Application-independent detection of wireless environment impacts

Patent metadata

Field	Value
Publication number	US-12495322-B2
Application number	US-202318222329-A
Country	US
Kind code	B2
Filing date	Jul 14, 2023
Priority date	Jul 14, 2023
Publication date	Dec 9, 2025
Grant date	Dec 9, 2025

Abstract

A method in a computing device includes: monitoring, via a communications interface of the computing device, wireless data elements including application data corresponding to a communications application, and non-application data; automatically generating labels based on the application data of the wireless data elements, the labels indicating performance impacts observable in the communications application; selecting a portion of the wireless data elements corresponding to the non-application data; extracting, from each wireless data element of the non-application data, a set of feature values; generating a plurality of samples from the non-application data, each sample including (i) a number of the sets of feature values based on a sample size, and (ii) one of the automatically generated labels; training a classifier based on the plurality of samples, the classifier configured to receive further non-application data and generate a predicted impact indicator selected from the labels; and deploying the classifier.

First claim

The invention claimed is:

1 . A method in a computing device, the method comprising:
monitoring, via a communications interface of the computing device, wireless data elements including application data corresponding to a communications application, and non-application data; automatically generating labels based on the application data of the wireless data elements, the labels indicating performance impacts observable in the communications application; selecting a portion of the wireless data elements corresponding to the non-application data; extracting, from each wireless data element of the non-application data, a set of feature values; generating a plurality of samples from the non-application data, each sample including (i) a number of the sets of feature values based on a sample size, and (ii) one of the automatically generated labels; training a classifier based on the plurality of samples, the classifier configured to receive further non-application data and generate a predicted impact indicator selected from the labels; and deploying the classifier.

2 . The method of claim 1 , wherein deploying the classifier comprises providing the classifier to a wireless communications device.

3 . The method of claim 1 , wherein deploying the classifier comprises, at the computing device:
monitoring, via the communications interface, further wireless data elements; selecting a further portion of the wireless data elements excluding application data; extracting, from each wireless data element of the further portion, a further set of feature values; providing the further sets of feature values to the classifier; receiving, from the classifier, one of the performance impact indicators defining a predicted impact of the further sets of feature values observable in the communications application; and selecting an action based on the one of the performance impact indicators, to mitigate the predicted impact.

4 . The method of claim 1 , wherein automatically generating the labels comprises:
maintaining a plurality of label identifiers in association with respective labelling criteria; determining that a portion of the application data corresponding to a time period meets a labelling criterion; and generating a label having the label identifier and an indication of the time period.

5 . The method of claim 1 , wherein the application data includes application data corresponding to a plurality of categories of communications application; and
wherein automatically generating the labels includes automatically generating labels for each of the categories of communications application.

6 . The method of claim 5 , wherein the categories of communications application include at least one of:
voice call applications, video call applications, and file transfer applications.

7 . The method of claim 1 , wherein the set of feature values extracted from each wireless data element includes at least one of:
a signal strength indicator, a signal-to-noise indicator, an element subtype, and a time elapsed between the wireless data element and an adjacent wireless data element in the non-application data.

8 . The method of claim 1 , further comprising, prior to generating the plurality of samples, determining the sample size.

9 . The method of claim 8 , wherein determining the sample size comprises:
detecting a plurality of predetermined patterns in the wireless data elements, each pattern defined by a subset of consecutive wireless data elements; and determining the smallest subset of consecutive wireless data elements as the sample size.

10 . A computing device, comprising:
a communications interface; and a processor configured to:
monitor, via the communications interface, wireless data elements including application data corresponding to a communications application, and non-application data;
automatically generate labels based on the application data of the wireless data elements, the labels indicating performance impacts observable in the communications application;
select a portion of the wireless data elements corresponding to the non-application data;
extract, from each wireless data element of the non-application data, a set of feature values;
generate a plurality of samples from the non-application data, each sample including (i) a number of the sets of feature values based on a sample size, and (ii) one of the automatically generated labels;
train a classifier based on the plurality of samples, the classifier configured to receive further non-application data and generate a predicted impact indicator selected from the labels; and
deploy the classifier.

11 . The computing device of claim 10 , wherein the processor is configured to deploy the classifier by providing the classifier to a wireless communications device.

12 . The computing device of claim 10 , wherein the processor is configured to deploy the classifier by:
monitoring, via the communications interface, further wireless data elements; selecting a further portion of the wireless data elements excluding application data; extracting, from each wireless data element of the further portion, a further set of feature values; providing the further sets of feature values to the classifier; receiving, from the classifier, one of the performance impact indicators defining a predicted impact of the further sets of feature values observable in the communications application; and selecting an action based on the one of the performance impact indicators, to mitigate the predicted impact.

13 . The computing device of claim 10 , wherein the processor is configured to automatically generate the labels by:
maintaining a plurality of label identifiers in association with respective labelling criteria; determining that a portion of the application data corresponding to a time period meets a labelling criterion; and generating a label having the label identifier and an indication of the time period.

14 . The computing device of claim 10 , wherein the application data includes application data corresponding to a plurality of categories of communications application; and
wherein the processor is configured to automatically generate the labels by automatically generating labels for each of the categories of communications application.

15 . The computing device of claim 14 , wherein the categories of communications application include at least one of:
voice call applications, video call applications, and file transfer applications.

16 . The computing device of claim 10 , wherein the set of feature values extracted from each wireless data element includes at least one of:
a signal strength indicator, a signal-to-noise indicator, an element subtype, and a time elapsed between the wireless data element and an adjacent wireless data element in the non-application data.

17 . The computing device of claim 10 , wherein the processor is configured, prior to generating the plurality of samples, to determine the sample size.

18 . The computing device of claim 17 , wherein the processor is configured to determine the sample size by:
detecting a plurality of predetermined patterns in the wireless data elements, each pattern defined by a subset of consecutive wireless data elements; and determining the smallest subset of consecutive wireless data elements as the sample size.

19 . A method in a computing device, the method comprising:
maintaining, at the computing device, a wireless communications applicat

Assignees

• Zebra Tech Corp

Inventors

• Shatil Ohad
• Chen Jonathan

Classifications

• H04W92/10

  between terminal device and access point, i.e. wireless air interface · CPC title

• H04W84/02

  Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop] · CPC title

• H04W16/22

  Traffic simulation tools or models · CPC title

• H04W80/12

  Application layer protocols, e.g. WAP [Wireless Application Protocol] · CPC title

• H04W88/02

  Terminal devices · CPC title