Discovery of computer code actions and parameters

1. A system, comprising:

a memory that stores computer executable components; and

a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:

an analysis component that:

selects documents that exceed a threshold rank from ranked documents in a question and answer repository, wherein the documents comprise questions related to computer-related tasks and answers to the questions,

parses, using a natural language processing technique, text of the questions and the answers in the documents to identify parameters and computer code actions in the text of the documents,

employs an autoencoder that:

applies topic labels to the questions and the answers based on the identified parameters and computer code actions,

maps the questions and answers to clusters based on the topic labels, and

generates a knowledge base based on the clusters of questions and answers;

a query component that receives a query associated with a computer-related task; and

a result component that:

performs a sentiment analysis on comments associated with the answers in the documents to determine respective efficacies of the computer code actions, and

selects a result from a cluster of the knowledge base based on the respective efficacies of the computer code actions and a mapping of the query to the result, the mapping being based on one or more parameters identified in the result and a criterion.

2. The system of claim 1 , wherein the criterion comprises a degree of similarity between the query and the one or more parameters identified in the result.

3. The system of claim 1 , wherein the result comprises at least one of a change ticket or a service ticket.

4. The system of claim 1 , wherein the computer executable components further comprise a transforming component that transforms at least one of the query or the result, based on a regular expression.

5. The system of claim 1 , wherein the one or more parameters are associated with the computer code actions.

6. The system of claim 1 , further comprising a parameter component that identifies a context for the one or more parameters, wherein the context comprises an environment for executing the computer code actions for the one or more parameters, and wherein the mapping is further based on the context of the one or more parameters identified in the result.

7. The system of claim 6 , wherein the context comprises at least one of, for the executing the computer code actions, a pre-condition, a post-condition, an application, or an operating system.

8. The system of claim 1 , wherein the computer executable components further comprise a validating component that validates the one or more parameters identified in the result based on at least one of, feedback or source documentation, of the one or more parameters identified in the result.

9. The system of claim 1 , wherein the mapping is further based on the topic labels.

10. A computer-implemented method, comprising:

selecting, by a system operatively connected to a processor, documents that exceed a threshold rank from ranked documents in a question and answer repository, wherein the documents comprise questions related to computer-related tasks and answers to the questions;

parsing, by the system, using a natural language processing technique, text of the questions and the answers in the documents to identify parameters and computer code actions in the text of the documents;

employing, by the system, an autoencoder that:

applies topic labels to the questions and the answers based on the identified parameters and computer code actions,

maps the questions and answers to clusters based on the topic labels, and

generates a knowledge base based on the clusters of questions and answers;

receiving, by the system, a query associated with a computer-related task;

determining, by the system, respective efficacies of the computer code actions in the results based on a sentiment analysis of comments associated with the answers in the documents; and

selecting, by the system, a result from a cluster of the knowledge base based on the respective efficacies of the computer code actions and a mapping of the query to the result, the mapping being based on one or more parameters identified in the result and a criterion.

11. The computer-implemented method of claim 10 , wherein the criterion comprises a degree of similarity between the query and the one or more parameters identified in the result.

12. The computer-implemented method of claim 10 , wherein the result comprise at least one of a change ticket or a service ticket.

13. The computer-implemented method of claim 10 , further comprising, transforming, by the system, at least one of the query or the result, based on a regular expression.

14. The computer-implemented method of claim 10 , wherein the one or more parameters are associated with the computer code actions.

15. The computer-implemented method of claim 10 , further comprising, identifying, by the system, a context for the one or more parameters, wherein the context comprises an environment for executing the computer code actions for the one or more parameters, and wherein the mapping is further based on the context of the one or more parameters identified in the result.

16. The computer-implemented method of claim 15 , wherein the context comprises at least one of, for the executing the computer code actions, a pre-condition, a post-condition, an application, or an operating system.

17. The computer-implemented method of claim 10 , further comprising validating the one or more parameters identified in the result based on at least one of, feedback or source documentation, of the one or more parameters identified in the result.

18. The computer-implemented method of claim 10 , wherein the mapping is further based on the topic labels.

19. A computer program product facilitating a selection of results, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

selecting documents that exceed a threshold rank from ranked documents in a question and answer repository, wherein the documents comprise questions related to computer-related tasks and answers to the questions;

parsing using a natural language processing technique, text of the questions and the answers in the documents to identify parameters and computer code actions in the text of the documents;

employing an autoencoder that:

applies topic labels to the questions and the answers based on the identified parameters and computer code actions,

maps the questions and answers to clusters based on the topic labels, and

generates a knowledge base based on the clusters of questions and answers;

receiving a query associated with a computer-related task;

determine respective efficacies of the computer code actions in the results based on a sentiment analysis of comments associated with the answers in the documents; and

select a result from a cluster of the knowledge base based on the respective efficacies of the computer code actions and a mapping of the query to the result, the mapping being based on one or more parameters identified in the result and a criterion.

20. A computer program product of claim 19 , wherein the criterion comprises a degree of similarity between the query and the one or more parameters identified in the result.