Text semantic matching method and device for intelligent questions and answers of fire safety knowledge

A technology of security knowledge and intelligent question answering, which is applied in neural learning methods, text database query, unstructured text data retrieval, etc., can solve problems such as emphasizing and less research on semantic matching, so as to improve comprehensiveness and accuracy, improve effect, the effect of improving accuracy

Pending Publication Date: 2022-05-27
QILU UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing methods usually achieve good performance by capturing semantic information at the word granularity, but these methods often focus on English, and there are few studies on Chinese semantic matching. Currently, Chinese-based semantic matching methods only consider word and word granularity information , however, pinyin and radical granularity information are also very important features

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
  • Text semantic matching method and device for intelligent questions and answers of fire safety knowledge
  • Text semantic matching method and device for intelligent questions and answers of fire safety knowledge
  • Text semantic matching method and device for intelligent questions and answers of fire safety knowledge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0128] The present invention provides a text semantic matching method for intelligent question answering of fire safety knowledge. The main frame structure of the present invention includes a text embedding module, an input encoding module, a multi-granularity interaction module, a feature fusion module and a prediction module. Among them, the text embedding module performs the embedding operation on the input text to obtain word embedding representation, pinyin embedding representation, radical embedding representation, and word embedding representation, and transmits the result to the input encoding module. The input encoding module encodes the word embedding representation, pinyin embedding representation, radical embedding representation, and word embedding representation through BiLSTM to obtain the word and word granularity context information, and obtains the pinyin and radical granularity semantics through the full connection layer for the pinyin and radical embedding ta...

Embodiment 2

[0130] The overall step flow of the present invention is as attached figure 1 shown, the specific steps are as follows:

[0131] S1. Build a text semantic matching knowledge base

[0132] The process of building a text semantic matching knowledge base is as follows figure 2 shown, the specific steps are as follows:

[0133] S101. Collect data: download a text semantic matching data set or an artificially constructed data set that has been published on the Internet, and use it as the original data for constructing a text semantic matching knowledge base.

[0134] For example: There are many public Q&A databases for fire safety knowledge on the Internet. The present invention collects these data and downloads them, thereby obtaining the original data for constructing the text semantic matching knowledge base, and the text examples therein are represented as follows:

[0135] txt P Why are cigarette butts easy to cause fire? txt Q How do cigarette butts st...

Embodiment 3

[0272] as attached Image 6 As shown, based on the text semantic matching device for intelligent question answering of fire safety knowledge based on Embodiment 2, the device includes:

[0273] Build a text semantic matching knowledge base, build a text semantic matching model training data set, build a text semantic matching model, train a text semantic matching model, and implement steps S1 and S2 in the text semantic matching method based on pinyin and radical interaction for intelligent customer service respectively , S3, S4 functions, the specific functions of each unit are as follows:

[0274] A text semantic matching knowledge base is constructed to obtain a large amount of text data, and then the text data is preprocessed to obtain a text semantic matching knowledge base that meets the training requirements.

[0275] Construct a training data set of text semantic matching model. For the data in the text semantic matching knowledge base, if the semantics are consistent...

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 text semantic matching method and device for intelligent questions and answers of fire safety knowledge, and belongs to the technical field of natural language processing. The technical problem to be solved by the invention is how to capture more semantic context features, relation of coding information among different dimensions and interaction information among texts so as to realize intelligent semantic matching of the texts. According to the technical scheme, a text semantic matching model composed of a text embedding module, an input coding module, a multi-granularity interaction module, a feature fusion module and a prediction module is constructed and trained, so that multi-level text feature extraction of text information is realized; meanwhile, a final matching representation vector of text semantics is obtained through maximum pooling, average pooling and multiple method matching mechanisms, and then the matching degree of the text is judged. The device comprises a text matching knowledge base construction unit, a training data set generation unit, a text semantic matching model construction unit and a text semantic matching model training unit.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence and natural language processing, and in particular relates to a text semantic matching method and device for intelligent question and answer of fire safety knowledge. Background technique [0002] Effective fire safety education is of great significance for reducing fire safety hazards and protecting people's property safety. In the face of a wide range of safety education needs, how to use human-computer interaction technology to realize intelligent automatic question and answer of fire safety knowledge to meet the needs of the masses for self-learning is an urgent problem to be solved. The intelligent question answering system can automatically find a standard question with similar semantics in the question and answer knowledge base for the question raised by the user, and push the answer of the standard question to the user, which can greatly reduce the burden of manual answerin...

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): G06F16/33G06F16/332G06N3/04G06N3/08
CPCG06F16/3344G06F16/3329G06N3/08G06N3/044Y02D10/00
Inventor 鹿文鹏张鑫赵鹏宇郑超群马凤英乔新晓张维玉
Owner QILU UNIV OF TECH
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