Method for adaptive conversation state management with filtering operators applied dynamically as part of a conversational interface

• US 10,031,968 B2
• Filed: 03/13/2013
• Issued: 07/24/2018
• Est. Priority Date: 10/11/2012
• Status: Active Grant

• Current Assignee: Veveo, Inc. (Adeia Inc.)
• Original Assignee: Veveo, Inc. (Adeia Inc.)
• Inventors: Venkataraman, Sashikumar, Mohaideen Pathurudeen, Ahmed Nizam, Reddy, K China Srinivasulu, Pujari, Mangesh Dattatray, Majumder, Soumyadip, Barve, Rakesh, Aravamudan, Murali
• Primary Examiner(s): Trujillo, James
• Assistant Examiner(s): Khoshnoodi, Fariborz
• Application Number:
  US13/801,958
• Publication Number:
  US 20140108453A1
• Time in Patent Office: 1,959 Days
• Field of Search: 707774, 707775
• CPC Class Codes: G06F 16/24535 of sub-queries or views
• CPC Class Codes: G06F 16/3349 Reuse of stored results of previous queries
• CPC Class Codes: G06F 16/907 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A system and method of processing a search request is provided. Identification of a desired content item is based on comparing a topic of the search request to previous user input. The method includes providing access to a set of content items with metadata that describes the corresponding content items and providing information about previous searches. The method further includes receiving a present input from the user and determining a relatedness measure between the information about the previous searches and an element of the present input. If the relatedness measure is high, the method also includes selecting a subset of content items based on comparing the present input and information about the previous searches with the metadata that describes the subset of content items. Otherwise, the method includes selecting a subset of content items based on comparing the present input with the metadata that describes the subset of content items.

Claims

1. A method of processing a search request received from a user, the search request directed at identifying a desired item from a set of items, in which the identification is based on applying filters in the search request, the method comprising:

providing access to a set of content items, and metadata that describes the set of content items;

providing access to a conversation state space containing a first filter;

receiving a first search request from the user, wherein the first search request comprises a second filter;

storing the second filter in the conversation state space;

receiving a second search request from the user, wherein the second search request comprises a third filter;

storing the third filter in the conversation state space;

determining whether the first, second, and third filters in the conversation state space have a relatedness measure exceeding a threshold value based on searching for content items in the set of content items that are associated with metadata matching all of the first, second, and third filters in the conversation state space;

based on determining that a first subset of content items in the set of content items is associated with metadata matching all of the first, second, and third filters in the conversation state space, presenting to the user the first subset of content items; and

based on determining that no content items in the set of content items are associated with metadata matching all of the first, second, and third filters in the conversation state space;

removing the second filter, that was receiving as a part of the first search request from the user, from the conversation state space;

searching for content items in the set of content items that are associated with metadata matching both of the first and third filters in the conversation state space; and

presenting to the user a second subset of content items that is associated with metadata matching both of the first and third filters in the conversation state space.

2. The method of claim 1 further comprising providing access to a relationship database containing relationship distances of content items, wherein determining whether the first, second, and third filters in the conversation state space have a relatedness measure exceeding the threshold value is further based on one or more of the relationship distances.

3. The method of claim 2, wherein the relationship database presents a relationship graph with nodes and edges, each node representing a content item and each edge representing a direct relationship between two content items.

4. The method of claim 3, wherein a relationship distance of two content items is measured in a number of hops between two nodes corresponding to the two content items.

5. The method of claim 3, wherein a relationship distance of two content items is measured in a smallest number of hops between two nodes corresponding to the two content items.

6. The method of claim 3, wherein each edge has a weight, wherein a relationship distance of two content items is a sum of weights of edges connecting two nodes corresponding to the two content items.

7. The method of claim 2, wherein the relationship distances are modified by user preferences acquired over time.

8. The method of claim 2, further comprising providing access to a database containing historical inputs, wherein the relationship distances of content items are determined based on how often content items were used together.

9. The method of claim 1 further comprising providing access to a database containing user preferences acquired over time and modifying the determined relatedness measure based on the user preferences.

10. The method of claim 1, further comprising determining the second and third filters based on applying a predefined rule to the first and second search requests respectively.

11. The method of claim 10, wherein the predefined rule uses a Bayes classifier.

12. The method of claim 1, wherein the threshold value is adjusted based on feedback from the user.

13. The method of claim 2, further comprising determining a number of relationships that content items associated with the first, second, and third filters in the conversation state space have in the relationship database, wherein the threshold value is determined based on the number of relationships.

14. The method of claim 1, further comprising asking the user for the second search request.

29. The method of claim 1, wherein removing the second filter from the conversation state space comprises selecting for removal the second filter based on determining that the second filter shares an entity type with the third filter.

15. A system for processing a search request received from a user, the search request directed at identifying a desired item from a set of items, in which the identification is based on applying filters in the search request, the system comprising:

computer readable instructions encoded on a non-transitory computer readable medium, the computer readable instructions causing a computer system to;

provide access to a set of content items and metadata that describes the set of content items;

provide access to a conversation state space containing a first filter;

receive a first search request from the user, wherein the first search request comprises a second filter;

store the second filter in the conversation state space;

receive a second search request from the user, wherein the second search request comprises a third filter;

store the third filter in the conversation state space;

determine whether the first, second, and third filters in the conversation state space have a relatedness measure exceeding a threshold value based on searching for content items in the set of content items that are associated with metadata matching all of the first, second, and third filters in the conversation state space;

based on determining that a first subset of content items in the set of content items is associated with metadata matching all of the first, second, and third filters in the conversation state space, present to the user the first subset of content items; and

based on determining that no content items in the set of content items are associated with metadata matching all of the first, second, and third filters in the conversation state space;

remove the second filter, that was receiving as a part of the first search request from the user, from the conversation state space;

search for content items in the set of content items that are associated with metadata matching both of the first and third filters in the conversation state space; and

present to the user a second subset of content items that is associated with metadata matching both of the first and third filters in the conversation state space.

16. The system of claim 15, wherein the computer readable instructions further cause the computer system to provide access to a relationship database containing relationship distances of content items and wherein the computer readable instructions cause the computer system to determine whether the first, second, and third filters in the conversation state space have a relatedness measure exceeding the threshold value further based on one or more of the relationship distances.

17. The system of claim 16, wherein the relationship database presents a relationship graph with nodes and edges, each node representing a content item and each edge representing a direct relationship between two content items.

18. The system of claim 17, wherein a relationship distance of two content items is measured in a number of hops between two nodes corresponding to the two content items.

19. The system of claim 17, wherein a relationship distance of two content items is measured in a smallest number of hops between two nodes corresponding to the two content items.

20. The system of claim 17, wherein each edge has a weight and wherein a relationship distance of two content items is a sum of weights of edges connecting two nodes corresponding to the two content items.

21. The system of claim 16, wherein the relationship distances are modified by user preferences acquired over time.

22. The system of claim 16, wherein the computer readable instructions further cause the computer system to provide access to a database containing historical inputs and wherein the relationship distances of content items are determined based on how often content items were used together.

23. The system of claim 15, wherein the computer readable instructions further cause the computer system to provide access to a database containing user preferences acquired over time and modify the determined relatedness measure based on the user preferences.

24. The system of claim 15, wherein the computer readable instructions further cause the computer system to determine the second and third filters based on applying a predefined rule to the first and second search requests respectively.

25. The system of claim 24, wherein the predefined rule uses a Bayes classifier.

26. The system of claim 15, wherein the threshold value is adjusted based on feedback from the user.

27. The system of claim 16, wherein the computer readable instructions further cause the computer system to determine a number of relationships that content items associated with the first, second, and third filters in the conversation state space have in the relationship database, and wherein the threshold value is determined based on the number of relationships.

28. The system of claim 15, wherein the computer readable instructions further cause the computer system to ask the user for the second search request.

30. The system of claim 15, wherein the computer readable instructions, when causing the computer system to remove the second filter from the conversation state space, cause the computer system to select for removal the second filter based on determining that the second filter shares an entity type with the third filter.

31. A method of processing search requests for identifying desired items by applying filters to the search requests, the method comprising:

maintaining a conversation state space for storing search terms and filters, the conversation state space comprising a first filter;

modifying the conversation state space to include a second filter and a third filter that were received from a user,

generating a first subset of content items, the first subset of content items including content items of a set of content items that are associated with metadata matching the first, the second and the third filters stored in the conversation space;

based on determining that the first subset of content items includes at least one content item, generating for display a first indication for the first subset of content items; and

based on determining that the first subset of content items includes no content items;

modifying the conversation state space to remove the second filter;

generating a second subset of content items, the second subset of content items including content items of the set of content items that are associated with metadata matching the first and third filters stored in the conversation space; and

generating for display a second indication for the second subset of content items.

32. The method of claim 31 further comprising:

determining whether the first, second, and third filters in the conversation state space have a relatedness measure exceeding a threshold value based on searching for content items in the set of content items; and

upon a condition in which the relatedness measure exceeds the threshold value, augmenting the conversation state space with elements of a present input received from the user.

33. The method of claim 32 further comprising providing access to a relationship database containing relationship distances of content items, wherein determining whether the first, second, and third filters in the conversation state space have a relatedness measure exceeding the threshold value is further based on one or more of the relationship distances.

34. The method of claim 33, wherein the relationship database presents a relationship graph with nodes and edges, each node representing a content item and each edge representing a direct relationship between two content items.

35. The method of claim 33, wherein a relationship distance of two content items is measured in a number of hops between two nodes corresponding to the two content items.

36. The method of claim 33, wherein a relationship distance of two content items is measured in a smallest number of hops between two nodes corresponding to the two content items.

37. The method of claim 33, wherein each edge has a weight, wherein a relationship distance of two content items is a sum of weights of edges connecting two nodes corresponding to the two content items.

38. The method of claim 32, further comprising providing access to a database containing historical inputs, wherein the relationship distances of content items are determined based on how often content items were used together.

39. The method of claim 32 further comprising providing access to a database containing user preferences acquired over time and modifying the determined relatedness measure based on the user preferences.

40. The method of claim 32, wherein the threshold value is adjusted based on feedback from the user.

50. The system of claim 32, wherein the computer readable instructions further cause the computer system to adjusted threshold value based on feedback from the user.

41. A system for of processing search requests for identifying desired items by applying filters to the search requests, the method comprising:

computer readable instructions encoded on a non-transitory computer readable medium, the computer readable instructions causing a computer system to;

maintain a conversation state space for storing search terms and filters, the conversation state space comprising a first filter;

modify the conversation state space to include a second filter and a third filter that were received from a user,

generate a first subset of content items, the first subset of content items including content items of a set of content items that are associated with metadata matching the first, the second and the third filters stored in the conversation space;

based on determining that the first subset of content items includes at least one content item, generate for display a first indication for the first subset of content items; and

based on determining that the first subset of content items includes no content items;

modify the conversation state space to remove the second filter;

generate a second subset of content items, the second subset of content items including content items of the set of content items that are associated with metadata matching the first and third filters stored in the conversation space; and

generate for display a second indication for the second subset of content items.

42. The system of claim 41, wherein the computer readable instructions further cause the computer system to:

determine whether the first, second, and third filters in the conversation state space have a relatedness measure exceeding a threshold value based on searching for content items in the set of content items; and

upon a condition in which the relatedness measure exceeds the threshold value, augment the conversation state space with elements of a present input received from the user.

43. The system of claim 42 wherein the computer readable instructions further cause the computer system to provide access to a relationship database containing relationship distances of content items, wherein determining whether the first, second, and third filters in the conversation state space have a relatedness measure exceeding the threshold value is further based on one or more of the relationship distances.

44. The system of claim 43, wherein the relationship database presents a relationship graph with nodes and edges, each node representing a content item and each edge representing a direct relationship between two content items.

45. The system of claim 43, wherein a relationship distance of two content items is measured in a number of hops between two nodes corresponding to the two content items.

46. The system of claim 43, wherein a relationship distance of two content items is measured in a smallest number of hops between two nodes corresponding to the two content items.

47. The system of claim 43, wherein each edge has a weight, wherein a relationship distance of two content items is a sum of weights of edges connecting two nodes corresponding to the two content items.

48. The system of claim 42, wherein the computer readable instructions further cause the computer system to provide access to a database containing historical inputs, wherein the relationship distances of content items are determined based on how often content items were used together.

49. The system of claim 42, wherein the computer readable instructions further cause the computer system to provide access to a database containing user preferences acquired over time and modifying the determined relatedness measure based on the user preferences.