A multi-strategy fusion knowledge question and answer method and system

A question answering system, multi-strategy technology, applied in the field of human-computer interaction

Active Publication Date: 2019-06-21
上海乐言科技股份有限公司
View PDF5 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the above-mentioned problems existing in the prior art. It provides a multi-strategy fusion knowledge question answering method and system, which adopts the fusion of multiple strategies based on semantic analysis to make up for the fact that existing products usually use a single strategy. The defects caused by

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
  • A multi-strategy fusion knowledge question and answer method and system
  • A multi-strategy fusion knowledge question and answer method and system
  • A multi-strategy fusion knowledge question and answer method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] figure 1 It is an overall flow chart of the multi-strategy fusion knowledge question answering method provided by the present invention, and the overall flow of the method includes an offline part and an online part.

[0061] The offline part includes the reference or construction of the knowledge map, which is used for the semantic analysis process based on the graph search and the knowledge call involved in the online part of the query process, where the knowledge map refers to the general knowledge map and the domain knowledge map; the query statement and the standard question method The establishment of the index is used for the semantic analysis process based on the paraphrase; the training and packaging of the offline model is used for the model used in the online part of the method, and the feature extraction and training are performed on it, and the package is released; the establishment of the rules is used for all Manual intervention is performed in the online...

Embodiment 2

[0088] Figure 5 It is an example block diagram of a multi-strategy fusion knowledge question answering system provided by the present invention, including an offline system and an online system.

[0089] The offline system shown includes: a knowledge graph module, used for the semantic analysis process based on graph search and knowledge invocation in the query process; a query statement and standard question method index module, used for the semantic analysis process based on paraphrase; offline model training and a packaging module, used for feature extraction and training of the model used in the online system module, and packaged and released; a rule module, used for manual intervention on the online system.

[0090] The shown online system includes: information receiving and spelling error correction module 10, for receiving user input sentences and judging whether there is a spelling error; word segmentation and part-of-speech tagging module 20, for combining with condi...

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 multi-strategy fusion knowledge question and answer method and system, and the method comprises an offline part and an online part, the offline part is mainly used for data preparation and model training, and the online part is mainly used for system service, and the method comprises the steps: receiving a statement input by a user, and correcting a spelling error; Performing word segmentation and part-of-speech tagging on the statement input by the user; Extracting entity information in the user statement, and linking the entity to the knowledge graph node; Obtainingan executable query statement through a multi-strategy fusion semantic analysis step according to the result of the entity recognition and connection process; Executing a query on a knowledge graph by the executable query statement to obtain an answer, and then generating a corresponding natural language reply user according to the answer through a reply generation mode combined by multiple methods, so that the question and answer system is suitable for question query of general and domain knowledge graphs, the system robustness is improved, and meanwhile, the good interpretability and controllability are achieved.

Description

technical field [0001] The invention relates to a human-computer interaction technology, in particular to a knowledge question answering method and system using multi-strategy fusion based on semantic analysis technology. Background technique [0002] Question Answering System (QA System) is the next generation paradigm of information retrieval system. It can understand human natural language and answer users' questions through accurate and concise natural language. It is an important application direction of artificial intelligence. There are currently many types of question answering systems, mainly including) and based on reading comprehension (Machine Reading Comprehension QA, MRCQA). Among them, the question answering system based on knowledge graph (Knowledge Graph, KG) satisfies the demand of question answering system for high-quality knowledge sources, and can effectively use the knowledge summarized by humans to achieve deeper question understanding and high-accurac...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F16/36G06F17/27
Inventor 周扬王昊奋
Owner 上海乐言科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap