Network trouble shooting digital assistant system

• US 10,355,912 B2
• Filed: 04/06/2017
• Issued: 07/16/2019
• 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
• Primary Examiner(s): Nguyen, Quang N
• Application Number:
  US15/480,768
• Publication Number:
  US 20180295013A1
• Time in Patent Office: 831 Days
• Field of Search: 709203, 709206, 709217, 709219, 709223, 709224, 709226, 709228, 709230, 709232, 709238, 707728, 707741, 703 11, 370254
• 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 virtual machine that acts a personal assistance agent in performing troubleshooting on the network, the virtual machine having a virtual central processor in communication with at least one memory, the 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 analyzes at least one of the contextual information in the knowledge base and the problem information in the problem monitor relevant to the query and generates a recommendation list;

wherein after generating the recommendation list, the query evaluation engine updates the knowledge base manager with the query, a recommendation selected via the interface, an impact on a problem identified in the query, and an impact on network elements.

2. The system of claim 1, wherein the problem monitor stores the problem information relevant to the query in a memory.

3. The system of claim 1, wherein the knowledge base stores the contextual information relevant to the query in a memory.

4. The system of claim 3, wherein the contextual information includes at least one of a representation of the network relevant to the query, performance data for network elements relevant to the query, past queries related to the query, past solutions relevant to the query, steps performed in attempting to resolve past queries relevant to the query, and the impact of past steps performed on the network.

5. The system of claim 1, wherein the knowledge base manager directs storage of the query and the recommendation list in a memory in at least one of the knowledge base and the problem monitor.

6. The system of claim 1, wherein the query evaluation engine stores a recommendation selected from the recommendation list, reevaluates the contextual information from knowledge base manager and problem manager to provide a follow up recommendation and prompt for a further query via the interface to form a network troubleshooting dialogue.

7. The system of claim 1, wherein the query evaluation engine is configured to provide an update to the knowledge base manager, the update including at least one of the query, the associated context for the query and the associated problems for the query.

8. The system of claim 1, wherein the problem monitor is configured to communicate updated problem information associated with the query to the knowledge base manager.

9. The system of claim 1, wherein the at least one data source includes at least one of a network topology, an event, an alarm, an interdependency, a relationship, a performance value, a key performance indicator, and a measurement related to a network element.

10. A personal assistance agent provided in 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 via the input/output device a troubleshooting query relating to at least one network via a query evaluation engine;

collecting contextual information relevant to the query;

obtaining problem information relevant to the query; and

outputting, via an interface, a recommendation list including at least one of a likelihood of success for each recommendation in the recommendation list and an impact of each recommendation in the recommendation list on the network;

wherein the processor is adapted to execute instructions received via an interface including;

translating the query from natural language to machine readable language;

wherein the processor executes instruction to provide a knowledge base manager and establish communication with at least one data source and populate a knowledge base within the memory with contextual information obtained by the knowledge base manager;

wherein the processor further executes instructions to instantiate a problem monitor in communication with the knowledge base the problem monitor being configured to identify problem information relevant to the query;

wherein the processor further executes instructions to update the knowledge base manager with the query, a recommendation selected via the interface, an impact on a problem identified in the query, and an impact on network elements.

11. The network device of claim 10, wherein the processor executes instructions to store at least one of the contextual information, the problem information and the recommendation list in association with the query in the memory.

12. A method comprising:

providing, a personal assistance agent on a network device comprising a knowledge base manager in communication with at least one data source within a network, the knowledge base manager being configured to obtain contextual information and problem information from the at least one data source;

receiving a query from an interface;

directing the query to a query evaluation engine;

obtaining at least one of the contextual information and the problem information relevant to the query and communicating the at least one of the contextual information and the problem information to the query evaluation engine;

analyzing the contextual information and problem information via the query evaluation engine;

generating via the query evaluation engine a recommendation list and communicating the recommendation list to the interface;

providing on the network device a knowledge base in communication with the knowledge base manager and storing at least one of the contextual information, the problem information, and the recommendation list relevant to the query in the knowledge base; and

updating the knowledge base manager with at least one of the contextual information, the problem information and the recommendation list associated with the query;

wherein after generating the recommendation list, updating the knowledge base manager with the query, a selection from the recommendation list, an impact on a problem identified in the query, and an impact on network elements.

13. The method of claim 12 wherein the query evaluation engine performs at least one of fault localization, fault detection, identifying component or system trends, what-if analysis, mitigation strategy, and pattern recognition based on at least one of the contextual information and problem information relevant to the query.