US 11,757,743 B1
Low-code/no-code machine learning data stream analysis system
Karl Davies-Barrett, Munich (DE); and Robert John Starling, San Francisco, CA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Mar. 31, 2022, as Appl. No. 17/710,302.
Int. Cl. H04L 43/08 (2022.01); H04L 41/16 (2022.01); H04L 65/61 (2022.01); H04L 41/0803 (2022.01); H04W 76/10 (2018.01)
CPC H04L 43/08 (2013.01) [H04L 41/0803 (2013.01); H04L 41/16 (2013.01); H04L 65/61 (2022.05); H04W 76/10 (2018.02)] 17 Claims
OG exemplary drawing
 
1. A system for performing customized machine learning analysis of a data stream, comprising:
a cloud service executed on at least one processor of a first datacenter, the cloud service configured to:
receive a first data stream from a sensor device;
train a machine-learning model to recognize selected elements of the first data stream that are selected from a package of template models, wherein the first data stream is a video stream, and the package of template models includes at least one set of image models, wherein to train the machine-learning model, the cloud service is configured to receive a selection of the at least one set of image models via a graphical user interface including a menu of the image models; and
deploy the machine-learning model to a second datacenter;
the second datacenter including a memory configured to store the machine-learning model and at least one processor configured to:
receive a second data stream via a network connection; and
locally interrogate the second data stream based on the machine-learning model to generate an element set including the selected elements; and
a logic service configured to:
receive a selection of one or more properties of the element set and one or more logical operators via a graphical user interface to generate user-configured logical rules; and
apply the user-configured logical rules to the element set.