Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Knowledge base question-answering system and device based on question generation

A question answering system and knowledge base technology, applied in the computer field, can solve problems such as heavy workload, long time-consuming, high labeling cost, etc., to achieve the effect of reducing workload, reducing development time, and reducing development cost

Pending Publication Date: 2020-12-01
HARBIN INST OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention is to solve the problems of high labeling cost, heavy workload, and long time-consuming due to the need for personnel with professional knowledge to label special data sets based on the knowledge graph question answering method

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
  • Knowledge base question-answering system and device based on question generation
  • Knowledge base question-answering system and device based on question generation

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0018] Specific implementation mode one: refer to figure 1 To describe this embodiment in detail,

[0019] An important feature of the present invention is that the question-answering system can be constructed without question-and-answer label data. The invention expands triples into question sentences with complete semantic information by writing templates, and establishes full-text indexes on the extended questions. When a user queries, the system first performs a full-text search to obtain a candidate set, then sorts the candidate set through the pre-trained semantic matching module, and selects the triplet with the highest score as the answer to return to the user. The flow of the whole method is described in detail below.

[0020] The knowledge base question answering system based on question generation described in this embodiment includes:

[0021] s1. Template writing and triple extension:

[0022] A template is a text file in json format written by the developer f...

specific Embodiment approach 2

[0032] The knowledge base question answering device based on question generation described in this embodiment is used for storing and / or running the question answering system based on question generation.

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 knowledge base question-answering system and device based on question generation, and relates to an automatic question-answering system. The invention aims to solve the problems of high labeling cost, large workload and long consumed time due to the fact that a knowledge graph-based question-answering method needs professional knowledge personnel to label a special data set. A template database of the system is used for storing templates; the triple extension module reads the triple and analyzes the triple, and all templates under the relationship are selected from the template library; symbols corresponding to the triples in the template are replaced with entities to generate sentences; the full-text retrieval module is used for segmenting a query text queried bya user, converting query statements segmented into words into Luene internal representation Query objects, and retrieving a group of sentences related to user query as a candidate set; and the semantic matching module is used for sorting the candidate sets by adopting a semantic matching network based on a pre-training model Bert, taking a triple corresponding to the highest score as an answer and returning the answer to the user. The invention is mainly used for realizing automatic questioning and answering.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to an automatic question answering system. Background technique [0002] With the development of science and technology, automatic answering robots, systems or voice assistants have been developed rapidly. The knowledge base question answering system based on knowledge graphs has attracted more and more attention from academia and industry because it can directly answer factual questions and meet people's needs for rapid knowledge acquisition. [0003] The knowledge graph is data organized in a triple format, such as <Yao Ming><Nationality><China>, where Yao Ming and China are entity 1 and entity 2, and nationality is the relationship between the two entities. The input of this type of question answering system is a text query q, and then one or a group of triples most relevant to the query is found in the knowledge base, and the corresponding entiti...

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): G06F16/36G06F16/332G06F16/31G06F40/186G06F40/289G06F40/30
CPCG06F16/367G06F16/3329G06F16/319G06F40/186G06F40/289G06F40/30
Inventor 车万翔乔振浩赵妍妍刘挺
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products