Novel audio-visual program advertisement broadcasting method
A delivery method and advertising delivery technology, applied in the field of video labeling, can solve the problems of fast processing, large amount of calculation, and complexity on the unfavorable player side, and achieve the effect of rich content, low calculation amount, and accurate matching.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0019] Embodiment one, such as figure 1 As shown, a novel audio-visual program advertisement delivery method includes:
[0020] Step 1, monitor and analyze the output of the audio broadcasting device;
[0021] Step 2, calculate the voice hash value in real time;
[0022] Step 3: Compare the voice hash value with the voice hash value of the audio-visual program in the advertisement annotation library, find the corresponding advertisement content, and display it on the screen.
[0023] The technology of the present invention has very low calculation amount, no complicated calculation, accurately matches the labeling information according to the corresponding relationship between the hash feature of the video file and the labeling content information of the video file, and is convenient for playing. When a user uses a playback device, regardless of the player used, as long as the sound output is turned on, the content-related advertisement can be loaded.
[0024] The present i...
Embodiment 2
[0025] Embodiment two, such as Image 6 As shown, on the basis of Embodiment 1, more preferably, the first step is to monitor and analyze the output of the audio broadcasting device; specifically, it includes recording the sound samples of the audio broadcasting device for a period of time, and normalizing them into a same Frequency of sound samples. Normalizing to a sound sample of the same frequency facilitates analysis of sound samples.
[0026] More optimally, it is normalized to a sound sample of the same frequency, the optimal sound sample is 8000HZ. Calculate the zero-crossing rate and perform matching at a lower sampling frequency. These subtle changes have little effect on matching.
[0027] More preferably, the second step is to calculate the voice hash value in real time; specifically, it includes calculating the one-way zero-crossing voice hash value of the sound samples in the past t time. In the oscillogram of voice data, the horizontal axis is the 0 axis, and...
PUM

Abstract
Description
Claims
Application Information

- R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com