NETWORK TROUBLE SHOOTING DIGITAL ASSISTANT SYSTEM

• US 20190319831A1
• Filed: 06/27/2019
• Published: 10/17/2019
• Est. Priority Date: 04/06/2017
• 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: Deb, Supratim, Sen, Subhabrata, Jamkhedkar, Pramod
• Granted Patent: US 10,764,116 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: H04L 41/0631 using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence

Abstract

A system for troubleshooting a network, the system comprising a virtual machine including a virtual central processor in communication with at least one memory, virtual machine including a knowledge base configured to store contextual information related to the network; a knowledge base manager in communication with the knowledge base, the knowledge base manager configured to collect at least one of contextual information and problem information from at least one data source on the network and populate the knowledge base; a problem monitor in communication with the knowledge base and the knowledge base manager, the problem monitor configured to receive the problem information from the knowledge base manager; a query evaluation engine in communication with the knowledge base and the problem monitor; an interface configured to receive a query; and a natural language query translator in communication with the interface and the query evaluation engine; wherein the natural language query translator is configured to provide a natural language query from the interface and transmit the query in a machine readable format to the query evaluation engine; wherein the query evaluation engine collects at least one of the contextual information in the knowledge base and the problem information in the problem manager relevant to the query and generate a recommendation list.

Claims

1. A system for troubleshooting a network, the system comprising:

a processor; and

a memory coupled to the processor, the memory storing executable instructions that when executed by the processor cause the processor to effectuate operations comprising;

receiving a first query, wherein the first query defines one or more problems in the network;

based on the first query, retrieving contextual information and problem information;

based on the retrieved contextual information and problem information, generating one or more recommendations, wherein each of the one or more recommendations comprises the contextual information or the problem information and at least one course of action;

analyzing an impact each course of action for the at least one course of action has on the network; and

based on the impact analysis, outputting a recommendation list to resolve the one or more problems defined in the first query, wherein the recommendation list comprises one or more of the generated recommendations.

2. The system of claim 1 further comprising:

receiving a selection of a recommendation from the recommendation list; and

based on the selected recommendation, updating the first query.

3. The system of claim 2 further comprising storing the selected recommendation and a resulting impact on performance for the network in response to performing the at least one course of action associated with the selected recommendation.

4. The system of claim 3 further comprising:

in response to the resulting impact on performance for the network, updating the recommendation list;

receiving a second query, wherein the second query defines one or more problems in the network associated with the first query; and

outputting the updated recommendation list to resolve the one or more problems defined in the second query.

5. The system of claim 2 further comprising:

in response to the selected recommendation, generating network performance data;

analyzing the performance data; and

based on the analysis of performance data, providing one or more follow-up recommendations to the one or more problems defined in the first query.

6. The system of claim 1, wherein the recommendation list is ordered based on an associated priority for each of the one or more of the generated recommendations.

7. The system of claim 1 further comprising evaluating the retrieved contextual information and problem information using at least one of:

fault localization and fault detection.

8. The system of claim 1, wherein the problem information comprises at least one of:

a history of problems for each network element or service relevant to the first query and solutions to problems relevant to the first query.

9. The system of claim 1, wherein the contextual information comprises at least one of:

a relationship of service elements and an interdependence of network elements.

10. A method for troubleshooting a network, the method comprising:

receiving a first query, wherein the first query defines one or more problems in the network;

based on the first query, retrieving contextual information and problem information;

based on the retrieved contextual information and problem information, generating one or more recommendations, wherein each of the one or more recommendations comprises the contextual information or the problem information and at least one course of action;

analyzing an impact each course of action for the at least one course of action has on the network; and

based on the impact analysis, outputting a recommendation list to resolve the one or more problems defined in the first query, wherein the recommendation list comprises one or more of the generated recommendations.

11. The method of claim 10 further comprising:

receiving a selection of a recommendation from the recommendation list; and

based on the selected recommendation, updating the first query.

12. The method of claim 11 further comprising storing the selected recommendation and a resulting impact on performance for the network in response to performing the at least one course of action associated with the selected recommendation.

13. The method of claim 12 further comprising:

in response to the resulting impact on performance for the network, updating the recommendation list;

receiving a second query, wherein the second query defines one or more problems in the network associated with the first query; and

outputting the updated recommendation list to resolve the one or more problems defined in the second query.

14. The method of claim 11 further comprising:

in response to the selected recommendation, generating network performance data;

analyzing the performance data; and

based on the analysis of performance data, providing one or more suggested alternate solutions to the one or more problems defined in the first query.

15. The method of claim 10, wherein the recommendation list is ordered based on an associated priority for each of the one or more of the generated recommendations.

16. The method of claim 10 further comprising evaluating the retrieved contextual information and problem information using at least one of:

fault localization and fault detection.

17. The method of claim 10, wherein the problem information comprises at least one of:

a history of problems for each network element or service relevant to the first query and solutions to problems relevant to the first query.

18. The method of claim 10, wherein the contextual information comprises at least one of:

a relationship of service elements and an interdependence of network elements.

19. A network device comprising:

a processor;

an input/output device coupled to the processor; and

a memory coupled with the processor, the memory comprising executable instructions that when executed by the processor cause the processor to effectuate operations comprising;

receiving a first query, wherein the first query defines one or more problems in the network;

based on the first query, retrieving contextual information and problem information;

based on the retrieved contextual information and problem information, generating one or more recommendations, wherein each of the one or more recommendations comprises the contextual information or the problem information and at least one course of action;

analyzing an impact each course of action for the at least one course of action has on the network; and

based on the impact analysis, outputting a recommendation list to resolve the one or more problems defined in the first query, wherein the recommendation list comprises one or more of the generated recommendations.

20. The network device of claim 19, wherein each of the one or more of the generated recommendations comprises a likelihood that an associated recommended solution will fix the one or more problems defined in the first query.