System and method for performing speech analytics with objective function and feature constaints

Abstract

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing trend analysis of speech. A system practicing the method receives a speech trend analysis request having candidate feature constraints, an objective function with respect to a speech trend to be analyzed, and a set of speech record constraints. The system selects a subset of speech records from the group of speech records based on the set of speech record constraints to yield selected speech records, identifies features in the selected speech records based on the set of candidate feature constraints to yield identified features, and assigns a weight to each of the identified features based on the objective function. Then the system ranks the identified features by their respective weights to yield ranked identified features, and outputs at least one of the ranked identified features associated with a speech-based trend in response to the speech trend analysis request.

We claim: 
     
         1 . A method comprising:
 generating, via a processor, elements of a time series, wherein each element comprises speech records having timestamps within a same time interval;   generating, via the processor, a numeric value for each element in the time series according to:
 (1) a weight for each speech record, wherein the weight is calculated using a set of candidate feature constraints; 
 (2) an objective function with respect to a trend to be analyzed; and 
 (3) a set of record constraints to be applied to a group of records; and 
   generating, via the processor, an alarm when a value for at least one element in the time series meets a threshold.   
     
     
         2 . The method of  claim 1 , wherein the weight is further calculated using a statistical regression. 
     
     
         3 . The method of  claim 1 , wherein a user specifies a size of the same time interval. 
     
     
         4 . The method of  claim 1 , wherein the elements of the time series are separated by an interval offset. 
     
     
         5 . The method of  claim 1 , wherein the numerical value for each element in the time series is further generated by summing respective scores for a plurality of features. 
     
     
         6 . The method of  claim 1 , further comprising notifying a user when a specific combination of alarms is generated, the specific combination of alarms including the alarm. 
     
     
         7 . The method of  claim 1 , wherein the threshold is relative to other elements in the time series. 
     
     
         8 . A system comprising:
 a processor; and   a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
 generating elements of a time series, wherein each element comprises speech records having timestamps within a same time interval; 
 generating a numeric value for each element in the time series according to:
 (1) a weight for each speech record, wherein the weight is calculated using a set of candidate feature constraints; 
 (2) an objective function with respect to a trend to be analyzed; and 
 (3) a set of record constraints to be applied to a group of records; and 
 
 generating an alarm when a value for at least one element in the time series meets a threshold. 
   
     
     
         9 . The system of  claim 8 , wherein the weight is further calculated using a statistical regression. 
     
     
         10 . The system of  claim 8 , wherein a user specifies a size of the same time interval. 
     
     
         11 . The system of  claim 8 , wherein the elements of the time series are separated by an interval offset. 
     
     
         12 . The system of  claim 8 , wherein the numerical value for each element in the time series is further generated by summing respective scores for a plurality of features. 
     
     
         13 . The system of  claim 8 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising notifying a user when a specific combination of alarms is generated, the specific combination of alarms including the alarm. 
     
     
         14 . The system of  claim 8 , wherein the threshold is relative to other elements in the time series. 
     
     
         15 . A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
 generating elements of a time series, wherein each element comprises speech records having timestamps within a same time interval;   generating a numeric value for each element in the time series according to:
 (1) a weight for each speech record, wherein the weight is calculated using a set of candidate feature constraints; 
 (2) an objective function with respect to a trend to be analyzed; and 
 (3) a set of record constraints to be applied to a group of records; and 
   generating an alarm when a value for at least one element in the time series meets a threshold.   
     
     
         16 . The computer-readable storage device of  claim 15 , wherein the weight is further calculated using a statistical regression. 
     
     
         17 . The computer-readable storage device of  claim 15 , wherein a user specifies a size of the same time interval. 
     
     
         18 . The computer-readable storage device of  claim 15 , wherein the elements of the time series are separated by an interval offset. 
     
     
         19 . The computer-readable storage device of  claim 15 , wherein the numerical value for each element in the time series is further generated by summing respective scores for a plurality of features. 
     
     
         20 . The computer-readable storage device of  claim 15 , having additional instructions stored which, when executed by the computing device, cause the computing device to perform operations comprising notifying a user when a specific combination of alarms is generated, the specific combination of alarms including the alarm.