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

Choice question generation model training method, choice question generation method, equipment and medium

A technology for generating models and training methods, which is applied in character and pattern recognition, instruments, and electronic digital data processing to achieve the effect of ensuring smoothness, feasibility, and good semantic understanding ability.

Active Publication Date: 2021-03-26
PING AN BANK CO LTD
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a multiple-choice question generation model training method, a multiple-choice question generation method, equipment, and media to solve the problems existing in the multiple-choice questions generated by using the method of hollowing out and filling in words

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
  • Choice question generation model training method, choice question generation method, equipment and medium
  • Choice question generation model training method, choice question generation method, equipment and medium
  • Choice question generation model training method, choice question generation method, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0048] In the multiple-choice question generation model training method provided by the embodiment of the present invention, the multiple-choice question generation model training method can be applied as figure 1 shown in the application environment. Specifically, the multiple-choice question generation model training method is applied in a model training system, and the model training system includes such as figure 1 The client and the server are sh...

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 choice question generation model training method, a choice question generation method, equipment and a medium. The method comprises the steps of obtaining a training document, standard topic information and standard interference options corresponding to a target application field; carrying out key paragraph extraction on the training document according to the standard topic information, and acquiring key paragraphs corresponding to the standard topic information; obtaining a FinBert-UniLM model, and configuring model parameters corresponding to the FinBert-UniLM model; inputting the key paragraph and the standard topic information into a FinBert-UniLM model for model training, and obtaining a topic generation model corresponding to the target application field; and inputting the key paragraph, the standard topic information and the standard interference option into a FinBert-UniLM model for model training, and obtaining an interference item generation model corresponding to the topic generation model. The method can ensure that the choice questions generated by the choice question generation model have language organization mode diversity and disturb the smoothness of options and question stems, and the lengths of the options meet the business requirements and the comprehensiveness of knowledge point coverage.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a multiple-choice question generation model training method, a multiple-choice question generation method, equipment and media. Background technique [0002] The multiple-choice question generation model is a model used to automatically generate multiple-choice questions. The multiple-choice question generation model can be used to process specific fragments in training documents or other documents in various training processes to generate multiple-choice questions corresponding to the specific fragments. Use this multiple choice question to realize the assessment of the knowledge of a specific segment. Generally speaking, multiple-choice questions include three parts: the question stem, the correct option and the interference option. Types of. [0003] Existing multiple-choice question generation models generally select the sentences that need to be asked from ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/211G06F40/30G06K9/62
CPCG06F40/211G06F40/30G06F18/214
Inventor 陈杭赖众程张舒婷史文鑫倪佳林志超何凤连李筱艺李会璟赖幸斌林嘉喜
Owner PING AN BANK CO LTD
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