Abstract: A method including receiving input data; selecting a classification scheme; transforming the input data into transformation data utilizing the classification scheme; transforming the input data into machine learner outputs; comparing the transformation data to the machine learner outputs; and altering machine state of one or more machines in response to comparing the transformation data to the machine learner outputs. Further, a method including receiving one or more sensor inputs; receiving one or more machine insights, the one or more machine insights comprising one or more states; selecting one of the one or more states; determining conditions of the one of the one or more states; comparing the conditions to the one or more sensor inputs; and altering a machine state of one or more machines in response to comparing the conditions to the one or more sensor inputs.
Abstract: A method for context-aware routing including receiving raw data; configuring a message handler with a routing table; determining data information flow with a remediation; utilizing a rule speed estimator and an orchestration speed; generating a selection signal with a resolution module to operate a selector to process the raw data; ordering the raw data with a sequencer to set a data processing order; processing the raw data; determining and sending a response message. A system for a context aware router involves service abstraction layers receiving input control signals; a router transforming the input control signals into message control signals; a rules interpretation component transforming the message control signals into rule control signals; a network abstraction layer receiving the message control signals and transforming the message control signals into a network control signal; and sending the network control signal to affect a machine state of one or more machines.
Abstract: A system and method receive raw data signals from a variety of edge devices. Observations are processed via a rule engine which may be preconfigured via a rule generator to implement a series of actions on remote or locally controlled machines. Rules are generated via a configurable user interface and may also be dynamically generated based on data received from the edge devices.
Type:
Grant
Filed:
January 23, 2018
Date of Patent:
July 30, 2019
Assignee:
BSQUARE CORP.
Inventors:
David Wagstaff, Matthew Honaker, Divya Krishnan