18238788. SYSTEMS AND METHODS THAT MATCH SEARCH QUERIES TO TELEVISION SUBTITLES simplified abstract (Google LLC)

From WikiPatents
Jump to navigation Jump to search

SYSTEMS AND METHODS THAT MATCH SEARCH QUERIES TO TELEVISION SUBTITLES

Organization Name

Google LLC

Inventor(s)

Zbigniew Skolicki of Krakow (PL)

Yaroslav Volovich of Cambridge (GB)

Ant Oztaskent of London (GB)

Varun Rajgarhia of London (GB)

SYSTEMS AND METHODS THAT MATCH SEARCH QUERIES TO TELEVISION SUBTITLES - A simplified explanation of the abstract

This abstract first appeared for US patent application 18238788 titled 'SYSTEMS AND METHODS THAT MATCH SEARCH QUERIES TO TELEVISION SUBTITLES

Simplified Explanation

The patent application describes a process that identifies a sudden increase in search queries submitted by users within a short period of time. This increase is considered a "spike" and is associated with a set of equivalent queries. The frequency of these queries during the spike is higher than the average frequency during a normal period of time. The process then correlates this spike to a video program by matching terms from the search queries to subtitles in the video program that appeared shortly before the spike. When a user expresses interest in the video program, the process sends search results related to the search queries from the spike to the user's device.

  • The process identifies a sudden increase in search queries within a short period of time.
  • The increase in queries is associated with a set of equivalent queries.
  • The frequency of these queries during the spike is higher than the average frequency during a normal period of time.
  • The process matches terms from the search queries to subtitles in a video program that aired shortly before the spike.
  • When a user shows interest in the video program, the process sends search results related to the search queries from the spike to the user's device.

Potential Applications

  • Content recommendation systems for video streaming platforms.
  • Real-time analysis of user search behavior for targeted advertising.
  • Identifying popular topics or trends based on search query spikes.

Problems Solved

  • Efficiently correlating search query spikes to specific video programs.
  • Providing relevant search results to users based on their interests.
  • Improving user engagement and satisfaction by delivering personalized content.

Benefits

  • Enhanced user experience by offering search results related to their interests.
  • Improved content discovery by linking search queries to relevant video programs.
  • Increased user engagement and retention through personalized recommendations.


Original Abstract Submitted

A process identifies a search query spike from queries submitted by users during a first span of time, which is less than a predefined duration. The spike corresponds to a set of queries identified as equivalent. The frequency of submitting queries from the set during the first time span exceeds the frequency of submitting queries from the set during an average span of time. The process correlates the spike to a broadcast video program by matching terms from the set of search queries to subtitle terms appearing in the video program at a first location. The first location in the video program was broadcast within a predefined time before the first span of time. The process receives notification from a user device indicating user interest in the video program. The process transmits to the user device search results corresponding to some search queries from the set of search queries.