CN102402625A - Method and system for recommending music - Google Patents
Method and system for recommending music Download PDFInfo
- Publication number
- CN102402625A CN102402625A CN2011104483534A CN201110448353A CN102402625A CN 102402625 A CN102402625 A CN 102402625A CN 2011104483534 A CN2011104483534 A CN 2011104483534A CN 201110448353 A CN201110448353 A CN 201110448353A CN 102402625 A CN102402625 A CN 102402625A
- Authority
- CN
- China
- Prior art keywords
- song
- user
- music
- classification
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention belongs to the technical field of multimedia and in particular relates to a method and a system for recommending music. The method comprises the following steps of: a, accessing a page server through a mobile terminal, browsing page information, and requesting a resource server to acquire page data which is required, wherein the page data comprises music resources and music recommending data; b, recording behaviors of users on accessing of the page server, and recording music acquisition behaviors of the users on the resource server and music resource information which is acquired; c, acquiring behavior records of the users, and classifying the users according to the behavior records; and d, classifying songs in a song classification mode, and generating corresponding song recommending lists according to different user types. By adoption of the invention, the users can more quickly and more effectively listen to favorite songs, so that personalization requirements of the users are met, and a contradiction between mass of the songs and the personalization of user favor is solved.
Description
Technical field
The invention belongs to multimedia technology field, relate in particular to a kind of method and system of music recommend.
Background technology
In recent years, the sustainable development of global digital entertainment industry, the Online Music development is particularly rapid, from the Chinese online music of starting in 2000, is the second largest application of China Internet, and increasing in numbers swiftly of pop music adds up the song amount and surpasses 1,000,000.Along with popularizing of network, the making of song is more and more convenient, and in view of this, the song amount will be exponential increase in following a period of time.In the time of song magnanimityization accumulative total, music user also shows tangible individualized music preference.The song that different user's preferences is different is even same user also has different music preferences different periods.How to let the user from the song of magnanimity, find the song of oneself liking, just become present problem to be solved.
To this problem, present solution is carried out music recommend for the recommended models that theorizes through mathematical method, stresses algorithm improvement and optimization in theory, and through the first song of hundreds of, a simulation hundreds of user makes up and verify recommended models.But this recommended models has mainly been inquired into feasible on the mathematical method, can't be applied to 1,000,000 songs and ten million user's actual environment at all.In addition, there is many and actual different hypothesis in the recommended models, for example: be based upon detailed user and mark in the tabulation, but it is few to provide the user of song scoring in the reality; Be based upon on the perfect quality of data, think that the quality of data is definitely credible, and in fact the quality of data has often determined the direction of modeling; Supposed the versatility of single model in addition; And in fact single recommended models often can only solve only a few user's problem, and therefore, existing music recommend method can not satisfy most of users' individual demand; And input-output ratio is low, is unfavorable for applying.
Summary of the invention
The invention provides a kind of method and system of music recommend, be intended to solve the individual demand that music recommend method of the prior art can not satisfy most of users, and input-output ratio low, be unfavorable for the problem applied.
The present invention is achieved in that a kind of method of music recommend, comprising:
Step a: through mobile terminal accessing page server browsing pages information, and the request resource server obtains the page data that needs; Wherein, said page data comprises music sources and music recommend data;
Step b: the behavior of recording user accession page server, and the music of recording user on the Resource Server music sources information obtaining behavior and obtain;
Step c: obtain user's behavior record, and the user is classified according to behavior record;
Steps d: according to the song mode classification song is classified, and generate corresponding song recommendations tabulation according to different user types.
Technical scheme of the present invention also comprises: in said steps d, said song mode classification specifically comprises the classification of song label, the classification of song similarity, the classification of heat song seniority among brothers and sisters, correlation rule classification, user clustering classification and collaborative filtering classification.
Technical scheme of the present invention also comprises: in said steps d, said song label classification is specially: the music sources in the Resource Server is carried out the song classification according to label, generate the song recommendations tabulation according to song label classification; Said song similarity classification is specially: carry out the song classification according to the base attribute of song, calculate the similarity of song in each song classification respectively, carry out song recommendations according to the size of song similarity; Wherein, the base attribute of said song comprises issuing date, singer's sex, audio frequency and the lyrics.
Technical scheme of the present invention also comprises: in said steps d, the classification of said heat song seniority among brothers and sisters is specially: generate popular song seniority among brothers and sisters Qu Ku through the rank of calculating a series of popular songs, and generate popular song recommendations Qu Ku according to certain weight and array mode; The classification of said correlation rule is specially: adopt association algorithm to calculate the correlation rule of user behavior record, and correlation rule integrated calculate corresponding related song recommendations tabulation.
Technical scheme of the present invention also comprises: in said steps d; The classification of said user clustering is specially: the behavior record according to the user hives off to the user, calculates in each group user's song and obtains seniority among brothers and sisters, and calculate the similarity between the user in each group; With the similarity is weight; Gather in each group the song of similar users and obtain seniority among brothers and sisters, delete download song, generate the song recommendations tabulation; Said collaborative filtering classification is specially: calculate the similarity between each user, generate the song recommendations tabulation according to user's similarity.
Technical scheme of the present invention also comprises: said steps d also comprises: music recommend information is sent to page server, and the user obtains corresponding music sources through music recommend information.
Another technical scheme of the present invention; A kind of system of music recommend; Comprise portable terminal, page server, log server, Resource Server and data mining server; Said portable terminal is used for the page data that accession page server browsing pages information is obtained needs, and said page server is used for user's browsing pages information, the page data that selection need be obtained; Said log server is used for the behavior of recording user accession page server, and behavior record is sent to data mining server; Said Resource Server is used to deposit music sources; And the obtain behavior of recording user on Resource Server and the music sources information of obtaining; And will obtain behavior and the music sources information obtained sends to data mining server, said data mining server is used to store user's behavior record and music sources information, according to behavior record the user is classified; According to the song mode classification song is classified, and generate corresponding song recommendations tabulation according to different user types.
Technical scheme of the present invention also comprises: said data mining server also comprises database and music recommend module; Said database is used to store behavior, the download behavior of user on Resource Server and the music sources information of obtaining of user to access pages server, and according to canned data the user is classified; Said music recommend module is used for according to different song mode classifications song being classified; Generate corresponding song recommendations tabulation according to the different user types in the database; And recommendation information returned to page server, the user through recommendation information to the corresponding music sources of Resource Server acquisition request.
Technical scheme of the present invention also comprises: said music recommend module also comprises song taxon, song similarity unit and heat song seniority among brothers and sisters unit; Said song taxon is carried out the song classification with the music sources in the Resource Server according to label, generates the song recommendations tabulation according to song label classification; Said song similarity unit is used for carrying out the song classification according to the base attribute of song, calculates the similarity of song in each song classification respectively, according to the size generation song recommendations tabulation of song similarity; Said heat song seniority among brothers and sisters unit generates popular song seniority among brothers and sisters Qu Ku through the rank of calculating a series of popular songs, and generates popular song recommendations Qu Ku according to certain weight and array mode.
Technical scheme of the present invention also comprises: said music recommend module also comprises correlation rule unit, user clustering unit and collaborative filtering unit; Said correlation rule unit is used to adopt association algorithm to calculate the correlation rule of user behavior record, and correlation rule integrated calculates corresponding related song recommendations tabulation; Said user clustering unit is used for according to user's behavior record the user being hived off; Calculate in each group user's song and obtain seniority among brothers and sisters; And calculate the similarity between the user in each group, and be weight with the similarity, gather in each group the song of similar users and obtain seniority among brothers and sisters; Delete download song, generate the song recommendations tabulation; Said collaborative filtering unit is used to calculate the similarity between each user, generates the song recommendations tabulation according to user's similarity.
Technical scheme of the present invention has following advantage or beneficial effect: the method and system of music recommend of the present invention are carried out record through the music behavior of obtaining to different user; And song is classified through multiple song mode classification; Generate the song recommendations information of each classification corresponding targetedly with the user according to user's behavior record; Make the user can listen to the song of oneself liking more quickly and effectively; Satisfy user's individual demand, solved the contradiction between song magnanimityization and the user preferences personalization, avoided looking at random the inconvenience of music tape and loaded down with trivial details; Secondly, application of the present invention has promoted the serviceability of page data, has reduced the poor efficiency of blindly recommending; Increase the download and the buying rate of music, and can promote the utilization factor of music sources, effectively deleted invalid resource; When promoting income, reduce the purchase cost of song copyright; In addition, the present invention has improved the chance that song shows the user, makes the minority singer who does not have the fund to carry out marketing activity usually also can show one's talent, and effectively finds the user who likes oneself, thus lifting creator's value.
Description of drawings
Accompanying drawing 1 is the process flow diagram of method of the music recommend of first embodiment of the invention;
Accompanying drawing 2 is process flow diagrams of method of the music recommend of second embodiment of the invention;
Accompanying drawing 3 is process flow diagrams of the method for song classification of the present invention;
Accompanying drawing 4 is structural representations of song recommendations tabulation of the present invention;
Accompanying drawing 5 is structural representations of system of the music recommend of first embodiment of the invention;
Accompanying drawing 6 is structural representations of system of the music recommend of second embodiment of the invention.
Embodiment
In order to make the object of the invention, technical scheme and advantage clearer,, the present invention is further elaborated below in conjunction with accompanying drawing and embodiment.Should be appreciated that specific embodiment described herein only in order to explanation the present invention, and be not used in qualification the present invention.
See also Fig. 1, be first embodiment of the invention process flow diagram.May further comprise the steps of first embodiment of the invention:
Step 100: through mobile terminal accessing page server browsing pages information, and the request resource server obtains the page data that needs; Wherein, said page data comprises music sources and music recommend data;
In step 100, portable terminal is that mobile phone or other can be taken charge of server with me through mobile Internet and carry out mutual equipment, and the user is through the service of portable terminal reception music recommend; Page data comprises data such as music sources and music recommend; Wherein, Music sources is deposited in the Resource Server; When portable terminal passed through to select audition or downloading page data in the page info of page server, through the URL of page data, portable terminal carried out audition or download to the corresponding music sources of Resource Server request.
Step 110: the behavior of recording user accession page server, and the music of recording user on the Resource Server music sources information obtaining behavior and obtain;
In step 110; When the user passes through the mobile terminal accessing page server; Log server is collected the page of user capture and the song of obtaining automatically through APCHE and tomcat; The storage user passes through the behavior of mobile terminal accessing page server, and these log records are sent to data mining server, as the essential information source of this user's music recommend; Log server and page server are set up the synchronous warehouse-in mechanism of daily record; When the user produced new behavior, log server can write down its behavior fast and accurately, and the time point of arranging; Send it to data mining server, to realize dynamically updating of data; When the user obtains music sources through Resource Server; Music sources information that Resource Server obtains the user and the Download History of user on Resource Server offer data mining server and store; Information source as this user's music recommend; Wherein, music sources information comprises the URL address of song title and song etc.
Step 120: obtain user's behavior record, and the user is classified according to behavior record;
In step 120, can for example Add User according to the obtaining (downloading or audition) mode and classify of the number of times of behavior record or music sources, audition user, slight download user, moderate download user and severe download user etc. to the user.
Step 130: according to the song mode classification song is classified, and generate corresponding song recommendations tabulation according to different user types.
In step 130, concrete song mode classification comprises the classification of song label, the classification of song similarity, the classification of heat song seniority among brothers and sisters, correlation rule classification, user clustering classification and collaborative filtering classification etc.
Seeing also Fig. 2, is the process flow diagram of method of the music recommend of second embodiment of the invention.The method of the music recommend of second embodiment of the invention may further comprise the steps:
Step 200: through mobile terminal accessing page server browsing pages information, and the request resource server obtains the page data that (audition or download) needs;
In step 200, portable terminal is that mobile phone or other can be taken charge of server with me through mobile Internet and carry out mutual equipment, and the user is through the service of portable terminal reception music recommend; Page data comprises data such as music sources and music recommend; Wherein, Music sources is deposited in the Resource Server; When portable terminal passed through to select audition or downloading page data in the page info of page server, through the URL of page data, portable terminal carried out audition or download to the corresponding music sources of Resource Server request.
Step 210: the behavior of recording user accession page server, and behavior record sent to data mining server;
In step 210; When the user passes through the mobile terminal accessing page server; Log server is collected the page of user capture and the song of obtaining automatically through APCHE and tomcat; The storage user passes through the behavior of mobile terminal accessing page server, and these log records are sent to data mining server, as the essential information source of this user's music recommend; Log server and page server are set up the synchronous warehouse-in mechanism of daily record; When the user produced new behavior, log server can write down its behavior fast and accurately, and the time point of arranging; Send it to data mining server, to realize dynamically updating of data.
Step 220: the music sources information that the music of recording user on Resource Server obtained behavior and obtained, and music obtained behavior and the music sources information obtained sends to data mining server;
In step 220; When the user obtains music sources through Resource Server; Music sources information that Resource Server obtains the user and the Download History of user on Resource Server offer data mining server and store; As the information source of this user's music recommend, wherein, music sources information comprises the URL address of song title and song etc.
Step 230: obtain user's behavior record, and the user is classified according to user's behavior record;
In step 230, can for example Add User according to the obtaining (downloading or audition) mode and classify of the number of times of behavior record or music sources, audition user, slight download user, moderate download user and severe download user etc. to the user.
Step 240: the song in the Resource Server classified according to different song mode classifications generates different classes of song recommendations tabulation;
In step 240; Concrete song mode classification comprises the classification of song label, the classification of song similarity, the classification of heat song seniority among brothers and sisters, correlation rule classification, user clustering classification and collaborative filtering classification; In order to clearly demonstrate the method for various song classification; Please further consulting Fig. 3, is the process flow diagram of the method for song classification of the present invention.The method of song classification of the present invention may further comprise the steps:
Step 241: the music sources in the Resource Server is carried out the song classification according to label (key word), generate the song recommendations tabulation according to song label classification;
In step 241, the label mode classification is specially: the lyrics to song split, and identify the key word that has the classification characteristic, and then confirm the classification of song through the classification under the judgement key word.
Step 242: carry out the song classification according to the base attribute of song, calculate the similarity of song in each song classification respectively, carry out song recommendations according to the size of song similarity;
In step 242, the base attribute of song comprises four factors such as issuing date, singer's sex, audio frequency and the lyrics, wherein; Because present music mainly is a popular song, popular song is different from classical music, and its maximum characteristics are exactly ageing; So issuing date just becomes a considerable essential information, find that through download behavioural analysis some user hankers after newly singing express delivery to the music user; Some user prefers to classics misses old times or old friends, and it serves to show the important of song time attribute; Secondly, user's music preferences also shows certain gender differences, and some people likes female voice, and some people likes male voice, and also some tends to men and women's mixing, so when the music similarity was calculated, singer's sex attribute can not be ignored; In addition, audio frequency, the lyrics also are most important two attributes of song, have comprised the height of song tone in the audio frequency; The height that can distinguish the tone of song exactly rises and falls; The lyrics have comprised the emotion of music especially, and can also reflect the speed of singing songs, just rhythm indirectly; Therefore, the present invention selects these four factors of issuing date, singer's sex, audio frequency and the lyrics as the Fundamentals of weighing the similarity of song own; In addition, because the difference of region, can also be with the area as another factor of weighing the song similarity, for example, interior ground, Hong Kong and Taiwan, America and Europe, Japan and Korea S etc. can be through the further refinement song of the classification classifications of region.
Step 243: generate popular song seniority among brothers and sisters Qu Ku through the rank of calculating a series of popular songs, and generate popular song recommendations Qu Ku according to certain weight and array mode;
In step 243; To after the song classification, generate basic popular song list according to base attributes such as issuing date and singer's sexes, for example be divided into classifications such as classical old song (woman), classical old song (man), classical love song antiphonal singing, popular new song (woman), popular new song (man), new love song antiphonal singing; Calculate the rank of all kinds of songs respectively according to the classification of song; And all kinds of songs packings are combined into the recommendation song according to the rank of song, and each category rank is recommended song to the user, and that recommend for the first time is the top1 of each classification; Be recommended as for the second time the top2 of each classification, and the like; Wherein, the rank of song according to every day actual conditions dynamically update.
Step 244: adopt association algorithm to calculate the correlation rule of user behavior record, and correlation rule integrated calculate corresponding related song recommendations tabulation;
In step 244, be fewer owing to satisfy the correlation rule of the requirement of given support and degree of confidence, so; In order to guarantee that every first song can both calculate relevant with it song, just must reduce the support of song data, even support is made as 0; Can find its pairing related song for the overwhelming majority's song so in theory, still, this has also caused declining to a great extent of efficiency of algorithm; In order to remedy this deficiency; The present invention classifies to the song resource, and only compute associations is regular between each classification, and between class, does not do computing.
Step 245: the behavior record according to the user hives off to the user; Calculate in each group user's song and obtain seniority among brothers and sisters; And calculate the similarity between the user in each group, and be weight with the similarity, gather in each group the song of similar users and obtain seniority among brothers and sisters; Delete download song, generate the song recommendations tabulation;
In step 245, the present invention adopt the ROCK clustering algorithm according to user's behavior record to tenant group.
Step 246: calculate the similarity between each user, generate the song recommendations tabulation according to user's similarity.
Step 250: generate corresponding song recommendations tabulation according to different user types;
In step 250, please consult Fig. 4 in the lump, be the structural representation of song recommendations tabulation of the present invention.
Step 260: music recommend information is sent to page server, and the user obtains corresponding music sources through music recommend information;
In step 260; In another embodiment of the present invention; The user can directly import or/and select the song mode classification, obtains the music recommend information of the respective classes corresponding with the user through user's behavior record, makes the user can listen to the song of oneself liking more quickly and effectively.
Step 270: finish this music recommend.
Seeing also Fig. 5, is the structural representation of system of the music recommend of first embodiment of the invention.The system of the music recommend of first embodiment of the invention comprises portable terminal, page server, log server, Resource Server and data mining server, wherein,
Portable terminal is used for the page data that accession page server browsing pages information is obtained needs; Wherein, portable terminal is that mobile phone or other can be taken charge of server with me through mobile Internet and carry out mutual equipment, and the user is through the service of portable terminal reception music recommend; Music sources is deposited in the Resource Server; When portable terminal passes through to select audition or downloading page data in the page info of page server; Through the URL of page data, portable terminal carries out audition or download to the corresponding music sources of Resource Server request.
Page server is used for user's browsing pages information, the page data that selection need be obtained;
Log server is used for the behavior of recording user accession page server, and behavior record is sent to data mining server; Wherein, When the user passes through the mobile terminal accessing page server; Log server is collected the page of user capture and the song of obtaining automatically through APCHE and tomcat; The storage user passes through the behavior of mobile terminal accessing page server, and these log records are sent to data mining server, as the essential information source of this user's music recommend; Log server and page server are set up the synchronous warehouse-in mechanism of daily record; When the user produced new behavior, log server can write down its behavior fast and accurately, and the time point of arranging; Send it to data mining server, to realize dynamically updating of data.
Resource Server is used to deposit music sources, and the obtain behavior of recording user on Resource Server and the music sources information of obtaining, and behavior of obtaining and the music sources information obtained are sent to data mining server; Wherein, When the user obtains music sources through Resource Server; Music sources information that Resource Server obtains the user and the Download History of user on Resource Server offer data mining server and store, as the information source of this user's music recommend; Music sources information comprises the URL address of song title and song etc.
Said data mining server is used to store user's behavior record and music sources information, according to behavior record the user is classified, and according to the song mode classification song is classified, and generates corresponding song recommendations tabulation according to different user types; Wherein, can for example Add User according to the obtaining (downloading or audition) mode and classify of the number of times of behavior record or music sources to the user, audition user, slight download user, moderate download user and severe download user etc.; Concrete song mode classification comprises the classification of song label, the classification of song similarity, the classification of heat song seniority among brothers and sisters, correlation rule classification, user clustering classification and collaborative filtering classification etc.
Seeing also Fig. 6, is the structural representation of system of the music recommend of second embodiment of the invention.The system of the music recommend of second embodiment of the invention comprises portable terminal, page server, log server, Resource Server and data mining server, wherein,
Portable terminal is used for accession page server browsing pages information, and the request resource server obtains the page data that (audition or download) needs; Wherein, portable terminal is that mobile phone or other can be taken charge of server with me through mobile Internet and carry out mutual equipment, and the user is through the service of portable terminal reception music recommend; Page data comprises data such as music sources and music recommend; Music sources is deposited in the Resource Server, and when portable terminal passed through to select audition or down-load music in the page info of page server, through the URL in the page data, portable terminal carried out audition or download to the corresponding music sources of Resource Server request.
Page server is used for user's browsing pages information, the URL address of page data that selection need be obtained and page data; Wherein, page data comprises music sources information and music recommend information etc., and the user passes through the URL address of page data to the corresponding music sources of Resource Server request.
Log server is used for the behavior of recording user accession page server, and behavior record is sent to data mining server; Wherein, When the user passes through the mobile terminal accessing page server; Log server is collected the page of user capture and the song of obtaining automatically through APCHE and tomcat; The storage user passes through the behavior of mobile terminal accessing page server, and these log records are sent to data mining server, as the essential information source of this user's music recommend; Log server and page server are set up the synchronous warehouse-in mechanism of daily record; When the user produced new behavior, log server can write down its behavior fast and accurately, and the time point of arranging; Send it to data mining server, to realize dynamically updating of data.
Resource Server is used to deposit music sources, and the music of recording user on the Resource Server music sources information obtaining behavior and obtain, and music is obtained behavior and the music sources information obtained sends to data mining server; Wherein, When the user obtains music sources through Resource Server; Music sources information that Resource Server obtains the user and the Download History of user on Resource Server offer data mining server and store; As the information source of this user's music recommend, wherein, music sources information comprises the URL address of song title and song etc.
Data mining server comprises database and music recommend module, wherein,
Database is used to store behavior, the download behavior of user on Resource Server and the behavior record data of obtaining such as music sources information of user to access pages server; Information source as this user's music recommend; And obtain user's behavior record, according to user's behavior record the user is classified; Wherein, can for example Add User according to the obtaining (downloading or audition) mode and classify of the number of times of behavior record or music sources to the user, audition user, slight download user, moderate download user and severe download user etc.
The music recommend module is used for according to different song mode classifications song being classified; Generate the corresponding song recommendations tabulation of different user types according to the user behavior record data in the database; And music recommend information returned to page server, the user through music recommend information to the corresponding music sources of Resource Server acquisition request; Particularly, the music recommend module also comprises song taxon, song similarity unit, heat song seniority among brothers and sisters unit, correlation rule unit, user clustering unit and collaborative filtering unit, wherein,
The song taxon is carried out the song classification with the music sources in the Resource Server according to label (key word), generates the song recommendations tabulation according to song label classification; Wherein, the label mode classification is specially: the lyrics to song split, and identify the key word that has the classification characteristic, and then confirm the classification of song through the classification under the judgement key word.
Song similarity unit is used for carrying out the song classification according to the base attribute of song, calculates the similarity of song in each song classification respectively, according to the size generation song recommendations tabulation of song similarity; Wherein, the base attribute of song comprises four factors such as issuing date, singer's sex, audio frequency and the lyrics, wherein; Because present music mainly is a popular song, popular song is different from classical music, and its maximum characteristics are exactly ageing; So issuing date just becomes a considerable essential information, find that through download behavioural analysis some user hankers after newly singing express delivery to the music user; Some user prefers to classics misses old times or old friends, and it serves to show the important of song time attribute; Secondly, user's music preferences also shows certain gender differences, and some people likes female voice, and some people likes male voice, and also some tends to men and women's mixing, so when the music similarity was calculated, singer's sex attribute can not be ignored; In addition, audio frequency, the lyrics also are most important two attributes of song, have comprised the height of song tone in the audio frequency; The height that can distinguish the tone of song exactly rises and falls; The lyrics have comprised the emotion of music especially, and can also reflect the speed of singing songs, just rhythm indirectly; Therefore, the present invention selects these four factors of issuing date, singer's sex, audio frequency and the lyrics as the Fundamentals of weighing the similarity of song own; In addition, because the difference of region, can also be with the area as another factor of weighing the song similarity, for example, interior ground, Hong Kong and Taiwan, America and Europe, Japan and Korea S etc. can be through the further refinement song of the classification classifications of region.
Heat song seniority among brothers and sisters unit generates popular song seniority among brothers and sisters Qu Ku through the rank of calculating a series of popular songs, and generates popular song recommendations Qu Ku according to certain weight and array mode; Wherein, To after the song classification, generate basic popular song list according to base attributes such as issuing date and singer's sexes, for example be divided into classifications such as classical old song (woman), classical old song (man), classical love song antiphonal singing, popular new song (woman), popular new song (man), new love song antiphonal singing; Calculate the rank of all kinds of songs respectively according to the classification of song; And all kinds of songs packings are combined into the recommendation song according to the rank of song, and each category rank is recommended song to the user, and that recommend for the first time is the top1 of each classification; Be recommended as for the second time the top2 of each classification, and the like; Wherein, the rank of song according to every day actual conditions dynamically update.
The correlation rule unit is used to adopt association algorithm to calculate the correlation rule of user behavior record, and correlation rule integrated calculates corresponding related song recommendations tabulation; Wherein, be fewer owing to satisfy the correlation rule of the requirement of given support and degree of confidence, so; In order to guarantee that every first song can both calculate relevant with it song, just must reduce the support of song data, even support is made as 0; Can find its pairing related song for the overwhelming majority's song so in theory, still, this has also caused declining to a great extent of efficiency of algorithm; In order to remedy this deficiency; The present invention classifies to the song resource, and only compute associations is regular between each classification, and between class, does not do computing.
The user clustering unit is used for according to user's behavior record the user being hived off; Calculate in each group user's song and obtain seniority among brothers and sisters; And calculate the similarity between the user in each group, and be weight with the similarity, gather in each group the song of similar users and obtain seniority among brothers and sisters; Delete download song, generate the song recommendations tabulation; Wherein, the present invention adopt the ROCK clustering algorithm according to user's behavior record to tenant group.
The collaborative filtering unit is used to calculate the similarity between each user, generates the song recommendations tabulation according to user's similarity.
The method and system of music recommend of the present invention are carried out record through the music behavior of obtaining to different user; And song is classified through multiple song mode classification; Generate the song recommendations information of each classification corresponding targetedly with the user according to user's behavior record; Make the user can listen to the song of oneself liking more quickly and effectively; Satisfy user's individual demand, solved the contradiction between song magnanimityization and the user preferences personalization, avoided looking at random the inconvenience of music tape and loaded down with trivial details; Secondly, application of the present invention has promoted the serviceability of page data, has reduced the poor efficiency of blindly recommending; Increase the download and the buying rate of music, and can promote the utilization factor of music sources, effectively deleted invalid resource; When promoting income, reduce the purchase cost of song copyright; In addition, the present invention has improved the chance that song shows the user, makes the minority singer who does not have the fund to carry out marketing activity usually also can show one's talent, and effectively finds the user who likes oneself, thus lifting creator's value.
The above is merely preferred embodiment of the present invention, not in order to restriction the present invention, all any modifications of within spirit of the present invention and principle, being done, is equal to and replaces and improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the method for a music recommend comprises:
Step a: through mobile terminal accessing page server browsing pages information, and the request resource server obtains the page data that needs; Wherein, said page data comprises music sources and music recommend data;
Step b: the behavior of recording user accession page server, and the music of recording user on the Resource Server music sources information obtaining behavior and obtain;
Step c: obtain user's behavior record, and the user is classified according to behavior record;
Steps d: according to the song mode classification song is classified, and generate corresponding song recommendations tabulation according to different user types.
2. the method for music recommend according to claim 1; It is characterized in that; In said steps d, said song mode classification specifically comprises the classification of song label, the classification of song similarity, the classification of heat song seniority among brothers and sisters, correlation rule classification, user clustering classification and collaborative filtering classification.
3. the method for music recommend according to claim 2; It is characterized in that; In said steps d, said song label classification is specially: the music sources in the Resource Server is carried out the song classification according to label, generate the song recommendations tabulation according to song label classification; Said song similarity classification is specially: carry out the song classification according to the base attribute of song, calculate the similarity of song in each song classification respectively, carry out song recommendations according to the size of song similarity; Wherein, the base attribute of said song comprises issuing date, singer's sex, audio frequency and the lyrics.
4. the method for music recommend according to claim 2; It is characterized in that; In said steps d; The classification of said heat song seniority among brothers and sisters is specially: generate popular song seniority among brothers and sisters Qu Ku through the rank of calculating a series of popular songs, and generate popular song recommendations Qu Ku according to certain weight and array mode; The classification of said correlation rule is specially: adopt association algorithm to calculate the correlation rule of user behavior record, and correlation rule integrated calculate corresponding related song recommendations tabulation.
5. the method for music recommend according to claim 2 is characterized in that, in said steps d; The classification of said user clustering is specially: the behavior record according to the user hives off to the user, calculates in each group user's song and obtains seniority among brothers and sisters, and calculate the similarity between the user in each group; With the similarity is weight; Gather in each group the song of similar users and obtain seniority among brothers and sisters, delete download song, generate the song recommendations tabulation; Said collaborative filtering classification is specially: calculate the similarity between each user, generate the song recommendations tabulation according to user's similarity.
6. according to the method for the described music recommend of claim 1 to 5, it is characterized in that said steps d also comprises: music recommend information is sent to page server, and the user obtains corresponding music sources through music recommend information.
7. the system of a music recommend; Comprise portable terminal and page server; Said portable terminal is used for the page data that accession page server browsing pages information is obtained needs, and said page server is used for user's browsing pages information, the page data that selection need be obtained; It is characterized in that; Also comprise log server, Resource Server and data mining server, said log server is used for the behavior of recording user accession page server, and behavior record is sent to data mining server; Said Resource Server is used to deposit music sources; And the obtain behavior of recording user on Resource Server and the music sources information of obtaining; And will obtain behavior and the music sources information obtained sends to data mining server, said data mining server is used to store user's behavior record and music sources information, according to behavior record the user is classified; According to the song mode classification song is classified, and generate corresponding song recommendations tabulation according to different user types.
8. the system of music recommend according to claim 7; It is characterized in that; Said data mining server also comprises database and music recommend module; Said database is used to store behavior, the download behavior of user on Resource Server and the music sources information of obtaining of user to access pages server, and according to canned data the user is classified; Said music recommend module is used for according to different song mode classifications song being classified; Generate corresponding song recommendations tabulation according to the different user types in the database; And recommendation information returned to page server, the user through recommendation information to the corresponding music sources of Resource Server acquisition request.
9. the system of music recommend according to claim 8; It is characterized in that; Said music recommend module also comprises song taxon, song similarity unit and heat song seniority among brothers and sisters unit; Said song taxon is carried out the song classification with the music sources in the Resource Server according to label, generates the song recommendations tabulation according to song label classification; Said song similarity unit is used for carrying out the song classification according to the base attribute of song, calculates the similarity of song in each song classification respectively, according to the size generation song recommendations tabulation of song similarity; Said heat song seniority among brothers and sisters unit generates popular song seniority among brothers and sisters Qu Ku through the rank of calculating a series of popular songs, and generates popular song recommendations Qu Ku according to certain weight and array mode.
10. the system of music recommend according to claim 8; It is characterized in that; Said music recommend module also comprises correlation rule unit, user clustering unit and collaborative filtering unit; Said correlation rule unit is used to adopt association algorithm to calculate the correlation rule of user behavior record, and correlation rule integrated calculates corresponding related song recommendations tabulation; Said user clustering unit is used for according to user's behavior record the user being hived off; Calculate in each group user's song and obtain seniority among brothers and sisters; And calculate the similarity between the user in each group, and be weight with the similarity, gather in each group the song of similar users and obtain seniority among brothers and sisters; Delete download song, generate the song recommendations tabulation; Said collaborative filtering unit is used to calculate the similarity between each user, generates the song recommendations tabulation according to user's similarity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011104483534A CN102402625A (en) | 2011-12-28 | 2011-12-28 | Method and system for recommending music |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011104483534A CN102402625A (en) | 2011-12-28 | 2011-12-28 | Method and system for recommending music |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102402625A true CN102402625A (en) | 2012-04-04 |
Family
ID=45884825
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011104483534A Pending CN102402625A (en) | 2011-12-28 | 2011-12-28 | Method and system for recommending music |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102402625A (en) |
Cited By (56)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103023971A (en) * | 2012-11-15 | 2013-04-03 | 广州酷狗计算机科技有限公司 | Information pushing method and system of music sharing radio stations |
CN103327107A (en) * | 2013-06-27 | 2013-09-25 | 苏州创智宏云信息科技有限公司 | Information push method for music sharing radio stations |
CN103427926A (en) * | 2012-05-17 | 2013-12-04 | 上海闻泰电子科技有限公司 | Method for achieving mobile phone terminal network radio |
CN103544407A (en) * | 2012-07-11 | 2014-01-29 | 中国科学院声学研究所 | Method and system for constructing copyright content similarity graph of peer-to-peer network |
CN103605656A (en) * | 2013-09-30 | 2014-02-26 | 小米科技有限责任公司 | Music recommendation method and device and mobile terminal |
CN103632303A (en) * | 2012-08-21 | 2014-03-12 | 北京友友天宇系统技术有限公司 | A magnetic object network service method with multiple attribute associations and a system |
CN103853778A (en) * | 2012-12-04 | 2014-06-11 | 大陆汽车投资(上海)有限公司 | Methods for updating music label information and pushing music, as well as corresponding device and system |
CN103885987A (en) * | 2012-12-21 | 2014-06-25 | 中国移动通信集团公司 | Music recommendation method and system |
CN103970754A (en) * | 2013-01-28 | 2014-08-06 | 腾讯科技(深圳)有限公司 | Automatic article selection method and device |
CN103970858A (en) * | 2014-05-07 | 2014-08-06 | 百度在线网络技术(北京)有限公司 | Recommended content determining system and method |
CN103995839A (en) * | 2014-04-30 | 2014-08-20 | 兴天通讯技术(天津)有限公司 | Commodity recommendation optimizing method and system based on collaborative filtering |
CN104331407A (en) * | 2013-12-26 | 2015-02-04 | 乐视网信息技术(北京)股份有限公司 | Multimedia file information recommending method and multimedia file information recommending device |
CN104408051A (en) * | 2014-10-28 | 2015-03-11 | 广州酷狗计算机科技有限公司 | Song recommendation method and device |
CN104584060A (en) * | 2012-06-25 | 2015-04-29 | 搜诺思公司 | Collecting and providing local playback system information |
CN104573105A (en) * | 2015-01-30 | 2015-04-29 | 福州大学 | Method of recommending hit songs and singers in music on-demand network |
CN104599702A (en) * | 2014-11-28 | 2015-05-06 | 深圳市金立通信设备有限公司 | Music playing method |
CN104636448A (en) * | 2015-01-23 | 2015-05-20 | 广东欧珀移动通信有限公司 | Music recommendation 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 |
CN104899302A (en) * | 2015-06-10 | 2015-09-09 | 百度在线网络技术(北京)有限公司 | Method and device for recommending music to user |
CN104951485A (en) * | 2014-09-02 | 2015-09-30 | 腾讯科技(深圳)有限公司 | Music file data processing method and music file data processing device |
CN105138696A (en) * | 2015-09-24 | 2015-12-09 | 深圳市冠旭电子有限公司 | Method and device for pushing music |
CN105354293A (en) * | 2015-11-02 | 2016-02-24 | 海信集团有限公司 | Assisted implementation method and apparatus for pushing playing object in mobile terminal |
CN105588287A (en) * | 2016-02-25 | 2016-05-18 | 四川长虹电器股份有限公司 | Control method and system of intelligent music air conditioner |
CN105592225A (en) * | 2016-01-11 | 2016-05-18 | 广东欧珀移动通信有限公司 | Method and system for setting alarm ringtone of mobile terminal |
CN105824818A (en) * | 2015-01-04 | 2016-08-03 | 中国移动通信集团河北有限公司 | Informationized management method, platform and system |
CN105930429A (en) * | 2016-04-19 | 2016-09-07 | 乐视控股(北京)有限公司 | Music recommendation method and apparatus |
CN105955938A (en) * | 2016-04-25 | 2016-09-21 | 广州酷狗计算机科技有限公司 | Method and device for editing lyrics |
CN106294426A (en) * | 2015-05-26 | 2017-01-04 | 徐维靖 | Content of joke provides web station system |
CN106294851A (en) * | 2016-08-22 | 2017-01-04 | 腾讯科技(深圳)有限公司 | A kind of data processing method and server |
CN106462623A (en) * | 2014-06-06 | 2017-02-22 | 谷歌公司 | Content item usage based song recommendation |
WO2017067156A1 (en) * | 2015-10-21 | 2017-04-27 | 广州酷狗计算机科技有限公司 | Playlist list determining method, device, electronic device and storage medium |
CN106951527A (en) * | 2017-03-21 | 2017-07-14 | 北京邮电大学 | A kind of song recommendations method and device |
CN107133232A (en) * | 2016-02-29 | 2017-09-05 | 惠州华阳通用电子有限公司 | A kind of vehicle-mounted Online Music recommends method and device |
CN107194754A (en) * | 2017-04-11 | 2017-09-22 | 美林数据技术股份有限公司 | Stock trader's Products Show method based on mixing collaborative filtering |
CN107220365A (en) * | 2017-06-07 | 2017-09-29 | 四川大学 | Accurate commending system and method based on collaborative filtering and correlation rule parallel processing |
WO2017173571A1 (en) * | 2016-04-05 | 2017-10-12 | 张阳 | Theater music control method and system |
CN107885745A (en) * | 2016-09-29 | 2018-04-06 | 亿览在线网络技术(北京)有限公司 | A kind of song recommendations method and device |
CN107918614A (en) * | 2016-10-08 | 2018-04-17 | 北京小唱科技有限公司 | A kind of recommendation method and server for singing accompaniment |
CN107967280A (en) * | 2016-10-19 | 2018-04-27 | 北京酷我科技有限公司 | A kind of method and system of label recommendations song |
CN108205533A (en) * | 2016-12-16 | 2018-06-26 | 北京酷我科技有限公司 | A kind of song recommendations method and system based on user collaborative |
CN108304441A (en) * | 2017-11-14 | 2018-07-20 | 腾讯科技(深圳)有限公司 | Network resource recommended method, device, electronic equipment, server and storage medium |
CN108399269A (en) * | 2018-03-31 | 2018-08-14 | 丁超 | Music recommends method, apparatus and computer storage media |
CN108549675A (en) * | 2018-03-31 | 2018-09-18 | 陈振奎 | A kind of Piano Teaching method based on big data and neural network |
CN108628886A (en) * | 2017-03-20 | 2018-10-09 | 中移(杭州)信息技术有限公司 | A kind of audio file recommendation method and device |
US10289621B2 (en) | 2014-05-28 | 2019-05-14 | Xiaomi Inc. | Method and apparatus for recommending multimedia resource |
CN109960763A (en) * | 2019-03-21 | 2019-07-02 | 湖南大学 | A kind of photography community personalization friend recommendation method based on user's fine granularity photography preference |
CN109982155A (en) * | 2019-03-25 | 2019-07-05 | 北京奇艺世纪科技有限公司 | One kind broadcasting single recommended method and system |
CN110297939A (en) * | 2019-06-21 | 2019-10-01 | 山东科技大学 | A kind of music personalization system of fusion user behavior and cultural metadata |
CN110704672A (en) * | 2019-09-29 | 2020-01-17 | 广州酷狗计算机科技有限公司 | Method and device for recommending accompaniment audio, computer equipment and storage medium |
CN112307250A (en) * | 2020-11-10 | 2021-02-02 | 珠海格力电器股份有限公司 | Music recommendation and play control method and equipment |
CN112612917A (en) * | 2020-12-30 | 2021-04-06 | 北京梧桐车联科技有限责任公司 | Song recommendation method, device, equipment and storage medium |
CN112765396A (en) * | 2021-01-28 | 2021-05-07 | 北京字节跳动网络技术有限公司 | Song recommendation method and device, electronic equipment and storage medium |
CN112860988A (en) * | 2021-01-18 | 2021-05-28 | 中国联合网络通信集团有限公司 | Service product recommendation method and device |
CN113010790A (en) * | 2021-03-30 | 2021-06-22 | 广州酷狗计算机科技有限公司 | Content recommendation method, device, server and storage medium |
CN113626539A (en) * | 2021-08-13 | 2021-11-09 | 深圳墨世科技有限公司 | User behavior data statistical method, server and client |
CN113832656A (en) * | 2020-06-08 | 2021-12-24 | 云米互联科技(广东)有限公司 | Washing control method of washing machine, washing machine and computer readable storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101901450A (en) * | 2010-07-14 | 2010-12-01 | 中兴通讯股份有限公司 | Media content recommendation method and media content recommendation system |
CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术(北京)有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
-
2011
- 2011-12-28 CN CN2011104483534A patent/CN102402625A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101901450A (en) * | 2010-07-14 | 2010-12-01 | 中兴通讯股份有限公司 | Media content recommendation method and media content recommendation system |
CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术(北京)有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
Cited By (86)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103427926A (en) * | 2012-05-17 | 2013-12-04 | 上海闻泰电子科技有限公司 | Method for achieving mobile phone terminal network radio |
CN104584060A (en) * | 2012-06-25 | 2015-04-29 | 搜诺思公司 | Collecting and providing local playback system information |
US11109157B2 (en) | 2012-06-25 | 2021-08-31 | Sonos, Inc. | Providing aggregate playback information |
CN104584060B (en) * | 2012-06-25 | 2018-05-22 | 搜诺思公司 | It collects and local playback system information is provided |
US10462569B2 (en) | 2012-06-25 | 2019-10-29 | Sonos, Inc. | Providing aggregate playback information |
CN103544407B (en) * | 2012-07-11 | 2016-08-03 | 中国科学院声学研究所 | The construction method of a kind of copyright content similarity graph of peer-to-peer network and system |
CN103544407A (en) * | 2012-07-11 | 2014-01-29 | 中国科学院声学研究所 | Method and system for constructing copyright content similarity graph of peer-to-peer network |
CN103632303A (en) * | 2012-08-21 | 2014-03-12 | 北京友友天宇系统技术有限公司 | A magnetic object network service method with multiple attribute associations and a system |
CN103023971A (en) * | 2012-11-15 | 2013-04-03 | 广州酷狗计算机科技有限公司 | Information pushing method and system of music sharing radio stations |
CN103023971B (en) * | 2012-11-15 | 2015-09-09 | 广州酷狗计算机科技有限公司 | The information-pushing method in music sharing radio station and system thereof |
CN103853778A (en) * | 2012-12-04 | 2014-06-11 | 大陆汽车投资(上海)有限公司 | Methods for updating music label information and pushing music, as well as corresponding device and system |
CN103885987B (en) * | 2012-12-21 | 2018-04-10 | 中国移动通信集团公司 | A kind of music recommends method and system |
CN103885987A (en) * | 2012-12-21 | 2014-06-25 | 中国移动通信集团公司 | Music recommendation method and system |
CN103970754A (en) * | 2013-01-28 | 2014-08-06 | 腾讯科技(深圳)有限公司 | Automatic article selection method and device |
CN103970754B (en) * | 2013-01-28 | 2018-05-18 | 腾讯科技(深圳)有限公司 | The automatically selecting method and device of article |
CN103327107A (en) * | 2013-06-27 | 2013-09-25 | 苏州创智宏云信息科技有限公司 | Information push method for music sharing radio stations |
CN103605656A (en) * | 2013-09-30 | 2014-02-26 | 小米科技有限责任公司 | Music recommendation method and device and mobile terminal |
CN104331407A (en) * | 2013-12-26 | 2015-02-04 | 乐视网信息技术(北京)股份有限公司 | Multimedia file information recommending method and multimedia file information recommending device |
CN103995839A (en) * | 2014-04-30 | 2014-08-20 | 兴天通讯技术(天津)有限公司 | Commodity recommendation optimizing method and system based on collaborative filtering |
CN103970858A (en) * | 2014-05-07 | 2014-08-06 | 百度在线网络技术(北京)有限公司 | Recommended content determining system and method |
US10289621B2 (en) | 2014-05-28 | 2019-05-14 | Xiaomi Inc. | Method and apparatus for recommending multimedia resource |
CN106462623A (en) * | 2014-06-06 | 2017-02-22 | 谷歌公司 | Content item usage based song recommendation |
CN104951485A (en) * | 2014-09-02 | 2015-09-30 | 腾讯科技(深圳)有限公司 | Music file data processing method and music file data processing device |
CN104408051B (en) * | 2014-10-28 | 2019-04-09 | 广州酷狗计算机科技有限公司 | Song recommendations method and device |
CN104408051A (en) * | 2014-10-28 | 2015-03-11 | 广州酷狗计算机科技有限公司 | Song recommendation method and device |
CN104599702A (en) * | 2014-11-28 | 2015-05-06 | 深圳市金立通信设备有限公司 | Music playing method |
CN105824818A (en) * | 2015-01-04 | 2016-08-03 | 中国移动通信集团河北有限公司 | Informationized management method, platform and system |
US10885107B2 (en) | 2015-01-23 | 2021-01-05 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Music recommendation method and apparatus |
CN104636448A (en) * | 2015-01-23 | 2015-05-20 | 广东欧珀移动通信有限公司 | Music recommendation method and device |
CN104636448B (en) * | 2015-01-23 | 2018-01-23 | 广东欧珀移动通信有限公司 | A kind of music recommends method and device |
CN104573105A (en) * | 2015-01-30 | 2015-04-29 | 福州大学 | Method of recommending hit songs and singers in music on-demand network |
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 |
CN104731954B (en) * | 2015-04-01 | 2018-01-26 | 天翼爱音乐文化科技有限公司 | Music is had an X-rayed based on group and recommends method and system |
CN106294426A (en) * | 2015-05-26 | 2017-01-04 | 徐维靖 | Content of joke provides web station system |
CN104899302A (en) * | 2015-06-10 | 2015-09-09 | 百度在线网络技术(北京)有限公司 | Method and device for recommending music to user |
CN104899302B (en) * | 2015-06-10 | 2018-07-17 | 百度在线网络技术(北京)有限公司 | Recommend the method and apparatus of music to user |
CN105138696A (en) * | 2015-09-24 | 2015-12-09 | 深圳市冠旭电子有限公司 | Method and device for pushing music |
CN105138696B (en) * | 2015-09-24 | 2019-11-19 | 深圳市冠旭电子股份有限公司 | A kind of music method for pushing and device |
CN106610968A (en) * | 2015-10-21 | 2017-05-03 | 广州酷狗计算机科技有限公司 | Song menu list determination method and apparatus, and electronic device |
WO2017067156A1 (en) * | 2015-10-21 | 2017-04-27 | 广州酷狗计算机科技有限公司 | Playlist list determining method, device, electronic device and storage medium |
US10846332B2 (en) | 2015-10-21 | 2020-11-24 | Guangzhou Kugou Computer Technology Co., Ltd. | Playlist list determining method and device, electronic apparatus, and storage medium |
CN106610968B (en) * | 2015-10-21 | 2020-09-04 | 广州酷狗计算机科技有限公司 | Method and device for determining song list and electronic equipment |
CN105354293A (en) * | 2015-11-02 | 2016-02-24 | 海信集团有限公司 | Assisted implementation method and apparatus for pushing playing object in mobile terminal |
CN105592225A (en) * | 2016-01-11 | 2016-05-18 | 广东欧珀移动通信有限公司 | Method and system for setting alarm ringtone of mobile terminal |
CN105592225B (en) * | 2016-01-11 | 2019-06-28 | Oppo广东移动通信有限公司 | The method and system of mobile terminal quarter-bell the tinkle of bells is set |
CN105588287B (en) * | 2016-02-25 | 2018-08-14 | 四川长虹电器股份有限公司 | The control method and system of intelligent music air-conditioning |
CN105588287A (en) * | 2016-02-25 | 2016-05-18 | 四川长虹电器股份有限公司 | Control method and system of intelligent music air conditioner |
CN107133232A (en) * | 2016-02-29 | 2017-09-05 | 惠州华阳通用电子有限公司 | A kind of vehicle-mounted Online Music recommends method and device |
WO2017173571A1 (en) * | 2016-04-05 | 2017-10-12 | 张阳 | Theater music control method and system |
CN105930429A (en) * | 2016-04-19 | 2016-09-07 | 乐视控股(北京)有限公司 | Music recommendation method and apparatus |
CN105955938A (en) * | 2016-04-25 | 2016-09-21 | 广州酷狗计算机科技有限公司 | Method and device for editing lyrics |
CN106294851A (en) * | 2016-08-22 | 2017-01-04 | 腾讯科技(深圳)有限公司 | A kind of data processing method and server |
CN106294851B (en) * | 2016-08-22 | 2021-04-27 | 腾讯科技(深圳)有限公司 | Data processing method and server |
CN107885745A (en) * | 2016-09-29 | 2018-04-06 | 亿览在线网络技术(北京)有限公司 | A kind of song recommendations method and device |
CN107885745B (en) * | 2016-09-29 | 2020-09-08 | 亿览在线网络技术(北京)有限公司 | Song recommendation method and device |
CN107918614A (en) * | 2016-10-08 | 2018-04-17 | 北京小唱科技有限公司 | A kind of recommendation method and server for singing accompaniment |
CN107967280B (en) * | 2016-10-19 | 2020-06-12 | 北京酷我科技有限公司 | Method and system for recommending songs by tag |
CN107967280A (en) * | 2016-10-19 | 2018-04-27 | 北京酷我科技有限公司 | A kind of method and system of label recommendations song |
CN108205533A (en) * | 2016-12-16 | 2018-06-26 | 北京酷我科技有限公司 | A kind of song recommendations method and system based on user collaborative |
CN108628886A (en) * | 2017-03-20 | 2018-10-09 | 中移(杭州)信息技术有限公司 | A kind of audio file recommendation method and device |
CN106951527A (en) * | 2017-03-21 | 2017-07-14 | 北京邮电大学 | A kind of song recommendations method and device |
CN106951527B (en) * | 2017-03-21 | 2020-01-17 | 北京邮电大学 | Song recommendation method and device |
CN107194754A (en) * | 2017-04-11 | 2017-09-22 | 美林数据技术股份有限公司 | Stock trader's Products Show method based on mixing collaborative filtering |
CN107220365A (en) * | 2017-06-07 | 2017-09-29 | 四川大学 | Accurate commending system and method based on collaborative filtering and correlation rule parallel processing |
CN107220365B (en) * | 2017-06-07 | 2020-10-23 | 四川大学 | Accurate recommendation system and method based on collaborative filtering and association rule parallel processing |
CN108304441A (en) * | 2017-11-14 | 2018-07-20 | 腾讯科技(深圳)有限公司 | Network resource recommended method, device, electronic equipment, server and storage medium |
CN108304441B (en) * | 2017-11-14 | 2022-04-26 | 腾讯科技(深圳)有限公司 | Network resource recommendation method and device, electronic equipment, server and storage medium |
CN108399269A (en) * | 2018-03-31 | 2018-08-14 | 丁超 | Music recommends method, apparatus and computer storage media |
CN108549675B (en) * | 2018-03-31 | 2021-09-24 | 河南理工大学 | Piano teaching method based on big data and neural network |
CN108549675A (en) * | 2018-03-31 | 2018-09-18 | 陈振奎 | A kind of Piano Teaching method based on big data and neural network |
CN109960763B (en) * | 2019-03-21 | 2020-12-22 | 湖南大学 | Photography community personalized friend recommendation method based on user fine-grained photography preference |
CN109960763A (en) * | 2019-03-21 | 2019-07-02 | 湖南大学 | A kind of photography community personalization friend recommendation method based on user's fine granularity photography preference |
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 |
CN109982155A (en) * | 2019-03-25 | 2019-07-05 | 北京奇艺世纪科技有限公司 | One kind broadcasting single recommended method and system |
CN110297939A (en) * | 2019-06-21 | 2019-10-01 | 山东科技大学 | A kind of music personalization system of fusion user behavior and cultural metadata |
CN110704672A (en) * | 2019-09-29 | 2020-01-17 | 广州酷狗计算机科技有限公司 | Method and device for recommending accompaniment audio, computer equipment and storage medium |
CN113832656A (en) * | 2020-06-08 | 2021-12-24 | 云米互联科技(广东)有限公司 | Washing control method of washing machine, washing machine and computer readable storage medium |
CN113832656B (en) * | 2020-06-08 | 2023-11-03 | 云米互联科技(广东)有限公司 | Washing control method of washing machine, washing machine and computer readable storage medium |
CN112307250A (en) * | 2020-11-10 | 2021-02-02 | 珠海格力电器股份有限公司 | Music recommendation and play control method and equipment |
CN112612917A (en) * | 2020-12-30 | 2021-04-06 | 北京梧桐车联科技有限责任公司 | Song recommendation method, device, equipment and storage medium |
CN112612917B (en) * | 2020-12-30 | 2024-04-12 | 北京梧桐车联科技有限责任公司 | Song recommendation method, device, equipment and storage medium |
CN112860988A (en) * | 2021-01-18 | 2021-05-28 | 中国联合网络通信集团有限公司 | Service product recommendation method and device |
CN112860988B (en) * | 2021-01-18 | 2023-06-16 | 中国联合网络通信集团有限公司 | Service product recommendation method and device |
CN112765396A (en) * | 2021-01-28 | 2021-05-07 | 北京字节跳动网络技术有限公司 | Song recommendation method and device, electronic equipment and storage medium |
CN113010790A (en) * | 2021-03-30 | 2021-06-22 | 广州酷狗计算机科技有限公司 | Content recommendation method, device, server and storage medium |
CN113626539A (en) * | 2021-08-13 | 2021-11-09 | 深圳墨世科技有限公司 | User behavior data statistical method, server and client |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102402625A (en) | Method and system for recommending music | |
US11853354B2 (en) | Override of automatically shared meta-data of media | |
US10949482B2 (en) | User profile based on clustering tiered descriptors | |
US10546006B2 (en) | Method and system for hybrid information query | |
US9626443B2 (en) | Searching and accessing application functionality | |
CN101464881B (en) | Method and system for generating media recommendations in a distributed environment based on tagging play history information with location information | |
US8572169B2 (en) | System, apparatus and method for discovery of music within a social network | |
CN102073699B (en) | For improving the method for Search Results, device and equipment based on user behavior | |
US20130325838A1 (en) | Method and system for presenting query results | |
CN110059249B (en) | Personalized recommendation method, terminal device and system | |
US20160148262A1 (en) | Providing Additional Functionality as Advertisements with Search Results | |
CN102970326B (en) | A kind of method and apparatus of the mood indication information for sharing users | |
TW201447797A (en) | Method and system for multi-phase ranking for content personalization | |
CN104156390A (en) | Comment recommendation method and system | |
CN102982042A (en) | Personalization content recommendation method and platform and system | |
WO2009126815A2 (en) | Diversified, self-organizing map system and method | |
CN107885745A (en) | A kind of song recommendations method and device | |
TW201229790A (en) | Information providing method and device | |
CN108648010A (en) | Method, system and respective media for providing a user content | |
US20130325897A1 (en) | System and methods for providing content | |
US20160034957A1 (en) | Generating Advertisements for Search Results Associated With Entities Based on Aggregated Entity Bids | |
CN104077707B (en) | A kind of optimization method and device for promoting presentation mode | |
WO2015110845A1 (en) | Autocreated campaigns for hashtag keywords | |
US20160328752A1 (en) | Native creative generation using hashtagged user generated content | |
US9430572B2 (en) | Method and system for user profiling via mapping third party interests to a universal interest space |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120404 |