US 12,147,430 B1
Real-time search and retrieval of streaming sensor data
Pragyana K Mishra, Seattle, WA (US)
Assigned to Armada Systems Inc., Greebrae, CA (US)
Filed by Armada Systems Inc., Greebrae, CA (US)
Filed on Apr. 3, 2024, as Appl. No. 18/626,236.
Application 18/626,236 is a continuation of application No. 18/524,576, filed on Nov. 30, 2023, granted, now 12,026,164.
Application 18/524,576 is a continuation of application No. 18/461,349, filed on Sep. 5, 2023, granted, now 11,899,671.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/2455 (2019.01); G06F 16/22 (2019.01)
CPC G06F 16/24568 (2019.01) [G06F 16/2228 (2019.01)] 29 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, by an edge device, a plurality of data streams corresponding to objects, activities, and events registered in an edge environment associated with the edge device;
generating, using one or more machine learning networks implemented on the edge device, a plurality of features corresponding to each respective data stream of the plurality of data streams;
determining, by the edge device, a subset of salient content from the plurality of data streams, wherein the subset of salient content is determined based on analyzing the plurality of features generated for each respective data stream of the plurality of data streams, wherein the determining the subset of salient content includes:
analyzing the plurality of features to identify duplicate data streams, wherein duplicate data streams have same or similar features as respective features of a previously indexed and stored data stream; and
generating the subset of salient content to include a portion of the plurality of data streams not identified as duplicate data streams;
generating, by the edge device, index information corresponding to the determined subset of salient content; and
storing the subset of salient content and the generated index information locally at the edge device for search and retrieval based on local queries received at the edge device, wherein at least a portion of the subset of salient content is stored based on bandwidth availability between the edge device and a cloud entity;
determining a respective relevance score for portions of the stored subset of salient content mapped to each inverse index key of inverse index keys; and
outputting, based on a received local query of the received local queries, corresponding identifiers of pieces of the stored subset of salient content with respective relevance score greater than a configured threshold.