Method and device for establishing learning participation degree recognition network model
A technology for identifying networks and establishing methods, which is applied to biological neural network models, character and pattern recognition, instruments, etc., and can solve problems such as low recognition accuracy and characteristics of recognition tasks that do not consider participation
Active Publication Date: 2020-10-27
CAPITAL NORMAL UNIVERSITY
View PDF5 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] This paper is used to solve the problem that the learning participation recognition method in the prior art does not consider the characteristics of the participation recognition task, and has the defect of low recognition accuracy
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
other Embodiment approach
[0099] In other implementation manners, other CNN networks may also be selected for learning the participation recognition network model, and the recognized participation degree may also be divided into other categories, which is not limited herein.
[0100] The minimum batch includes fusion features of multiple video samples, and the fusion features of the video samples in the minimum batch can simultaneously train the learning participation recognition network model and share parameters in the learning participation recognition network model. Specifically, the minimum batch includes an anchor point, K-nearest neighbor samples of the anchor point, and other randomly sampled samples. Multiple triplets sharing anchor points can be obtained by using the triplet sampling strategy according to the minimum batch (used for training the learning participation recognition network model, see the following examples for the specific training process).
[0101] Step 130, constructing an o...
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 provides a method and device for establishing a learning participation degree recognition network model. The method comprises the steps: carrying out the preprocessing of a plurality ofobtained video samples, and obtaining a fusion feature; constructing a minimum batch for training a learning participation degree recognition network model according to the fusion features of the video samples; constructing an ordered measurement loss function according to the principle that the embedded vector distance of the video sample pair in the minimum batch and the participation degree label distance of the video sample pair in the minimum batch are consistent and ordered, the embedded vector being calculated by the learning participation degree recognition network model according to the fusion characteristics of the video samples; and optimizing parameters in the learning participation degree recognition network model according to the ordered measurement loss function. The accuracy of learning participation degree recognition can be improved.
Description
technical field [0001] This article relates to the field of artificial intelligence, in particular to a method and device for establishing a learning participation recognition network model. Background technique [0002] Participation is a kind of emotional state, which includes emotional participation, behavioral participation, cognitive participation and so on. Learning participation is the result of the interaction between teachers and students through education and teaching activities, and it is an important indicator for evaluating students' learning participation. In traditional education, teachers can directly observe students' behavior to judge students' participation, but they cannot observe every student comprehensively at the same time. With the emergence of electronic learning environment in the field of education, online education provides a new mode of knowledge dissemination and learning. Online education platforms use rich network information resources for ...
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 IPC IPC(8): G06K9/62G06N3/04G06K9/00
CPCG06V40/168G06V40/20G06V20/40G06N3/045G06F18/22G06F18/214G06F18/253
Inventor 徐敏董瑶马晓阳周丽娟张树东孙众
Owner CAPITAL NORMAL UNIVERSITY