Identifying an end of a television program

A system to identify an end of a television program, comprising:

• at least one processor;
• memory;
• and
• at least one program stored in the memory and executable by the at least one processor, the at least one program comprising instructions for:
• periodically obtaining subtitles for a plurality of television programs during respective predetermined time intervals proximate to and including respective times when respective television programs in the plurality of television programs are scheduled to end;
• identifying sequences of strings from the subtitles for the plurality of television programs that satisfy predefined criteria associated with the plurality of television programs, wherein the predefined criteria include a threshold percentage of the plurality of television programs in which any of the sequences occurs at the end of the programs;
• and
• updating an aggregation of subtitles indicating that a television program in the plurality of television programs has ended, with the identified sequences of strings.

A non-transitory computer readable storage medium storing at least one program configured for execution by at least one processor of a computing device, the at least one program comprising instructions for:

• periodically obtaining subtitles for a plurality of television programs during respective predetermined time intervals proximate to and including respective times when respective television programs in the plurality of television programs are scheduled to end;
• identifying sequences of strings from the subtitles for the plurality of television programs that satisfy predefined criteria associated with the plurality of television programs, wherein the predefined criteria include a threshold percentage of the plurality of television programs in which any of the sequences occurs at the end of the programs;
• and
• updating an aggregation of subtitles indicating that a television program in the plurality of television programs has ended, with the identified sequences of strings.