CN105912650B - Method and device for recommending songs - Google Patents
Method and device for recommending songs Download PDFInfo
- Publication number
- CN105912650B CN105912650B CN201610218865.4A CN201610218865A CN105912650B CN 105912650 B CN105912650 B CN 105912650B CN 201610218865 A CN201610218865 A CN 201610218865A CN 105912650 B CN105912650 B CN 105912650B
- Authority
- CN
- China
- Prior art keywords
- songs
- information
- client
- recommended
- multimedia information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
Abstract
The invention relates to a method and a device for recommending songs. The method comprises the following steps: acquiring multimedia information shared by a client to a network community, extracting content characteristic information contained in the multimedia information, and searching songs according to the content characteristic information to obtain recommended songs; and recommending the recommended songs to the client. According to the method and the device, the multimedia information shared by the users to the network community is collected, the songs related to the multimedia information are recommended to the users, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of internet information push, in particular to a method and a device for recommending songs.
Background
When a user listens to songs on line based on a song client of an intelligent mobile terminal such as a mobile phone and a tablet, the song client usually provides a recommended song list for the user, for example: latest single song recommendations, popular song recommendations, japanese-korean song recommendations, and the like.
The main implementation forms of the existing song recommendation function include: and recommending songs with similar types according to the song listening history data of the user, or recommending based on the number of clicks of the songs, or recommending the songs based on friends of the user. However, these song recommendation methods still have difficulty in meeting the diversified requirements of people for listening to songs, for example, when people are on a trip, it is more desirable to listen to songs related to the trip, and the existing song recommendation methods cannot automatically adapt to such requirements.
Disclosure of Invention
Based on this, the method and the device for recommending songs provided by the embodiments of the present invention can recommend related songs according to the state information of the user, and are beneficial to improving user experience.
One aspect of the present invention provides a method of recommending songs, comprising:
acquiring multimedia information shared by a client to a network community;
extracting content characteristic information contained in the multimedia information;
searching songs according to the content characteristic information to obtain recommended songs;
and recommending the recommended songs to the client.
Another aspect of the present invention provides an apparatus for recommending songs, comprising:
the information collection module is used for acquiring multimedia information shared by the client to the network community;
the characteristic extraction module is used for extracting content characteristic information contained in the multimedia information;
the searching module is used for searching songs according to the content characteristic information to obtain recommended songs;
and the recommending module is used for recommending the recommended songs to the client.
According to the technical scheme, the multimedia information shared to the network community by the client is obtained, and the content characteristic information contained in the multimedia information is extracted, so that the state information of the environment where the user is located, the interested things and the like is obtained; and searching songs according to the content characteristic information to obtain related recommended songs, and recommending the recommended songs to the client, so that the songs related to the environment where the user is located or the interested things can be obtained. According to the scheme of the embodiment of the invention, the multimedia information shared by the user to the network community can be collected, and the songs related to the multimedia information are recommended to the user, so that the user experience is favorably improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of the present invention in an operating environment;
FIG. 2 is a schematic diagram illustrating a structure of a song playback client according to an embodiment;
FIG. 3 is a block diagram of a server according to an embodiment;
FIG. 4 is a schematic flow chart diagram of a method of recommending songs of an embodiment;
FIG. 5 is a technical framework diagram of a method of recommending songs, according to an embodiment;
FIG. 6 is a schematic flow chart diagram of a method of recommending songs in another embodiment;
FIG. 7 is a schematic block diagram of an apparatus for recommending songs in one embodiment;
fig. 8 is a schematic configuration diagram of an apparatus for recommending songs according to another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
FIG. 1 illustrates a schematic diagram of an operating environment of an embodiment of the present invention. The song playing client 100 with the song playing function, taking an intelligent mobile terminal as an example, includes a mobile phone, a tablet, a portable computer, etc. shown in fig. 1, and can be connected with the server 200 through a network to obtain songs through the server 200. The network may be a wireless network or a wired network. The server 200 may be a cloud server. When the song playing client 100 is used for playing songs online, the related information of the song playing client 100 is sent to the server 200, the server 200 searches for songs based on a predefined recommendation rule to obtain corresponding recommended songs, the recommended song information is sent to the song playing client 100, and the recommended songs are displayed and played through a recommended song list of the song playing client 100.
A schematic diagram of the structure of the song playback client 100 in one embodiment is shown in fig. 2. The song playing client comprises a processor, a storage medium, a display device, a communication interface, a power interface and a memory which are connected through a system bus. The device can generate a recommended song list according to the recommended songs sent by the server, and display and play the songs in the recommended song list. The display device of the song playing client can display the recommended song list and the song playing related information. The communication interface of the song playing client is used for being connected and communicated with the server, the power supply interface of the song playing client is used for being connected with an external power supply, and the external power supply supplies power to the song playing client through the power supply interface. The song playing client may be any one of the devices listed in fig. 1, and may also be other devices having the above-described structure.
A schematic diagram of the server 200 in one embodiment is shown in fig. 3. The server comprises a processor, a power supply module, a storage medium, a memory and a communication interface which are connected through a system bus. The storage medium of the server stores an operating system, a database and a song recommending device, and the song recommending device is used for realizing the song recommending method. The communication interface of the server is used for connection and communication with the song playback client 100.
Embodiments of a method for recommending songs and an apparatus for recommending songs are described below with reference to the schematic diagrams shown in fig. 1, fig. 2, and fig. 3.
FIG. 4 is a schematic flow chart diagram of a method of recommending songs of an embodiment; in this embodiment, the method is applied to the server 200 in fig. 1 as an example for explanation.
As shown in fig. 4, the method for recommending songs in this embodiment includes the steps of:
s11, acquiring multimedia information shared by the client to the network community;
the client in this embodiment may be an intelligent mobile terminal with a function of playing songs online, such as a mobile phone, a tablet, and a portable computer, or may be a software client installed in the intelligent mobile terminal and capable of playing songs online. The client side shares the multimedia information of the network community, and the sharing comprises the following steps: the client shares information of network communities such as WeChat friend circles, QQ spaces and/or microblogs. The multimedia information can be picture, character or audio-video information, or the combination of more than two of the picture, the character and the audio-video information.
In this embodiment, if the client is an intelligent mobile terminal, the client will submit the device identification information when sharing multimedia information to a network community; the corresponding web server can detect the uploading operation of the client through the equipment identification information and acquire the uploaded multimedia information. If the client is a software client in the intelligent terminal, a user can preset the association between a plurality of software clients and the music playing software (for example, the association between WeChat, QQ and/or Tencent microblog and QQ music in the intelligent terminal is set), any software client associated with the music playing software shares multimedia information to a corresponding network community, and the corresponding web server can obtain the uploading operation of the software client through the association relationship and obtain the uploaded multimedia information.
Further, the acquired multimedia information is stored in a pre-established multimedia storage component, and the association between each multimedia information and the corresponding device identification information or the music playing software client user information is established. And then, multimedia information shared by the corresponding user to the network community can be acquired from the multimedia storage component in real time or according to a set time interval.
S12, extracting content characteristic information contained in the multimedia information;
it is understood that the content feature information included in the multimedia information refers to information such as landscape features, animal features, character features, or weather features. Taking a picture as an example, the specific object information including flowers, plants, mountains, seas, stars, snow or rain can be identified based on the picture identification technology. If the multimedia information shared by the user in the network community is a video file, capturing a video frame picture according to a set time interval, and extracting content characteristic information contained in the captured video frame picture, thereby obtaining the content characteristic information contained in the video file.
Preferably, the magic identification model can be used for identifying the content characteristics of flowers, plants, mountains and waters and the like contained in the picture. The image recognition of the pan-magic recognition model has 4 layers. The first layer is the "ghost image" which performs the simplest task, and they just record the original image of the outside world just like the retina gets the image of the outside stimulus; this image is then further analyzed by "feature ghost". In the analysis process, each feature ghost searches for image features related to the feature ghost; the cognitive ghost receives the reaction of the characteristic ghost, each cognitive ghost searches for the characteristic related to the image which is responsible for identification from the reaction of the characteristic ghost, and when the characteristic is found, the cognitive ghost yells, the more the found characteristics are, the louder the sound is; and finally, selecting the reaction of the cognitive ghost with the maximum yelling sound as the image characteristic to be identified according to the sizes of a plurality of cognitive ghosts and yelling sounds by the decision ghost. For example: when recognizing the image of the letter R, the "ghost" encodes R first and transmits the information to the "ghost" for further processing, and at this time, 5 "ghosts" respectively report a vertical line, two horizontal lines, an oblique line, 3 right angles and a discontinuous curve included in the image. Many "cognizant ghosts" then identify whether or not they are the image of the letter for which they are responsible based on the reported characteristics and their number. At this point D, P, R ghost reacts, but Pty has only 4 features to match it and one feature (diagonal) to match it; d ghost has only 3 characteristics which are in accordance with the D ghost, and has two characteristics (oblique lines and right angles) which are not in accordance with the D ghost; only R ghost has 5 features to fit it and these 5 features include all the features of R, so that the shout of R ghost is the largest, so that the decision ghost makes a decision to select R image as the recognition result easily. Moreover, the universal magic recognition model can be distinguished for similar graphs, so that confusion is avoided; for distorted patterns, such as letters to be recognized, the recognition is not difficult when the size changes. Therefore, the embodiment adopts the magic identification model to identify the content characteristics contained in the picture, and the identification accuracy is good.
As a preferred implementation of step S12, the manner of extracting the content feature information included in the multimedia information may be: and matching the multimedia information with a reference file in a preset media library to obtain a matched reference file, and acquiring preset keywords associated with the matched reference file as content characteristic information of the multimedia information. Correspondingly, a media library is required to be created in advance, and a plurality of reference files are stored in the media library; and setting keywords associated with the reference files. For example, a picture is identified by adopting an image identification technology, content characteristic information contained in the picture is matched with a preset reference picture in a picture library to obtain a matched reference picture, keywords preset for the matched reference picture are acquired, and the content characteristic information of the picture is replaced by the keywords to perform song retrieval according to the keywords. Correspondingly, a picture library is required to be created in advance, a plurality of reference pictures are stored in the picture library, and relevant keywords are set for each reference picture.
S13, searching songs according to the content characteristic information to obtain recommended songs;
in this embodiment, the content feature information may be directly used as a keyword to perform song search, and the content feature information may also be reasonably expanded or deformed to obtain a more accurate and comprehensive keyword to perform song search.
And S14, recommending the recommended songs to the client.
It can be understood that a piece of multimedia information may include a plurality of pieces of content characteristic information, and song search may be performed according to each piece of content characteristic information, or a plurality of pieces of content characteristic information may be combined, and song search may be performed based on the combined information. There may be repeated songs in the resulting recommended songs. As a preferred embodiment, before recommending the recommended song to the client, the method further includes detecting whether there is a repeated song in the recommended song, and if so, performing deduplication on the recommended song. For example: and detecting whether the recommended songs have the same song name and singer, and if so, performing de-duplication on the same song.
It will be appreciated that the rules for de-duplicating the recommended songs may be adjusted according to the user's preferences, such as: and detecting whether songs with the same name, singer and file size exist in the recommended songs, and if so, performing de-duplication on the same songs. So that the same song sung by different singers is preserved because the file sizes are different.
In this embodiment, the recommended song is sent to the client, and the recommended song is added to a recommended song list of the client. It will be appreciated that the newly derived recommended songs may be added to the end of the client recommended song list, inserted into the top of the client recommended song list, or randomly inserted into the client recommended song list. As a preferred implementation manner, in this embodiment, a newly obtained recommended song is inserted into the top of the recommended song list of the client, so that the newly obtained recommended song can be preferentially played.
As a preferred embodiment, step S11 may further include a step of obtaining sharing time information corresponding to each multimedia message. Correspondingly, the method also comprises the following steps after the recommended songs are obtained: according to the sequence of the sharing time, sequencing the recommended songs corresponding to the multimedia information, and sequencing the recommended songs corresponding to the multimedia information with the later sharing time in front; and sending the sequenced recommended songs to the client, and adding the recommended songs into a recommended song list of the client according to the sequence.
Similarly, after the recommended songs are added to the recommended song list of the client, repeated songs may exist in the recommended song list. Therefore, whether repeated songs exist in a recommended song list of the client side can be detected, and the songs in the recommended song list are deduplicated; and the client displays the de-duplicated recommended song list for the user to click and play.
FIG. 5 is a technical framework diagram of a method of recommending songs, according to an embodiment; as shown in fig. 5, taking a picture as an example, the way of recommending songs in this embodiment is divided into two ways, namely real-time recommendation and non-real-time recommendation. The two pathways are described separately below.
Recommending songs in real time: in this approach, the step S11 of obtaining the multimedia information shared by the client to the network community means that the multimedia information currently shared by the client to the network community is obtained; and searching songs based on the content characteristic information of the multimedia information to obtain recommended songs related to the current sharing information of the user so as to ensure the real-time property of song recommendation. For example: the method comprises the steps that a client clicks a button for sharing (or uploading) a picture to a network community, a network server receives information that the client shares the picture to the network community, a relevant background CGI (background service interface service processing program) is informed to obtain the picture shared by the client at present, content characteristic information (such as flowers, mountains, snow and the like) of the picture is extracted, relevant recommended songs are obtained according to the content characteristic information, the recommended songs are sent to the client, the recommended songs are added into a recommended song list of the client, and the client clicks and plays the recommended songs by displaying the recommended song list. If the user shares the picture of a certain scenery, the recommended songs related to the scenery can be obtained in real time.
Non-real-time song recommendation: in this approach, the step S11 of obtaining the multimedia information shared by the client to the network community means that all the multimedia information shared by the client to the network community within a set time is collected, the multimedia information is analyzed in a unified manner, content feature information of each multimedia information is extracted to perform song search, and a recommended song related to each multimedia information is obtained. For example: users share pictures to a circle of friends or other types of web communities. The network server receives the information of sharing the pictures by the client, informs a related background CGI to count the shared pictures, and the pictures shared by the user are all stored in a specified network TFS (multimedia storage component such as pictures, audios and videos); and by inquiring the network TFS, collecting all pictures which are shared by the user in the network community within 24 hours before the current time, analyzing content characteristic information contained in each picture, uniformly searching songs, sending recommended songs to the client, and adding the recommended songs to a recommended song list of the client. If a user shares a picture of a certain landscape today, recommended songs related to the landscape are available tomorrow.
The differences between the two approaches include: the real-time performance of the method is high, the content characteristics of the multimedia information shared by the user to the network community are extracted in real time, the corresponding recommended song is quickly found, and the user experience is good in real time; the latter has low time requirement, so that more detailed feature extraction can be performed on the multimedia information shared by the user to the network community (for example, a way of matching with reference information in a media library, taking a picture as an example, specifically, the picture is respectively matched with reference pictures in a picture library, feature information corresponding to the matched reference pictures is read, and the feature information is used as content feature information contained in the picture shared by the user), so that more comprehensive and accurate recommended songs can be obtained.
As another preferred embodiment, a way of recommending songs in non-real time is to collect multimedia information shared by a client to a network community within a set time, and then read sharing time information corresponding to each piece of multimedia information (i.e., time when the client shares the multimedia information); and sequencing the recommended songs corresponding to the multimedia information according to the sequence of the sharing time, and sequencing the recommended songs corresponding to the multimedia information with the later sharing time in front. And sending the sequenced recommended songs to the client, and adding the recommended songs into a recommended song list of the client according to the sequence, so that the recommended songs corresponding to the multimedia information with later sharing time are preferentially played.
Based on the method for recommending songs in the embodiment, the user shares the picture of the sea to the WeChat friend circle when playing at the sea, and the server can acquire the picture and extract the content characteristic information contained in the picture, so that the songs related to the sea are recommended for the user. Or the user shares the pictures of the forest to a friend circle or a network when playing in the forest, and the server can acquire the pictures and extract content characteristic information contained in the pictures to recommend songs related to the forest for the user. And the user can display and play the recommended songs sent by the server through the recommended song list displayed by the client. Based on the method for recommending songs, the obtained recommended songs are more in line with the state of the user, and the user experience is favorably improved.
FIG. 6 is a schematic flow chart diagram of a method of recommending songs in another embodiment; in this embodiment, the description will be given taking an application to the server 200 as an example. The main differences between this embodiment and the previous embodiment are: and recommending songs by combining the geographical position information of the client when the user shares the multimedia information to the network community.
As shown in fig. 6, the method for recommending songs in this embodiment includes the steps of:
s21, acquiring multimedia information shared by the client to the network community, and acquiring position information when the client shares the multimedia information;
the network community comprises: the network communities such as WeChat friend circles, QQ spaces, microblogs and the like. The multimedia information is one or more of pictures, characters and audio/video information. The location information is GPS information or other information indicating the geographic location of the client.
S22, extracting content characteristic information contained in the multimedia information;
s23, searching songs according to the content characteristic information and the position information to obtain recommended songs;
and S23, recommending the recommended songs to the client.
Specific implementation manners of step S23 may include the following two types:
and in the first mode, song searching is directly carried out according to the content characteristic information and the position information to obtain a recommended song. The content characteristic information and the position information are used as keywords to conduct song search, and therefore the obtained recommended songs include songs related to the content of the multimedia information and songs related to the sharing place of the multimedia information.
The second method comprises the following steps: judging whether the position of the client when the client shares the multimedia information is a preset area or not according to the content characteristic information and the position information; if the preset area is found, searching songs by using the keywords corresponding to the content characteristic information and the keywords corresponding to the preset area; otherwise, only the keywords corresponding to the content characteristic information are used for song searching.
Preferably, the predetermined area in this embodiment is a tourist area. In the second mode, the specific mode of determining whether the sharing location corresponding to the multimedia information is the predetermined area according to the content feature information and the position information may include: if the content feature information contains landscape features and the position information exists in a position list of a preset area, judging that the sharing place corresponding to the multimedia information is a tourism area; otherwise, judging that the sharing place corresponding to the multimedia information is not a tourist area. Taking pictures as an example, when the client shares landscape pictures to the network community, the client also acquires the GPS information of the client and submits the GPS information to the relevant background CGI. The background CGI sends the landscape picture and the GPS information to a picture analysis matching service, the picture analysis service extracts content characteristic information of the landscape picture, and whether a sharing place of the landscape picture is a tourist area is judged according to the content characteristic information (such as mountains, seas and the like) and the GPS information; if so, recommending songs of the tourist area related to the picture scenery, or recommending songs of the tourist area and songs of the picture scenery; if not, only songs relevant to the picture scenery are recommended.
According to the method for recommending songs, the multimedia information shared by the client to the network community and the sharing position information of the multimedia information are obtained, the content characteristic information contained in the multimedia information is extracted, and the state of the user when the user shares the multimedia information can be obtained more accurately based on the content characteristic information and the sharing position information; and searching songs according to the content characteristic information and the position information, so that the matching degree of the recommended songs and the user state is better.
It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present invention is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present invention.
Based on the same idea as the method of recommending songs in the above embodiments, the present invention also provides an apparatus for recommending songs, which can be used to perform the above method of recommending songs. For convenience of explanation, only the parts related to the embodiments of the present invention are shown in the schematic structural diagram of the embodiment of the apparatus for recommending songs, and it will be understood by those skilled in the art that the illustrated structure does not constitute a limitation to the apparatus, and may include more or less components than those illustrated, or combine some components, or arrange different components.
FIG. 7 is a schematic block diagram of an apparatus for recommending songs in accordance with an embodiment of the present invention; as shown in fig. 7, the apparatus for recommending songs of the present embodiment includes: an information collection module 710, a feature extraction module 720, a search module 730, and a recommendation module 740, each of which is detailed as follows:
the information collecting module 710 is configured to obtain multimedia information that the client shares with the network community;
it can be understood that, in this embodiment, the network community includes: the network communities such as WeChat friend circles, QQ spaces, microblogs and the like. The multimedia information is one or more of pictures, characters and audio/video information. The location information is GPS information or other information indicating the geographic location of the client.
The feature extraction module 720 is configured to extract content feature information included in the multimedia information;
as can be understood, the content feature information includes: one or more of landscape features, animal features, character features, weather features.
The search module 730 is configured to perform song search according to the content feature information to obtain a recommended song;
in this embodiment, the content feature information may be directly used as a keyword to perform song search, and the content feature information may also be reasonably expanded or deformed to obtain a more accurate and comprehensive keyword to perform song search.
The recommending module 740 is configured to recommend the recommended song to the client.
As a preferred implementation manner, the information collecting module 710 in this embodiment may include:
the first information acquisition unit is used for collecting multimedia information shared by the client to the network community within a set time; or, the second information obtaining unit is configured to obtain the multimedia information currently shared by the client to the network community.
As another preferred embodiment, the feature extraction module 720 may be configured to match the multimedia information with a reference file in a preset media library to obtain a matched reference file, and obtain a preset keyword associated with the matched reference file as content feature information of the multimedia information. Correspondingly, the device for recommending songs in the embodiment may further include a setting module, configured to create a media library, where the multimedia library stores a plurality of reference files; and setting keywords associated with the reference files.
As another preferred embodiment, the apparatus for recommending songs of this embodiment further includes: and the duplication removing module is used for detecting whether repeated songs exist in the recommended songs or not, and if so, carrying out duplication removal on the recommended songs. For example: detecting whether songs with the same name and the same singer exist in the recommended songs, and if so, removing the duplication from the same songs; or detecting whether songs with the same name, singer and file size exist in the recommended songs, and if so, performing de-duplication on the same songs. Correspondingly, the recommending module 740 may be configured to send the deduplicated recommended song to the client, so as to add the recommended song to the recommended song list of the client.
As another preferred embodiment, the information obtaining module 710 is further configured to obtain sharing time information corresponding to each multimedia information. Correspondingly, the apparatus for recommending songs of the present embodiment may further include: and the sorting module is used for sorting the recommended songs corresponding to the multimedia information according to the sequence of the sharing time, and sorting the recommended songs corresponding to the multimedia information with the later sharing time in front. Correspondingly, the recommending module 740 may be configured to send the sorted recommended songs to the client, so as to add the recommended songs to the recommended song list of the client according to the sort.
FIG. 8 is a schematic block diagram of an apparatus for recommending songs in another embodiment; on the basis of the previous embodiment, the information collection module 710 in this embodiment is further configured to obtain location information when the client shares the multimedia information. Correspondingly, the searching module 730 is further configured to search for a song according to the content feature information and the location information. Preferably, the searching module 730 may specifically include:
a determining unit 731, configured to determine whether a sharing location corresponding to the multimedia information is a predetermined area according to the content feature information and the position information; a first searching unit 732, configured to perform a song search using the keyword corresponding to the content feature information and the keyword corresponding to the predetermined area if the determination result of the determining unit is yes; the second searching unit 733 is configured to perform a song search using the keyword corresponding to the content feature information if the determination result of the determining unit is negative.
In a preferred embodiment, the predetermined area is a tourist area. Correspondingly, the determining unit 731 can be specifically configured to: and if the content feature information contains landscape features and the position information exists in a position list of a preset area, determining that the sharing place corresponding to the multimedia information is a tourist area. Of course, the predetermined area may be set to other types of areas.
As a preferred embodiment, the location information in this embodiment is client GPS information, but may be set as other information that can represent the geographic location of the client.
It should be noted that, in the implementation of the foregoing example device for recommending songs, because the contents of information interaction, execution process, and the like between the modules/units are based on the same concept as the foregoing method embodiment of the present invention, the technical effect brought by the above example method embodiment of the present invention is the same as the foregoing method embodiment of the present invention, and specific contents may refer to the description in the method embodiment of the present invention, and are not described herein again.
In addition, in the above-mentioned embodiment of the song recommending apparatus, the logical division of the functional modules is only an example, and in practical applications, the above-mentioned function distribution may be performed by different functional modules according to needs, for example, due to the configuration requirements of corresponding hardware or the convenience of implementation of software, that is, the internal structure of the song recommending apparatus is divided into different functional modules to perform all or part of the above-mentioned functions. The functional modules can be realized in a hardware mode or a software functional module mode.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium and sold or used as a stand-alone product. The program, when executed, may perform all or a portion of the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. It will be understood that the terms "first," "second," and the like as used herein are used herein to distinguish one object from another, but the objects are not limited by these terms. For example, the first search unit may be referred to as a second search unit, and the second search unit may be referred to as a first search unit without departing from the scope of the present invention.
The above-described examples merely represent several embodiments of the present invention and should not be construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (16)
1. A method of recommending songs, comprising:
setting an association between at least one client and music playing software;
the method for acquiring the multimedia information shared by the client to the network community comprises the following steps: when any associated client side is detected to share the multimedia information to a corresponding network community, the uploading operation of the client side is obtained, and the uploaded multimedia information is obtained; the multimedia information comprises picture or audio/video information;
extracting content characteristic information contained in the multimedia information based on an image recognition technology; the content characteristic information is used for representing at least one of the environment where the user is located and things which the user is interested in the multimedia information, and the content characteristic information is information which is irrelevant to music in the multimedia information;
searching songs according to the content characteristic information to obtain recommended songs;
and recommending the recommended songs to the client.
2. The method for recommending songs of claim 1, wherein extracting content feature information contained in the multimedia information comprises:
matching the multimedia information with a reference file in a preset media library to obtain a matched reference file, and acquiring preset keywords associated with the matched reference file as content characteristic information of the multimedia information; the reference file is a reference picture.
3. The method for recommending songs according to claim 1, wherein the obtaining of the multimedia information shared by the client to the web community further comprises:
acquiring position information when the client shares the multimedia information;
the song searching according to the content characteristic information comprises the following steps:
and searching songs according to the content characteristic information and the position information.
4. The method of claim 3, wherein the performing a song search according to the content characteristic information and the location information comprises:
judging whether a sharing place corresponding to the multimedia information is a preset area or not according to the content characteristic information and the position information; if the preset area is found, searching songs by using the keywords corresponding to the content characteristic information and the keywords corresponding to the preset area; otherwise, searching songs by using the keywords corresponding to the content characteristic information.
5. The method for recommending songs according to claim 1, wherein the obtaining of the multimedia information shared by the client to the web community further comprises:
acquiring sharing time information corresponding to each multimedia information;
obtaining a recommended song, and then:
according to the sequence of the sharing time, sequencing the recommended songs corresponding to the multimedia information, and sequencing the recommended songs corresponding to the multimedia information with the later sharing time in front;
the recommending the recommended song to the client comprises:
and sending the sequenced recommended songs to the client, and adding the recommended songs into a recommended song list of the client according to the sequence.
6. The method of recommending songs of claim 1, wherein obtaining a recommended song further comprises:
and detecting whether the recommended songs have the same song name and singer, and if so, removing the duplication from the same songs.
7. The method of recommending songs of claim 1, wherein said multimedia information further comprises: and (5) writing.
8. An apparatus for recommending songs, comprising:
the setting module is used for setting the association between at least one client and the music playing software;
the information collection module is used for obtaining the multimedia information shared by the client to the network community, and comprises: when any associated client side is detected to share the multimedia information to a corresponding network community, the uploading operation of the client side is obtained, and the uploaded multimedia information is obtained; the multimedia information comprises picture or audio/video information;
the characteristic extraction module is used for extracting content characteristic information contained in the multimedia information based on an image recognition technology; the content characteristic information is used for representing at least one of the environment where the user is located and things which the user is interested in the multimedia information, and the content characteristic information is information which is irrelevant to music in the multimedia information;
the searching module is used for searching songs according to the content characteristic information to obtain recommended songs;
and the recommending module is used for recommending the recommended songs to the client.
9. The apparatus for recommending songs of claim 8, wherein the feature extraction module is configured to match the multimedia information with a reference file in a preset media library to obtain a matched reference file, and obtain a preset keyword associated with the matched reference file as content feature information of the multimedia information; the reference file is a reference picture.
10. The apparatus for recommending songs of claim 8, wherein the information collection module is further configured to obtain location information when the client shares the multimedia information;
and the searching module is also used for searching songs according to the content characteristic information and the position information.
11. The apparatus for recommending songs of claim 10, wherein said search module comprises:
the judging unit is used for judging whether a sharing place corresponding to the multimedia information is a preset area or not according to the content characteristic information and the position information;
a first searching unit, configured to, if the determination result of the determining unit is yes, perform song search using the keyword corresponding to the content feature information and the keyword corresponding to the predetermined area;
and the second searching unit is used for searching songs by using the keywords corresponding to the content characteristic information if the judgment result of the judging unit is negative.
12. The apparatus for recommending songs of claim 8, wherein the information obtaining module is further configured to obtain sharing time information corresponding to each multimedia information;
the apparatus for recommending songs further comprises: the sorting module is used for sorting the recommended songs corresponding to the multimedia information according to the sequence of the sharing time, and sorting the recommended songs corresponding to the multimedia information with the later sharing time in front;
and the recommending module is used for sending the sequenced recommended songs to the client so as to add the recommended songs into a recommended song list of the client according to the sequence.
13. The apparatus for recommending songs of claim 8, further comprising:
the duplication removing module is used for detecting whether songs with the same name and the same singer exist in the recommended songs or not, and if so, duplication removing is carried out on the same songs;
and the recommending module is used for sending the de-duplicated recommended songs to the client so as to add the recommended songs to a recommended song list of the client.
14. The apparatus for recommending songs of claim 8, wherein said multimedia information further comprises: and (5) writing.
15. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
16. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
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 CN105912650A (en) | 2016-08-31 |
| CN105912650B true 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) |
Families Citing this family (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 |
| 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 |
| 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 |
| 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 |
| 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 |
| JP2019117562A (en) * | 2017-12-27 | 2019-07-18 | トヨタ自動車株式会社 | Vehicle interior environment adjustment device, program, and vehicle interior environment adjustment system |
| CN111277859B (en) * | 2020-01-15 | 2021-12-14 | 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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7853622B1 (en) * | 2007-11-01 | 2010-12-14 | Google Inc. | Video-related recommendations using link structure |
| US20140108408A1 (en) * | 2012-10-11 | 2014-04-17 | Microsoft Corporation | Topic collections |
| CN103034706B (en) * | 2012-12-07 | 2015-10-07 | 合一网络技术(北京)有限公司 | A kind of generation device of the video recommendations list based on information network and method |
| CN103455587B (en) * | 2013-08-29 | 2017-09-26 | 百度在线网络技术（北京）有限公司 | Obtain and push the method and device of content, receive the method and device for pushing content |
| 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 |
| US10565212B2 (en) * | 2014-05-30 | 2020-02-18 | 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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105912650A (en) | 2016-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105912650B (en) | Method and device for recommending songs | |
| US11451856B2 (en) | Providing visual content editing functions | |
| US9727565B2 (en) | Photo and video search | |
| US8826320B1 (en) | System and method for voting on popular video intervals | |
| US9189699B2 (en) | Augmented reality interaction implementation method and system | |
| CN103207870B (en) | Photo classification management method, server, device and system | |
| CN103635953B (en) | User's certain content is used to strengthen the system of viewdata stream | |
| CN107291888B (en) | Machine learning statistical model-based living recommendation system method near living hotel | |
| CN110162643B (en) | Electronic album report generation method, device and storage medium | |
| US11070851B2 (en) | System and method for providing image-based video service | |
| WO2017197826A1 (en) | Relationship-based image feature matching method, device, and system | |
| 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 | |
| CN105872717A (en) | Video processing method and system, video player and cloud server | |
| CN104168433A (en) | Media content processing method and system | |
| CN103440243A (en) | Teaching resource recommendation method and device thereof | |
| Adams et al. | Extraction of social context and application to personal multimedia exploration | |
| US8655883B1 (en) | Automatic detection of similar business updates by using similarity to past rejected updates | |
| CN110633404A (en) | Application message pushing method and device, storage medium and terminal equipment | |
| CN110609879B (en) | Interest point duplicate determination method and device, computer equipment and storage medium | |
| WO2014197218A1 (en) | Photo and video sharing | |
| CN105843865B (en) | Media file playing method and device | |
| CN113422826A (en) | Information pushing method and device | |
| CN106411975B (en) | Data output method and device and computer readable storage medium | |
| CN109522444B (en) | Request processing method and device, storage medium and electronic device |
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 |