利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

20 条记录 (耗时 0.009 秒)

    METHOD FOR MULT-CHANNEL NATURAL LANGUAGE PROCESSING ON LOW CODE SYSTEMS
    2.
    发明公开
    METHOD FOR MULT-CHANNEL NATURAL LANGUAGE PROCESSING ON LOW CODE SYSTEMS 审中-公开

    公开(公告)号：EP4020306A1

    公开(公告)日：2022-06-29

    申请号：EP21000361.2

    申请日：2021-12-21

    申请人： Altice Labs, S.A.

    发明人： MATOS DE ALMEIDA E SILVA, João Pedro

    IPC分类号： G06F40/35 ,  G06Q10/00 ,  H04L51/02 ,  G06N3/00

    摘要： The diversity of communication channels available in a Virtual Assistant creation Platform result in added complexity on the development of the responses for the user utterances in multi-channel scenarios, especially in Platforms that require no (or low) technical skills to create such Virtual Assistants (also known as Low Code Systems). This is a paradox in the perspective of a low code System. This invention provides a method for defining multi-channel answers (3.1, 3.2, 3.3.) to each of the existing intents in a single window of the System User Interface, allowing the System Administrator to have an overview of the answers for an intent. The inlying advantage of this method relies on the holistic perspective of the Virtual Assistant's answers (3) per intent to the System Administrator.

    METHDO FOR NATURAL LANGUAGE PROCESSING BASED ON MULTI-MODEL SEGMENTS USING AN HYBRID NLP
    8.
    发明公开
    METHDO FOR NATURAL LANGUAGE PROCESSING BASED ON MULTI-MODEL SEGMENTS USING AN HYBRID NLP 审中-公开

    公开(公告)号：EP4020304A1

    公开(公告)日：2022-06-29

    申请号：EP21000357.0

    申请日：2021-12-16

    申请人： Altice Labs, S.A.

    发明人： DA SILVA FURÃO, Sara

    IPC分类号： G06F40/279 ,  G06F40/284 ,  G06F40/295 ,  G06F40/30 ,  G06N20/00

    摘要： The present invention provides a Natural Language Processing solution based on a method using small trained data models, which may be individually activated or signed, to select the most suitable in order to give the best answer, given the context of the dialogue. This method allows the use of multiple models previously created, without requiring the training of a huge dataset, and is based on the application of heuristics (102) over the results of a Natural Language Understanding engine, taking advantage of dataset segmentation (101) to define contexts for each dataset (100), enabling context aware Natural Language Processing and a Hybrid NLP engine which reduce or eliminate ambiguity on choosing the best answer from all models. This would not be possible with a Natural Language Understanding engine alone.