公开(公告)号：US20240126991A1

公开(公告)日：2024-04-18

申请号：US18046116

申请日：2022-10-12

Applicant: Verint Americas Inc.

Inventor： Ron Peretz Epstein Koch ,  Avidor Tenenboim ,  Dvir Cohen ,  Eran Sela

IPC: G06F40/289 ,  G06F9/451 ,  G06F40/58

CPC classification number: G06F40/289 ,  G06F9/452 ,  G06F40/58 ,  G06F16/23

Abstract: An automated interaction processing system is deployed to automatically process an interaction transcription or content to generate response data in a manner that does not require intensive human manual effort.

公开(公告)号：US20240127800A1

公开(公告)日：2024-04-18

申请号：US18046969

申请日：2022-10-17

Applicant: Verint Americas Inc.

Inventor： Ron Peretz Epstein Koch ,  Ian Beaver ,  Dvir Cohen

IPC: G10L15/08 ,  G10L15/02

CPC classification number: G10L15/083 ,  G10L15/02 ,  G10L2015/088

Abstract: A system including an interaction processing component is deployed to automatically validate information exchanged during an interaction.

公开(公告)号：US20250111323A1

公开(公告)日：2025-04-03

申请号：US18477701

申请日：2023-09-29

Applicant: Verint Americas Inc.

Inventor： Ron Peretz Epstein Koch ,  Karni Gilon ,  Dvir Cohen

IPC: G06Q10/0639 ,  G06N3/045 ,  G06N3/08

Abstract: Systems and methods for automating quality metrics are provided. Transcripts of interactions with agents and assigned quality metrics for a variety of questions are collected for an entity. The quality metrics may relate to questions such as “Did the agent greet the customer with a friendly greeting?” and “Did the agent answer the customer's question after returning from the hold?”. For each question used by the entity to generate quality metrics, a large language model or classifier is trained for the question using the transcripts and the assigned quality metrics for the question. The transcripts may be processed to include textual information corresponding to metadata associated with the communications such as time stamps for call holds, utterances, and silent periods. The trained large language model or classifiers may then be used later to automatically assign quality metrics to current interactions for their corresponding question.