CN107220330A - Song intelligent search method and system - Google Patents

Song intelligent search method and system Download PDF

Info

Publication number
CN107220330A
CN107220330A CN201710372460.0A CN201710372460A CN107220330A CN 107220330 A CN107220330 A CN 107220330A CN 201710372460 A CN201710372460 A CN 201710372460A CN 107220330 A CN107220330 A CN 107220330A
Authority
CN
China
Prior art keywords
time
user
shaft
song
music
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
Application number
CN201710372460.0A
Other languages
Chinese (zh)
Inventor
王炳文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wanye (tianjin) Technology Co Ltd
Original Assignee
Wanye (tianjin) Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wanye (tianjin) Technology Co Ltd filed Critical Wanye (tianjin) Technology Co Ltd
Priority to CN201710372460.0A priority Critical patent/CN107220330A/en
Publication of CN107220330A publication Critical patent/CN107220330A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/683Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content

Landscapes

  • Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Electrophonic Musical Instruments (AREA)

Abstract

A kind of song intelligent search method, including:S1, the dynamic shaft for being provided for matching song volume level and the time shaft for matching mood and musical time transformation node;S2, in advance in music libraries by all SoundBreeze Clubtunes carry out mood classification;And song volume level and musical time transformation node pretreatment are carried out to SoundBreeze Clubtunes in music libraries;S3, obtain user for time shaft drag operation information;Determined to need the mood and musical time of the SoundBreeze Clubtunes matched in music libraries to change node according to the drag operation information to time shaft;S4, acquisition user determine to select the volume level of fragment in the SoundBreeze Clubtunes in the range of time shaft seclected time according to user for the operation information of dynamic shaft for the operation information of dynamic shaft;The mood categorizing selection frame of fragment is selected in S5, the SoundBreeze Clubtunes in the range of ejection selection time axle seclected time;Obtain the selection information of user;S6, search result is presented to user.

Description

Song intelligent search method and system
Technical field
The present invention relates to song retrieval technical field, more particularly to a kind of song intelligent search method and system.
Background technology
Music has as a kind of important media resource, the retrieval of music for musical database and construction of digital library Very important meaning.Multimedia resource amount is very huge on network, and people need efficient search engine from vast as the open sea Data in find out the music sources of needs.In addition, music retrieval Karaoke retrieval and auxiliary video frequency searching in terms of all There are wide Research Prospects and huge application value.In face of ever-increasing vast resources and high standard of the people to music retrieval Standard, the music retrieval demand based on background music and chanteur's tone color is also continuously increased.Realized using correlation technique for similar The retrieval of music can not only change present manual retrieval's mode, and chanteur can utilize according to oneself sound and style The system retrieval song similar to oneself, can not only save the substantial amounts of time, can obtain more preferable effect, meanwhile, user The song oneself liked can be automatically selected from substantial amounts of chant music storehouse, individualized music retrieval is met and services.
At present, the search method for song is divided into two major classes:Method based on text marking and the method based on content.
Practical song retrieval system all employ text based method, such as Baidu music retrieval, nine cruel music at present Net, extort net etc., this method needs first manually to mark the song in library, mark out song title, singer, The features such as categorizing songs, recycle the method for keyword match to be searched.This method has some to be difficult to more in practicality The defect of benefit.First, many features of song are difficult to word accurate description (such as chanteur's sound characteristic, song style, section Play, background music tone color etc.), thus be difficult to be retrieved for these characteristics;Secondly, the accurate performance of retrieval of text matches is very The accuracy of text marking is depended in big degree, and the evaluation of many characteristics (such as categorizing songs, mood) is with very strong Subjectivity, accuracy is difficult to ensure that;3rd, for the similar songs Search Requirement of " looking for song to sing ", text based method mesh It is preceding also to realize.
The content of the invention
In view of this, the present invention proposes a kind of song intelligent search method that can realize the intelligent quick-searching of song and is System.
A kind of song intelligent search method, it comprises the following steps:
S1, be provided for match song volume level dynamic shaft and for match mood and musical time transformation node Time shaft;
S2, in advance in music libraries by all SoundBreeze Clubtunes carry out mood classification;And SoundBreeze Clubtunes in music libraries is carried out Song volume level and musical time transformation node pretreatment;
S3, obtain user for time shaft drag operation information;Need are determined according to the drag operation information to time shaft Mood and musical time the transformation node for the SoundBreeze Clubtunes to be matched in music libraries;
S4, acquisition user determine the time according to user for the operation information of dynamic shaft for the operation information of dynamic shaft The volume level of fragment is selected in SoundBreeze Clubtunes in the range of axle seclected time;
The mood categorizing selection frame of fragment is selected in S5, the SoundBreeze Clubtunes in the range of ejection selection time axle seclected time; Obtain the selection information of user;
S6, node, song volume level are changed according to the selection information combining music time of user carried out from music libraries Matching search;And search result is presented to user.
In song intelligent search method of the present invention, it is provided for matching song volume level in the step S1 Dynamic shaft include:
In dynamic shaft divide represent volume level size it is strong, in, weak three ranks;By obtaining user in dynamic shaft The mode of upper lifting decibel meter determines requirement of the user to snatch of music volume level in the range of the set time.
In song intelligent search method of the present invention, when matching mood and music are provided in the step S1 Between transformation node time shaft include:
User selectes after musical time transformation node on a timeline, when setting default before and after musical time transformation node The long radiation scope for being used to expand search result.
In song intelligent search method of the present invention, the categories of emotions includes 6 kinds of conventional moods, various conventional Include all kinds of music styles and orchestration method in mood.
In song intelligent search method of the present invention, described song intelligent search method is used for movie score;
Also include after the step S6:
Audition button is generated after search result, the music purchasing information of user is obtained after user's audition is complete.
The present invention also provides a kind of song intelligent retrieval system, and it includes such as lower unit:
Dynamic shaft, time shaft dispensing unit, for be provided for match song volume level dynamic shaft and for Change the time shaft of node with mood and musical time;
SoundBreeze Clubtunes pretreatment unit, for all SoundBreeze Clubtunes to be carried out into mood classification in music libraries in advance;And it is right SoundBreeze Clubtunes carries out song volume level and musical time transformation node pretreatment in music libraries;
Time shaft dispensing unit, for obtaining drag operation information of the user for time shaft;Dragged according to time shaft Dynamic operation information determines to need the mood and musical time of the SoundBreeze Clubtunes matched in music libraries to change node;
Dynamic shaft dispensing unit, for obtaining operation information of the user for dynamic shaft, according to user for dynamic shaft Operation information determines to select the volume level of fragment in the SoundBreeze Clubtunes in the range of time shaft seclected time;
Mood categorizing selection unit, fragment is selected for ejecting in the SoundBreeze Clubtunes in the range of selection time axle seclected time Mood categorizing selection frame;Obtain the selection information of user;
Music retrieval unit, for changing node, song volume level according to the selection information combining music time of user Matching search is carried out from music libraries;And search result is presented to user.
In song intelligent retrieval system of the present invention, it is provided in the dynamic shaft, time shaft dispensing unit The dynamic shaft of matching song volume level includes:
In dynamic shaft divide represent volume level size it is strong, in, weak three ranks;By obtaining user in dynamic shaft The mode of upper lifting decibel meter determines requirement of the user to snatch of music volume level in the range of the set time.
In song intelligent retrieval system of the present invention, it is provided in the dynamic shaft, time shaft dispensing unit The time shaft of matching mood and musical time transformation node includes:
User selectes after musical time transformation node on a timeline, when setting default before and after musical time transformation node The long radiation scope for being used to expand search result.
In song intelligent retrieval system of the present invention, the categories of emotions includes 6 kinds of conventional moods, various conventional Include all kinds of music styles and orchestration method in mood.
In song intelligent retrieval system of the present invention, described song intelligent search method is used for movie score;
Also include after the music retrieval unit:
Audition button is generated after search result, the music purchasing information of user is obtained after user's audition is complete.
Song intelligent search method and system that the present invention is provided, relative to prior art, can realize is made by selection It is that label carries out intelligent retrieval and obtains the material and by simply paying of dubbing in background music required for user to time, volume and mood Function authorizes to obtain the legal of the music.
Brief description of the drawings
Fig. 1 is the song intelligent retrieval system structured flowchart of the embodiment of the present invention.
Fig. 2 is the use state of the embodiment of the present invention with reference to figure;
Fig. 3 is the dragging dynamic shaft of the embodiment of the present invention and ejects the schematic diagram of choice box;
Fig. 4 is the schematic diagram of the dragging time shaft of the embodiment of the present invention.
Embodiment
As shown in Figures 1 to 4, a kind of song intelligent search method of the embodiment of the present invention, it comprises the following steps:
S1, be provided for match song volume level dynamic shaft and for match mood and musical time transformation node Time shaft;
S2, in advance in music libraries by all SoundBreeze Clubtunes carry out mood classification;And SoundBreeze Clubtunes in music libraries is carried out Song volume level and musical time transformation node pretreatment;
S3, obtain user for time shaft drag operation information;Need are determined according to the drag operation information to time shaft Mood and musical time the transformation node for the SoundBreeze Clubtunes to be matched in music libraries;
S4, acquisition user determine the time according to user for the operation information of dynamic shaft for the operation information of dynamic shaft The volume level of fragment is selected in SoundBreeze Clubtunes in the range of axle seclected time;
The mood categorizing selection frame of fragment is selected in S5, the SoundBreeze Clubtunes in the range of ejection selection time axle seclected time; Obtain the selection information of user;
S6, node, song volume level are changed according to the selection information combining music time of user carried out from music libraries Matching search;And search result is presented to user.
In song intelligent search method of the present invention, it is provided for matching song volume level in the step S1 Dynamic shaft include:
In dynamic shaft divide represent volume level size it is strong, in, weak three ranks;By obtaining user in dynamic shaft The mode of upper lifting decibel meter determines requirement of the user to snatch of music volume level in the range of the set time.
Alternatively, it is strong, in, it is weak can be marked in dynamic shaft, the weak interval of persistent erection can be with equal or difference.
Long block (dynamic shaft in lift decibel meter) of the user in dragging Fig. 2, can pass through color gradient from bottom to top Height in long block and dynamic shaft to user, intuitively point out by volume level.
Alternatively, after mouse up, the choice box of ejection categories of emotions, such as " broad ", " humour is cheerful and light-hearted ", " nervous fierce " etc..After selection, corresponding categories of emotions classification can be shown above corresponding long block.
In song intelligent search method of the present invention, when matching mood and music are provided in the step S1 Between transformation node time shaft include:
User selectes after musical time transformation node on a timeline, when setting default before and after musical time transformation node The long radiation scope for being used to expand search result.
Alternatively, musical time transformation node is selected by dragging the time point on time shaft, the musical time that is connected turns I.e. the width of the time interval long block become between node;The width of different long blocks can be different.
In song intelligent search method of the present invention, the categories of emotions includes 6 kinds of conventional moods, various conventional Include all kinds of music styles and orchestration method in mood.
In song intelligent search method of the present invention, described song intelligent search method is used for movie score;
Also include after the step S6:
Audition button is generated after search result, the music purchasing information of user is obtained after user's audition is complete.
It by implementing the present embodiment, can easily do a film in score, the rhythm of film can be combined, by the difficulty dubbed in background music Degree is substantially reduced.
The present invention also provides a kind of song intelligent retrieval system, and it includes such as lower unit:
Dynamic shaft, time shaft dispensing unit, for be provided for match song volume level dynamic shaft and for Change the time shaft of node with mood and musical time;
SoundBreeze Clubtunes pretreatment unit, for all SoundBreeze Clubtunes to be carried out into mood classification in music libraries in advance;And it is right SoundBreeze Clubtunes carries out song volume level and musical time transformation node pretreatment in music libraries;
Time shaft dispensing unit, for obtaining drag operation information of the user for time shaft;Dragged according to time shaft Dynamic operation information determines to need the mood and musical time of the SoundBreeze Clubtunes matched in music libraries to change node;
Dynamic shaft dispensing unit, for obtaining operation information of the user for dynamic shaft, according to user for dynamic shaft Operation information determines to select the volume level of fragment in the SoundBreeze Clubtunes in the range of time shaft seclected time;
Mood categorizing selection unit, fragment is selected for ejecting in the SoundBreeze Clubtunes in the range of selection time axle seclected time Mood categorizing selection frame;Obtain the selection information of user;
Music retrieval unit, for changing node, song volume level according to the selection information combining music time of user Matching search is carried out from music libraries;And search result is presented to user.
In song intelligent retrieval system of the present invention, it is provided in the dynamic shaft, time shaft dispensing unit The dynamic shaft of matching song volume level includes:
In dynamic shaft divide represent volume level size it is strong, in, weak three ranks;By obtaining user in dynamic shaft The mode of upper lifting decibel meter determines requirement of the user to snatch of music volume level in the range of the set time.
In song intelligent retrieval system of the present invention, it is provided in the dynamic shaft, time shaft dispensing unit The time shaft of matching mood and musical time transformation node includes:
User selectes after musical time transformation node on a timeline, when setting default before and after musical time transformation node The long radiation scope for being used to expand search result.
In song intelligent retrieval system of the present invention, the categories of emotions includes 6 kinds of conventional moods, various conventional Include all kinds of music styles and orchestration method in mood.
In song intelligent retrieval system of the present invention, described song intelligent search method is used for movie score;
Also include after the music retrieval unit:
Audition button is generated after search result, the music purchasing information of user is obtained after user's audition is complete.
Song intelligent search method and system that the present invention is provided, relative to prior art, can realize is made by selection It is that label carries out intelligent retrieval and obtains the material and by simply paying of dubbing in background music required for user to time, volume and mood Function authorizes to obtain the legal of the music.
Hardware, computing device can be directly used with reference to the method or algorithm that the embodiments described herein is described Software module, or the two combination are implemented.Software module can be placed in random access memory, internal memory, read-only storage, electricity can Well known in programming ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field In the storage medium of any other forms.
It is understood that for the person of ordinary skill of the art, can be done with technique according to the invention design Go out other various corresponding changes and deformation, and all these changes and deformation should all belong to the protection model of the claims in the present invention Enclose.

Claims (10)

1. a kind of song intelligent search method, it is characterised in that it comprises the following steps:
S1, be provided for match song volume level dynamic shaft and for match mood and musical time transformation node when Countershaft;
S2, in advance in music libraries by all SoundBreeze Clubtunes carry out mood classification;And song is carried out to SoundBreeze Clubtunes in music libraries Volume level and musical time transformation node pretreatment;
S3, obtain user for time shaft drag operation information;Determined to need according to the drag operation information to time shaft Mood and musical time the transformation node of the SoundBreeze Clubtunes matched in music libraries;
S4, acquisition user determine that time shaft is selected according to user for the operation information of dynamic shaft for the operation information of dynamic shaft The volume level of fragment is selected in SoundBreeze Clubtunes in the range of fixing time;
The mood categorizing selection frame of fragment is selected in S5, the SoundBreeze Clubtunes in the range of ejection selection time axle seclected time;Obtain The selection information of user;
S6, node, song volume level are changed according to the selection information combining music time of user matched from music libraries Search;And search result is presented to user.
2. song intelligent search method as claimed in claim 1, it is characterised in that matching song is provided in the step S1 The dynamic shaft of bent volume level includes:
In dynamic shaft divide represent volume level size it is strong, in, weak three ranks;Above carried in dynamic shaft by obtaining user The mode of decibel meter is drawn to determine requirement of the user to snatch of music volume level in the range of the set time.
3. song intelligent search method as claimed in claim 1, it is characterised in that be provided for matching feelings in the step S1 The time shaft of thread and musical time transformation node includes:
User is selected after musical time transformation node on a timeline, and preset duration is set before and after musical time changes node Radiation scope for expanding search result.
4. song intelligent search method as claimed in claim 1, it is characterised in that the categories of emotions includes 6 kinds of conventional feelings Include all kinds of music styles and orchestration method in thread, various conventional moods.
5. song intelligent search method as claimed in claim 1, it is characterised in that described song intelligent search method is used for Movie score;
Also include after the step S6:
Audition button is generated after search result, the music purchasing information of user is obtained after user's audition is complete.
6. a kind of song intelligent retrieval system, it is characterised in that it includes such as lower unit:
Dynamic shaft, time shaft dispensing unit, for being provided for matching the dynamic shaft of song volume level and for matching feelings Thread and musical time change the time shaft of node;
SoundBreeze Clubtunes pretreatment unit, for all SoundBreeze Clubtunes to be carried out into mood classification in music libraries in advance;And to music SoundBreeze Clubtunes carries out song volume level and musical time transformation node pretreatment in storehouse;
Time shaft dispensing unit, for obtaining drag operation information of the user for time shaft;According to the dragging behaviour to time shaft Making information determines to need the mood and musical time of the SoundBreeze Clubtunes matched in music libraries to change node;
Dynamic shaft dispensing unit, for obtaining operation information of the user for dynamic shaft, according to operation of the user for dynamic shaft Information determines to select the volume level of fragment in the SoundBreeze Clubtunes in the range of time shaft seclected time;
Mood categorizing selection unit, the feelings of fragment are selected for ejecting in the SoundBreeze Clubtunes in the range of selection time axle seclected time Thread categorizing selection frame;Obtain the selection information of user;
Music retrieval unit, for changing node, song volume level from sound according to the selection information combining music time of user Matching search is carried out in music storehouse;And search result is presented to user.
7. song intelligent retrieval system as claimed in claim 6, it is characterised in that the dynamic shaft, time shaft dispensing unit In be provided for match song volume level dynamic shaft include:
In dynamic shaft divide represent volume level size it is strong, in, weak three ranks;Above carried in dynamic shaft by obtaining user The mode of decibel meter is drawn to determine requirement of the user to snatch of music volume level in the range of the set time.
8. song intelligent retrieval system as claimed in claim 6, it is characterised in that the dynamic shaft, time shaft dispensing unit In be provided for match mood and musical time transformation node time shaft include:
User is selected after musical time transformation node on a timeline, and preset duration is set before and after musical time changes node Radiation scope for expanding search result.
9. song intelligent retrieval system as claimed in claim 6, it is characterised in that the categories of emotions includes 6 kinds of conventional feelings Include all kinds of music styles and orchestration method in thread, various conventional moods.
10. song intelligent retrieval system as claimed in claim 6, it is characterised in that described song intelligent search method is used In movie score;
Also include after the music retrieval unit:
Audition button is generated after search result, the music purchasing information of user is obtained after user's audition is complete.
CN201710372460.0A 2017-05-24 2017-05-24 Song intelligent search method and system Pending CN107220330A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710372460.0A CN107220330A (en) 2017-05-24 2017-05-24 Song intelligent search method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710372460.0A CN107220330A (en) 2017-05-24 2017-05-24 Song intelligent search method and system

Publications (1)

Publication Number Publication Date
CN107220330A true CN107220330A (en) 2017-09-29

Family

ID=59944572

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710372460.0A Pending CN107220330A (en) 2017-05-24 2017-05-24 Song intelligent search method and system

Country Status (1)

Country Link
CN (1) CN107220330A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6528715B1 (en) * 2001-10-31 2003-03-04 Hewlett-Packard Company Music search by interactive graphical specification with audio feedback
CN1755686A (en) * 2004-09-30 2006-04-05 株式会社东芝 Music search system and music search apparatus
CN105389356A (en) * 2015-11-04 2016-03-09 上海艺瓣文化传播有限公司 Music database retrieval system based on feature extraction

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6528715B1 (en) * 2001-10-31 2003-03-04 Hewlett-Packard Company Music search by interactive graphical specification with audio feedback
CN1755686A (en) * 2004-09-30 2006-04-05 株式会社东芝 Music search system and music search apparatus
CN105389356A (en) * 2015-11-04 2016-03-09 上海艺瓣文化传播有限公司 Music database retrieval system based on feature extraction

Similar Documents

Publication Publication Date Title
US20120023403A1 (en) System and method for dynamic generation of individualized playlists according to user selection of musical features
US8321456B2 (en) Generating metadata for association with a collection of content items
US8838617B2 (en) Method and apparatus for searching for recommended music using emotional information of music
US8438168B2 (en) Scalable music recommendation by search
Lidy et al. On the suitability of state-of-the-art music information retrieval methods for analyzing, categorizing and accessing non-western and ethnic music collections
KR100890993B1 (en) Intelligent style music information search system and method
Neumayer et al. Playsom and pocketsomplayer, alternative interfaces to large music collections
US20060282789A1 (en) Browsing method and apparatus using metadata
US20100125539A1 (en) Hybrid audio-visual categorization system and method
US7930329B2 (en) System, method and medium browsing media content using meta data
US20080188964A1 (en) Procedure And Apparatus For Generating Automatic Replay Of Recordings
Logan et al. A content-based music similarity function
KR20090033750A (en) Method and apparatus for recommending playlist of contents
Knees et al. Intelligent User Interfaces for Music Discovery.
KR101942459B1 (en) Method and system for generating playlist using sound source content and meta information
Allik et al. Musiclynx: Exploring music through artist similarity graphs
Pachet et al. Popular music access: The Sony music browser
CN107016134A (en) Can Auto-matching song intelligent search method and system
US11960536B2 (en) Methods and systems for organizing music tracks
Schindler Multi-modal music information retrieval: augmenting audio-analysis with visual computing for improved music video analysis
Pachet et al. The cuidado music browser: an end-to-end electronic music distribution system
Herrera et al. SIMAC: Semantic interaction with music audio contents
CN107220330A (en) Song intelligent search method and system
Haus et al. A score‐driven approach to music information retrieval
Sharma et al. Audio songs classification based on music patterns

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170929