Task type multi-round dialogue method and system for office scene

Abstract

The invention relates to a task type multi-round dialogue method and system for an office scene. The method comprises the steps of performing scene definition on different office application tasks toobtain intentions and imperfection values of the different office application tasks; performing data acquisition on the intentions and the imperfection values of the different office application tasksto obtain acquired data; determining an intention recognition model and a imperfection extraction model by using a deep learning model training method and a customized rule processing method according to the acquired data; performing dialogue management until necessary information is collected; determining a current user intention and a current imperfection value according to the intention recognition model, the imperfection extraction model and the necessary information; and executing the service according to the current user intention and the current imperfection value. According to the invention, different office task scenes can be covered, the requirements of users are accurately met, and the office efficiency is improved.

Description

technical field [0001] The present invention relates to the field of task dialogue in office scenes, in particular to a task-type multi-round dialogue method and system in office scenes. Background technique [0002] As the basic technology of information exchange between humans and computers in the information age, human-computer interaction has attracted extensive attention from academia and industry. Human-computer dialogue is the core field of human-computer interaction technology, which aims to imitate the way of dialogue between humans to the greatest extent, so that humans can communicate with machines in a more natural way. Generally speaking, human-computer dialogue systems can be roughly divided into two types: task dialogue systems and non-task dialogue systems. Non-task systems are also called chat robots. [0003] The chatbots represented by Microsoft Xiaoice make the human-computer dialogue technology more practical and commercial, but there is still a certain...

AI Technical Summary

Problems solved by technology

However, the amount of data in the office field is small, and there are certain requirements for the accuracy of business completion. Therefore, it is not possible to obtain good results based entirely on deep learning algorithms.

In addition, there are also systems that use single-round dialogs or simple multi-round dialogs, which cannot fully meet the needs of office systems

Images