Audio-based personalized recommendation method and device and mobile terminal

An audio and audio recognition technology, applied in special data processing applications, instruments, biological neural network models, etc., can solve the problems of low recommendation success rate and failure to consider the characteristics of the anchor's voice

Active Publication Date: 2019-04-02
GUANGZHOU LIZHI NETWORK TECH CO LTD
View PDF12 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention discloses an audio-based personalized recommendation method, device and mobile terminal to solve the problem that the recommendation process does not consider the voice characteristics of the anchor, resulting in a low recommendation success rate

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
  • Audio-based personalized recommendation method and device and mobile terminal
  • Audio-based personalized recommendation method and device and mobile terminal
  • Audio-based personalized recommendation method and device and mobile terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] refer to figure 1 , which shows a flow chart of the steps of an audio-based personalized recommendation method according to the present invention, which may specifically include the following steps:

[0086] Step 101, train an audio recognition model according to the audio sample set, and the audio recognition model is obtained by cascading a convolutional neural network and a cyclic neural network.

[0087] Among them, the audio sample set is several pre-marked audio samples, and each audio sample is marked as a positive sample or a negative sample or a reference sample. The positive sample and the reference sample have the same characteristics, and the negative sample and the reference sample have different characteristics.

[0088] In the embodiment of the present invention, the training of the audio recognition model is the training of the convolutional neural network and the cyclic neural network. By continuously adjusting the parameters of the convolutional neural...

Embodiment 2

[0104] refer to figure 2 , which shows a flow chart of steps of another audio-based personalized recommendation method of the present invention, which may specifically include the following steps:

[0105] Step 201, respectively input the mel spectral coefficients of the reference sample, positive sample, and negative sample into the convolutional neural network to obtain a first feature vector.

[0106] In an embodiment of the present invention, the audio sample set includes: a reference sample, a positive sample, and a negative sample, wherein the reference sample is a standard sample, the audio features of the positive sample and the reference sample are similar, and the audio features of the negative sample and the reference sample are not similar.

[0107] Among them, the convolutional neural network may include one or more convolutional units, so that the sample is input to the first convolutional unit, and the output of the first convolutional unit is the input of the ...

Embodiment 3

[0175] refer to image 3 , which shows a structural block diagram of an audio-based personalized recommendation device according to the present invention, which may specifically include the following modules:

[0176] The audio recognition model training module 301 is used to train the audio recognition model according to the audio sample set, and the audio recognition model is obtained by cascading a convolutional neural network and a cyclic neural network.

[0177] The target audio feature acquisition module 302 is configured to acquire target audio features of the target user.

[0178] A target audio vector prediction module 303, configured to input the target audio feature into the audio recognition model to obtain a target audio vector.

[0179] A target object acquiring module 304, configured to acquire the target object from the candidate object list according to the target audio vector.

[0180] A target object recommending module 305, configured to recommend the tar...

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 embodiment of the invention provides an audio-based personalized recommendation method and device and a mobile terminal, and the method comprises the steps: training an audio recognition model according to an audio sample set, and enabling the audio recognition model to be obtained through the cascade connection of a convolutional neural network and a recurrent neural network; acquiring a target audio feature of the target user; inputting the target audio feature into the audio recognition model to obtain a target audio vector; obtaining a target object from a candidate object list according to the target audio vector; and recommending the target object to the target user. According to the invention, the target audio vector (sound feature) can be obtained through the audio recognitionmodel to recommend the sound liked by the user to the user, which is helpful for improving the success rate of recommendation.

Description

technical field [0001] The present invention relates to the technical field of audio recognition, in particular to an audio-based personalized recommendation method, device and mobile terminal. Background technique [0002] Radio stations provide information to users through audio. For example, a car radio system can facilitate drivers to obtain road conditions, or music, or other information. In practical applications, it is also possible to make personalized audio recommendations to users, that is, to find anchors similar to the user's favorite anchors from the anchor list. [0003] In the prior art, it is usually possible to perform personalized audio recommendation based on the anchor's basic information, where the basic information includes: anchor's gender, age, program type, and so on. Specifically, at first, obtain the gender, age, and program type of the anchor with more historical listening times from the user's historical listening records as target information; ...

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
IPC IPC(8): G06F16/635G06N3/04
CPCG06N3/045
Inventor 朱玉婷
Owner GUANGZHOU LIZHI NETWORK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap