Strategy for Providing Query Results Based on Analysis of User Intent

• US 20080082518A1
• Filed: 09/29/2006
• Published: 04/03/2008
• Est. Priority Date: 09/29/2006
• Status: Active Grant

• Current Assignee: A9.com Incorporated (Amazon.com, Inc.)
• Original Assignee: A9.com Incorporated (Amazon.com, Inc.)
• Inventors: Loftesness, David E.
• Granted Patent: US 7,860,886 B2
• Time in Patent Office: Days
• US Class Current: 707/5
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A strategy is described for responding to a user'"'"'s query based on a consideration of the user'"'"'s intent in entering the query. The user'"'"'s intent, in turn, is determined by examining prior query-related behavior of a population of users.

Claims

1. A computerized method for providing query results based on user intent, comprising:

receiving an individual user'"'"'s query;

identifying, using classification mapping information, a result-generating function associated with the query, wherein the classification mapping information maps queries into different result-generating functions based on an analysis of prior query-related behavior of a plurality of users; and

generating query results for the user using the identified result-generating function.

2. The computerized method of claim 1, further comprising determining the query-related behavior of the plurality of users, wherein the determining of the query-related behavior comprises:

receiving queries from a plurality of users;

generating results based on the queries;

providing the results to the plurality of users; and

identifying actions that the users take upon receiving the results.

3. The computerized method of claim 2, wherein the actions comprise at least one purchase of an item.

4. The computerized method of claim 2, wherein the actions comprise at least one instruction to add an item to a shopping cart.

5. The computerized method of claim 2, wherein the actions comprise at least one click-through event in which a user clicks on an item.

6. The computerized method of claim 2, wherein the analysis of the prior query-related behavior comprises:

identifying patterns in the actions that evince a predominant intent of the users in entering the queries;

associating result-generating functions with the identified patterns to provide classification results; and

creating the classification mapping information based on the classification results.

7. The computerized method of claim 1, wherein the analysis of the prior query-related behavior operates by weighting the query-related behavior based on time.

8. The computerized method of claim 1, wherein the result-generating functions provide different respective strategies for ranking query results.

9. The computerized method of claim 1, wherein the plurality of result-generating functions are associated with different respective classifications.

10. The computerized method of claim 9, wherein at least one classification indicates that a query is predominately used to identify a title of a desired item.

11. The computerized method of claim 9, wherein at least one classification indicates that a query is predominately used to identify a theme of a desired item.

12. The computerized method of claim 9, wherein at least one classification indicates that a query is predominately used to identify a desired item having a defined brand.

13. The computerized method of claim 9, wherein at least one classification indicates that a query is predominately used to identify a desired item having a defined temporal status.

14. The computerized method of claim 9, wherein at least one of the result-generating functions is used as a default if a classification of the individual user'"'"'s query cannot be determined.

15. The computerized method of claim 9, further comprising determining a classification corresponding to the user'"'"'s query based on the entirety of the query.

16. The computerized method of claim 9, comprising determining a classification corresponding to the user'"'"'s query based on at least one key term in the user'"'"'s query, in the event that classification cannot be performed based on the entirety of the query.

17. One or more computer-readable media containing computer-readable instructions for implemented the computerized method of claim 1.

18. One or more computing devices, comprising:

one or more processors; and

memory to store computer-executable instructions that, when executed by the one or more processors, perform the computerized method of claim 1.

19. A computerized method for creating classification mapping information for use in generating query results based on user intent, comprising:

identifying patterns in actions of a plurality of users that evince a predominant intent of the users in entering queries;

associating result-generating functions with the identified patterns to provide classification results; and

creating, based on the classification results, classification mapping information that maps the queries into associated result-generating functions.

20. The computerized method of claim 19, further comprising

receiving queries from the plurality of users;

generating results based on the queries;

providing the results to the plurality of users; and

identifying actions that the plurality of users take upon receiving the results, the identified actions comprising the actions of the plurality of users from which patterns are identified.

21. One or more computer-readable media containing computer-readable instructions for implemented the computerized method of claim 19.

22. One or more computing devices, comprising:

one or more processors; and

memory to store computer-executable instructions that, when executed by the one or more processors, perform the computerized method of claim 19.

23. An apparatus for providing query, results based on user intent, comprising:

a data mining module operative to;

collect information regarding behavior of users who have submitted a certain query; and

identify a pattern of behavior of the users that evinces a predominant intent of the users submitting the certain query; and

a query module operative to;

generate search results for a subsequent user in response to a similar query, wherein the search results are tailored to a probable intent of the subsequent user, and wherein the probable intent of the subsequent user is determined based at least in part on the pattern of behavior of the users.

24. The apparatus of claim 23, wherein the pattern of behavior indicates that the certain query is predominately used to identify a title of a desired item.

25. The apparatus of claim 23, wherein the pattern of behavior indicates that the certain query is predominately used to identify a theme of a desired item.

26. The apparatus of claim 23, wherein the pattern of behavior indicates that the certain query is predominately used to identify a desired item having a defined brand.

27. The apparatus of claim 23, wherein the pattern of behavior indicates that the certain query is predominately used to identify a desired item having a defined temporal status.

28. The apparatus of claim 23, wherein the data mining module is further operative to identify the behavior of the users by identifying actions that the users have taken upon receiving query results.

29. The apparatus of claim 23, wherein the data mining module is further operative to create classification mapping information that maps queries with patterns of behavior predominately associated with the queries.

30. The apparatus of claim 23, wherein the query module provides a plurality of result-generating functions, wherein the result-generating functions apply different respective strategies for producing search results.

31. The apparatus of claim 30, wherein the query module is operative to select one of the plurality of result-generating functions in response to an input of the similar query, based at least in part on the pattern of behavior assessed by the data mining module.

32. The apparatus of claim 30, wherein the result-generating functions are operative to provide different respective strategies for ranking query results.

33. The apparatus of claim 32, wherein at least one of the result-generating functions is operative to generate results that give relative priority to result items that have a title-based affiliation with a query.

34. The apparatus of claim 32, wherein at least one of the result-generating functions is operative to generate results that give relative priority to result items that have a theme-based affiliation with a query.

35. A system comprising the apparatus of claim 23, the apparatus being communicatively coupled to a plurality of user devices via a digital network.

36. One or more computer-readable media containing computer-readable instructions for implementing, when executed by one or more processors, functionality for providing query results based on user intent, comprising:

logic operative to receive a user'"'"'s query;

logic operative to map the user'"'"'s query to a ranking function, selected from a plurality of ranking functions,

wherein the ranking function is generates output results in response to the user'"'"'s query according to an associated ranking strategy associated with the ranking function,

wherein the associated ranking strategy has been determined to apply to the user'"'"'s query based on prior query-related behavior of a plurality of users.

37. A method for providing query results based on user intent, the method comprising:

recording selections made by users in association with prior queries made by the users;

identifying, for each prior query, a pattern which evinces a predominate intent of the users in entering the query, to provide a plurality of patterns;

receiving a particular query from an individual user;

identifying the individual user'"'"'s probable intent in entering the particular query based on the patterns associated with the prior queries of the users;

providing results that are tailored to the identified probable intent in response to the individual user'"'"'s particular query

38. The method of claim 37, wherein the providing of the results comprises:

selecting, based on the individual users'"'"' probable intent, a result-generating function from among a plurality of result-generating functions, wherein the result-generating functions apply different respective strategies for providing search results; and

providing the results using the selected result-generating function.

39. The method of claim 38, wherein the result-generating functions provide different respective strategies for ranking query results.