System and method for auto-determining solutions for dynamic issues in a distributed network

1. A system comprising:

a memory operable to store:

a plurality of sets of previous data objects associated with corresponding previous application issues and issue patterns associated with corresponding applications, wherein each data object represents an operation status of a corresponding application, wherein each issue pattern represents one or more recurring operation status of the corresponding application, and

a plurality of series of executable operations for solving the previous application issues; and

a processor operably coupled to the memory, the processor configured to:

detect an application issue associated with an application running at a network node at a particular timestamp;

receive a set of data objects associated with the application issue;

classify, by a machine learning model, the set of the data objects of the application issue into one or more issue patterns, wherein the machine learning model is trained based on the plurality of sets of the data objects and corresponding issue patterns associated with the corresponding previous application issues;

process, through a neural network, the one or more issue patterns and application information associated with the application issue at the network node to determine a series of executable operations for solving the application issue, wherein the neural network is trained based on the plurality of the issue patterns and associations between the issue patterns and the plurality of series of the executable operations; and

deploy the series of the executable operations to solve the application issue at the network node to prevent a failure operation of the application.

2. The system of claim 1 , wherein the previous data objects and the previous application issues are associated with corresponding executable operations for the same application running on different network nodes in a distributed network, and

wherein the previous data objects and the previous application issues are associated with the corresponding applications operating on the same network node in the distributed network.

3. The system of claim 2 , wherein the processor is further configured to:

identify a plurality of issue patterns from the plurality of sets of the data objects by classifying the plurality of sets of the previous data objects; and

determine associations between the issue patterns and corresponding executable operations for solving the previous application issues,

wherein the plurality of sets of the data objects comprise vector representations of the corresponding operation status associated with the previous application issues.

4. The system of claim 3 , wherein the processor is further configured to:

determine, by the neural network, a solution identifier for each series of executable operations associated with a corresponding application issue; and

associate the corresponding solution identifier with the issue pattern and the corresponding application issue.

5. The system of claim 1 , wherein the processor is further configured to:

determine whether the network node is communicating with the processor;

in response to determining that the network node is communicating with the processor, deploy the series of the executable operations to the network node to solve the application issue to prevent a failure operation of the application; and

determine a deployment result of the application.

6. The system of claim 1 , wherein the series of the executable operations comprises one or more of:

a solution identifier,

an issue pattern identifier,

an issue identifier indicative of the application issue,

an application identifier,

a network node identifier indicative of a network node address,

a current status of the application associated with the application issue, or

a set of executable instructions for solving the application issue.

7. The system of claim 1 , wherein the application information comprises textual data of an operation status of the application, and the operation status of the application comprises one or more measurable features of CPU utilization, memory capacity, memory utilization, memory boundary, data accessibility associated with the application, network node address, network node status, input data, output data, or an application issue statement.

8. A method comprising:

detecting an application issue associated with an application running at a network node at a particular timestamp;

receiving a set of data objects associated with the application issue;

classifying, by a machine learning model, the set of the data objects of the application issue into one or more issue patterns, wherein the machine learning model is trained based on a plurality of sets of the data objects and corresponding issue patterns associated with corresponding previous application issues;

processing, through a neural network, the one or more issue patterns and application information associated with the application issue at the network node to determine a series of executable operations for solving the application issue, wherein the neural network is trained based on the plurality of the issue patterns and associations between the issue patterns and the plurality of series of the executable operations; and

deploying the series of the executable operations for solving the application issue at the network node to prevent a failure operation of the application.

9. The method of claim 8 , wherein the previous data objects and the previous application issues are associated with corresponding executable operations for the same application running on different network nodes in a distributed network, and

wherein the previous data objects and the previous application issues are associated with the corresponding applications operating on the same network node in the distributed network.

10. The method of claim 9 , further comprising:

identifying a plurality of issue patterns from the plurality of sets of the data objects by classifying the plurality of sets of the previous data objects; and

determining associations between the issue patterns and corresponding executable operations for solving the previous application issues,

wherein the plurality of sets of the data objects comprise vector representations of the corresponding operation status associated with the previous application issues.

11. The method of claim 10 , further comprising:

determining, by the neural network, a solution identifier for each series of executable operations associated with a corresponding application issue; and

associating the corresponding solution identifier with the issue pattern and the corresponding application issue.

12. The method of claim 8 , further comprising:

determining whether the network node is communicating with the processor;

in response to determining that the network node is communicating with the processor, deploying the series of the executable operations to the network node, wherein the series of the executable operations is configured to be automatically executed at the network node to solve the application issue; and

determining a deployment result of the application.

13. The method of claim 8 , wherein the series of the executable operations comprises one or more of:

a solution identifier,

an issue pattern identifier,

an issue identifier indicative of the application issue,

an application identifier,

a network node identifier indicative of a network node address,

a current status of the application associated with the application issue, or

a set of executable instructions for solving the application issue.

14. The method of claim 8 , wherein the application information comprises textual data of an operation status of the application, and the operation status of the application comprises one or more measurable features of CPU utilization, memory capacity, memory utilization, memory boundary, data accessibility associated with the application, network node address, network node status, input data, output data, or an application issue statement.

15. A non-transitory computer-readable medium storing instructions that when executed by a processor cause the processor to:

detect an application issue associated with an application running at a network node at a particular timestamp;

receive a set of data objects associated with the application issue;

classify, by a machine learning model, the set of the data objects of the application issue into one or more issue patterns, wherein the machine learning model is trained based on a plurality of sets of the data objects and corresponding issue patterns associated with corresponding previous application issues;

process, through a neural network, the one or more issue patterns and application information associated with the application issue at the network node to determine a series of executable operations for solving the application issue, wherein the neural network is trained based on the plurality of the issue patterns and associations between the issue patterns and the plurality of series of the executable operations; and

deploy the series of the executable operations to solve the application issue at the network node to prevent a failure operation of the application.

16. The non-transitory computer-readable medium of claim 15 , wherein the previous data objects and the previous application issues are associated with corresponding executable operations for the same application running on different network nodes in a distributed network, and

wherein the previous data objects and the previous application issues are associated with the corresponding applications operating on the same network node in the distributed network.

17. The non-transitory computer-readable medium of claim 16 , wherein the instructions further cause the processor to:

identify a plurality of issue patterns from the plurality of sets of the data objects by classifying the plurality of sets of the previous data objects; and

determine associations between the issue patterns and corresponding executable operations for solving the previous application issues,

wherein the plurality of sets of the data objects comprise vector representations of the corresponding operation status associated with the previous application issues.

18. The non-transitory computer-readable medium of claim 17 , wherein the instructions further cause the processor to:

determine, by the neural network, a solution identifier for each series of executable operations associated with a corresponding application issue; and

associate the corresponding solution identifier with the issue pattern and the corresponding application issue.

19. The non-transitory computer-readable medium of claim 15 , wherein the instructions further cause the processor to:

determine whether the network node is communicating with the processor;

in response to determining that the network node is communicating with the processor, deploy the series of the executable operations to the network node, wherein the series of the executable operations is configured to be automatically executed at the network node to solve the application issue; and

determine a deployment result of the application.

20. The non-transitory computer-readable medium of claim 15 , wherein the series of the executable operations comprises one or more of:

a solution identifier,

an issue pattern identifier,

an issue identifier indicative of the application issue,

an application identifier,

a network node identifier indicative of a network node address,

a current status of the application associated with the application issue, or

a set of executable instructions for solving the application issue, and

wherein the application information comprises textual data of an operation status of the application, and the operation status of the application comprises one or more measurable features of CPU utilization, memory capacity, memory utilization, memory boundary, data accessibility associated with the application, network node address, network node status, input data, output data, or an application issue statement.