Audio frequency feature based method and system for marking and identifying broadcast television program
A technology of audio features and program identification, applied in electrical components, image communication, selective content distribution, etc., can solve problems such as infringement of user privacy, inconvenience to viewers, cumbersome operation, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0085] Such as figure 1 As shown, the present invention provides a kind of radio and television program identification and the method for identification based on audio feature, comprises the following steps:
[0086] S1, the server reads P program audio files according to the set rules {W 1 , W 2 ...W P}, for the program audio file W i Execute S1.1-S1.3 to get P program audio feature data packets {Z 1 ,Z 2 ...Z P};
[0087] Setting rules include one or a combination of the following rules:
[0088] Rule 1, the server only reads the program audio files contained in the program bound to the interactive application;
[0089] Rule 2, assuming that the broadcasting time of the program broadcasted by the TV is TA, the server reads the program at the time TB before the broadcasting time TA; wherein, the time interval from the time TB to the time TA is less than the preset value; for example, set The fixed value can be 24 hours. Before a certain program is played, the audio ...
Embodiment 2
[0106] On the basis of Embodiment 1, as a preferred implementation mode, the present invention also provides a method for segmentally matching recorded audio files and program audio files, thereby increasing the probability that recorded audio files are matched to the program audio files to which they belong , specifically, includes the following steps:
[0107](1) For the program audio file W i , perform the following steps:
[0108] program audio file W i Divided into a program audio segment {W with a duration of TW i1 , W i2 ...W ia}, there is overlap between the audio segments of two adjacent programs, and the overlapping duration is TS; taking the start time of the program as the origin, calculate the start time tp of the audio segments of each program, and get {tp i1 , tp i2 ...tp ia}, where the start time tp i2 is the program audio segment W i1 The time interval from the start time of program broadcasting, j ∈ (1, 2...a); program audio feature extraction is per...
Embodiment 3
[0133] The invention also provides a system for identifying and identifying radio and television programs based on audio features, including a server end and a mobile terminal.
[0134] (1) Server side
[0135] The server side includes:
[0136] The reading module is used to read P program audio files {W according to the set rules 1 , W 2 ...W p}; Also used to read the program audio file W i At q playback time points {T 1 ,T 2 ... T q}Respectively associated q interactive applications{Y 1 , Y 2 ...Y q}, wherein, the playback time point T i Apply Y to the interaction it is associated with i The startup time point; wherein, the setting rule according to which the reading module reads is: one or a combination of the following rules: Rule 1, the server only reads the content contained in the program bound to the interactive application Program audio file; rule 2, assuming that the broadcasting time of the program through the TV is TA, then the server reads the program ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com