minor sort of row obtains destination multimedia sequence.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: the candidate multimedia of the first quantity is chosen according to the result of the first minor sort and forms candidate collection, wherein candidate collection
In candidate multimedia arranged according to the result of the first minor sort.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: the candidate multimedia of the second quantity is chosen according to the result of the second minor sort and forms destination multimedia sequence, wherein the
Two quantity are less than or equal to the first quantity.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: the first label includes multiple first subtabs, and the second label includes multiple second subtabs；It calculates candidate multimedia
First similarity of the second label and the first label may include: by multiple second subtabs respectively with multiple first subtabs into
Row matches for the first time；The first similarity is obtained according to matched result and multiple respective weighted values of second subtab for the first time.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: the preference data of user includes multiple third subtabs；The candidate collection is carried out according to the preference data of user
It includes: by multiple third subtabs respectively in candidate collection multimedia second that second minor sort, which obtains destination multimedia sequence,
Subtab carries out second and matches；According to second of position of the matched result to multimedia in candidate collection in the first minor sort
It is secondary to be promoted, reduced or remained unchanged.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: determining that multiple first subtabs may include: at least one first subtab being directed to reference to multimedia sequence, and/
Or for reference at least one each multimedia first subtab in multimedia sequence.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: determine that the first subtab or the second subtab include at least one of: style information, type information, language information,
Temporal information, author information.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: destination multimedia sequence is saved as into multimedia collections, for selection by the user；Or it is generated according to destination multimedia sequence
Playlist simultaneously plays out.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: determine that above-mentioned multimedia may include: one of image, text, animation, video, music or a variety of.
In certain embodiments of the present invention, for realizing such as when the processor of the equipment executes said program code
Lower step: can also include: displaying circle in reference multimedia sequence before obtaining the first label with reference to multimedia sequence
The first control is shown in face；When detecting the first operation for the first control, start obtain with reference to multimedia sequence
The first label the step of.
It should be understood that above-mentioned medium can be readable signal medium or readable storage medium storing program for executing.Readable storage medium
Matter can be for example but not limited to: electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or it is any
Above combination.The more specific example (non exhaustive list) of readable storage medium storing program for executing includes: to have one or more conducting wires
Electrical connection, portable disc, hard disk, random access memory (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read only memory (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.
Readable signal medium may include in a base band or as the data-signal that carrier wave a part is propagated, wherein carrying
Readable program code.The data-signal of this propagation can take various forms, including but not limited to: electromagnetic signal, light letter
Number or above-mentioned any appropriate combination.Readable signal medium can also be any readable medium other than readable storage medium storing program for executing,
The readable medium can be sent, propagated or be transmitted for being used by instruction execution system, device or device or being tied with it
Close the program used.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to: wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and is executed in equipment, partially partially executes or remotely counted completely on a remote computing on the user computing device
It calculates and is executed on equipment or server.In the situation for being related to remote computing device, remote computing device can pass through any kind
Network --- be connected to user calculating equipment including local area network (LAN) or wide area network (WAN)-, or, it may be connected to it is outer
Portion calculates equipment (such as connecting using ISP by internet).
Exemplary means
After describing the medium of exemplary embodiment of the invention, next, with reference to Fig. 7 to the exemplary reality of the present invention
The multimedia sequence generating means for applying mode are illustrated.
Fig. 7 schematically shows the block diagram of the multimedia sequence generating means of embodiment according to the present invention.
Refering to what is shown in Fig. 7, the multimedia sequence generating means 70 of embodiment according to the present invention, may include multimedia
Acquiring unit 71, similarity calculated 72, sequencing unit 73, multimedia sequence determination unit 74.
Specifically, multimedia acquiring unit 71, for obtaining the first label for referring to multimedia sequence；Similarity calculation list
Member 72, for calculating the first similarity of candidate multimedia second label and the first label；Sequencing unit 73, for according to the
One similarity carries out the first minor sort to candidate multimedia and obtains candidate collection；Multimedia sequence determination unit 74 is used for basis
The preference data of user carries out the second minor sort to candidate collection and obtains destination multimedia sequence.
In some embodiments of the invention, sequencing unit 73 includes: the first sequencing unit 701, for according to for the first time
The result of sequence chooses the candidate multimedia of the first quantity and forms candidate collection, wherein the candidate multimedia in candidate collection is pressed
It is arranged according to the result of the first minor sort.
In some embodiments of the invention, multimedia sequence determination unit 74 includes: the second sequencing unit 702, is used for
The second quantity candidate multimedia, which is chosen, according to the result of second minor sort forms the destination multimedia sequence,
In, second quantity is less than or equal to first quantity.
In some embodiments of the invention, the first label may include multiple first subtabs, and the second label can wrap
Include multiple second subtabs；Thus similarity calculated 72 may include: the first matching unit 703, be used for multiple second
Subtab carries out first time matching with multiple first subtabs respectively；Similarity acquiring unit 704, for being matched according to first time
Result and multiple respective weighted values of second subtab obtain the first similarity.
In some embodiments of the invention, the preference data of user may include multiple third subtabs；Thus more matchmakers
Body sequence determination unit 74 may include: the second matching unit 705, be used for multiple third subtabs respectively and in candidate collection
Multimedia second subtab carries out second and matches；Sequence adjustment unit 706, for second of matched result of basis to time
Precedence of the multimedia in the first minor sort is promoted, reduced or is remained unchanged in selected works conjunction.
In some embodiments of the invention, multimedia acquiring unit 71 may include: subtab determination unit 707, use
It is directed at least one first subtab for referring to multimedia sequence in determining, and/or for reference to each more matchmakers in multimedia sequence
At least one first subtab of body.
In some embodiments of the invention, similarity calculated 72 can be also used for: determine the first subtab or
Two subtabs include at least one of: style information, type information, language information, temporal information, author information.
In some embodiments of the invention, multimedia sequence determination unit 74 can also include: recommendation unit 708, use
In destination multimedia sequence is saved as multimedia collections, for selection by the user；Or it is generated and is played according to destination multimedia sequence
List simultaneously plays out.
In some embodiments of the invention, above-mentioned multimedia sequence generating means 70 can also include: page presentation list
Member 709, for showing the first control in the displaying interface of reference multimedia sequence；Trigger unit 710, for detecting needle
When operating to the first of the first control, start the step of obtain the first label for referring to multimedia sequence.
In some embodiments of the invention, the multimedia in above-mentioned multimedia sequence generating means 70 may include: figure
One of picture, text, animation, video, music are a variety of.
Exemplary computer device
After method, medium and the device for describing exemplary embodiment of the invention, next, introducing according to this hair
The calculating equipment of bright another exemplary embodiment.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
In some possible embodiments, the calculating equipment of embodiment can include at least at least one according to the present invention
A processor and at least one processor.Wherein, the memory is stored with program code, when said program code is by institute
When stating processor execution, so that the processor executes described in above-mentioned " illustrative methods " part of this specification according to this hair
Step in the multimedia generation method of bright various illustrative embodiments.For example, the processor can execute institute as shown in figure 1
The step S11. shown obtains the first label for referring to multimedia sequence；Step S12. calculates candidate multimedia second label and institute
State the first similarity of the first label；Step S13. carries out first time row to the candidate multimedia according to first similarity
Sequence obtains candidate collection；Step S14. carries out the second minor sort to the candidate collection according to the preference data of user and obtains target
Multimedia sequence.For another example, the processor can also execute step as shown in Figure 2.
It should be noted that although being referred to several unit or sub-units of multimedia generating means in the above detailed description,
But this division is only exemplary, and is not enforceable.In fact, embodiment according to the present invention, is retouched above
The feature and function of two or more modules or unit for stating can embody in a module or unit.Conversely, retouching above
The feature and function of the module or unit stated can be to be embodied by multiple modules or unit with further division.
In addition, although describing the operation of the method for the present invention in the accompanying drawings with particular order, this do not require that or
Hint must execute these operations in this particular order, or have to carry out shown in whole operation be just able to achieve it is desired
As a result.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or by one
Step is decomposed into execution of multiple steps.
Although detailed description of the preferred embodimentsthe spirit and principles of the present invention are described by reference to several, it should be appreciated that, this
Invention is not limited to invented specific embodiment, does not also mean that the feature in these aspects cannot to the division of various aspects
Combination is benefited to carry out, this to divide the convenience merely to statement.The present invention is directed to cover appended claims spirit and
Included various modifications and equivalent arrangements in range.
Claims (10)
1. a kind of multimedia sequence generation method, comprising:
Obtain the first label for referring to multimedia sequence；
Calculate the first similarity of candidate multimedia second label and first label；
The first minor sort is carried out to the candidate multimedia according to first similarity and obtains candidate collection；
The second minor sort is carried out to the candidate collection according to the preference data of user and obtains destination multimedia sequence.
2. according to the method described in claim 1, described carry out first to the candidate multimedia according to first similarity
Minor sort obtains candidate collection, comprising:
The first quantity candidate multimedia, which is chosen, according to the result of first minor sort forms the candidate collection,
In, the candidate multimedia in the candidate collection is ranked up according to the result of first minor sort.
3. method according to claim 1 or 2, the preference data according to user carries out second to the candidate collection
Minor sort obtains destination multimedia sequence, comprising:
The second quantity candidate multimedia, which is chosen, according to the result of second minor sort forms the destination multimedia sequence
Column, wherein second quantity is less than or equal to first quantity.
4. the second label includes multiple according to the method described in claim 1, first label includes multiple first word labels
Second subtab；
First similarity for calculating candidate multimedia second label and first label, comprising:
Multiple second subtabs are subjected to first time matching with multiple first subtabs respectively；
It is similar that described first is obtained according to the various weighted value of the first time matched result and multiple second subtabs
Degree.
5. according to the method described in claim 4, the preference data of the user includes multiple third subtabs；
The preference data according to user carries out the second minor sort to the candidate collection and obtains destination multimedia sequence, wraps
It includes:
Multiple third subtabs are carried out second with the second subtab multimedia in the candidate collection respectively to match；
Precedence of the multimedia in the candidate collection in first sequence is carried out according to second of matched result
It is promoted, reduced or remained unchanged.
6. according to the method described in claim 4, the multiple first subtab includes:
For described at least one first subtab with reference to multimedia sequence, and/or for described with reference in multimedia sequence
At least one each multimedia first subtab.
7. according to the method described in claim 4, first subtab or second subtab include at least one of:
Style information, type information, language information, temporal information, author information.
8. a kind of medium, is stored thereon with program, such as any one of claims 1 to 7 is realized when which is executed by processor
The method.
9. a kind of multimedia sequence generating means, comprising:
Multimedia acquiring unit, for obtaining the first label for referring to multimedia sequence；
Similarity calculated, for calculating the first similarity of candidate multimedia second label and first label；
Sequencing unit obtains Candidate Set for carrying out the first minor sort to the candidate multimedia according to first similarity
It closes；
Multimedia sequence determination unit carries out the second minor sort to the candidate collection for the preference data according to user and obtains
Destination multimedia sequence.
10. a kind of calculating equipment, comprising: processor and memory, the memory are stored with executable instruction, the processor
Executable instruction for calling the memory storage executes the method as described in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811393179.6A CN109558500A (en) | 2018-11-21 | 2018-11-21 | Multimedia sequence generation method, medium, device and calculating equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811393179.6A CN109558500A (en) | 2018-11-21 | 2018-11-21 | Multimedia sequence generation method, medium, device and calculating equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109558500A true CN109558500A (en) | 2019-04-02 |
Family
ID=65866969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811393179.6A Pending CN109558500A (en) | 2018-11-21 | 2018-11-21 | Multimedia sequence generation method, medium, device and calculating equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109558500A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110121085A (en) * | 2019-05-29 | 2019-08-13 | 深圳市元征科技股份有限公司 | Multimedia content management method, device, server and storage medium |
| CN110519621A (en) * | 2019-09-20 | 2019-11-29 | 北京字节跳动网络技术有限公司 | Video recommendation method, device, electronic equipment and computer-readable medium |
| CN110532405A (en) * | 2019-08-15 | 2019-12-03 | 咪咕文化科技有限公司 | Multimedia file processing method, communication device and computer readable storage medium |
| CN110956980A (en) * | 2019-12-10 | 2020-04-03 | 腾讯科技（深圳）有限公司 | Media data processing method, device and storage medium |
| CN111008349A (en) * | 2020-03-09 | 2020-04-14 | 深圳博士创新技术转移有限公司 | Big data information pushing processing method and system |
| CN111414543A (en) * | 2020-03-25 | 2020-07-14 | 北京字节跳动网络技术有限公司 | Method, apparatus, electronic device, and medium for generating comment information sequence |
| CN112131410A (en) * | 2020-09-18 | 2020-12-25 | 北京达佳互联信息技术有限公司 | Multimedia resource display method, device, system and storage medium |
| CN113535992A (en) * | 2020-04-15 | 2021-10-22 | 西安诺瓦星云科技股份有限公司 | Play sorting method, device and system and computer readable storage medium |
| CN116975418A (en) * | 2022-10-26 | 2023-10-31 | 中移（杭州）信息技术有限公司 | A media asset determination method, device, equipment and computer-readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009151928A2 (en) * | 2008-05-27 | 2009-12-17 | Qualcomm Incorporated | Method and apparatus for aggregating and presenting data associated with geographic locations |
| US9477757B1 (en) * | 2012-06-14 | 2016-10-25 | Google Inc. | Latent user models for personalized ranking |
| CN106649848A (en) * | 2016-12-30 | 2017-05-10 | 合网络技术（北京）有限公司 | Video recommendation method and video recommendation device |
| US20180144052A1 (en) * | 2016-11-21 | 2018-05-24 | Comcast Cable Communications, Llc | Content recommendation system with weighted metadata annotations |
| CN108288229A (en) * | 2018-03-02 | 2018-07-17 | 北京邮电大学 | A kind of user's portrait construction method |
-
2018
- 2018-11-21 CN CN201811393179.6A patent/CN109558500A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009151928A2 (en) * | 2008-05-27 | 2009-12-17 | Qualcomm Incorporated | Method and apparatus for aggregating and presenting data associated with geographic locations |
| US9477757B1 (en) * | 2012-06-14 | 2016-10-25 | Google Inc. | Latent user models for personalized ranking |
| US20180144052A1 (en) * | 2016-11-21 | 2018-05-24 | Comcast Cable Communications, Llc | Content recommendation system with weighted metadata annotations |
| CN106649848A (en) * | 2016-12-30 | 2017-05-10 | 合网络技术（北京）有限公司 | Video recommendation method and video recommendation device |
| CN108288229A (en) * | 2018-03-02 | 2018-07-17 | 北京邮电大学 | A kind of user's portrait construction method |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110121085A (en) * | 2019-05-29 | 2019-08-13 | 深圳市元征科技股份有限公司 | Multimedia content management method, device, server and storage medium |
| CN110532405B (en) * | 2019-08-15 | 2023-01-10 | 咪咕文化科技有限公司 | Multimedia file processing method, communication device, and computer-readable storage medium |
| CN110532405A (en) * | 2019-08-15 | 2019-12-03 | 咪咕文化科技有限公司 | Multimedia file processing method, communication device and computer readable storage medium |
| CN110519621A (en) * | 2019-09-20 | 2019-11-29 | 北京字节跳动网络技术有限公司 | Video recommendation method, device, electronic equipment and computer-readable medium |
| US12526479B2 (en) | 2019-09-20 | 2026-01-13 | Beijing Bytedance Network Technology Co., Ltd. | Video recommendation method and apparatus, electronic device, and computer-readable medium |
| CN110956980A (en) * | 2019-12-10 | 2020-04-03 | 腾讯科技（深圳）有限公司 | Media data processing method, device and storage medium |
| CN110956980B (en) * | 2019-12-10 | 2024-04-09 | 腾讯科技（深圳）有限公司 | Media data processing method, device and storage medium |
| CN111008349A (en) * | 2020-03-09 | 2020-04-14 | 深圳博士创新技术转移有限公司 | Big data information pushing processing method and system |
| CN111414543B (en) * | 2020-03-25 | 2023-03-21 | 抖音视界有限公司 | Method, device, electronic equipment and medium for generating comment information sequence |
| CN111414543A (en) * | 2020-03-25 | 2020-07-14 | 北京字节跳动网络技术有限公司 | Method, apparatus, electronic device, and medium for generating comment information sequence |
| CN113535992A (en) * | 2020-04-15 | 2021-10-22 | 西安诺瓦星云科技股份有限公司 | Play sorting method, device and system and computer readable storage medium |
| CN113535992B (en) * | 2020-04-15 | 2024-03-15 | 西安诺瓦星云科技股份有限公司 | Method, device and system for playing ordering and computer readable storage medium |
| CN112131410A (en) * | 2020-09-18 | 2020-12-25 | 北京达佳互联信息技术有限公司 | Multimedia resource display method, device, system and storage medium |
| CN116975418A (en) * | 2022-10-26 | 2023-10-31 | 中移（杭州）信息技术有限公司 | A media asset determination method, device, equipment and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109558500A (en) | Multimedia sequence generation method, medium, device and calculating equipment | |
| CN108288468B (en) | Audio recognition method and device | |
| JP7335062B2 (en) | Voice service providing method and apparatus | |
| JP7199756B2 (en) | Method and system for automatic generation of video content integrated metadata using video metadata and script data | |
| US8321414B2 (en) | Hybrid audio-visual categorization system and method | |
| CN107918653A (en) | A kind of intelligent playing method and device based on hobby feedback | |
| US10049675B2 (en) | User profiling for voice input processing | |
| CN107832434A (en) | Method and apparatus based on interactive voice generation multimedia play list | |
| CN110347872B (en) | Video cover image extraction method and device, storage medium and electronic equipment | |
| US8862615B1 (en) | Systems and methods for providing information discovery and retrieval | |
| JP2021524686A (en) | Machine learning to recognize and interpret embedded information card content | |
| US20220083583A1 (en) | Systems, Methods and Computer Program Products for Associating Media Content Having Different Modalities | |
| CN110188356B (en) | Information processing method and device | |
| CN109036417A (en) | Method and apparatus for handling voice request | |
| WO2020232796A1 (en) | Multimedia data matching method and device, and storage medium | |
| CN109165302A (en) | Multimedia file recommendation method and device | |
| CN111383631A (en) | Voice interaction method, device and system | |
| CN111046225A (en) | Audio resource processing method, device, equipment and storage medium | |
| US20200034385A1 (en) | Method and system for creating combined media and user-defined audio selection | |
| CN107895016A (en) | One kind plays multimedia method and apparatus | |
| CN109920409A (en) | A kind of speech search method, device, system and storage medium | |
| CN112989104A (en) | Information display method and device, computer readable storage medium and electronic equipment | |
| CN110148393A (en) | Music generation method, device and system, and data processing method | |
| CN109710799B (en) | Voice interaction method, medium, device and computing equipment | |
| CN113891142A (en) | Song data processing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190402 |