Engineering expert system

• US 20080319936A1
• Filed: 06/18/2008
• Published: 12/25/2008
• Est. Priority Date: 06/21/2007
• Status: Active Grant

• Current Assignee: Alcon Incorporated
• Original Assignee: Novartis Ag
• Inventors: Wong, Chiak Wu, Tran, Huong Giang, Lai, Aaric Chee Meng
• Granted Patent: US 8,250,018 B2
• Time in Patent Office: Days
• US Class Current: 706/47
• CPC Class Codes: G06N 5/00 Computing arrangements using knowledge-based models

Abstract

An expert system aids engineering personnel working in a manufacturing or other industrial environment by answering questions relating to machines, processes, systems or other elements of the environment. Users can interact with the system using kiosks in the relevant areas of the plant to enter queries and receive answers. A user can enter a query in a natural language format, which the system parses for keywords or keyterms. The system can use a backward chaining method to reach a solution, based upon the user'"'"'s answer to further questions that the system asks the user.

Claims

1. An expert system for aiding engineering personnel in a contact lens manufacturing, comprising:

a user interface for receiving a query from a user regarding an element of business entity'"'"'s industrial environment in which the user works in a contact lens manufacturing related capacity;

a database containing information describing aspects of elements of the business entity'"'"'s industrial environment; and

an inference engine subsystem for receiving the query via the user interface and obtaining solution information from the database by matching keyterms in the query, wherein the user interface outputs the solution information to the user.

2. The expert system claimed in claim 1, further comprising a kiosk operable by the user through the user interface.

3. The expert system claimed in claim 1, wherein the user interface, inference engine and database operate on one or more server computers to serve web pages to a client computer having a browser operated by the user.

4. The expert system claimed in claim 1, wherein the inference engine subsystem determines whether query relates to a knowledge-based solution or an expert consultation-based solution by matching keyterms in the query.

5. The expert system claimed in claim 4, wherein the inference engine subsystem matches description-oriented keyterms in the query to determine if the query relates to a knowledge-based solution.

6. The expert system claimed in claim 5, wherein the description-oriented keyterms relate to at least one of:

“

what is”

;

“

what are”

;

“

where is”

;

“

where are”

;

“

how many”

;

“

how long”

;

“

how to”

;

“

how do I”

;

“

tell about”

; and

“

describe”

.

7. The expert system claimed in claim 4, wherein the inference engine subsystem matches reasoning-oriented keywords in the query to determine if the query relates to an expert consultation-oriented solution.

8. The expert system claimed in claim 7, wherein the reasoning-oriented keyterms relate to:

“

why”

.

11. The expert system claimed in claim 1, wherein:

an inference engine matches keyterms in the query with keyterms associated with rules to select a rule from the database; and

the inference engine obtains a further question from the database associated with the selected rule;

the user interface prompts the user to answer the further question; and

the inference engine determines if solution information associated with a user'"'"'s answer to the further question is available in the database.

12. The expert system claimed in claim 1, further comprising a feedback subsystem for updating the database in response to receiving feedback information from a user.

23. The computer program product claimed in claim 1, further comprising feedback subsystem code for updating the database in response to receiving feedback information from an engineer user.

9-10. -10. (canceled)

13. A computer program product comprising a computer-readable medium on which is recorded a computer program for aiding engineering personnel in a contact lens manufacturing, the computer program comprising:

user interface code for receiving a query from a user regarding an element of a business entity'"'"'s industrial environment in which the user works in a contact lens manufacturing related capacity;

database code containing information describing aspects of elements of the business entity'"'"'s industrial environment; and

inference engine code for receiving the query via the user interface and obtaining solution information from the database by matching keyterms in the query, wherein the user interface outputs the solution information to the user.

14. The computer program product claimed in claim 13, wherein the user interface code and inference engine code are included in active server pages (ASP).

15. The computer program product claimed in claim 13, wherein the inference engine code determines whether query relates to a knowledge-based solution or an expert consultation-based solution by matching keyterms in the query.

16. The computer program product claimed in claim 15, wherein the inference engine code matches description-oriented keyterms in the query to determine if the query relates to a knowledge-based solution.

17. The computer program product claimed in claim 16, wherein the description-oriented keyterms relate to at least one of:

“

what is”

;

“

what are”

;

“

where is”

;

“

where are”

;

“

how many”

;

“

how long”

;

“

how to”

;

“

how do I”

;

“

tell about”

; and

“

describe”

.

18. The computer program product claimed in claim 15, wherein the inference engine code matches reasoning-oriented keywords in the query to determine if the query relates to an expert consultation-oriented solution.

19. The computer program product claimed in claim 18, wherein the reasoning-oriented keyterms relate to:

“

why”

.

22. The computer program product claimed in claim 13, wherein:

the inference engine code matches keyterms in the query with keyterms associated with rules to select a rule from the database; and

the inference engine code obtains a further question from the database associated with the selected rule;

the user interface code prompts the user to answer the further question; and

the inference engine code determines if solution information associated with a user'"'"'s answer to the further question is available in the database.

20-21. -21. (canceled)