Method, device and storage medium for heart rate monitoring based on deep learning

Abstract

The invention relates to a heart rate monitoring method based on deep learning, which comprises the following steps of: acquiring heart rate data of a monitored object; analyzing the heart rate data to obtain a marking processing result of the heart rate data; training a neural network; analyzing the acquired real-time heart rate data in the trained neural network to obtain a corresponding real-time marking processing result; when the real-time marking processing result is of a preset first marking type, sending warning information to the monitored object corresponding to the real-time heart rate data; when the real-time marking processing result is of a preset second marking type, storing the heart rate data of a preset step number in the trained neural network; and marking the processingresult to carry out iterative training. The method, a device and a storage medium for heart rate monitoring based on deep learning have the advantages that the heart rate signals are monitored and analyzed by using a deep learning method, and the heart rate signals are classified into four types of normal, abnormal, near danger and strong danger for reminding, monitoring, rescuing and the like.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of artificial intelligence big data processing, and in particular to a heart rate monitoring method, device and storage medium based on deep learning. Background technique [0002] With the increasing popularity of marathon events in China, more and more people participate in marathons every year, and dangerous incidents occur frequently during events. The life protection of marathon runners on the field has received more and more attention. Cardiac arrest is a probabilistic event, but the difference in the outcome of an accident is the response speed of the rescue team in each event; at the same time, the players' ignorance of their own bodies and non-stop after physical problems are the main reasons for the emergence of A big part of marathon accidents. [0003] As the simplest abstraction and simulation of the human brain, the neural network abstracts the neural network of the human...

AI Technical Summary

Problems solved by technology

[0003]As the simplest abstraction and simulation of the human brain, the neural network abstracts the human brain neural network with mathematical and physical simulation methods and information processing methods. And establish a simplified model, the model has a certain learning ability, deep learning is generally learning by feature extraction or pattern classification, after the neural network is initialized, the deep learning neural network is randomly assigned or according to the data to be trained Irrelevant rules give initial values, and then carry out learning and training. This kind of random assignment cannot flexibly adapt to various application scenarios quickly, and random assignment cannot quickly adapt to each different application scenario. Therefore, it is currently not There is no solution to the above problem or the device appears

Images