CN109299317A - Method, apparatus, storage medium and the terminal device that musical works is recommended - Google Patents
Method, apparatus, storage medium and the terminal device that musical works is recommended Download PDFInfo
- Publication number
- CN109299317A CN109299317A CN201811340909.6A CN201811340909A CN109299317A CN 109299317 A CN109299317 A CN 109299317A CN 201811340909 A CN201811340909 A CN 201811340909A CN 109299317 A CN109299317 A CN 109299317A
- Authority
- CN
- China
- Prior art keywords
- music
- user
- target
- target music
- behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a kind of method, apparatus, storage medium and terminal device that musical works is recommended, wherein the described method includes: obtaining the relevant user behavior data of target music；According to the user behavior data, the similarity degree of the target music and other music is determined；According to the data volume of the user behavior data and affiliated data type, target music confidence level similar with other music is determined；According to the similarity degree and confidence level of the target music and other music, the similar music of the target music is determined；And recommend the similar music to the relevant user of the target music.Using the present invention, the recommendation quality of similar music can be improved.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of method, apparatus of musical works recommendation, storage medium
And terminal device.
Background technique
With the development of mobile internet, mobile subscriber can pass through music APP in mobile device (Application, meter
Calculation machine application program) carry out Music Appreciation or interaction.Mobile subscriber uses the technical ability of music APP, usually are as follows: search for and push away
It recommends.Music expected from user can be quickly and accurately found by search, the resource and retrieval frame of server offer are provided
Structure.But music recommends general relative complex, no specific standard, is a relatively open demand.Wherein, shifting is recommended
The recommendation quality for employing the music at family can influence user and the keys such as song duration, the interaction duration being deposited on music APP is listened to refer to
Mark.
For the personalized recommendation of music, Clustering Model is generallyd use to carry out music recommendation.Specifically, a large amount of sounds are extracted
The characteristic informations such as happy singer, period, style, songwriter, composer or audio volume control.Then believed using the feature extracted
Breath is trained Clustering Model.In the analysis process, the similar music of feature is gathered using trained Clustering Model
Class, to obtain the similar music of feature.The similar music of feature is finally recommended into user.
But main problem present in above scheme is: being clustered using the model of machine learning to music, mistake
In dependence Clustering Model.Moreover, the accuracy of machine recognition depends on the maturity of machine training.The cluster low for maturity
Model, recommendation effect are relatively general.
Summary of the invention
The embodiment of the present invention provides a kind of method, apparatus, storage medium and terminal device that musical works is recommended, to solve
Or alleviate above one or more technical problems in the prior art.
In a first aspect, the embodiment of the invention provides a kind of methods that musical works is recommended, comprising:
Obtain the relevant user behavior data of target music；
According to the user behavior data, the similarity degree of the target music and other music is determined；
According to the data volume of the user behavior data and affiliated data type, the target music and other are determined
The similar confidence level of music；
According to the similarity degree and confidence level of the target music and other music, the similar sound of the target music is determined
It is happy；And
To the target music, relevant user recommends the similar music.
In one embodiment, the user behavior data includes the song list for recommending the target music, and according to
The user behavior data of the target music determines the similarity degree of the target music and other music, comprising:
According to the target music and other music appear in the same single frequency of occurrence of song and the target music with
Other music appear in the single spread length of same song, determine similar journey of the target music to other music on song list
Degree.
In one embodiment, the user behavior data includes user search music behavior, and according to the mesh
The happy user behavior data of mark with phonetic symbols, determines the similarity degree of the target music and other music, comprising:
From user search music behavior, user's inspection that each user retrieves the target music in the set time period is chosen
Suo Yinle behavior；
According to the user search music behavior chosen, counts each user and retrieve the target music during the period of time
With other music retrieval time interval and the target music and other music during the period of time by user search
Retrieval number of users；And
According to the retrieval time interval and the retrieval number of users, determine the target music and other music with
Retrieve the similarity degree in music behavior in family.
In one embodiment, the user behavior data includes user's collection music behavior, and according to the mesh
The happy user behavior data of mark with phonetic symbols, determines the similarity degree of the target music and other music, comprising:
It is collected in music behavior from user, chooses user's receipts that each user collects the target music in the set time period
Hide music behavior；
Music behavior is collected according to the user chosen, each user is counted and collects the target music during the period of time
With the collection time interval of other music and the target music and other music during the period of time by same user
The collection number of users of collection；And
According to the collection time interval and the collection number of users, determine the target music and other music with
Collect the similarity degree in music behavior in family.
In one embodiment, further includes:
Judge whether target music confidence level similar with other music meets confidence level correction conditions；
If meeting the confidence level correction conditions, obtains the expert comprising the target music and recommend song single；
Recommend song single according to the expert, carries out music recommendation；And
During the target music is recommended, target music confidence level similar with other music is corrected.
In one embodiment, during the target music is recommended, the target music and other sounds are corrected
Happy similar confidence level, comprising:
During the target music is recommended, the relevant user behavior data of the target music is obtained again；With
And
According to the data volume of the user behavior data got again and affiliated data type, the target sound is determined
Happy confidence level similar with other music.
Second aspect, the embodiment of the present invention also provide a kind of device that similar music is recommended, comprising:
Behavioral data obtains module, for obtaining the relevant user behavior data of target music；
Similarity degree determining module, for determining the target music and other music according to the user behavior data
Similarity degree；
Confidence determination module, for the data volume and affiliated data type according to the user behavior data, really
Determine target music confidence level similar with other music；
Similar music determining module, for the similarity degree and confidence level according to the target music and other music, really
The similar music of the fixed target music；And
Similar music recommending module, for recommending the similar music to the relevant user of the target music.
In one embodiment, the user behavior data includes recommending the song list of the target music and described
Similarity degree determining module includes:
Single similarity determining unit is sung, for appearing in the single appearance of same song according to the target music and other music
The frequency and the target music and other music appear in the single spread length of same song, determine the target music and its
He is singing the similarity degree on list at music.
In one embodiment, the user behavior data includes the behavior of user search music and the similar journey
Spending determining module includes:
Retrieval behavior selection unit, for choosing each user and examining in the set time period from user search music behavior
The user search music behavior of Suo Suoshu target music；
Data statistics unit is retrieved, for counting each user when described according to the user search music behavior chosen
Between in section the retrieval target music and other music retrieval time interval and the target music and other music exist
By the retrieval number of users of user search in the period；And
Similarity determining unit is retrieved, for determining institute according to the retrieval time interval and the retrieval number of users
State target music and similarity degree of other music in user search music behavior.
In one embodiment, the user behavior data includes that user collects music behavior and the similar journey
Spending determining module includes:
Collection behavior selection unit is chosen each user and is received in the set time period for collecting in music behavior from user
The user for hiding the target music collects music behavior；
Data statistics unit is collected, for collecting music behavior according to the user chosen, counts each user when described
Between in section the collection time interval and the target music of the collection target music and other music and other music exist
The collection number of users collected in the period by same user；And
Similarity determining unit is collected, for determining institute according to the collection time interval and the collection number of users
It states target music and other music and collects the similarity degree in music behavior in user.
In one embodiment, further includes:
Confidence level judgment module, for judging whether target music confidence level similar with other music meets confidence
Spend correction conditions；
Recommend song is single to obtain module, if obtaining includes the target music for meeting the confidence level correction conditions
Expert recommend song single；
The happy recommending module of single-tone is sung, for recommending song single according to the expert, carries out music recommendation；And
Confidence level correction module, for correcting the target music and other during the target music is recommended
The similar confidence level of music.
In one embodiment, the confidence level correction module includes:
Behavioral data acquiring unit, for obtaining the target music again during the target music is recommended
Relevant user behavior data；And
Confidence level determination unit, for the data volume and affiliated data according to the user behavior data got again
Type determines target music confidence level similar with other music.
The third aspect, the embodiment of the invention provides the device that a kind of musical works is recommended, the function of described device can be with
By hardware realization, corresponding software realization can also be executed by hardware.The hardware or software include it is one or more with
The corresponding module of above-mentioned function.
It include processor and memory, the memory in the structure that musical works is recommended in a possible design
The device recommended for musical works executes the program of above-mentioned musical works recommendation, the processor is configured to being used to execute institute
State the program stored in memory.The device that the musical works is recommended can also include communication interface, push away for musical works
The device and other equipment or communication recommended.
Fourth aspect, the embodiment of the present invention also provide a kind of computer readable storage medium, recommend for musical works
Computer software instructions used in device, including for executing program involved in the method that above-mentioned musical works is recommended.
Any one technical solution in above-mentioned technical proposal have the following advantages that or the utility model has the advantages that
The embodiment of the present invention is determined by the user behavior data of target music between target music and other music
Similarity degree, and data volume situation and affiliated data type according to user behavior data, to determine this similarity degree
Confidence level, last similarity degree and confidence according between target music and other music cease to determine the similar of target music
Music.In turn, similar music can be recommended to the relevant user of target music, realizes the recommendation of similar music, realizes that difficulty is low,
And duration and desire that user appreciates similar music can be improved.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing description
Schematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is further
Aspect, embodiment and feature, which will be, to be readily apparent that.
Detailed description of the invention
In the accompanying drawings, unless specified otherwise herein, otherwise indicate the same or similar through the identical appended drawing reference of multiple attached drawings
Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention
Disclosed some embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 is the flow diagram of the one embodiment for the method that musical works provided by the invention is recommended.
Fig. 2 is the flow diagram of one embodiment of the determination process of retrieval similarity degree provided by the invention.
Fig. 3 is the flow diagram of one embodiment of the determination process of collection similarity degree provided by the invention.
Fig. 4 is the flow diagram of one embodiment of confidence level makeover process provided by the invention.
Fig. 5 is the structural schematic diagram of the one embodiment for the device that musical works provided by the invention is recommended.
Fig. 6 is the structural schematic diagram of one embodiment of terminal device provided by the invention.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.
Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Referring to Fig. 1, the embodiment of the invention provides a kind of methods that musical works is recommended.The present embodiment can be applied
In audio player or audio website.For example, the audio players such as KuGoo, Netease's cloud music, dried shrimp.It can also apply in video
In player or video website, for example, recommending the MV (Music Video, music short-movie) of musical works.Video player can be with
Including youku.com, iqiyi.com, trill etc..The present embodiment includes step S100 to step S500, specific as follows:
S100 obtains the relevant user behavior data of target music.
In the present embodiment, music may include classical music, pop music, blues songs, rock music, jazz, pipe
String band's music, contemporary music etc..It can also classify by the generating mode of music, for example, percussion music, He Zou pleasure, philharmonic
Happy, qin pleasure etc..Music may include song, MV etc..MV can be the short-movie with song collocation.User behavior data may include
The behavioral data that user interacts with audio player.For example, personal user creates song list, administrator or the resource sound of personal name
The song that happy user recommends to the user of network is singly, personal user carries out the behavior of music retrieval in audio player, individual uses
The behavior etc. of music is actively collected in audio player in family.Acquired user behavior data all refers in this step S100
To target music.For example, multiple users have collected the behavioral data of target music.
S200 determines the similarity degree of target music Yu other music according to user behavior data.
In some embodiments, for singing single user behavior number for example, being directed under same data type or input dimension
According to the similarity degree of target music Yu other music can be searched out in largely song forms data.When a large amount of behavioral data
When showing relevant property between two songs, it can think from the statistical significance, this two first song is similar.For different numbers
According to the user behavior data of type, the similarity between two songs can be different.Similarity degree can be with numerical value, number
Value section is divided.
S300 determines target music and other sounds according to the data volume of user behavior data and affiliated data type
Happy similar confidence level.
Based on the user behavior data of different data volumes, the similarity for counting to obtain two songs is usually all different
Identical, similarity degree has different confidence levels.For example, singly being counted on based on 100 songs, music A is similar with music B to be set
Reliability is different with the music A confidence level similar with music B singly counted on based on 1000 songs.Wherein, data volume is got over
More, confidence level is higher.Data type or input dimension may include song list, the behavior of user search music, user's collection music row
For etc..Even if using same data volume, but the user behavior data with different data types, the target sound being calculated
Happy confidence level similar with other music is also different.Different data types can respectively correspond different confidence levels.
S400 determines the similar music of target music according to the similarity degree and confidence level of target music and other music.
It in some embodiments, can be by target music and its if user behavior data only includes a kind of data type
He is multiplied at the similarity degree of music with confidence level, obtains one of target music and other music phase for combining confidence level
Like degree.In turn, sequence from big to small is carried out to the similarity degree for combining confidence level, extracts sequence and exists in most preceding or sequence
Music corresponding to preceding M similarity degrees, the similar music as target music.M can be preset positive integer.
In some embodiments, if user behavior data includes multiple data types, be based respectively on target music with
Similarity degree and confidence level of other music in each data type, are weighted summation, and take mean value, obtain target music with
One of other music combines the similarity degree of confidence level.In turn, to combine confidence level similarity degree carry out from greatly to
Sequence music corresponding to most preceding or preceding M similarity degree, the similar music as target music are extracted in small sequence.
S500, to target music, relevant user recommends similar music.
In some embodiments, the relevant user of target music may include retrieving, collect or broadcasting in the set time period
Put the user of target music.It may include one or more users.
The embodiment of the present invention has incorporated user behavior data and has assessed the similarity degree between music, and is based on user
Both the data volume of behavioral data and affiliated data type assess confidence level similar between music, finally combine
Assessment numerical value obtains similar music, can substantially increase the recommendation quality of similar music.
In some embodiments, if user behavior data includes the song list for recommending target music, target can be calculated
The similarity degree of music and other music on song list, can be described as singing single similarity degree.Calculating process may include: according to target
Music appears in same song single frequency of occurrence and target music with other music and other music appear in same song list
Spread length determines the similarity degree of target music and other music on song list.
In the present embodiment, song be singly major mainstream music media be user output or user input form of music it
One.Music in the same song list has certain similitude in some or multiple dimensions, for example, with the polymerization of Blues style
Song list in music be Blues jazz.For another example, the music in the song list to listen to music scene polymerization, such as " be suitble to read
Music in the song list of the American-European ditty listened when book " is suitable for listening when reading.The single source of song is generally two classes: by resource music
Person or music editor create and are created by personal user.Wherein, the song list created by resource music person or music editor is more
With it is professional with it is propagated, but song covering with song odd number measure be bound to it is limited；Although and being lacked by the song list of personal user's creation
It is weary professional, but due to its substantial amounts, there is also reasonability in statistical significance.
In some embodiments, can be single for each song, add up target music and other music, such as target music A and
Music B appears in the single frequency of occurrence of same song.It is single for each song, calculate separately target music and other music, such as target
Music A and music B appears in the single spread length of each song.That is, spread length be it is each song list in music B to music A away from
From.Using the distance of the music B to target music A in each song list, progress mathematical statistics obtain the statistics of music B to music A away from
From.Data statistics may include taking mean value, median, variance etc..Finally, can be appeared in combining target music A and music B
The single frequency of occurrence of same song obtains music B both to the statistical distance of music A, and target music A and music B is calculated
Song list similarity degree.The frequency of occurrence of target music and other music is higher, statistical distance is smaller, in statistical significance, two
The song list similarity degree of person is higher.
It in some embodiments, can be according to target sound if user behavior data includes user search music behavior
Happy user search music behavior determines target music and similarity degree of other music in user search music behavior, i.e.,
Retrieve similarity degree.As shown in Fig. 2, the determination process of retrieval similarity degree provided in this embodiment, may include step S312
It is as follows to step S316:
S312 chooses the user of each user searched targets music in the set time period from user search music behavior
Retrieve music behavior.Wherein, set period of time may include in past 1 day, in two days, in one week etc..User search sound
Happy behavior may include the information such as user of retrieval time point, retrieval.
S314 counts each user searched targets sound in the set time period according to the user search music behavior chosen
It is happy with other music retrieval times interval and target music and the equal set period of time of other music in by the inspection of user search
Rope number of users.
S316, according to statistics obtain retrieval time interval and retrieval number of users, determine target music and other music
Similarity degree in user search music behavior.
In some embodiments, user can be retrieved when listening to music on audio player.For example, user can be with
The information such as musical works title, composer, player or the lyrics are inputted, music searching is carried out.It can also be inputted by voice, it can
It is retrieved with more convenient user.From the point of view of the retrieval behavior of user, user is carried out continuously the music of retrieval, generally has similar
The association of property.For example, music style, music use field shadow, user interest etc..
Illustratively, if the retrieval number of users for being detected target music A and music B simultaneously by user in one day is 5
It is a, including user Y1 to user Y5, and, if user Y1 to user Y5 detects the detection between target music A and music B
Between be spaced successively are as follows: 20 minutes, 30 minutes, 10 minutes, 25 minutes, 15 minutes.Target music A and music B can then be calculated
Between average detected time interval be 20 minutes, that is, 20 minutes, 30 minutes, 10 minutes, 25 minutes and 15 minutes summations
With the ratio between retrieval number of users 5.Interval and retrieval number of users, determine mesh when then, according to the average detected time
Mark with phonetic symbols pleasure and similarity degree of other music in user search music behavior.Average detected time interval is shorter, retrieves user
Quantity is more, then similarity degree is higher.
It in some embodiments, can be according to target sound if user behavior data includes that user collects music behavior
Happy user collects music behavior, determines that target music and other music collect the similarity degree in music behavior in user, i.e.,
Collect similarity degree.As shown in figure 3, the determination process of collection similarity degree provided in this embodiment, may include step S322
It is as follows to step S326:
S322 collects in music behavior from user, chooses the user that each user collects target music in the set time period
Collect music behavior.
S324 collects music behavior according to the user chosen, counts each user and collect target sound in the set time period
Happy collection time interval and target music with other music is received by same user in the set time period with other music
The collection number of users of hiding.
S326 determines that target music and other music are collected in user according to collection time interval and collection number of users
Similarity degree in music behavior.
In some embodiments, can pass through a little if user likes a certain first song or album, user in the process of listening to music
Collection control is hit, this head song or this album are stowed in collection, with the wish of expression " I likes ".Utilize a large amount of user
The data for collecting music behavior, can assist the present embodiment to judge the similarity degree between music.User within the same period,
For example, the music similarity liked in one day, in a week is larger.So the set period of time of the present embodiment may include
In one day, in a week etc..
Illustratively, if the collection number of users that user collects target music A and music B simultaneously in one day is 5,
Including user Y1 to user Y5, and, if the collection time between user Y1 to user Y5 collection target music A and music B
Interval is successively are as follows: 15 minutes, 30 minutes, 10 minutes, 25 minutes, 20 minutes.Can then calculate target music A and music B it
Between average collection time interval be 20 minutes, that is, 15 minutes, 30 minutes, 10 minutes, 25 minutes and 20 minutes summations with
Retrieve the ratio between number of users 5.Interval and collection number of users, determine target when then, according to the averagely collection time
The similarity degree of music and other music in user's collection music behavior.For any two music, when averagely collecting
Between be spaced it is shorter, collection number of users it is more, then similarity degree is higher.
In some embodiments, for example, audient face is lesser or the music newly issued, its relevant user behavior number is obtained
According to data volume may it is relatively small, cause the similar confidence level of music limited.Alternatively, got by reasons such as loss of data
User behavior data is limited, and it is limited to also result in the similar confidence level of music.Therefore, the present embodiment can be not high in confidence level
Situation incorporates expert and recommends, such as senior musician or music platform carry out tentative recommendation to comprising target sound music and songs list, this
Music in a little target sound music and songs lists has similitude in one or more dimensions.Also, user is obtained in recommendation process
Behavioral data, not correct confidence level.As shown in figure 4, confidence level makeover process provided in this embodiment, may include step
S610 is as follows to step S640:
S610, judges whether target music confidence level similar with other music meets confidence level correction conditions.
In some embodiments, if the numerical value of target music confidence level similar with other music is too low, before illustrating
It states that user behavior data amount that step S100 is got is less or there are other problems, meets confidence level correction conditions, it can be with
Confidence level is modified using subsequent step.If the numerical value of target music confidence level similar with other music is normal,
Say that the data volume for user's row data that abovementioned steps S100 is got is normal or more, also there is no have other influences confidence level
Problem is unsatisfactory for confidence level correction conditions, can not continue to execute subsequent step.
S620 obtains the expert comprising target music and recommends song single if meeting confidence level correction conditions.Wherein, expert
Recommend song is single can be by the song list of the creations such as senior musician, music platform, team.This song is single can be manually generated or sharp
It is generated with machine learning.
S630 recommends song single, carries out music recommendation according to expert.When being recommended, the whole network recommendation can be carried out, it can also
To recommend for specific user, for example, thering is detection, collection, the user for sharing target sound pleasure, this user to broadcast in audio
Put the follower or the person of being concerned or the relevant user of this user etc. in device.
S640, during target music is recommended, amendment target music confidence level similar with other music.
In some embodiments, the relevant user behavior data of target music can be obtained again, this is obtained in the process
Take process consistent with the effect of step S100, details are not described herein.Then, according to the number of the user behavior data got again
According to amount and affiliated data type, target music confidence level similar with other music is determined.This determination process and step
The effect of S300 is consistent, and details are not described herein.
The present embodiment can carry out tentative recommendation, continuous improvement is got for minority's music or the music newly issued
User behavior data data volume so that confidence level is also continuously improved.To guarantee minority's music or the music newly issued
The recommendation quality of similar music.
Referring to Fig. 5, the embodiment of the present invention also provides a kind of device that similar music is recommended, comprising:
Behavioral data obtains module 100, for obtaining the relevant user behavior data of target music；
Similarity degree determining module 200, for determining the target music and other sounds according to the user behavior data
Happy similarity degree；
Confidence determination module 300, for the data volume and affiliated data type according to the user behavior data,
Determine target music confidence level similar with other music；
Similar music determining module 400, for the similarity degree and confidence level according to the target music and other music,
Determine the similar music of the target music；And
Similar music recommending module 500, for recommending the similar music to the relevant user of the target music.
In one embodiment, the user behavior data includes recommending the song list of the target music and described
Similarity degree determining module includes:
Single similarity determining unit is sung, for appearing in the single appearance of same song according to the target music and other music
The frequency and the target music and other music appear in the single spread length of same song, determine the target music and its
He is singing the similarity degree on list at music.
In one embodiment, the user behavior data includes the behavior of user search music and the similar journey
Spending determining module includes:
Retrieval behavior selection unit, for choosing each user and examining in the set time period from user search music behavior
The user search music behavior of Suo Suoshu target music；
Data statistics unit is retrieved, for counting each user when described according to the user search music behavior chosen
Between in section the retrieval target music and other music retrieval time interval and the target music and other music exist
By the retrieval number of users of user search in the period；And
Similarity determining unit is retrieved, for determining institute according to the retrieval time interval and the retrieval number of users
State target music and similarity degree of other music in user search music behavior.
In one embodiment, the user behavior data includes that user collects music behavior and the similar journey
Spending determining module includes:
Collection behavior selection unit is chosen each user and is received in the set time period for collecting in music behavior from user
The user for hiding the target music collects music behavior；
Data statistics unit is collected, for collecting music behavior according to the user chosen, counts each user when described
Between in section the collection time interval and the target music of the collection target music and other music and other music exist
The collection number of users collected in the period by same user；And
Similarity determining unit is collected, for determining institute according to the collection time interval and the collection number of users
It states target music and other music and collects the similarity degree in music behavior in user.
In one embodiment, further includes:
Confidence level judgment module, for judging whether target music confidence level similar with other music meets confidence
Spend correction conditions；
Recommend song is single to obtain module, if obtaining includes the target music for meeting the confidence level correction conditions
Expert recommend song single；
The happy recommending module of single-tone is sung, for recommending song single according to the expert, carries out music recommendation；And
Confidence level correction module, for correcting the target music and other during the target music is recommended
The similar confidence level of music.
In one embodiment, the confidence level correction module includes:
Behavioral data acquiring unit, for obtaining the target music again during the target music is recommended
Relevant user behavior data；And
Confidence level determination unit, for the data volume and affiliated data according to the user behavior data got again
Type determines target music confidence level similar with other music.
The function of described device can also execute corresponding software realization by hardware realization by hardware.It is described
Hardware or software include one or more modules corresponding with above-mentioned function.
It include processor and memory, the memory in the structure that musical works is recommended in a possible design
The device recommended for musical works executes the program that musical works is recommended in above-mentioned first aspect, the processor is configured to
For executing the program stored in the memory.The device that the musical works is recommended can also include communication interface, be used for
The device and other equipment or communication that musical works is recommended.
The embodiment of the present invention also provides a kind of terminal device that musical works is recommended, as shown in fig. 6, the equipment includes: to deposit
Reservoir 21 and processor 22, being stored in memory 21 can be in the computer program on processor 22.Processor 22 executes calculating
The method that the musical works in above-described embodiment is recommended is realized when machine program.The quantity of memory 21 and processor 22 can be one
It is a or multiple.
The equipment further include:
Communication interface 23, for the communication between processor 22 and external equipment.
Memory 21 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-volatile
Memory), a for example, at least magnetic disk storage.
If memory 21, processor 22 and the independent realization of communication interface 23, memory 21, processor 22 and communication are connect
Mouth 23 can be connected with each other by bus and complete mutual communication.Bus can be industry standard architecture (ISA,
Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral Component) be total
Line or extended industry-standard architecture (EISA, Extended Industry Standard Component) bus etc..Always
Line can be divided into address bus, data/address bus, control bus etc..Only to be indicated with a thick line in Fig. 6, but simultaneously convenient for indicating
Only a bus or a type of bus are not indicated.
Optionally, in specific implementation, if memory 21, processor 22 and communication interface 23 are integrated in chip piece
On, then memory 21, processor 22 and communication interface 23 can complete mutual communication by internal interface.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment of the present invention or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden
It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise
Clear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, to execute function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicating, propagating or passing
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.
The computer-readable medium of the embodiment of the present invention can be computer-readable signal media or computer-readable deposit
Storage media either the two any combination.The more specific example at least (non-exclusive of computer readable storage medium
List) include the following: there is the electrical connection section (electronic device) of one or more wirings, portable computer diskette box (magnetic dress
Set), random access memory (RAM), read-only memory (ROM), erasable edit read-only storage (deposit by EPROM or flash
Reservoir), fiber device and portable read-only memory (CDROM).In addition, computer readable storage medium can even is that
Can the paper of print routine or other suitable media on it because can for example be swept by carrying out optics to paper or other media
It retouches, is then edited, interprets or handled when necessary with other suitable methods electronically to obtain program, then will
It is stored in computer storage.
In embodiments of the present invention, computer-readable signal media may include in a base band or as carrier wave a part
The data-signal of propagation, wherein carrying computer-readable program code.The data-signal of this propagation can use a variety of
Form, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media is also
It can be any computer-readable medium other than computer readable storage medium, which can send, pass
It broadcasts or transmits for instruction execution system, input method or device use or program in connection.Computer can
The program code for reading to include on medium can transmit with any suitable medium, including but not limited to: wirelessly, electric wire, optical cable, penetrate
Frequently (Radio Frequency, RF) etc. or above-mentioned any appropriate combination.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is the program that relevant hardware can be instructed to complete by program, which can store in a kind of computer-readable storage
In medium, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.If integrated module with
The form of software function module is realized and when sold or used as an independent product, also can store computer-readable at one
In storage medium.Storage medium can be read-only memory, disk or CD etc..
More than, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement, these
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims
It is quasi-.
Claims (14)
1. a kind of method that musical works is recommended characterized by comprising
Obtain the relevant user behavior data of target music；
According to the user behavior data, the similarity degree of the target music and other music is determined；
According to the data volume of the user behavior data and affiliated data type, the target music and other music are determined
Similar confidence level；
According to the similarity degree and confidence level of the target music and other music, the similar music of the target music is determined；
And
To the target music, relevant user recommends the similar music.
2. the method as described in claim 1, which is characterized in that the user behavior data includes recommending the target music
Song is single, and according to the user behavior data of the target music, determines the similarity degree of the target music and other music,
Include:
The same single frequency of occurrence of song and the target music and other are appeared according to the target music and other music
Music appears in the single spread length of same song, determines the similarity degree of the target music and other music on song list.
3. the method as described in claim 1, which is characterized in that the user behavior data includes user search music behavior,
And the user behavior data according to the target music, determine the similarity degree of the target music and other music, comprising:
From user search music behavior, the user search sound that each user retrieves the target music in the set time period is chosen
Happy behavior；
According to the user search music behavior chosen, counts each user and retrieve the target music and its during the period of time
His music retrieval time interval and the target music and other music during the period of time by the inspection of user search
Rope number of users；And
According to the retrieval time interval and the retrieval number of users, determine that the target music and other music are examined in user
Similarity degree in Suo Yinle behavior.
4. the method as described in claim 1, which is characterized in that the user behavior data includes that user collects music behavior,
And the user behavior data according to the target music, determine the similarity degree of the target music and other music, comprising:
It is collected in music behavior from user, chooses user's collection sound that each user collects the target music in the set time period
Happy behavior；
Music behavior is collected according to the user chosen, each user is counted and collects the target music and its during the period of time
The collection time interval of his music and the target music are collected by same user during the period of time with other music
Collection number of users；And
According to the collection time interval and the collection number of users, determine that the target music and other music are received in user
Hide the similarity degree in music behavior.
5. such as the described in any item methods of Claims 1-4, which is characterized in that further include:
Judge whether target music confidence level similar with other music meets confidence level correction conditions；
If meeting the confidence level correction conditions, obtains the expert comprising the target music and recommend song single；
Recommend song single according to the expert, carries out music recommendation；And
During the target music is recommended, target music confidence level similar with other music is corrected.
6. method as claimed in claim 5, which is characterized in that during the target music is recommended, correct the mesh
The happy confidence level similar with other music of mark with phonetic symbols, comprising:
During the target music is recommended, the relevant user behavior data of the target music is obtained again；And
According to the data volume of the user behavior data got again and affiliated data type, determine the target music with
The similar confidence level of other music.
7. the device that a kind of similar music is recommended characterized by comprising
Behavioral data obtains module, for obtaining the relevant user behavior data of target music；
Similarity degree determining module, for determining the phase of the target music and other music according to the user behavior data
Like degree；
Confidence determination module determines institute for the data volume and affiliated data type according to the user behavior data
State target music confidence level similar with other music；
Similar music determining module determines institute for the similarity degree and confidence level according to the target music and other music
State the similar music of target music；And
Similar music recommending module, for recommending the similar music to the relevant user of the target music.
8. device as claimed in claim 7, which is characterized in that the user behavior data includes recommending the target music
Song list and the similarity degree determining module include:
Single similarity determining unit is sung, for appearing in the single appearance frequency of same song according to the target music and other music
The secondary and described target music and other music appear in the single spread length of same song, determine the target music and other
Similarity degree of the music on song list.
9. device as claimed in claim 7, which is characterized in that the user behavior data includes user search music behavior,
And the similarity degree determining module includes:
Retrieval behavior selection unit, for choosing each user and retrieving institute in the set time period from user search music behavior
State the user search music behavior of target music；
Data statistics unit is retrieved, for counting each user in the period according to the user search music behavior chosen
The interior retrieval target music and other music retrieval time interval and the target music with other music described
By the retrieval number of users of user search in period；And
Similarity determining unit is retrieved, for determining the mesh according to the retrieval time interval and the retrieval number of users
Mark with phonetic symbols pleasure and similarity degree of other music in user search music behavior.
10. device as claimed in claim 7, which is characterized in that the user behavior data includes that user collects music behavior,
And the similarity degree determining module includes:
Collection behavior selection unit chooses each user and collects institute in the set time period for collecting in music behavior from user
The user for stating target music collects music behavior；
Data statistics unit is collected, for collecting music behavior according to the user chosen, counts each user in the period
The interior collection target music is with the collection time interval of other music and the target music with other music described
The collection number of users collected in period by same user；And
Similarity determining unit is collected, for determining the mesh according to the collection time interval and the collection number of users
Mark with phonetic symbols is happy to collect the similarity degree in music behavior in user with other music.
11. such as the described in any item devices of claim 7 to 10, which is characterized in that further include:
Confidence level judgment module is repaired for judging whether target music confidence level similar with other music meets confidence level
Positive condition；
Recommend song is single to obtain module, if obtained special comprising the target music for meeting the confidence level correction conditions
Family recommends song single；
The happy recommending module of single-tone is sung, for recommending song single according to the expert, carries out music recommendation；And
Confidence level correction module, for correcting the target music and other music during the target music is recommended
Similar confidence level.
12. device as claimed in claim 11, which is characterized in that the confidence level correction module includes:
Behavioral data acquiring unit, for it is related to obtain the target music again during the target music is recommended
User behavior data；And
Confidence level determination unit, for according to the data volume of user behavior data and affiliated data class got again
Type determines target music confidence level similar with other music.
13. a kind of terminal device realizing musical works and recommending, which is characterized in that the terminal device includes:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors
Realize such as method as claimed in any one of claims 1 to 6.
14. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the program is held by processor
Such as method as claimed in any one of claims 1 to 6 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811340909.6A CN109299317B (en) | 2018-11-12 | 2018-11-12 | Method, apparatus, storage medium and the terminal device that musical works is recommended |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811340909.6A CN109299317B (en) | 2018-11-12 | 2018-11-12 | Method, apparatus, storage medium and the terminal device that musical works is recommended |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109299317A true CN109299317A (en) | 2019-02-01 |
| CN109299317B CN109299317B (en) | 2019-09-27 |
Family
ID=65146245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811340909.6A Active CN109299317B (en) | 2018-11-12 | 2018-11-12 | Method, apparatus, storage medium and the terminal device that musical works is recommended |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109299317B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110647653A (en) * | 2019-09-30 | 2020-01-03 | 广州酷狗计算机科技有限公司 | Song recommendation method and device and computer storage medium |
| CN111143699A (en) * | 2020-01-03 | 2020-05-12 | 上海理工大学 | Recommendation system based on similarity and confidence clustering |
| CN113032616A (en) * | 2021-03-19 | 2021-06-25 | 腾讯音乐娱乐科技（深圳）有限公司 | Audio recommendation method and device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090193015A1 (en) * | 2008-01-28 | 2009-07-30 | Samsung Electronics Co., Ltd. | Method and appartus for adaptively updating recommend user group |
| CN107818138A (en) * | 2017-09-28 | 2018-03-20 | 银江股份有限公司 | A kind of case legal regulation recommends method and system |
| CN108200142A (en) * | 2017-12-28 | 2018-06-22 | 广州酷狗计算机科技有限公司 | A kind of music method for pushing and sound-box device |
-
2018
- 2018-11-12 CN CN201811340909.6A patent/CN109299317B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090193015A1 (en) * | 2008-01-28 | 2009-07-30 | Samsung Electronics Co., Ltd. | Method and appartus for adaptively updating recommend user group |
| CN107818138A (en) * | 2017-09-28 | 2018-03-20 | 银江股份有限公司 | A kind of case legal regulation recommends method and system |
| CN108200142A (en) * | 2017-12-28 | 2018-06-22 | 广州酷狗计算机科技有限公司 | A kind of music method for pushing and sound-box device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110647653A (en) * | 2019-09-30 | 2020-01-03 | 广州酷狗计算机科技有限公司 | Song recommendation method and device and computer storage medium |
| CN111143699A (en) * | 2020-01-03 | 2020-05-12 | 上海理工大学 | Recommendation system based on similarity and confidence clustering |
| CN111143699B (en) * | 2020-01-03 | 2023-07-28 | 上海理工大学 | Recommendation system based on similarity and confidence coefficient clustering |
| CN113032616A (en) * | 2021-03-19 | 2021-06-25 | 腾讯音乐娱乐科技（深圳）有限公司 | Audio recommendation method and device, computer equipment and storage medium |
| CN113032616B (en) * | 2021-03-19 | 2024-02-20 | 腾讯音乐娱乐科技（深圳）有限公司 | Audio recommendation method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109299317B (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5565374B2 (en) | Device for changing the segmentation of audio works | |
| CN109299318A (en) | Method, apparatus, storage medium and the terminal device that music is recommended | |
| CN109299317B (en) | Method, apparatus, storage medium and the terminal device that musical works is recommended | |
| JP4775379B2 (en) | Apparatus and method for specifying various segment classes | |
| CN101689225B (en) | Generating music thumbnails and identifying related song structure | |
| US20170300567A1 (en) | Media content items sequencing | |
| Yang et al. | Revisiting the problem of audio-based hit song prediction using convolutional neural networks | |
| KR100895009B1 (en) | System and method for recommending music | |
| US20060224260A1 (en) | Scan shuffle for building playlists | |
| CN109408665A (en) | A kind of information recommendation method and device, storage medium | |
| US20090228799A1 (en) | Method for visualizing audio data | |
| Schuller et al. | ‘Mister DJ, Cheer Me Up!’: Musical and textual features for automatic mood classification | |
| MX2007016220A (en) | Providing community-based media item ratings to users. | |
| CN106991163A (en) | A kind of song recommendations method based on singer's sound speciality | |
| CN108877753B (en) | Music synthesis method and system, terminal and computer readable storage medium | |
| Panda et al. | How does the spotify api compare to the music emotion recognition state-of-the-art? | |
| Duinker et al. | In search of the golden age hip-hop sound (1986–1996) | |
| CN105280196A (en) | Method and system for detecting chorus | |
| KR100868764B1 (en) | Method and system of recommending a music using user model, and update method of a conditional user model | |
| Smith et al. | Audio properties of perceived boundaries in music | |
| JP2008515012A (en) | Apparatus and method for grouping time segments of music | |
| US9037278B2 (en) | System and method of predicting user audio file preferences | |
| Schuller et al. | Music theoretic and perception-based features for audio key determination | |
| CN111460215B (en) | Audio data processing method and device, computer equipment and storage medium | |
| CN106095943B (en) | It gives song recitals and knows well range detection method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210508 Address after: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Patentee after: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. Patentee after: Shanghai Xiaodu Technology Co.,Ltd. Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Patentee before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |