公开(公告)号：US20220101139A1

公开(公告)日：2022-03-31

申请号：US17548816

申请日：2021-12-13

Applicant: ABB Schweiz AG

Inventor： Johannes Schmitt ,  Christian Gross

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: A system for action indication determination includes an inputter, first and second processors, and an outputter. The inputter provides the first processor with sensor data from a plurality of sensors. The second processor implements a machine learning algorithm to generate at least one pre-processing rule, where the generation includes utilization of a plurality of training sensor data and associated training action indications. The second processor provides the first processor with the at least one pre-processing rule. The first processor implements a pre-processing algorithm to determine pre-processed sensor data, where the determination includes utilization of the at least one pre-processing rule and the sensor data. The first processor provides the pre-processed sensor data to the second processor. The second processor implements the machine learning algorithm to determine at least one action indication, where the determination includes utilization of the pre-processed sensor data. The outputter outputs the at least one action indication.

公开(公告)号：US20210223748A1

公开(公告)日：2021-07-22

申请号：US17129954

申请日：2020-12-22

Applicant: ABB Schweiz AG

Inventor： Johannes Schmitt ,  Christian Gross

IPC: G05B13/02 ,  G06F16/901

Abstract: A method for providing an evaluation and control model for controlling target building automation devices of a target building automation system includes: providing a plurality of pre-trained source evaluation and control models for controlling source building automation devices of a source building automation system; generating for each pre-trained source evaluation and control model a semantic based description of a context in which the model was trained; generating a semantic based description of the context of the target building automation system; retrieving the semantic based description of the context of each pre-trained source evaluation and control model of the plurality of pre-trained source evaluation and control models; and matching the generated semantic based description of the context of the target building automation system and the semantic based description of the context in which the pre-trained source evaluation and control models were trained by using a semantic matchmaking concept.