Sony Interactive Entertainment Inc.

Mahdi Azmandian

Steven Osman

Olga Rudi

Jorge Arroyo Palacios

Victoria Dorn

Sudha Krishnamurthy

Sepideh Karimi

Celeste Bean

Sarah Karp

Elizabeth Ruth Juenger

Kristie Ramirez

David Nelson

Todd Tokubo

Bethany Tinklenberg

Xiaoyong Ye

Kristine Young

Jin Zhang

Zhenhao Ge

Brielle Powell

Matthew Bennett

Angela Bartolome

Brendan Rehon

Lee Kirsten Gould

Tatianna Forget

Joshua M Eads

Ravi Coimbatore Madhavan

A first AI-based image generation system generates a reference image based on a reference input specification that is initially set equal to an initial input for AI-based image generation. A second AI-based image generation system generates a trial image based on a trial input specification that is initially set equal to the initial input for AI-based image generation. An image matching assessment system processes the trial image and the reference image through an image analysis AI model to determine an amount of similarity therebetween and generate a corresponding image match score. A trial input specification adjustment engine generates a revised version of the trial input specification for the second AI-based image generation system to generate a new trial image that improves the image match score. In this manner, trial images are iteratively generated until the image match score is equal to or greater than the minimum required image match score.

Systems and associated methods for aligning outputs of different artificial intelligence (AI) models

Techniques are described for smooth switchover of computer game control. The current states of game input is communicated to a new player assuming control. The new player is allowed time to catch up to the game. New player control is detected, and any errors are communicated to the new player. If there are differences between the old control scheme and that of the new player, they are reconciled. The outgoing player is adjusted to the transition.

Smooth switchover of computer game control

To protect a user's privacy by reducing a malicious developer's ability to eavesdrop on unwitting HMD users by converting signals from a motion sensor in the HMD to speech or speaker recognition, a microphone can record ambient sound and voice which is subtracted from the motion sensor data before the sensor data is made available to the game developer. In another technique, a band pass filter subtracts frequency in the sensor signals within the voice range. Still a third technique blends statistical noise into the motion sensor signal before passing to game developers to obfuscate the user's speech. The amount by which voice components in the motion signal are eliminated or obfuscated can be tuned by a person or app.

Tunable filtering of voice-related components from motion sensor

A method for providing an auto-play mode option to a user during gameplay of a video game includes accessing, by a server, a user play model, which incorporates extracted features related to gameplay by the user and classification of the extracted features. The accessing of the model is triggered at a current time during gameplay. The method also includes identifying, by the server, predicted interactive activity that is predicted to occur ahead of the current time of gameplay. The method further includes identifying, by the server, at least part of the predicted interactive activity to be anticipated grinding content (AGC). The method also includes providing a notification, by the server, to a display screen of a user device, where the notification identifies the AGC in upcoming gameplay and provides the user with an option to use the auto-play mode during gameplay of the AGC.

Method and system for auto-playing portions of a video game

Methods and systems for representing emotions of an audience of spectators viewing online gaming of a video game include capturing interaction data from spectators of an audience engaged in watching gameplay of the video game. The captured interaction data is used to cluster the spectators into different groups in accordance to emotions detected from the interactions of spectators in the audience. A reaction track is identified for each group based on the emotion associated with the group. The reaction tracks representing distinct emotions of different groups of spectators are presented alongside content of the video game.

Reaction track for different spectator groups within an audience

The present disclosure generally relates to providing virtual education and education to a user. More specifically, the present system relates to educating and onboarding spectators of electronic sports (eSports) events. The onboarding activities are used to further engage the spectators with the eSports event in general, as well as the game played during the eSports event. In other aspects, the eSports onboarding activity may be modified based on the type of game being played, the user's experience with the specific game or game genre, and other user preferences.

Esports spectator onboarding

A method for executing a session of a video game is provided, including the following operations: recording speech of a player engaged in gameplay of the session of the video game; analyzing a game state generated by the execution of the session of the video game, wherein analyzing the game state identifies a context of the gameplay; analyzing the recorded speech using the identified context of the gameplay and a speech recognition model, to identify textual content of the recorded speech; applying the identified textual content as a gameplay input for the session of the video game.

Methods for examining game context for determining a user's voice commands

The performance of a player of a computer game is noted and the player accorded a latency handicap based thereon. The latency handicap is used to slow down play of the computer game, preferably only during times of high player activity. The latency handicap can be reduced over time or owing to improvement in the player's performance.

Adaptive time dilation based on player performance

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 dynamic audio optimization associated with digital content are provided. One or more audio profiles including one or more audio settings for one or more audio output devices available to a user may be stored in memory. An incoming audio stream associated with a current interactive session of the user and real-world audio within an identified real-world space where the user is located may be monitored. One or more audio deviations may be detected based on a comparison of the incoming audio stream and the real-world audio within the identified real-world space. An audio profile associated with the current interactive session may be automatically recalibrated to modify at least one of the audio settings. The audio output device may then process audio of the incoming audio stream in accordance with the at least one modified audio setting.

Dynamic audio optimization

Privacy of a conversation between a computer game player and an entity such as a person or virtual assistant is preserved by various techniques so that other players of the computer game who are not part of the conversation cannot apprehend the conversation. The conversation may be voice or txt but is not an online chat associated with the computer game.

SMS, phone and video call support while gaming

A cloud-based gaming system generates first and second instances of a virtual world of an online game for first and second players, respectively. First and second video streams of the first and second instances of the virtual world, respectively, are transmitted to the first and second players, respectively. The second video stream includes a ghosted version of a feature within the first instance of the virtual world. A request is received from the second player to merge the first and second instances of the virtual world. With the first player's approval, a merged instance of the virtual world is automatically generated by the cloud-gaming system as a combination of the first and second instances of the virtual world. Third and fourth video streams of the merged instance of the virtual world are transmitted to the first and second players, respectively, in lieu of the first and second video streams, respectively.

Systems and methods for managing virtual world in cloud-based gaming

Methods of the present disclosure may collect data when a user plays one or more different types of games when determinations are made as to whether the difficulty of a game should be changed. The collected data maybe evaluated to identify whether a user gaming performance level corresponds to an expected level of performance. When the user gaming performance level does not correspond to an expected level of performance, parameters that change the difficultly of the game may be changed automatically. Parameters that relate to movement speed, delay or hesitation, character strengths, numbers of competitors, or other metrics may be changed incrementally until a current user performance level corresponds to an expectation level of a particular user currently playing the game. At this time, the user expectation level may be changed, and the process may be repeated as skills of the user are developed over time.

Adaptive difficulty calibration for skills-based activities in virtual environments

Methods and systems for cooperative or coached gameplay in virtual environments are disclosed. Memory may store a content control profile regarding a set of control input associated with an action in a virtual environment of a digital content title. A request may be received from a set of one or more users associated with different source devices regarding cooperative gameplay of the digital content title. At least one virtual avatar may be generated for an interactive session of the digital content title in response to the request. A plurality of control inputs may be received from the plurality of different source devices and combined into a combination set of control inputs. Generating the combination set of control input may be based on the content control profile. Virtual actions associated with the virtual avatar may be controlled within the virtual environment in accordance with the combination set of control inputs.

Cooperative and coached gameplay

A player who is interrupted during play of a computer simulation such as a computer game and must attend to other matters (colloquially referred to herein as being 'away from keyboard' or “AFK”) is assisted in three phases. A first type of assistance is rendered when entering AFK, as in, at the start of the interruption. A second type of assistance is rendered during AFK, while the player is away. A third type of assistance is rendered when the player returns from AFK to the computer simulation.

Growing community of inventors

San Mateo, CA, United States of America

Mahdi Azmandian