Methods for identifying audio or video content

摘要

The present disclosure relates to analyzing user uploaded visual or audio content. One method comprises: generating fingerprint data from user uploaded visual or audio content, the user uploaded visual or audio content having been uploaded by a user to a first party's online video service for distribution from the first party's online video service to the public; identifying plural items of reference content, from a universe of reference content, that are a possible match of the user uploaded visual or audio content, said identifying being based on the fingerprint data and being performed by a computer system configured to perform such act; assessing a score for each of the identified plural items of reference content, each score indicating a likely correspondence of the user uploaded visual or audio content with a respective item of reference content; for items in the plural items of reference content that fall within a predetermined score range, queuing for review by a second party, different than the first party, the user uploaded visual or audio content item and data associated with the items in the plural items of reference content that fall within a predetermined score range; receiving assessment data from the second party, the assessment data indicating a result of a subjective comparison of the user uploaded visual or audio content and the items in the plural items of reference content that fall within a predetermined score range; using the assessment data and a score assessed in said act of assessing in concluding that at least one item in the identified plural items of reference content corresponds with the user uploaded visual or audio content; and limiting distribution of the user uploaded visual or audio content from the first party's online video service to the public based on the concluding. Of course other methods and combinations are disclosed as well.

主权项

1. A method comprising:
generating fingerprint data from user uploaded visual or audio content, the user uploaded visual or audio content having been uploaded by a user to a first party's online video service for distribution from the first party's online video service to the public; identifying plural items of reference content, from a universe of reference content, that are a possible match of the user uploaded visual or audio content, said identifying being based on the fingerprint data and being performed by a computer system configured to perform such act; assessing a score for each of the identified plural items of reference content, each score indicating a likely correspondence of the user uploaded visual or audio content with a respective item of reference content; for items in the plural items of reference content that fall within a predetermined score range, queuing for review by a second party, different than the first party, the user uploaded visual or audio content item and data associated with the items in the plural items of reference content that fall within a predetermined score range; receiving assessment data from the second party, the assessment data indicating a result of a subjective comparison of the user uploaded visual or audio content and the items in the plural items of reference content that fall within a predetermined score range; using the assessment data and a score assessed in said act of assessing in concluding that at least one item in the identified plural items of reference content corresponds with the user uploaded visual or audio content; and limiting distribution of the user uploaded visual or audio content from the first party's online video service to the public based on the concluding.