US 12,347,095 B1
Sensor data processing for monitoring device performance
Thomas E. Bell, San Francisco, CA (US); Peter Bordow, Fountain Hills, AZ (US); Julio Jiron, San Bruno, CA (US); Akhlaq M. Khan, San Francisco, CA (US); Volkmar Scharf-Katz, San Francisco, CA (US); Jeff J. Stapleton, Arlington, TX (US); Richard Orlando Toohey, San Francisco, CA (US); and Ramesh Yarlagadda, San Francisco, CA (US)
Assigned to Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed by Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed on Aug. 26, 2022, as Appl. No. 17/896,407.
Int. Cl. G06T 7/00 (2017.01); G06K 7/14 (2006.01); G06V 10/94 (2022.01); G10L 25/03 (2013.01)
CPC G06T 7/001 (2013.01) [G06K 7/1417 (2013.01); G06V 10/95 (2022.01); G10L 25/03 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/30164 (2013.01); G06V 2201/06 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for maintaining identity elements for manufactured articles, the method comprising:
receiving, from a computing device, a first data packet comprising scan data corresponding to a scan by an imaging device of the computing device;
analyzing the scan data in the first data packet to determine that the scan data corresponds to a manufactured article;
transmitting, to the computing device, a first indication that the manufactured article has been identified and a request for audiovisual data and motion data corresponding to an operation of the manufactured article;
receiving, from the computing device, a second data packet comprising audiovisual data corresponding to a recording by at least one of the imaging device or a microphone of the computing device;
extracting, from the second data packet, a sound sample corresponding to sounds made during the operation of the manufactured article;
receiving, from the computing device, a third data packet comprising the motion data of the manufactured article captured by a vibration sensor in proximity to the manufactured article, the motion data indicating vibrations created by the manufactured article during operation of the manufactured article;
generating frequency-domain sound data and frequency-domain motion data based on the sound sample, the motion data, and a frequency-domain transformation operation;
generating a status metric based on (i) a comparison of the frequency-domain sound data to a sound signature in an identity profile of the manufactured article, and (ii) a comparison of the frequency-domain motion data to a vibration signature in the identity profile of the manufactured article; and
transmitting, to the computing device, a status of the manufactured article based on the status metric.