Human body fall-reduction and quakeproof intelligent monitoring method and system based on multi-sensor data reinforcement learning

Abstract

The invention belongs to the field of sensor data processing, and particularly relates to a human body fall-reduction shockproof intelligent monitoring method and system based on multi-sensor data reinforcement learning, and the method comprises the steps: carrying out the real-time monitoring of a monitored object, and collecting the sensing data of the monitored object through multiple sensors; obtaining a human body tumble related state according to the sensing data; inputting the related state information into a semi-observation Markov decision process model to obtain an optimal execution strategy; the execution arm system executes corresponding actions according to the strategy, and the actions comprise the steps that an execution arm with the maximum protection effect is selected from execution arms of candidate parts, the execution arm is activated, an inflation command is output, and the effects of reducing falling and preventing vibration are achieved; after the execution arm action is completed, the sensor sensing data are collected again, the human body tumble related state is obtained, and then the next-stage decision support process is started; according to the intelligent air bag intervention mode based on reinforcement learning, the injury risk of falling down can be lowered in a targeted mode for patients of different falling down types.

Description

technical field [0001] The invention belongs to the field of sensor data processing, and in particular relates to an intelligent monitoring method and system for human body fall reduction and anti-shock based on multi-sensor data reinforcement learning. Background technique [0002] Health technology innovation in the process of population aging has become a hot topic in the relevant theoretical circles and industries. Population aging began in the Western world in the 20th century, which is unprecedented in human history. In China, the number of elderly people over 60 years old has been on the rise between 2010 and 2050, and the degree of population aging is increasing. In the case of unintentional injury in the elderly, falls are an important factor in the death of the elderly, which is due to the increase of the elderly with the increase of age, the ability to respond and balance will be weakened, and the muscle strength will also decrease. Patients with fall-related tr...

AI Technical Summary

Problems solved by technology

[0004] However, it can be seen from the existing research technologies that the core devices for monitoring the falls of the elderly all use three-axis acceleration sensors; and the process of collecting information about the elderly through sensors is easily affected by environmental factors and the elderly’s own factors, making the acquisition Errors in the received information lead to difficulties in monitoring; therefore, there is an urgent need for a solution to achieve effective early warning, timely response, reduce the impact of the fall process, and alleviate the injury caused by the fall.

Images