公开(公告)号：US11451658B1

公开(公告)日：2022-09-20

申请号：US17320295

申请日：2021-05-14

Applicant: Nice Ltd.

Inventor： Roman Frenkel ,  Gal Wolbe ,  Ofir Lavi

IPC: H04M3/22 ,  H04M3/51 ,  G10L17/12 ,  H04M3/42

Abstract: Methods for improved fraudster detection in a call center. A subset of a plurality of voiceprints from a plurality of interactions between callers and agents at a call center can be used as the basis for fraudster detection. A plurality of connected components that represents one or more voiceprints can be determined based on the subset of the plurality of voiceprints.

公开(公告)号：US11375063B1

公开(公告)日：2022-06-28

申请号：US17197742

申请日：2021-03-10

Applicant: NICE LTD.

Inventor： Roman Frenkel ,  Tal Raskin ,  Adi Ben Zeev ,  Stav Mishory ,  Dan Teplitski ,  Hadas Katz

IPC: H04M3/523 ,  G06F40/295 ,  G10L15/02 ,  G10L15/26 ,  H04M3/51

Abstract: Systems for and methods of determining the priority of a call interaction include receiving a call interaction from a call center; validating, by a validation and transcription engine, that the call interaction is authentic; converting, by the validation and transcription engine, the call interaction into text; extracting, by a data calculation engine, organization, location, and time information from the text; calculating, by the data calculation engine, a priority of the call interaction from the extracted information and the text; determining that the call interaction should be transmitted to a queue of the call center for initial handling by a call center agent; and transmitting the call interaction, the calculated priority, and the extracted information to the call center.

公开(公告)号：US11039012B2

公开(公告)日：2021-06-15

申请号：US16525606

申请日：2019-07-30

Applicant: NICE LTD

Inventor： Levan Michaeli ,  Zvika Weingarten ,  Itay Harel ,  Roman Frenkel ,  Matan Keret ,  Amit Sharon ,  Sigal Lev

IPC: H04M3/51 ,  G06N20/00 ,  G10L17/00 ,  G10L15/22 ,  G10L17/04 ,  G10L15/26 ,  G06F21/43

Abstract: A computer-implemented method for proactive fraudster exposure in a customer service center having multiple service channels is provided herein. The computer-implemented method may collect call interactions based on predefined rules by a calls collection engine and store the collected call interactions. The computer-implemented method may further analyze the call interactions by a Proactive Fraud Exposure engine by: (i) generating a voiceprint for each call interaction; (ii) using machine learning technique to group the call interactions into one or more clusters based on respective voiceprints in the voiceprints database; (iii) storing the one or more clusters; and (iv) ranking and classifying the one or more clusters to yield a list of potential fraudsters. The computer-implemented method may further transmit the list of potential fraudsters to a user to enable the user to review said list of potential fraudsters and to add fraudsters from the list to a watchlist database.

公开(公告)号：US10885920B2

公开(公告)日：2021-01-05

申请号：US16236655

申请日：2018-12-31

Applicant: NICE LTD

Inventor： Alon Menahem Shoa ,  Roman Frenkel ,  Matan Keret

IPC: G10L17/22

Abstract: A method for separating and authenticating speech of a speaker on an audio stream of speakers over an audio channel may include receiving audio stream data of the audio stream with speech from a speaker to be authenticated speaking with a second speaker. A voiceprint may be generated for each data chunk in the audio stream data divided into a plurality of data chunks. The voiceprint for each data chunk may be assessed as to whether the voiceprint has speech belonging to the speaker to be authenticated or to the second speaker using representative voiceprints of both speakers. An accumulated voiceprint may be generated using the verified data chunks with speech of the speaker to be authenticated. The accumulated voiceprint may be compared to the reference voiceprint of the speaker to be authenticated for authenticating the speaker speaking with the second speaker over the audio channel.