Abstract: Embodiments of systems presented herein may identify users to play a multiplayer video game together using a mapping system and machine learning algorithms to create sets of matchmaking plans for the multiplayer video game that increases player or user retention. Embodiments of systems presented herein can determine the predicted churn rate, or conversely retention rate, of a user waiting to play a video game if the user is matched with one or more additional users in a multiplayer instance of the video game.

Abstract: The present disclosure provides embodiments of a virtual mapping system for using real world geographical locations to generate virtual environments within game applications. The virtual mapping system allows a game application to identify geographical information associated with real world locations. The geographical information can be used by the game application to recreate the selected geographical location using virtual assets from the game application.

Abstract: An example method of automated selection of audio asset synthesizing pipelines includes: receiving an audio stream comprising human speech; determining one or more features of the audio stream; selecting, based on the one or more features of the audio stream, an audio asset synthesizing pipeline; training, using the audio stream, one or more audio asset synthesizing models implementing respective stages of the selected audio asset synthesizing pipeline; and responsive to determining that a quality metric of the audio asset synthesizing pipeline satisfies a predetermined quality condition, synthesizing one or more audio assets by the selected audio asset synthesizing pipeline.

Abstract: A persona system determines a player persona for a player of a gaming system based on gameplay information for the user and, for example, performs dynamic content generation or additional product recommendations based on the player persona. The persona system may receive a request for content based on a persona of a player and receive gameplay data associated with gameplay of the player in a plurality of games. The persona system may then generate a player persona of the player based on the gameplay data associated with the gameplay of the player in the plurality of games, determine persona based content based at least in part on a portion of the player persona, and output the persona based content in response to the request.

Abstract: A persona system determines a player persona for a player of a gaming system based on gameplay information for the user and, for example, performs dynamic content generation or additional product recommendations based on the player persona. The persona system may receive a request for content based on a persona of a player and receive gameplay data associated with gameplay of the player in a plurality of games. The persona system may then generate a player persona of the player based on the gameplay data associated with the gameplay of the player in the plurality of games, determine persona based content based at least in part on a portion of the player persona, and output the persona based content in response to the request.

Abstract: A system for use in video game development to generate expressive speech audio comprises a user interface configured to receive user-input text data and a user selection of a speech style. The system includes a machine-learned synthesizer comprising a text encoder, a speech style encoder and a decoder. The machine-learned synthesizer is configured to generate one or more text encodings derived from the user-input text data, using the text encoder of the machine-learned synthesizer; generate a speech style encoding by processing a set of speech style features associated with the selected speech style using the speech style encoder of the machine-learned synthesizer; combine the one or more text encodings and the speech style encoding to generate one or more combined encodings; and decode the one or more combined encodings with the decoder of the machine-learned synthesizer to generate predicted acoustic features.

Abstract: Systems and methods for generating a customized virtual animal character are disclosed. A system may obtain video data or other media depicting a real animal, and then may provide the obtained media to one or more machine learning models configured to learn visual appearance and behavior information regarding the particular animal depicted in the video or other media. The system may then generate a custom visual appearance model and a custom behavior model corresponding to the real animal, which may subsequently be used to render, within a virtual environment of a video game, a virtual animal character that resembles the real animal in appearance and in-game behavior.

Abstract: A video game includes a single player mode where completion of storyline objectives advances the single player storyline. The video game also includes a multiplayer mode where a plurality of players can play on an instance of a multiplayer map. Storyline objectives from the single player mode are selected and made available for completion to players in the multiplayer mode, and the single player storylines can be advanced by players completing respective storyline objectives while playing in the multiplayer mode. Combinations of storyline objectives are selected from pending storyline objectives for players connecting to a multiplayer game for compatibility with multiplayer maps. Constraints can be used to determine compatibility.

Abstract: According to a first aspect of this specification, there is disclosed a computer implemented method comprising: training, based on an initial behavior goal and using reinforcement-learning, a reinforcement-learning model for controlling behavior of a non-playable character in a computer game environment; converting the trained reinforcement-learning model into a behavior tree model for controlling behavior of the non-playable character; editing, based on a user input, the behavior tree model to generate an updated behavior tree model for controlling behavior of the non-playable character; and outputting a final model for controlling non-player character behavior for use in the computer game environment, wherein the model for controlling non-player character behavior is based at least in part on the updated behavior tree model.

Abstract: A videogame metrics query system, and related method, has one or more databases and a speculative cache. The system stores videogame metrics and tracks queries relating to videogame metrics. The system generates multiple queries, based on a received query and tracked queries. The system generates a combined query that has greater computational efficiency of execution. From executing the combined query, the system extracts query results relevant to the received query, and caches remaining results in the speculative cache.

Abstract: A method, computer-readable storage medium, and device for generating an animation sequence are disclosed. The method comprises: receiving an input animation sequence, wherein the input animation sequence comprises character position information over a series of frames and a first style tag; executing an encoder to process the input animation sequence to generate a compressed representation of the input animation sequence, wherein the compressed representation of the input animation sequence comprises a vector representing the input animation sequence; and executing a decoder to generate an output animation sequence, wherein executing the decoder is based on the compressed representation of the input animation sequence, wherein the output animation sequence comprises character position information over a series of frames, and wherein the output animation sequence is based on the input animation sequence and comprises a second style tag.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for game state synchronization. The method includes recording game state changes in a distributed queue. The method also includes updating a global state based on the recorded game state changes in the distributed queue. The method also includes recording a snapshot of the global state, the snapshot comprising an offset from a latest game state change recorded in the distributed queue. The method also includes updating at least one in-sync service of a plurality of in-sync services based on the game state changes and the snapshot of the global state.

Abstract: Methods for providing multi-objective experiments with dynamic group assignment are provided. In one aspect, a method includes receiving, from a configuration component of an experiment management system, a plurality of objectives and at least one constraint for an experiment. The method also includes assigning a test population of the experiment into a plurality of groups. The method also includes determining a progress summary that predicts completion rates for the plurality of objectives according to the at least one constraint. The method also includes modifying a prioritization of the plurality of objectives to optimize the predicted completion rates. The method also includes receiving a request to add additional users into the test population. The method also includes distributing the additional users into the plurality of groups according to the modified prioritization. Systems and machine-readable media are also provided.

Abstract: According to an aspect of this specification, there is described a computer implemented method comprising: receiving input data, the input data comprising data relating to a user of a computer game; generating, based on the input data, one or more candidate challenges for the computer game; determining, using a machine-learned model, whether each of the one or more of the candidate challenges satisfies a threshold condition, wherein the threshold condition is based on a target challenge difficultly; in response to a positive determination, outputting the one or more candidate challenges that satisfy the threshold condition for use in the computer game by the user.

Abstract: A method, computer-readable storage medium, and device for generating an animation sequence are disclosed. The method comprises: receiving an input animation sequence, wherein the input animation sequence comprises character position information over a series of frames and a first style tag; executing an encoder to process the input animation sequence to generate a compressed representation of the input animation sequence, wherein the compressed representation of the input animation sequence comprises a vector representing the input animation sequence; and executing a decoder to generate an output animation sequence, wherein executing the decoder is based on the compressed representation of the input animation sequence, wherein the output animation sequence comprises character position information over a series of frames, and wherein the output animation sequence is based on the input animation sequence and comprises a second style tag.

Abstract: A computer-implemented method for providing video game content is provided. The method comprises monitoring a request rate of requests to provide video game content; and in response to the request rate exceeding a threshold request rate: initialising at least one instance of a first machine learning model, wherein the first machine learning model is configured to provide an output which is approximate to the output of a second machine learning model from which the first machine learning model is derived, the first machine learning model being produced by a model derivation process to have a faster response time compared to the second machine learning model; and providing video game content, wherein providing the video game content comprises generating an output responsive to the specified input using the at least one instance of the first machine learning model.

Abstract: Embodiments of an automated fraud detection system are disclosed that can detect user accounts that are engaging in unauthorized activities within a game application. The fraud detection system can provide an automated system that identifies parasitic accounts. The fraud detection system may identify patterns using machine learning based on characteristics, such as gameplay and transaction characteristics, associated with the parasitic user accounts. The fraud detection system may generate a model that can be applied to existing accounts within the game in order to automatically identify users that are engaging in unauthorized activities. The fraud detection system may automatically identify these parasitic accounts and implement appropriate actions to prevent the accounts from impacting legitimate users within the game application.

Abstract: Embodiments of the present disclosure provide a tutorial system that can aid a user in performing various game commands in response to different game states in a virtual game environment. As the user plays the game, various game states may be encountered. A tutorial engine may, based on a current game state, determine one or more game commands to be recommended to the user, based on historical information of the user and a game state model, wherein the game state model maintains associations between game states and different segments of users. The user is recommended relevant game commands during the normal course of gameplay, based on their own gameplay history and on game commands commonly performed by other users of the game application.

Abstract: A method, computer-readable storage medium, and device for generating a character model. The method comprises: receiving an input image of a reference subject; processing the input image to generate a normalized image; identifying a set of features present in the normalized image, wherein each feature in the set of features corresponds to a portion of a head or body of the reference subject; for each feature in the set of features, processing at least a portion of the normalized image including the feature by a neural network model corresponding to the feature to generate a parameter vector corresponding to the feature; and combining the parameter vectors output by respective neural network models corresponding to respective features in the set of features to generate a parameterized character model corresponding to reference subject in the input image.

Abstract: Embodiments of systems presented herein may identify users to include in a match plan. A parameter model may be generated to predict the retention time of a set of users. A queue of potential users, a set of teammates, and/or opponents may be selected from a queue of waiting users. User information for the set of teammates and/or opponents may be provided to the parameter model to generate a predicted retention time. The set of teammates and/or opponents may be approved if the predicted retention time meets a predetermined threshold. Advantageously, by creating a match plan based on retention rates, the engagement and/or retention level for a number of users may be improved compared to existing multiplayer matching systems.