An intelligent question answering method based on task-driven multi-round conversation

Abstract

The invention discloses an intelligent question answering method based on task-driven multi-round dialogue. The specific method comprises preparing data according to different tasks; obtaining intention classification model and element extraction model through training; promoting each round of dialogue through multi-round dialogue management mechanism and decision-making mechanism to complete theintelligent question answering method; wherein the intention classification model and element extraction model are used to analyze the intention and key elements of the user's questions or answers. The multi-round dialogue management mechanism and the decision-making mechanism are used for effectively assisting a user to complete multi-round dialogues around a task by continuously making decisionson the next optimal action to be taken according to the current state. Compared with the prior art, the intelligent question answering method based on task-driven multi-round dialogue realizes automatic initiation, guidance and multi-round dialogue within a limited range, improves the success probability of human-computer interaction, and can meet the requirements of people for obtaining information quickly and accurately.

Description

technical field [0001] The invention belongs to the field of human-computer interaction, relates to natural language processing, knowledge management, question answering system, etc., and in particular relates to a task-driven multi-round dialogue method and system. Background technique [0002] An intelligent question answering system is an automaton that can answer questions in any natural language form. For a specified question, by analyzing semantic information, it can find the correct answer in a large-scale real online text, instead of returning several web pages like a keyword search engine composed list. An important function in intelligent question answering is multi-round interaction based on contextual dialogue scenarios, which is also one of its difficulties. [0003] In practical applications, the intelligent question answering system is not a simple question and answer, but may be complex process-based knowledge. Among them, Dialog Management (Dialog Manageme...

AI Technical Summary

Problems solved by technology

[0005] However, the multi-round conversational interaction system through manual definition of rules is more complicated in task customization, and it is prone to conflicts of multiple rules; the statistical dialogue system based on reinforcement learning can automatically learn this under the premise of sufficient training corpus. Tree-shaped dependency relationship, but it is difficult to obtain corpus, and the learned content is poorly understandable and difficult to control

Images