English composition problem-moving judgment method based on image recognition
An image recognition and composition technology, applied in the field of text processing, can solve the problem that the recognized composition text cannot be judged, etc.
Inactive Publication Date: 2020-04-28
安徽七天网络科技有限公司
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] Solve the problem that the recognized composition text cannot judge whether it is off-topic, and provide a method for detecting off-topic based on the composition text identified by multi-dimensional analysis
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0034] In order to make the purpose / technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and cases. The specific implementation cases described here are only for explaining the present invention, but not for limiting the present invention.
[0035] Such as figure 1 As shown, the present invention is a technical solution, a method for judging off-topic English composition by image recognition, and the whole method is characterized by constructing four modules of text pair calculation Bilstm+siamese similarity, tfidf+cosine similarity, high-frequency word hit, and proper noun hit In the extraction stage, the feature value is extended and calculated for xgboost model prediction to realize the function of off-topic prediction.
[0036] Bilstm+siamese similar module: first construct the text pair data, divide the students' composition identified in an exam i...
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
Login to View More Abstract
The invention discloses an English composition topic determination method based on image recognition, and relates to the field of text classification. Aiming at the problem that whether the English composition obtained by scanning the test paper runs out of questions or not, a solution for calculating the similarity among all examinee compositions from multiple dimensions and judging whether the composition runs out of questions or not by utilizing similarity deviation is provided. According to the judgment method, a glove word vector is required to be matched with a Bilstm + siamese network architecture, the network architecture is combined with a tfidf and cosine similar calculation method, and a specific word set hit ratio is used as a supplementary feature, so that text information canbe comprehensively mined. The method mainly comprises the following modules: a deep feature module, a shallow feature module and an integrated prediction module. Besides text features can be mined inmultiple dimensions, an integration module can balance the influence of each feature on the score by utilizing the advantages of a large amount of data, and the accuracy of problem movement judgmentis further optimized.
Description
technical field [0001] The invention belongs to the technical field of text processing, in particular to a method for multi-dimensionally analyzing composition texts to detect whether they go off topic. Background technique [0002] In the past ten years, Internet technology has developed rapidly, and the trend of networking has impacted all walks of life. The field of education is constantly innovating with the times. In addition to online teaching and electronic teaching aids, networked examination marking is also a trend. There are 12 grades in elementary school, junior high school, and senior high school. Dozens of exams are conducted in each grade every year. Composition grading for each exam is a considerable human burden. Systems that digitize essays and grade them have also begun to enter the market. However, the accuracy rate of scoring is not satisfactory, and a considerable part of the error is caused by failure to consider off-topic factors. Therefore, it is ...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06F40/284G06F40/30
CPCG06V30/413
Inventor 侯冲董平陈家海叶家鸣吴波
Owner 安徽七天网络科技有限公司