Systems and methods for classification and rating of calls based on voice and text analysis

Abstract

Methods and systems include sending recording data of a call to a first server and a second server, wherein the recording data includes a first voice of a first participant of the call and a second voice of a second participant of the call; receiving, from the first server, a first emotion score representing a degree of a first emotion associated with the first voice, and a second emotion score representing a degree of a second emotion associated with the first voice; receiving, from the second server, a first sentiment score, a second sentiment score, and a third sentiment score; determining a quality score and classification data for the recording data based on the first emotion score, the second emotion score, the first sentiment score, the second sentiment score, and the third sentiment score; and outputting the quality score and the classification data for visualization of the recording data.

What is claimed is: 
     
         1 - 20 . (canceled) 
     
     
         21 . A system, comprising:
 a non-transitory computer-readable medium configured to store instructions; and   at least one processor configured to execute the instructions to perform operations comprising:
 analyzing recording data of a call, wherein:
 the recording data comprises a first voice of a first participant of the call and a second voice of a second participant of the call; and 
 the analyzing includes: 
 determining a first emotion score representing a degree of a first emotion associated with the first voice, wherein the first emotion score is determined using a voice-based emotion scoring technique; 
 determining a first sentiment score associated with a first transcript of both the first voice and the second voice, wherein the first sentiment score is determined using a text-based sentiment scoring technique; 
 
 determining a quality score for the recording data based on the first emotion score and the first sentiment score; 
 determining classification data for the recording data based on the quality score; and 
 outputting the quality score and the classification data for visualization of the recording data. 
   
     
     
         22 . The system of  claim 21 , wherein:
 the analyzing further includes determining a second emotion score representing a degree of a second emotion associated with the first voice; and   the quality score is determined based on the first emotion score, the second emotion score, and the first sentiment score.   
     
     
         23 . The system of  claim 22 , wherein:
 the analyzing further includes determining a second sentiment score associated with a second transcript of the first voice and a third sentiment score associated with a third transcript of the second voice, wherein the second sentiment score and the third sentiment score are determined using a text-based sentiment scoring technique; and   the quality score is determined based on the first emotion score, the second emotion score, the first sentiment score, the second sentiment score, and the third sentiment score.   
     
     
         24 . The system of  claim 23 , wherein the recording data comprises a first recording of both the first voice and the second voice, a second recording of the first voice, and a third recording of the second voice. 
     
     
         25 . The system of  claim 24 , wherein the operations further comprise:
 generating the second recording and the third recording from the first recording; and   analyzing the second recording to determine the first emotion score and the second emotion score.   
     
     
         26 . The system of  claim 25 , wherein the operations further comprise:
 analyzing the third recording to determine a third emotion score representing a degree of the first emotion associated with the second voice and a fourth emotion score representing a degree of the second emotion associated with the second voice.   
     
     
         27 . The system of  claim 23 , wherein the first transcript, the second transcript, and the third transcript are generated using a speech-to-text technique using the first voice and the second voice as inputs. 
     
     
         28 . The system of  claim 23 , wherein determining the quality score for the recording data comprises:
 determining the quality score as a weighted sum of the first emotion score, the second emotion score, the first sentiment score, the second sentiment score, and the third sentiment score.   
     
     
         29 . The system of  claim 28 , wherein:
 the weighted sum is determined by applying weights to any one or more of: the first emotion score, the second emotion score, the first sentiment score, the second sentiment score, and the third sentiment score; and   the weights are determined based on any one of:
 a weight of the first emotion score is higher than a weight of the second emotion score in response to the first emotion score being higher than the second emotion score; 
 the weight of the second sentiment score is higher than the weight of the first sentiment score or a weight of the third sentiment score in response to the first participant being a customer and the second participant being an agent; 
 the weight of the first emotion score and the weight of the second sentiment score are linearly proportional based on the corresponding emotional score; or 
 the weight of the first emotion score and the weight of the second sentiment score are correlated based on the corresponding emotional score. 
   
     
     
         30 . The system of  claim 23 , wherein the operations further comprise:
 determining a set of weighted keywords, wherein:
 each keyword is associated with a weight value; and 
 the set of weighted keywords is determined based on the first transcript, the second transcript, or the third transcript; and 
   outputting the set of weighted keywords, the quality score, and the classification data for visualization of the recording data.   
     
     
         31 . The system of  claim 30 , wherein the operations further comprise:
 determining relationship data linking a portion of the recording data and a word in one of the first transcript, the second transcript, or the third transcript, wherein the relationship data enables finding the portion of the recording data by searching for the word.   
     
     
         32 . The system of  claim 23 , wherein the operations further comprise:
 determining a third emotion score representing a degree of the first emotion associated with the second voice and a fourth emotion score representing a degree of the second emotion associated with the second voice; and   determining the quality score based on the first emotion score, the second emotion score, the third emotion score, the fourth emotion score, the first sentiment score, the second sentiment score, and the third sentiment score.   
     
     
         33 . The system of  claim 22 , wherein the first emotion and the second emotion are selected from: anger, happiness, sadness, fear, or neutrality. 
     
     
         34 . The system of  claim 21 , wherein:
 the quality score is divided into a set of predetermined ranges;   each predetermined range is associated with a label; and   the classification data is the label corresponding to the predetermined range of the quality score.   
     
     
         35 . The system of  claim 21 , wherein the classification data is indicative of a negative label, a positive label, or a neutral label. 
     
     
         36 . A computer-implemented method, comprising:
 analyzing recording data of a call, wherein:
 the recording data comprises a first voice of a first participant of the call and a second voice of a second participant of the call; and 
 the analyzing includes:
 determining a first emotion score representing a degree of a first emotion associated with the first voice, wherein the first emotion score is determined using a voice-based emotion scoring technique; 
 determining a first sentiment score associated with a first transcript of both the first voice and the second voice, wherein the first sentiment score is determined using a text-based sentiment scoring technique; 
 
   determining a quality score for the recording data based on the first emotion score and the first sentiment score;   determining classification data for the recording based on the quality score; and   outputting the quality score and the classification data for visualization of the recording data.   
     
     
         37 . The computer-implemented method of  claim 36 , wherein:
 the analyzing further includes determining a second emotion score representing a degree of a second emotion associated with the first voice; and   the quality score is determined based on the first emotion score, the second emotion score, and the first sentiment score.   
     
     
         38 . The computer-implemented method of  claim 37 , wherein:
 the analyzing further includes determining a second sentiment score associated with a second transcript of the first voice and a third sentiment score associated with a third transcript of the second voice, wherein the second sentiment score and the third sentiment score are determined using a text-based sentiment scoring technique; and   the quality score is determined based on the first emotion score, the second emotion score, the first sentiment score, the second sentiment score, and the third sentiment score.   
     
     
         39 . The computer-implemented method of  claim 38 , wherein determining the quality score for the recording data comprises:
 determining the quality score as a weighted sum of the first emotion score, the second emotion score, the first sentiment score, the second sentiment score, and the third sentiment score.   
     
     
         40 . The computer-implemented method of  claim 39 , wherein:
 the weighted sum is determined by applying weights to any one or more of: the first emotion score, the second emotion score, the first sentiment score, the second sentiment score, and the third sentiment score; and   the weights are determined based on any one of:
 a weight of the first emotion score is higher than a weight of the second emotion score in response to the first emotion score being higher than the second emotion score; 
 the weight of the second sentiment score is higher than the weight of the first sentiment score or a weight of the third sentiment score in response to the first participant being a customer and the second participant being an agent; 
 the weight of the first emotion score and the weight of the second sentiment score are linearly proportional based on the corresponding emotional score; or 
 the weight of the first emotion score and the weight of the second sentiment score are correlated based on the corresponding emotional score. 
   
     
     
         41 . The computer-implemented method of  claim 38 , further comprising:
 determining a set of weighted keywords, wherein:
 each keyword is associated with a weight value; 
 the set of weighted keywords is determined based on the first transcript, the second transcript, or the third transcript; and 
   outputting the set of weighted keywords, the quality score, and the classification data for visualization of the recording data.   
     
     
         42 . The computer-implemented method of  claim 41 , further comprising:
 determining relationship data linking a portion of the recording data and a word in one of the first transcript, the second transcript, or the third transcript, wherein the relationship data enables finding the portion of the recording data by searching for the word.   
     
     
         43 . The computer-implemented method of  claim 38 , further comprising:
 determining a third emotion score representing a degree of the first emotion associated with the second voice and a fourth emotion score representing a degree of the second emotion associated with the second voice; and   determining the quality score based on the first emotion score, the second emotion score, the third emotion score, the fourth emotion score, the first sentiment score, the second sentiment score, and the third sentiment score.   
     
     
         44 . The computer-implemented method of  claim 37 , wherein the first emotion and the second emotion are selected from anger, happiness, sadness, fear, or neutrality.