Heart rate variability data analysis feedback method and system combined with virtual reality technology

Abstract

The invention relates to the technical field of virtual reality, and discloses a heart rate variability data analysis feedback method and system combined with the virtual reality technology, and the method comprises the steps: collecting the heart rate data of a testee in a calm state; performing virtual environment switching on a tester by utilizing a virtual reality technology, and collecting heart rate data after environment switching; in each environment, analyzing the heart rate variability data to obtain the response intensity of the testee; feeding back a virtual environment through the reaction intensity, and generating characteristic parameters for a tester; and generating feature distribution of the testee on the test features through the feature parameters. By combining the VR technology and heart rate variability (HRV) analysis, physiological signals of a testee are monitored in real time, and the virtual environment is dynamically adjusted to adapt to the state of the testee. Through characteristic parameter analysis and neural network optimization, irregular signals can be identified and corrected, and the analysis precision and the feedback response efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality technology, and in particular to a heart rate variability data analysis and feedback method and system combined with virtual reality technology. Background Art

[0002] With the development of virtual reality (VR) technology, its application in the fields of medicine, education, entertainment and training has become more and more extensive. Especially in psychological stress assessment, emotion regulation and rehabilitation training, VR provides a new way for personalized testing and intervention by creating a highly immersive virtual environment. However, traditional VR testing methods only rely on behavioral performance and subjective feedback, lack real-time monitoring and analysis of the tester's physiological signals, and cannot accurately evaluate the tester's state changes in the virtual environment. Heart rate variability (HRV), as an important physiological indicator of autonomic nervous system activity, can objectively reflect the tester's stress level, emotional state and adaptability. However, the application of HRV data in existing technologies is mostly focused on static analysis, and it is impossible to dynamically adjust the virtual environment to meet the personalized needs of the tester. Therefore, combining HRV analysis with VR technology and realizing dynamic environmental feedback through intelligent algorithms is an important direction of current technological development and the key to solving the above problems. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is that the existing heart rate variability data analysis method has a large randomness in the analysis results and cannot fully reflect the heart rate status of the tester.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a heart rate variability data analysis and feedback method combined with virtual reality technology, comprising: Collect the tester's heart rate data when he is calm; Using virtual reality technology, the tester switches the virtual environment and collects the heart rate data after the environment switches; In each environment, the heart rate variability data were analyzed to obtain the intensity of the test subject's response; Through the reaction intensity, the virtual environment is fed back and characteristic parameters for the tester are generated; The characteristic distribution of the test subject on the test characteristics is generated by using the characteristic parameters.

[0006] As a preferred solution of the heart rate variability data analysis and feedback method combined with virtual reality technology described in the present invention, wherein: the heart rate data includes: the tester wears a sensor device, the sensor device is used to collect monitoring signals, and the monitoring signals are converted into heart rate data; The sensing devices include ECG and PPG; The ECG or PPG monitoring signal is input into the embedded processing unit for data calculation: Calculation of ECG monitoring signals: extract R wave position and calculate continuous RR intervals; Calculation of PPG monitoring signal: extract pulse peak point and calculate pulse wave interval; The heart rate data is calculated to obtain heart rate variability data.

[0007] As a preferred solution of the heart rate variability data analysis and feedback method combined with virtual reality technology of the present invention, wherein: the virtual environment switching includes setting an environment sequence, in which the stimulation of the environment to the heart rate gradually increases; When the tester uses virtual reality technology, the initial environment of the virtual environment is: the first environment in the environment sequence; When the monitoring signal reaches the dynamic threshold in the current virtual environment, the tester switches the virtual environment and enters the next virtual environment in the environment sequence.

[0008] As a preferred solution of the heart rate variability data analysis and feedback method combined with virtual reality technology described in the present invention, wherein: the dynamic threshold includes performing feature analysis on the monitoring signal of the tester in the current environment, if the analysis result shows that the monitoring signal presents regularity, it is judged that the dynamic threshold is reached; if the analysis result shows that the monitoring signal does not present regularity, it is judged that the dynamic threshold is not reached; The feature analysis includes identifying irregular features in the monitoring signal when the tester is calm, and obtaining accompanying features based on the irregular features; matching the irregular features and the accompanying features with the monitoring signal in the current virtual environment; the specific steps include: Using the pre-trained neural network algorithm, a three-step recognition is completed; the first step is to identify the regular parts of the monitoring signal; the second step is to identify the parts that do not conform to the regularity in the regular parts; and classify all the parts that are identified as not conforming to the regularity; the third step is to identify the type of each part that does not conform to the regularity When the monitoring signal appears, the regular part of the monitoring signal appears at the same time ,right and Matching is performed to obtain the accompanying features of each type that does not conform to the regularity part and its matching, recorded as ; After the tester enters the virtual environment, the monitoring signal is The waveforms whose similarity is greater than a preset value are corrected: the parts that do not conform to the regularity are eliminated, and only the accompanying features of the eliminated parts are retained; The modified monitoring signal is identified by using the neural network algorithm. After the monitoring signal shows regularity, after continuous sampling time T, the original monitoring signal corresponding to the regular part is output; and the new , supplement the set E; after the output is completed, it is determined that the dynamic threshold is reached; in, It represents a pairing set consisting of each type that does not conform to the regularity and its accompanying features that match it; It represents the paired combination consisting of the type of the i-th part that does not conform to the regularity and its matching accompanying feature; It indicates the i-th type in the environment that is identified as not conforming to the regularity; express The accompanying characteristics; the irregular characteristics include the irregular parts that appear in the regular monitoring signal of the tester; the accompanying characteristics include the characteristics that appear simultaneously in the regular part when the irregular characteristics occur.

[0009] As a preferred solution of the heart rate variability data analysis and feedback method combined with virtual reality technology described in the present invention, wherein: the reaction intensity includes, according to the original monitoring signal, obtaining corresponding heart rate variability data; Assume that the heart rate variability data is , represents the heart rate variability data in the nth environment; When the tester is calm and does not enter the environment, it is recorded as ; Comparing the changes in the heart rate variability data before and after each environment switch with the standard changes, and providing feedback to the virtual environment based on the comparison results to achieve the jump of the virtual environment; The changes in the heart rate variability data include: , calculation and The difference is recorded as ; The change of the standard includes calculating the difference of the heart rate variability data between every two environments according to the historical records of the database to obtain the standard value of the heart rate variability data between every two environments.

[0010] As a preferred solution of the heart rate variability data analysis and feedback method combined with virtual reality technology described in the present invention, wherein: the feedback of the virtual environment includes that the change of the heart rate variability data for m consecutive times is less than the change of the standard, and for m consecutive times, it satisfies When , the feedback mechanism is triggered to jump to the virtual environment. The number of scenes jumped is R, directly jumping from the current nth environment to the delayed n+Rth environment; in, express The corresponding changes in the standards; It represents the average value of the changes of the m heart rate variability data when the changes of the heart rate variability data are all less than the changes of the standard for m consecutive times; It indicates that the maximum value of the standard change is obtained when the change of the heart rate variability data is smaller than the change of the standard for m consecutive times.

[0011] As a preferred solution of the heart rate variability data analysis and feedback method combined with virtual reality technology described in the present invention, wherein: the characteristic parameters include: the tester obtains the heart rate variability data in each virtual environment, matches the heart rate variability data with the corresponding virtual environment, and records the matching results and ; For each virtual environment that the tester has visited, output the corresponding and , get the set of characteristic parameters that have been traveled ; Using the trained Bayesian network, the output is U, and the output is the probability distribution of the test feature; in, represents the specific environment corresponding to the nth environment, and N represents the number of virtual environments that the tester has visited; The test features include preset labels used as target values ​​when training the Bayesian network.

[0012] A heart rate variability data analysis and feedback system using the method of the present invention combined with virtual reality technology, wherein: A collection unit collects the heart rate data of the tester when he is calm; The simulation unit uses virtual reality technology to switch the virtual environment of the test subject and collect the heart rate data after the environment is switched; The analysis unit analyzes the heart rate variability data in each environment to obtain the test subject's reaction intensity; A feedback unit, which provides feedback to the virtual environment through the reaction intensity and generates characteristic parameters for the tester; The output unit generates a feature distribution of the test subject on the test feature through the feature parameters.

[0013] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein: the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0014] A computer-readable storage medium stores a computer program, wherein: when the computer program is executed by a processor, the steps of any one of the methods of the present invention are implemented.

[0015] Beneficial effects of the invention: The invention combines VR technology with heart rate variability (HRV) analysis to monitor the tester's physiological signals in real time and dynamically adjust the virtual environment to adapt to the tester's state. Through characteristic parameter analysis and neural network optimization, irregular signals can be identified and corrected, improving analysis accuracy and feedback response efficiency. The system realizes personalized scene adaptation and optimizes user experience, and is suitable for psychological assessment, emotional regulation, rehabilitation training and other fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 This is an overall flow chart of the heart rate variability data analysis and feedback method combined with virtual reality technology provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0019] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a heart rate variability data analysis and feedback method combined with virtual reality technology, comprising: S1: Collect the test subject’s heart rate data when he / she is at rest.

[0020] Furthermore, the heart rate data includes that the test subject wears a sensor device, collects monitoring signals through the sensor device, and converts the monitoring signals into heart rate data.

[0021] The sensing device includes ECG and PPG. The monitoring signal of ECG or PPG is input into the embedded processing unit to perform data calculation: Calculation of ECG monitoring signals: extract R wave position and calculate continuous RR intervals.

[0022] Calculation of PPG monitoring signal: extract pulse peak point and calculate pulse wave interval.

[0023] The heart rate data is calculated to obtain heart rate variability data. Heart rate variability data (HRV) is a set of characteristic values ​​calculated based on heart rate data (such as RR intervals or pulse wave intervals), which can reflect the activity of the autonomic nervous system and cardiovascular health. HRV data includes time domain analysis, frequency domain analysis and nonlinear analysis.

[0024] Time domain analysis reflects the overall level and short-term changes of heart rate variability by statistically analyzing the characteristics of heartbeat interval time series. Main indicators: SDNN (standard deviation): represents the standard deviation of all heartbeat intervals, reflecting the overall level of heart rate variability.

[0025] RMSSD (root mean square): represents the root mean square of the difference between adjacent heartbeat intervals, reflecting the parasympathetic nervous system activity.

[0026] pNN50: indicates the proportion of adjacent heartbeat intervals greater than 50 ms, reflecting short-term fluctuations.

[0027] AVNN (Average Heart Beat Neighborhood): represents the average value of all heart beat intervals and is used to estimate the overall heart rate.

[0028] HR (Heart Rate): The number of heart beats per minute calculated from the intervals between your heart beats.

[0029] Frequency domain analysis analyzes the power of different frequency components by performing spectrum decomposition on the heartbeat interval time series, revealing the dynamic balance between sympathetic and parasympathetic nerves. Main indicators: VLF (Very Low Frequency Power): Frequency range: 0.003–0.04 Hz.

[0030] May be related to thermoregulation or other slow physiological fluctuations.

[0031] LF (Low Frequency Power): Frequency range: 0.04–0.15 Hz.

[0032] Reflects the joint activity of sympathetic and parasympathetic nerves.

[0033] HF (High Frequency Power): Frequency range: 0.15–0.4 Hz.

[0034] It is mainly controlled by the parasympathetic nervous system and reflects a state of relaxation.

[0035] TP (Total Power): Total spectral power, representing the sum of the variations in all frequency bands.

[0036] LF / HF ratio: indicates the balance between sympathetic and parasympathetic nerves.

[0037] Nonlinear analysis focuses on the complexity, dynamics and nonlinear characteristics of heart rate variability time series, and can reflect complex physiological regulation mechanisms.

[0038] Key indicators: Approximate Entropy (ApEn): Measures the complexity of a time series, with higher values ​​indicating more complex fluctuations.

[0039] Sample entropy (SampEn): measures the irregularity of the time series and is more robust to short time series.

[0040] Poincaré plot features: SD1: reflects short-term fluctuations in heart rate (instantaneous variability).

[0041] SD2: reflects long-term fluctuations in heart rate (overall variability).

[0042] Detrended fluctuation analysis (DFA): Assessing the self-similarity and long-term correlation of time series.

[0043] Lyapunov index: measures the sensitivity of the time series and reflects the dynamic stability of the signal.

[0044] S2: Using virtual reality technology, the tester switches virtual environments and collects heart rate data after the environment switches. In each environment, the heart rate variability data is analyzed to obtain the tester's reaction intensity. Through the reaction intensity, the virtual environment is fed back and characteristic parameters for the tester are generated.

[0045] Furthermore, the virtual environment switching includes setting an environment sequence, wherein the stimulation of the environment to the heart rate in the sequence gradually increases. When the tester uses virtual reality technology, the initial environment of the virtual environment is: the first environment in the environment sequence. When the tester is in the current virtual environment, when the monitoring signal reaches the dynamic threshold, the virtual environment is switched to the next virtual environment in the environment sequence.

[0046] The environment switching in the prior art is measured by time as the threshold. This is not suitable for content with large fluctuations such as heart rate. A dynamic threshold is used for improvement. The dynamic threshold includes a feature analysis of the monitoring signal of the tester in the current environment. If the analysis result shows that the monitoring signal shows regularity, it is judged that the dynamic threshold is reached; if the analysis result shows that the monitoring signal does not show regularity, it is judged that the dynamic threshold is not reached.

[0047] The feature analysis includes identifying irregular features in the monitoring signal when the tester is calm, and obtaining accompanying features based on the irregular features; matching the irregular features and the accompanying features with the monitoring signal in the current virtual environment; the specific steps include: Using a pre-trained neural network algorithm, (this algorithm is a simple recognition algorithm, which can be a simplified version of a neural network, because only the "specificity" needs to be recognized. That is, the irregular components mixed in the regularity of the monitoring data) complete the three-step recognition; the first step is to identify the regular parts of the monitoring signal; the second step is to identify the parts of the regular parts that do not conform to the regularity; and classify all the parts that are identified as not conforming to the regularity; the third step is to identify the type of each part that does not conform to the regularity When the monitoring signal appears, the regular part of the monitoring signal appears at the same time ,right and Matching is performed to obtain the accompanying features of each type that does not conform to the regularity part and its matching, recorded as .

[0048] After the tester enters the virtual environment, the monitoring signal is The waveforms whose similarity is greater than the preset value are corrected: the parts that do not conform to the regularity are eliminated, and only the accompanying features of the elimination are retained. The modified monitoring signal is identified using the neural network algorithm. After the monitoring signal shows regularity, after continuous sampling for a period of time T, the original monitoring signal corresponding to the regular part is output (the signal that has not been eliminated corresponds to the beginning and end moments of the output signal in the time series); and the new , supplement the set E; after the output is completed, it is determined that the dynamic threshold is reached.

[0049] It should be said that although neural networks (LSTM or convolutional neural networks can be used here) can achieve recognition, the recognition cycle is a bit long. For switching between multiple environments, if each environment takes too long, it will not be good for the experience. Therefore, by recognizing that the accompanying "irregular" part is actually the mutation part, for this part, if there are signs of occurrence in the regular part, then it can be completely understood that this is a part of the regularity. In this way, both fast recognition can be completed and the amount of calculation of the neural network can be reduced, thereby adapting to the simplified version of the neural network.

[0050] in, It represents a pairing set consisting of each type that does not conform to the regularity and its accompanying features that match it; It represents the paired combination consisting of the type of the i-th part that does not conform to the regularity and its matching accompanying feature; It indicates the i-th type in the environment that is identified as not conforming to the regularity; express The accompanying characteristics include irregular parts that appear in the regular monitoring signal of the tester; the accompanying characteristics include features that appear simultaneously in the regular part when the irregular characteristics occur. For example, in the regular part, when the value is greater than a certain value or less than a certain value (this value still belongs to the category of the regular part), an irregular feature will follow. Or it is a special case when the peak value of the PPG monitoring signal reaches a certain value. Therefore, this technical means has different meanings for ECG and PPG, for the detection signal of ECG.

[0051] It should be noted that in the monitoring signal, the data may contain irregular components due to physiological or environmental interference factors. These components will affect the analysis of the regular part of the signal, thereby reducing the accuracy of the virtual environment feedback. Through the following steps: Step 1: Extract the regular part of the signal and separate the main components that conform to the rules in the original signal. Step 2: Identify the irregular components in the regular part, classify them, and clarify their sources or characteristics. Step 3: Match the irregular components with the regular features, extract the associated information, and ensure that the processing of the abnormal part does not affect the integrity of the regular signal. This design ensures that when analyzing the signal, the irregular components will not mislead the judgment of the regular data, and improve the accuracy of signal processing. Through the classification of irregular parts and the matching of accompanying features: clarify the type of irregularity: such as sudden anomalies, gradual drift, spike fluctuations, etc. Identify its accompanying features: for example, when irregularity occurs, the change pattern of the regular signal (such as the associated changes of amplitude and frequency). This classification and matching helps to build a refined processing solution for irregular signals, avoiding the loss of important associated information by simply eliminating irregular parts. As data accumulates, the system gradually increases its understanding of irregularity types and their associated features, improving its recognition capabilities. The rich feature set E provides high-quality data for subsequent model retraining, continuously improving the system's learning ability and feedback accuracy.

[0052] Finally, the process based on identification, correction and dynamic threshold judgment is: monitoring signal → regularity identification → correction → dynamic threshold judgment → environment adjustment. It reduces the time that the tester stays in a single environment and avoids repeated or invalid tests.

[0053] The reaction intensity includes obtaining the corresponding heart rate variability data according to the original monitoring signal. Assume that the heart rate variability data is , represents the heart rate variability data in the nth environment. When the tester is calm and has not entered the environment, it is recorded as The changes in the heart rate variability data before and after each environment switch are compared with the standard changes, and the virtual environment is fed back according to the comparison results to achieve the jump of the virtual environment.

[0054] The changes in the heart rate variability data include: , calculation and The difference is recorded as The change of the standard includes calculating the difference of the heart rate variability data between each two environments according to the historical records of the database to obtain the standard value of the heart rate variability data between each two environments.

[0055] Furthermore, the feedback to the virtual environment includes that the change of the heart rate variability data is less than the change of the standard for m consecutive times, and for m consecutive times, it satisfies When , the feedback mechanism is triggered to jump to the virtual environment. The number of scenes jumped is R, and it jumps directly from the current nth environment to the delayed n+Rth environment.

[0056] in, express The corresponding changes in the standards; It represents the average value of the changes of the m heart rate variability data when the changes of the heart rate variability data are all less than the changes of the standard for m consecutive times; It indicates that the maximum value of the standard change is obtained when the change of the heart rate variability data is smaller than the change of the standard for m consecutive times.

[0057] It is to compare the actual change value of HRV with the historical standard in the database to determine whether the current environment has the expected stimulation effect on the tester. A single change in HRV data may be affected by external noise or short-term fluctuations, and it is difficult to accurately reflect the overall state of the tester. Therefore, a continuous judgment mechanism for m times is designed: when the tester switches between multiple continuous environments, the change in HRV is less than the standard change value, indicating that the stimulation of the current environment on the tester is gradually weakened. The average value of the continuous m HRV changes is compared with the maximum value of the standard change to further confirm the effectiveness of the environmental stimulation. Through the continuous m-time change judgment, short-term abnormal fluctuations are filtered out, and the stability and scientificity of the judgment of the tester's physiological state changes are enhanced. In the virtual environment test, staying in an invalid or overly stressful scene for too long may cause excessive fatigue or emotional stress to the tester. Through the real-time monitoring and jump mechanism of HRV changes, the tester is ensured to remain safe and comfortable throughout the test.

[0058] S3: Generate a feature distribution of the test subject on the test feature using the feature parameters.

[0059] Furthermore, the characteristic parameters include: the tester obtains the heart rate variability data in each virtual environment, matches the heart rate variability data with the corresponding virtual environment, and records the matching results. and For each virtual environment that the tester has visited, the corresponding and , get the set of characteristic parameters that have been traveled Using the trained Bayesian network, the output is U, which is the probability distribution of the test feature.

[0060] in, represents the specific environment corresponding to the nth environment, and N represents the number of virtual environments that the tester has traveled through. The test feature includes a preset label used as a target value when training the Bayesian network.

[0061] By analyzing the changes in the tester's physiological state in different virtual environments, their physiological adaptability, emotional fluctuations and recovery ability are comprehensively evaluated. As the tester travels through the virtual environment, the system can update the characteristic parameter set in real time to dynamically reflect their physiological and psychological state.

[0062] During the Bayesian network training phase, preset labels (such as high adaptability and low adaptability) are set for the target values. The system optimizes the feature distribution and model parameters by comparing the actual output with the target value. The system can conduct real-time and intelligent evaluation of the tester's physiological and psychological state. By quickly judging the tester's state, the design of the virtual environment can be adjusted in time to improve the user experience.

[0063] The target value labels mentioned above are generally preset during the training phase and are preset according to test requirements. They are designed based on test requirements and scenarios, and can reflect the physiological, psychological, and behavioral characteristics of the tester in multiple dimensions and levels. Examples of common target label content: (1) Single label: The test subject’s status in the virtual environment is reflected in a single dimension.

[0064] Adaptability (high / medium / low) Stress level (high / medium / low) Recovery ability (fast / medium / slow) (2) Combined label: The tester’s status is described by a combined label of multiple dimensions.

[0065] Example: Label = (Adaptability: High, Stress: Low, Recovery: Fast) Label = (Adaptability: High, Stress: Low, Recovery: Fast) Label = (task performance: average, emotion: nervous) Label = (task performance: average, emotion: nervous) (3) Continuous labels: Target value labels can be continuous values, reflecting the intensity or degree of the state.

[0066] Adaptability score: A score in the range [0,1], where higher values ​​indicate greater adaptability.

[0067] Stress Index: A stress score calculated from HRV.

[0068] Recovery time: in seconds or minutes.

[0069] Tag example: Stress test scenario: Tags: stress response.

[0070] High stress: HRV index decreased by more than 50%, and the LF / HF ratio increased significantly.

[0071] Moderate stress: HRV index decreases by 20%-50%, and the LF / HF ratio increases slightly.

[0072] Low stress: HRV changes little and the LF / HF ratio remains balanced.

[0073] Rehabilitation training scenario: Tags: Resilience.

[0074] Fast recovery: Heart rate variability indicators return to baseline values ​​within 2 minutes.

[0075] Medium recovery: The indicator recovery time is 2-5 minutes.

[0076] Slow recovery: No recovery after more than 5 minutes.

[0077] Virtual training scenario: Tags: adaptability.

[0078] High adaptability: stable HRV and high task completion efficiency.

[0079] Moderate adaptability: HRV fluctuates and task completion efficiency is moderate.

[0080] Low adaptability: HRV fluctuates drastically and task completion efficiency is low.

[0081] The design of target value labels is the key to training Bayesian networks. It can cover multiple dimensions such as adaptability, stress response, and recovery ability. The specific content should be flexibly preset according to test requirements and scenarios. These labels not only support the effective learning of the model, but also provide important basis for the optimization of the virtual environment and the improvement of user experience.

[0082] On the other hand, this embodiment also provides a heart rate variability data analysis and feedback system combined with virtual reality technology, which includes: The collection unit collects the heart rate data of the test subject when he is calm.

[0083] The simulation unit uses virtual reality technology to switch the virtual environment of the test subject and collect the heart rate data after the environment is switched.

[0084] The analysis unit analyzes the heart rate variability data in each environment to obtain the response intensity of the test subject.

[0085] The feedback unit provides feedback to the virtual environment through the reaction intensity and generates characteristic parameters for the tester.

[0086] The output unit generates a feature distribution of the test subject on the test feature through the feature parameters.

[0087] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0088] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0089] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0090] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0091] Example 2 is an embodiment of the present invention, which provides a heart rate variability data analysis and feedback method combined with virtual reality technology. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0092] The goal of the experiment is to evaluate the improvements of the proposed method in terms of test efficiency, accuracy, and user experience through key parameters such as total test time, test accuracy score, and user experience score.

[0093] The experiment selected 45 volunteers, all of whom were healthy adults, and divided them into three groups, with 15 people in each group.

[0094] Experimental group (the group using the method of the present invention): the heart rate variability data analysis and feedback method of the present invention was adopted to adjust the virtual environment switching in real time through a dynamic threshold.

[0095] Control group A (fixed time group): Each virtual environment is fixed for 2 minutes before switching, with no feedback mechanism.

[0096] Control group B (manual operation group): The testers switched scenes based on their own subjective judgment and operated the device.

[0097] Experimental equipment and environment: The experiment set up five virtual scenes, namely quiet scene (E1), light stress scene (E2), medium stress scene (E3), high stress scene (E4) and extremely high stress scene (E5). The stimulation of the scenes gradually increased.

[0098] All testers wore ECG and PPG sensor devices to collect heart rate variability data for dynamic analysis, and recorded the switching timing, total test duration and user experience.

[0099] Experimental process: Baseline data collection: The test subjects collected baseline data in the initial sitting state.

[0100] Virtual environment testing: Experimental group: The dynamic feedback mechanism automatically switches scenes and enters the next scene when the heart rate variability data reaches the dynamic threshold.

[0101] Control group A: The environment was switched at a fixed time (every 2 minutes) without considering the test subject's physiological data.

[0102] Control group B: The operator subjectively operated the device and switched to the next scene that he or she deemed appropriate.

[0103] Data recording: The total test time, switching accuracy scores, and user experience scores of the three groups of testers were recorded.

[0104] Table 1 Data record table

[0105] By comparing the experimental data of total test time, test accuracy and user experience score, it can be seen that the method of the present invention is significantly superior to the existing technology in terms of test efficiency, accuracy and user experience.

[0106] The total test time of the experimental group was 480 seconds, which was significantly shorter than that of the fixed time group (600 seconds) and the manual operation group (590 seconds). The dynamic feedback mechanism enabled the experimental group to switch the virtual environment in time according to the changes in the tester's physiological state, avoiding wasting time in invalid scenes. Compared with the fixed time group, the method of the present invention reduced the test time by 20% and significantly improved the test efficiency.

[0107] The accuracy score of the experimental group was 95.2%, which was close to that of the manual operation group (91.7%) and significantly higher than that of the fixed time group (80.3%). The accuracy of the fixed time group was low because it could not respond to the tester's physiological state in real time, resulting in poor timing of scene switching. The method of the present invention can accurately capture the tester's state changes during switching through dynamic threshold adjustment, reducing errors caused by switching too early or too late.

[0108] The user experience score of the experimental group was 8.8, significantly higher than that of the fixed time group (6.5) and the manual operation group (7.0). User feedback showed that the dynamic feedback mechanism of the experimental group brought a smoother testing experience, and the timing of scene switching was more natural and in line with the physiological state of the testers. The fixed time group had a poor experience because the switching was rigid and could not respond to the actual state of the testers. The user experience score of the manual operation group was also lower than that of the experimental group because frequent manual switching increased the operating burden, causing some testers to feel tired.

[0109] The experimental results fully prove that the method of the present invention has significant advantages in shortening the total test time, improving the test accuracy and enhancing the user experience, and shows outstanding innovation and practical value compared with the existing technology. Through the dynamic feedback mechanism, the present invention realizes personalized scene adjustment, optimizes the overall process of virtual environment testing, and provides an efficient and scientific solution for practical applications.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A heart rate variability data analysis and feedback method combined with virtual reality technology, characterized in that: include: Collect the tester's heart rate data when he is calm; Using virtual reality technology, the tester switches the virtual environment and collects the heart rate data after the environment switches; In each environment, the heart rate variability data were analyzed to obtain the intensity of the test subject's response; Through the reaction intensity, the virtual environment is fed back and characteristic parameters for the tester are generated; The characteristic distribution of the test subject on the test characteristics is generated by using the characteristic parameters.

2. The heart rate variability data analysis and feedback method combined with virtual reality technology as claimed in claim 1, characterized in that: The heart rate data includes collecting monitoring signals by wearing a sensor device on the tester and converting the monitoring signals into heart rate data; The sensing devices include ECG and PPG; The ECG or PPG monitoring signal is input into the embedded processing unit for data calculation: Calculation of ECG monitoring signals: extract R wave position and calculate continuous RR intervals; Calculation of PPG monitoring signal: extract pulse peak point and calculate pulse wave interval; The heart rate data is calculated to obtain heart rate variability data.

3. The heart rate variability data analysis and feedback method combined with virtual reality technology as claimed in claim 2, characterized in that: The virtual environment switching includes setting an environment sequence, wherein the stimulation of the environment to the heart rate gradually increases; When the tester uses the virtual reality technology, the initial environment of the virtual environment is: the first environment in the environment sequence; When the monitoring signal reaches the dynamic threshold in the current virtual environment, the tester switches the virtual environment and enters the next virtual environment in the environment sequence.

4. The heart rate variability data analysis and feedback method combined with virtual reality technology as claimed in claim 3, characterized in that: The dynamic threshold includes performing feature analysis on the monitoring signal of the tester in the current environment, and if the analysis result shows that the monitoring signal presents regularity, then judging that the dynamic threshold is reached; If the analysis result shows that the monitoring signal does not show regularity, it is determined that the dynamic threshold is not reached; The feature analysis includes identifying irregular features in the monitoring signal when the test subject is calm, and obtaining accompanying features based on the irregular features; Matching the irregular feature and the accompanying feature with the monitoring signal in the current virtual environment; the specific steps include: Using the pre-trained neural network algorithm, a three-step recognition is completed; the first step is to identify the regular parts of the monitoring signal; the second step is to identify the parts that do not conform to the regularity in the regular parts; and classify all the parts that are identified as not conforming to the regularity; the third step is to identify the type of each part that does not conform to the regularity When the monitoring signal appears, the regular part of the monitoring signal appears at the same time ,right and Matching is performed to obtain the accompanying features of each type that does not conform to the regularity part and its matching, recorded as ; After the tester enters the virtual environment, the monitoring signal is The waveforms whose similarity is greater than a preset value are corrected: the parts that do not conform to the regularity are eliminated, and only the accompanying features of the eliminated parts are retained; The modified monitoring signal is identified by using the neural network algorithm. After the monitoring signal shows regularity, after continuous sampling time T, the original monitoring signal corresponding to the regular part is output; and the new , supplement the set E; after the output is completed, it is determined that the dynamic threshold is reached; in, It represents a pairing set consisting of each type that does not conform to the regularity and its accompanying features that match it; It represents the paired combination consisting of the type of the i-th part that does not conform to the regularity and its matching accompanying feature; It indicates the i-th type in the environment that is identified as not conforming to the regularity; express The accompanying characteristics; the irregular characteristics include the irregular parts that appear in the regular monitoring signal of the tester; the accompanying characteristics include the characteristics that appear simultaneously in the regular part when the irregular characteristics occur.

5. The heart rate variability data analysis and feedback method combined with virtual reality technology as claimed in claim 4, characterized in that: The reaction intensity includes obtaining corresponding heart rate variability data according to the original monitoring signal; Assume that the heart rate variability data is , represents the heart rate variability data in the nth environment; When the tester is calm and does not enter the environment, it is recorded as ; Comparing the changes in the heart rate variability data before and after each environment switch with the standard changes, and providing feedback to the virtual environment based on the comparison results to achieve the jump of the virtual environment; The changes in the heart rate variability data include: , calculation and The difference is recorded as ; The change of the standard includes calculating the difference of the heart rate variability data between every two environments according to the historical records of the database to obtain the standard value of the heart rate variability data between every two environments.

6. The heart rate variability data analysis and feedback method combined with virtual reality technology as claimed in claim 5, characterized in that: The feedback to the virtual environment includes that the change of the heart rate variability data is less than the change of the standard for m consecutive times, and for m consecutive times, it is satisfied When , the feedback mechanism is triggered to jump to the virtual environment. The number of scenes jumped is R, directly jumping from the current nth environment to the delayed n+Rth environment; in, express The corresponding changes in the standards; It represents the average value of the changes of the m heart rate variability data when the changes of the heart rate variability data are all less than the changes of the standard for m consecutive times; It indicates that the maximum value of the standard change is obtained when the change of the heart rate variability data is smaller than the change of the standard for m consecutive times.

7. The heart rate variability data analysis and feedback method combined with virtual reality technology as claimed in claim 6, characterized in that: The characteristic parameters include: the tester obtains the heart rate variability data in each virtual environment, matches the heart rate variability data with the corresponding virtual environment, and records the matching results. and ; For each virtual environment that the tester has visited, output the corresponding and , get the set of characteristic parameters that have been traveled ; Using the trained Bayesian network, the output is U, and the output is the probability distribution of the test feature; in, represents the specific environment corresponding to the nth environment, and N represents the number of virtual environments that the tester has visited; The test features include preset labels used as target values ​​when training the Bayesian network.

8. A heart rate variability data analysis and feedback system using the method according to any one of claims 1 to 7 combined with virtual reality technology, characterized in that: A collection unit collects the heart rate data of the tester when he is calm; The simulation unit uses virtual reality technology to switch the virtual environment of the test subject and collect the heart rate data after the environment is switched; The analysis unit analyzes the heart rate variability data in each environment to obtain the test subject's reaction intensity; A feedback unit, which provides feedback to the virtual environment through the reaction intensity and generates characteristic parameters for the tester; The output unit generates a feature distribution of the test subject on the test feature through the feature parameters.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any method as claimed in claim 1 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images