CN-122004859-A - Heart rate emotion monitoring method and system for VR game

CN122004859ACN 122004859 ACN122004859 ACN 122004859ACN-122004859-A

Abstract

The invention provides a heart rate emotion monitoring method and system for a VR game, the method comprises the steps of obtaining an original heart rate signal collected by a millimeter wave radar, carrying out distance dimension FFT and spectral peak search on the original heart rate signal to obtain distance information, respectively extracting phase information of the original heart rate signal through phase unwrapping, phase unwrapping and phase difference based on the distance information, extracting the heart rate signal in the original heart rate signal through an SSA-VME algorithm according to the phase information, carrying out spectral peak analysis on the heart rate signal through secondary CZT to obtain a heart rate, and identifying the emotion type of a user through a trained SVM classifier based on HRV time-frequency domain characteristics of the heart rate. Through this scheme can realize accurate heart rate monitoring and emotion monitoring, monitor with low costs and reliable and stable, and then can ensure the security and the user experience of VR recreation.

Inventors

GAO JUNFENG
LV JIAN
Luo Siyu
ZHANG QIAN
XIANG JIE
YUAN CHENGLIN

Assignees

苏州雷佳达健康科技有限公司

Dates

Publication Date: 20260512
Application Date: 20251230

Claims (10)

1. A heart rate emotion monitoring method for a VR game, comprising: acquiring an original heartbeat signal acquired by a millimeter wave radar; performing distance dimension FFT and spectral peak search on an original heartbeat signal to obtain distance information; Based on the distance information, extracting phase information of an original heartbeat signal through phase unwrapping, phase unwrapping and phase difference respectively; extracting a heartbeat signal in the original heartbeat signal through an SSA-VME algorithm according to the phase information, and carrying out spectral peak analysis on the heartbeat signal through secondary CZT to obtain a heart rate; Based on HRV time-frequency domain characteristics of heart rate, identifying emotion types of the user through the trained SVM classifier.
2. The method of claim 1, wherein the acquiring the raw heartbeat signal acquired by the millimeter wave radar comprises: Continuously transmitting the linear frequency modulation signals through a millimeter wave radar transmitting antenna, and receiving the reflected signals through a receiving antenna; The transmitting signal and the receiving signal are mixed by a mixer to obtain an intermediate frequency signal, and the intermediate frequency signal is subjected to analog-to-digital conversion.
3. The method of claim 1, wherein the extracting the heartbeat signal from the original heartbeat signal by SSA-VME algorithm comprises: solving the center frequency of the target modal component of the original heartbeat signal in the VME algorithm through a minimization criterion; constructing a wiener filter, and extracting signals near the center frequency through the wiener filter; Based on the signals near the center frequency, lagrangian multipliers and quadratic penalty terms are introduced, and heartbeat signals corresponding to target modal components are solved according to Paswal identities.
4. The method of claim 3, wherein solving for the center frequency of the original heartbeat signal target modality component in the VME algorithm by a minimization criterion comprises: And randomly generating parameter groups through an SSA algorithm, extracting the center frequency of a target modal component from each group of parameters through a VME algorithm, wherein the fitness of the VME algorithm is a fuzzy entropy function, updating the sparrow position according to the fitness value of the VME algorithm by the SSA algorithm, searching the parameter combination with the maximum fitness through iterative updating, and taking the parameter combination with the maximum fitness as the optimal parameter combination of the VME algorithm.
5. The method of claim 1, wherein the performing spectral peak analysis on the heartbeat signal by secondary CZT to obtain the heart rate comprises: sampling the heartbeat signal at a first frequency range to calculate a first predetermined number Spectrum of the individual samples: ; In the formula, A spectrum of sampling points representing a first frequency range, Represents the heartbeat signal, N represents the signal length, Sampling point signals representing a first frequency range, n, k being both counting variables, and ; Setting the frequency range of the area where the peak value is located in the first frequency range as a second frequency range, and calculating a second preset quantity Spectrum of the individual samples: ; In the formula, Representing the spectrum of sampling points of the second frequency range, N representing the signal length, Represents a sampling point signal of a second frequency range, n and k are all counting variables, and ; Wherein the second frequency range is smaller than the first frequency range, a second predetermined amount Greater than a first predetermined number 。
6. The method of claim 1, wherein the HRV time-frequency domain characteristics of the heart rate include at least a standard deviation of all intervals, a root mean square of adjacent interval differences, an average of intervals, energy in a high frequency range, energy in a low frequency range, and an energy ratio of the low frequency range to the high frequency range.
7. The method of claim 1, wherein prior to identifying the user emotion type by the trained SVM classifier comprises: Selecting HRV time-frequency domain characteristics of heart rate as a data set, removing abnormal values in the data set and carrying out normalization processing; Dividing the data set into a training set and a testing set, determining an optimal super-parameter combination through grid search and ten-fold cross validation, and training and testing the SVM classifier based on the optimal super-parameter combination.
8. A heart rate emotion monitoring system for a VR game, comprising: the signal acquisition module is used for acquiring an original heartbeat signal acquired by the millimeter wave radar; the signal analysis module is used for carrying out distance dimension FFT and spectral peak search on the original heartbeat signal to obtain distance information; The phase extraction module is used for extracting phase information of the original heartbeat signal through phase unwrapping, phase unwrapping and phase difference respectively based on the distance information; the heart rate analysis module is used for extracting the heart beat signals in the original heart beat signals through an SSA-VME algorithm according to the phase information, and carrying out spectral peak analysis on the heart beat signals through secondary CZT to obtain heart rate; And the emotion recognition module is used for recognizing the emotion type of the user through the trained SVM classifier based on the HRV time-frequency domain characteristics of the heart rate.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the steps of a heart rate emotion monitoring method of a VR game as set forth in any one of claims 1 to 7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed implements the steps of a heart rate emotion monitoring method of a VR game as set forth in any one of claims 1 to 7.

Description

Heart rate emotion monitoring method and system for VR game Technical Field The invention belongs to the technical field of physiological state monitoring, and particularly relates to a heart rate emotion monitoring method and system for a VR game. Background Virtual Reality (VR) is a super-strong simulation system capable of man-machine interaction, and VR games have wide market prospects due to good immersion, interactivity and the like. In VR games, because of the stimulus and rapid movement and rotation of high-intensity scenes, physiological reactions of players are easily triggered to cause heart rate rising, and the immersive experience of games enables players to substitute scenes to generate real tension to cause fear or pleasure, the emotions also cause heart rate rising, and besides, factors such as specific space setting, time limitation, equipment discomfort and the like of VR affect heart rate variation. However, excessive heart rate can cause physical discomfort and even physical health, and can pose a potential risk to players with cardiovascular disease, thus necessitating monitoring of the player's heart rate, mood. Currently, common heart rate monitoring modes generally adopt a photoelectric method (PPG), an electrical signal method (ECG), an electrocardiogram, a pressure sensor and the like, and the methods need to wear professional sensing equipment to realize heart rate measurement, so that actual use is inconvenient for VR game users. The millimeter wave radar is used as a non-contact sensor, and although the millimeter wave radar can be not influenced by factors such as light rays and clothes, the convenient heart rate measurement can be realized, but the millimeter wave radar is easily influenced by external factors such as respiration, and the actual heart rate monitoring accuracy is low. Meanwhile, current VR game emotion monitoring generally requires collection of multiple items of physiological index data, is high in emotion monitoring cost, and cannot identify user emotion based on heart rate. Disclosure of Invention In view of the above, the embodiments of the present invention provide a heart rate emotion monitoring method and system for VR games, which are used for solving the problems that the current heart rate monitoring accuracy is low, the emotion monitoring cost is high, and the emotion of a user cannot be identified based on the heart rate. In a first aspect of an embodiment of the present invention, there is provided a heart rate emotion monitoring method for a VR game, including: acquiring an original heartbeat signal acquired by a millimeter wave radar; performing distance dimension FFT and spectral peak search on an original heartbeat signal to obtain distance information; Based on the distance information, extracting phase information of an original heartbeat signal through phase unwrapping, phase unwrapping and phase difference respectively; extracting a heartbeat signal in the original heartbeat signal through an SSA-VME algorithm according to the phase information, and carrying out spectral peak analysis on the heartbeat signal through secondary CZT to obtain a heart rate; Based on HRV time-frequency domain characteristics of heart rate, identifying emotion types of the user through the trained SVM classifier. In a second aspect of the embodiments of the present invention, there is provided a heart rate emotion monitoring system for a VR game, including: the signal acquisition module is used for acquiring an original heartbeat signal acquired by the millimeter wave radar; the signal analysis module is used for carrying out distance dimension FFT and spectral peak search on the original heartbeat signal to obtain distance information; The phase extraction module is used for extracting phase information of the original heartbeat signal through phase unwrapping, phase unwrapping and phase difference respectively based on the distance information; the heart rate analysis module is used for extracting the heart beat signals in the original heart beat signals through an SSA-VME algorithm according to the phase information, and carrying out spectral peak analysis on the heart beat signals through secondary CZT to obtain heart rate; And the emotion recognition module is used for recognizing the emotion type of the user through the trained SVM classifier based on the HRV time-frequency domain characteristics of the heart rate. In a third aspect of the embodiments of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to the first aspect of the embodiments of the present invention when the computer program is executed by the processor. In a fourth aspect of the embodiments of the present invention, there is provided a computer readable storage medium storing a computer program which, when exe