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: Using transaction data to present search results is described. A payment service computing platform may receive transaction data associated with users of a payment service, and may receive a search query from a payment application associated with the payment service and executing on a device of a user. The payment service computing platform may then determine, based at least in part on a portion of the transaction data associated with the user, a user risk metric associated with the user, may generate a list of entities based at least in part on the user risk metric, and may cause a user interface of the payment application to present at least a portion of the list of entities as a search result to the search query.

Abstract: Embodiments of the systems and methods described herein provide a terrain generation and population system that can determine terrain population rules for terrain population objects and features when placing objects and features in a three dimensional virtual space. As such, the terrain generation and population system can generate realistic terrain for use in game. The terrain generation and population system can receive an image, such as a satellite image, and utilize artificial intelligence to perform image segmentation at the pixel level to segment features and/or objects in the image. The game terrain system can automatically detect and apply feature and object masks based on the identified features and/or objects from the image segmentation. The game terrain system can place the features and/or objects in corresponding masks in the three dimensional space according to the application of terrain population rules.

Abstract: Embodiments of the systems and methods described herein provide a dynamic animation generation system that can apply a real-life video clip with a character in motion to a first neural network to receive rough motion data, such as pose information, for each of the frames of the video clip, and overlay the pose information on top of the video clip to generate a modified video clip. The system can identify a sliding window that includes a current frame, past frames, and future frames of the modified video clip, and apply the modified video clip to a second neural network to predict a next frame. The dynamic animation generation system can then move the sliding window to the next frame while including the predicted next frame, and apply the new sliding window to the second neural network to predict the following frame to the next frame.

Abstract: In some embodiments, the dynamic animation generation system can provide a deep learning framework to produce a large variety of martial arts movements in a controllable manner from unstructured motion capture data. The system can imitate animation layering using neural networks with the aim to overcome challenges when mixing, blending and editing movements from unaligned motion sources. The system can synthesize movements from given reference motions and simple user controls, and generate unseen sequences of locomotion, but also reconstruct signature motions of different fighters. For achieving this task, the dynamic animation generation system can adopt a modular framework that is composed of the motion generator, that maps the trajectories of a number of key joints and root trajectory to the full body motion, and a set of different control modules that map the user inputs to such trajectories.

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: A computer-implemented method of generating speech audio in a video game is provided. The method includes inputting, into a synthesizer module, input data that represents speech content. Source acoustic features for the speech content in the voice of a source speaker are generated and are input, along with a speaker embedding associated with a player of the video game into an acoustic feature encoder of a voice convertor. One or more acoustic feature encodings are generated as output of the acoustic feature encoder, which are inputted into an acoustic feature decoder of the voice convertor to generate target acoustic features. The target acoustic features are processed with one or more modules, to generate speech audio in the voice of the player.

Abstract: Using a machine learning model(s) for fraud reduction is described. A payment service computing platform may receive, from an electronic device, user data associated with a user, and dynamically determine an incentive(s) associated with the user based on the user data. The incentive(s) may be determined using a trained machine learning model(s) that is trained based on previously collected user data. The payment service computing platform can then cause a user interface to be displayed via a payment application executing on the electronic device, wherein the user interface presents an interactive element(s) for receiving the incentive(s) in exchange for the user referring at least one other user to a payment service.

Abstract: Using transaction data to rank search results is described. A payment service computing platform may receive transaction data associated with users of a payment service, and may receive a search query from a payment application associated with the payment service and executing on a device of a user. The payment service computing platform may then generate a list of entities based at least in part on a likelihood, determined using a portion of the transaction data associated with the entities, that the user will be able to successfully complete a transaction in association with the entities, and may cause a user interface of the payment application to present at least a portion of the list of entities as a search result to the search query.

Abstract: This specification describes systems and methods for aging voice audio, in particular voice audio in computer games. According to one aspect of this specification, there is described a method for aging speech audio data. The method comprises: inputting an initial audio signal and an age embedding into a machine-learned age convertor model, wherein: the initial audio signal comprises speech audio; and the age embedding is based on an age classification of a plurality of speech audio samples of subjects in a target age category; processing, by the machine-learned age convertor model, the initial audio signal and the age embedding to generate an age-altered audio signal, wherein the age-altered audio signal corresponds to a version of the initial audio signal in the target age category; and outputting, from the machine-learned age convertor model, the age-altered audio signal.

Abstract: A graphics rendering system is disclosed for generating and streaming graphics data of a 3D environment from a server for rendering on a client in 2.5D. 2D textures can be transmitted in advance of frames showing the textures. Data transmitted for each frame can include 2D vertex positions of 2D meshes and depth data. The 2D vertex positions can be positions on a 2D projection as seen from a viewpoint within the 3D environment. Data for each frame can include changes to vertex positions and/or depth data. A prediction system can be used to predict when new objects will be displayed, and textures of those new objects can be transmitted in advance.

Abstract: Systems and methods are provided for enhanced animation generation based on using motion mapping with local bone phases. An example method includes accessing first animation control information generated for a first frame of an electronic game including local bone phases representing phase information associated with contacts of a plurality of rigid bodies of an in-game character with an in-game environment. Executing a local motion matching process for each of the plurality of local bone phases and generating a second pose of the character model based on the plurality of matched local poses for a second frame of the electronic game.

Abstract: Embodiments of the systems and methods described herein provide a dynamic animation generation system that can apply a real-life video clip with a character in motion to a first neural network to receive rough motion data, such as pose information, for each of the frames of the video clip, and overlay the pose information on top of the video clip to generate a modified video clip. The system can identify a sliding window that includes a current frame, past frames, and future frames of the modified video clip, and apply the modified video clip to a second neural network to predict a next frame. The dynamic animation generation system can then move the sliding window to the next frame while including the predicted next frame, and apply the new sliding window to the second neural network to predict the following frame to the next frame.

Abstract: This specification describes a system for generating positions of map items such as buildings, for placement on a virtual map. The system comprises: at least one processor; and a non-transitory computer-readable medium including executable instructions that when executed by the at least one processor cause the at least one processor to perform at least the following operations: receiving an input at a generator neural network trained for generating map item positions; generating, with the generator neural network, a probability of placing a map item for each subregion of a plurality of subregions of the region of the virtual map; and generating position data of map items for placement on the virtual map using the probability for each subregion.

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 the systems and methods described herein provide a three dimensional reconstruction system that can receive an image from a camera, and then utilize machine learning algorithms to identify objects in the image. The three dimensional reconstruction system can identify a geolocation of a user, identify features of the surrounding area, such as structures or geographic features, and reconstruct the scene including the identified features. The three dimensional reconstruction system can generate three dimensional object data for the features and/or objects, modify the three dimensional objects, arrange the objects in a scene, and render a two dimensional view of the scene.

Abstract: This specification describes a computer-implemented method of generating speech audio for use in a video game, wherein the speech audio is generated using a voice convertor that has been trained to convert audio data for a source speaker into audio data for a target speaker. The method comprises receiving: (i) source speech audio, and (ii) a target speaker identifier. The source speech audio comprises speech content in the voice of a source speaker. Source acoustic features are determined for the source speech audio. A target speaker embedding associated with the target speaker identifier is generated as output of a speaker encoder of the voice convertor. The target speaker embedding and the source acoustic features are inputted into an acoustic feature encoder of the voice convertor. One or more acoustic feature encodings are generated as output of the acoustic feature encoder. The one or more acoustic feature encodings are derived from the target speaker embedding and the source acoustic features.

Abstract: This specification describes a computer-implemented generative interior design method. The method comprises obtaining input data comprising boundary data. The boundary data defines a boundary of an interior region of a video game building. A floor plan for the interior region of the video game building is generated. This comprises processing the input data using a floor plan generator model. The floor plan divides the interior region into a plurality of interior spaces. A layout for at least one of the plurality of interior spaces defined by the floor plan is generated by a layout generator model comprising one or more graph neural networks. The layout represents a configuration of one or more objects to be placed in the interior region.

Abstract: This specification describes a computing system for generating visual assets for video games. The computing system comprises an image segmentation model, a first 3D generation model, and a second 3D generation model. At least one of the first 3D generation model and the second 3D generation model comprises a machine-learning model. The system is configured to obtain: (i) a plurality of images corresponding to the visual asset, each image showing a different view of an object to be generated in the visual asset, and (ii) orientation data for each image that specifies an orientation of the object in the image. A segmented image is generated for each image. This comprises processing the image using the image segmentation model to segment distinct portions of the image into one or more classes of a predefined set of classes. For each image, 3D shape data is generated for a portion of the object displayed in the image.

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.