Abstract: Non-players can vote and comment on uploaded video clips or livestreams of video games played by video game players. The video game players that upload the clips or do the livestreaming and that then receive the most votes can be awarded digital awards. The non-players providing the best comments can also be awarded digital awards. This incentivizes these behaviors, providing ample training data in the process so that the votes and comments can be used to train a model to make inferences related to video game video. For instance, the model may be trained to provide auto-generated comments in real time as a second video game is played, where the comments are in video game domain-specific language.

Abstract: A device, system, and non-transitory computer readable medium for providing a specialized agent comprising an application and a virtual assistant are disclosed. The virtual assistant includes a neural network trained with a machine learning algorithm to emulate a communication style of a character and wherein the virtual assistant is further trained on application metadata to a predict response to questions about the application.

Abstract: Embodiments of the present disclosure may include a method. The method can include detecting a game state corresponding to award of a video game object responsive to completion of a video game event and presenting, on a display device, the video game object. A presentation of the video game object can include data emphasizing one or more features of metrics associated with the game state, wherein the metrics are based on metadata associated with gameplay information and commentary on award of the video game object.

Abstract: Embodiments of the present disclosure may include a method for enhancing a video game trophy, including detecting an end game state to a video game corresponding to award of a trophy. Embodiments may also include extracting metadata relating to a structure of the end game state from gameplay information associated with award of the trophy. Embodiments may also include determining metrics for the end game state from the metadata. Embodiments may also include applying a drama engine to the metrics for the end game state to generate commentary data corresponding to commentary on the award of the trophy.

Abstract: A cloud-based platform significantly lowers the barrier to creating and testing gaming concepts. On the platform, game developers can publish and test a full game, or just a self-contained mission or activity, to allow maximum agility to test and get quick market feedback on a granular discrete set of gaming concepts.

Abstract: Personalized experiences for a user are based on the input patterns of the user. Scrolling behavior on a touchscreen may be used to deliver personalized experiences. The point-by-point coarse scrolling data is aggregated and condensed on the user device being scrolled and the condensed data sent to a server for analysis to save bandwidth.

Abstract: A device, system, and non-transitory computer readable medium for providing a specialized agent comprising an application and a virtual assistant are disclosed. The virtual assistant includes a neural network trained with a machine learning algorithm to emulate a communication style of a character and wherein the virtual assistant is further trained on application metadata to a predict response to questions about the application.

Abstract: Personalized experiences for respective users sharing the same computer game system account are provided based on their interactions with games by analyzing deep signals such as browsing history, active times, playing history, and playing style during active sessions. To verify the detection, each user can be automatically prompted to confirm his or her identity, such as through notifications or on-screen prompts. Once verified, the experience can be tailored to each user, including content and artistic styles, to maximize the user's enjoyment and satisfaction.

Abstract: A method includes receiving information indicative of a sign-in request associated with an account registered on a service; determining whether the sign-in request comprises a fingerprint, wherein the fingerprint comprises one or more attributes associated with an interaction of a user during a sign-in on the account; dynamically generating a risk score based on a comparison of the one or more attributes of the fingerprint with one or more attributes of a set of attributes collected from a plurality of sign-in requests, wherein the risk score is based on a determination that the fingerprint correlates with attributes in a set of attributes identified as associated with behavior associated with a bot; and in response to the risk score being at or above a risk score threshold, issuing an indication of failure of the sign-in request.

Abstract: A system for location-based player feedback for video games may include a data collection module, a pattern recognition module, a localization module and a feedback module. The collection module collects gameplay data for a video game. The pattern recognition module analyzes the collected gameplay data to identify a pattern associated with player difficulty. The localization module associates a game world location with the identified pattern. The feedback module presents a message to players at the game world location associated with the identified pattern requesting feedback. The data collection, pattern recognition, and localization modules may include neural networks trained with machine learning algorithms.

Abstract: Non-players can vote and comment on uploaded video clips or livestreams of video games played by video game players. The video game players that upload the clips or do the livestreaming and that then receive the most votes can be awarded digital awards. The non-players providing the best comments can also be awarded digital awards. This incentivizes these behaviors, providing ample training data in the process so that the votes and comments can be used to train a model to make inferences related to video game video. For instance, the model may be trained to provide auto-generated comments in real time as a second video game is played, where the comments are in video game domain-specific language.

Abstract: A device, system, and non-transitory computer readable medium for providing a specialized agent comprising an application and a virtual assistant are disclosed. The virtual assistant includes a neural network trained with a machine learning algorithm to emulate a communication style of a character and wherein the virtual assistant is further trained on application metadata to a predict response to questions about the application.

Abstract: Embodiments of the present disclosure may include a method for enhancing a video game trophy, including detecting an end game state to a video game corresponding to award of a trophy. Embodiments may also include extracting metadata relating to a structure of the end game state from gameplay information associated with award of the trophy. Embodiments may also include determining metrics for the end game state from the metadata. Embodiments may also include applying a drama engine to the metrics for the end game state to generate commentary data corresponding to commentary on the award of the trophy.

Abstract: Aspects of the present disclosure relate to detecting churn in video games. Gameplay data for a video game is collected. The collected data is then analyzed with a first trained neural network to identify a pattern associated with one or more patterns associated with a player stopping playing the video game. The one or more patterns are analyzed with a second trained neural network to associate the one or more identified patterns with one or more reasons for the player stopping playing the video game. The one or more reasons are presented to a game developer. A system for detecting player churn in video games and methods for training such a system are also disclosed.

Abstract: A device, system, and method of training for application highlight detection. A first of set one or more of unimodal modules is configured to generate interest features from application data. A second set of unimodal modules is configured to generate refined interest features from application data with interest features and a multimodal neural network trained with a machine learning algorithm to classify application highlights from the application data with the interest features and the refined interest features.

Abstract: A system, device, and method of training for detection and generation of a gameplay highlight are disclosed. An application is run and one or more inputs for the application and application data are provided to a trained highlight detection neural network, which is trained to predict at least one highlight determined from at least one of the application data and the one or more inputs for the application.

Abstract: Non-players can vote and comment on uploaded video clips or livestreams of video games played by video game players. The video game players that upload the clips or do the livestreaming and that then receive the most votes can be awarded digital awards. The non-players providing the best comments can also be awarded digital awards. This incentivizes these behaviors, providing ample training data in the process so that the votes and comments can be used to train a model to make inferences related to video game video. For instance, the model may be trained to provide auto-generated comments in real time as a second video game is played, where the comments are in video game domain-specific language.

Abstract: Non-players can vote and comment on uploaded video clips or livestreams of video games played by video game players. The video game players that upload the clips or do the livestreaming and that then receive the most votes can be awarded digital awards. The non-players providing the best comments can also be awarded digital awards. This incentivizes these behaviors, providing ample training data in the process so that the votes and comments can be used to train a model to make inferences related to video game video. For instance, the model may be trained to provide auto-generated comments in real time as a second video game is played, where the comments are in video game domain-specific language.

Abstract: Provided a wide-angle lens includes: first lens, second lens, third lens, fourth lens, fifth lens, sixth lens, and seventh lens arranged sequentially from object surface to image surface along optic axis; first lens and sixth lens are negative focal power lenses, third lens, fourth lens, fifth lens, and seventh lens are positive focal power lenses, and second lens is negative or positive focal power lens; focal lengths of first lens, second lens, third lens, fourth lens, fifth lens, sixth lens, seventh lens, and the wide-angle lens are f1, f2, f3, f4, f5, f6, f7 and f respectively, satisfying: 0.3?|f1/f|?2.6, |f2/f|?2, 2.3?|f3/f|?7.2, |f4/f|?0.8, 0.67?|f5/f|?2.94, 0.32?|f6/f|?2.77, and |f7/f|?0.16. The wide-angle lens can satisfy surveillance requirements of high definition and small distortion while ensuring low cost.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for perform predictive data analysis operations using natural language input data. For example, certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis operations by using sentence embedding machine learning models that are trained in coordination with similarity-based machine learning models.