Determining TV program information based on analysis of audio fingerprints

摘要

A computer-implemented method for clustering audio fingerprints from different set top boxes into groups based on their similarities is disclosed. The computer server receives audio fingerprints generated at different set top boxes and partitions them into multiple groups such that audio fingerprints within a group correspond to a respective TV program being played at the respective set top boxes. Upon receipt of an audio fingerprint from a set top box, the computer server identifies a group of audio fingerprints that are substantially similar to the audio fingerprint, determines TV program information for the audio fingerprint in accordance with the channel metadata associated with the identified group of audio fingerprints, and returns the TV program information to the requesting set top box.

主权项

1. A computer-implemented method, comprising:
at a computer server system including one or more processors and memory:
receiving information associated with TV programs from a plurality of set top boxes, wherein the TV programs have associated audio signals and video signals, wherein the information includes audio fingerprints generated from the audio signals of TV programs captured at the plurality of set top boxes and channel metadata associated with at least a subset of the audio fingerprints, and wherein the information includes a respective video scene transition type for at least a plurality of the audio fingerprints;partitioning the audio fingerprints into multiple groups such that audio fingerprints within a respective group correspond to a same respective TV program and correspond to a same video scene transition type;receiving a query for TV program information from a set top box, wherein the query includes an audio fingerprint and an associated video scene transition type generated at the set top box;comparing the audio fingerprint with the multiple groups of audio fingerprints to identify a group of audio fingerprints whose difference from the audio fingerprint is less than a predefined threshold, wherein the video scene transition type associated with the audio fingerprint matches the video scene transition type corresponding to the identified group of audio fingerprints;identifying a subset of audio fingerprints from the identified group, wherein the subset includes a plurality of audio fingerprints and each audio fingerprint in the identified subset has associated channel metadata received from the set top boxes;determining TV program information for the audio fingerprint based on a consensus among the channel metadata received from the set top boxes for the audio fingerprints in the identified subset; andreturning the TV program information to the requesting set top box.