Resource selection using quality prediction

• US 10,084,665 B1
• Filed: 07/28/2017
• Issued: 09/25/2018
• Est. Priority Date: 07/25/2017
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Arunachalam, Chidambaram, Salgueiro, Gonzalo, Nainar, Nagendra Kumar, Chen, Eric, Griffin, Keith
• Primary Examiner(s): Tieu, Binh Kien
• Application Number:
  US15/663,655
• Time in Patent Office: 424 Days
• Field of Search: 370351, 370400, 370401
• CPC Class Codes: H04L 41/06 Management of faults, events, alarms or notifications
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 41/5009 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 Class Codes: H04L 43/04 Processing captured monitoring data, e.g. for logfile generation
• CPC Class Codes: H04L 43/062 related to network traffic
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 43/0829 Packet loss
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/10 Active monitoring, e.g. heartbeat, ping or trace-route
• CPC Class Codes: H04L 47/82 Miscellaneous aspects
• CPC Class Codes: H04L 47/83 based on usage prediction
• CPC Class Codes: H04L 65/102 Gateways arrangements for connecting between networks having differing types of switching systems, e.g. gateways, H04L12/66
• CPC Class Codes: H04L 65/1023 Media gateways
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04L 65/80 Responding to QoS
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/75 Indicating network or usage conditions on the user display
• CPC Class Codes: H04M 2203/556 Statistical analysis and interpretation
• CPC Class Codes: H04M 3/2218 : Call detail recording
• CPC Class Codes: H04M 3/2227 : Quality of service monitoring
• CPC Class Codes: H04M 7/0027 : Collaboration services where a computer is used for data transfer and the telephone is used for telephonic communication
• CPC Class Codes: H04M 7/006 : Networks other than PSTN/ISDN providing telephone service, e.g. Voice over Internet Protocol (VoIP) , including next generation networks with a packet-switched transport layer H04L65/00 takes precedence; aspects not specific to the type of network H04M3/00; special services in those networks H04M3/42
• CPC Class Codes: H04M 7/1285 : Details of finding and selecting a gateway for a particular call
• CPC Class Codes: H04Q 2213/13514 : quality of service - inc. grade of service

Abstract

Disclosed is a system and method for receiving a communication session request and identifying a plurality of available gateways available to handle the communication session request. For each gateway of the plurality of available gateways, gateway metrics of the performance of the gateway are predicted. Based on the predicted gateway metrics, a user rating for the communication session request being handled by the gateway is predicted. Based on the predicted user rating for each gateway, a gateway is selected from the plurality of available gateways.

Claims

1. A computer-implemented method for selecting a media gateway, the method comprising:

receiving a communication session request;

identifying a plurality of available gateways available to handle the communication session request, and for each gateway of the plurality of available gateways;

predicting gateway metrics of the performance of the gateway; and

based on the predicted gateway metrics, predicting a user rating for the communication session request being handled by the gateway;

selecting a gateway from the plurality of available gateways based on the predicted user rating for each gateway.

2. The computer-implemented method of claim 1, wherein predicting gateway metrics of the performance of the gateway comprises:

receiving historical network information and historical gateway metrics corresponding to the historical network information;

generating a predictive model of gateway metrics; and

based on current network information and the predictive model of gateway metrics, generating predicted gateway metrics of the performance of the gateway.

3. The computer-implemented method of claim 2, wherein the predictive model of gateway metrics is generated by training a first machine learning module on the historical network information and historical gateway metrics.

4. The computer-implemented method of claim 2, wherein predicting a user rating for the communication session request being handled by the gateway comprises:

receiving historical client attributes associated with a client device and historical gateway metrics;

receiving historical user ratings corresponding to the historical client attributes and the historical gateway metrics;

generating a predictive model of user ratings; and

based on current client attributes, the predicted gateway metrics, and the predictive model of user ratings, generating predicted user ratings for the communication session request being handled by the gateway.

5. The computer-implemented method of claim 4, wherein the predictive model of user ratings is generated by training a second machine learning module on the historical client attributes, the historical gateway metrics, and the historical user ratings.

6. The computer-implemented method of claim 2, wherein one or more of the historical network information, the historical gateway metrics, and the historical client attributes are polled and collected or updated at a pre-defined interval.

7. The computer-implemented method of claim 1, wherein the gateway metrics include one or more of packet loss, jitter, and delay.

8. The computer-implemented method of claim 4, wherein the client attributes include one or more of time of day, day of week, device type, connectivity type, media gateway or user rating.

9. The computer-implemented method of claim 4, wherein the current client attributes and the predicted gateway metrics are combined before generating predicted user ratings.

10. The computer-implemented method of claim 1, wherein selecting a gateway from the plurality of available gateways further comprises:

ranking the predicted user ratings of each gateway of the plurality of gateways; and

selecting the gateway of the plurality of gateways with the highest ranking.

11. The computer-implemented method of claim 10, wherein two or more gateways of the plurality of available gateways are equally ranked and ranking further comprises assigning the higher ranking to the gateway that is in closer proximity to a device initiating the communication session request.

12. A system comprising:

one or more processors; and

at least one computer-readable storage medium having stored therein instructions which, when executed by the one or more processors, cause the system to;

receive a communication session request;

identify a plurality of available gateways available to handle the communication session request, and for each gateway of the plurality of available gateways;

predict gateway metrics of the performance of the gateway; and

based on the predicted gateway metrics, predict a user rating for the communication session request being handled by the gateway;

select a gateway from the plurality of available gateways based on the predicted user rating for each gateway.

13. The system of claim 12, wherein the instructions which cause the system to predict gateway metrics of the performance of the gateway comprise instructions which cause the system to:

receive historical network information and historical gateway metrics corresponding to the historical network information;

train a first machine learning module on the historical network information and historical gateway metrics;

generate, based on the first machine learning module, a predictive model of gateway metrics; and

based on current network information and the predictive model of gateway metrics, generate predicted gateway metrics of the performance of the gateway.

14. The system of claim 13, wherein the instructions which cause the system to predict a user rating for the communication session request being handled by the gateway comprise instructions which cause the system to:

receive historical client attributes associated with a client device and historical gateway metrics;

receive historical user ratings corresponding to the historical client attributes and the historical gateway metrics;

train a second machine learning module on the historical client attributes, the historical gateway metrics, and the historical user ratings

generate, based on the second machine learning module, a predictive model of user ratings; and

based on current client attributes, the predicted gateway metrics, and the predictive model of user ratings, generate predicted user ratings for the communication session request being handled by the gateway.

15. The system of claim 14, wherein one or more of the historical network information, the historical gateway metrics, and the historical client attributes are polled and collected or updated at a pre-defined interval.

16. The system of claim 12, wherein the gateway metrics include one or more of packet loss, jitter, and delay.

17. The system of claim 12, wherein the historical network information is added after a first threshold time period and removed after a second threshold time period.

18. The system of claim 14, wherein the client attributes include one or more of time of day, day of week, device type, connectivity type, media gateway or user rating.

19. The system of claim 12, wherein the instructions which cause the system to select a gateway from the plurality of available gateways further comprise instructions which cause the system to:

rank the predicted user ratings of each gateway of the plurality of gateways; and

select the gateway of the plurality of gateways with the highest ranking.

20. The system of claim 19, wherein two or more gateways of the plurality of available gateways are equally ranked and ranking further comprises assigning the higher ranking to the gateway that is in closer proximity to a device initiating the communication session request.