Computer support service with solution function updates as a function of pre-delivery expert changes to automatically generated solutions

• US 20050278213A1
• Filed: 04/06/2005
• Published: 12/15/2005
• Est. Priority Date: 06/15/2004
• Status: Active Grant

• Current Assignee: Micro Focus LLC (Open Text Corporation)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Faihe, Yassine
• Granted Patent: US 7,257,514 B2
• Time in Patent Office: Days
• US Class Current: 705/11
• CPC Class Codes: G06F 11/2257 using expert systems

Abstract

A solution engine (31) of a vendor'"'"'s highly-automated adaptive computer support system (10) for a remote customer (20) automatically generates proposed solutions, e.g., sets of support documents, as a function of diagnostic data received from a customer'"'"'s computer system (23). The automatically generated solution can be subject to expert review (35) prior to publication (37) to the customer, e.g., when the automated system assigns a low confidence level to the solution. In addition, expert review can be triggered by feedback (39) from the customer once a proposed solution is communicated. The diagnostic data, solutions and feedback for an incident are packaged (at 41) as a “case” and entered into an historical case database (45). A solution function updater (43) updates the solution function as a function, at least in part, of the expert review and customer feedback.

Claims

1. A computer support system comprising:

a solution engine for applying a solution function to diagnostic data regarding a computer system of a customer to provide an automatically-generated solution;

an expert review function for presenting said diagnostic data and said automatically-generated solution to an expert and accepting changes to said solution from said expert so as to provide an expert solution;

a delivery function for presenting a customer solution including at least one of said automatically-generated solution and said expert solution to said customer; and

an updater for changing said solution function at least in part in response to said changes.

2. A system as claimed in claim 1 wherein said solution engine applies artificial-intelligence approaches to said diagnostic data to obtain plural partial solutions, said solution engine including a solution combiner for combining said partial solutions to obtain said automatically-generated solution.

3. A system as claimed in claim 2 wherein said solution combiner assigns a confidence value to said automatically generated solution.

4. A system as claimed in claim 3 wherein said expert review function presents said automatically generated solution to an expert unless said confidence level meets a predetermined threshold criterion.

5. A system as claimed in claim 4 wherein said delivery function delivers said expert solution if said confidence level fails to meet said criterion.

6. A system as claimed in claim 4 wherein said delivery function delivers said automatically generated solution if said confidence level meets said criterion.

7. A system as claimed in claim 1 further comprising a feedback collector for accepting feedback from said customer in response to presentation of said customer solution, said updater also changing said solution function at least in part as a function of said feedback.

8. A system as claimed in claim 1 wherein said updater includes an historical case base.

9. A system as claimed in claim 1 wherein said solution engine includes a rule-based engine and a rule base, said updater including a rules induction engine.

10. A system as claimed in claim 1 wherein said solution engine includes a similarity-based engine, said updater including a prototype case induction engine for generating prototypical cases to be used by said similarity-based engine.

11. A computer support method comprising:

receiving diagnostic data from a computer system of a customer;

automatically generating an automatically-generated solution as a solution function of said diagnostic data;

providing said automatically-generated solution to an expert and accepting changes thereto by said expert to establish an expert solution;

delivering said expert solution to a customer;

updating said solution function at least in part as a function of said changes.

12. A method as claimed in claim 11 wherein said automatically generating involves generating partial solutions using respective ones of a plural artificial-intelligence approaches and combining said partial solutions to yield said automatically-generated solution.

13. A method as claimed in claim 11 wherein said automatically generating further involves assigning a confidence level to said automatically-generated solution.

14. A method as claimed in claim 13 wherein said providing is conditioned on said confidence level failing to meet a predetermined criterion.

15. A method as claimed in claim 13 wherein said providing is precluded when said confidence level meets said criterion.

16. A method as claimed in claim 11 wherein said automatically generating is effected using a rule-based approach and said updating is effected by inducing rules.

17. A method as claimed in claim 11 wherein said automatically generating is effected using classification and said updating is effected using statistical learning.

18. A method as claimed in claim 11 wherein said automatically generating is effected using a similarity-based criteria and said updating is effected using by inducing prototype cases.

19. A method as claimed in claim 11 further comprising receiving feedback from said customer regarding said expert solution, said updating of said solution function being a function in part of said feedback.

20. A method as claimed in claim 19 further comprising determining from said feedback whether or not the delivered solution solved a problem and, if not, performing a post-delivery expert review.

21. A computer support method comprising:

applying plural solution functions in parallel to diagnostic data;

calculating a confidence factor from the results of the plural solution functions;

if the confidence factor does not meet predefinable criteria, triggering an expert review of the results prior to the delivery; and

delivering the results either directly or following modification by an expert without direct contact between the expert and the customer.

22. A method as claimed in claim 21 wherein one said plural solution functions employs a rule-based approach.

23. A method as claimed in claim 21 wherein one of said plural solution functions employs a classification approach.

24. A method as claimed in claim 21 wherein one of said plural solution functions employs a similarity-based approach.

25. A method as claimed in claim 23 wherein said similarity-based approach accesses prototype cases.

26. A computer support system comprising:

a solution engine for generating a result from diagnostic data by combining plural solutions generating using distinct artificial-intelligence approaches, said solution engine assigning a confidence factor to said result;

an expert review function for providing said result to an expert for review if said confidence level fails to meet predefinable criteria;

delivery means for delivering said result to a customer directly if said confidence factor meets said criteria and after modification by said expert if said confidence factor fails to meet said criteria without direct contact between the expert and the customer.

27. A method as claimed in claim 26 wherein said solution engine includes a rule-based engine.

28. A method as claimed in claim 26 wherein said solution engine includes a classification engine.

29. A method as claimed in claim 26 wherein said solution engine includes a similarity-based engine.

30. A method as claimed in claim 29 wherein said similarity-based engine also includes a database of prototype cases.

31. A computer support system comprising:

a solution engine for applying a solution function to diagnostic data regarding a computer system of a customer to provide automatically-generated solutions;

a delivery function for presenting said automatically-generated solutions to said customer;

an expert interface for accepting a contribution from an expert for updating said solution function; and

evaluation means for providing an evaluation of the effectiveness of said contribution as it is employed in said automatically generated solutions.

32. A system as claimed in claim 31 wherein said evaluation means determines the number of times said contribution provides a successful solution.

33. A system as claimed in claim 31 wherein said evaluation means further provides said evaluation to said expert.

34. A computer support method comprising:

receiving diagnostic data from a computer system of a customer;

automatically generating automatically-generated solutions as a solution function of said diagnostic data;

delivering said automatically-generated solutions to said customer;

updating said solution function of a contribution by an expert; and

evaluating said contribution as it is employed in said automatically-generated solutions.

35. A method as claimed in claim 34 wherein said evaluating involves determining the number of times said contribution provides for a successful automatically generated solution.

36. A method as claimed in claim 34 further comprising providing an evaluation resulting from said evaluating step to said expert.