Streaming media service rate prediction method and device

A technology of service rate and prediction method, which is applied in the field of streaming media and can solve problems such as inaccurate prediction results

CN106454437AActive Publication Date: 2017-02-22CHINA MOBILE GROUP DESIGN INST
1 Cites 17 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2017-02-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The present invention discloses a streaming media service rate prediction method and device. According to the scheme of the present invention, the service rate influence data of the previous data sampling time period of the current moment can be obtained, the obtained service rate influence data is inputted to a set least squares support vector machine (LS-SVM) rate prediction model to obtain the service prediction rate of the next data sampling time period of the current moment, and the corresponding streaming media data is generated according to the service prediction rate, wherein the LS-SVM rate prediction model is obtained by training multiple sets of sample data within the previous set time period of the current moment according to a set LS-SVM rate prediction algorithm, so that the service rate prediction accuracy is improved, the code rate of the generated streaming media matches a current network rate more accurately, and the problems, such as the video lag, the network bandwidth waste, etc., are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of streaming media, in particular to a streaming media service rate prediction method and device. Background technique

[0002] With the rapid development of mobile communication technology and mobile terminal technology, users urgently need to be able to receive Internet information and services anytime, anywhere while moving. Moreover, with the continuous improvement of mobile network performance and terminal processing capabilities, users have more requirements for multimedia services such as high-quality video and audio. On this basis, the streaming media transmission service based on the HLS (HTTP Living Streaming) protocol came into being. The streaming media transmission service based on the HLS protocol can better adapt to the existing network, provide users with a near real-time playback experience, and is widely used in scenarios such as video on demand and live broadcast.

[0003] Specifically, ...

Examples

Embodiment 1

[0024] Embodiment 1 of the present invention provides a streaming media service rate prediction method. The streaming media service rate prediction method is applicable to a streaming media transmission service system based on the HLS protocol, which is not limited in this embodiment of the present invention. Specifically, such as figure 1 As shown, it is a schematic flow chart of the streaming media service rate prediction method in Embodiment 1 of the present invention, and the streaming media service rate prediction method may include the following steps:

[0025] Step 101: Obtain service rate impact data of the previous data sampling time period at the current moment.

[0026] Optionally, the service rate impact data may include: service data transmission success rate, service data retransmission rate, service data out-of-sequence rate, service drop times, service average rate, and the like.

[0027] Among them, the specific meaning of each service rate impact data can be...

Embodiment 2

[0117] Based on the same inventive concept, Embodiment 2 of the present invention provides a streaming media service rate prediction device. The streaming media service rate prediction device may be a network side device such as a video server, which is not limited in this embodiment of the present invention; in addition, It should be noted that, for the specific implementation of the streaming media service rate prediction device, refer to the relevant description in the first method embodiment above, and the repetition will not be repeated, as shown in Figure 4 As shown, the streaming media service rate prediction device may include:

[0118] The training unit 41 can be used to train multiple sets of sample data in the previous set period of time according to the set LS-SVM rate prediction algorithm to obtain the LS-SVM rate prediction model, wherein each set of samples The data includes the actual service rate of the first data sampling time period, and the service rate im...