Back to results
US 12,400,101 B1Granted
Artificially intelligent systems, devices, and methods for learning and/or using an avatar's circumstances for autonomous avatar operation
OwnerJasmin Cosicinventor
Life of this patent
Estimating the term…
Abstract
Aspects of the disclosure generally relate to computing devices and/or systems, and may be generally directed to devices, systems, methods, and/or applications for learning an avatar's or an application's operation in various circumstances, storing this knowledge in a knowledgebase (i.e. neural network, graph, sequences, etc.), and/or enabling autonomous operation of the avatar or the application.
Claims74
A system comprising:
- one or more non-transitory machine readable media storing machine readable code that, when executed, causes at least:
- accessing a knowledgebase that includes one or more inputs for inputting a collection of object representations, wherein the one or more inputs are correlated with one or more instruction sets for operating a first avatar of an application;
- generating or receiving a stream of collections of object representations, wherein the stream includes:
- a first collection of object representations that represents multiple objects of the application, and a second collection of object representations that represents multiple objects of the application;
- determining the one or more instruction sets for operating the first avatar of the application at least by:
- inputting the first collection of object representations of the stream into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first avatar of the application;
- and
- performing, by the first avatar of the application or by a second avatar of the application or by a first avatar of another application, one or more operations defined by the one or more instruction sets for operating the first avatar of the application, wherein the performing includes executing the one or more instruction sets for operating the first avatar of the application at least in response to the determining.
5 more elements
A system comprising:
- one or more non-transitory machine readable media storing machine readable code that, when executed, causes at least:
- accessing a knowledgebase that includes one or more inputs for inputting a collection of object representations that:
- (i) comprises multiple object representations that each includes:
- a label indicating object type, and coordinates indicating object location, and (ii) represents:
- multiple objects of an application, or multiple objects of another application, wherein the one or more inputs are correlated with one or more instruction sets for operating a first avatar of the application;
- generating or receiving a stream of collections of object representations, wherein the stream includes:
- a first collection of object representations that:
- (i) comprises multiple object representations that each includes:
- a label indicating object type, and coordinates indicating object location, and (ii) represents:
- multiple objects of the application at a first time, or multiple objects of the another application at a first time, and
- a second collection of object representations that:
- (i) comprises multiple object representations that each includes:
- a label indicating object type, and coordinates indicating object location, and (ii) represents:
- multiple objects of the application at a second time, or multiple objects of the another application at a second time;
- determining the one or more instruction sets for operating the first avatar of the application at least by:
- inputting the first collection of object representations of the stream into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first avatar of the application;
- and
- autonomously performing, by the first avatar of the application or by a second avatar of the application or by a first avatar of the another application, one or more operations defined by the one or more instruction sets for operating the first avatar of the application, wherein the autonomously performing includes executing the one or more instruction sets for operating the first avatar of the application at least in response to the determining.
15 more elements
A method comprising:
- accessing a knowledgebase that includes one or more inputs for inputting a collection of object representations that:
- (i) comprises multiple object representations that each includes:
- a label indicating object type, and coordinates indicating object location, and (ii) represents:
- multiple objects of an application, or multiple objects of another application, wherein the one or more inputs are correlated with one or more instruction sets for operating a first avatar of the application;
- generating or receiving a stream of collections of object representations, wherein the stream includes:
- a first collection of object representations that:
- (i) comprises multiple object representations that each includes:
- a label indicating object type, and coordinates indicating object location, and (ii) represents:
- multiple objects of the application at a first time, or multiple objects of the another application at a first time, and
- a second collection of object representations that:
- (i) comprises multiple object representations that each includes:
- a label indicating object type, and coordinates indicating object location, and (ii) represents:
- multiple objects of the application at a second time, or multiple objects of the another application at a second time;
- determining the one or more instruction sets for operating the first avatar of the application at least by:
- inputting the first collection of object representations of the stream into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first avatar of the application;
- and
- autonomously performing, by the first avatar of the application or by a second avatar of the application or by a first avatar of the another application, one or more operations defined by the one or more instruction sets for operating the first avatar of the application, wherein the autonomously performing includes executing the one or more instruction sets for operating the first avatar of the application at least in response to the determining.
14 more elements
Dependencies are inferred from the claim text.