Check patentability & draft patents in minutes with Patsnap Eureka AI!

Search question-answering system based on pre-training

A question answering system and pre-training technology, applied in the fields of natural language processing and machine learning, to improve question answering efficiency and user experience

Pending Publication Date: 2020-05-08
SHANDONG SYNTHESIS ELECTRONICS TECH
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a search question answering system based on pre-training, which can effectively solve the problems of knowledge generalization transfer, noise judgment and QA customization, and greatly improve the efficiency of question answering while improving user experience

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Search question-answering system based on pre-training
  • Search question-answering system based on pre-training
  • Search question-answering system based on pre-training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] figure 1 It is the architecture diagram of the entire search question answering system, including the noise judgment module, QA question answering module, knowledge matching module and response output module. When the system receives a user question, it first judges whether it is noise. If it is not noise, it performs QA question answer matching. If there is still no response, index matching is performed on the questions in the knowledge base, and the top 5 similar questions are selected after sorting by similarity and returned to the response module, and finally the response gives a question-and-answer response.

[0035] In this embodiment, the noise judging module judges whether the user's question is noise through the industry lexicon and the exclusion lexicon. When the user question contains industry words and does not contain exclus...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a search question-answering system based on pre-training. The search question-answering system comprises a noise judgment module, a QA question-answering module, a knowledge matching module and a response output module, the noise judgment module judges whether the user problem belongs to noise or not; the QA question and answer module comprises a rule input unit and a ruleanalysis unit. The knowledge matching module is used for indexing questions and knowledge in a question and answer library and performing similarity sorting, knowledge indexes comprise an inverted index mode and an Annoy index mode, the response output module is used for outputting responses, and the responses comprise four types of similar question lists, accurate answers, no answers and recommended popular questions. The problems of knowledge generalization migration, noise judgment and QA customization can be effectively solved, and the question and answer efficiency is greatly improved while the user experience is improved.

Description

technical field [0001] The invention relates to a search question answering system based on pre-training, which is a system for obtaining a language model and an existing question-answer database based on pre-training, and interacting with customer questions, belonging to the fields of natural language processing and machine learning. Background technique [0002] The search question answering system means that the system receives user questions, searches and sorts similar questions in the question answer knowledge base, presents a list of similar questions to users, and allows users to make choices to solve user questions as much as possible. At present, this question-and-answer mode is used in various knowledge base question-and-answer systems, intelligent customer service assistants, self-service machines and other terminal equipment. Different from the traditional dialogue system, the focus of the dialogue system is interaction, while the focus of the search question ans...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/332G06F16/951
CPCG06F16/3329G06F16/951Y02D10/00
Inventor 申冲张传锋朱锦雷薛付忠杨帆
Owner SHANDONG SYNTHESIS ELECTRONICS TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More