Extracting and recommending business processes from evidence in natural language systems

Patent metadata

Field	Value
Publication number	US-9514124-B2
Application number	US-201514615071-A
Country	US
Kind code	B2
Filing date	Feb 5, 2015
Priority date	Feb 5, 2015
Publication date	Dec 6, 2016
Grant date	Dec 6, 2016

Abstract

A natural language question and answer system analyzes a question to determine key characteristics (such as focus and lexical answer type), and matches those characteristics to business processes from business process repositories. The matching business processes are ranked and at least one is presented as a recommended answer to the user. The system can offer the user a trigger to invoke the particular business process. The analysis includes examining a user profile to determine an attribute relevant to the question, and further includes named entity searching and fuzzy string matching against the business process repositories. Each business process in a repository is designated as either idempotent, non-binding or retrieve-only. The matching can include performing a factorial LDA algorithm on both extracted named entities and latent factors of the business processes in the repositories.

First claim

What is claimed is:

1. A method of responding to a natural language question from a user, comprising:
receiving the natural language question in a computer-readable form, by executing first instructions in a computer system;
analyzing the natural language question to find a plurality of key characteristics, by executing second instructions in the computer system;
matching a plurality of business processes from at least one business process repository to the key characteristics, by executing third instructions in the computer system;
ranking the plurality of matching business processes, by executing fourth instructions in the computer system; and
recommending at least one particular business process from the plurality of matching business processes based on said ranking, by executing fifth instructions in the computer system, wherein said recommending includes displaying information regarding said ranking of the matching business processes on a display device of the computer system as part of a user interface.

2. The method of claim 1 wherein said analyzing includes named entity searching and fuzzy string matching of one or more of the key characteristics against the business process repository.

3. The method of claim 1 wherein said analyzing includes examining a user profile for the user to determine a user attribute that is relevant to the natural language question.

4. The method of claim 1 wherein the key characteristics at least include a focus term and a lexical answer type.

5. The method of claim 1 wherein each business process in the repository is designated as one of three process types including idempotent, non-binding or retrieve-only.

6. The method of claim 1 further comprising offering the user a trigger to invoke the particular business process.

7. The method of claim 1 wherein said matching includes performing a factorial LDA algorithm on both extracted named entities and latent factors from evidence against the key characteristics.

8. A computer system comprising:
one or more processors which process program instructions;
a memory device connected to said one or more processors; and
program instructions residing in said memory device for responding to a natural language question from a user by receiving the natural language question in a computer-readable form, analyzing the natural language question to find a plurality of key characteristics, matching a plurality of business processes from at least one business process repository to the key characteristics, ranking the plurality of matching business processes, by executing third instructions in the computer system, and recommending at least one particular business process from the plurality of matching business processes based on said ranking, including displaying information regarding the ranking of the matching business processes on a display device of the computer system as part of a user interface.

9. The computer system of claim 8 wherein the analyzing includes named entity searching and fuzzy string matching of one or more of the key characteristics against the business process repository.

10. The computer system of claim 8 wherein the analyzing includes examining a user profile for the user to determine a user attribute that is relevant to the natural language question.

11. The computer system of claim 8 wherein the key characteristics at least include a focus term and a lexical answer type.

12. The computer system of claim 8 wherein each business process in the repository is designated as one of three process types including idempotent, non-binding or retrieve-only.

13. The computer system of claim 8 wherein said program instructions further include offering the user a trigger to invoke the particular business process.

14. The computer system of claim 8 wherein the matching includes performing a factorial LDA algorithm on both extracted named entities and latent factors from evidence against the key characteristics.

15. A computer program product comprising:
a computer readable storage medium; and
program instructions residing in said storage medium for responding to a natural language question from a user by receiving the natural language question in a computer-readable form, analyzing the natural language question to find a plurality of key characteristics, matching a plurality of business processes from at least one business process repository to the key characteristics, ranking the plurality of matching business processes, by executing third instructions in the computer system, and recommending at least one particular business process from the plurality of matching business processes based on said ranking, including displaying information regarding the ranking of the matching business processes on a display device of the computer system as part of a user interface.

16. The computer program product of claim 15 wherein the analyzing includes named entity searching and fuzzy string matching of one or more of the key characteristics against the business process repository.

17. The computer program product of claim 15 wherein the analyzing includes examining a user profile for the user to determine a user attribute that is relevant to the natural language question.

18. The computer program product of claim 15 wherein the key characteristics at least include a focus term and a lexical answer type.

19. The computer program product of claim 15 wherein each business process in the repository is designated as one of three process types including idempotent, non-binding or retrieve-only.

20. The computer program product of claim 15 wherein said program instructions further include offering the user a trigger to invoke the particular business process.

21. The computer program product of claim 15 wherein the matching includes performing a factorial LDA algorithm on both extracted named entities and latent factors from evidence against the key characteristics.

Assignees

• IBM

Inventors

• Allen Corville O
• Altaf Faheem
• Chandrasekaran Swaminathan
• Wiggins James D

Classifications

• G06F40/284 Primary

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06Q10/06316 Primary

  Sequencing of tasks or work · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F17/2785

  Physics · mapped topic

• G06F17/277 Primary

  Physics · mapped topic