知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

459 records (took 0.022 seconds)

    System for Transparent Provisioning of Functionally Identical Resources across Diverse Hosting and Cloud Platforms
    171.
    发明公开
    System for Transparent Provisioning of Functionally Identical Resources across Diverse Hosting and Cloud Platforms 审中-公开

    公开(公告)号：US20240231918A1

    公开(公告)日：2024-07-11

    申请号：US18095201

    申请日：2023-01-10

    Applicant: Verint Americas Inc.

    Inventor： Constantine COIS ,  Henry ZEKTSER

    IPC: G06F9/50

    CPC classification number: G06F9/5027 ,  G06F9/5072

    Abstract: A method for deployment of cloud resources in one or more cloud environments includes receiving a request, through a user interface, to deploy a cloud resource, the request comprising an abstract resource definition and one or more target deployment locations; identifying and executing a first resource manager associated with a first target deployment location of the one or more target deployment locations; generating, with the first resource manager based on the abstract resource definition, a first manifest for deployment of the cloud resource at the first target deployment location; deploying, with the first resource manager, an instance of the cloud resource on a first cloud-computing infrastructure defined by the first target deployment location, wherein the instance is based on the first manifest; and returning, through the user interface, information corresponding to the instance of the cloud resource deployed on the first cloud-computing infrastructure.

    METHOD AND SYSTEM FOR VIRTUAL ASSISTANT CONVERSATIONS
    173.
    发明公开
    METHOD AND SYSTEM FOR VIRTUAL ASSISTANT CONVERSATIONS 审中-公开

    公开(公告)号：US20240089375A1

    公开(公告)日：2024-03-14

    申请号：US18511563

    申请日：2023-11-16

    Applicant: Verint Americas Inc.

    Inventor： Daniel Thomas Spohrer

    IPC: H04M3/51 ,  G06F3/16 ,  G06N5/043 ,  G10L15/22

    CPC classification number: H04M3/5191 ,  G06F3/167 ,  G06N5/043 ,  G10L15/22 ,  H04M3/5166 ,  H04M3/5175 ,  G10L2015/223

    Abstract: Techniques and architectures for implementing a team of virtual assistants are described herein. The team may include multiple virtual assistants that are configured with different characteristics, such as different functionality, base language models, levels of training, visual appearances, personalities, and so on. The characteristics of the virtual assistants may be configured by trainers, end-users, and/or a virtual assistant service. The virtual assistants may be presented to end-users in conversation user interfaces to perform different tasks for the users in a conversational manner. The different virtual assistants may adapt to different contexts. The virtual assistants may additionally, or alternatively, interact with each other to carry out tasks for the users, which may be illustrated in conversation user interfaces.

    SYSTEM AND METHODS FOR SUMMARIZING TRANSCRIBED AUDIO
    174.
    发明公开
    SYSTEM AND METHODS FOR SUMMARIZING TRANSCRIBED AUDIO 审中-公开

    公开(公告)号：US20240086461A1

    公开(公告)日：2024-03-14

    申请号：US17930880

    申请日：2022-09-09

    Applicant: Verint Americas Inc.

    Inventor： Konstantin Varakin

    IPC: G06F16/683 ,  G06F40/284 ,  G06F40/40

    CPC classification number: G06F16/685 ,  G06F40/284 ,  G06F40/40

    Abstract: A system and method use a trained transformer model to generate summaries of audio interactions based on keywords. Training the transformer model includes obtaining a transcription of an audio interaction, obtain keywords for summarizing the audio interaction, training a transformer model to generate a summary of the audio interaction based on the keywords and the transcription, where the transcription is an input to the transformer model and the keywords are injected between an encoder and a decoder of the transformer model, and deploying the trained transformer model to be used for generating summaries of subsequent audio interactions.

    INFLUENCE SCORING FOR SEGMENT ANALYSIS SYSTEMS AND METHODS
    176.
    发明公开
    INFLUENCE SCORING FOR SEGMENT ANALYSIS SYSTEMS AND METHODS 审中-公开

    公开(公告)号：US20240037586A1

    公开(公告)日：2024-02-01

    申请号：US17873271

    申请日：2022-07-26

    Applicant: Verint Americas Inc.

    Inventor： Hamed Janani ,  Anirudh Challa ,  Hong Wang ,  Mohamad Al-Sharara ,  José R. Benkí ,  Zealand Cooley ,  Danielle Vesia

    IPC: G06Q30/02

    CPC classification number: G06Q30/0203 ,  G06Q30/0204 ,  G06Q30/0201

    Abstract: The segment analysis system analyzes survey data to determine the influence each custom question/response combination (segment) has on a given aggregate scored survey metric for a given date/date range. The system removes from consideration all surveys that do not include a scored survey metric and date that matche the aggregate scored survey metric and given date/date range. The system further removes from consideration all surveys not pertaining received user-defined filtering. Once the system has eliminated all extraneous surveys from consideration, the system segments each question/response combinations across the pool of surveys to generate an influence score for each question/response combination. The system identifies which segment has the greatest positive and negative influence on the aggregate scored survey metric for the given date/date range. The system generates reports for the segment analysis and stores all segment analyses for further comparative analysis.

    System to detect and reduce understanding bias in intelligent virtual assistants
    179.
    发明授权
    System to detect and reduce understanding bias in intelligent virtual assistants 有权

    公开(公告)号：US11854532B2

    公开(公告)日：2023-12-26

    申请号：US17567493

    申请日：2022-01-03

    Applicant: Verint Americas Inc.

    Inventor： Ian Beaver

    IPC: G10L15/18 ,  G10L15/06 ,  G06F40/20 ,  G06F17/16

    CPC classification number: G10L15/063 ,  G06F17/16 ,  G06F40/20 ,  G10L15/18 ,  G10L2015/0636

    Abstract: Disclosed is a system and method for detecting and addressing bias in training data prior to building language models based on the training data. Accordingly system and method, detect bias in training data for Intelligent Virtual Assistant (IVA) understanding and highlight any found. Suggestions for reducing or eliminating them may be provided This detection may be done for each model within the Natural Language Understanding (NLU) component. For example, the language model, as well as any sentiment or other metadata models used by the NLU, can introduce understanding bias. For each model deployed, training data is automatically analyzed for bias and corrections suggested.

    ANOMALY DETECTION SYSTEMS AND METHODS
    180.
    发明公开
    ANOMALY DETECTION SYSTEMS AND METHODS 审中-公开

    公开(公告)号：US20230401591A1

    公开(公告)日：2023-12-14

    申请号：US17840279

    申请日：2022-06-14

    Applicant: Verint Americas Inc.

    Inventor： Hamed Janani ,  Anirudh Challa ,  Hong Wang ,  Mohamad Al-Sharara ,  José R. Benkí ,  Zealand Cooley

    IPC: G06Q30/02 ,  G06K9/62

    CPC classification number: G06Q30/0203 ,  G06K9/6256 ,  G06Q30/0201

    Abstract: An anomaly detection system using machine learning to generate predicted survey scores for a given duration and a given metric based on historic survey score data. The system compares a predicted survey score to the actual survey score and identifies anomalous actual survey scores. The anomaly detection system trains a plurality of survey score prediction models using historic survey score data. Each survey score prediction model is based on a specific survey score metric and a specific duration. The survey score prediction models generate expected survey score results for the given duration and the given metric. Based on the user-determined filtering and tolerances, the system determines if the actual survey score result is anomalous. The system generates reports for the detected anomalies and continually updates the survey score prediction models with newly obtained actual survey results, thereby improving the anomaly detection accuracy over time.

Patent Agency Ranking