Systems and methods for remote collaboration

Patent metadata

Field	Value
Publication number	US-11411840-B2
Application number	US-202117223790-A
Country	US
Kind code	B2
Filing date	Apr 6, 2021
Priority date	Apr 7, 2020
Publication date	Aug 9, 2022
Grant date	Aug 9, 2022

Abstract

Described herein are systems and methods for work from home solutions according to various embodiments of the invention. These solutions accurately diagnose connectivity issue locations and severity from any, some, or all points in a network framework. Embodiments of these solutions may also use artificial intelligence and machine learning to process customer quality-of-experience (QoE) feedback and other relevant indicators. The solutions may improve network connectivity based on these measurements and processes.

First claim

What is claimed is:

1. A method comprising:
accessing data relating to one or more network devices and/or connections, the data comprising at least quality of service (QoS) data and quality of experience (QoE) data, the QoS data providing an objective measure of connection quality for an associated network connection, and the QoE data providing a measure of user experience for an associated network connection or application software; and
training a QoE estimator model for generating estimated QoE data from QoS data, wherein the QoE estimator model uses a machine learning method in which the QoS data are used as input data and the QoE data are used to define one or more labels such that the QoE estimator model determines a respective estimator for each of the one or more labels based on the input data.

2. The method of claim 1 wherein the accessed data comprise current and/or historical data relating to the one or more network devices and/or connections.

3. The method of claim 1 wherein the input data further comprise timing data which provide time spans and/or time stamps associated with the QoS data and the QoE data.

4. The method of claim 1 wherein the QoE data comprise real time user feedback data and/or delayed user feedback data.

5. The method of claim 1 wherein the QoE data comprise direct user feedback data and/or indirect user feedback data.

6. A method comprising:
accessing data relating to one or more network devices and/or connections, wherein each datum is associated with one or more applications from a plurality of applications;
selecting at least one application of interest from the plurality of applications; and
analysing the data to determine an application-specific connectivity (ASC) metric that is indicative of the effect of connection quality on user productivity for the at least one application of interest; wherein the ASC metric is determined using an ASC model trained on ASC training data, the ASC training data comprising current and/or historical data relating to the one or more network devices and/or connections, the ASC training data comprising at least quality of service (QoS) data and associated quality of experience (QoE) data, the QoS data providing an objective measure of connection quality for an associated network connection, and the QoE data providing a measure of user experience for an associated network connection or application software.

7. The method of claim 6 wherein the at least one application of interest comprises one or more application software associated with WFH activities and/or remote learning/teaching and/or telemedicine and/or other virtual gatherings and/or distribution of streaming entertainment media and/or security-camera systems and/or sensors and/or smart-home appliances.

8. The method of claim 6 wherein the ASC metric for the at least one application of interest may further be determined based on an ASC metric for at least one other application of interest.

9. The method of claim 6 wherein the ASC metric is individually determined for each network connection associated with the at least one application of interest.

10. The method of claim 6 wherein the ASC metric is aggregated over multiple network connections associated with the at least one application of interest.

11. The method of clause 10 wherein the multiple network connections over which the ASC metric is aggregated comprise those network connections associated with a single home network.

12. The method of claim 6 wherein the accessed data comprise one or more of: data from one or more internet service providers (ISPs); data from one or more home networks; data from one or more application servers; data from one or more user devices; and data from one or more stakeholders (e.g. employers).

13. The method of claim 6 wherein accessed data comprise one or more of: QoS data; QoE data; productivity data which provide a measure of user productivity for an associated network connection; user preference data which provide user preferences associated with a particular network device or connection; configuration data which provide configuration settings associated with a particular network device or connection; and timing data which provide time spans and/or time stamps associated with particular types of data.

14. A method comprising:
accessing data relating to one or more network devices and/or connections, the data comprising quality of service (QoS) data and further comprising quality of experience (QoE) data and/or productivity data, the QoS data providing an objective measure of connection quality for an associated network connection, the QoE data providing a measure of user experience for an associated network connection or application software, and the productivity data providing a measure of user productivity for an associated network connection; and
training a productivity estimator model for generating estimated productivity data from QoS data, wherein the productivity estimator model uses a machine learning method in which the QoS data are used as input data and the QoE data and/or productivity data are used to define one or more labels such that the productivity estimator model determines a respective estimator for each of the one or more labels based on the input data.

15. The method of claim 14 wherein the QoS data and/or the QoE data and/or the productivity data are normalised for use in the productivity estimator model.

16. The method of claim 14 wherein the productivity estimator model is optimized/derived over all linear functions of the input data.

17. The method of claim 14 wherein the productivity estimator model is further based on application software data which provide data regarding one or more application software associated with a particular network device or connection of the one or more network devices and/or connections.

18. The method of claim 14 wherein the productivity estimator model is able to be updated based on additional data relating to the one or more network devices and/or connections.

19. The method of claim 14 further comprising using the productivity estimator model to subsequently generate predicted productivity data from predicted QoS data.

20. The method of claim 14 wherein the productivity estimator model is further based on user preference data which provide user preferences associated with a particular network device or connection of the one or more network devices and/or connections.

Assignees

• Assia Spe Llc

Inventors

• Cioffi John M
• Hwang Chan-Soo
• Silverman Peter Joshua
• Cil Tuncay
• Bednarz Philip
• Chow Peter
• Garcia Hernandez Carlos

Classifications

• H04L41/5019 Primary

  Ensuring fulfilment of SLA · CPC title

• G06Q10/103

  Workflow collaboration or project management · CPC title

• H04L41/5009

  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

• H04L41/5016 Primary

  based on statistics of service availability, e.g. in percentage or over a given time · CPC title

• H04L41/5006

  Creating or negotiating SLA contracts, guarantees or penalties · CPC title