CN106844504B - A kind of method and apparatus for sending song and singly identifying - Google Patents
A kind of method and apparatus for sending song and singly identifying Download PDFInfo
- Publication number
- CN106844504B CN106844504B CN201611225021.9A CN201611225021A CN106844504B CN 106844504 B CN106844504 B CN 106844504B CN 201611225021 A CN201611225021 A CN 201611225021A CN 106844504 B CN106844504 B CN 106844504B
- Authority
- CN
- China
- Prior art keywords
- song
- list
- similarity
- numerical value
- matching degree
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information 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 embodiment of the invention discloses a kind of method and apparatus for sending song and singly identifying, and belong to field of computer technology.The described method includes: obtaining the behavior similarity of the single every song of the first song every song single with the second song；According to the behavior similarity of the single every song of the first song every song single with the second song, the behavior similarity that the first song is single and the second song is single is calculated；According to the behavior similarity of the first song list and the second song list, the matching degree numerical value of the first song list and the second song list is determined, and by the single song list mark with the second song list of the first song, matching degree numerical value, store to every two and sing in single and matching degree numerical value corresponding relationship；When the single song list acquisition request of the correspondence target song for receiving terminal transmission, according to the single corresponding relationship with matching degree numerical value of every two song, the determining maximum preset number song of the matching degree numerical value single with target song is single, sends the single song list mark of preset number song to terminal.Using the present invention, the single efficiency of selection song can be improved.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of method and apparatus for sending song and singly identifying.
Background technique
With the development of computer technology, the terminals such as mobile phone, computer are widely used, in corresponding terminal
The type of application program is more and more, function is more and more abundant.Playback of songs class application program is a kind of application being in daily use
Program.
User can play song by playback of songs class application program.Currently, playback of songs class application program is often
It is single to provide some songs, wherein include number of songs in song list.User wants to play song by playback of songs class application program
When, it can be in the single-row table of song that playback of songs class application program provides, it can be according to letters such as song single label, title, brief introductions
Breath, selects the song list for oneself liking listening, it is then possible to click play button, triggering terminal plays the song in selected song list.
In the implementation of the present invention, the inventor finds that the existing technology has at least the following problems:
Based on above-mentioned processing mode, when user wants some song list of selection every time, it is required in playback of songs class application journey
The song list for oneself liking listening is selected in the single-row table of song that sequence provides, the song odd number amount often sung in single-row table is relatively more, thus, it leads
The efficiency for causing selection song single is lower.
Summary of the invention
In order to solve the problems, such as that the efficiency for selecting song single in the prior art is lower, the embodiment of the invention provides a kind of transmissions
Sing the method and apparatus singly identified.The technical solution is as follows:
In a first aspect, providing a kind of method for sending song and singly identifying, which comprises
In the corresponding behavior similarity list of pre-stored every two song, every first song that the first song singly includes is obtained
The behavior similarity of the bent every song for singly including with the second song；
The every song for singly including according to first song is similar to the behavior of every song that second song singly includes
Degree calculates the single behavior similarity of single and described second song of first song；
According to the single behavior similarity of the first song list and second song, the first song list and described second are determined
Sing single matching degree numerical value, and by the single song list mark of the single single mark of song of first song, second song, the matching degree
Numerical value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song；
When the single song list acquisition request of the correspondence target song for receiving terminal transmission, according to every two song it is single with
Corresponding relationship with degree value, the determining maximum preset number song of the matching degree numerical value single with target song is single, Xiang Suoshu
Terminal sends the single song list mark of the preset number song.
Optionally, the method also includes:
Obtain the recommended information of first song single recommended information and the second song list；
According to the single recommended information of the single recommended information of first song and second song, determine first song it is single and
The single content similarity of second song；
The behavior similarity single according to single and described second song of first song, determines that first song is single and described
The single matching degree numerical value of second song, comprising:
According to single and described second song of first song single behavior similarity and content similarity, first song is determined
The single matching degree numerical value of single and described second song.
Optionally, the recommended information includes title text information and/or brief introduction text information；
The recommended information of the recommended information single according to first song and the second song list, determines first song
The single content similarity of single and described second song, comprising:
The recommended information of the recommended information single to first song and the second song list carries out word segmentation processing respectively, obtains
The set of words of first song single set of words and the second song list；
Determine each frequency of occurrence for presetting word respectively in the single set of words of first song and described second
The frequency of occurrence in single set of words, and the single corresponding set of words of all songs according to the pre-stored data are sung, is determined described every
The corresponding reverse document-frequency of a default word；
According to frequency of occurrence of each default word in the single set of words of first song and described each pre-
If the corresponding reverse document-frequency of word, the single corresponding text vector of the first song is determined, according to each default word
Frequency of occurrence and each default corresponding reverse document-frequency of word in the single set of words of second song, determine
The single corresponding text vector of second song；
It is similar with the cosine of the single corresponding text vector of the second song to calculate the single corresponding text vector of the first song
Degree obtains the single content similarity of single and described second song of first song.
Optionally, the recommended information includes label information；
The recommended information of the recommended information single according to first song and the second song list, determines first song
The single content similarity of single and described second song, comprising:
The recommended information single according to the single recommended information of first song and second song respectively, determines first song
Single corresponding label vector and the single corresponding label vector of the second song；
It is similar with the cosine of the single corresponding label vector of the second song to calculate the single corresponding label vector of the first song
Degree obtains the single content similarity of single and described second song of first song.
Optionally, the behavior similarity and content similarity single according to single and described second song of first song, really
The single matching degree numerical value of fixed single and described second song of first song, comprising:
Behavior similarity according to the pre-stored data and the corresponding weight of content similarity and first song it is single and
Second song single behavior similarity and content similarity determine the single matching degree of single and described second song of first song
Value.
Optionally, described according to the single corresponding relationship with matching degree numerical value of every two song, it is determining to be sung with the target
The maximum preset number song of single matching degree numerical value is single, comprising:
The single corresponding label information of each song according to the pre-stored data, determines the label of label information and target song list
The song Dan Jihe that information matches；
According to the single corresponding relationship with matching degree numerical value of every two song, in the song singly set, selection with it is described
The maximum preset number song of the single matching degree numerical value of target song is single.
Second aspect, provides a kind of device for sending song and singly identifying, and described device includes:
First obtains module, in the corresponding behavior similarity list of pre-stored every two song, acquisition the
The behavior similarity for every song that every song that one song singly includes singly includes with the second song；
Computing module, every song that every song and second song for singly including according to first song singly include
Bent behavior similarity calculates the single behavior similarity of single and described second song of first song；
Memory module determines described first for the behavior similarity single according to single and described second song of first song
The single matching degree numerical value of single and described second song of song, and the song list that the single single mark of song of first song, second song is single
Mark, the matching degree numerical value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song；
Sending module, for when the single song list acquisition request of the correspondence target song for receiving terminal transmission, according to described
The single corresponding relationship with matching degree numerical value of every two song, the determining matching degree numerical value maximum preset number single with target song
A song is single, and Xiang Suoshu terminal sends the single song list mark of the preset number song.
Optionally, described device further include:
Second obtains module, for obtaining the recommended information of first song single recommended information and the second song list；
Determining module is determined for the recommended information single according to the single recommended information of first song and second song
The single content similarity of single and described second song of first song；
The memory module, is used for:
According to single and described second song of first song single behavior similarity and content similarity, first song is determined
The single matching degree numerical value of single and described second song.
Optionally, the recommended information includes title text information and/or brief introduction text information；
The determining module, is used for:
The recommended information of the recommended information single to first song and the second song list carries out word segmentation processing respectively, obtains
The set of words of first song single set of words and the second song list；
Determine each frequency of occurrence for presetting word respectively in the single set of words of first song and described second
The frequency of occurrence in single set of words, and the single corresponding set of words of all songs according to the pre-stored data are sung, is determined described every
The corresponding reverse document-frequency of a default word；
According to frequency of occurrence of each default word in the single set of words of first song and described each pre-
If the corresponding reverse document-frequency of word, the single corresponding text vector of the first song is determined, according to each default word
Frequency of occurrence and each default corresponding reverse document-frequency of word in the single set of words of second song, determine
The single corresponding text vector of second song；
It is similar with the cosine of the single corresponding text vector of the second song to calculate the single corresponding text vector of the first song
Degree obtains the single content similarity of single and described second song of first song.
Optionally, the recommended information includes label information；
The determining module, is used for:
The recommended information single according to the single recommended information of first song and second song respectively, determines first song
Single corresponding label vector and the single corresponding label vector of the second song；
It is similar with the cosine of the single corresponding label vector of the second song to calculate the single corresponding label vector of the first song
Degree obtains the single content similarity of single and described second song of first song.
Optionally, the memory module, is used for:
Behavior similarity according to the pre-stored data and the corresponding weight of content similarity and first song it is single and
Second song single behavior similarity and content similarity determine the single matching degree of single and described second song of first song
Value.
Optionally, the sending module, is used for:
The single corresponding label information of each song according to the pre-stored data, determines the label of label information and target song list
The song Dan Jihe that information matches；
According to the single corresponding relationship with matching degree numerical value of every two song, in the song singly set, selection with it is described
The maximum preset number song of the single matching degree numerical value of target song is single.
Technical solution provided in an embodiment of the present invention has the benefit that
In the embodiment of the present invention, server can according to user behavior (such as broadcasting in the past period, downloading and
Collection record) the behavior similarity of song two-by-two is precalculated, in turn, server can be similar according to the behavior of song two-by-two
Degree calculates the behavior similarity that the first song is single and the second song is single；According to the behavior similarity that the first song is single and the second song is single, determine
The matching degree numerical value that first song is single and the second song is single, and by the single song list mark of the single mark of the single song of the first song, the second song, matching
Degree value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song.Whenever the correspondence for receiving terminal transmission
When the song list acquisition request of target song list, according to the single corresponding relationship with matching degree numerical value of every two song, determining and target song is single
Matching degree numerical value maximum preset number song it is single, in turn, the single song list of preset number song can be sent to terminal and is identified.
In this way, user can sing in single mark in the preset number of server push, the song list for oneself liking listening is selected, without in institute
Have in song list and select, it is thus possible to improve the single efficiency of selection song.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of method flow diagram for sending song and singly identifying provided in an embodiment of the present invention；
Fig. 2 is a kind of system framework schematic diagram provided in an embodiment of the present invention；
Fig. 3 is a kind of apparatus structure schematic diagram for sending song and singly identifying provided in an embodiment of the present invention；
Fig. 4 is a kind of apparatus structure schematic diagram for sending song and singly identifying provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of server provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
The embodiment of the invention provides a kind of method for sending song and singly identifying, the executing subject of this method is server,
In, which can be the background server of playback of songs class application program.Processor can be set in the server, received
Device and memory are sent out, processor can be used for calculating the single matching degree numerical value of every two song, and determining and target sings single-phase
The relevant treatment for the single-row table of song matched, transceiver can be used for sending and receiving data, and memory can be used for storing following places
The data for needing and generating during reason.
Below in conjunction with specific embodiment, process flow shown in FIG. 1 is described in detail, content can be as
Under:
Step 101, in the corresponding behavior similarity list of pre-stored every two song, obtaining the first song singly includes
Every song with second song singly include every song behavior similarity.
Wherein, the behavior similarity of every two song can be according to the calculated song similarity of user behavior.
In an implementation, detection cycle can be previously stored in server, every preset detection cycle, server can be with
Pre-stored each account identification is obtained in default historical period to the behavioral data of every song, wherein behavioral data
It may include the broadcasting, downloading, collection record data of user, then, for each account identification, server can be according to the account
Family identifies the behavioral data to every song, gives a mark to every song, obtains scoring of the account mark to every song,
Wherein, each account identification can be stored (wherein, account mark to the scoring of every song by server in the form of two-dimensional matrix
The quantity of knowledge is the line number of two-dimensional matrix, and the quantity of song is the columns of two-dimensional matrix), each position in two-dimensional matrix
Numerical value indicate the scoring of the account identification of the row to the song of the column, for example, the numerical value of position (p, q) indicates account identification p
Scoring to song q.After obtaining two-dimensional matrix, server can use matrix decomposition algorithm, and it is corresponding every to obtain two-dimensional matrix
The song features vector of the every song of account vector sum of a account identification.It, can after obtaining the song features vector of every song
With calculate two-by-two the feature vector of song cosine similarity cosin to get to cosine similarity be this two song pair
The behavior similarity answered, wherein the cosine similarity cosin (x, y) of song x and song y can be calculated according to formula (1),
In,Indicate the song features vector of song x,Indicate the song features vector of song y,It indicatesMould it is long,It indicatesMould it is long.After obtaining the behavior similarity of all songs two-by-two, it can be stored.
For each detection cycle, after obtaining the behavior similarity of every two song, server can be calculated and is stored in advance
The single matching degree numerical value of every two song.Below for calculating the matching degree numerical value that the first song is single and the second song is single, detailed table
State the calculation method of the single matching degree numerical value of every two song:
The song that server can determine that the first song list and the second song singly separately include in turn can be pre-stored
In the corresponding behavior similarity list of every two song, obtains every song that the first song singly includes and second and sing singly include every
The behavior similarity of song, that is to say, that for first song singly include every song, the available song of server and
The behavior similarity for each song that second song singly includes, obtains multiple behavior similarities.
Step 102, the every song for singly including according to the first song is similar to the behavior of every song that the second song singly includes
Degree calculates the behavior similarity that the first song is single and the second song is single.
In an implementation, server obtains the row for every song that every song that the first song singly includes singly includes with the second song
After similarity, the behavior similarity for every song that every song that the first song singly includes singly includes with the second song can be calculated
Average similarity, and can be using obtained average similarity as the behavior similarity that the first song is single and the second song is single.Specifically
, server can calculate the average similarity of multiple behavior similarities according to formula (2), it can calculate according to formula (2)
The behavior similarity S2 that first song is single and the second song is single.
Wherein, S1i,jIndicate the behavior similarity of song i and song j, n is the quantity for the song that the first song singly includes, and m is
The quantity for the song that second song singly includes.
Step 103, the behavior similarity single according to the first song list and the second song, determines of the first song list and the second song list
With degree value, and by the single song list mark of the single mark of the single song of the first song, the second song, matching degree numerical value, corresponding storage arrives every two
In a single corresponding relationship with matching degree numerical value of song.
In an implementation, the song identity that every two song can be previously stored in server is corresponding with matching degree numerical value
Relationship can be corresponded to and be added in corresponding relationship whenever determining the two single matching degree numerical value of song.Specifically, clothes
After business device determines the first song list and the single behavior similarity of the second song, the first song list and the can be determined according to behavior similarity
The single matching degree numerical value of two songs in turn can be by the single song list mark of the single mark of the single song of the first song, the second song, matching degree
Value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song.
Optionally, the recommended information that server can also be single according to song, determines the content similarity of the two, correspondingly, place
Reason process can be such that the recommended information for obtaining the single recommended information of the first song and the second song list；According to the single introduction of the first song
The recommended information of information and the second song list determines the content similarity of the first song list and the second song list.Correspondingly, step 103
Treatment process can be such that according to the behavior similarity and content similarity that the first song is single and the second song is single, determine the first song list
Single matching degree numerical value with the second song.
Wherein, recommended information can be for introducing the text information for singing single feature.
In an implementation, each song singly can be often corresponding with recommended information (such as title, brief introduction etc.), and server can be with
Obtain the recommended information that the first song is single and the second song is single respectively, in turn, server can according to the single recommended information of the first song and
The single recommended information of second song calculates the content similarity that the first song is single and the second song is single, wherein specific to determine that method be rear
Continuous detailed description.It, can be single according to the first song after obtaining behavior similarity and the content similarity of the first song list and the second song list
Single behavior similarity and content similarity with the second song determine the matching degree numerical value of the first song list and the second song list.
Optionally, server can be by the weighted sum of calculating behavior similarity and content similarity, to determine matching degree
Numerical value, correspondingly, the treatment process of step 103 can be such that behavior similarity according to the pre-stored data and content similarity point
Not corresponding weight and the first song is single and the second song is single behavior similarity and content similarity determine the first song list and the
The single matching degree numerical value of two songs.
In an implementation, behavior similarity and the corresponding weight of content similarity can be previously stored in server,
After determining every two song single content similarity and behavior similarity, the single matching degree numerical value of the two songs is calculated.Clothes
After business device determines behavior similarity and the content similarity of the first song list and the second song list, pre-stored behavior can be based on
Similarity and the corresponding weight of content similarity calculate the matching degree numerical value that the first song is single and the second song is single, for example, content
The weight of similarity is a, and the weight of behavior similarity is 1-a, and the content similarity that the first song is single and the second song is single is
Content, the behavior similarity that the first song is single and the second song is single are behavior, then the matching degree that the first song is single and the second song is single
Numerical value can be a*content+ (1-a) * behavior.In addition, after current detection cycle service device recommends song list to terminal, clothes
Business device can count the information such as the single clicking rate (or broadcasting rate) of the song recommended to all terminals, in turn, according to the click of statistics
The information such as rate, the weight of Suitable content similarity and the weight of behavior similarity, until determining that suitable Suitable content is similar
The weight of degree and the weight of behavior similarity, so that clicking rate reaches preset threshold.
Optionally, when recommended information includes title text information and/or brief introduction text information, list is sung in above-mentioned determination first
The treatment process for singing single content similarity with second can be such that single to the first song respectively recommended information and the second song list
Recommended information carries out word segmentation processing, obtains the set of words of the first song list and the set of words that the second song is single；It determines each default
Word sings the frequency of occurrence in single set of words and the frequency of occurrence in the single set of words of the second song first respectively, and
The single corresponding set of words of all songs according to the pre-stored data, determines each default corresponding reverse document-frequency of word；According to
Frequency of occurrence of each default word in the single set of words of the first song and it is each preset the corresponding reverse document-frequency of word,
Determine the first song singly corresponding text vector, according to frequency of occurrence of each default word in the single set of words of the second song and
Each default corresponding reverse document-frequency of word, determines the second song singly corresponding text vector；It is single corresponding to calculate the first song
The cosine similarity of text vector and the single corresponding text vector of the second song obtains the content of the first song list and the second song list
Similarity.
In an implementation, after available first song of server single title and/or profile information, it can be segmented
Processing obtains the set of words of the first song list and the set of words that the second song is single.Then, server can be by calculating TFIDF
(Term Frequency-Inverse Document Frequency, the reverse document-frequency of word frequency -), to calculate the first song list
Text vector and the single text vector of the second song.Specifically, word matrix can have been pre-defined in server, wherein word
Every a line of language matrix indicates that the single corresponding text vector of some song, text vector indicate that the dimension is corresponding per one-dimensional numerical value
Word is preset in the TFIDF of the song list, it is word matrix column number that the dimension of text vector, which is the number of default word,
The line number of word matrix is the single number of song.For example, the numerical value of the first dimension of the text vector of the first song list indicates the first dimension
Default word (word 1) TFIDF single in the first song, the numerical value of the first dimension of the single text vector of the second song indicates the first dimension
Default word (word 1) TFIDF single in the second song.Each numerical value of word matrix can be according to the word collection of each song list
It closes and determines, specifically, the first determination method for singing the list text vector single with the second song can be such that and sing list for first, obtain
After the set of words single to the first song, it can count and go out occurrence in the single set of words of the first song per one-dimensional default word
Number, and the summation of the frequency of occurrence of each default word can be calculated, in turn, the corresponding appearance of each default word can be calculated
The ratio of the summation of number and frequency of occurrence, at this point, defining the corresponding TF of each default word.Determine default word
TF after, the IDF of each default word can also be calculated, specifically, for each default word (i.e. for the every of word matrix
One column), server can count the song odd number mesh that frequency of occurrence is not zero, and in turn, can calculate singular mesh (the i.e. word square of total song
The line number of battle array) the song odd number purpose number ratio that is not zero with frequency of occurrence, logarithm then is asked to number ratio, it is default to obtain this
The IDF of word.It is single for the first song, after obtaining the corresponding TF and IDF of each default word, TF can be multiplied with IDF, be obtained
The single text vector of first song.It is single for the second song, after obtaining the set of words of the second song list, it can count and be preset per one-dimensional
Frequency of occurrence of the word in the single set of words of the second song, and the summation of the frequency of occurrence of each default word can be calculated,
In turn, the ratio of the summation of the corresponding frequency of occurrence of each default word and frequency of occurrence can be calculated, at this point, defining
Each default corresponding TF of word, it is then, the corresponding TF of each default word is corresponding with the above-mentioned each word determined
IDF is multiplied, and obtains the text vector of the second song list.
After text vector and the text vector that the second song is single of determining the first song list, the can be calculated according to formula (1)
The cosine similarity of the text vector of the single text vector of one song and the second song list, and obtained cosine similarity can be determined
For the single content similarity corresponding with the second song list of the first song, (in such cases, content similarity is referred to as similar herein
Degree).
Optionally, when recommended information is label information, the content similarity of list and the second song list is sung in above-mentioned determination first
Treatment process can be such that recommended information single according to the single recommended information of the first song and the second song respectively, determine the first song
Single corresponding label vector and the single corresponding label vector of the second song；It calculates the single corresponding label vector of the first song and the second song is single
The cosine similarity of corresponding label vector obtains the content similarity of the first song list and the second song list.
In an implementation, each song is single is corresponding with label information toward contact, wherein label information can be the single corresponding mark of song
Signature (for example, the label information of certain song list is referred to as prevalence, national language, folk rhyme, rock and roll etc.).It can also have been pre-defined in server
Label vector, wherein label vector indicates that the label information of the song list does not include the dimension pair per one-dimensional numerical value for 0 or 1,0
The default label (such as folk rhyme) answered, 1 indicates that the label information of the song list includes the corresponding default label of the dimension.Label vector
Dimension is the number of default label.For example, the numerical value of the first dimension of the label vector of the first song list indicates the single mark of the first song
Label information whether include the first dimension default label (such as folk rhyme), the numerical value of the first dimension of the single label vector of the second song indicates
The single label information of second song whether include the first dimension default label (such as folk rhyme).Server gets the first song as a result,
After the label information of single label information and the second song list, it can be determined that the single label of the label information and the second song of the first song list
Which default label is information contain, and does not include which default label, in turn, the single label vector of available first song and the
The single label vector of two songs.The first song is obtained singly after corresponding label vector and the single corresponding label vector of the second song, it can be by
The cosine similarity that the single corresponding label vector of the first song and the single corresponding label vector of the second song are calculated according to formula (1), obtains
The content similarity that first song is single and the second song is single (in such cases, content similarity is referred to as label similarity).
In addition, the recommended information in this programme can include title text information and/or brief introduction text information, and mark simultaneously
Information is signed, in such cases, it is similar with the text of the second song that server can calculate in the manner described above the first song respectively
Degree and label similarity in turn can be right respectively with behavior similarity according to the pre-stored data, text similarity and label similarity
Single and described second song of weight and first song answered single behavior similarity, text similarity and label similarity, really
The matching degree numerical value that fixed first song is single and the second song is single.
Step 104, it when the single song list acquisition request of the correspondence target song for receiving terminal transmission, is sung according to every two single
With the corresponding relationship of matching degree numerical value, the determining maximum preset number song of the matching degree numerical value single with target song is single, to terminal
Send the single song list mark of preset number song.
In an implementation, it after user selects a certain song list, can be played by playback of songs class application program in the song list
Song, when terminal detects the terminal play instruction single to target song, or when terminal detects that terminal corresponds to target song list
Similar song list acquisition instruction when, the single song list acquisition request of corresponding target song can be sent to server, server receive
When the single song list acquisition request of the correspondence target song that terminal is sent, can pre-stored every two sing single song identity with
In the corresponding relationship of matching degree numerical value, the corresponding relationship item single comprising target song is chosen, and in each corresponding relationship item of selection
Matching degree numerical value be ranked up, the matching degree numerical value in each corresponding relationship item can be carried out according to descending sequence
Sequence, in such cases, the forward preset number song of the available sequence of server singly, can also be according to ascending suitable
Sequence is ranked up the matching degree numerical value in each corresponding relationship item, in such cases, available sequence rearward pre- of server
If number song is single.After determining preset number song list, the single song list mark of preset number song can be sent to terminal, eventually
End can receive the single song list mark of preset number song, and can show to it, and user can be in each song list of display
In mark, the song list listened wherein oneself is liked in selection, wherein system framework figure is as shown in Figure 2.
Optionally, server can also determine the single corresponding song Dan Jihe of target song, in turn, in the single set of song selection with
The maximum preset number song of the single matching degree numerical value of target song is single, correspondingly, the treatment process of step 104 can be such that root
According to the single corresponding label information of pre-stored each song, the song that the label information of label information and target song list matches is determined
Single set；The matching single with target song is chosen in the single set of song according to the single corresponding relationship with matching degree numerical value of every two song
The maximum preset number song of degree value is single.
In an implementation, when the single song list acquisition request of the correspondence target song for receiving terminal transmission, server can be
In all song lists, the label information for choosing label information and target song list has the song Dan Jihe of same label in turn can be every
In the corresponding relationship of two songs single song identity and matching degree numerical value, single single with target song of song in the single set of song is determined
With degree value.Server can sing single matching degree numerical value single with target song according in the single set of song, therefrom selection and target
It is single to sing the maximum preset number song of single matching degree numerical value.In addition, determining that server can also be all when singing single set
It sings in list, chooses label information and the single label information of target song except (such as the differentiations such as prevalence, national language effect of default public label
Small label) except have the song Dan Jihe of same label.For example, the label information of target song list includes label 1, label 2 and mark
Label 3 sing the song in single set as long as then song Dan Jun of the label information comprising one of label is the song list in the single set of song
Single label information is including at least one in label 1, label 2, label 3.
In addition, if it is determined that the single set of song in song odd number amount be less than preset number, then server can sung again
In song list outside single set, the song list of the maximum volume residual of matching degree numerical value is chosen.For example, preset number is 10, song is single
There are 7 songs lists in set, then it in such cases, can also be single in song outside 7 songs list in the single set of the available song of server
In song list outside set, select 3 songs single, wherein the single matching degree numerical value single with target song of this 3 songs is outer in the single set of song
Song list in it is maximum.
In the embodiment of the present invention, server can according to user behavior (such as broadcasting in the past period, downloading and
Collection record) the behavior similarity of song two-by-two is precalculated, in turn, server can be similar according to the behavior of song two-by-two
Degree calculates the behavior similarity that the first song is single and the second song is single；According to the behavior similarity that the first song is single and the second song is single, determine
The matching degree numerical value that first song is single and the second song is single, and by the single song list mark of the single mark of the single song of the first song, the second song, matching
Degree value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song.Whenever the correspondence for receiving terminal transmission
When the song list acquisition request of target song list, according to the single corresponding relationship with matching degree numerical value of every two song, determining and target song is single
Matching degree numerical value maximum preset number song it is single, in turn, the single song list of preset number song can be sent to terminal and is identified.
In this way, user can sing in single mark in the preset number of server push, the song list for oneself liking listening is selected, without in institute
Have in song list and select, it is thus possible to improve the single efficiency of selection song.
Based on the same technical idea, the embodiment of the invention also provides a kind of devices for sending song and singly identifying, such as Fig. 3 institute
Show, which includes:
First obtains module 310, in the corresponding behavior similarity list of pre-stored every two song, acquisition
The behavior similarity for every song that every song that first song singly includes singly includes with the second song；
Computing module 320, for according to it is described first song singly include every song with it is described second sing singly include it is every
The behavior similarity of song calculates the single behavior similarity of single and described second song of first song；
Memory module 330 determines described for the behavior similarity single according to single and described second song of first song
The single matching degree numerical value of single and described second song of one song, and the song that the single single mark of song of first song, second song is single
Single mark, the matching degree numerical value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song；
Sending module 340, for when the single song list acquisition request of the correspondence target song for receiving terminal transmission, according to institute
State the single corresponding relationship with matching degree numerical value of every two song, the determining matching degree numerical value maximum present count single with target song
Mesh song is single, and Xiang Suoshu terminal sends the single song list mark of the preset number song.
Optionally, as shown in figure 4, described device further include:
Second obtains module 350, for obtaining the reference of first song single recommended information and the second song list
Breath；
Determining module 360, for the recommended information single according to the single recommended information of first song and second song, really
The single content similarity of fixed single and described second song of first song；
The memory module 330, is used for:
According to single and described second song of first song single behavior similarity and content similarity, first song is determined
The single matching degree numerical value of single and described second song.
Optionally, the recommended information includes title text information and/or brief introduction text information；
The determining module 360, is used for:
The recommended information of the recommended information single to first song and the second song list carries out word segmentation processing respectively, obtains
The set of words of first song single set of words and the second song list；
Determine each frequency of occurrence for presetting word respectively in the single set of words of first song and described second
The frequency of occurrence in single set of words, and the single corresponding set of words of all songs according to the pre-stored data are sung, is determined described every
The corresponding reverse document-frequency of a default word；
According to frequency of occurrence of each default word in the single set of words of first song and described each pre-
If the corresponding reverse document-frequency of word, the single corresponding text vector of the first song is determined, according to each default word
Frequency of occurrence and each default corresponding reverse document-frequency of word in the single set of words of second song, determine
The single corresponding text vector of second song；
It is similar with the cosine of the single corresponding text vector of the second song to calculate the single corresponding text vector of the first song
Degree obtains the single content similarity of single and described second song of first song.
Optionally, the recommended information includes label information；
The determining module 360, is used for:
The recommended information single according to the single recommended information of first song and second song respectively, determines first song
Single corresponding label vector and the single corresponding label vector of the second song；
It is similar with the cosine of the single corresponding label vector of the second song to calculate the single corresponding label vector of the first song
Degree obtains the single content similarity of single and described second song of first song.
Optionally, the memory module 330, is used for:
Behavior similarity according to the pre-stored data and the corresponding weight of content similarity and first song it is single and
Second song single behavior similarity and content similarity determine the single matching degree of single and described second song of first song
Value.
Optionally, the sending module 340, is used for:
The single corresponding label information of each song according to the pre-stored data, determines the label of label information and target song list
The song Dan Jihe that information matches；
According to the single corresponding relationship with matching degree numerical value of every two song, in the song singly set, selection with it is described
The maximum preset number song of the single matching degree numerical value of target song is single.
In the embodiment of the present invention, server can according to user behavior (such as broadcasting in the past period, downloading and
Collection record) the behavior similarity of song two-by-two is precalculated, in turn, server can be similar according to the behavior of song two-by-two
Degree calculates the behavior similarity that the first song is single and the second song is single；According to the behavior similarity that the first song is single and the second song is single, determine
The matching degree numerical value that first song is single and the second song is single, and by the single song list mark of the single mark of the single song of the first song, the second song, matching
Degree value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song.Whenever the correspondence for receiving terminal transmission
When the song list acquisition request of target song list, according to the single corresponding relationship with matching degree numerical value of every two song, determining and target song is single
Matching degree numerical value maximum preset number song it is single, in turn, the single song list of preset number song can be sent to terminal and is identified.
In this way, user can sing in single mark in the preset number of server push, the song list for oneself liking listening is selected, without in institute
Have in song list and select, it is thus possible to improve the single efficiency of selection song.
It should be understood that it is provided by the above embodiment send the device that singly identifies of song send sing single mark when, only with
The division progress of above-mentioned each functional module can according to need and for example, in practical application by above-mentioned function distribution by not
Same functional module is completed, i.e., the internal structure of server is divided into different functional modules, described above complete to complete
Portion or partial function.In addition, the method reality that device and transmission song that transmission song provided by the above embodiment singly identifies singly identify
It applies example and belongs to same design, specific implementation process is detailed in embodiment of the method, and which is not described herein again.
Fig. 5 is the structural schematic diagram of server provided in an embodiment of the present invention.The server 1900 can be because of configuration or performance
It is different and generate bigger difference, it may include one or more central processing units (central processing
Units, CPU) 1922 (for example, one or more processors) and memory 1932, one or more storage applications
The storage medium 1930 (such as one or more mass memory units) of program 1942 or data 1944.Wherein, memory
1932 and storage medium 1930 can be of short duration storage or persistent storage.The program for being stored in storage medium 1930 may include one
A or more than one module (diagram does not mark), each module may include to the series of instructions operation in server.More into
One step, central processing unit 1922 can be set to communicate with storage medium 1930, execute storage medium on server 1900
Series of instructions operation in 1930.
Server 1900 can also include one or more power supplys 1926, one or more wired or wireless nets
Network interface 1950, one or more input/output interfaces 1958, one or more keyboards 1956, and/or, one or
More than one operating system 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM
Etc..
Server 1900 may include have memory and one perhaps more than one program one of them or one
A procedure above is stored in memory, and is configured to execute one or one by one or more than one processor
A procedure above includes the instruction for performing the following operation:
In the corresponding behavior similarity list of pre-stored every two song, every first song that the first song singly includes is obtained
The behavior similarity of the bent every song for singly including with the second song；
The every song for singly including according to first song is similar to the behavior of every song that second song singly includes
Degree calculates the single behavior similarity of single and described second song of first song；
According to the single behavior similarity of the first song list and second song, the first song list and described second are determined
Sing single matching degree numerical value, and by the single song list mark of the single single mark of song of first song, second song, the matching degree
Numerical value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song；
When the single song list acquisition request of the correspondence target song for receiving terminal transmission, according to every two song it is single with
Corresponding relationship with degree value, the determining maximum preset number song of the matching degree numerical value single with target song is single, Xiang Suoshu
Terminal sends the single song list mark of the preset number song.
Optionally, the method also includes:
Obtain the recommended information of first song single recommended information and the second song list；
According to the single recommended information of the single recommended information of first song and second song, determine first song it is single and
The single content similarity of second song；
The behavior similarity single according to single and described second song of first song, determines that first song is single and described
The single matching degree numerical value of second song, comprising:
According to single and described second song of first song single behavior similarity and content similarity, first song is determined
The single matching degree numerical value of single and described second song.
Optionally, the recommended information includes title text information and/or brief introduction text information；
The recommended information of the recommended information single according to first song and the second song list, determines first song
The single content similarity of single and described second song, comprising:
The recommended information of the recommended information single to first song and the second song list carries out word segmentation processing respectively, obtains
The set of words of first song single set of words and the second song list；
Determine each frequency of occurrence for presetting word respectively in the single set of words of first song and described second
The frequency of occurrence in single set of words, and the single corresponding set of words of all songs according to the pre-stored data are sung, is determined described every
The corresponding reverse document-frequency of a default word；
According to frequency of occurrence of each default word in the single set of words of first song and described each pre-
If the corresponding reverse document-frequency of word, the single corresponding text vector of the first song is determined, according to each default word
Frequency of occurrence and each default corresponding reverse document-frequency of word in the single set of words of second song, determine
The single corresponding text vector of second song；
It is similar with the cosine of the single corresponding text vector of the second song to calculate the single corresponding text vector of the first song
Degree obtains the single content similarity of single and described second song of first song.
Optionally, the recommended information includes label information；
The recommended information of the recommended information single according to first song and the second song list, determines first song
The single content similarity of single and described second song, comprising:
The recommended information single according to the single recommended information of first song and second song respectively, determines first song
Single corresponding label vector and the single corresponding label vector of the second song；
It is similar with the cosine of the single corresponding label vector of the second song to calculate the single corresponding label vector of the first song
Degree obtains the single content similarity of single and described second song of first song.
Optionally, the behavior similarity and content similarity single according to single and described second song of first song, really
The single matching degree numerical value of fixed single and described second song of first song, comprising:
Behavior similarity according to the pre-stored data and the corresponding weight of content similarity and first song it is single and
Second song single behavior similarity and content similarity determine the single matching degree of single and described second song of first song
Value.
Optionally, described according to the single corresponding relationship with matching degree numerical value of every two song, it is determining to be sung with the target
The maximum preset number song of single matching degree numerical value is single, comprising:
The single corresponding label information of each song according to the pre-stored data, determines the label of label information and target song list
The song Dan Jihe that information matches；
According to the single corresponding relationship with matching degree numerical value of every two song, in the song singly set, selection with it is described
The maximum preset number song of the single matching degree numerical value of target song is single.
In the embodiment of the present invention, server can according to user behavior (such as broadcasting in the past period, downloading and
Collection record) the behavior similarity of song two-by-two is precalculated, in turn, server can be similar according to the behavior of song two-by-two
Degree calculates the behavior similarity that the first song is single and the second song is single；According to the behavior similarity that the first song is single and the second song is single, determine
The matching degree numerical value that first song is single and the second song is single, and by the single song list mark of the single mark of the single song of the first song, the second song, matching
Degree value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song.Whenever the correspondence for receiving terminal transmission
When the song list acquisition request of target song list, according to the single corresponding relationship with matching degree numerical value of every two song, determining and target song is single
Matching degree numerical value maximum preset number song it is single, in turn, the single song list of preset number song can be sent to terminal and is identified.
In this way, user can sing in single mark in the preset number of server push, the song list for oneself liking listening is selected, without in institute
Have in song list and select, it is thus possible to improve the single efficiency of selection song.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of method for sending song and singly identifying, which is characterized in that the described method includes:
In the corresponding behavior similarity list of pre-stored every two song, obtain every song that the first song singly includes and
The behavior similarity for every song that second song singly includes, wherein the behavior similarity is one that first song singly includes
Similarity between the song features vector for the song that the song features vector of song and second song singly include, institute
The song features vector for stating the song that the first song singly includes is singly to include respectively to first song based on multiple accounts
What the behavioral data of one song determined, the song features vector for the song that second song singly includes is based on described more
The behavioral data for the song that a account singly includes to second song respectively determines；
The behavior similarity for every song that the every song and second song for singly including according to first song singly include, meter
Calculate the single behavior similarity of single and described second song of first song；
According to the single behavior similarity of single and described second song of first song, determine that single and described second song of first song is single
Matching degree numerical value, and by the single song list mark of the single single mark of song of first song, second song, the matching degree
Value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song；
When the single song list acquisition request of the correspondence target song for receiving terminal transmission, list and matching degree are sung according to the every two
The corresponding relationship of numerical value, the determining maximum preset number song of the matching degree numerical value single with target song is single, Xiang Suoshu terminal
Send the single song list mark of the preset number song.
2. the method according to claim 1, wherein the method also includes:
Obtain the recommended information of first song single recommended information and the second song list；
According to the single recommended information of the single recommended information of first song and second song, determine that first song is single and described
The single content similarity of second song；
The behavior similarity single according to the first song list and second song, determines the first song list and described second
Sing single matching degree numerical value, comprising:
According to single and described second song of first song single behavior similarity and content similarity, determine first song it is single and
The single matching degree numerical value of second song.
3. according to the method described in claim 2, it is characterized in that, the recommended information includes title text information and/or letter
Jie's text information；
The recommended information single according to first song and the single recommended information of second song, determine first song it is single and
The single content similarity of second song, comprising:
The recommended information of the recommended information single to first song and the second song list carries out word segmentation processing respectively, obtains described
The set of words of the single set of words of first song and the second song list；
Determine the frequency of occurrence each preset word respectively in the single set of words of first song and in the second song list
Set of words in frequency of occurrence, and the single corresponding set of words of all songs according to the pre-stored data determines described each pre-
If the corresponding reverse document-frequency of word；
Frequency of occurrence and each default word in single set of words are sung described first according to each default word
The corresponding reverse document-frequency of language determines the single corresponding text vector of the first song, according to each default word in institute
State frequency of occurrence in the set of words of the second song list and each default corresponding reverse document-frequency of word, determine described in
The single corresponding text vector of second song；
The cosine similarity for calculating the single corresponding text vector of first song and the single corresponding text vector of the second song, obtains
The content similarity single to single and described second song of first song.
4. according to the method described in claim 2, it is characterized in that, the recommended information includes label information；
The recommended information single according to first song and the single recommended information of second song, determine first song it is single and
The single content similarity of second song, comprising:
The recommended information single according to the single recommended information of first song and second song respectively, determines the first song single pair
The label vector and the single corresponding label vector of the second song answered；
The cosine similarity for calculating the single corresponding label vector of first song and the single corresponding label vector of the second song, obtains
The content similarity single to single and described second song of first song.
5. according to the method described in claim 2, it is characterized in that, described sing list with described second according to first song is single
Behavior similarity and content similarity determine the single matching degree numerical value of single and described second song of first song, comprising:
Behavior similarity according to the pre-stored data and the corresponding weight of content similarity and first song are single and described
Second song single behavior similarity and content similarity determine the single matching degree numerical value of single and described second song of first song.
6. the method according to claim 1, wherein described according to every two song list and matching degree numerical value
Corresponding relationship, the determining maximum preset number song of the matching degree numerical value single with target song are single, comprising:
The single corresponding label information of each song according to the pre-stored data, determines the label information of label information and target song list
The song Dan Jihe to match；
It is chosen and the target in the song singly set according to the single corresponding relationship with matching degree numerical value of every two song
It is single to sing the maximum preset number song of single matching degree numerical value.
7. a kind of send the device that singly identifies of song, which is characterized in that described device includes:
First obtains module, for obtaining first and singing in the corresponding behavior similarity list of pre-stored every two song
The behavior similarity for every song that the every song for singly including singly includes with the second song, wherein the behavior similarity is institute
The song features for the song that the song features vector and second song for stating the song that the first song singly includes singly include
The song features vector of similarity between vector, the song that first song singly includes is right respectively based on multiple accounts
The behavioral data for the song that first song singly includes determines that the song for the song that second song singly includes is special
Sign vector is that the behavioral data for the song for singly including respectively is determined to second song based on the multiple account；
Computing module, every song that every song and second song for singly including according to first song singly include
Behavior similarity calculates the single behavior similarity of single and described second song of first song；
Memory module determines that first song is single for the behavior similarity single according to single and described second song of first song
Single matching degree numerical value with second song, and by the single song list mark of the single single mark of song of first song, second song,
The matching degree numerical value, corresponding storage is into the single corresponding relationship with matching degree numerical value of every two song；
Sending module, for when the single song list acquisition request of the correspondence target song for receiving terminal transmission, according to described every two
A single corresponding relationship with matching degree numerical value of song, the determining matching degree numerical value maximum preset number single with target song are sung
Single, Xiang Suoshu terminal sends the single song list mark of the preset number song.
8. device according to claim 7, which is characterized in that described device further include:
Second obtains module, for obtaining the recommended information of first song single recommended information and the second song list；
Determining module, described in determining according to the recommended information of the first song list and the recommended information of the second song list
The single content similarity of single and described second song of first song；
The memory module, is used for:
According to single and described second song of first song single behavior similarity and content similarity, determine first song it is single and
The single matching degree numerical value of second song.
9. device according to claim 8, which is characterized in that the recommended information includes title text information and/or letter
Jie's text information；
The determining module, is used for:
The recommended information of the recommended information single to first song and the second song list carries out word segmentation processing respectively, obtains described
The set of words of the single set of words of first song and the second song list；
Determine the frequency of occurrence each preset word respectively in the single set of words of first song and in the second song list
Set of words in frequency of occurrence, and the single corresponding set of words of all songs according to the pre-stored data determines described each pre-
If the corresponding reverse document-frequency of word；
Frequency of occurrence and each default word in single set of words are sung described first according to each default word
The corresponding reverse document-frequency of language determines the single corresponding text vector of the first song, according to each default word in institute
State frequency of occurrence in the set of words of the second song list and each default corresponding reverse document-frequency of word, determine described in
The single corresponding text vector of second song；
The cosine similarity for calculating the single corresponding text vector of first song and the single corresponding text vector of the second song, obtains
The content similarity single to single and described second song of first song.
10. device according to claim 8, which is characterized in that the recommended information includes label information；
The determining module, is used for:
The recommended information single according to the single recommended information of first song and second song respectively, determines the first song single pair
The label vector and the single corresponding label vector of the second song answered；
The cosine similarity for calculating the single corresponding label vector of first song and the single corresponding label vector of the second song, obtains
The content similarity single to single and described second song of first song.
11. device according to claim 8, which is characterized in that the memory module is used for:
Behavior similarity according to the pre-stored data and the corresponding weight of content similarity and first song are single and described
Second song single behavior similarity and content similarity determine the single matching degree numerical value of single and described second song of first song.
12. device according to claim 7, which is characterized in that the sending module is used for:
The single corresponding label information of each song according to the pre-stored data, determines the label information of label information and target song list
The song Dan Jihe to match；
It is chosen and the target in the song singly set according to the single corresponding relationship with matching degree numerical value of every two song
It is single to sing the maximum preset number song of single matching degree numerical value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611225021.9A CN106844504B (en) | 2016-12-27 | 2016-12-27 | A kind of method and apparatus for sending song and singly identifying |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611225021.9A CN106844504B (en) | 2016-12-27 | 2016-12-27 | A kind of method and apparatus for sending song and singly identifying |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106844504A CN106844504A (en) | 2017-06-13 |
| CN106844504B true CN106844504B (en) | 2019-10-11 |
Family
ID=59135866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611225021.9A Active CN106844504B (en) | 2016-12-27 | 2016-12-27 | A kind of method and apparatus for sending song and singly identifying |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106844504B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107368552A (en) * | 2017-06-30 | 2017-11-21 | 广东欧珀移动通信有限公司 | A kind of friend recommendation method, apparatus, storage medium, server and terminal |
| CN109982155B (en) * | 2019-03-25 | 2021-10-12 | 北京奇艺世纪科技有限公司 | Playlist recommendation method and system |
| CN112487236A (en) * | 2020-12-01 | 2021-03-12 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, device, equipment and storage medium for determining associated song list |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970802A (en) * | 2013-02-05 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Song recommending method and device |
| CN104731954A (en) * | 2015-04-01 | 2015-06-24 | 天翼爱音乐文化科技有限公司 | Music recommendation method and system based on group perspective |
| CN105451068A (en) * | 2015-11-24 | 2016-03-30 | 华数传媒网络有限公司 | Electronic program list generation method and device |
| CN105718575A (en) * | 2016-01-22 | 2016-06-29 | 华南理工大学 | Crawler-based music labelling method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012019637A1 (en) * | 2010-08-09 | 2012-02-16 | Jadhav, Shubhangi Mahadeo | Visual music playlist creation and visual music track exploration |
-
2016
- 2016-12-27 CN CN201611225021.9A patent/CN106844504B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970802A (en) * | 2013-02-05 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Song recommending method and device |
| CN104731954A (en) * | 2015-04-01 | 2015-06-24 | 天翼爱音乐文化科技有限公司 | Music recommendation method and system based on group perspective |
| CN105451068A (en) * | 2015-11-24 | 2016-03-30 | 华数传媒网络有限公司 | Electronic program list generation method and device |
| CN105718575A (en) * | 2016-01-22 | 2016-06-29 | 华南理工大学 | Crawler-based music labelling method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106844504A (en) | 2017-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11252245B2 (en) | Information pushing method and device | |
| CN103020845B (en) | A kind of method for pushing and system of mobile application | |
| US10747771B2 (en) | Method and apparatus for determining hot event | |
| WO2017181612A1 (en) | Personalized video recommendation method and device | |
| CN110287421A (en) | Information content recommendation method and device and electronic equipment | |
| WO2020088058A1 (en) | Information generating method and device | |
| CN106708817B (en) | Information searching method and device | |
| WO2018121700A1 (en) | Method and device for recommending application information based on installed application, terminal device, and storage medium | |
| CN107426328B (en) | Information pushing method and device | |
| JP2019519019A (en) | Method, apparatus and device for identifying text type | |
| CN106484777A (en) | A kind of multimedia data processing method and device | |
| CN109242537A (en) | Advertisement placement method, device, computer equipment and storage medium | |
| CN106951527B (en) | Song recommendation method and device | |
| CN106844504B (en) | A kind of method and apparatus for sending song and singly identifying | |
| CN108401005B (en) | Expression recommendation method and device | |
| CN111242709A (en) | Message pushing method and device, equipment and storage medium thereof | |
| CN110503506A (en) | Item recommendation method, device and medium based on score data | |
| JP2013164704A (en) | Information processing apparatus, information processing method, and program | |
| CN110197404A (en) | The personalized long-tail Method of Commodity Recommendation and system of popularity deviation can be reduced | |
| CN107562432B (en) | Information processing method and related product | |
| CN111787042B (en) | Method and device for pushing information | |
| CN109146551A (en) | A kind of advertisement recommended method, server and computer-readable medium | |
| CN106257449B (en) | A kind of information determines method and apparatus | |
| CN111667018B (en) | Object clustering method and device, computer readable medium and electronic equipment | |
| CN104077320B (en) | method and device for generating information to be issued |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 510660 Guangzhou City, Guangzhou, Guangdong, Whampoa Avenue, No. 315, self - made 1-17 Applicant after: Guangzhou KuGou Networks Co., Ltd. Address before: 510000 B1, building, No. 16, rhyme Road, Guangzhou, Guangdong, China 13F Applicant before: Guangzhou KuGou Networks Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |