IDENTIFICATION AND CLASSIFICATION OF TALK-OVER SEGMENTS DURING VOICE COMMUNICATIONS USING MACHINE LEARNING MODELS

    公开(公告)号:US20230215429A1

    公开(公告)日:2023-07-06

    申请号:US17570121

    申请日:2022-01-06

    Applicant: NICE LTD

    Abstract: A system and methods are provided to analyze audio signals from an incoming voice call. The system includes a processor and a computer readable medium operably coupled thereto, to perform voice analysis operations which include receiving a first audio signal comprising a first audio waveform of a first speech between at least two users during the incoming voice call, accessing speech segment parameters for analyzing the audio signals, determining one or more talk-over segments in the first audio waveform using the speech segment parameters, extracting audio features from each of the one or more talk-over segments, determining, using a machine learning (ML) model trained for interruption analysis of the audio signals, whether each of the one or more talk-over segments are a negative interruption or a non-negative interruption based on the audio features, and determining whether to output a first notification for the negative interruption or the non-negative interruption.

    SYSTEMS AND METHODS FOR FINDING AN INTERACTION SUBSET WITHIN A SET OF INTERACTIONS

    公开(公告)号:US20220092616A1

    公开(公告)日:2022-03-24

    申请号:US17541856

    申请日:2021-12-03

    Applicant: Nice Ltd.

    Abstract: A method and system for analyzing interactions (for example between a person and an organization) may include for a number of series of interactions (which may be termed journeys), each interaction represented by a channel and a reason, iterating over the series of interactions by selecting initial information including an interaction subset including one or more interactions, and if there is a set of interaction series among the series of interactions meeting certain conditions, adding an interaction to the interaction subset and determining in a recursive fashion if for the interaction subset, there is a subset among the set of interaction series meeting the conditions which also meet the conditions. Conditions may include a threshold average rating for the set of interaction series, and a threshold number of interaction series in which the interaction subset is found.

    SYSTEMS AND METHODS FOR SELECTING A TRAINING PROGRAM FOR A WORKER

    公开(公告)号:US20210097634A1

    公开(公告)日:2021-04-01

    申请号:US16583303

    申请日:2019-09-26

    Applicant: NICE LTD.

    Abstract: A system and method for selecting a training program from a plurality of training programs for a selected worker may include evaluating performance improvement of a plurality of workers who have taken training programs of the plurality of training programs, and associating a performance improvement grade to each of the workers for each of the training programs the worker has taken; selecting, in a worker database, workers that are similar to the selected worker; and selecting the training program for the selected worker based on the performance improvement grades associated with the similar workers for the plurality of training programs.

    SYSTEM AND METHOD FOR MAPPING A CUSTOMER JOURNEY TO A CATEGORY

    公开(公告)号:US20200082822A1

    公开(公告)日:2020-03-12

    申请号:US16564841

    申请日:2019-09-09

    Applicant: NICE LTD.

    Abstract: Systems and methods of mapping a customer journey in an interactive voice response (IVR) system to a contact reason from a contact reasons list: receive an IVR log comprising a plurality of customer journey entries, wherein each customer journey entry comprises a sequence of one or more menu identifiers; generate an embedding vector for each menu identifier; filter one or more menu identifiers from a menu identifier list, wherein the menu identifier list comprises all menu identifiers contained in the IVR log; cluster one or more remaining menu identifiers from the menu identifier list into one or more clusters, based on the embedding vector of each menu identifier; map each cluster to a contact reason; and create a rule that categorizes a newly received IVR sequence based on a cooccurrence of at least one menu identifier in the newly received IVR sequence and in a given cluster.

Patent Agency Ranking