Generative chatting robot based on deep learning method

Abstract

The invention discloses a generative chatting robot based on a deep learning method, which comprises historical dialogue coding, knowledge selection, knowledge coding and dialogue generation, and is characterized in that the historical dialogue coding firstly splices historical dialogues, then converts the historical dialogues into vector representation, and then codes the historical dialogues byusing a bidirectional gating neural unit; according to the method, a historical dialogue representation is obtained through a bidirectional gating neural unit and an attention layer, and then each dialogue representation in the historical dialogue passes through a bidirectional gating neural unit and also passes through an attention layer, so that a final historical dialogue representation is obtained. On the basis of a traditional seq2seq model, the problems are solved by introducing external knowledge and a knowledge encoder, firstly, the knowledge encoder can store a dialogue theme during knowledge selection, and equivalently, key information in historical dialogues is stored.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a generative chat robot based on a deep learning method. Background technique [0002] With the development of Internet, information communication and artificial intelligence technology, the natural convenience of man-machine dialogue system makes it a new way to communicate with computing equipment, which is considered to be the next step after mouse and keyboard tapping, screen touch and so on. After control, a new generation of interaction paradigm in the future. Human-computer dialogue technology has been applied to various types of product services by the industry. People are familiar with personal assistant systems such as Apple’s Siri, Microsoft’s Cortana, Google’s Allo, and Baidu’s Dumi, as well as Amazon’s Echo smart home service system and Alibaba’s Xiaomi e-commerce smart customer service system. These man-machine dialogue products have brought great ...

AI Technical Summary

Problems solved by technology

[0010] 1) It is easy to produce insignificant or unclear, generic and meaningless replies, such as "I don't know" and "haha" replies without practical meaning;

[0011] 2) Chatbots generally have multiple rounds of conversations. For multi-rounds of long conversations, it is difficult for the model to preserve previous memories, which may lead to inconsistencies in the topics of the conversations before and after;

[0012] 3) For different expressions of the same topic, different results may be obtained

[0013] The emergence of problems 1 and 3 is mainly because the model does not have certain prior knowledge like humans, and the problem 2 is because the traditional seq2seq is based on deep neural network (recurrent neural network (RNN)) for sequence encoding, in When there are too many rounds or the dialogue is too long, it is impossible to capture all the information of the dialogue

Images