CN105912650A - Method and apparatus of recommending songs - Google Patents
Method and apparatus of recommending songs Download PDFInfo
- Publication number
- CN105912650A CN105912650A CN201610218865.4A CN201610218865A CN105912650A CN 105912650 A CN105912650 A CN 105912650A CN 201610218865 A CN201610218865 A CN 201610218865A CN 105912650 A CN105912650 A CN 105912650A
- Authority
- CN
- China
- Prior art keywords
- song
- recommendation
- client
- information
- multimedia messages
- 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
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a method and apparatus of recommending songs. The method comprises obtaining multimedia information shared to a network community by a client, extracting content characteristic information included in the multimedia information, searching songs according to the content characteristic information, and obtaining recommended songs; and recommending the recommended songs to the client. The songs related to the multimedia information are recommended for the user through collecting the multimedia information shared to the network community by the user, and thereby facilitating user experience improvement.
Description
Technical field
The present invention relates to internet information push technology field, particularly relate to the method and apparatus recommending song.
Background technology
When user's song based on the intelligent mobile terminal such as mobile phone, flat board client listens song online, song visitor
Family end would generally provide the user one and recommend list of songs, such as: latest song is recommended, hit song pushes away
Recommend, Japan and Korea S's song recommendations etc..
The main way of realization of existing song recommendations function includes: listen song historical data according to user oneself
Recommend the song of similar type, or number of clicks based on song is recommended, or based on user good friend
Song recommendations.But these song recommendations modes are still difficult to meet, and people are diversified listens song demand, example
As people on the road time, be more desirable to hear is and song that travelling is relevant, existing song recommendations mode
Cannot automatically adapt to such demand.
Summary of the invention
Based on this, the embodiment of the present invention provides the method and apparatus recommending song, it is possible to according to the state of user
The song that information recommendation is relevant, is conducive to promoting Consumer's Experience.
One aspect of the present invention provides the method recommending song, including:
Obtain client and share the multimedia messages of Web Community;
Extract the content characteristic information that described multimedia messages comprises;
Carry out song search according to described content characteristic information, obtain recommending song;
Described recommendation song is recommended to described client.
Another aspect of the present invention provides the device recommending song, including:
Information collection module, shares the multimedia messages of Web Community for obtaining client;
Characteristic extracting module, for extracting the content characteristic information that described multimedia messages comprises;
Search module, for carrying out song search according to described content characteristic information, obtains recommending song;
Recommending module, for recommending described recommendation song to described client.
Technique scheme, shares the multimedia messages of Web Community by obtaining client, extracts described
The content characteristic information that multimedia messages comprises, it follows that the shapes such as user place environment, things interested
State information;Carry out song search according to described content characteristic information, obtain the recommendation song being correlated with, to described
Client recommends described recommendation song, thus available relevant to user place environment or things interested
Song.The scheme of the above embodiment of the present invention, can collect user and share the multimedia messages of Web Community,
And recommend the song relevant to described multimedia messages for user, be conducive to promoting Consumer's Experience.
Accompanying drawing explanation
Fig. 1 is the working environment schematic diagram of the present invention program of an embodiment;
Fig. 2 is the composition structural representation of the playback of songs client of an embodiment;
Fig. 3 is the composition structural representation of the server of an embodiment;
Fig. 4 is the indicative flowchart of the method for the recommendation song of an embodiment;
Fig. 5 is the technological frame schematic diagram of the method for the recommendation song of an embodiment;
Fig. 6 is the indicative flowchart of the method for the recommendation song of another embodiment;
Fig. 7 is the schematic diagram of the device of the recommendation song of an embodiment;
Fig. 8 is the schematic diagram of the device of the recommendation song of another embodiment.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing and reality
Execute example, the present invention is further elaborated.Only should be appreciated that specific embodiment described herein
Only in order to explain the present invention, it is not intended to limit the present invention.
Fig. 1 shows the working environment schematic diagram of one embodiment of the invention.The song with playback of songs function is broadcast
Put client 100, as a example by intelligent mobile terminal, including the mobile phone shown in Fig. 1, flat board, portable electric
Brains etc., all can be connected with server 200 by network, obtain song by server 200.Here network
Can be wireless network, it is also possible to be cable network.Server 200 can be cloud server.Use song
When client end of playing back 100 plays song online, the relevant information of this playback of songs client 100 can be sent to
Server 200, server 200 carries out song search based on the recommendation rules pre-defined, and obtains correspondence
Recommend song, described recommendation song information is sent to playback of songs client 100, by playback of songs client
Described recommendation song is shown and plays by the recommendation list of songs of end 100.
Playback of songs client 100 structural representation in one embodiment is as shown in Figure 2.This playback of songs
Processor that client includes being connected by system bus, storage medium, display device, communication interface, electricity
Source interface and internal memory.Wherein, the storage medium storage of playback of songs client has the online device playing song,
This device can generate according to the recommendation song that server sends recommends list of songs, to recommending in list of songs
Song is shown and plays.The display device of playback of songs client can be to recommending list of songs and song
Play relevant information to show.The communication interface of playback of songs client is used for being connected with server and communicating,
The power interface of playback of songs client for being connected with external power source, external power source by this power interface to
Playback of songs client is powered.Playback of songs client can be any equipment cited in Fig. 1, also
Can be that other have the equipment of said structure.
Server 200 structural representation in one embodiment is as shown in Figure 3.Server includes passing through system
Processor, supply module, storage medium, internal memory and the communication interface that bus connects.Wherein, server
Storage medium storage has operating system, data base and a kind of device recommending song, and this device pushes away for realization
The method recommending song.The communication interface of server is for being attached with playback of songs client 100 and communicating.
In conjunction with the schematic diagram shown in Fig. 1, Fig. 2, Fig. 3, below to recommending the method for song and recommending song
Each embodiment of device illustrates.
Fig. 4 is the indicative flowchart of the method for the recommendation song of an embodiment;In this embodiment it is that with
The method is applied in Fig. 1 illustrate as a example by server 200.
As shown in Figure 4, the method for the recommendation song in the present embodiment includes step:
S11, obtains client and shares the multimedia messages of Web Community;
Client in the present embodiment can be that mobile phone, flat board, portable computer etc. have online broadcasting song merit
The intelligent mobile terminal of energy, it is possible to for the software client that can play song online installed in intelligent mobile terminal
End.Described client is shared the multimedia messages of Web Community and is included: client share wechat circle of friends,
The information of the Web Communities such as QQ space and/or microblogging.Described multimedia messages can be that picture, word or sound regard
Frequently information, or be combinations two or more in picture, word, audio/video information.
In the present embodiment, if described client is intelligent mobile terminal, the most described client is sharing many matchmakers
Body information is to submitting its equipment identification information during Web Community in the lump;Corresponding web server is by described
Equipment identification information can detect that the upload operation of this client, and obtains uploaded multimedia messages.As
The most described client is the software client in intelligent terminal, user can pre-set some software clients with
Association between music player software (such as arranges wechat in intelligent terminal, QQ and/or Tengxun's microblogging and QQ
Association between music), any software client that there is association with music player software shares multimedia messages
When arriving corresponding Web Community, corresponding web server can obtain this software client by described incidence relation
The upload operation of end, and obtain uploaded multimedia messages.
Further, the multimedia information storage of acquisition is stored in assembly to the multimedia pre-build, and
Set up each multimedia messages and corresponding equipment identification information or music player software client user's information
Association.Then in real time or corresponding user can be obtained according to setting time interval from described multimedia storage assembly
Share the multimedia messages of Web Community.
S12, extracts the content characteristic information that described multimedia messages comprises;
It is understood that the content characteristic information that multimedia messages comprises refers to landscape feature, animal
The information such as feature, character features or weather characteristics.As a example by picture, can know based on picture recognition technology
Do not go out concrete separate feature such as wherein including flowers and plants, mountain, sea, star, snow or rain.If user divides
The multimedia messages enjoying Web Community is video file, then according to setting time interval capture frame of video picture,
Extract the content characteristic information comprised in the frame of video picture of capture again, it follows that described video file comprises
Content characteristic information.
Preferably, flowers and plants, the content characteristic such as scenery with hills and waters that general evil spirit identifies that Model Identification picture comprises can be used.General
Evil spirit identifies that the image recognition of model has 4 levels.Ground floor is carried out " the map ghost " of simple task,
They simply record extraneous original image, and erect image retina obtains the map of environmental stimuli;Then by " special
Levy ghost " analyze this map further.During analyzing, each feature ghost looks for relevant with oneself
Characteristics of image;The reaction of feature ghost is accepted again, anti-from feature ghost of each cognitive ghost by " cognitive ghost "
Find in should and oneself be responsible for the image-related feature that identifies, it was found that during this feature, it is with regard to " shout ",
The feature found is the most, and " shout " sound is the biggest;Finally " decision-making ghost " is according to many " cognitive ghost " " shouts "
The size of sound, selects the reaction of " cognitive ghost " of cry maximum as characteristics of image to be identified.Example
As: when identifying the image of letter r, R is first encoded by " map ghost ", conveys information to " feature
Ghost " be further processed, at this moment have 5 " features ghost " vertical line respectively included by report image,
Article two, horizontal line, an oblique line, 3 right angles and a discontinuous curve.Then many " cognitive ghost " then roots
The letter image being oneself to be responsible for is identified whether according to these features reported and quantity thereof.At this moment D, P,
R ghost all can respond, but only 4 features of P ghost meet with it, and has a feature (oblique line) with it not
Meet;Only 3 features of D ghost meet with it, and have two features (oblique line, right angle) not meet with it;
Only R ghost has 5 features to meet with it, and these 5 features include again whole features of R, so
The cry of R ghost is maximum, and therefore " decision-making ghost " the R image that makes one's options the most easily is as recognition result
Decision.Further, general evil spirit identifies that model can also be differentiated for similar figure, will not obscure;For losing
Genuine figure, when the size of letter the most to be identified changes, identifies and difficulty also will not occur.Therefore,
The present embodiment uses general evil spirit to identify the content characteristic that Model Identification picture comprises, and recognition accuracy is good.
As a preferred implementation of step S12, the content characteristic information that extraction multimedia messages comprises
Mode can be: by described multimedia messages and mating with reference to file in default media library, is mated
With reference to file, obtain that preset with the described keyword with reference to file association mated, as described many matchmakers
The content characteristic information of body information.Corresponding, media library need to be pre-created, if in described media library there being storage
Trepang is according to file;And each keyword with reference to file association is set.As a example by picture, image is first used to know
Other technology identifies the content characteristic information that picture comprises, then the content characteristic information of the picture that will identify that with
The reference picture preset in picture library is mated, and obtains the reference picture of coupling, then obtains in advance for described
The keyword that the reference picture of coupling is arranged, replaces the content characteristic information of described picture with described keyword,
To carry out song retrieval according to described keyword.Corresponding, picture library need to be pre-created, in described picture library
Storage has some reference pictures, arranges related keyword for each reference picture.
S13, carries out song search according to described content characteristic information, obtains recommending song;
In the present embodiment, available described content characteristic information carries out song search directly as keyword, it is possible to
Described content characteristic information is reasonably extended or deforms, obtains keyword more accurate, comprehensive and carry out
Song search.
S14, recommends described recommendation song to described client.
It is understood that a multimedia messages may comprise several content characteristic information, can be according to respectively
Content characteristic information carries out song search respectively, it is possible to be combined, multiple content characteristic information based on group
Conjunction information carries out song search.Thus obtained recommendation song there may be the song of repetition.Excellent as one
Select embodiment, before described client recommends described recommendation song, also include detecting described recommendation song
In whether there is the song of repetition, if so, described recommendation song is carried out duplicate removal.Such as: push away described in detection
Recommend and whether song exists title of the song and the most identical song of singer, if so, carry out in described identical song
The step of duplicate removal.
It is understood that the rule of described recommendation song duplicate removal can be adjusted according to the preference of user,
Can be the most also: detect in described recommendation song whether there is the song that title of the song, singer and file size are the most identical
Song, if so, to the step carrying out duplicate removal in described identical song.Make the same song that different singer sings
Song, the most retained because file size differs.
In the present embodiment, send described recommendation song to described client, described recommendation song is joined institute
State in the recommendation list of songs of client.It is understood that to visitor can be added newly obtained recommendation song
Family end recommends the end of list of songs, or newly obtained recommendation song is inserted into client recommendation song row
The prostatitis of table, or the client that is inserted into random for newly obtained recommendation song is recommended in list of songs.
As a preferred implementation, newly obtained recommendation song is inserted into pushing away of described client by the present embodiment
Recommend the prostatitis of list of songs so that newly obtained recommendation song can preferentially be play.
As a preferred implementation, step S11 may also include acquisition corresponding the sharing of each multimedia messages
The step of temporal information.Corresponding, further comprise the steps of: the elder generation according to share time after obtaining recommending song
After, the recommendation song that described multimedia messages is corresponding is ranked up, posterior for share time multimedia is believed
The recommendation song that breath is corresponding sorts front;Recommendation song after described client sends sequence, pushes away described
Recommend in the recommendation list of songs that song is joined described client by sequence.
In like manner, after described recommendation song being joined in the recommendation list of songs of described client, described in push away
Recommend the song that there may be repetition in list of songs.Therefore, also can detect in the recommendation list of songs of client
The song whether existence repeats, carries out duplicate removal to the song in described recommendation list of songs;Client displaying is gone
Recommendation list of songs after Chong clicks on broadcasting for user.
Fig. 5 is the technological frame schematic diagram of the method for the recommendation song of an embodiment;As it is shown in figure 5, to scheme
As a example by sheet, the present embodiment is recommended the mode of song be divided into real-time recommendation and two kinds of approach of non real-time recommendation.Under
In the face of two kinds of approach are described respectively.
Real-time recommendation song: under this approach, obtains client and shares many matchmakers of Web Community in step S11
Body information refers to, obtains client and currently shares the multimedia messages of Web Community;Believe based on this multimedia
The content characteristic information of breath carries out song search, obtains the recommendation song that the current sharing information of user is relevant, with
Ensure the real-time of song recommendations.Such as: client click is shared (or uploading) picture and arrived Web Community
Button, the webserver receives client and shares the picture information to Web Community, the backstage CGI that notice is relevant
(background server business processing program) obtains the picture that client is currently shared, and extracts the content of this picture
Characteristic information (such as flower, mountain, snow etc.), obtains the recommendation song being correlated with according to described content characteristic information, to
Described client sends recommends song, and described recommendation song joins the recommendation list of songs of described client
In, client is by showing that recommending list of songs to click on broadcasting for user recommends song.If user has shared certain
The picture of individual landscape, can obtain the recommendation song relevant to this landscape in real time.
Non real-time recommendation song: under this approach, obtaining client in step S11, to share Web Community many
Media information refers to collection client and shares all multimedia messages of Web Community within the setting time,
Described multimedia messages is carried out unified Analysis, and the content characteristic information extracting each multimedia messages carries out song
Search, obtains the recommendation song relevant to each multimedia messages.Such as: user share picture to circle of friends or
The other kinds of Web Community of person.The webserver receives client and shares the information of picture, and notice is correlated with
Backstage CGI adds up the picture shared, the picture that user shares all store specify network TFS (picture,
The multimedia storage assemblies such as audio frequency and video);By inquiring about described network TFS, it is collected in before current time 24 little
Time this user interior share all pictures of Web Community, analyze the content characteristic information that each picture comprises, system
One carries out song search, sends to described client and recommends song, described recommendation song is joined described visitor
In the recommendation list of songs of family end.As user has shared the picture of certain landscape today, can obtain tomorrow and be somebody's turn to do
The recommendation song that landscape is relevant.
The difference of above two approach includes: the former real-time is relatively strong, by real time user being shared network
The multimedia messages of community carries out Content Feature Extraction, is quickly found out the recommendation song of correspondence, user's real-time volume
Test preferably;The latter is the highest to time requirement, and the multimedia messages that therefore user can share Web Community enters
The more detailed feature extraction of row (such as carries out the mode mated, with picture is with the reference information in media library
Example, concretely: mated with the reference picture of picture library respectively by described picture, reading matches
Reference picture characteristic of correspondence information, the content that described characteristic information is comprised as the picture that user shares
Characteristic information), can get and recommend song more comprehensively, accurately.
As another preferred implementation, the approach of non real-time recommendation song, collect client in the time of setting
After inside sharing the multimedia messages of Web Community, can also read the share time that each multimedia messages is corresponding
Information (time when i.e. client shares multimedia messages);Priority according to share time is to described multimedia
Recommendation song corresponding to information is ranked up, by recommendation song corresponding for posterior for share time multimedia messages
Sequence is front.Recommendation song after described client sends sequence, is added described recommendation song by sequence
In the recommendation list of songs of described client, it is simple to the recommendation that the posterior multimedia messages of share time is corresponding
Song is by preferential broadcasting.
The method of recommendation song based on above-described embodiment, when user plays by the sea, shares the picture in sea
To wechat circle of friends, server can obtain this picture and extract the content characteristic information that this picture comprises, for this
User recommends the song closed with marine facies.Or user is when forest is played, share the picture of forest to friend
Circle or network, server can obtain this picture and extract the content characteristic information that this picture comprises, for this use
The song relevant to forest is recommended at family.The recommendation list of songs that user can be shown by client, to server
The recommendation song sent is shown and plays.Method based on above-mentioned recommendation song, the recommendation song obtained
More meet the state of user, be conducive to promoting Consumer's Experience.
Fig. 6 is the indicative flowchart of the method for the recommendation song of another embodiment;In this embodiment it is that
Illustrate as a example by being applied to server 200.The present embodiment differs primarily in that with previous embodiment:
Share multimedia messages to the geographical location information at client place during Web Community in conjunction with user, carry out song
Recommend.
As shown in Figure 6, the method for the recommendation song in the present embodiment includes step:
S21, obtains client and shares the multimedia messages of Web Community, and obtains client and share described many
Positional information during media information;
Described Web Community includes: the Web Communities such as wechat circle of friends, QQ space, microblogging.Described multimedia
Information be picture, word, audio/video information one or more.Described positional information is GPS information, or
The information in other expression client geographical position of person.
S22, extracts the content characteristic information that described multimedia messages comprises;
S23, carries out song search according to described content characteristic information and described positional information, obtains recommending song;
S23, recommends described recommendation song to described client.
Wherein, the detailed description of the invention of step S23 can include following two:
Mode one, directly carries out song search according to described content characteristic information and described positional information,
To recommending song.Described content characteristic information, described positional information all will carry out song as keyword and search
Rope, had both included the song relevant to multimedia content in thus obtained recommendation song, include again and institute
That states multimedia messages shares the song that place is relevant.
Mode two: according to described content characteristic information and described positional information, it is judged that client is shared described many
Whether position during media information is presumptive area;If presumptive area, corresponding by described content characteristic information
Keyword and keyword corresponding to described presumptive area carry out song search;Otherwise, only described content is used
The keyword that characteristic information is corresponding carries out song search.
Preferably, the presumptive area in the present embodiment is tourist district.In mode two, according to described content characteristic
Information and described positional information, it is judged that what described multimedia messages was corresponding shares whether place is presumptive area
If concrete mode comprises the steps that described content characteristic information comprises landscape feature, and described positional information is present in
In the list of locations of presumptive area, it is judged that the share place corresponding for described multimedia messages is tourist district;No
Then, it is judged that for described multimedia messages corresponding share place Bu Shi tourist district.As a example by picture, client
When sharing scenery picture to Web Community, also will obtain the GPS information at client place and be submitted to phase in the lump
The backstage CGI closed.Described scenery picture and GPS information are sent to picture analyzing coupling service by backstage CGI,
The content characteristic information of this scenery picture is extracted in picture analyzing service, according to described content characteristic information (as mountain,
Sea etc.) judge described scenery picture with GPS information share place whether as tourist district;If it is,
Recommend the song relevant to picture landscape of described tourist district, or recommend song that described tourist district is relevant with
And the song that described picture landscape is relevant;If it is not, then only recommend the song relevant to described picture landscape.
The method of the recommendation song of the present embodiment, the multimedia sharing Web Community by obtaining client is believed
Breath, and the sharing positional information of described multimedia messages, extract the content spy that described multimedia messages comprises
Reference ceases, and can obtain user based on content characteristic information more accurately with sharing positional information and share multimedia letter
State during breath;Carry out song search according to described content characteristic information and described positional information, recommended
Song is more preferable with the matching degree of User Status.
It should be noted that for aforesaid each method embodiment, in order to simplicity describes, it is all expressed as
A series of combination of actions, but those skilled in the art should know, and the present invention is not moved by described
The restriction of work order, because according to the present invention, some step can use other order or carry out simultaneously.
Based on the thought identical with the method for the recommendation song in above-described embodiment, the present invention also provides for recommending song
Device, the method that this device can be used for performing above-mentioned recommendation song.For convenience of description, it is recommended that song
In the structural representation of device embodiment, illustrate only the part relevant to the embodiment of the present invention, this area
Those of skill will appreciate that, it is illustrated that structure is not intended that the restriction to device, can include than diagram more or
Less parts, or combine some parts, or different parts are arranged.
Fig. 7 is the schematic diagram of the device of the recommendation song of one embodiment of the invention;As it is shown in fig. 7,
The device of the recommendation song of the present embodiment includes: information collection module 710, characteristic extracting module 720, search
Module 730 and recommending module 740, details are as follows for each module:
Above-mentioned information collection module 710, shares the multimedia messages of Web Community for obtaining client;
It should be understood that Web Community includes described in the present embodiment: wechat circle of friends, QQ space, microblogging
Deng Web Community.Described multimedia messages be picture, word, audio/video information one or more.Described
Positional information is GPS information, or other represent the information in client geographical position.
Features described above extraction module 720, for extracting the content characteristic information that described multimedia messages comprises;
It should be understood that described content characteristic information includes: landscape feature, animal character, character features,
One or more of weather characteristics.
Above-mentioned search module 730, for carrying out song search according to described content characteristic information, obtains recommending song
Bent;
In the present embodiment, available described content characteristic information carries out song search directly as keyword, it is possible to
Described content characteristic information is reasonably extended or deforms, obtains keyword more accurate, comprehensive and carry out
Song search.
Above-mentioned recommending module 740, for recommending described recommendation song to described client.
As a preferred implementation, in the present embodiment, information collection module 710 comprises the steps that
First information acquiring unit, shares many matchmakers of Web Community for collecting client within the setting time
Body information;Or, the second information acquisition unit, for obtaining client, currently to share Web Community many
Media information.
As another preferred implementation, features described above extraction module 720, can be used for described multimedia messages
With mating with reference to file in default media library, obtain coupling with reference to file, obtain preset with institute
State the keyword with reference to file association of coupling, as the content characteristic information of described multimedia messages.Corresponding
, the device of the recommendation song of the present embodiment may also include and arranges module, is used for creating media library, described many
In media library, storage has some with reference to file;Each keyword with reference to file association is set.
As another preferred implementation, the device of the recommendation song of the present embodiment also includes: deduplication module,
For detecting the song that whether there is repetition in described recommendation song, if so, described recommendation song is gone
Weight.Such as: detect whether described recommendation song exists title of the song and the most identical song of singer, the most right
Described identical song carries out duplicate removal;Or, detect in described recommendation song whether there is title of the song, singer
And the song that file size is the most identical, if so, to the step carrying out duplicate removal in described identical song.Corresponding
, above-mentioned recommending module 740 can be used for the recommendation song after described client sends duplicate removal, with by described
Song is recommended to join in the recommendation list of songs of described client.
As another preferred implementation, above-mentioned data obtaining module 710, it is additionally operable to obtain each multimedia messages
Corresponding share time information.Corresponding, the device of the recommendation song of the present embodiment may also include that sequence mould
Block, for the priority according to share time, is ranked up the recommendation song that described multimedia messages is corresponding,
Recommendation song corresponding for posterior for share time multimedia messages is sorted front.Corresponding, above-mentioned recommendation mould
Block 740 can be used for the recommendation song after described client sends sequence, so that described recommendation song is pressed sequence
Join in the recommendation list of songs of described client.
Fig. 8 is the schematic diagram of the device of the recommendation song of another embodiment;Base at previous embodiment
On plinth, the information collection module 710 in the present embodiment, it is additionally operable to obtain client and shares described multimedia messages
Time positional information.Corresponding, search module 730, it is additionally operable to according to described content characteristic information and institute's rheme
Confidence breath carries out song search.Preferably, described search module 730 may particularly include:
Identifying unit 731, for according to described content characteristic information and described positional information, it is judged that described many matchmakers
What body information was corresponding shares whether place is presumptive area;First search unit 732, for if it is determined that unit
Result of determination is yes, the keyword corresponding by described content characteristic information and pass corresponding to described presumptive area
Key word carries out song search;Second search unit 733, for if it is determined that the result of determination of unit is no, uses institute
State keyword corresponding to content characteristic information and carry out song search.
As a preferred implementation, described presumptive area is tourist district.Corresponding, above-mentioned identifying unit 731
Can be specifically for: if described content characteristic information comprises landscape feature, and described positional information is present in predetermined
In the list of locations in region, then it is judged as that the place of sharing that described multimedia messages is corresponding is tourist district.Certainly
Also presumptive area can be set as other kinds of region.
As a preferred implementation, in the present embodiment, positional information is client GPS information, the most also may be used
It is set as that other can characterize the information in client geographical position.
It should be noted that in the embodiment of the device of the recommendation song of above-mentioned example, each module/unit it
Between the content such as mutual, the execution process of information, due to preceding method embodiment of the present invention based on same design,
Its technique effect brought is identical with preceding method embodiment of the present invention, and particular content can be found in the inventive method
Narration in embodiment, here is omitted.
Additionally, in the embodiment of the device of the recommendation song of above-mentioned example, the logical partitioning of each functional module
Be merely illustrative of, in actual application can as required, such as corresponding hardware configuration requirement or
The convenient consideration of the realization of software, is completed above-mentioned functions distribution by different functional modules, will described in push away
The internal structure of the device recommending song is divided into different functional modules, with complete described above all or
Partial function.The most each function mould both can realize to use the form of hardware, it would however also be possible to employ software function mould
The form of block realizes.
It will appreciated by the skilled person that all or part of flow process realizing in above-described embodiment method,
Can be by computer program and complete to instruct relevant hardware, described program can be stored in a calculating
In machine read/write memory medium, as independent production marketing or use.Described program upon execution, can be held
All or part of step of the embodiment of row such as above-mentioned each method.Wherein, described storage medium can be magnetic disc,
CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random
Access Memory, RAM) etc..
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, in certain embodiment the most in detail
The part stated, may refer to the associated description of other embodiments.It is appreciated that the term " used in it
One ", " second " etc. be used for distinguishing object in this article, but these objects should not be limited by these terms.Such as,
Without departing from the scope of the invention, the first search unit can be referred to as the second search unit, will
Second search unit is referred to as the first search unit.
Embodiment described above only have expressed the several embodiments of the present invention, it is impossible to is interpreted as the present invention special
The restriction of profit scope.It should be pointed out that, for the person of ordinary skill of the art, without departing from this
On the premise of inventive concept, it is also possible to make some deformation and improvement, these broadly fall into the protection model of the present invention
Enclose.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (14)
1. the method recommending song, it is characterised in that including:
Obtain client and share the multimedia messages of Web Community;
Extract the content characteristic information that described multimedia messages comprises;
Carry out song search according to described content characteristic information, obtain recommending song;
Described recommendation song is recommended to described client.
The method of recommendation song the most according to claim 1, it is characterised in that extract described multimedia
The content characteristic information that information comprises, including:
By described multimedia messages and mating with reference to file in default media library, obtain the reference of coupling
File, obtains the default keyword with the described reference file association mated, as described multimedia messages
Content characteristic information.
The method of recommendation song the most according to claim 1, it is characterised in that obtain client and share
To the multimedia messages of Web Community, the most also include:
Acquisition client shares positional information during described multimedia messages;
Described carry out song search according to described content characteristic information, including:
Song search is carried out according to described content characteristic information and described positional information.
The method of recommendation song the most according to claim 3, it is characterised in that described according to described interior
Hold characteristic information and described positional information carries out song search, including:
According to described content characteristic information and described positional information, it is judged that corresponding the sharing of described multimedia messages
Whether place is presumptive area;If presumptive area, the keyword corresponding by described content characteristic information and
Keyword corresponding to described presumptive area carries out song search;Otherwise, corresponding by described content characteristic information
Keyword carries out song search.
The method of recommendation song the most according to claim 1, it is characterised in that obtain client and share
To the multimedia messages of Web Community, the most also include:
Obtain the share time information that each multimedia messages is corresponding;
Obtain recommending song, the most also include:
According to the priority of share time, the recommendation song that described multimedia messages is corresponding is ranked up, will divide
The recommendation song that time of enjoying posterior multimedia messages is corresponding sorts front;
Described to described client recommend described recommendation song, including:
Recommendation song after described client sends sequence, is joined described by described recommendation song by sequence
In the recommendation list of songs of client.
The method of recommendation song the most according to claim 1, it is characterised in that obtain recommending song,
The most also include:
Detect and whether described recommendation song exists title of the song and the most identical song of singer, if so, to described phase
Same song carries out duplicate removal.
The method of recommendation song the most according to claim 1, it is characterised in that described multimedia messages
Including: picture, word, audio/video information one or more.
8. the device recommending song, it is characterised in that including:
Information collection module, shares the multimedia messages of Web Community for obtaining client;
Characteristic extracting module, for extracting the content characteristic information that described multimedia messages comprises;
Search module, for carrying out song search according to described content characteristic information, obtains recommending song;
Recommending module, for recommending described recommendation song to described client.
The device of recommendation song the most according to claim 8, it is characterised in that described feature extraction mould
Block, for by described multimedia messages and mating with reference to file in default media library, obtaining coupling
With reference to file, obtain the default keyword with the described reference file association mated, as described multimedia
The content characteristic information of information.
The device of recommendation song the most according to claim 8, it is characterised in that described information
Module, is additionally operable to obtain positional information when client shares described multimedia messages;
Described search module, is additionally operable to carry out song according to described content characteristic information and described positional information and searches
Rope.
The device of 11. recommendation songs according to claim 10, it is characterised in that described search module
Including:
Identifying unit, for according to described content characteristic information and described positional information, it is judged that described multimedia
What information was corresponding shares whether place is presumptive area;
First search unit, for if it is determined that the result of determination of unit is yes, by described content characteristic information pair
The keyword answered and keyword corresponding to described presumptive area carry out song search;
Second search unit, for if it is determined that the result of determination of unit is no, by described content characteristic information pair
The keyword answered carries out song search.
The device of 12. recommendation songs according to claim 8, it is characterised in that described acquisition of information
Module, is additionally operable to obtain the share time information that each multimedia messages is corresponding;
The device of described recommendation song, also includes: order module, for the priority according to share time, right
The recommendation song that described multimedia messages is corresponding is ranked up, and posterior for share time multimedia messages is corresponding
Recommendation song sort front;
Described recommending module, the recommendation song after sending sequence to described client, with by described recommendation
Song is joined in the recommendation list of songs of described client by sequence.
The device of 13. recommendation songs according to claim 8, it is characterised in that also include:
Whether deduplication module, exist title of the song and the most identical song of singer for detecting in described recommendation song,
If so, duplicate removal is carried out in described identical song;
Described recommending module, the recommendation song after sending duplicate removal to described client, with by described recommendation
Song joins in the recommendation list of songs of described client.
The device of 14. recommendation songs according to claim 8, it is characterised in that described multimedia is believed
Breath includes: picture, word, audio/video information one or more.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610218865.4A CN105912650B (en) | 2016-04-07 | 2016-04-07 | Method and device for recommending songs |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610218865.4A CN105912650B (en) | 2016-04-07 | 2016-04-07 | Method and device for recommending songs |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105912650A true CN105912650A (en) | 2016-08-31 |
CN105912650B CN105912650B (en) | 2021-08-24 |
Family
ID=56745779
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610218865.4A Active CN105912650B (en) | 2016-04-07 | 2016-04-07 | Method and device for recommending songs |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105912650B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106339504A (en) * | 2016-09-23 | 2017-01-18 | 乐视控股(北京)有限公司 | Music pushing method and apparatus |
CN106446180A (en) * | 2016-09-27 | 2017-02-22 | 维沃移动通信有限公司 | Song recognition method and mobile terminal |
CN106776774A (en) * | 2016-11-11 | 2017-05-31 | 努比亚技术有限公司 | Mobile terminal chooses picture device and method |
CN106815364A (en) * | 2017-01-24 | 2017-06-09 | 百度在线网络技术(北京)有限公司 | Content delivery method and device |
CN107220854A (en) * | 2017-05-31 | 2017-09-29 | 深圳正品创想科技有限公司 | A kind of method and device for sending electronic ticket |
CN108108436A (en) * | 2017-12-20 | 2018-06-01 | 东软集团股份有限公司 | Date storage method, device, storage medium and electronic equipment |
CN109840793A (en) * | 2017-11-28 | 2019-06-04 | 广州腾讯科技有限公司 | Method for pushing and device, storage medium, the electronic device of promotion message |
CN109969109A (en) * | 2017-12-27 | 2019-07-05 | 丰田自动车株式会社 | Environment inside car adjusts device, storage medium and environment inside car and adjusts system |
CN111277859A (en) * | 2020-01-15 | 2020-06-12 | 腾讯科技(深圳)有限公司 | Method and device for acquiring score, computer equipment and storage medium |
CN113076445A (en) * | 2021-04-21 | 2021-07-06 | 广州酷狗计算机科技有限公司 | Music recommendation method, device, terminal and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103034706A (en) * | 2012-12-07 | 2013-04-10 | 合一网络技术(北京)有限公司 | Video recommended list generating device and method based on information network |
US8533236B1 (en) * | 2007-11-01 | 2013-09-10 | Google Inc. | Video-related recommendations using link structure |
CN103294824A (en) * | 2013-06-19 | 2013-09-11 | 北京华悦博智科技有限责任公司 | Music collecting and combining method and system |
CN103455587A (en) * | 2013-08-29 | 2013-12-18 | 百度在线网络技术(北京)有限公司 | Method and device for obtaining push contents as well as method and device for receiving push contents |
CN103544256A (en) * | 2013-10-15 | 2014-01-29 | 北京奇虎科技有限公司 | Method and device for providing network multimedia resources |
CN103577511A (en) * | 2013-01-22 | 2014-02-12 | 网易(杭州)网络有限公司 | Method, device and system for realizing media application |
CN103858449A (en) * | 2011-07-22 | 2014-06-11 | S.M.娱乐有限公司 | Method and system for providing a social music service using an LBS, and recording medium for recording a program for executing the method |
CN103888785A (en) * | 2014-03-10 | 2014-06-25 | 百度在线网络技术(北京)有限公司 | Method and device for providing information |
CN103942337A (en) * | 2014-05-08 | 2014-07-23 | 北京航空航天大学 | Video search system based on image recognition and matching |
CN104919444A (en) * | 2012-10-11 | 2015-09-16 | 微软技术许可有限责任公司 | Topic collections |
US20150347413A1 (en) * | 2014-05-30 | 2015-12-03 | Facebook, Inc. | Systems and methods for providing non-manipulable trusted recommendations |
-
2016
- 2016-04-07 CN CN201610218865.4A patent/CN105912650B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8533236B1 (en) * | 2007-11-01 | 2013-09-10 | Google Inc. | Video-related recommendations using link structure |
CN103858449A (en) * | 2011-07-22 | 2014-06-11 | S.M.娱乐有限公司 | Method and system for providing a social music service using an LBS, and recording medium for recording a program for executing the method |
CN104919444A (en) * | 2012-10-11 | 2015-09-16 | 微软技术许可有限责任公司 | Topic collections |
CN103034706A (en) * | 2012-12-07 | 2013-04-10 | 合一网络技术(北京)有限公司 | Video recommended list generating device and method based on information network |
CN103577511A (en) * | 2013-01-22 | 2014-02-12 | 网易(杭州)网络有限公司 | Method, device and system for realizing media application |
CN103294824A (en) * | 2013-06-19 | 2013-09-11 | 北京华悦博智科技有限责任公司 | Music collecting and combining method and system |
CN103455587A (en) * | 2013-08-29 | 2013-12-18 | 百度在线网络技术(北京)有限公司 | Method and device for obtaining push contents as well as method and device for receiving push contents |
CN103544256A (en) * | 2013-10-15 | 2014-01-29 | 北京奇虎科技有限公司 | Method and device for providing network multimedia resources |
CN103888785A (en) * | 2014-03-10 | 2014-06-25 | 百度在线网络技术(北京)有限公司 | Method and device for providing information |
CN103942337A (en) * | 2014-05-08 | 2014-07-23 | 北京航空航天大学 | Video search system based on image recognition and matching |
US20150347413A1 (en) * | 2014-05-30 | 2015-12-03 | Facebook, Inc. | Systems and methods for providing non-manipulable trusted recommendations |
Non-Patent Citations (2)
Title |
---|
刘日升 等: "《外语信息检索概论》", 31 July 2009, 辽宁师范大学出版社 * |
郭安: "手机音乐分享社区应用的交互设计研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106339504A (en) * | 2016-09-23 | 2017-01-18 | 乐视控股(北京)有限公司 | Music pushing method and apparatus |
CN106446180A (en) * | 2016-09-27 | 2017-02-22 | 维沃移动通信有限公司 | Song recognition method and mobile terminal |
CN106446180B (en) * | 2016-09-27 | 2021-01-08 | 维沃移动通信有限公司 | Song identification method and mobile terminal |
CN106776774A (en) * | 2016-11-11 | 2017-05-31 | 努比亚技术有限公司 | Mobile terminal chooses picture device and method |
CN106815364A (en) * | 2017-01-24 | 2017-06-09 | 百度在线网络技术(北京)有限公司 | Content delivery method and device |
WO2018218859A1 (en) * | 2017-05-31 | 2018-12-06 | 深圳正品创想科技有限公司 | Method and device for sending electronic coupon |
CN107220854A (en) * | 2017-05-31 | 2017-09-29 | 深圳正品创想科技有限公司 | A kind of method and device for sending electronic ticket |
CN109840793A (en) * | 2017-11-28 | 2019-06-04 | 广州腾讯科技有限公司 | Method for pushing and device, storage medium, the electronic device of promotion message |
CN109840793B (en) * | 2017-11-28 | 2023-11-17 | 广州腾讯科技有限公司 | Promotion information pushing method and device, storage medium and electronic device |
CN108108436A (en) * | 2017-12-20 | 2018-06-01 | 东软集团股份有限公司 | Date storage method, device, storage medium and electronic equipment |
CN108108436B (en) * | 2017-12-20 | 2020-07-31 | 东软集团股份有限公司 | Data storage method and device, storage medium and electronic equipment |
CN109969109A (en) * | 2017-12-27 | 2019-07-05 | 丰田自动车株式会社 | Environment inside car adjusts device, storage medium and environment inside car and adjusts system |
CN111277859A (en) * | 2020-01-15 | 2020-06-12 | 腾讯科技(深圳)有限公司 | Method and device for acquiring score, computer equipment and storage medium |
CN113076445A (en) * | 2021-04-21 | 2021-07-06 | 广州酷狗计算机科技有限公司 | Music recommendation method, device, terminal and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105912650B (en) | 2021-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105912650A (en) | Method and apparatus of recommending songs | |
CN112565825B (en) | Video data processing method, device, equipment and medium | |
CN103888837B (en) | A kind of video information method for pushing and device | |
CN103635953B (en) | User's certain content is used to strengthen the system of viewdata stream | |
US10467287B2 (en) | Systems and methods for automatically suggesting media accompaniments based on identified media content | |
CN107278374A (en) | Interactive advertisement display method, terminal and smart city interactive system | |
WO2018017836A1 (en) | Live video streaming services with machine-learning based highlight replays | |
CN105872717A (en) | Video processing method and system, video player and cloud server | |
CN110008300A (en) | Determination method, apparatus, computer equipment and the storage medium of POI alias | |
CN103797482A (en) | Methods and systems for performing comparisons of received data and providing follow-on service based on the comparisons | |
CN106462609A (en) | Methods, systems, and media for presenting music items relating to media content | |
CN105653636A (en) | Information processing method and apparatus as well as information processing apparatus | |
CN105653572A (en) | Resource processing method and apparatus | |
CN111491187B (en) | Video recommendation method, device, equipment and storage medium | |
WO2017080173A1 (en) | Nature information recognition-based push system and method and client | |
CN105190618A (en) | Acquisition, recovery, and matching of unique information from file-based media for automated file detection | |
CN104834720A (en) | O2O (Online to Offline) mode-based interest point information display method and system | |
CN104838420A (en) | Rotation of image based on image content to correct image orientation | |
CN106407358B (en) | Image searching method and device and mobile terminal | |
CN103634736A (en) | A hot news sharing method based on geographical information, an apparatus and a system | |
CN106371702A (en) | Image information editing method and device and mobile terminal | |
CN103399855B (en) | Behavior intention determining method and device based on multiple data sources | |
Papadopoulos et al. | ClustTour: City exploration by use of hybrid photo clustering | |
CN109509472A (en) | Method, apparatus and system based on voice platform identification background music | |
CN113810742A (en) | Virtual gift processing method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |