Intelligent question-answer interaction method and system based on machine reading understanding

A technology for reading comprehension and intelligent question answering, which is applied to instruments, digital data processing, and natural language data processing. It can solve the problems of high training data costs and low recognition accuracy, optimize model training, reduce data acquisition costs, The effect of shortening the business implementation time

CN112035652APending Publication Date: 2020-12-04杭州云嘉云计算有限公司
7 Cites 7 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2020-12-04
Patent Text Reader

Abstract

The invention discloses an intelligent question and answer interaction method and system based on machine reading understanding, and the system comprises: a first text word segmentation module which segments an original text into a sequence taking words and characters as units; a statistical mining module, a data translation module, a data layering module, a vector representation module, a first model training module and a statistical rule mining module. The legal provision pushing system comprises a second text word segmentation module, a new word discovery module and a second model trainingmodule. The interaction method comprises the following steps: respectively inputting an original text and a questioning text into a reading understanding system and a legal provision pushing system, wherein the original text and the questioning text are default Chinese texts; preprocessing the input original text and questioning text; inputting the preprocessed text into a model training module for training; and outputting a prediction result. By establishing an intelligent question-answer interaction system, the public service capability in the judicial field is improved, and the manual customer service cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of computer natural language processing and automatic question answering, in particular to an intelligent question answering interaction method and system based on machine reading comprehension. Background technique

[0002] The task of reading comprehension refers to enabling machines to read and understand the information in documents. It is an important task of natural language processing. With the rise of deep learning technology, it has become a hot spot in academic and industrial circles in recent years. , Automatic question answering has been widely used.

[0003] To train a machine to read comprehension, it is important to build a machine learning model that performs algorithm training through given text data and answers, so as to find answers to questions in text fragments. Different from general single-sentence processing tasks, machine reading comprehension tasks pay more attention to the...

Examples

Embodiment

[0063] Embodiment: a kind of intelligent question and answer interactive method based on machine reading comprehension, comprises the following steps:

[0064] Input the original text and the question text into the reading comprehension system and the law push system respectively; the original text and the question text are both Chinese text by default, and if they contain foreign languages, they need to be converted into Chinese through a translator; for example, the original text content

[0065] Preprocessing the input original text and question text; preprocessing the input original text and question text includes the following steps:

[0066] Using the first text segmentation module to segment the original text into a sequence of words and characters;

[0067] Using the second text word segmentation module to segment the question text into sequences with words and characters as units;

[0068] Through the word segmentation module, each text is divided into a sequence of ...