南方科技大学知识苑(SUSTech KC): 一种脊柱侧弯检测模型的生成方法和计算机设备

Title	一种脊柱侧弯检测模型的生成方法和计算机设备
Alternative Title	Scoliosis detection model generation method and computer equipment
Author	安丰伟; 刘展志
First Inventor	安丰伟
Original applicant	南方科技大学
First applicant	南方科技大学
Address of First applicant	518055 广东省深圳市南山区学苑大道1088号南方科技大学
Current applicant	南方科技大学
Address of Current applicant	518055 广东省深圳市南山区学苑大道1088号南方科技大学 (广东,深圳,南山区)
First Current Applicant	南方科技大学
Address of First Current Applicant	518055 广东省深圳市南山区学苑大道1088号南方科技大学 (广东,深圳,南山区)
Application Number	CN202010170575.3
Application Date	2020-03-12
Open (Notice) Number	CN111383221A
Date Available	2020-07-07
Status of Patent	实质审查 ; 许可
Legal Date	2020-07-31
Subtype	发明申请
SUSTech Authorship	First
Abstract	本申请涉及一种脊柱侧弯检测模型的生成方法和计算机设备，所述脊柱侧弯检测模型的生成方法包括：获取训练数据，将训练数据输入初始神经网络，以得到训练数据对应的预测结果，其中，训练数据包括一个训练样本在行进过程中多个时刻的行进参数和训练样本对应的真实结果；根据真实结果和预测结果，调整初始神经网络的参数，并继续执行将所训练数据输入初始神经网络，以得到预测结果的步骤，直至满足预设训练条件，以得到已训练的脊柱侧弯检测模型。所述训练数据包括一个训练样本在行进过程中多个时刻的行进参数，是动态的数据，通过行进过程中的动态数据训练初始神经网络，使得已训练的脊柱侧弯检测模型在实际使用时，能得到更准确的检测结果。
Other Abstract	The invention relates to a scoliosis detection model generation method and computer equipment. The scoliosis detection model generation method comprises steps that training data is acquired, the training data are inputted to an initial neural network to acquire a prediction result corresponding to the training data, and the training data comprise advancing parameters of one training sample at multiple moments in an advancing process and a real result corresponding to the training sample; and according to the real result and the prediction result, adjusting parameters of the initial neural network, and continuously executing the step of inputting the training data into the initial neural network to obtain the prediction result until a preset training condition is met so as to obtain a trained scoliosis detection model. The training data comprise advancing parameters of one training sample at multiple moments in the advancing process, the training data is dynamic data, and the initial neural network is trained through the dynamic data in the advancing process, so that a trained scoliosis detection model can obtain a more accurate detection result in actual use.
CPC Classification Number	G06T7/0012 ; G06T2207/10028 ; G06T2207/20081 ; G06T2207/20084 ; G06T2207/30012
IPC Classification Number	G06T7/00
INPADOC Legal Status	（ENTRY INTO FORCE OF RECORDATION OF PATENT LICENSING CONTRACT）[2021-06-25][CN]
INPADOC Patent Family Count	1
Extended Patent Family Count	1
Priority date	2020-03-12
Patent Agent	吴志益
Agency	深圳市君胜知识产权代理事务所(普通合伙)
URL	[Source Record]
Data Source	PatSnap
Document Type	Patent
Identifier	http://kc.sustech.edu.cn/handle/2SGJ60CL/534002
Department	SUSTech Institute of Microelectronics 南方科技大学-香港科技大学深港微电子学院筹建办公室
Recommended Citation GB/T 7714	安丰伟,刘展志. 一种脊柱侧弯检测模型的生成方法和计算机设备.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation Sequential No:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh