Intelligent customer service construction method driven by business document

Abstract

A business document-driven intelligent customer service construction method is characterized by comprising the following steps: step 1, collecting a current input q of a user, a business document D and a dialogue history, and encoding and pooling the current input q, the business document D and the dialogue history to obtain a sentence level representation of the current input q, the business document D and the dialogue history; 2, taking each item in the sentence level representation Ds of the business document as a discourse unit, and sequentially establishing a correlation between the sentence level representation q currently input by the user and each discourse unit and a correlation between each discourse unit and the sentence level representation Hs of the dialogue history, therefore, document structure analysis and dialogue state tracking are realized in sequence; and step 3, classifying the business document and the dialogue history based on the association relationship obtained in the step 2, and reasoning the current answer to generate an optimal strategy. Corpus association and accurate reasoning are realized by referring to a rhetorical structure theory, the problem of an information slot is overcome, system dialogue is represented by an interaction state of a discourse unit, and the system dialogue efficiency is improved. And the conversation is smoothly driven.

Description

technical field [0001] The present invention relates to the field of natural language processing, and more specifically, relates to a business document-driven intelligent customer service construction method. Background technique [0002] The intelligent customer service system is an industry-oriented application developed on the basis of large-scale knowledge processing. It is an intelligent platform suitable for large-scale knowledge processing, natural language understanding, knowledge management, automatic question answering system, reasoning and other technical industries. At present, the intelligent customer service system can not only provide enterprises with fine-grained knowledge management technology, but also establish fast and effective technical means based on natural language for communication between enterprises and massive users, and at the same time provide enterprises with the fine-grained management required Statistical Analysis Information. Its huge comm...

AI Technical Summary

Problems solved by technology

[0004] This intelligent customer service technology based on slot filling has two problems: first, the construction of task ontology and data labeling work require high time and labor costs, and domain migration is difficult, resulting in long implementation time and high cost of intelligent customer service system. High; Secondly, the set of information slots is a flat structure, and different information slots are independent of each other, making it difficult to describe more complex customer service tasks in practical applications

However, all of the above methods lack sufficient parsing and representation of the document structure, making it difficult to accurately track the global dialogue state

Images