Optimization of multiple services via machine learning

• US 10,719,777 B2
• Filed: 07/28/2016
• Issued: 07/21/2020
• Est. Priority Date: 07/28/2016
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Gopalan, Raghuraman, Begeja, Lee, Gibbon, David Crawford, Liu, Zhu, Mu, Yadong, Renger, Bernard S., Shahraray, Behzad, Zavesky, Eric
• Primary Examiner(s): Taylor, Nicholas R
• Assistant Examiner(s): Roy, Sanjoy
• Application Number:
  US15/222,653
• Publication Number:
  US 20180034921A1
• Time in Patent Office: 1,454 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 41/00 Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
• CPC Class Codes: H04L 47/20 Traffic policing

Abstract

A method, computer-readable medium, and apparatus for modeling data of a service for providing a policy are disclosed. For example, a method may include a processor for generating a first policy for a first service by a first policy model using machine learning for processing first data of the first service, determining whether the first policy is to be applied to a second service, applying the first policy to the second service when the first policy is deemed to be applicable to the second service, wherein the applying the first policy provides the first policy to a second policy model using machine learning for processing second data of the second service, generating a second policy for the second service, and implementing the second policy in the second service, wherein the first service and the second service are provided by a single service provider.

Claims

1. A device comprising:

a processor; and

a computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising;

generating a first policy for a first service of a network by a first policy model for the first service using machine learning for processing first data of the first service, wherein the first policy defines a first action of the first service;

determining whether the first policy is to be applied to a second service of the network, wherein each of the first service and the second service comprises at least one of;

a landline telephony service, a cellular service, a data service, a multimedia delivery service, a connected car service, or a connected premises service, wherein the first service and the second service are different;

applying the first policy to the second service when the first policy is deemed to be applicable to the second service, wherein the applying the first policy provides the first policy to a second policy model for the second service using machine learning for processing second data of the second service;

generating a second policy for the second service, wherein the second policy defines a second action of the second service; and

implementing the second policy in the second service, wherein the implementing the second policy in the second service comprises generating a function for an autonomous system supporting the second service, wherein the autonomous system comprises a customer care system, wherein the function is inferred from at least one service feature of the first service via the first policy, wherein the at least one service feature comprises at least one of;

a privacy feature, a security feature, a billing feature, a performance feature, or a safety feature, and wherein the first service and the second service are provided by a single service provider.

2. The device of claim 1, the operations further comprising:

determining whether the second policy is to be applied to the first service; and

applying the second policy to the first service when the second policy is deemed to be applicable to the first service, wherein the applying the second policy provides the second policy to the first policy model.

3. The device of claim 2, wherein the determining whether the second policy is to be applied to the first service is based on a service feature of the second policy.

4. The device of claim 1, wherein the determining whether the first policy is to be applied to the second service is based on at least one of the at least one service feature of the first policy.

5. The device of claim 1, wherein the autonomous system further comprises at least one of:

a trouble ticketing system, a network provisioning system, a network maintenance scheduling system, or a network resource instantiation controller for the network, wherein the network comprises a software defined network.

6. The device of claim 1, wherein the machine learning comprises reinforcement learning.

19. The device of claim 1, wherein generating the second policy for the second service comprises generating the second policy for the second service based on at least the first policy and the second policy model.

7. A method comprising:

generating, by a processor, a first policy for a first service of a network by a first policy model for the first service using machine learning for processing first data of the first service, wherein the first policy defines a first action of the first service;

determining, by the processor, whether the first policy is to be applied to a second service of the network, wherein each of the first service and the second service comprises at least one of;

a landline telephony service, a cellular service, a data service, a multimedia delivery service, a connected car service, or a connected premises service, wherein the first service and the second service are different;

applying, by the processor, the first policy to the second service when the first policy is deemed to be applicable to the second service, wherein the applying the first policy provides the first policy to a second policy model for the second service using machine learning for processing second data of the second service;

generating, by the processor, a second policy for the second service, wherein the second policy defines a second action of the second service; and

implementing, by the processor, the second policy in the second service, wherein the implementing the second policy in the second service comprises generating a function for an autonomous system supporting the second service, wherein the autonomous system comprises a customer care system, wherein the function is inferred from at least one service feature of the first service via the first policy, wherein the at least one service feature comprises at least one of;

a privacy feature, a security feature, a billing feature, a performance feature, or a safety feature, and wherein the first service and the second service are provided by a single service provider.

8. The method of claim 7, further comprising:

determining, by the processor, whether the second policy is to be applied to the first service; and

applying, by the processor, the second policy to the first service when the second policy is deemed to be applicable to the first service, wherein the applying the second policy provides the second policy to the first policy model.

9. The method of claim 8, wherein the determining whether the second policy is to be applied to the first service is based on a service feature of the second policy.

10. The method of claim 7, wherein the determining whether the first policy is to be applied to the second service is based on at least one of the at least one service feature of the first policy.

11. The method of claim 7, wherein the autonomous system further comprises at least one of:

a trouble ticketing system, a network provisioning system, a network maintenance scheduling system, or a network resource instantiation controller for the network, wherein the network comprises a software defined network.

17. The method of claim 7, wherein the machine learning comprises reinforcement learning.

20. The method of claim 7, wherein generating the second policy for the second service comprises generating the second policy for the second service based on at least the first policy and the second policy model.

12. A tangible computer-readable medium storing instructions which, when executed by a processor, cause the processor to perform operations, the operations comprising:

generating a first policy for a first service of a network by a first policy model for the first service using machine learning for processing first data of the first service, wherein the first policy defines a first action of the first service;

determining whether the first policy is to be applied to a second service of the network, wherein each of the first service and the second service comprises at least one of;

a landline telephony service, a cellular service, a data service, a multimedia delivery service, a connected car service, or a connected premises service, wherein the first service and the second service are different;

applying the first policy to the second service when the first policy is deemed to be applicable to the second service, wherein the applying the first policy provides the first policy to a second policy model for the second service using machine learning for processing second data of the second service;

generating a second policy for the second service, wherein the second policy defines a second action of the second service; and

implementing the second policy in the second service, wherein the implementing the second policy in the second service comprises generating a function for an autonomous system supporting the second service, wherein the autonomous system comprises a customer care system, wherein the function is inferred from at least one service feature of the first service via the first policy, wherein the at least one service feature comprises at least one of;

a privacy feature, a security feature, a billing feature, a performance feature, or a safety feature, and wherein the first service and the second service are provided by a single service provider.

13. The tangible computer-readable medium of claim 12, the operations further comprising:

determining whether the second policy is to be applied to the first service; and

applying the second policy to the first service when the second policy is deemed to be applicable to the first service, wherein the applying the second policy provides the second policy to the first policy model.

14. The tangible computer-readable medium of claim 13, wherein the determining whether the second policy is to be applied to the first service is based on a service feature of the second policy.

15. The tangible computer-readable medium of claim 12, wherein the determining whether the first policy is to be applied to the second service is based on at least one of the at least one service feature of the first policy.

16. The tangible computer-readable medium of claim 12, wherein the machine learning comprises reinforcement learning.

18. The tangible computer-readable medium of claim 12, wherein generating the second policy for the second service comprises generating the second policy for the second service based on at least the first policy and the second policy model.