公开(公告)号：US20190392641A1

公开(公告)日：2019-12-26

申请号：US16019240

申请日：2018-06-26

Applicant: Sony Interactive Entertainment Inc.

Inventor： Michael Taylor ,  Glenn Black ,  Javier Fernandez Rico

IPC: G06T19/00 ,  H04R1/10 ,  G10L15/08 ,  G02B27/01 ,  G10L25/54 ,  H04R3/00

Abstract: An augmented reality (AR) system adapts sounds based on the physical properties of real world materials found in a user's environment through material classification to sound modification. The sounds may be emulated sounds of virtual objects being emulated to impact real world objects in the AR space.

公开(公告)号：US20190388781A1

公开(公告)日：2019-12-26

申请号：US16019140

申请日：2018-06-26

Applicant: Sony Interactive Entertainment Inc.

Inventor： Michael Taylor ,  Glenn Black ,  Javier Fernandez Rico

IPC: A63F13/26 ,  G06T7/579 ,  G06T19/00 ,  A63F13/213 ,  A63F13/5378 ,  A63F13/35

Abstract: “Feature points” in “point clouds” that are visible to multiple respective cameras (i.e., aspects of objects imaged by the cameras) are reported via wired and/or wireless communication paths to a compositing processor which can determine whether a particular feature point “moved” a certain amount relative to another image. In this way, the compositing processor can determine, e.g., using triangulation and recognition of common features, how much movement occurred and where any particular camera was positioned when a latter image from that camera is captured. Thus, “overlap” of feature points in multiple images is used so that the system can close the loop to generate a SLAM map. The compositing processor, which may be implemented by a server or other device, generates the SLAM map by merging feature point data from multiple imaging devices.

公开(公告)号：US20190355092A1

公开(公告)日：2019-11-21

申请号：US16526819

申请日：2019-07-30

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Michael Taylor ,  Dennis Dale Castleman

IPC: G06T3/40 ,  G06T17/05 ,  G06T7/70

Abstract: Systems and methods for unmanned aerial vehicle (UAV) course profiling are provided. A plurality of images may be captured by a UAV flying along a course at a first location. A profile may be constructed for the course based on the images captured by the UAV. The constructed course profile is transmitted over a communication network to a virtual reality system at a second location. The virtual reality system may generate a virtual environment corresponding to the course based on the constructed course profile, and a second UAV at the second location may fly along the virtual course.

公开(公告)号：US20190126152A1

公开(公告)日：2019-05-02

申请号：US15801203

申请日：2017-11-01

Applicant: Sony Interactive Entertainment Inc.

Inventor： Michael Taylor ,  Glenn Black

IPC: A63F13/655 ,  G06K9/00 ,  H04L12/58 ,  A63F13/87

Abstract: Techniques for emoji-based communications derived from facial features during game play provide a communication channel accessible by players associated with gameplay hosted by the online game platform and capture an image of a user using a controller that includes a camera. The techniques further determine facial features of the user based on the image, generate an emoji based on the facial features of the user, and transmit the emoji to the players associated with the online game platform over the communication channel.

公开(公告)号：US20190102684A1

公开(公告)日：2019-04-04

申请号：US15724011

申请日：2017-10-03

Applicant: Sony Interactive Entertainment Inc.

Inventor： Erik Beran ,  Michael Taylor ,  Masanori Omote

IPC: G06N5/02 ,  G06F11/34 ,  G05B23/02 ,  H04L29/08 ,  G06F15/18

Abstract: A method for building an artificial intelligence (AI) model. The method includes accessing data related to monitored behavior of a user. The data is classified, wherein the classes include an objective data class identifying data relevant to a group of users including the user, and a subjective data class identifying data that is specific to the user. Objective data is accessed and relates to monitored behavior of a plurality of users including the user. The method includes providing as a first set of inputs into a deep learning engine performing AI the objective data and the subjective data of the user, and a plurality of objective data of the plurality of users. The method includes determining a plurality of learned patterns predicting user behavior when responding to the first set of inputs. The method includes building a local AI model of the user including the plurality of learned patterns.

公开(公告)号：US20190102667A1

公开(公告)日：2019-04-04

申请号：US15721637

申请日：2017-09-29

Applicant: Sony Interactive Entertainment Inc.

Inventor： Sergey Bashkirov ,  Michael Taylor ,  Javier Fernandez-Rico

IPC: G06N3/00 ,  G06N5/02 ,  G06N3/08

Abstract: An autonomous personal companion utilizing a method of object identification that relies on a hierarchy of object classifiers for categorizing one or more objects in a scene. The classifier hierarchy is composed of a set of root classifiers trained to recognize objects based on separate generic classes. Each root acts as the parent of a tree of child nodes, where each child node contains a more specific variant of its parent object classifier. The method covers walking the tree in order to classify an object based on more and more specific object features. The system is further comprised of an algorithm designed to minimize the number of object comparisons while allowing the system to concurrently categorize multiple objects in a scene.

公开(公告)号：US20190091576A1

公开(公告)日：2019-03-28

申请号：US15715653

申请日：2017-09-26

Applicant: Sony Interactive Entertainment Inc.

Inventor： Michael Taylor ,  Glenn Black

IPC: A63F13/63 ,  A63F13/30

Abstract: A method, system, and processor-readable storage medium for providing audio playback are disclosed to enable users to replace a background music in a computer or video game with music of user choice, while preserving other in-game sounds. An example method comprises receiving a game music stream from a gaming application of a user which includes a game background soundtrack and in-game sounds, extracting audio parameters of the game background soundtrack, determining an emotional classification of the game background soundtrack based on the audio parameters of the game background soundtrack, selecting a user soundtrack from a user music library that matches the emotional classification of game background soundtrack, replacing at least a part of the game background soundtrack with the user soundtrack, and providing a replacement game music stream to the user, the replacement game music including the user soundtrack and the in-game sounds.

公开(公告)号：US20190079722A1

公开(公告)日：2019-03-14

申请号：US16121441

申请日：2018-09-04

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Michael Taylor ,  Dennis Dale Castleman

IPC: G06F3/16

Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for altering and combining real and simulated audio streams. For example, a system can determine a location of a first unmanned aerial vehicle (UAV). The system can then determine a location of an object and can receive an audio stream associated with the object. The system can then determine a distance between the location of the first UAV and the location of the object. The system can adjust the audio stream volume according to the distance. The system can then send the audio stream to a listener.

公开(公告)号：US20190065960A1

公开(公告)日：2019-02-28

申请号：US15684830

申请日：2017-08-23

Applicant: Sony Interactive Entertainment Inc.

Inventor： Michael Taylor ,  Javier Fernandez-Rico ,  Sergey Bashkirov ,  Jaekwon Yoo ,  Ruxin Chen

IPC: G06N3/08

Abstract: An autonomous personal companion executing a method including capturing data related to user behavior. Patterns of user behavior are identified in the data and classified using predefined patterns associated with corresponding predefined tags to generate a collected set of one or more tags. The collected set is compared to sets of predefined tags of a plurality of scenarios, each to one or more predefined patterns of user behavior and a corresponding set of predefined tags. A weight is assigned to each of the sets of predefined tags, wherein each weight defines a corresponding match quality between the collected set of tags and a corresponding set of predefined tags. The sets of predefined tags are sorted by weight in descending order. A matched scenario is selected for the collected set of tags that is associated with a matched set of predefined tags having a corresponding weight having the highest match quality.

公开(公告)号：US20250010199A1

公开(公告)日：2025-01-09

申请号：US18348298

申请日：2023-07-06

Applicant: Sony Interactive Entertainment Inc.

Inventor： Michael Taylor ,  Yasunori Matsui ,  Yurika Kondo ,  Mihee Kang

IPC: A63F13/67 ,  A63F13/213

Abstract: A machine learning-based model or other system is configured to release user commands to a computer game at a time when the command correctly aligns with what is going on in the computer game. As such, the command might be predicted and released before the user input action is completed, or might be delayed after completion and processing until a later time when the command is most appropriate for release.