Adding deep learning based ai control
AssigneeAIBrain Corporation
InventorsDániel László Kovács, Jinhwal Lee, Taejun Kang, Sichang Yang, Hankyul Kim, Hong Shik Shinn
Life of this patent
Estimating the term…
Abstract
An encoded artificial intelligence (AI) behavior specification is received. A data generation configuration specification is received. And a deep neural network configuration specification is received. A training data set based on the data generation configuration specification is generated. An AI behavior deep neural network that conforms to the deep neural network configuration specification is trained using at least a subset of the generated training data. The trained AI behavior deep neural network is provided from a remote AI add-in service to a development environment.
Claims20
A method, comprising:
- receiving an encoded artificial intelligence behavior specification;
- receiving a data generation configuration specification;
- receiving a deep neural network configuration specification;
- generating a training data set based on the data generation configuration specification;
- training an artificial intelligence behavior deep neural network using at least a subset of the generated training data, wherein the artificial intelligence behavior deep neural network conforms to the deep neural network configuration specification;
- and
- providing from a remote artificial intelligence add-in service to a development environment the trained artificial intelligence behavior deep neural network.
A system, comprising:
- a processor;
- and
- a memory coupled with the processor, wherein the memory is configured to provide the processor with instructions which when executed cause the processor to:
- receive an encoded artificial intelligence behavior specification;
- receive a data generation configuration specification;
- receive a deep neural network configuration specification;
- generate a training data set based on the data generation configuration specification;
- train an artificial intelligence behavior deep neural network using at least a subset of the generated training data, wherein the artificial intelligence behavior deep neural network conforms to the deep neural network configuration specification;
- and
- provide from a remote artificial intelligence add-in service to a development environment the trained artificial intelligence behavior deep neural network.
A method, comprising:
- creating an artificial intelligence entity type, wherein the artificial intelligence entity type includes one or more properties;
- associating one or more objects of a scene to the artificial intelligence entity type;
- defining an artificial intelligence environment corresponding to a environment of the scene;
- creating a configured artificial intelligence behavior specification associated with an artificial intelligence agent, wherein the artificial intelligence agent is an instance of the artificial intelligence entity type;
- compiling the configured artificial intelligence behavior specification;
- uploading the configured artificial intelligence behavior specification to an artificial intelligence add-in service for training a deep neural network;
- receiving the trained deep neural network from the artificial intelligence add-in service;
- and
- providing an application programming interface configured to interface with the trained deep neural network.
Dependencies are inferred from the claim text.