Using artificial intelligence and natural language processing for data collection in message oriented middleware frameworks
A method includes receiving a natural language query requesting data from a message oriented middleware infrastructure comprising a plurality of message oriented middleware providers, and analyzing the natural language query to determine one or more types of the data being requested. In the method, one or more queries corresponding to the determined one or more types of the data are dynamically generated. The one or more queries are in native command formats corresponding to respective ones of the plurality of message oriented middleware providers. The method also includes executing the one or more queries in the native command formats to retrieve the data from the plurality of message oriented middleware providers, and providing a response to the natural language query based on the retrieved data to a user via a user interface.
1. An apparatus comprising:
at least one processing platform comprising a plurality of processing devices;
said at least one processing platform being configured:
to receive a natural language query requesting data from a message oriented middleware infrastructure comprising a plurality of message oriented middleware providers;
to analyze the natural language query to determine one or more types of the data being requested;
to dynamically generate one or more queries corresponding to the determined one or more types of the data;
wherein the one or more queries are in native command formats corresponding to respective ones of the plurality of message oriented middleware providers;
to execute the one or more queries in the native command formats to retrieve the data from the plurality of message oriented middleware providers;
to provide a response to the natural language query based on the retrieved data to a user via a user interface; and
to identify whether any of a plurality of stored queries correspond to the determined one or more types of the data;
wherein, in identifying whether any of the plurality of stored queries correspond to the determined one or more types of the data, said at least one processing platform is configured to compute a plurality of similarity scores between the plurality of stored queries and the natural language query.
2. The apparatus of claim 1 wherein, in analyzing the natural language query, said at least one processing platform is configured to use natural language processing techniques to determine the one or more types of the data being requested.
3. The apparatus of claim 1 wherein the one or more types of the data comprise at least one of integration statistics, application statistics, system statistics, channel status, queue status, errors and message counts.
4. The apparatus of claim 1
wherein, in identifying whether any of the plurality of stored queries correspond to the determined one or more types of the data, said at least one processing platform is further configured
to determine whether any of the plurality of similarity scores reaches or exceeds a predetermined threshold.
5. The apparatus of claim 4 wherein, in identifying whether any of the plurality of stored queries correspond to the determined one or more types of the data, said at least one processing platform is configured to use one or more machine learning techniques.
6. The apparatus of claim 4 wherein said at least one processing platform is further configured to determine that there is not a match of the natural language query with any of the plurality of stored queries if none of the plurality of similarity scores reaches or exceeds the predetermined threshold.
7. The apparatus of claim 6 wherein said at least one processing platform is further configured:
to generate one or more natural language query restructure options in response to the determination that there is not a match; and
to send the one or more natural language query restructure options to the user with a request that the user restructure the natural language query.
8. The apparatus of claim 7 wherein the one or more natural language query restructure options comprise at least one of grammatical rephrasing of and word modifications to the natural language query.
9. The apparatus of claim 7 wherein said at least one processing platform is further configured to receive from the user an acceptance of a given natural language query restructure option of the one or more natural language query restructure options;
wherein, in dynamically generating the one or more queries, said at least one processing platform is configured to convert the given natural language query restructure option into the one or more queries.
10. The apparatus of claim 7 wherein said at least one processing platform is further configured:
to receive from the user a rejection of the one or more natural language query restructure options; and
to generate one or more additional natural language query restructure options in response to the rejection.
11. The apparatus of claim 1 wherein said at least one processing platform is further configured to dynamically generate one or more query representations corresponding to the dynamically generated one or more queries, wherein the one or more query representations comprise natural language terms representing the dynamically generated one or more queries.
12. The apparatus of claim 1 wherein the user interface comprises a chatbot interface.
13. The apparatus of claim 1 wherein, in executing the one or more queries, said at least one processing platform is configured to insert one or more variables based on the natural language query into the one or more queries.
14. The apparatus of claim 1 wherein the native command formats corresponding to the respective ones of the plurality of message oriented middleware providers are different.
15. A method comprising:
receiving a natural language query requesting data from a message oriented middleware infrastructure comprising a plurality of message oriented middleware providers;
analyzing the natural language query to determine one or more types of the data being requested;
dynamically generating one or more queries corresponding to the determined one or more types of the data;
wherein the one or more queries are in native command formats corresponding to respective ones of the plurality of message oriented middleware providers;
executing the one or more queries in the native command formats to retrieve the data from the plurality of message oriented middleware providers;
providing a response to the natural language query based on the retrieved data to a user via a user interface; and
identifying whether any of a plurality of stored queries correspond to the determined one or more types of the data;
wherein the identifying comprises computing a plurality of similarity scores between the plurality of stored queries and the natural language query; and
wherein the method is performed by at least one processing platform comprising at least one processing device comprising a processor coupled to a memory.
16. The method of claim 15
wherein the identifying further comprises
determining whether any of the plurality of similarity scores reaches or exceeds a predetermined threshold.
17. The method of claim 16 further comprising determining that there is not a match of the natural language query with any of the plurality of stored queries if none of the plurality of similarity scores reaches or exceeds the predetermined threshold.
18. The method of claim 17 further comprising:
generating one or more natural language query restructure options in response to the determination that there is not a match; and
sending the one or more natural language query restructure options to the user with a request that the user restructure the natural language query.
19. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing platform causes said at least one processing platform:
to receive a natural language query requesting data from a message oriented middleware infrastructure comprising a plurality of message oriented middleware providers;
to analyze the natural language query to determine one or more types of the data being requested;
to dynamically generate one or more queries corresponding to the determined one or more types of the data;
wherein the one or more queries are in native command formats corresponding to respective ones of the plurality of message oriented middleware providers;
to execute the one or more queries in the native command formats to retrieve the data from the plurality of message oriented middleware providers;
to provide a response to the natural language query based on the retrieved data to a user via a user interface; and
to identify whether any of a plurality of stored queries correspond to the determined one or more types of the data;
wherein, in identifying whether any of the plurality of stored queries correspond to the determined one or more types of the data, the program code causes said at least one processing platform to compute a plurality of similarity scores between the plurality of stored queries and the natural language query.
20. The computer program product according to claim 19
wherein, in identifying whether any of the plurality of stored queries correspond to the determined one or more types of the data, the program code further causes said at least one processing platform
to determine whether any of the plurality of similarity scores reaches or exceeds a predetermined threshold.