Abstract: Systems and methods for dynamically controlling a knowledge scope of artificial intelligence (AI) characters are provided. An example method includes associating a knowledge store with an AI character generated by an AI character model, where the AI character is a virtual character in a virtual world; determining context parameters for the AI character; defining, based on the context parameters, a scope of knowledge available to the AI character from a knowledge store; constricting access of the AI character to the knowledge store based on the defined scope of knowledge; monitoring changes in the context parameters; and dynamically adjusting the scope of knowledge based on the changes in the context parameters.

Abstract: Systems and methods for providing multi-source based knowledge data for Artificial Intelligence (AI) characters are provided. An example method includes providing a plurality of data sources; receiving, from a user, at least one word during a conversation between the user and an AI character; ascertaining a speech style of the AI character; analyzing the at least one word to determine a type of information needed to generate a reply to the user; selecting, based on the type of information, at least one data source from the plurality of data sources; generating, based on the at least one word, one or more queries; sending the one or more queries to the at least one data source; receiving one or more responses from the at least one data source; forming, based on the one or more responses and the speech style of the AI character, the reply for providing to the user.

Abstract: Systems and methods for continuously updating emotional states of artificial intelligence (AI) characters using emotional state models are provided. An example method includes providing an emotional state model trained to predict an emotional state of an AI character generated by an AI character model in a virtual environment; continuously monitoring a context of an interaction involving the AI character; generating, based on the context, an input for the emotional state model; providing the input to the emotional state model; obtaining, from the emotional state model, the emotional state of the AI character based on the input; and adjusting, based on the emotional state, parameters of the AI character model, thereby causing the AI character to act according to the emotional state.

Abstract: A user interface device includes at least a biopotential sensor and a location sensor. The user interface device is constructed to be worn by a person. A responsive device, such as a computer, receives data based on the outputs from the biopotential sensor and the location sensor, and performs actions based on the received data. Primitive gestures detected in the received data are associated with inputs of an operating system of the responsive device. For a wrist-worn device, a primitive gesture can be based on a pose of the hand or location of a wrist or both. The association of primitive gestures with inputs of the operating system can include associating primitive gestures with mouse inputs, inputs to request launching an application or switching applications, or inputs to perform other operations.

Abstract: A user interface to a machine such as a computer or computer-controlled device, is implemented by a combination of a user interface device and a responsive device. The user interface device includes at least a biopotential sensor and a location sensor. The user interface device is constructed to be worn by a person so that a biopotential sensor is positioned at least at the top of the wrist. The responsive device receives data based on the outputs from the biopotential sensor and the location sensor, and performs actions based on the received data. The responsive device is responsive to the received data to perform operations based on primitive gestures detected in the received data. A primitive gesture can be based on a pose of the hand or location of the wrist or both. The operation performed also can be based on any other information from other sensors on the user interface device. The selected operation also can be based on any context information available to the responsive device.

Abstract: A user interface device includes at least a biopotential sensor and a location sensor. The user interface device is constructed to be worn by a person. A responsive device, such as a computer, receives data based on the outputs from the biopotential sensor and the location sensor, and performs actions based on the received data. Primitive gestures detected in the received data are associated with inputs of an operating system of the responsive device. For a wrist-worn device, a primitive gesture can be based on a pose of the hand or location of a wrist or both. The association of primitive gestures with inputs of the operating system can include associating primitive gestures with mouse inputs, inputs to request launching an application or switching applications, or inputs to perform other operations.