Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A structured and test paper technology, applied in the direction of structured data retrieval, database model, database management system, etc., to achieve the effect of reducing complicated work and improving work efficiency
Active Publication Date: 2022-05-24
江西风向标智能科技有限公司
View PDF0 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
Based on natural language processing technology, combined with deep learning, under the condition of a large number of labeled samples, text segmentation and information extraction are realized, which is the technical trend of automatic processing of existing test papers. However, due to the particularity of English test papers, there is no particularly accurate treatment
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0017] In order to facilitate the understanding of the present invention, the related terms that may be involved are explained as follows:
[0018] Multi-stage text classification: A large task can be decomposed into multiple small tasks, and there is continuity between the tasks before and after. Each task is a text classification task, called multi-stage text classification.
[0019] Structured text: Text is unstructured data. Extract the information contained in the text in the form of key-value pairs for easy reading and reference by other tasks.
[0020] Sequence labeling: For a piece of text, label each text unit with a class label. The process of predicting the category label of each text unit for new text in the future using sequence models such as conditional random fields, hidden Markov, and RNN.
[0021] Conditional random field: It is a conditional probability distribution model P(Y|X), which represents a Markov random field of another set of output random varia...
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
A method for structuring an English test paper, comprising the steps of: S1. converting the word format English test paper into an html format, and then converting the html format into a txt format; S2, dividing the description of the title of the English test paper from the content of the title, and the description of the title refers to the test paper Explanatory sentences for structure, question type, and score value do not involve the content of the question itself; S3, English question type identification, uses each question description and question content to identify the question type; S4, each question type is divided twice, and the content of the question is extracted The question number, question stem, options, option content information, also includes the classification of question stems and options, essay and non-essay classification, ABCD in options and option content identification and extraction; S5, structuring the answers, including dividing the answers into These are: listening materials, essay answers, essay correction answers, word answers, ABCD option answers; S6, match and integrate the structured information of the topic content with the answers.
Description
technical field [0001] The invention belongs to the technical field of intelligent education, and particularly relates to an English test paper structuring method and device. Background technique [0002] Natural language processing technology is a subfield of artificial intelligence. With the development of deep learning technology, the performance of natural language processing combined with deep learning has made breakthroughs in various classic projects. Text segmentation and information extraction technology has been a hot area of research by scholars for a long time, and it is also a business scenario encountered in all walks of life. Based on natural language processing technology, combined with deep learning, under the condition of a large number of labeled samples, the realization of text segmentation and information extraction is the technical trend of automatic processing of existing test papers. However, for English test papers, due to the particularity of Eng...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more