Method for adaptive conversation state management with filtering operators applied dynamically as part of a conversational interface
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.
1. A method for processing search requests received from the user, the method comprising:
receiving, in a conversation state space defined by a first filter, the first filter comprising a first term of a first attribute type, a first speech input;
identifying in the first speech input a second filter comprising a first term of a second attribute type;
selecting a first set of content items based on the first filter and the second filter;
generating for display the first set of content items;
receiving a second speech input;
identifying in the second speech input a third filter comprising a second term of the second attribute type;
determining whether any content items match the first filter, the second filter, and the third filter;
in response to determining that a content item matches the first filter, the second filter, and the third filter:
selecting a second set of content items based on the first filter, the second filter, and the third filter; and
generating for display the second set of content items; and
in response to determining that no content items match the first filer, the second filter, and the third filter:
replacing the second filter with the third filter;
selecting a third set of content items based on the first filter and the third filter; and
generating for display third set of content items.
2. The method of claim 1 wherein replacing the second filter with the third filter further comprises:
accessing a relationship database containing relationship distances between filters; and
determining that a relationship distance between the second filter and the third filter exceeds a threshold value.
3. The method of claim 1 wherein the relationship database comprises a relationship graph with nodes and edges, each node representing a filter and each edge representing a direct relationship between two filters.
4. The method of claim 2 , wherein a relationship distance between two filters is measured in a smallest number of hops between two nodes corresponding to the two filters.
5. The method of claim 2 , wherein each edge has a weight, and wherein a relationship distance between two filters is measured as a sum of weights of edges connecting two nodes corresponding to the two filters.
6. The method of claim 2 , wherein the relationship distances in the relationship database are modified by user preferences acquired over time.
7. The method of claim 2 , further comprising:
providing access to a database containing historical inputs, wherein the relationship distances between filters are determined based on how often the filters were used together.
8. The method of claim 1 , wherein selecting a first set of content items further comprises determining that the first and second filters in the conversation state space have a related measure exceeding a threshold value based on searching for content items in the set of content items that are associated with metadata matching the first and the second filters in the conversation space.
9. The method of claim 1 , wherein selecting the second set of content items further comprises determining that the first, second and third filters in the conversation state space have a related 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 space.
10. The method of claim 1 , wherein selecting the third set of content items further comprises determining that the first and third filters in the conversation state space have a related measure exceeding a threshold value based on searching for content items in the set of content items that are associated with metadata matching the first and third filters in the conversation space.
11. A system for processing search requests received from a user, the system comprising:
input circuitry configured to receive speech inputs; and
control circuitry configured to:
receive, using the input circuitry, in a conversation state space defined by a first filter, the first filter comprising a first term of a first attribute type, a first speech input;
identify in the first speech input a second filter comprising a first term of a second attribute type;
select a first set of content items based on the first filter and the second filter;
generating for display the first set of content items;
receive, using the input circuitry, a second speech input;
identify in the second speech input a third filter comprising a second term of the second attribute type;
determine whether any content items match the first filter, the second filter, and the third filter;
in response to determining that a content item matches the first filter, the second filter, and the third filter:
select a second set of content items based on the first filter, the second filter, and the third filter; and
generate for display the second set of content items; and
in response to determining that no content items match the first filer, the second filter, and the third filter:
replace the second filter with the third filter;
select a third set of content items based on the first filter and the third filter; and
generate for display third set of content items.
12. The system of claim 11 wherein the control circuitry configured to replace the second filter with the third filter is further configured to:
access relationship database containing relationship distances between filters; and
determine that a relationship distance between the second filter and the third filter exceeds a threshold value.
13. The system of claim 12 wherein the relationship database comprises a relationship graph with nodes and edges, each node representing a filter and each edge representing a direct relationship between two filters.
14. The system of claim 12 , wherein a relationship distance between two filters is measured in a smallest number of hops between two nodes corresponding to the two filters.
15. The system of claim 12 , wherein each edge has a weight, and wherein a relationship distance between two filters is measured as a sum of weights of edges connecting two nodes corresponding to the two filters.
16. The system of claim 12 , wherein the relationship distances in the relationship database are modified by user preferences acquired over time.
17. The system of claim 12 , wherein the control circuitry is further configured to:
provide access to a database containing historical inputs, wherein the relationship distances between filters are determined based on how often the filters were used together.
18. The system of claim 11 , wherein the control circuitry configured to select the first set of content items is further configured to determine that the first and second filters in the conversation state space have a related measure exceeding a threshold value based on searching for content items in the set of content items that are associated with metadata matching the first and the second filters in the conversation space.
19. The system of claim 11 , wherein the control circuitry configured to select the second set of content items is further configured to determine that the first, second and third filters in the conversation state space have a related 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 space.
20. The system of claim 11 , wherein the control circuitry configured to select third set of content items is further configured to determine that the first and third filters in the conversation state space have a related measure exceeding a threshold value based on searching for content items in the set of content items that are associated with metadata matching the first and third filters in the conversation space.