Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method and device for constructing an online real-time update massive audio fingerprint library

An audio fingerprint, real-time update technology, applied in audio data retrieval, audio data indexing, instruments and other directions, can solve the problem of inconvenient online real-time update of massive audio fingerprint database, to ensure data timeliness, improve overall performance, and achieve response Effect

Active Publication Date: 2019-03-15
高第网络技术(北京)有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] To this end, the present invention provides a method and device for constructing an online real-time update audio fingerprint library, which solves the technical problem that the massive audio fingerprint library in the prior art is inconvenient for online real-time update

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and device for constructing an online real-time update massive audio fingerprint library
  • A method and device for constructing an online real-time update massive audio fingerprint library
  • A method and device for constructing an online real-time update massive audio fingerprint library

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Without loss of generality, as figure 2 As shown, in order to solve the technical problem of inconvenient online real-time update of massive audio fingerprint databases in the prior art, the present invention provides a method for constructing online real-time update audio fingerprint databases, including:

[0042] S1000. Establishing a corresponding relationship between audio fingerprints and key values ​​having the same key value;

[0043] S2000. Establish an index list containing each key value and its corresponding audio fingerprint, so that each key value in the index list points to its corresponding audio fingerprint in the form of a pointer; and

[0044] S3000. Continuously store the audio fingerprints with the same key value.

[0045] Although the same song will have multiple audio fingerprints, and each audio fingerprint will have a key value, the same key value will appear repeatedly in many different songs in the prior art; There will be multiple audio fin...

Embodiment 2

[0049] Preferably, the above-mentioned index list of the present invention is realized by establishing multiple arrays arranged in sequence, and then, as Figure 4 As shown, step S1000 further includes:

[0050] S1100: Divide audio fingerprints with the same key value into the same array.

[0051] For example: as shown in Figure: 5: the key 1 with value 1 and value 4 Divide into the first array and the rest in order.

[0052] Further, such as Figure 6 As shown, in step S2000, establishing an index list comprising each key value and its corresponding audio fingerprint further includes:

[0053] S2100: Make the index list include arrays whose number is the same as the number of key values.

[0054] Such as Figure 5 As shown: there are as many corresponding arrays as there are keys, and keys in different arrays may correspond to multiple audio fingerprints (values) at the same time.

Embodiment 3

[0056] Preferably, since the number of audio files that need to be added online in the prior art is usually a lot, each audio file usually contains several key values, and each key value corresponds to an audio fingerprint, but there are often many audio fingerprints in these audio fingerprints. Audio fingerprints have the same key value, so if Figure 7 Shown, the present invention further comprises the steps:

[0057] S4000: Add audio fingerprint online.

[0058] Further, such as Figure 8 As shown, step S4000 includes:

[0059] S4100: Group the audio fingerprints to be added according to their corresponding key values, and the audio fingerprints to be added in each group have the same corresponding key value, which is convenient for positioning and supplementary addition in the index list according to the corresponding key values ​​of each group in the next step Audio fingerprints, adding audio fingerprints in groups can greatly increase the speed of adding, and further ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a method and device for constructing an online real-time update audio fingerprint database, which solves the technical problem in the prior art that a massive audio fingerprint database is inconvenient for online real-time update. Wherein, the method for constructing online real-time update audio fingerprint database includes: establishing the corresponding relationship between the audio fingerprint with the same key value and the key value; establishing an index list comprising each key value and its corresponding audio fingerprint, so that the index list Each key value points to its corresponding audio fingerprint in the form of a pointer; and the audio fingerprints with the same key value are stored continuously. The present invention enables the online service engine to support real-time addition and deletion of song fingerprints without affecting the search service, avoiding the tedious and time-consuming work caused by offline database building and restarting services, and at the same time ensuring the data of a massive audio fingerprint database Timeliness, realizing the second-level data update demand response capability.

Description

technical field [0001] The invention relates to the technical field of audio fingerprint identification, in particular to a method and device for constructing an online real-time update massive audio fingerprint database. Background technique [0002] Audio fingerprint recognition (commonly known as "listening to music") is an emerging music search technology. This technology extracts digital features called "audio fingerprints" by analyzing the frequency spectrum of audio files, and uses digital features to construct "massive audio fingerprints". Library", deployed on the network server, the client can send the recorded unknown audio clips to the server, the server uses the same algorithm to extract the "audio fingerprint", and then uses the search algorithm to find similar features in the massive audio fingerprint library, and based on the found Several features of the target audio file are speculated, and the result is returned to the client to complete the entire recogni...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/61
CPCG06F21/32G06F21/6272G06F16/2386G06F16/2255G06F16/61
Inventor 王磊
Owner 高第网络技术(北京)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products