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

Retrieval method of scientific and technological resources based on machine reading comprehension

A reading comprehension and machine technology, applied in the field of scientific and technological resource retrieval based on machine reading comprehension, can solve the problems of incomprehensible keywords, professionalism, intellectual complexity, difficulty in meeting the needs of scientific and technological resource services, etc., and achieve improved retrieval Efficiency and effectiveness, the effect of improving retrieval efficiency and increasing the ability of model understanding

Active Publication Date: 2022-04-05
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because scientific and technological resources are different from ordinary life and production resources, they have significant professionalism, knowledge and complexity, and keyword search methods cannot understand their characteristics, and as a result, it is difficult to meet the needs of scientific and technological resources services

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
  • Retrieval method of scientific and technological resources based on machine reading comprehension
  • Retrieval method of scientific and technological resources based on machine reading comprehension
  • Retrieval method of scientific and technological resources based on machine reading comprehension

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0102] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0103] like figure 1 As shown, at present, the retrieval method of scientific and technological text resources based on statistics is mainly used to retrieve relevant scientific and technological texts, and relevant texts are obtained by calculating the word frequency and inverse text frequency in the text. Ability and other issues, the specific performance is as follows:

[0104] (1) Low accuracy of text matching: in existing methods, text matching only calculates the word frequen...

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 scientific and technological resource retrieval method based on machine reading comprehension, which sequentially performs noise removal, Chinese text word segmentation, stop word removal and word vector processing of scientific and technological text on text; the processed text adopts TF-IDF of n-gram The text matching method, by calculating the word frequency TF, inverse text frequency IDF and word order information of words in the text, finally calculates the similarity score between the text and keywords, and then determines the relevant text; the matched text is read and understood by machine The method integrates the machine reading comprehension model into the retrieval model, and returns the retrieval results by understanding the content in the text. This retrieval method not only fully considers the frequency TF and inverse text frequency IDF of the words in the text, but also fully considers the order information of the words, and then fully understands the semantics of the text, achieves more accurate text matching, and increases the ability of the model to understand. The content in the text returns more accurate retrieval results and improves the user's retrieval efficiency.

Description

technical field [0001] The invention belongs to the technical field of data retrieval, and in particular relates to a scientific and technological resource retrieval method based on machine reading comprehension. Background technique [0002] The science and technology service industry is an important part of the modern service industry. It is a key link to realize technological innovation leading industrial upgrading and promoting the economy to a high-end level. It is of great significance for the in-depth implementation of the innovation-driven development strategy and the promotion of economic quality and efficiency upgrading. . In developed countries, the knowledge-intensive service industry is a typical representative of the science and technology service industry. Among them, the science and technology resources represented by research and development, intellectual property rights, and science and technology consulting are the main objects and sources of science and t...

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 Patents(China)
IPC IPC(8): G06F16/33G06F40/284G06F40/289G06F40/216G06K9/62G06N3/04G06N3/08
CPCG06F16/3344G06F40/284G06F40/289G06F40/216G06N3/08G06N3/044G06F18/22
Inventor 廖伟智叶光磊
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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