Customer self service subsystem for adaptive indexing of resource solutions and resource lookup

• US 6,643,639 B2
• Filed: 02/07/2001
• Issued: 11/04/2003
• Est. Priority Date: 02/07/2001
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Jasura, Donn P., Keller, Neal M., Biebesheimer, Debra L., Oblinger, Daniel A., Rolando, Stephen J.
• Primary Examiner(s): Mizrahi, Diane D.
• Application Number:
  US09/778,135
• Publication Number:
  US 20020152190A1
• Time in Patent Office: 1,000 Days
• Field of Search: 707/1, 707/3, 707/2, 707/5, 707/10, 707/4, 705/37, 704/9, 704/8, 704/3
• US Class Current: 707/709
• CPC Class Codes: G06F 16/901 Indexing; Data structures therefor; Storage structures for retrieval from the web G06F16/951
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

An adaptive resource indexing and lookup method for a customer self service system that performs resource search and selection and includes a resource library having selectable resources. The method includes steps of: receiving a current user query for requesting resources; receiving a user context vector associated with the current user query, the user context vector comprising data associating an interaction state with the user; mapping each user query and associated context vector to a sub-set of resources from the resource library; and, generating a response set including the sub-set of resources that are most relevant to the user'"'"'s query. An adaptive indexing function implementing a supervised learning algorithm is applied for increasing the value of search results for a current user in their context and for enhancing and optimizing the performance of the resource indexing functions by increasing their relevance and specificity for mapping user queries to resources.

Claims

1. An adaptive resource indexing and lookup system for a customer self service system that performs resource search and selection, said self service system including a resource library having selectable resources, said adaptive resource indexing and lookup system comprising:

mechanism for receiving a current user query for requesting resources;

mechanism for receiving a user context vector associated with said current user query, said user context vector comprising data associating an interaction state with said user; and

, including context that is a function of the user;

a resource indexing mechanism generating resource indexing functions having logic for mapping each user query and associated user context vector to a sub-set of resources from said resource library, and generating a response set including said sub-set of resources that are most relevant to said user'"'"'s query, said resource indexing mechanism implementing supervised learning for receiving said user context data and adapting said resource indexing functions based on user interactions with said system,

whereby said adapted resource indexing functions have increased relevance and specificity for mapping user queries to resources.

2. The adaptive resource indexing and lookup system as claimed in claim 1, wherein said resource indexing functions include resource parameters for facilitating narrower searches.

3. The adaptive resource indexing and lookup system as claimed in claim 1, wherein said system provides a graphical user interface, said resource parameters of said resource indexing functions being selectable and modifiable by a current user via said interface.

4. The adaptive resource indexing and lookup system as claimed in claim 2, wherein said resource indexing mechanism iplements an adaptive indexing process for enhancing said resource indexing functions by increasing their relevance and specificity for mapping user queries to resources, said adaptive indexing process increasing the value of search results for a current user in their context

5. The adaptive resource indexing and lookup system as claimed in claim 4, wherein said self service system includes a database of user interaction records including actual resources selected by the users, said adaptive indexing process further implementing a supervised learning algorithm for receiving user interaction data from among said database of user interaction records and resources from said resource library and, adapting resource indexing functions based on a history of user interactions with said system as provided in said database of user interaction records.

6. The adaptive resource indexing and lookup system as claimed in claim 5, wherein said adaptive indexing processing for generating said resource indexing functions is performed off-line and on-line during an executed query to use the most current data.

7. The adaptive resource indexing and lookup system as claimed in claim 5, wherein said user interaction data comprises past and present user queries.

8. The adaptive resource indexing and lookup system as claimed in claim 5, wherein said user interaction data comprises system responses to said user queries.

9. The adaptive resource indexing and lookup system as claimed in claim 5, wherein said user interaction datacomprises raw context information including:

one or more of static, historical context, transient context, organizational context, community context, and environment context.

10. The adaptive resource indexing and lookup system as claimed in claim 9, wherein said user interaction data comprises other raw context associated with the user and dependent upon that user'"'"'s interaction state and query domain.

11. The adaptive resource indexing and lookup system as claimed in claim 10, wherein a query domain includes one of:

education, travel and real estate.

12. The adaptive resource indexing and lookup system as claimed in claim 5, wherein said user interaction data comprises user interaction feedback including history of prior interaction with the resource search and selection system, said supervised learning algorithm optimizing a performance of said resource indexing functions as measured by an evaluation metric applied to the user interaction feedback and user context.

13. The adaptive resource indexing and lookup system as claimed in claim 12, wherein one measure of performance of said resource indexing functions is coverage of the resources eventually selected by a user given a user query and user context pair.

14. An adaptive resource indexing and lookup method for a customer self service system that performs resource search and selection, said self service system including a resource library having selectable resources, said method comprising the steps of:

a) receiving a current user query for requesting resources;

b) receiving a user context vector associated with said current user query, said user context vector comprising data associating an interaction state with said user, and including context that is a function of the user;

c) generating resource indexing functions having logic for mapping each user query and associated context vector to a sub-set of resources from said resource library,

d) implementing supervised learning for receiving said user context data and adapting said resource indexing functions based on user interactions with said system; and

,

e) generating a response set including said sub-set of resources that are most relevant to said user'"'"'s query, whereby said adapted resource indexing functions have increased relevance and specificity for mapping user queries to resources.

15. The method as claimed in claim 14, wherein said resource indexing functions include resource parameters for facilitating narrower searches.

16. The method as claimed in claim 15, wherein said system provides a graphical user interface, said method including the step of:

enabling a current user to select and modify resource parameters of said resource indexing functions via said user interface.

17. The method as claimed in claim 15, wherein the step of adapting said resource indexing functions includes applying an adaptive indexing function for increasing the value of search results for a current user in their context.

18. The method as claimed in claim 17, wherein said self service system includes a database of user interaction records including actual resources selected by the users, said adaptive indexing process implementing a supervised learning algorithm for receiving user interaction data from among said database of user interaction records and resources from said resource library, and adapting resource indexing functions based on a history of user interactions with said system as provided in said database of user interaction records.

19. The method as claimed in claim 18, wherein said user interaction data comprises user interaction feedback, said supervised learning algorithm optimizing a performance of said resource indexing functions as measured by an evaluation metric applied to the user interaction feedback.

20. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for adaptive resource indexing and lookup for a customer self service system that performs resource search and selection, said self service system including a resource library having selectable resources, said method comprising the steps of:

a) receiving a current user query for requesting resources,

b) receiving a user context vector associated with said current user query, said user context vector comprising data associating an interaction state with said user, and including context that is a function of the user;

c) generating resource indexing functions having logic for mapping each user query and associated context vector to a sub-set of resources from said resource library; and

,

d) implementing supervised learning for receiving said user context data and adapting said resource indexing functions based on user interactions with said system; and

,

e) generating a response set including said sub-set of resources that are most relevant to said user'"'"'s query whereby said adapted resource indexing functions have increased relevance and specificity for mapping user queries to resources.

21. The program storage device readable by machine as claimed in claim 20, wherein said resource indexing functions including resource parameters for facilitating narrower searches.

22. The program storage device readable by machine as claimed in claim 20, wherein said system provides a graphical user interface, said method including the step of:

enabling a current user to select and modify resource parameters of said resource indexing functions via said user interface.

23. The program storage device readable by machine as claimed in claim 20, wherein the step of adapting said resource indexing functions includes applying an adaptive indexing function for increasing the value of search results for a current user in their context.

24. The program storage device readable by machine as claimed in claim 22, wherein said self service system includes a database of user interaction records including actual resources selected by the users, said adaptive indexing process implementing a supervised learning algorithm for receiving user interaction data from among said database of user interaction records and resources from said resource library, and adapting resource indexing functions based on a history of user interactions with said system as provided in said database of user interaction records.

25. The program storage device readable by machine as claimed in claim 24, wherein said user interaction data comprises user interaction feedback, said supervised learning algorithm optimizing a performance of said resource indexing functions as measured by an evaluation metric applied to the user interaction feedback.