Sony Interactive Entertainment Inc.

Celeste Bean

Victoria Dorn

Olga Rudi

Glenn T Black

Sepideh Karimi

Sarah Karp

Sergey Bashkirov

Kristie Ramirez

Tatianna Manzon-Gutzman

Steven Osman

Michael G Taylor

Mahdi Azmandian

Elizabeth Ruth Juenger

Michael Taylor

Courtney Yingling

Kristine Young

Alessandra Luizello

Angela Bartolome

Benaisha Patel

Genie-Rose Luluquisin

Arthur Charles Kwun

Sudha Krishnamurthy

Jin Zhang

Rui Yang

Brielle Powell

Victoria Walker

Katie Egeland

Lachmin Singh

Hsin-Yi Chien

Arran Green

Ritagya Meharishi

Alex Duplessie

Tooba Ahsen

Liz Juenger

Steve Osman

Supriti Dan

Christopher M Pontiga

Alerts can be generated to inform a prime user to unblock another user, whose audio and/or video the prime user has blocked, owing to an emerging context that may be of interest to the prime user. The prime user can be informed of such a context and provided the ability to selectively view the blocked user's comments so the full context can be understood. This aims to help protect the prime user who may have been the subject of harassment from the blocked user originally causing the blocked user to be muted or otherwise blocked in the first place.

Context sensitive alerts involving muted users

Systems and methods of intelligent reporting within online communities are provided. A current communication session associated with a plurality of user device may be monitored. The current communication session may include a stream of audio-visual content generated in real-time based on interactions between the user devices. A recording trigger may be detected within the current communication session. A recording of a portion of the stream of audio-visual content may be recorded in response to the detected trigger event. The recording may be analyzed to attribute one or more sub-portions within the recording to one or more of the user devices. At least one of the sub-portions attributed to an identified one of the user devices may be determined to meet a moderation event. A report regarding the identified user device may be generated that includes the at least one sub-portion that meets the moderation event.

Intelligent reporting within online communities

A method performed for evaluating activity in a video game, including: executing a multi-player session of a video game; during the multi-player session, receiving flag event data from a first player device, the flag event data indicating that a first player has flagged a gameplay incident occurring during the multi-player session as potentially inappropriate; responsive to receiving the flag event data, then sending a request to a plurality of second player devices, wherein responsive to said request each of the plurality of second player devices renders a voting interface to obtain voting input from each of a plurality of second players regarding whether the gameplay incident is inappropriate; receiving said voting input from the plurality of second player devices, and responsive to said voting input identifying a threshold amount of the plurality of second players considering the gameplay incident to be inappropriate, then administering a penalty for the gameplay incident.

Reporting and crowd-sourced review whether game activity is appropriate for user

A system uses map data of a virtual environment and object data of an avatar object including a moveset to generate an action path for traversal of the virtual environment by the avatar object. The system applies machine learning model(s) to generate one or more pathways through the virtual environment, and decompose the one or more pathways into one or more pathway segments that can be evaluated for feasibility and other factors. The system can iteratively generate and evaluate a move sequence of the action path having one or more parameters for execution by the avatar object. The system can construct the action path by combination of a plurality of pathway segments to satisfy one or more constraints associated with traversal by the avatar object from a start location to a destination location within the virtual environment.

Action path creation assistant

The present technology provides solutions for spectator-based interactions in a virtual esports environment. A method can include establishing an interactive session associated with the virtual esports environment, the interactive session including a plurality of user devices, wherein a subset of the user devices is associated with designated players, and another subset of the user devices is associated with designated spectators; receiving data from one of the user devices over a communication network, the data indicating a spectator action performed by a spectator associated with the user device; identifying that the spectator action is associated with one of the players in the virtual esports environment; and modifying the virtual esports environment based on the spectator action and the association with the identified player.

Spectator participation in esports events

Machine learning is used to transform screen renders from the viewpoint of the player's character to be from the viewpoint of other non-player characters (NPC) in the room. One or more neural networks are trained using game images captured during a human play session, and then subsequently the neural networks are used to create realistic video from the NPC viewpoints. To avoid rendering multiple viewpoints simultaneously, a single viewpoint is rendered, and neural networks are used to transform it for the viewpoints of other NPCs in the area. A group of NPCs may be treated as a batch and a single viewpoint transformed to multiple viewpoints in a single inference pass. For cloud gaming the game video can be rendered/sent immediately for the player but the actions of the NPCs are delayed for a frame while the neural network generates the behavior.

Use of machine learning to transform screen renders from the player viewpoint

A method for providing assistance during gameplay is described. The method includes accessing a profile model associated with a user account of a user. The profile model is used to generate one or more predictive indicators based on a plurality of game contexts of one or more games. The method further includes receiving a request for accessing a game for a game session via the user account and generating assistance input for the user responsive to the one or more predictive indicators that the user will be unable to complete a task in the game. The task is associated to a game context. The assistance input is provided before the user performs the task.

Systems and methods for enabling predictive assistance during gameplay

A method generating an image according to a style is described. The method includes receiving a textual description describing a first image. The method further includes applying an artificial intelligence (AI) model to determine the style of a second image based on the textual description, the first image, a plurality of descriptions, and a plurality of images to generate a suggestion. The style provides a context to the second image. The style is lacking in the first image. The method includes generating the second image with the suggestion according to the style and providing the second image to a client device for display.

Systems and methods for generating images to achieve a style

To avoid startling a computer game player immersed in virtual reality for example, active noise cancelation is gradually introduced. As an alternative, ambient noise is gradually increased to conceal loud external sounds. The noise cancelation or ambient noise generation is established according to sound exceeding a background threshold as detected by a microphone. The noise cancelation or ambient noise generation can be established according to images of a noisy object as imaged by a camera.

Gradual noise canceling in computer game

Methods and systems for processing audio for a user include identifying an interactive zone of the user as the user is interacting with a video game in a real-world environment. The real-world environment is monitored to detect any changes that can affect the interactive zone. Responsive to detecting changes, a volume of the audio directed to one side or both side of a headphone providing the audio to one or both ears of the user is dynamically adjusted. The adjustment to the audio is to prevent the user from getting distracted while interacting with the video game.

Methods and systems for dynamically adjusting sound based on detected objects entering interaction zone of user

Systems and methods for audio processing are described. An audio processing system receives audio content that includes a voice sample. The audio processing system analyzes the voice sample to identify a sound type in the voice sample. The sound type corresponds to pronunciation of at least one specified character in the voice sample. The audio processing system generates a filtered voice sample at least in part by filtering the voice sample to modify the sound type. The audio processing system outputs the filtered voice sample.

Systems and methods for automated customized voice filtering

A method including executing game logic of a video game to generate a plurality of video frames for a game play of the video game by a player, wherein game state data is generated during the executing the game logic. The method including determining a current context in the game play of the video game based on the game state data. The method including determining a user sentiment of the player towards the current context in the game play of the video game. The method including determining that the user sentiment of the player is inconsistent with an expected user sentiment for the current context. The method including generating an in-game effect for the current context. The method including presenting the in-game effect simultaneous with one or more video frames associated with the current context in the game play of the video game.

User sentiment detection to identify user impairment during game play providing for automatic generation or modification of in-game effects

A method is provided, including: executing an interactive application, wherein executing the interactive application includes rendering video and audio of a virtual environment, the video being presented on a display viewed by a user, and the audio being presented through headphones worn by the user, and wherein executing the interactive application is responsive to user input generated from interactivity by the user with the presented video and audio; receiving environmental input from at least one sensor that senses a local environment in which the user is disposed; analyzing the environmental input to identify activity occurring in the local environment; responsive to identifying the activity, then adjusting a level of active noise cancellation applied by the headphones.

Method for adjusting noise cancellation in headphones based on real-world activity or game context

Systems and methods for automated visual trigger profiling and detection within virtual environments are provided. A visual trigger profile may be stored in memory that includes a set of visual trigger characteristics associated with a type of visual sensitivity. Buffered frames of an audiovisual stream that have not yet been displayed may be monitored to identify when a buffered frame includes a threshold level of the visual trigger characteristics associated with the visual sensitivity. A frame modification that decreases the level of the detected visual trigger characteristics associated with the visual sensitivity may be identified and applied to the identified frames. The modified frames may thereafter be presented during the audiovisual stream in place of the original (unmodified) identified frames.

Automated visual trigger profiling and detection

A method and system for generating a customized summary of virtual actions and events. Gameplay data sent over a communication network from a client device of the player engaged in a current activity of the respective interactive content title within a current gameplay session may be monitored. A trigger in the monitored gameplay data is detected and associated with a request for a summary that encapsulates actions and events of past gameplay associated with the trigger. A subset of the actions and events of the past gameplay for the summary is selected based on one or more selected customized tags associated with the trigger. The summary is generated based on the selected subset of the actions and events and provided to the client device for presentation.

Growing community of inventors

San Francisco, CA, United States of America

Celeste Bean