Google Inc.

Johan Georg Granstrom

Luca Chiarandini

Oliver Heckmann

Gang Ji

Tristan Schmelcher

Nicola Muscettola

Thomas Weich

Matthias Rochus Konrad

Roman Vorushin

Alexander Pak

Stephane Zermatten

Marius Vlad

Iakov Dlugach

Holger Brandsmeier

Todd Gage

Methods and systems of determining competition for search queries on a video hosting system on a computer network are provided. Search records associated with search queries directed to the video hosting system are received. Each search record identifies videos available on the video hosting system that are search results for a corresponding search query and indicates associated view durations that the videos were viewed responsive to the search query. Search queries directed to a first and second videos and associated view durations that the first video was watched in response to the queries are identified from the received search records. A competition score indicating an amount of competition between the first and second videos for views of users of the video hosting system is calculated based on the identified search queries and associated view durations.

Video competition discovery and recommendation

A method, system, and computer program instructions detect and score video channels based on content reuse. Matches between two videos occur when one video reuses a segment of video or audio content from another video. A video graph stores information about videos, channels the videos belong to, and their matches with other videos. Channels are given similarity scores based on their similarity to a video, channel, or group of channels. Similarity scores are calculated using information about video matches from the video graph.

Detecting channel similarity based on content reuse

Methods and systems of providing metadata association with videos on a video hosting system on a computer network are provided. Search records associated with search queries directed to the video hosting system are received. Each search record identifies videos that are search results for a search query and indicates view durations that the videos were viewed responsive to the search query. First and second videos competing for views of users are identified from the received search records. The first and second videos each have metadata respectively describing the first and second videos. Search queries directed to the first video are identified from the search records. Search terms associated with the search queries are further identified and compared to the metadata of the second video. Search terms that are not included in the metadata of the second video are identified as metadata improvements to the second video.

Video metadata association recommendation

Systems and methods for identifying duplicate media items in a media system are provided. In particular, media content can be uploaded to a serve. The media content can be fingerprinted. A digest is generated based on the fingerprint. The digest is indexed and potential matching media items are identified. Matches are determined from the potential matching media items.

Real-time duplicate detection of videos in a massive video sharing system

A method for promoting preferred content in a search query is disclosed. The method includes obtaining a search result set of content items from a corpus of content items, the search result set responsive to a search query and comprising a rank of the content items, identifying content items in the search result set, the identified content items comprising at least a preferred content item uploaded by a user, adjusting, by a processing device, a position of the preferred content item with respect to a position of a claimed content item in the rank of the content items within the search result set, the claimed content item claimed by the user.

Promoting preferred content in a search query

An access policy module automatically applies an access policy to a video. Access policies frequently require manual review of an item to determine a proper access policy for the video, such as whether the video should be taken down, age-limited, or permitted general access. Results of a manual review of a video are stored along with the portion of the video that was manually reviewed and the access policy applied to the video. When a trigger event occurs indicating access policies should be considered for a video, the video is compared to reviewed portions of videos that were manually reviewed to determine if an access policy can be automatically applied with sufficient confidence. When insufficient confidence is reached or conflicting access policies both have high confidence, the video is scheduled for manual review with a priority level based on the possible access level of the video.

Automated application of manually reviewed videos using matching

Systems and methods are disclosed for identifying unauthorized presentation of protected content by one or more participants in a media collaboration. In one implementation, a processing device receives one or more content elements, each of the one or more content elements being provided within a media collaboration and associated with one or more users. The processing device identifies an unauthorized presentation of at least one of the one or more content elements within the media collaboration. Based on an identification of the unauthorized presentation, the processing device initiates one or more actions with respect to one or more of the users associated with the at least one of the one or more content elements.

Growing community of inventors

Kilchberg, Switzerland

Johan Georg Granstrom