Back to results
US 2026/0093313 A1Published application
Computer system and method employing artificial intelligence engine
AssigneeSimology Corp.
InventorVance W. Boatwright
Life of this patent
Estimating the term…
Abstract
A user enters natural language text into a mobile phone. The mobile phone detects features of the user. An artificial reality engine modifies features of the user based on an intent derived from the natural language.
Claims30
A computer system comprising:
- a sensor positioned to capture at least one position of object to generate a digital signal representing the at least one position of the object;
- a pose estimator connected to the sensor and executable by at least one processor to estimate a pose of the object based on the digital signal;
- an input device positioned to a capture a user input from a user in the form of language;
- an artificial intelligence interface module connected to the input device and operable by the at least one processor to transmit the language to an artificial intelligence engine executable by the at least one processor to determine an intent of the user based on the language, and to generate code based on the intent, the artificial intelligence engine entering the intent in a rendering engine connected to the pose estimator and to the artificial intelligence engine and executable by the at least one processor to render the pose in a scene that includes at least the pose and with the scene being modified based on the generated code;
- a display;
- a display module connected to the rendering engine to create a visual representation of the scene as modified based on the generated code for displaying by the display;
- a humanoid robot;
- and
- a robot controller connected to the robot and executable by the at least one processor, wherein the artificial intelligence engine controls the robot through the robot controller based on the generated code.
6 more elements
(canceled)
(canceled)
A computer-implemented method comprising:
- capturing, with a sensor, at least one position of object to generate a digital signal representing the at least one position of the object;
- estimating, with a pose estimator connected to the sensor and executable by at least one processor, a pose of the object based on the digital signal;
- capturing, with an input device, a user input from a user in the form of language;
- determining, with an artificial intelligence engine connected to the input device and operable by the at least one processor, an intent of the user based on the language, the artificial intelligence engine generating a code based on the intent;
- rendering, with a rendering engine connected to the pose estimator and to the artificial intelligence engine and executable by the at least one processor, the pose in a scene that includes at least the pose and with the scene being modified based on the generated code;
- creating, with a display connected to the rendering engine, a visual representation of the scene as modified based on the generated code;
- and
- determining, with a body part tracker connected to the sensor and executable by at least one processor, body part features of the user;
- wherein the body part tracker determines gestures from the body part features of the user, the gestures being used by the artificial intelligence engine to update the scene.
6 more elements
(canceled)
(canceled)
A computer-implemented method comprising:
- capturing, with a sensor, at least one position of object to generate a digital signal representing the at least one position of the object;
- estimating, with a pose estimator connected to the sensor and executable by at least one processor, a pose of the object based on the digital signal;
- capturing, with an input device, a user input from a user in the form of language;
- determining, with an artificial intelligence engine connected to the input device and operable by the at least one processor, an intent of the user based on the language, the artificial intelligence engine generating a code based on the intent;
- rendering, with a rendering engine connected to the pose estimator and to the artificial intelligence engine and executable by the at least one processor, the pose in a scene that includes at least the pose and with the scene being modified based on the generated code;
- creating, with a display connected to the rendering engine, a visual representation of the scene as modified based on the generated code;
- wherein the artificial intelligence engine controls a robot through a robot controller based on the generated code.
4 more elements
A computer-implemented method comprising:
- capturing, with a sensor, at least one position of object to generate a digital signal representing the at least one position of the object;
- estimating, with a pose estimator connected to the sensor and executable by at least one processor, a pose of the object based on the digital signal;
- capturing. with an input device, a user input from a user in the form of language;
- determining, with an artificial intelligence engine connected to the input device and operable by the at least one processor, an intent of the user based on the language, the artificial intelligence engine generating a code based on the intent;
- rendering, with a rendering engine connected to the pose estimator and to the artificial intelligence engine and executable by the at least one processor, the pose in a scene that includes at least the pose and with the scene being modified based on the generated code;
- creating, with a display connected to the rendering engine, a visual representation of the scene as modified based on the generated code;
- controlling, by an artificial reality generator, a virtual objects generator to generate virtual objects based on the generated code for rendering by the rendering engine;
- and
- detecting, with an object interaction module connected to the virtual objects generator and executable by the at least one processor, collisions of the virtual objects.
6 more elements
30-42. (canceled)
Dependencies are inferred from the claim text.