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

Scoring method and device and electronic equipment

A similarity analysis and text technology, applied in the field of deep learning, can solve problems such as ambiguity in the scoring process, low reliability, and long time consumption, and achieve the effect of increasing reliability and reducing scoring time

Pending Publication Date: 2020-06-02
HUAZHONG NORMAL UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, in manual scoring, the scoring standards are mostly descriptive language, and the respondents can also score points if they answer similar meanings. Because the interpretation and understanding of the scoring standards by the raters is different from the understanding of the language expressions of the respondents, the raters only Can judge the meaning of questions and standard answers subjectively, and compare the answers of respondents with this, which leads to the ambiguity of the scoring process, and it is difficult to score objectively, and it takes a long time to mark the test papers, and the reliability is not high
Existing machine scoring is generally performed by extracting shallow text features, and the extracted features are relatively single, resulting in low reliability of the scoring results

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
  • Scoring method and device and electronic equipment
  • Scoring method and device and electronic equipment
  • Scoring method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] see figure 1 A flow chart of a scoring method shown, the method includes the following steps:

[0035] Step S102, acquiring the text to be scored and the preset standard text.

[0036] Text to be graded refers to the text being graded, for example, answers to short answer questions written by students. The standard text is used to score the text to be graded, for example, the standard answer corresponding to the short answer question. It should be noted that the text to be scored corresponds to the standard text, and there may be many copies of the text to be scored for a standard text.

[0037] Step S104, extracting feature data of the text to be scored and the standard text; the above feature data includes semantic features and text features.

[0038] Treat rated text and standard text separately to extract feature data. Feature data refers to the characteristics of expressing a certain aspect of the text, and the feature data is generally determined by constructi...

Embodiment 2

[0047] The embodiment of the present invention also provides another scoring method; this method is implemented on the basis of the method of the above-mentioned embodiment; this method focuses on the specific implementation of determining the scoring of the text to be scored according to the semantic similarity, text similarity and retrieval similarity Way.

[0048] Such as figure 2 A flow chart of another scoring method shown, the method includes the following steps:

[0049] Step S202, acquiring the text to be scored and the preset standard text.

[0050] For the obtained text to be scored and the preset standard text, preprocessing is first required, including deduplication of characters, clauses, and special symbols.

[0051] Step S204, extracting feature data of the text to be scored and the standard text; the above feature data includes semantic features and text features.

[0052] Feature data includes semantic features and text features. For text features, it is ...

Embodiment 3

[0103] Corresponding to the above method embodiment, the embodiment of the present invention provides a scoring device, such as Figure 8 A structural schematic diagram of a scoring device shown, the device includes:

[0104] Text obtaining module 81, for obtaining the text to be scored and the preset standard text;

[0105] Feature data extraction module 82, for extracting the feature data of text to be scored and standard text; Feature data includes semantic feature and text feature;

[0106] The first similarity calculation module 83 is used to input the feature data of the text to be scored and the standard text into a preset similarity analysis model to obtain the similarity data of the text to be scored and the standard text; the similarity data includes semantic similarity degree and text similarity;

[0107] The second similarity calculation module 84 is used to calculate the retrieval similarity of the text to be scored and the standard text;

[0108] The score deter...

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 provides a scoring method and device and electronic equipment. The method comprises the steps of obtaining a to-be-scored text and a preset standard text; extracting feature data; inputting the feature data into a preset similarity analysis model to obtain similarity data of the to-be-scored text and the standard text; calculating retrieval similarity between the to-be-scored text and the standard text; and determining the score of the to-be-scored text according to the semantic similarity, the text similarity and the retrieval similarity. According to the method, text features and semantic features are considered, the score of the to-be-scored text is determined according to the retrieval similarity, the scoring time can be shortened, and the scoring reliability is improved.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a scoring method, device and electronic equipment. Background technique [0002] In related technologies, most of the subjective questions are graded by manual scoring or machine scoring. Among them, in manual scoring, the scoring standards are mostly descriptive language, and the respondents can also score points if they answer similar meanings. Because the interpretation and understanding of the scoring standards by the raters is different from the understanding of the language expressions of the respondents, the raters only The meaning of the questions and the standard answers can be judged subjectively and compared with the answers of the respondents, which leads to the ambiguity of the scoring process, which makes it difficult to score objectively, and it takes a long time to mark the test papers, and the reliability is not high. Existing machine scoring is ge...

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): G06F16/33G06F40/30
CPCG06F16/3344Y02D10/00
Inventor 黄涛张浩刘三女牙杨宗凯杨华利王一岩
Owner HUAZHONG NORMAL UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com