Evaluating 3G and voice over long term evolution voice quality

Patent metadata

Field	Value
Publication number	US-9119086-B1
Application number	US-201414273433-A
Country	US
Kind code	B1
Filing date	May 8, 2014
Priority date	May 8, 2014
Publication date	Aug 25, 2015
Grant date	Aug 25, 2015

Abstract

Systems and methods for evaluating cellular voice call quality are disclosed. In some implementations, training data points are received. Each data point includes a call quality value and values of key performance indicators (KPIs) related to call quality. For each KPI, a linear relationship, having a goodness-of-fit value, between the KPI and the call quality value is determined using the multiple data points. Compulsory KPIs are selected based on the goodness-of-fit values. The training data points are separated into clusters based on the compulsory KPI values and the quality values. For each cluster, a mathematical relationship for calculating the call quality within the cluster is determined based on the one or more compulsory KPIs. A module is generated for predicting the call quality value by combining the determined mathematical relationships.

First claim

What is claimed is:

1. A method comprising:
receiving, at a computing device, a plurality of training data points, wherein each data point in the plurality of training data points includes a cellular voice call quality value and values for at least a subset of a set of key performance indicators (KPIs) related to cellular voice call quality;
determining, for each KPI in the set of KPIs and the using the plurality of training data points, a linear relationship between the KPI and the cellular voice call quality value, wherein each linear relationship is associated with a goodness of fit value;
selecting, based on the goodness of fit values, one or more compulsory KPIs;
separating the plurality of training data points into a plurality of clusters based on at least one of the compulsory KPI values or the cellular voice call quality values;
determining, for each cluster in the plurality of clusters and using the plurality of training data points in the cluster, a mathematical relationship for calculating the cellular voice call quality within the cluster based on the one or more compulsory KPIs;
generating a module for predicting the cellular voice call quality value by combining the determined mathematical relationships; and
reporting, based on information generated using the module, that changing one or more of the compulsory KPI values would improve the cellular voice call quality.

2. The method of claim 1 , further comprising:
providing, via the computing device, an indication that the module has been generated.

3. The method of claim 1 , further comprising:
calculating the goodness of fit value associated with each linear relationship using a regression analysis technique.

4. The method of claim 1 , further comprising:
predicting, using the generated module, a new cellular voice call quality value based on input KPIs; and
providing, via the computing device, an indication of one or more of the input KPIs to change for improving the predicted cellular voice call quality value in a case where the predicted cellular voice call quality value is insufficient.

5. The method of claim 1 , wherein the cellular voice call quality value comprises a Perceptual Objective Listening Quality Assessment (POLQA) score.

6. The method of claim 1 , further comprising:
selecting, based on the goodness of fit values, one or more optional KPIs different from the one or more compulsory KPIs, wherein the mathematical relationship for calculating the cellular voice call quality is based on the one or more compulsory KPIs and at least one of the one or more optional KPIs.

7. The method of claim 6 , wherein:
the one or more compulsory KPIs have goodness of fit values below a first threshold value; and
the one or more optional KPIs have goodness of fit values exceeding the first threshold value and below a second threshold value.

8. The method of claim 1 , wherein:
separating the plurality of training data points into the plurality of clusters based on the compulsory KPI values or the cellular voice call quality values comprises:
separating the plurality of data points into different numbers of clusters, wherein each of the different numbers is greater than or equal to two; and
determining, based on the plurality of training data points, which of the numbers of clusters results in a most accurate module for predicting the cellular voice call quality.

9. The method of claim 1 , wherein the plurality of training data points comprise measured data points from a mobile device or an audio sample in a long term evolution (LTE) cellular network.

10. A non-transitory computer-readable medium comprising instructions which, when executed by a computer, cause the computer to:
receive, at the computer, a plurality of training data points, wherein each data point in the plurality of training data points includes a cellular voice call quality value and values for at least a subset of a set of key performance indicators (KPIs) related to cellular voice call quality;
determine, for each KPI in the set of KPIs and the using the plurality of training data points, a linear relationship between the KPI and the cellular voice call quality value, wherein each linear relationship is associated with a goodness of fit value;
select, based on the goodness of fit values, one or more compulsory KPIs;
separate the plurality of training data points into a plurality of clusters based on at least one of the compulsory KPI values or the cellular voice call quality values;
determine, for each cluster in the plurality of clusters and using the plurality of training data points in the cluster, a mathematical relationship for calculating the cellular voice call quality within the cluster based on the one or more compulsory KPIs;
generate a module for predicting the cellular voice call quality value by combining the determined mathematical relationships; and
report, based on information generated using the module, that changing one or more of the compulsory KPI values would improve the cellular voice call quality.

11. The computer-readable medium of claim 10 , further comprising instructions which, when executed by the computer, cause the computer to:
provide an indication that the module has been generated.

12. The computer-readable medium of claim 10 , further comprising instructions which, when executed by the computer, cause the computer to:
calculate the goodness of fit value associated with each linear relationship using a regression analysis technique.

13. The computer-readable medium of claim 10 , further comprising instructions which, when executed by the computer, cause the computer to:
predict, using the generated module, a new cellular voice call quality value based on input KPIs; and
provide, via the computer, an indication of one or more of the input KPIs to change for improving the predicted cellular voice call quality value in a case where the predicted cellular voice call quality value is insufficient.

14. The computer-readable medium of claim 10 , wherein the cellular voice call quality value comprises a Perceptual Objective Listening Quality Assessment (POLQA) score.

15. The computer-readable medium of claim 10 , further comprising instructions which, when executed by the computer, cause the computer to:
select, based on the goodness of fit values, one or more optional KPIs different from the one or more compulsory KPIs, wherein the mathematical relationship for calculating the cellular voice call quality is based on the one or more compulsory KPIs and at least one of the one or more optional KPIs.

16. The computer-readable medium of claim 15 , wherein:
the one or more compulsory KPIs have goodness of fit values below a first threshold value; and
the one or more optional KPIs have goodness of fit values exceeding the first threshold value and below a second threshold value.

17. The computer-readable medium of claim 10 , wherein:
the instructions to separate the plurality of training data points into the plurality of clusters based on the compulsory KPI values or the cellular voice call quality values comprise instructions which, when executed by the computer, cause the computer to:
separate the plurality of data points into different numbers of clusters, wherein each of the different numbers is greater than or equal to two; and
determine, based on the plurality of training data points, which of the numbers of clusters results in a most accurate module for predicting the cellular voice call quality.

18. The computer-readable medium of claim 11 , where

Assignees

• Cellco Partnership Dba Verizon

Inventors

• Ouyang Ye
• Becht Carol
• Lowe Benjamin

Classifications

• H04W24/10

  Scheduling measurement reports {; Arrangements for measurement reports} · CPC title

• H04W24/02 Primary

  Arrangements for optimising operational condition · CPC title

• H04L41/5009 Primary

  Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF] · CPC title

• H04L41/5087

  wherein the managed service relates to voice services (management of VoIP services H04M7/0081) · CPC title

• H04L43/0829

  Packet loss · CPC title