Generating an AI conversation model using API test data

1. A computer-implemented method comprising:

generating an intent representative of a verb identified in application programming interface (API) test data associated with an API test case;

generating a first entity representative of a first noun identified in the API test data and a second entity representative of a second noun identified in the API test data associated with the API test case;

identifying the intent as being associated with a relationship between the first entity and the second entity in the API test case;

generating a first relationship model associated with the API test case, wherein the relationship model comprises the intent as the relationship between the first entity and the second entity; and

generating a conversation model of an artificial intelligence (AI) conversation agent by mapping the intent and the first and second entities to dialog nodes of the conversation model.

2. The computer-implemented method according to claim 1 , further comprising:

parsing, by a processor using natural language processing, the API test data, wherein the parsing results include identification of the verb and identification of the first and second nouns.

3. The computer-implemented method according to claim 1 , wherein the generating of the first relationship model comprises generating a parent node representative of the first entity, a child node representative of the second entity, and an edge representative of the intent, wherein the edge connects the parent node and the child node.

4. The computer-implemented method according to claim 1 , further comprising:

associating the first relationship model with a first query type;

generating a second relationship model associated with the API test case; and

associating the second relationship model with a second query type.

5. The computer-implemented method according to claim 4 , further comprising:

identifying the first and second entities as being part of an API request being tested by the API test case;

generating a third entity representative of a third noun identified in the API test data; and

identifying the third entity as being part of an expected response to the API request.

6. The computer-implemented method according to claim 5 , wherein the generating of the second relationship model comprises:

generating a parent node representative of the first entity, a first child node representative of the second entity, and a second child node representative of the third entity;

generating a first edge representative of the intent connecting the parent node and the first child node; and

generating a second edge representative of the intent connecting the first child node and the second child node.

7. The computer-implemented method according to claim 5 , further comprising:

generating a third relationship model associated with the API test case; and

associating the third relationship model with a third query type.

8. The computer-implemented method according to claim 7 , further comprising:

generating a fourth entity representative of a fourth noun identified in the API test data; and

identifying the fourth entity as being part of an error response to the API request.

9. The computer-implemented method according to claim 8 , wherein the generating of the third relationship model comprises:

generating a first child node representative of the second entity, a second child node representative of the second entity, a third child node representative of the third entity, and a fourth child node representative of the fourth entity;

generating a first edge representative of an error intent connecting the first child node and the fourth child node; and

generating a second edge representative of the intent connecting the second child node and the third child node.

10. The computer-implemented method according to claim 9 , wherein the generating of the third relationship model further comprises generating a path from the fourth child node to the second child node, wherein the path includes a reply associated with debugging information for the error response and wherein the path to the second child node provides for correct usage information for the error response.

11. A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by a processor to cause the processor to perform operations comprising:

generating an intent representative of a verb identified in application programming interface (API) test data associated with an API test case;

generating a first entity representative of a first noun identified in the API test data and a second entity representative of a second noun identified in the API test data associated with the API test case;

identifying the intent as being associated with a relationship between the first entity and the second entity in the API test case;

generating a first relationship model associated with the API test case, wherein the relationship model comprises the intent as the relationship between the first entity and the second entity; and

generating a conversation model of an artificial intelligence (AI) conversation agent by mapping the intent and the first and second entities to dialog nodes of the conversation model.

12. The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.

13. The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

program instructions to meter use of the program instructions associated with the request; and

program instructions to generate an invoice based on the metered use.

14. The computer program product of claim 11 , further comprising:

associating the first relationship model with a first query type;

generating a second relationship model associated with the API test case;

associating the second relationship model with a second query type;

generating a third relationship model associated with the API test case; and

associating the third relationship model with a third query type.

15. The computer program product of claim 14 , further comprising:

identifying the first and second entities as being part of an API request being tested by the API test case;

generating a third entity representative of a third noun identified in the API test data;

identifying the third entity as being part of an expected response to the API request;

generating a fourth entity representative of a fourth noun identified in the API test data; and

identifying the fourth entity as being part of an error response to the API request.

16. The computer program product of claim 15 , wherein:

the generating of the second relationship model comprises:

generating a parent node representative of the first entity, a first child node representative of the second entity, and a second child node representative of the third entity;

generating a first edge representative of the intent connecting the parent node and the first child node; and

generating a second edge representative of the intent connecting the first child node and the second child node; and

the generating of the third relationship model comprises:

generating a parent node representative of the first entity, a first child node representative of the second entity, and a second child node representative of the fourth entity;

generating a first edge representative of the intent connecting the parent node and the first child node; and

generating a second edge representative of the intent connecting the first child node and the second child node.

17. A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:

generating an intent representative of a verb identified in application programming interface (API) test data associated with an API test case;

generating a first entity representative of a first noun identified in the API test data and a second entity representative of a second noun identified in the API test data associated with the API test case;

identifying the intent as being associated with a relationship between the first entity and the second entity in the API test case;

generating a first relationship model associated with the API test case, wherein the relationship model comprises the intent as the relationship between the first entity and the second entity; and

generating a conversation model of an artificial intelligence (AI) conversation agent by mapping the intent and the first and second entities to dialog nodes of the conversation model.

18. The computer system of claim 17 , further comprising:

associating the first relationship model with a first query type;

generating a second relationship model associated with the API test case;

associating the second relationship model with a second query type;

generating a third relationship model associated with the API test case; and

associating the third relationship model with a third query type.

19. The computer system of claim 18 , further comprising:

identifying the first and second entities as being part of an API request being tested by the API test case;

generating a third entity representative of a third noun identified in the API test data;

identifying the third entity as being part of an expected response to the API request;

generating a fourth entity representative of a fourth noun identified in the API test data; and

identifying the fourth entity as being part of an error response to the API request.

20. The computer system of claim 19 , wherein:

the generating of the second relationship model comprises:

generating a parent node representative of the first entity, a first child node representative of the second entity, and a second child node representative of the third entity;

generating a first edge representative of the intent connecting the parent node and the first child node; and

generating a second edge representative of the intent connecting the first child node and the second child node; and

the generating of the third relationship model comprises:

generating a parent node representative of the first entity, a first child node representative of the second entity, and a second child node representative of the fourth entity;

generating a first edge representative of the intent connecting the parent node and the first child node; and

generating a second edge representative of the intent connecting the first child node and the second child node.