Multi-task learning intelligent paper marking method and device suitable for judicial examination subjective questions
A technology of multi-task learning and subjective questions, applied in neural learning methods, biological neural network models, semantic analysis, etc., can solve problems such as the ineffective judgment of subjective test scenarios based on keywords, and improve the accuracy of judgment Effect
Pending Publication Date: 2021-10-15
上海艾爵斯信息科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The main purpose of the present invention is to provide a multi-task learning intelligent marking method and device suitable for the subjective questions of the judicial examination, so as to solve the problem that the existing keyword-based pattern matching strategy cannot effectively judge the scene of the subjective questions of the judicial examination
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
[0070] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.
[0071] It should be noted that the terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It should be understood that the data so used may be interchanged under appropr...
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 a multi-task learning intelligent paper marking method and device suitable for judicial examination subjective questions. The method comprises the steps of collecting student answering texts and standard score points corresponding to judicial examination subjective questions; using the spliced text as an input text of a pre-training language model BERT; carrying out hidden layer semantic interaction and coding to obtain a text hidden layer semantic representation; determining a score point extraction task, and predicting a starting position and an ending position of each score point in the text answered by the student word by word; determining a score point judgment task, and judging each score point in the student answer text and score information of each score point; and adopting a multi-task joint learning framework and a BERT semantic identification layer to optimize a joint loss function of the score point extraction task and the score point judgment task, and calculating a total score according to score information of each score point after joint optimization so as to realize intelligent paper marking. According to the invention, the subjective question scene of the law test is effectively scored, and the purpose of improving the learning efficiency of students of the law test is achieved.
Description
technical field [0001] The invention relates to the field of computer-aided examination papers, in particular to a method and device for multi-task learning intelligent examination papers suitable for subjective questions of judicial examinations. Background technique [0002] In recent years, artificial intelligence technology has developed rapidly and is gradually integrating into many fields such as finance, justice, and education. As the national unified legal professional qualification examination, the judicial examination (referred to as the legal examination) has continued to increase in popularity in the recent stage, and the traditional manual marking method has become difficult. To meet the current high-efficiency needs, in order to reduce the pressure on teachers to review high-load test papers, computer artificial intelligence technology is often used for intelligent marking. [0003] Most of the existing intelligent marking systems focus on text recognition base...
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): G06F40/30G06F40/211G06F40/279G06F40/44G06K9/62G06N3/04G06N3/08
CPCG06F40/30G06F40/211G06F40/279G06F40/44G06N3/084G06N3/045G06F18/24
Inventor 王加伟杜向阳
Owner 上海艾爵斯信息科技有限公司