Unlock instant, AI-driven research and patent intelligence for your innovation.

Semantic matching model for knowledge point positioning

A technology of semantic matching and knowledge point, applied in the field of semantic matching model of knowledge point location

Pending Publication Date: 2021-06-08
SOUTHEAST UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, a deep learning model based on BERT coding is added to solve the problem of unregistered words, and perform a deeper semantic understanding and support fuzzy semantic understanding

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
  • Semantic matching model for knowledge point positioning
  • Semantic matching model for knowledge point positioning
  • Semantic matching model for knowledge point positioning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The implementation process of the present invention will be described in detail below in conjunction with examples and accompanying drawings.

[0042] The present invention is a semantic matching model method for knowledge point location, including the following 6 steps:

[0043] 1) For a given teaching material in the field of electricity, in order to facilitate the positioning of knowledge points, it is divided into sections, and the chapter information and page number of each section are recorded.

[0044] (1) In this model, if one sentence is selected as the search granularity, it will lead to too many corpus, large computational complexity and long reaction time. However, selecting pages as the search granularity will result in inaccurate positioning and an overly broad scope. In order to better locate the position of knowledge points, it is more appropriate to choose paragraphs as the granularity of positioning, that is, each paragraph of text is regarded as a co...

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 semantic matching model for knowledge point positioning. The semantic matching model is mainly used for solving the problem of question knowledge point positioning in the field of electricity. The method comprises the following steps: firstly, preprocessing an original textbook to form a corpus; then, using statistics-based semantic matching models TF-IDF, LSI and LDA for coding, afterwards, using a deep learning semantic matching model for enhancing deep semantic understanding, and carrying out BERT coding; then, for the four coding modes, calculating cosine similarity to serve as measurement of semantic similarity; and finally, selecting a specified number of textbook fragments by the user as a final knowledge point positioning result according to the number of times that the textbook fragments appear in the front and the cosine similarity based on the voting semantic matching integration model.

Description

technical field [0001] The invention belongs to the field of natural language processing, and in particular relates to a semantic matching model for knowledge point positioning. Background technique [0002] Semantic matching is an important basic problem in natural language processing, which can be applied to a large number of NLP tasks, such as information retrieval, question answering system, paraphrase question, dialogue system, machine translation, etc. These NLP tasks can be abstracted to a large extent as Semantic matching problem. The quality of the semantic matching model will greatly affect the effect of the final application. [0003] Traditional semantic matching technologies include BoW, VSM, TF-IDF, BM25, Jaccord, SimHash and other algorithms. For example, the BM25 algorithm calculates the matching score between the two through the coverage of the query field. The higher the score, the matching degree of the web page and the query better. It mainly solves th...

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): G06F40/30G06F40/289G06F40/216
CPCG06F40/30G06F40/289G06F40/216
Inventor 吴亦珂吴天星李林高超禹漆桂林
Owner SOUTHEAST UNIV