Multi-round dialogue processing method, device and equipment

A dialogue processing and multiple group technology, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve problems such as meaningless replies, multiple repetitions, etc.
CN110032633AActive Publication Date: 2019-07-19TENCENT TECH (SHENZHEN) CO LTD
12 Cites 16 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
TENCENT TECH (SHENZHEN) CO LTD
Publication Date
2019-07-19

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a multi-round dialogue processing method, device and equipment, belongs to the technical field of natural language processing, and is used for improving the accuracy of a multi-round dialogue. In the method, a structured knowledge map is combined with a non-structured text at an encoding stage. Namely, in the encoding stage, the knowledge multivariate group, the conversation history and the background knowledge are combined, the obtained encoding result can cover the relation among the conversation history, the conversation background and entities in the conversation, and therefore the obtained encoding result information is richer, and the encoding result can be more accurate. In this way, a better response can be obtained in the decoding stage according to a moreaccurate coding result.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of natural language processing, in particular to a multi-lun dialogue processing method, device and equipment. Background technique

[0002] The model of Seq2Seq (sequence-to-sequence, multi-round dialogue generation system) is a kind of end-to-end (end-to-end) algorithm framework. It is often used in scenarios such as machine translation and automatic response. Seq2Seq is generally implemented through the Encoder-Decoder (encoding-decoding) framework. The Encoder and Decoder parts can process any text, voice, image, and video data. The Encoder-Decoder model can use CNN (Convolutional Neural Networks, convolutional neural network), RNN (Recurrent Neural Network, cyclic neural network), LSTM ( Long Short-Term Memory, long short-term memory network), GRU (gated recurrent neural network, gated recurrent neural network), BLSTM (bidirectional long short-term memory, bidirectional long short-term memory ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More