Abstract: Techniques for assisting a passenger to identify a vehicle and for assisting a vehicle to identify a passenger are discussed herein. Also discussed herein are techniques for capturing data via sensors on a vehicle or user device and for presenting such data in various formats. For example, in the context of a ride hailing service using autonomous vehicles, the techniques discussed herein can be used to identify a passenger of the autonomous vehicle at the start of a trip, and can be used to assist a passenger to identify an autonomous vehicle that has been dispatched for that particular passenger. Additionally, data captured by sensors of the vehicle and/or by sensors of a user device can be used to initiate a ride, determine a pickup location, orient a user within an environment, and/or provide visualizations or augmented reality elements to provide information and/or enrich a user experience.

Abstract: Techniques for assisting a passenger to identify a vehicle and for assisting a vehicle to identify a passenger are discussed herein. Also discussed herein are techniques for capturing data via sensors on a vehicle or user device and for presenting such data in various formats. For example, in the context of a ride hailing service using autonomous vehicles, the techniques discussed herein can be used to identify a passenger of the autonomous vehicle at the start of a trip, and can be used to assist a passenger to identify an autonomous vehicle that has been dispatched for that particular passenger. Additionally, data captured by sensors of the vehicle and/or by sensors of a user device can be used to initiate a ride, determine a pickup location, orient a user within an environment, and/or provide visualizations or augmented reality elements to provide information and/or enrich a user experience.

Abstract: Techniques for assisting a passenger to identify a vehicle and for assisting a vehicle to identify a passenger are discussed herein. Also discussed herein are techniques for capturing data via sensors on a vehicle or user device and for presenting such data in various formats. For example, in the context of a ride hailing service using autonomous vehicles, the techniques discussed herein can be used to identify a passenger of the autonomous vehicle at the start of a trip, and can be used to assist a passenger to identify an autonomous vehicle that has been dispatched for that particular passenger. Additionally, data captured by sensors of the vehicle and/or by sensors of a user device can be used to initiate a ride, determine a pickup location, orient a user within an environment, and/or provide visualizations or augmented reality elements to provide information and/or enrich a user experience.

Abstract: According to an implementation, an application distribution system may receive a search query from a user and generate indicators of a set of applications based on the search query. The system may determine an influence rating for an entity that provided social media posts associated with one of the applications. The system may determine a sentiment rating for the content of the posts and determine a reliability rating for the entity. The reliability rating may be based the number of posts and the number of the entity's social media relationships. The system may determine an application rating for the application based on the influence rating, the sentiment rating, and the reliability rating. The system may rank the application within a list of the set of applications based on the application rating and provide the list to the device associated with the user.

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: Implementations disclosed herein related to apportioning revenue to a content-creating user if that user's content assisted in the fulfillment of a purchase opportunity. User-generated content may be selected based on criteria, for example, that will likely lead to consummation of a purchase opportunity. Some of the revenue generated from the sale may be sent to the user whose content was associated with the sale. In this way, the user may be encouraged to generate more such content and be rewarded for the advertising the content provided.

Abstract: A method may provide, by a content distribution system, access to interactive content, such as a game, to a group of users and obtain a social media data indicating an interaction level of the users on a social network. The method may determine a content sharing rating for the users based on the social media data and select a user from the group based on the content sharing rating. The method may determine a recommendation for an incentive to be provided to the user within the interactive content, in exchange for the user performing an action to connect the interactive content to the user on a social network, such as by posting a link to the game. The method may provide the recommendation to an administrative system that administers the interactive content, such as the game developer, and that is distinct from the content distribution system.

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 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.

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: Techniques are provided for creating a game-aware compression algorithm for a specific gaming application. A method may include receiving a gaming application and selecting a video compression technique based on the gaming application. A video codec may be created for the gaming application based on the selected video compression technique. The video codec may be provided to a device on which the gaming application is installed. A compressed video of gameplay within the gaming application may be received from the device, and the video of gameplay may have been compressed using the video codec. Additionally, a method may include receiving, from a gaming application provider, a video codec based on a gaming application. A video of gameplay within the gaming application may be recorded. The recorded video of gameplay may be compressed using the video codec and the compressed video of gameplay may be provided to the gaming application provider.

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: 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: Implementations disclosed herein related to apportioning revenue to a content-creating user if that user's content assisted in the fulfillment of a purchase opportunity. User-generated content may be selected based on criteria, for example, that will likely lead to consummation of a purchase opportunity. Some of the revenue generated from the sale may be sent to the user whose content was associated with the sale. In this way, the user may be encouraged to generate more such content and be rewarded for the advertising the content provided.

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.