Ranking based on speech pattern detection
First Claim
Patent Images
1. A computer-implemented method for processing a query, comprising operations for:
- in response to receiving the query, identifying, using a processor of a computer, search results comprising items from multiple items stored in a data store;
building a confidence model that applies speech characteristics in a context of public speaking experience level of a speaker and expertise level of the speaker;
ranking the items of the search results using the confidence model based on a confidence score associated with each of the items, wherein the confidence score is generated for each of the items by,detecting the speech characteristics of the item;
determining a hesitation level of the item based on the speech characteristics, wherein the hesitation level is adjusted based on counts including a count of filler words and pauses of the item, a count of each change in pitch of a user associated with the item, and a count of bridge transitions of the item;
generating a confidence score based on the hesitation level; and
storing an item identifier of the item, the hesitation level, the confidence score, and the counts in a database; and
displaying, on a display screen of the computer, the ranked items of the search results with the confidence score associated with each of the items to respond to the query.
2 Assignments
0 Petitions
Accused Products
Abstract
Provided are techniques for processing a query in a Q&A system and ranking search results based on speech pattern detection. In response to the query, search results comprising items from multiple items are identified. The search results are ranked based on a confidence score associated with each of the items from the multiple items. The confidence score is generated for each of the items by, detecting speech characteristics of the item, determining a hesitation level of the item based on the speech characteristics, and generating a confidence score based on the hesitation level.
-
Citations
20 Claims
-
1. A computer-implemented method for processing a query, comprising operations for:
-
in response to receiving the query, identifying, using a processor of a computer, search results comprising items from multiple items stored in a data store; building a confidence model that applies speech characteristics in a context of public speaking experience level of a speaker and expertise level of the speaker; ranking the items of the search results using the confidence model based on a confidence score associated with each of the items, wherein the confidence score is generated for each of the items by, detecting the speech characteristics of the item; determining a hesitation level of the item based on the speech characteristics, wherein the hesitation level is adjusted based on counts including a count of filler words and pauses of the item, a count of each change in pitch of a user associated with the item, and a count of bridge transitions of the item; generating a confidence score based on the hesitation level; and storing an item identifier of the item, the hesitation level, the confidence score, and the counts in a database; and displaying, on a display screen of the computer, the ranked items of the search results with the confidence score associated with each of the items to respond to the query. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computer program product for processing a query, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by at least one processor of a computer to perform operations for:
-
in response to receiving the query, identifying search results comprising items from multiple items stored in a data store; building a confidence model that applies speech characteristics in a context of public speaking experience level of a speaker and expertise level of the speaker; ranking the items of the search results using the confidence model based on a confidence score associated with each of the items, wherein the confidence score is generated for each of the items by, detecting the speech characteristics of the item; determining a hesitation level of the item based on the speech characteristics, wherein the hesitation level is adjusted based on counts including a count of filler words and pauses of the item, a count of each change in pitch of a user associated with the item, and a count of bridge transitions of the item; generating a confidence score based on the hesitation level; and storing an item identifier of the item, the hesitation level, the confidence score, and the counts in a database; and displaying, on a display screen of the computer, the ranked items of the search results with the confidence score associated with each of the items to respond to the query. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A computer system for processing a query, comprising:
-
one or more processors, one or more computer-readable memories and one or more computer-readable, tangible storage devices; and program instructions, stored on at least one of the one or more computer-readable, tangible storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to perform operations comprising; in response to receiving the query, identifying search results comprising items from multiple items stored in a data store; building a confidence model that applies speech characteristics in a context of public speaking experience level of a speaker and expertise level of the speaker; ranking the items of the search results using the confidence model based on a confidence score associated with each of the items, wherein the confidence score is generated for each of the items by, detecting the speech characteristics of the item; determining a hesitation level of the item based on the speech characteristics, wherein the hesitation level is adjusted based on counts including a count of filler words and pauses of the item, a count of each change in pitch of a user associated with the item, and a count of bridge transitions of the item; generating a confidence score based on the hesitation level; and storing an item identifier of the item, the hesitation level, the confidence score, and the counts in a database; and displaying, on a display screen of the computer system, the ranked items of the search results with the confidence score associated with each of the items to respond to the query. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification