Method for realizing task-type man-machine conversation task based on multiple documents

Abstract

The invention discloses a multi-document-based task type man-machine conversation task implementation method, which comprises the following steps of: when each round of conversation is finished, utilizing a preset man-machine conversation task model to process a question and answer text of the round of conversation, wherein the processing comprises the following steps of: generating a question andanswer vector based on the question and answer text; calculating the similarity between the question and answer vector and the attribute related vector of each candidate document; generating probability distribution of each candidate document in the round of conversation and attribute distribution of the round of conversation based on the question-answer vector and the similarity; updating a global candidate document probability distribution vector according to the probability distribution; updating a global attribute distribution vector according to the attribute distribution; if a man-machine conversation ending condition is met, determining a task execution result based on the global candidate document probability distribution vector and outputting the task execution result; otherwise,based on the global candidate document probability distribution vector and the global attribute distribution vector, determining the next question information by using the natural language conversation template. The task execution efficiency and success rate can be improved, and the method is easy to implement.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method for realizing a multi-document-based task-type man-machine dialogue task. Background technique [0002] The human-computer dialogue system aims to build a computer system that uses natural language processing to interact with humans. According to different usage scenarios, it can be divided into task-based human-computer dialogue and non-task-oriented human-computer dialogue. Among them, task-based human-computer dialogue is aimed at a specific field, through multiple rounds of dialogue, assisting users to complete one or more tasks, such as common intelligent customer service systems. [0003] In many human-computer dialogue scenarios, such as product recommendation, file retrieval, personal assistant, etc., it is necessary to estimate the target object that the user is interested in, so as to more accurately assist the user to complete the task of the corresponding s...

AI Technical Summary

Problems solved by technology

When building a structured knowledge base, it is necessary to extract structured knowledge from a large amount of unstructured knowledge, which is complex and requires a lot of manpower and material resources.

Moreover, in the human-computer dialogue scenario based on structured knowledge, the user will be limited to choose the answer dialogue in the structured option set (such as yes, no and don't know)

Compared with the unstructured answer method of natural language, the information carried by this structured answer method is limited, so that, on the one hand, it will affect the accuracy of estimating the target object of interest to the user, and on the other hand, it will also lead to the need for more Multiple rounds of dialogue can estimate the user's interested target, thereby reducing the user's man-machine dialogue experience

Therefore, using the existing task-based human-computer dialogue scheme to estimate the target object of interest to the user will have problems such as high deployment cost, poor accuracy, and many dialogue rounds, so it is not suitable for human-computer interaction to estimate the target object of interest to the user. dialogue task

Images