US 11,232,395 B1Granted

Signal processing techniques

AssigneeAmazon Technologies, Inc.

InventorsRobert Crandall, Paul Eugene Munger, Nikhil Chacko, Liefeng Bo, Gerard Guy Medioni

Life of this patent

Estimating the term…

Loading patent…

Abstract

This disclosure describes techniques for removing noise from a signal to generate a modified signal, with the modified signal preserving any transitions of interest (e.g., sharp-edge discontinuities) present within the initial signal. In one example, the signal comprises a time-series signal with the time series representing a sequence of weight measurements from a scale device. In some examples, the scale device includes a platform that supports one or more physical items that may be selectively removed or added to. Here, the signal may include a sequence of step functions corresponding to changes in weight on the scale device (based on the removal or addition of items on the platform), plus corrupting noise from vibration. The techniques described herein may remove the corrupting noise, while preserving the sharp edges representing sudden changes in weight.

Claims21

Dependent claims

A system comprising:

a platform to hold one or more items;
a load cell coupled to the platform and configured to generate a signal, the signal corresponding to a weight of the one or more items;
one or more processors;
and
one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising:
calculating a first mean of a first number of data points, N, of the signal;
calculating a first left mean comprising a mean of a first half of the first N number of data points;
calculating a first right mean comprising a mean of a second half of the first N number of data points;
calculating a first absolute value of a difference between the first left mean and the first right mean;
determining that the first absolute value of the difference is less than a threshold;
assigning a first value equal to the first mean to each data point of the first N number of data points;
calculating a second mean of a second number of data points, N, at least some of the second N number of data points being the same as data points of the first N number of data points;
calculating a second left mean comprising a mean of a first half of the second N number of data points;
calculating a second right mean comprising a mean of a second half of the second N number of data points;
calculating a second absolute value of a difference between the second left mean and the second right mean;
determining that the second absolute value of the difference is greater than the threshold;
assigning a second value equal to the second left mean to each data point of the first half of the second N number of data points;
assigning a third value equal to the second right mean to each data point of the second half of the second N number of data points;
and
generating a modified signal based at least in part on the first values, the second values, and the third values.

17 more elements

A method comprising:

generating, using one or weight sensors coupled to a platform, a signal representing a weight of one or more items on the platform;
calculating a first mean for a first portion of a first set of data points of the signal;
calculating a second mean for a second portion of the first set of data points;
comparing a difference between the first mean and the second mean to a threshold;
assigning, based at least in part on the comparing, a first value equal to the first mean to each data point of the first portion of the first set of data points;
assigning, based at least in part on the comparing, a second value equal to the second mean to each data point of the second portion of the first set of data points;
generating a modified signal based at least in part on the first value assigned to each data point of the first portion of the first set of data points and the second value assigned to each data point of the second portion of the first set of data points;
analyzing the modified signal to determine that the weight has changed by a least a threshold amount;
determining that at least one item has been removed from or placed onto the platform;
and
updating a virtual cart of a user to indicate that the at least one item has been removed from or placed onto the platform.

8 more elements

A system comprising:

one or more weight sensors coupled to a platform and configured to generate a signal, the signal corresponding to a weight of one or more items on the platform;
one or more processors;
and
one or more computer-readable media storing computer-executable instructions that, when executed on the one or more processors, cause the one or more processors to perform acts comprising:
receiving the signal representing the weight of one or more items on the platform;
analyzing a set of data points of the signal to determine a function to associate with the set of data points, the set having a size of N data points, each of the N data points corresponding to a respective time value between a time TA and a time TB, the N data points including a first data point;
assigning a particular value to the first data point based at least in part on the function;
incrementing a value of A and a value of B by a common amount, the common amount corresponding to a single data point of the signal;
repeating the analyzing, the associating, the assigning, and the incrementing at least N-1 number of times such that N particular values are assigned to the first data point;
determining a final value of the first data point based at least in part on the N particular values assigned to the first data point;
generating a modified signal based at least in part on the final value of the first data point;
analyzing the modified signal to determine that the weight has changed by a least a threshold amount;
determining that at least one item has been removed from or placed onto the platform;
and
updating a virtual cart of a user to indicate that the at least one item has been removed from or placed onto the platform.

12 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/199,030Filed 30 Jun 2016
Granted: 25 Jan 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

G06Q 10/087
Logistics, e.g. warehousing, loading or distribution; Inventory or stock management: inventory or stock management, e.g. order filling,…
G06F 7/02
Methods or arrangements for processing data by operating upon the order or content of the data handled: comparing digital values
G06Q 10/08741
Inventory fulfillment: by picking of items from inventory for fulfillment
G06Q 10/08772
By inventory control or reporting using inventory tracking or counting: inventory counting methods