公开(公告)号：US20230342771A1

公开(公告)日：2023-10-26

申请号：US18139482

申请日：2023-04-26

Applicant: FMR LLC

Inventor： Eoghan Considine ,  Luella Gergen Wong ,  Aidan Fogarty ,  Rosaleen Gilligan ,  Shane Tully ,  Eamonn Fox ,  Seemanthini Jois ,  Jenson Joy

IPC: G06Q20/40 ,  H04M3/22 ,  G10L25/66 ,  G10L25/30

CPC classification number: G06Q20/40 ,  H04M3/2236 ,  G10L25/66 ,  G10L25/30

Abstract: Systems and methods are described herein for identifying diminished capacity of a voice call participant based on audio data analysis. A server generates an audio image based on an audio file comprising speech data corresponding to a first user on a voice call. The server determines a diminished capacity score based on one or more characteristics of the audio image analyzed using a deep learning classification model. The server applies a security protocol to an account associated with the first user when the diminished capacity score is at or above a threshold value. The server receives a transaction request corresponding to the account from the first user. The server processes the transaction request based on the security protocol applied to the account.

公开(公告)号：US12113934B1

公开(公告)日：2024-10-08

申请号：US18626879

申请日：2024-04-04

Applicant: FMR LLC

Inventor： Bryan Dempsey ,  Saquib Ilahi ,  Jenson Joy ,  Nirupam Sarkar ,  Murad Maayah ,  Abigail Parker ,  Meagan Gilbert ,  Derek Kaschl

IPC: H04M3/51 ,  G09B5/02 ,  G10L15/18 ,  G10L15/183 ,  H04M3/42

CPC classification number: H04M3/5175 ,  G09B5/02 ,  G10L15/1815 ,  G10L15/183 ,  H04M3/42221 ,  H04M2201/405 ,  H04M2201/42 ,  H04M2203/401 ,  H04M2203/403

Abstract: A computer-implemented method is provided for quantitative performance evaluation of a call agent. The method comprises converting an audio recording of a call between the call agent and a customer to a text-based transcript and identifying at least one topic for categorizing the transcript. The method also includes retrieving a set of criteria associated with the topic. Each criterion correlates to a set of predefined questions for interrogating the transcript to evaluate the performance of the call agent with respect to the corresponding criterion. Each question captures a sub-criterion under the corresponding criterion. The method further includes inputting the predefined questions and the transcript into a trained large language model to obtain scores for respective ones of the predefined questions. Each score measures a degree of satisfaction of the performance of the call agent during the call with respect to the sub-criterion captured by the corresponding predefined question.

公开(公告)号：US12039531B2

公开(公告)日：2024-07-16

申请号：US18139482

申请日：2023-04-26

Applicant: FMR LLC

Inventor： Eoghan Considine ,  Luella Gergen Wong ,  Aidan Fogarty ,  Rosaleen Gilligan ,  Shane Tully ,  Eamonn Fox ,  Seemanthini Jois ,  Jenson Joy

IPC: G06Q20/40 ,  G10L25/30 ,  G10L25/66 ,  H04M3/22

CPC classification number: G06Q20/40 ,  G10L25/30 ,  G10L25/66 ,  H04M3/2236

Abstract: Systems and methods are described herein for identifying diminished capacity of a voice call participant based on audio data analysis. A server generates an audio image based on an audio file comprising speech data corresponding to a first user on a voice call. The server determines a diminished capacity score based on one or more characteristics of the audio image analyzed using a deep learning classification model. The server applies a security protocol to an account associated with the first user when the diminished capacity score is at or above a threshold value. The server receives a transaction request corresponding to the account from the first user. The server processes the transaction request based on the security protocol applied to the account.