Abstract: A dynamic reasoning system may include a symbolic reasoning engine that iteratively calls a dynamic rule generator to answer an input query. The symbolic reasoning engine may determine a primary goal and/or secondary goals to generate proofs for the answer. The symbolic reasoning engine may call a rules component to provide rules to prove a current input goal. The rules component may use a static rule knowledge base and/or the dynamic rule generator to retrieve and rank rules relevant to the current input goal. The dynamic rule generator may generate new rules that lead to the current input goal. The dynamic rule generator may include a statistical model that generates unstructured or structured probabilistic rules based on context related to the input query. The symbolic reasoning engine may return a list of rules with confidence for explaining the answer to the input goal.

Abstract: A dynamic reasoning system may include a symbolic reasoning engine that iteratively calls a dynamic rule generator to answer an input query. The symbolic reasoning engine may determine a primary goal and/or secondary goals to generate proofs for the answer. The symbolic reasoning engine may call a rules component to provide rules to prove a current input goal. The rules component may use a static rule knowledge base and/or the dynamic rule generator to retrieve and rank rules relevant to the current input goal. The dynamic rule generator may generate new rules that lead to the current input goal. The dynamic rule generator may include a statistical model that generates unstructured or structured probabilistic rules based on context related to the input query. The symbolic reasoning engine may return a list of rules with confidence for explaining the answer to the input goal.

Abstract: A factory automation and monitoring method includes monitoring streams of data packets of M2M data on a mirrored port of a network switch coupled to computing elements of respective machines amongst industrial machinery, determining for the M2M data, a corresponding machine and acquiring a contemporaneous state of the corresponding machine. Then, a record is stored in a data store recording an association between the M2M data for each of the data packet streams, the corresponding machine for each of the data packet streams, and the contemporaneous state for the corresponding machine. Subsequently additional M2M data is received in the mirrored port and, in response, one of the machines is identified for the additional M2M data, a record from the data store retrieved for the identified machine, and, on condition that the additional M2M data demonstrates a threshold deviation from data in the retrieved record, an alert generated.