METHOD FOR ADAPTIVE CONVERSATION STATE MANAGEMENT WITH FILTERING OPERATORS APPLIED DYNAMICALLY AS PART OF A CONVERSATIONAL INTERFACE

• US 20140108453A1
• Filed: 03/13/2013
• Published: 04/17/2014
• 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, BARVE, Rakesh, ARAVAMUDAN, Murali, PUJARI, Mangesh Dattatray, MAJUMDER, Soumyadip
• Granted Patent: US 10,031,968 B2
• Time in Patent Office: Days
• US Class Current: 707/774
• 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 comparing a topic of the search request to previous user input, the method comprising:

providing access to a set of content items, each of the content items being associated with metadata that describes the corresponding content items;

providing information about at least one search previously received from a user;

receiving a present input from the user, the present input intended by the user to identify a desired content item;

determining a measure of relatedness between the information about the at least one previous search and an element of the present input;

upon a condition in which the relatedness measure does not exceed a threshold value, selecting a subset of content items based on comparing the present input with the metadata that describes the subset of content items; and

upon a condition in which the relatedness measure exceeds the threshold value, selecting a subset of content items based on comparing the present input and information about the at least one previous search with the metadata that describes the subset of content items.

2. The method of claim 1 further comprising:

upon a condition in which the relatedness measure does not exceed the threshold value, resetting a conversation state space as the elements of the present input; and

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

wherein the conversation state space stores the at least one of previous search inputs.

3. The method of claim 2, wherein augmenting the conversation state space is based on at least one of adding at least one of the elements of the present input to the conversation state space and removing at least one of the elements of the conversation state space.

4. The method of claim 1 further comprising providing access to a relationship database containing relationship distances of content items, wherein the relatedness measure is based on one of the relationship distances.

5. The method of claim 4, 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 any two content items.

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

7. The method of claim 5, 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.

8. The method of claim 5, 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.

9. The method of claim 4, wherein the relationship distances are modified by user preferences acquired over time.

10. The method of claim 4, further comprising providing access to a database containing historical inputs, wherein the relationship distances of content items are determined based on how often the content items were used together.

11. 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.

12. The method of claim 1, wherein determining the elements of the present input is based on applying a predefined rule.

13. The method of claim 12, wherein the predefined rule uses a Bayes classifier.

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

15. The method of claim 1, further comprising determining a number of relationships the at least one previous search has, wherein the threshold value is determined based on the number of relationships.

16. The method of claim 1 further comprising asking the user for the present input.

17. 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 comparing a topic of the search request to previous user input, 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, each of the content items being associated with metadata that describes the corresponding content items;

provide information about at least one search previously received from a user;

receive a present input from the user, the present input intended by the user to identify a desired content item;

determine a measure of relatedness between the information about the at least one previous search and an element of the present input;

upon a condition in which the relatedness measure does not exceed a threshold value, select a subset of content items based on comparing the present input with the metadata that describes the subset of content items; and

upon a condition in which the relatedness measure exceeds the threshold value, select a subset of content items based on comparing the present input and information about the at least one previous search with the metadata that describes the subset of content items.

18. The system of claim 17, wherein the computer readable instructions further cause the computer system to:

upon a condition in which the relatedness measure does not exceed the threshold value, reset a conversation state space as the elements of the present input; and

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

wherein the conversation state space stores the at least one of previous search inputs.

19. The system of claim 18, wherein augmenting the conversation state space is based on at least one of adding at least one of the elements of the present input to the conversation state space and removing at least one of the elements of the conversation state space.

20. The system of claim 17, 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 relatedness measure is based on one of the relationship distances.

21. The system of claim 20, 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 any two content items.

22. The system of claim 21, wherein a relationship distance of two content items is measured in a number of hops between two nodes corresponding to the two content items.

23. The system of claim 21, 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.

24. The system of claim 21, 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.

25. The system of claim 20, wherein the relationship distances are modified by user preferences acquired over time.

26. The system of claim 20, 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 the content items were used together.

27. The system of claim 17, 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.

28. The system of claim 17, wherein determining the elements of the present input is based on applying a predefined rule.

29. The system of claim 28, wherein the predefined rule uses a Bayes classifier.

30. The system of claim 17, wherein the threshold value is adjusted based on feedback from the user.

31. The system of claim 17, wherein the computer readable instructions further cause the computer system to determine a number of relationships the at least one previous search has and wherein the threshold value is determined based on the number of relationships.

32. The system of claim 17, wherein the computer readable instructions further cause the computer system to ask the user for the present input.