Abstract: Examples disclosed herein relate to receiving a query via a chat interaction, translating the received query into one of a set of predefined commands according to a trained machine-learning model, and providing a result of the one of the set of predefined commands to the chat interaction.

Abstract: Examples disclosed herein relate to determining a response based on hierarchical models. In one implementation, a processor applies a first model to an image of an environment to select a second model. The processor applies the selected second model to the image and creates an environmental description representation based on the output of the second model. The processor determines a response based on the environmental description information.

Abstract: Examples disclosed herein relate to extracting a plurality of features from a document according to a heuristic extraction model, generating a vector representation of the document according to the plurality of extracted features, associating at least one security rule with the document, determining if a received vector representation matches the stored vector representation of the document, and providing a response to a requested action on the document according to the determination.

Abstract: Examples disclosed herein relate to determining a response based on hierarchical models. In one implementation, a processor applies a first model to an image of an environment to select a second model. The processor applies the selected second model to the image and creates an environmental description representation based on the output of the second model. The processor determines a response based on the environmental description information.

Abstract: Examples disclosed herein relate to receiving a query via a chat interaction, translating the received query into one of a set of predefined commands according to a trained machine-learning model, and providing a result of the one of the set of predefined commands to the chat interaction.

Abstract: A method of providing feedback to a presenter in a remote meeting includes capturing images of remote participants in the remote meeting using cameras associated with computing devices that display content presented by the presenter. Eye gaze angle information for at least one of the remote participants is determined based on the captured images. At least one region of interest in the displayed content is identified based on the eye gaze angle information. Feedback is provided to the presenter including an indication of the identified at least one region of interest.

Abstract: A method of providing feedback to a presenter in a remote meeting includes capturing images of remote participants in the remote meeting using cameras associated with computing devices that display content presented by the presenter. Eye gaze angle information for at least one of the remote participants is determined based on the captured images. At least one region of interest in the displayed content is identified based on the eye gaze angle information. Feedback is provided to the presenter including an indication of the identified at least one region of interest.

Abstract: Examples disclosed herein relate to extracting a plurality of features from a document according to a heuristic extraction model, generating a vector representation of the document according to the plurality of extracted features, associating at least one security rule with the document, determining if a received vector representation matches the stored vector representation of the document, and providing a response to a requested action on the document according to the determination.