利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

10 条记录 (耗时 0.018 秒)

    Reactive learning for efficient dialog tree expansion
    1.
    发明授权
    Reactive learning for efficient dialog tree expansion 有权

    公开(公告)号：US09812127B1

    公开(公告)日：2017-11-07

    申请号：US15142187

    申请日：2016-04-29

    申请人： Conduent Business Services, LLC

    发明人： Julien Perez ,  Nicolas Monet

    IPC分类号： G10L15/22 ,  G06F17/27 ,  G06F17/24 ,  G10L15/06

    CPC分类号： G10L15/22 ,  G06F17/241 ,  G06F17/279

    摘要： A method for generating dialogs for learning a dialog policy includes, for each of at least one scenario, in which annotators in a pool of annotators serve as virtual agents and users, generating a respective dialog tree in which each path through the tree corresponds to a dialog and nodes of the tree correspond to dialog acts provided by the annotators. The generation includes computing a measure of uncertainty for nodes in the dialog tree, identifying a next node to be annotated, based on the measure of uncertainty, selecting an annotator from the pool to provide an annotation for the next node, receiving an annotation from the selected annotator for the next node, and generating a new node of the dialog tree based on the received annotation. A corpus of dialogs is generated from the dialog tree.

    Generative discriminative approach for transactional dialog state tracking via collective matrix factorization
    2.
    发明授权
    Generative discriminative approach for transactional dialog state tracking via collective matrix factorization 有权

    公开(公告)号：US09811519B2

    公开(公告)日：2017-11-07

    申请号：US14864076

    申请日：2015-09-24

    申请人： Conduent Business Services, LLC

    发明人： Julien Perez

    IPC分类号： G06F17/00 ,  G10L15/00 ,  G06Q30/00 ,  G06F17/27 ,  G10L15/22

    CPC分类号： G06F17/279 ,  G10L15/22

    摘要： A computer-implemented method for dialog state tracking employs first and second latent variable models which have been learned by reconstructing a decompositional model generated from annotated training dialogs. The decompositional model includes, for each of a plurality of dialog state transitions corresponding to a respective turn of one of the training dialogs, state descriptors for initial and final states of the transition and a respective representation of the dialog for that turn. The first latent variable model includes embeddings of the plurality of state transitions, and the second latent variable model includes embeddings of features of the state descriptors and embeddings of features of the dialog representations. Data for a new dialog state transition is received, including a state descriptor for the initial time and a respective dialog representation. A state descriptor for the final state of the new dialog state transition is predicted using the learned latent variable models.

    System and method for automatic process error detection and correction
    3.
    发明授权
    System and method for automatic process error detection and correction 有权

    公开(公告)号：US11113670B2

    公开(公告)日：2021-09-07

    申请号：US15477825

    申请日：2017-04-03

    申请人： Conduent Business Services, LLC

    发明人： Julien Perez ,  Tomi Viljam Silander ,  Adrian Corneliu Mos

    IPC分类号： G06Q10/10 ,  H04L12/58

    摘要： A method and apparatus for detecting an error in a business process via an exchange of email messages. In one example, the method may be executed by a processor of a business process analysis server (BPAS). For example, the method includes receiving an email, wherein the email includes an address of the BPAS, analyzing the email to determine at least one feature, determining the business process based on the at least one feature, determining one or more variables that is associated with the business process, detecting the error in the business process associated with the email based on at least variable of the one or more variables associated with the business process and generating an alert email in response to the error that is detected, wherein the alert email requests a correction to the at least one variable to complete the business process.

    REACTIVE LEARNING FOR EFFICIENT DIALOG TREE EXPANSION
    7.
    发明申请
    REACTIVE LEARNING FOR EFFICIENT DIALOG TREE EXPANSION 有权

    公开(公告)号：US20170316777A1

    公开(公告)日：2017-11-02

    申请号：US15142187

    申请日：2016-04-29

    申请人： Conduent Business Services, LLC

    发明人： Julien Perez ,  Nicolas Monet

    IPC分类号： G10L15/22 ,  G06F17/24 ,  G10L15/06 ,  G06F17/27

    CPC分类号： G10L15/22 ,  G06F17/241 ,  G06F17/279

    摘要： A method for generating dialogs for learning a dialog policy includes, for each of at least one scenario, in which annotators in a pool of annotators serve as virtual agents and users, generating a respective dialog tree in which each path through the tree corresponds to a dialog and nodes of the tree correspond to dialog acts provided by the annotators. The generation includes computing a measure of uncertainty for nodes in the dialog tree, identifying a next node to be annotated, based on the measure of uncertainty, selecting an annotator from the pool to provide an annotation for the next node, receiving an annotation from the selected annotator for the next node, and generating a new node of the dialog tree based on the received annotation. A corpus of dialogs is generated from the dialog tree.

    Distributed and privacy-preserving prediction method
    9.
    发明授权
    Distributed and privacy-preserving prediction method 有权

    公开(公告)号：US10102478B2

    公开(公告)日：2018-10-16

    申请号：US14752129

    申请日：2015-06-26

    申请人： Conduent Business Services, LLC

    发明人： Guillaume Bouchard ,  Julien Perez ,  James Brinton Henderson

    IPC分类号： G06N7/00 ,  G06N99/00 ,  G06F21/62 ,  H04W4/21 ,  H04L29/08

    摘要： Each computer of a peer-to-peer (P2P) network performs an iterative computer-based modeling task defined by a set of training data including at least some training data that are not accessible to the other computers of the P2P network, and by a set of parameters including a shared parameter. The modeling task optimizes an objective function comparing a model parameterized by the set of parameters with the training data. Each iteration includes: performing an iterative gradient step update of parameter values stored at the computer based on the objective function; receiving parameter values of the shared parameter from other computers of the P2P network; adjusting the parameter value of the shared parameter stored at the computer by averaging the received parameter values; and sending the parameter value of the shared parameter stored at the computer to other computers of the P2P network.