Man-machine collaborative dialogue interaction system and method

Abstract

The embodiment of the invention provides a man-machine collaborative dialogue interaction system and method and electronic equipment, and the system comprises a dialogue type pre-training layer, a dialogue expression learning layer, a dialogue structure learning layer, and a service layer. Wherein the dialogue type pre-training layer is used for outputting structural information of dialogue data according to the to-be-processed dialogue data, and the dialogue data comprises multiple rounds of dialogues; the dialogue representation learning layer is used for obtaining a semantic representation vector carrying phrase dimension semantic information, sentence dimension semantic information and theme dimension semantic information corresponding to the dialogue data according to the structure information; the dialogue structure learning layer is used for obtaining a semantic transfer relationship between rounds of dialogues according to the semantic representation vector; and the service layer is used for determining dialogue data matched with a service demand according to the semantic representation vector and the semantic transfer relationship so as to perform preset service processing through the determined dialogue data.

Description

technical field [0001] The embodiments of the present application relate to the technical field of artificial intelligence, and in particular, to a human-machine collaborative dialogue interaction system and method. Background technique [0002] Human-machine collaborative dialogue interaction is a technology in which machines learn knowledge from customer-human customer service dialogue, and assist and guide human customer service to complete on-line tasks. In recent years, the application of intelligent dialogue robots based on this technology has become more and more common in various service industries. However, due to the progress of current human-machine collaborative dialogue interaction technology and the complexity of practical application scenarios, intelligent dialogue robots can only replace some services. staff work. Taking the customer service industry as an example, in manual customer service, there are several key problems: (1) low service efficiency and lar...

AI Technical Summary

Problems solved by technology

In recent years, the application of intelligent dialogue robots based on this technology has become more and more common in various service industries, but limited by the progress of the current man-machine collaborative dialogue interaction technology and the complexity of actual application scenarios, intelligent dialogue robots can only replace some services staff work

Taking the customer service industry as an example, there are several key problems in manual customer service: (1) Low service efficiency and large differences in service levels: Due to the professionalism and complexity of customer service work, manual customer service cannot master all service knowledge, so in service During the process, it is often necessary to query the knowledge base and historical cases for specific service issues, which affects service efficiency and reduces customer service satisfaction; (2) Also due to the professionalism and complexity of customer service work, new and old customer service personnel The service level varies greatly, and new customer service personnel often cannot fully grasp the standard service process and speaking skills, which further affects the service quality; (3) The on-the-job training cycle is long: due to the need to learn complex service knowledge, manual customer service requires long-term training before taking up the job , the cost of manual training is high

[0003] Similarly, other service industries also have situations where intelligent dialogue robots cannot meet service needs well

Images