Abstract:
Systems, device and techniques are disclosed for rating a multiplayer videogame active player based on the retention of one or more qualifying players after their interaction with the active player. An interaction event between an active player and a qualifying player may be detected and a retention value based on the qualifying player returning to the multiplayer videogame may be determined. The active player may be rated based at least on the retention value of the qualifying player.
Abstract:
A video clip may be automatically generated from a gameplay recording based on an interest metric. The interest metric may be determined from a variety of sources, such as developer provided signals, platform-based signals, and reception signal. A machine learning technique may be applied to each of the signals individually and/or in aggregate (e.g., the interest metric) to ascertain a weighting scheme, for example, for each individual signal or the interest metric to improve the selection of portions of video from a gameplay recording.
Abstract:
A player model for a video game is generated based on inputs received from users who have played past versions of the game. The player model can be used to simulate user actions in a new version of the video game and make predictions about average user session length, average earnings per session, number of games played per day, etc. More than one player model may be generated for a game. Each player model for a game may represent one or more features, such as a user skill level, for a group of users.
Abstract:
Systems, device and techniques are disclosed for receiving content based on a subscription to channel by a user. An indication of a user subscription, by a user, may be received. The subscription may be for a channel associated with a channel manager for the channel. An indication of a content to be provided via the channel may be received from the channel manager for the channel. A determination may be made that the content value associated with the content is below an available user subscription value. The content may be automatically provided to the user, based on the determination and the content value may be deducted from the available subscription value.
Abstract:
The present disclosure allows for automatic detection of an entity referenced in a video and presentation of a purchasable item associated with the identified entity to a user viewing the video. A method may include evaluating a video using one or more entity analysis techniques and identifying an entity associated with the video based on the evaluation. Next, one or more purchasable items associated with the entity may be identified. A first purchasable item may be selected from among the one or more purchasable items based on a user history associated with a user and the selected first purchasable item may be presented to the user during playback of the video.
Abstract:
A player model for a video game is generated based on inputs received from users who have played past versions of the game. The player model can be used to simulate user actions in a new version of the video game and make predictions about average user session length, average earnings per session, number of games played per day, etc. More than one player model may be generated for a game. Each player model for a game may represent one or more features, such as a user skill level, for a group of users.
Abstract:
A video clip may be automatically generated from a gameplay recording based on an interest metric. The interest metric may be determined from a variety of sources, such as developer provided signals, platform-based signals, and reception signal. A machine learning technique may be applied to each of the signals individually and/or in aggregate (e.g., the interest metric) to ascertain a weighting scheme, for example, for each individual signal or the interest metric to improve the selection of portions of video from a gameplay recording.