CN103092854A - Music data sorting method - Google Patents
Music data sorting method Download PDFInfo
- Publication number
- CN103092854A CN103092854A CN2011103382790A CN201110338279A CN103092854A CN 103092854 A CN103092854 A CN 103092854A CN 2011103382790 A CN2011103382790 A CN 2011103382790A CN 201110338279 A CN201110338279 A CN 201110338279A CN 103092854 A CN103092854 A CN 103092854A
- Authority
- CN
- China
- Prior art keywords
- music data
- music
- unit
- classified
- sorting technique
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention provides a music data sorting method. The method includes: dividing music data into a plurality of rhythm units according to a time unit, obtaining a music property corresponding to each rhythm unit, endowing a time value for every rhythm unit according to the time unit; establishing a coordinate system to reflect the corresponding correlation between time values of the rhythm units and the music properties, mapping the plurality of rhythm units of the music data with a plurality coordinate points on the coordinate system one by one; sequentially linking the coordinate points according to the time values to obtain a polygon chain; extracting characteristics of the polygon chain, and sorting the music data according to the characteristics of the polygon chain. According to above mode, the music data sorting method is simple in algorithm, low operand, and capable of quickly sorting a large amount of music data.
Description
Technical field
The present invention relates to the music data processing technology field, particularly relate to a kind of music data sorting technique.
Background technology
The data volume that is stored at present the multi-medium data in computer system increases day by day, and how discovery information, information extraction from these data becomes more and more difficult; Simultaneously, the appearance of new multimedia data type has brought challenge also for traditional data base management system (DBMS).Traditional multimedia class and search method are normally based on the manual implementation method of textual description.The descriptor of these Textualities is enough for the data of some multimedia type, but said method when the sound data file such as processing music, can bring inaccurate or even misleading result usually with stronger subjectivity.
Current up-to-date Intelligentized method adopts the characteristic information that extracts from music data, and unartificial textual description, removed the artificial participation in the music assorting process, whole process is realized by operation robotization, intelligentized audio music data classification algorithm by computing machine.This key point and difficult point wherein is feature extraction, and it comprises two problems: what feature extract and how to extract.And the shortcoming of music data sorting technique of the prior art is the algorithm complexity, and calculated amount is large, is difficult for realizing.
Therefore, need to provide a kind of music data sorting technique, to address the above problem.
Summary of the invention
The technical matters that the present invention mainly solves is to provide a kind of music data sorting technique, can carry out Fast Classification to the magnanimity music data.
For solving the problems of the technologies described above, the technical scheme that the present invention adopts is: a kind of music data sorting technique is provided, it comprises the following steps: a. becomes a plurality of beats unit with music data by a time dividing elements, and obtaining each music attribute corresponding to beat unit, each beat unit is that unit gives a time value according to time quantum; B. set up a coordinate system, the time value of coordinate system reflection beat unit and the corresponding relation between music attribute, and a plurality of beats unit of music data and a plurality of coordinate points on coordinate system are shone upon one by one; C. a plurality of coordinate points are carried out line successively according to time value, to obtain a polygonal chain; D. extract the feature of polygonal chain, and according to the feature of polygonal chain, music data is classified.
Wherein, in step a, time quantum is the duration of minimum beat in music data.
Wherein, in step b, coordinate is an x-y plane right-angle coordinate, and wherein, the unit of x axle is time quantum, and the unit of y axle is music attribute, and music attribute comprises pitch, loudness of a sound or tone color one or a combination set of.
Wherein, when the linear module of music attribute is pitch, also comprise in step b: obtain the pitch of a plurality of beats unit, be mapped to one by one on the x-y plane right-angle coordinate with the beat unit with music data.
Wherein, in steps d, the feature of polygonal chain comprises: time or the maximum saltus step of polygonal chain on the y axle that the minimum y value of time, polygonal chain that the maximum y value of polygonal chain is kept is kept.
Wherein, in steps d, further choose the sorting parameter of the feature composition of one or more polygonal chains, and according to sorting parameter, music data is classified.
Wherein, sorting technique is further comprising the steps: f. obtains classified music data sample, and the music data sample is carried out sort operation by step a to d; E. obtain the sorting parameter of music data sample according to sort operation; G. obtain non-classified music data, non-classified music data is carried out sort operation by step a to steps d, and according to sorting parameter, non-classified music data is classified.
The invention has the beneficial effects as follows: the situation that is different from prior art, a kind of music data sorting technique of the present invention, by music data is become a plurality of beats unit by a time dividing elements, set up a coordinate system according to time quantum and music attribute, to obtain a polygonal chain, and according to the feature of polygonal chain, music data is classified, have advantages of that algorithm is simple, operand is less, and can carry out Fast Classification to the magnanimity music data.
Description of drawings
Fig. 1 is the process flow diagram of a preferred embodiment of a kind of music data sorting technique of the present invention; And
Fig. 2 is the time quantum of a kind of music data sorting technique according to the present invention and the schematic diagram of the x-y plane right-angle coordinate that music attribute is set up.
Embodiment
See also Fig. 1 to Fig. 2, Fig. 1 is the schematic block diagram of a preferred embodiment of a kind of music data sorting technique of the present invention, and Fig. 2 is the time quantum of a kind of music data sorting technique according to the present invention and the schematic diagram of the x-y plane right-angle coordinate that music attribute is set up.As shown in Figure 1, a kind of music data sorting technique of the present invention comprises the following steps:
Step 101: music data is become a plurality of beats unit by a time dividing elements, and obtain each music attribute corresponding to beat unit, each beat unit is that unit gives a time value according to time quantum;
Step 102: set up a coordinate system, the time value of coordinate system reflection beat unit and the corresponding relation between music attribute, and a plurality of beats unit of music data and a plurality of coordinate points on coordinate system are shone upon one by one;
Step 103: a plurality of coordinate points are carried out line successively according to time value, to obtain a polygonal chain;
Step 104: extract the feature of polygonal chain, and according to the feature of polygonal chain, music data is classified.
In step 101, time quantum is the duration of minimum beat in music data, wherein, when the magnanimity music data is classified, this time quantum be one regular time value, time value is for choosing the duration of minimum beat from the magnanimity music data.
In step 102, set up an x-y plane right-angle coordinate according to time quantum and music attribute.Wherein, music attribute comprises pitch, loudness of a sound or tone color one or a combination set of, and the physical parameter of sound comprises acoustic pressure, time-histories and frequency spectrum, and in music, acoustic pressure will determine intensity or the sensation of loudness of music, and frequency spectrum determines the tone color of music.Pitch is called tone on acoustics, determined by the fundamental frequency in frequency spectrum.In the present embodiment, the unit of the x axle of x-y plane right-angle coordinate is time quantum, and the unit of y axle is music attribute, and wherein the linear module of music attribute is pitch.In other embodiments, those skilled in the art's linear module of music attribute fully is set to tone color or loudness of a sound, to set up an x-y plane right-angle coordinate.
In step 102, further obtain the pitch of a plurality of beats unit, be mapped to one by one on the x-y plane right-angle coordinate with the beat unit with music data.
In step 104, the feature of polygonal chain comprises: time or the maximum saltus step of polygonal chain on the y axle that the minimum y value of time, polygonal chain that the maximum y value of polygonal chain is kept is kept, as shown in Figure 2, the time that the maximum y value of polygonal chain is kept is lines 201, the time that the minimum y value of polygonal chain is kept is lines 202, and the maximum saltus step of polygonal chain on the y axle is lines 203.Wherein, select the feature of above-mentioned or two or more polygonal chains to form sorting parameter, and according to sorting parameter, the magnanimity music data is classified.
Below further describe the music data sorting technique that the present invention discloses.
At first, obtain the music data sample of having classified, this music data sample is carried out sort operation by step 101 to 104.Subsequently, obtain the sorting parameter of music data sample according to the sort operation of music data sample, and carry out related with the music type of music data sample the sorting parameter of music data sample.Subsequently, obtain non-classified music data, non-classified music data is carried out sort operation by step 101 to step 104.Subsequently, obtain its sorting parameter according to the sort operation of non-classified music data, and the sorting parameter of non-classified music data and the sorting parameter of music data sample are compared, so that non-classified music data is classified.
In sum, a kind of music data sorting technique of the present invention, by music data is become a plurality of beats unit by a time dividing elements, set up a coordinate system according to time quantum and music attribute, to obtain a polygonal chain, and according to the feature of polygonal chain, music data is classified, have advantages of that algorithm is simple, operand is less, and can carry out Fast Classification to the magnanimity music data.
The above is only embodiments of the invention; not thereby limit the scope of the claims of the present invention; every equivalent structure or equivalent flow process conversion that utilizes instructions of the present invention and accompanying drawing content to do; or directly or indirectly be used in other relevant technical fields, all in like manner be included in scope of patent protection of the present invention.
Claims (7)
1. a music data sorting technique, is characterized in that, described sorting technique comprises the following steps:
A. described music data is become a plurality of beats unit by a time dividing elements, and obtain each music attribute corresponding to described beat unit, each described beat unit is that unit gives a time value according to described time quantum;
B. set up a coordinate system, the described time value of the described coordinate system described beat of reflection unit and the corresponding relation between described music attribute, and a plurality of described beat unit of described music data and a plurality of coordinate points on described coordinate system are shone upon one by one;
C. a plurality of described coordinate points are carried out line successively according to described time value, to obtain a polygonal chain;
D. extract the feature of described polygonal chain, and according to the feature of described polygonal chain, described music data is classified.
2. music data sorting technique according to claim 1, is characterized in that, in step a, described time quantum is the duration of minimum beat in described music data.
3. music data sorting technique according to claim 2, it is characterized in that, in step b, described coordinate is an x-y plane right-angle coordinate, wherein, the unit of described x axle is described time quantum, and the unit of described y axle is described music attribute, and the linear module of described music attribute comprises pitch, loudness of a sound or tone color one or a combination set of.
4. music data sorting technique according to claim 3, it is characterized in that, when the linear module of described music attribute is pitch, also comprise in step b: obtain the pitch of a plurality of described beats unit, be mapped to one by one on described x-y plane right-angle coordinate with the described beat unit with described music data.
5. music data sorting technique according to claim 3, it is characterized in that, in steps d, the feature of described polygonal chain comprises: time or the maximum saltus step of described polygonal chain on the y axle that the minimum y value of time, described polygonal chain that the maximum y value of described polygonal chain is kept is kept.
6. music data sorting technique according to claim 5, is characterized in that, in steps d, further chooses the sorting parameter of the feature composition of one or more described polygonal chains, and according to described sorting parameter, described music data is classified.
7. music data sorting technique according to claim 1, is characterized in that, described sorting technique is further comprising the steps:
F. obtain classified music data sample, described music data sample is carried out sort operation by step a to d;
E. obtain the sorting parameter of described music data sample according to described sort operation;
G. obtain non-classified music data, described non-classified music data is carried out sort operation by step a to steps d, and according to described sorting parameter, described non-classified music data is classified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110338279.0A CN103092854B (en) | 2011-10-31 | 2011-10-31 | Music data sorting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110338279.0A CN103092854B (en) | 2011-10-31 | 2011-10-31 | Music data sorting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103092854A true CN103092854A (en) | 2013-05-08 |
| CN103092854B CN103092854B (en) | 2017-02-08 |
Family
ID=48205437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110338279.0A Active CN103092854B (en) | 2011-10-31 | 2011-10-31 | Music data sorting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103092854B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105843931A (en) * | 2016-03-30 | 2016-08-10 | 广州酷狗计算机科技有限公司 | Classification method and device |
| CN113515209A (en) * | 2020-11-26 | 2021-10-19 | 腾讯科技（深圳）有限公司 | Music screening method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1698095A (en) * | 2003-03-06 | 2005-11-16 | 索尼株式会社 | Information detection device, method, and program |
| CN1720517A (en) * | 2002-11-28 | 2006-01-11 | 新加坡科技研究局 | Summarizing digital audio data |
| CN1777891A (en) * | 2003-04-24 | 2006-05-24 | 皇家飞利浦电子股份有限公司 | Parameterized temporal feature analysis |
| US20100058186A1 (en) * | 2008-08-28 | 2010-03-04 | Sony Corporation | Reproducing apparatus and reproducing method |
-
2011
- 2011-10-31 CN CN201110338279.0A patent/CN103092854B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1720517A (en) * | 2002-11-28 | 2006-01-11 | 新加坡科技研究局 | Summarizing digital audio data |
| CN1698095A (en) * | 2003-03-06 | 2005-11-16 | 索尼株式会社 | Information detection device, method, and program |
| CN1777891A (en) * | 2003-04-24 | 2006-05-24 | 皇家飞利浦电子股份有限公司 | Parameterized temporal feature analysis |
| US20100058186A1 (en) * | 2008-08-28 | 2010-03-04 | Sony Corporation | Reproducing apparatus and reproducing method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105843931A (en) * | 2016-03-30 | 2016-08-10 | 广州酷狗计算机科技有限公司 | Classification method and device |
| CN113515209A (en) * | 2020-11-26 | 2021-10-19 | 腾讯科技（深圳）有限公司 | Music screening method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103092854B (en) | 2017-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103902698B (en) | A kind of data-storage system and storage method | |
| CN102779249B (en) | Malware detection methods and scanning engine | |
| US20150207704A1 (en) | Public opinion information display system and method | |
| US8316041B1 (en) | Generation and processing of numerical identifiers | |
| CN105138515A (en) | Named entity recognition method and device | |
| CN109299258A (en) | A kind of public sentiment event detecting method, device and equipment | |
| CN101980211A (en) | Machine learning model and establishing method thereof | |
| CN102650995A (en) | Multi-dimensional data analyzing model generating system and method | |
| CN105550253B (en) | Method and device for acquiring type relationship | |
| CN110188217A (en) | Image duplicate checking method, apparatus, equipment and computer-readable storage media | |
| CN108335010A (en) | A kind of wind power output time series modeling method and system | |
| CN107748739A (en) | A kind of extracting method and relevant apparatus of short message text masterplate | |
| CN101963972A (en) | Method and system for extracting emotional keywords | |
| CN105244041A (en) | Song audition evaluation method and device | |
| CN103150409B (en) | Method and system for recommending user search word | |
| CN103092854A (en) | Music data sorting method | |
| CN106651513A (en) | Quoting method and apparatus for circuit board order | |
| CN106844743B (en) | Emotion classification method and device for Uygur language text | |
| CN109299312B (en) | Music rhythm analysis method based on big data | |
| CN103186672B (en) | file ordering method and device thereof | |
| CN111008285A (en) | Author disambiguation method based on thesis key attribute network | |
| US20220335070A1 (en) | Method and apparatus for querying writing material, and storage medium | |
| CN105608201A (en) | Text matching method supporting multi-keyword expression | |
| KR20120109763A (en) | Apparatus and method for analyzing information of polyphonic sound source using neural computer | |
| CN106443182B (en) | A kind of method that test item Electromagnetic Launching amplitude spectrum data based on spectrum signature are classified |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201118 Address after: 226600 Industrial Concentration Zone of Qutang Town, Haian City, Nantong City, Jiangsu Province (Liuwei Village) Patentee after: Jiangsu Fanyu Machinery Technology Co., Ltd Address before: 518057, No. 9 software building, central high tech Zone, Nanshan District hi tech Zone, Guangdong, Shenzhen Patentee before: KUANG-CHI INSTITUTE OF ADVANCED TECHNOLOGY |