公开(公告)号：US11455331B2

公开(公告)日：2022-09-27

申请号：US16711870

申请日：2019-12-12

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： Roger Donaldson ,  Gregory Conn

IPC: G06F16/00 ,  G06F16/532 ,  G06F16/583 ,  G06F17/16 ,  G06V40/16

Abstract: A device, system and method for anonymously comparing query images to reference images is provided. A computing device receives, from at least one camera, a query image. The computing device generates a query characteristic vector associated with the query image. The computing device applies a mathematical operator on the query characteristic vector to obtain a query vector. The computing device compares the query vector to a reference vector, the reference vector obtained by applying a complementary mathematical operator on a reference characteristic vector associated with a reference image, the complementary mathematical operator comprising a complement of the mathematical operator. The computing device, in response to the comparing indicating a match between the query vector and the reference vector, provides a notification of the match.

公开(公告)号：US11893057B2

公开(公告)日：2024-02-06

申请号：US17034285

申请日：2020-09-28

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： Roger Donaldson ,  Jehan Wickramasuriya

IPC: G06F16/835 ,  G06Q50/26 ,  G06F21/53 ,  G06F40/284 ,  G06F40/205 ,  G06N3/08 ,  G06N3/045

CPC classification number: G06F16/8358 ,  G06F21/53 ,  G06F40/205 ,  G06F40/284 ,  G06N3/045 ,  G06N3/08 ,  G06Q50/26 ,  G06F2221/033

Abstract: A method of processing a query to a database from a query source is provided, comprising: receiving the query, the query in a first format supported by the query source; inputting the query into a first neural network; outputting, by the first neural network, the query in a second format, wherein the second format is a format supported by the database; receiving, from the database, a response to the query, the response in the second format; inputting the response to the query into a second neural network; outputting, by the second neural network, the response to the query in the first format; wherein each neural network is trained by inputting a first plurality of pairs of semi-structured data, each pair of semi-structured data comprising a sample query or response in the first format and the sample query or response in the second format.