Anxiety disorder virtual training system based on multiple parameters

Abstract

The invention relates to the technical field of virtual training, in particular to an anxiety disorder virtual training system based on multiple parameters, which comprises an acquisition module, a state determination module, a degree determination module, an intervention module, a judgment module, a recording module and an adjustment module. Through multi-parameter real-time monitoring and dynamic closed-loop intervention, comprehensive quantitative evaluation of preoperative anxiety of children is realized, intervention intensity is automatically adjusted based on state abnormality, threshold parameters are dynamically optimized in combination with historical data, intervention individuation and self-adaption are ensured, short-term physiological fluctuation is filtered through preset observation duration, and accuracy and accuracy of intervention are improved. According to the method, the judgment accuracy is improved, the whole intervention decision process is automatic, children are helped to rapidly reach the preoperative preparation state, the operation process is optimized, the safety and reliability of preoperative intervention are improved, and the problems that the preoperative anxiety intervention effect lags behind and the judgment accuracy is low due to static threshold comparison and parameter isolation analysis are effectively solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of virtual training, and in particular to a virtual training system for anxiety disorders based on multiple parameters. BACKGROUND

[0002] With the deep integration of precision medicine and child-friendly diagnosis and treatment concepts, perioperative psychological and physiological collaborative management for special child groups has become an important frontier in clinical practice, especially in the field of neurosurgery. How to safely and effectively stabilize the preoperative state of children and avoid the transformation of their anxiety into direct physiological risks constitutes a multi-dimensional clinical challenge that urgently needs to be broken through.

[0003] Chinese Patent Application Publication No. CN117637118A discloses an anxiety disorder virtual reality training system. The system includes a virtual scene construction module, a patient wearing a head-mounted device, a virtual daily life scene is constructed according to the anxiety disorder of the patient; a patient physiological data acquisition module, the patient wearing a physiological monitoring device, acquiring physiological data of the patient before social anxiety disorder training, and marking as normal physiological data; the patient performs social anxiety disorder training in the virtual daily life scene, physiological data of the patient is collected during the training process, and is marked as anxiety physiological data; a patient physiological data analysis module analyzes the collected normal physiological data and anxiety physiological data to obtain the corresponding anxiety level; a positive guidance module, during the social anxiety disorder training process, according to the change of the corresponding anxiety level of the patient, the virtual character in the virtual daily life scene gives positive guidance; a virtual scene adjustment module, according to the corresponding anxiety level of the patient, judges whether to adjust the virtual daily life scene where the patient is located; a method providing module provides a solution for the patient to overcome social anxiety disorder in actual social activities after the patient completes the social anxiety disorder training.

[0004] It can be seen that the anxiety disorder virtual reality training system has the following problems: the system does not specify the specific physiological indicator type and the multi-modal data fusion mechanism, which can easily lead to a single evaluation dimension and insufficient reliability and validity; the system relies on the anxiety level determination after a complete training cycle, and cannot realize continuous dynamic adjustment based on real-time physiological feedback; the system lacks an individualized baseline adaptive mechanism, and fixed threshold determination can easily lead to misjudgment. SUMMARY

[0005] Therefore, the present application provides an anxiety disorder virtual training system based on multiple parameters to overcome the problems of preoperative anxiety intervention effect lag and low determination accuracy caused by static threshold comparison and parameter isolated analysis in the prior art through multi-modal parameter fusion and dynamic closed-loop intervention.

[0006] To achieve the above purpose, the present application provides an anxiety disorder virtual training system based on multiple parameters, comprising: The acquisition module is used to acquire in real time the target's prefrontal cortex blood oxygen saturation, abnormal discharge index of electroencephalography, optical volume vibration index of the heart, transient amplitude of skin conductance, dispersion deviation of pupils and respiratory rate within a preset observation period. The state determination module is used to determine whether the state is abnormal based on the temporal characteristics of the abnormal discharge index and the blood oxygen saturation and a preset abnormal threshold, so as to obtain the state abnormality result. The degree determination module is used to determine the degree of anxiety based on the state abnormality result, according to the abnormal discharge index, the photovolume vibration index and the respiratory rate, so as to obtain the state abnormality degree. An intervention module is used to initiate intervention based on the intervention intensity corresponding to the state abnormality, and to determine the state change trend and improvement degree based on the skin conductance transient amplitude, the dispersion deviation and the respiratory rate, so as to determine the intervention response degree; The determination module is used to adjust the intervention intensity based on the intervention response rate, and to determine whether the preoperative status meets the standard based on the threshold comparison result of the intervention response rate, the abnormal discharge index and the blood oxygen saturation after adjusting the intervention intensity, so as to generate a stop intervention signal; A recording module is used to record the number of times the intervention intensity is corrected based on the intervention responsiveness before the stop intervention signal is generated, so as to obtain the number of corrections; The adjustment module is used to adjust the preset anomaly threshold or the preset observation duration based on the temporal characteristics of the number of corrections within a preset historical period.

[0007] Furthermore, the state determination module includes: An extraction unit is used to determine an index time series vector based on the abnormal discharge index within the preset observation period, and to determine a blood oxygen time series vector based on the blood oxygen saturation within the preset observation period. A local construction unit, connected to the extraction unit, is used to determine local index elements based on the exponential time series vector and a preset exponential vector to obtain an exponential local matrix, and to determine local blood oxygen elements based on the blood oxygen time series vector and a preset blood oxygen vector to obtain a blood oxygen local matrix. An accumulation building unit, connected to the local building unit, is used to build an exponential accumulation matrix based on the distance between the local exponential element and the starting local exponential element, and to build a blood oxygen accumulation matrix based on the distance between the local blood oxygen element and the starting local blood oxygen element. A state determination unit, connected to the cumulative construction unit, is used to determine the abnormality similarity based on the exponential cumulative matrix and the blood oxygen cumulative matrix, and to determine whether the target state is abnormal based on the abnormality similarity and the preset abnormality threshold, so as to obtain a state abnormality result.

[0008] Furthermore, the state determination unit includes: A distance calculation subunit is used to obtain the exponential cumulative distance based on the distance between the beginning and end of the local exponential elements in the exponential cumulative matrix, and to obtain the blood oxygen cumulative distance based on the distance between the beginning and end of the local blood oxygen elements in the blood oxygen cumulative matrix. A similarity calculation subunit, connected to the distance calculation subunit, is used to calculate exponential similarity based on the exponential cumulative distance, and to calculate blood oxygen similarity based on the blood oxygen cumulative distance; An anomaly determination subunit, connected to the similarity calculation subunit, is used to perform a weighted summation calculation on the exponential similarity and the blood oxygen similarity to obtain the anomaly similarity, and to obtain a state anomaly result based on the comparison result of the anomaly similarity and the preset anomaly threshold.

[0009] Furthermore, the degree determination module includes: The determination unit is used to determine an abnormal anxiety state when the abnormal discharge index is greater than a preset index threshold, the photovolume vibration index is less than a preset vibration threshold, and the respiratory rate is greater than a preset respiratory threshold. A deviation calculation unit, connected to the determination unit, is used to calculate the relative deviation between the abnormal discharge index and the preset index threshold to obtain the index deviation, and to calculate the relative deviation between the photovolume vibration index and the preset vibration threshold to obtain the vibration deviation, and to calculate the relative deviation between the respiratory rate and the preset respiratory threshold to obtain the respiratory deviation. A degree determination unit, connected to the deviation calculation unit, is used to determine the degree of anxiety based on the index deviation, the vibration deviation, and the breathing deviation, in order to obtain the state abnormality degree.

[0010] Furthermore, the degree determination unit includes: The degree calculation subunit is used to perform a weighted summation of the index deviation, the vibration deviation, and the breathing deviation to obtain the degree of anxiety; A degree determination subunit, which is connected to the degree calculation subunit, is used to obtain the state abnormality degree based on the comparison result between the anxiety degree and the preset anxiety threshold.

[0011] Furthermore, the intervention module includes: The change calculation unit is used to determine the intervention intensity based on the state anomaly degree and the preset rule base. After the intervention is initiated, it determines several skin conductance deviations based on the skin conductance transient amplitude and the preset amplitude threshold at each time within the preset intervention duration, and determines several dispersion deviations based on the dispersion deviation degree and the preset dispersion threshold at each time within the preset intervention duration, and determines several respiratory rate deviations based on the respiratory rate and the preset respiratory rate threshold at each time within the preset intervention duration. A trend statistics unit, connected to the change calculation unit, is used to calculate the proportion of the number of times when the skin conductance deviation is less than a preset change threshold, the dispersion deviation is less than a preset change threshold, and the call frequency deviation is less than a preset change threshold, relative to the total number of times of the preset intervention duration, so as to obtain the trend consistency. A collaborative statistics unit, connected to the change calculation unit, is used to calculate the proportion of the number of times when the skin conductance deviation is greater than a preset deflection threshold, the dispersion deviation is greater than a preset dispersion threshold, and the respiratory frequency deviation is greater than a preset respiratory deviation threshold, relative to the total number of times of the preset intervention duration, so as to obtain the degree of collaborative improvement. An intervention unit, which is connected to the trend statistics unit and the collaborative statistics unit respectively, is used to calculate the weighted geometric mean of the trend consistency degree and the collaborative improvement degree to obtain the intervention response degree.

[0012] Furthermore, the determination module includes: An adjustment unit is used to increase the intervention intensity when the intervention response is less than a preset response threshold; A response determination unit, connected to the adjustment unit, is used to determine the intervention response result when the intervention response degree, which is re-determined after increasing the intervention intensity, is greater than the preset response threshold. A determination unit, connected to the response determination unit, is used to determine whether the preoperative state target has been met based on the abnormal discharge index and blood oxygen saturation of the target when the intervention response result is determined, so as to generate a stop intervention signal.

[0013] Furthermore, the determination unit includes: The frequency determination subunit is used to obtain the normal discharge result based on the comparison result between the abnormal discharge index and the preset index threshold. An intensity determination subunit, connected to the frequency determination subunit, is used to generate a stop intervention signal based on the comparison between the blood oxygen saturation and a preset saturation threshold, according to the normal discharge result.

[0014] Furthermore, the number of corrections is determined based on the number of times the intervention intensity was corrected according to the intervention responsiveness before the stop intervention signal was generated, as recorded by the recording module.

[0015] Furthermore, the adjustment module includes: The correction analysis unit is used to calculate the linear regression slope of the number of corrections corresponding to each time within the preset historical period, so as to obtain the correction slope. A fluctuation calculation unit is used to calculate the standard deviation of the number of corrections corresponding to each time within the preset historical period, so as to obtain the corrected fluctuation value. A threshold adjustment unit, which is connected to the correction analysis unit and the fluctuation calculation unit respectively, is used to adjust the preset abnormal threshold according to the comparison result of the correction slope and the preset slope threshold and the comparison result of the correction fluctuation value and the preset fluctuation threshold. The duration adjustment unit is connected to the correction analysis unit and the fluctuation calculation unit respectively, and is used to adjust the preset observation duration according to the comparison results of the correction slope and the preset slope threshold and the comparison results of the correction fluctuation value and the preset fluctuation threshold.

[0016] Compared with existing technologies, the advantages of this invention lie in achieving a comprehensive quantitative assessment of preoperative anxiety in children through real-time monitoring of multiple parameters and dynamic closed-loop intervention. Specifically, by automatically adjusting the intervention intensity based on the degree of abnormality and dynamically optimizing threshold parameters based on historical data, the invention ensures personalized and adaptive intervention, effectively avoiding insufficient or excessive intervention. By filtering short-term physiological fluctuations through preset observation durations, the accuracy of judgment is improved, and the entire intervention decision-making process is automated. This helps children quickly reach a preoperative preparation state, optimizes the surgical procedure, and enhances the safety and reliability of preoperative intervention. It effectively solves the problems of delayed intervention effects and low accuracy in judgment caused by using static threshold comparisons and isolated parameter analysis.

[0017] Furthermore, by employing a dynamic time warping algorithm, real-time collected abnormal discharge index and blood oxygen saturation time-series data are dynamically matched with a preset vector. By constructing local and cumulative distance matrices, the degree of difference between the real-time physiological sequence and the standard pattern is accurately quantified. This overcomes the insensitivity of traditional static threshold methods to temporal features, effectively identifying anxiety-specific physiological fluctuation patterns, significantly improving the accuracy of abnormal state assessment, and providing a more reliable basis for subsequent interventions. Overall, by comprehensively capturing the dynamic characteristics of preoperative anxiety in children through time-series data, the accuracy and response speed of assessment are improved, continuously enhancing the ability to identify complex anxiety states and the adaptability of intervention strategies.

[0018] Furthermore, by calculating the minimum cumulative distance between the exponential cumulative matrix and the blood oxygen cumulative matrix, the time series of abnormal discharge index and blood oxygen saturation can be dynamically aligned, quantifying the deviation of the child's physiological changes from the norm reference during the preoperative observation period, thereby obtaining the exponential cumulative distance and the blood oxygen cumulative distance. Based on this, the distance is converted into a normalized similarity index, achieving continuous and quantifiable abnormal characterization. In addition, by weighted summation of exponential similarity and blood oxygen similarity, a comprehensive abnormality similarity is generated, achieving the fusion and judgment of multi-dimensional physiological signals. A preset abnormality threshold is used to determine the presence of an abnormal state, thus avoiding the limitations of single-parameter judgment. This dynamically and accurately reflects subtle changes in the child's preoperative anxiety state, enhancing the sensitivity and stability of the judgment, and improving the automation, reliability, and efficiency of preoperative intervention.

[0019] Furthermore, by jointly analyzing three types of physiological indicators, a refined assessment of children's preoperative anxiety state can be achieved. When the abnormal discharge index increases, the photovolume vibration index decreases, and the respiratory rate increases, an abnormal anxiety state can be promptly identified, effectively avoiding misjudgments that may be caused by relying on a single physiological indicator. Based on this, by calculating the relative deviation of each indicator from the preset threshold, the deviation of the anxiety state is quantified, and the degree of anxiety is determined based on the relative deviation. This comprehensively reflects the contribution of different physiological signals to the overall anxiety state, generating a state abnormality degree, thereby providing a scientific and quantitative basis for intervention. It enables real-time and dynamic monitoring of the anxiety state, allowing intervention strategies to be adaptively adjusted based on the individual physiological feedback of the child, improving the pertinence and responsiveness of the intervention.

[0020] Furthermore, by weighted integration of abnormal discharge index deviation, optical volume vibration index deviation, and respiratory index deviation, a quantitative assessment of preoperative anxiety levels in children about to undergo neurosurgical procedures is achieved. This reflects the relative contribution of each physiological indicator to the overall anxiety state, avoiding the excessive influence of a single indicator on the judgment results. When the anxiety level exceeds a preset threshold, a state abnormality degree is generated through relative deviation, achieving a continuous and quantitative representation of the anxiety state. This reflects the dynamic changes in the child's physiological and psychological state, allowing intervention strategies to adaptively adjust according to individual differences, improving the intervention's targeting and response speed. Simultaneously, quantifying the relationship between anxiety level and abnormal state enhances the scientific rigor, controllability, and efficiency of preoperative intervention.

[0021] Furthermore, through dynamic deviation analysis and composite statistical methods of multiple physiological indicators, a refined quantitative assessment of the intervention effect was achieved, thereby enhancing the system's sensitivity and reliability to the anxiety improvement process. By showing the improvement trends of the three indicators at each time step in the form of relative deviations, subtle physiological changes during the intervention process could be continuously tracked. Based on this, the stability of the synchronous decline in overall physiological load was measured by the proportion of times with deviations less than zero, reflecting whether the intervention was continuously effective. In addition, by further identifying the proportion of times when all three indicators achieved significant improvement, the synergistic physiological recovery effect of the intervention during the high-intensity phase was captured. A weighted geometric average was then used to integrate the long-term trend and transient synergistic improvement into the intervention responsiveness, avoiding the dominance of a single indicator and reflecting the comprehensive effectiveness of the intervention in actual anxiety relief.

[0022] Furthermore, by establishing a closed-loop control mechanism of "response degree, intensity adjustment, and physiological verification," the intervention intensity is automatically increased when insufficient intervention response is detected. Once the response reaches the target, the key physiological indicators of abnormal discharge index and blood oxygen saturation are immediately verified. Through dynamic adjustment and dual verification mechanism, the problems of fixed intervention intensity and single evaluation indicators in traditional methods are effectively overcome. This ensures that the intervention measures are always in the optimal intensity range, and the authenticity and stability of anxiety relief are finally confirmed through physiological parameters, thereby significantly improving the reliability and success rate of preoperative psychological preparation.

[0023] Furthermore, by establishing a dual verification mechanism of abnormal discharge index and blood oxygen saturation, the two key physiological indicators are evaluated as a final assessment after the intervention response reaches the target. This cross-validation method effectively overcomes the accidental risks that may occur in the determination of a single parameter. It ensures that anxiety relief is manifested in the motor dimension as a decrease in muscle tension, i.e., a reduction in tremor frequency, and in the vascular dimension as an improvement in peripheral circulation, i.e., the recovery of blood oxygen saturation. This significantly improves the accuracy and reliability of the preoperative condition assessment and provides dual protection for the safe implementation of the surgery.

[0024] Furthermore, by quantifying the number of intensity corrections during the intervention process, a key indicator is provided for assessing the individual's anxiety resistance and the effectiveness of the intervention strategy. The more corrections, the worse the stability of the anxiety state. This not only achieves refined quantitative management of the intervention process, but also provides data support for the system to adaptively optimize threshold parameters, significantly improving the system's intelligence level and intervention accuracy.

[0025] Furthermore, by intelligently analyzing the temporal characteristics of the number of corrections, a parameter optimization mechanism based on slope-fluctuation dual-modal analysis was established. Specifically, when the number of corrections exhibits a high slope and low fluctuation characteristic, the system's anomaly judgment criteria are identified as overly sensitive, and the anomaly threshold is increased through an adaptive formula to reduce false alarms. When it exhibits a low slope and high fluctuation characteristic, baseline instability caused by insufficient observation time is diagnosed, and the observation time is dynamically extended to improve data reliability. This self-optimization system based on dynamic feedback overcomes the limitations of fixed parameter systems in the face of individual differences and state changes, enabling the system to continuously iterate and upgrade, significantly improving the accuracy of personalized interventions and the long-term adaptability of the system. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the structure of the anxiety disorder virtual training system based on multiple parameters in this embodiment; Figure 2 This is a logic diagram for determining target state anomalies by the state determination unit in this embodiment. Figure 3 This is a logic diagram for determining abnormal anxiety states in the severity determination module of this embodiment; Figure 4 This is a logic diagram for determining whether the preoperative condition meets the criteria by the determination unit in this embodiment. Detailed Implementation

[0027] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0028] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0029] Please see Figure 1 As shown, this is a schematic diagram of the structure of the virtual training system for anxiety disorders based on multiple parameters in this embodiment. This embodiment provides a virtual training system for anxiety disorders based on multiple parameters, including: The acquisition module is used to acquire in real time the blood oxygen saturation of the prefrontal cortex, the abnormal discharge index of the electroencephalogram, the optical volume vibration index of the heart, the transient amplitude of the skin conductance, the divergence of the pupils, and the respiratory rate of the target within a preset observation period. A state determination module, which is connected to the acquisition module, is used to determine whether the state is abnormal based on the temporal characteristics of the abnormal discharge index and the blood oxygen saturation and a preset abnormal threshold, so as to obtain a state abnormality result. A degree determination module, which is connected to the acquisition module and the state determination module respectively, is used to determine the degree of anxiety based on the state abnormality result, according to the abnormal discharge index, the photovolume vibration index and the respiratory rate, so as to obtain the state abnormality degree. An intervention module, which is connected to the acquisition module and the degree determination module respectively, is used to initiate intervention based on the intervention intensity corresponding to the state abnormality, and after the intervention is initiated, to determine the state change trend and improvement degree based on the skin conductance transient amplitude, the dispersion deviation and the respiratory rate, so as to determine the intervention response degree. The determination module, which is connected to the acquisition module and the intervention module respectively, is used to correct the intervention intensity based on the intervention response degree, and to determine whether the preoperative status meets the standard based on the threshold comparison result of the intervention response degree, the abnormal discharge index and the blood oxygen saturation after correcting the intervention intensity, so as to generate a stop intervention signal; A recording module, connected to the determination module, is used to record the number of times the intervention intensity is corrected based on the intervention response degree before the stop intervention signal is generated, so as to obtain the number of corrections; An adjustment module, which is connected to the acquisition module, the state determination module and the recording module respectively, is used to adjust the preset anomaly threshold or the preset observation duration according to the temporal characteristics of the number of corrections within a preset historical period.

[0030] This embodiment targets children with epilepsy who experience preoperative anxiety. The intervention is a virtual training program designed to help children overcome anxiety disorders. In this embodiment, a multi-parameter-based virtual training system for anxiety disorders is applied to the preoperative anxiety management and safety intervention scenario for children with epilepsy. For epilepsy patients about to undergo neurosurgical procedures, including electrophysiological examinations, craniotomy, and interventional procedures, preoperative anxiety significantly increases cortical excitability, raising the risk of abnormal discharges and preoperative seizures. Against this backdrop, multiple physiological parameters are collected in real-time to assess the preoperative state. Based on the multi-parameter assessment of abnormalities and anxiety levels, virtual training intervention is initiated. Simultaneously, the intervention intensity and observation thresholds are dynamically adjusted until the child's preoperative state meets the standards, generating a stop-intervention signal. This ensures that the child meets the psychological and physiological conditions required to cooperate with the surgery.

[0031] In this embodiment, the acquisition module collects data in real time to provide comprehensive data support for subsequent anxiety state determination. Among them, blood oxygen saturation is an indicator reflecting the hemodynamic and metabolic state related to the level of neural activity in a brain region, specifically manifested as the relative change in the concentration of oxyhemoglobin and deoxyhemoglobin, which can be obtained through functional near-infrared spectroscopy brain imaging technology; the abnormal discharge index of electroencephalography (EEG) is a comprehensive indicator that quantifies the pathological electrical activity present in scalp EEG signals, used to characterize the severity and frequency of pathological and synchronized abnormal excitation of brain neurons, which can be obtained through multi-lead high-density EEG equipment and subsequent signal processing and pattern recognition algorithms; the photoplethysmography index of the heart is a quantitative indicator reflecting cardiovascular autonomic nervous activity and anxiety state by measuring the tiny pulse vibrations of blood vessels in the fingers or earlobes, which can be obtained through photoplethysmography sensors; the transient amplitude of skin conductance reflects the rapid change in skin conductance in a short period of time, and is a direct indicator of sympathetic nervous activity, which can be obtained through skin conductance sensors; the pupillary dispersion deviation is a parameter reflecting visual attentional distraction or saccade disorder caused by anxiety, which can be obtained through high frame rate eye trackers or video eye tracking; respiratory rate is the respiratory rhythm, which can be obtained through chest strap strain sensors or infrared imaging.

[0032] The preset observation duration is a time window for stable sampling of physiological parameters such as abnormal discharge index and blood oxygen saturation in children before intervention. It depends on the natural fluctuation cycle of the physiological signals of anxiety and the sensor sampling rate, and is usually set between 30 seconds and 2 minutes. In this embodiment, it is set to 60 seconds, which can effectively filter out physiological fluctuations caused by brief curiosity or slight tension and accurately trigger the judgment process of clinically significant anxiety state. The preset abnormal threshold is a critical value for judging whether the physiological state has entered the "abnormal" range. It depends on the baseline physiological data of the target population and clinical experience standards, and is usually set between 0.35 and 0.55. In this embodiment, it is set to 0.4, which can achieve a balance between sensitivity and specificity, so that the system can identify the increase in anxiety in time but avoid misjudging normal physiological fluctuations. The preset historical period is a time window for counting the number of corrections for different children in multiple rounds of virtual training intervention. It depends on the stability of the preoperative anxiety fluctuations of children in the same batch, and is usually set between 3 and 10 complete intervention cycles. In this embodiment, it is set to 5 times, which can identify the temporal change trend of the number of corrections in the historical records of individuals, thereby realizing dynamic adaptive adjustment of parameters.

[0033] By employing multi-parameter real-time monitoring and dynamic closed-loop intervention, a comprehensive quantitative assessment of preoperative anxiety in children is achieved. Specifically, the intervention intensity is automatically adjusted based on the degree of abnormality, and threshold parameters are dynamically optimized using historical data to ensure personalized and adaptive intervention, effectively avoiding under- or over-intervention. Pre-set observation durations filter short-term physiological fluctuations, improving accuracy and automating the entire intervention decision-making process. This helps children quickly reach a preoperative preparation state, optimizes the surgical procedure, and enhances the safety and reliability of preoperative intervention. It effectively solves the problems of delayed intervention effects and low accuracy caused by using static threshold comparisons and isolated parameter analysis.

[0034] Specifically, the state determination module includes: The extraction unit is used to extract the index value of the abnormal discharge index corresponding to each moment within the preset observation period to obtain the index time series vector, and to extract the blood oxygen value of the blood oxygen saturation corresponding to each moment within the preset observation period to obtain the blood oxygen time series vector. A local construction unit, connected to the extraction unit, is used to determine local index elements based on the absolute value of the difference between each index value in the exponential time series vector and each index value in the preset exponential vector to obtain an exponential local matrix, and to determine local blood oxygen elements based on the absolute value of the difference between each blood oxygen value in the blood oxygen time series vector and each blood oxygen value in the preset blood oxygen vector to obtain a blood oxygen local matrix. An accumulation building unit, connected to the local building unit, is used to select the minimum distance from each local index element in the exponential local matrix to the starting local index element to obtain an exponential accumulation matrix, and to select the minimum distance from each local blood oxygen element in the blood oxygen local matrix to the starting local blood oxygen element to obtain a blood oxygen accumulation matrix. A state determination unit, connected to the cumulative construction unit, is used to determine the abnormality similarity based on the exponential cumulative matrix and the blood oxygen cumulative matrix, and to determine whether the target state is abnormal based on the abnormality similarity and the preset abnormality threshold, so as to obtain a state abnormality result.

[0035] In this embodiment, the process of selecting the minimum distance from each element in the exponential local matrix to the starting element to obtain the exponential cumulative matrix is ​​as follows: First, the starting element of the exponential local matrix is ​​used as the starting element of the exponential cumulative matrix. For the first row and first column of the exponential cumulative matrix, the value of each element is equal to the sum of the values ​​of the corresponding elements in the exponential local matrix and the values ​​of the preceding elements in the corresponding position of the exponential cumulative matrix. For elements in other positions, the value is equal to the sum of the value of that element in the exponential local matrix and the minimum value among the three neighboring elements to its left, above, and upper left in the exponential cumulative matrix.

[0036] In this embodiment, the process of selecting the minimum distance from each element in the local blood oxygen matrix to the starting element to obtain the cumulative blood oxygen matrix is ​​as follows: First, the starting element of the local blood oxygen matrix is ​​used as the starting element of the cumulative blood oxygen matrix. For the first row and first column of the cumulative blood oxygen matrix, the value of each element is equal to the sum of the value of the corresponding element in the local blood oxygen matrix and the value of the preceding element in the corresponding position of the cumulative blood oxygen matrix. For the elements in other positions, the value is equal to the sum of the value of that element in the local blood oxygen matrix and the minimum value among the three neighboring elements to its left, above, and upper left in the cumulative blood oxygen matrix.

[0037] In this embodiment, the preset index vector is a reference sequence established based on the characteristics of the hand-brain electroencephalogram (EEG) discharge index in a child's non-anxious state. It is usually set between 0.1 and 0.3. In this embodiment, 60 sampling points are used. The specific values ​​of each sampling point are generated according to a normal distribution within this range, with a mean of 0.18 and a standard deviation of 0.04. This can serve as an individualized or standardized comparison benchmark, allowing the system to quantify the degree of deviation from the normal or baseline state by calculating the difference between real-time data and this vector. The preset blood oxygen vector is based on the prefrontal cortex blood oxygen saturation data of healthy children in a resting state. Its blood oxygen value range is usually set between 65% and 80%. In this embodiment, it also includes 60 sampling points. The values ​​are generated according to a uniform distribution within this range, with a mean of 72% and a standard deviation of 3%. This can provide a stable blood oxygen metabolism baseline reference, which can be used to sensitively detect increased cortical activity or perfusion changes caused by states such as anxiety.

[0038] By employing a dynamic time warping algorithm, real-time collected abnormal discharge index and blood oxygen saturation time-series data are dynamically matched with a preset vector. Through the construction of local and cumulative distance matrices, the degree of difference between the real-time physiological sequence and the standard pattern is accurately quantified. This overcomes the insensitivity of traditional static threshold methods to temporal features, effectively identifying physiological fluctuation patterns unique to anxiety, significantly improving the accuracy of abnormal state assessment, and providing a more reliable basis for subsequent interventions. Overall, by comprehensively capturing the dynamic characteristics of preoperative anxiety in children through time-series data, the accuracy and response speed of assessment are improved, continuously enhancing the ability to identify complex anxiety states and the adaptability of intervention strategies.

[0039] Please continue reading. Figure 2 As shown, this is a logic diagram for determining an abnormal target state by the state determination unit in this embodiment. In this embodiment, the state determination unit includes: The distance calculation subunit is used to calculate the minimum cumulative distance from the local index element at the lower right corner of the exponential cumulative matrix to the starting local index element, so as to obtain the exponential cumulative distance; and to calculate the minimum cumulative distance from the local blood oxygen element at the lower right corner of the blood oxygen cumulative matrix to the starting local blood oxygen element, so as to obtain the blood oxygen cumulative distance. A similarity calculation subunit, connected to the distance calculation subunit, is used to calculate exponential similarity based on the exponential cumulative distance, where A = 1 / (1+a), where A is the exponential similarity and a is the exponential cumulative distance; and to calculate blood oxygen similarity based on the blood oxygen cumulative distance, where B = 1 / (1+b), where B is the blood oxygen similarity and b is the blood oxygen cumulative distance. An anomaly determination subunit, connected to the similarity calculation subunit, is used to perform a weighted summation calculation on the exponential similarity and the blood oxygen similarity to obtain the anomaly similarity, and to determine the target state anomaly when the anomaly similarity is greater than the preset anomaly threshold to obtain the state anomaly result.

[0040] In this embodiment, during the weighted summation of the exponential similarity and the blood oxygen similarity, the weight corresponding to the exponential similarity is used to reflect the importance of the abnormal discharge index in the abnormality determination of the target state in the abnormality similarity calculation. It depends on the sensitivity and stability of the abnormal discharge index in the preoperative anxiety manifestations of children, and is usually set between 0.4 and 0.6. In this embodiment, it is set to 0.5 to ensure that the frequency change has a moderate impact on the abnormality determination without being overemphasized. The weight corresponding to the blood oxygen similarity is used to reflect the importance of blood oxygen saturation in the abnormality determination of the target state in the abnormality similarity calculation. It depends on the fluctuation range of blood oxygen saturation in the anxiety state and the determination sensitivity, and is usually set between 0.4 and 0.6. In this embodiment, it is set to 0.5 to ensure that the blood oxygen similarity has a moderate impact on the abnormality determination without being overemphasized.

[0041] By calculating the minimum cumulative distance between the exponential cumulative matrix and the blood oxygen cumulative matrix, the time series of abnormal discharge index and blood oxygen saturation can be dynamically aligned, quantifying the deviation of children's physiological changes from norm references during the preoperative observation period, thereby obtaining the exponential cumulative distance and blood oxygen cumulative distance. Based on this, the distance is converted into a normalized similarity index, achieving continuous and quantifiable abnormal characterization. Furthermore, by weighted summation of exponential similarity and blood oxygen similarity, a comprehensive abnormality similarity is generated, enabling the fusion and judgment of multi-dimensional physiological signals. A preset abnormality threshold is used to determine the presence of abnormal states, thus avoiding the limitations of single-parameter judgment. This dynamically and accurately reflects subtle changes in children's preoperative anxiety state, enhancing the sensitivity and stability of the judgment, and improving the automation, reliability, and efficiency of preoperative intervention.

[0042] Please continue reading. Figure 3 As shown, this is a logic diagram for determining abnormal anxiety states by the severity determination module in this embodiment. In this embodiment, the severity determination module includes: The determination unit is used to determine an abnormal anxiety state when the abnormal discharge index is greater than a preset index threshold, the photovolume vibration index is less than a preset vibration threshold, and the respiratory rate is greater than a preset respiratory threshold. A deviation calculation unit, connected to the determination unit, is used to calculate the relative deviation between the abnormal discharge index and the preset index threshold to obtain the index deviation, and to calculate the relative deviation between the photovolume vibration index and the preset vibration threshold to obtain the vibration deviation, and to calculate the relative deviation between the respiratory rate and the preset respiratory threshold to obtain the respiratory deviation. A degree determination unit, connected to the deviation calculation unit, is used to determine the degree of anxiety based on the index deviation, the vibration deviation, and the breathing deviation, in order to obtain the state abnormality degree.

[0043] The preset index threshold is a critical value used to determine whether abnormal EEG discharge activity has reached an anxiety-related abnormal level. It depends on the clinical EEG data of the target population and the pathophysiological correlation of the anxiety state, and is usually set between 0.20 and 0.28. In this embodiment, it is set to 0.25, which can indicate that when the abnormal discharge index exceeds this threshold, the abnormal electrical activity of the brain has entered an abnormal range that may be related to the anxiety state. The preset vibration threshold is a reference value used to determine whether the cardiac optical volume vibration index is abnormal. It depends on the cardiovascular autonomic nerve fluctuation characteristics of children in a non-anxious state, and is usually set between 0.2 and 0.5. In this embodiment, it is set to 0.35, which can reflect the weakening of vascular pulsation caused by anxiety. The preset respiratory threshold is a reference value used to determine whether the respiratory rate is abnormal. It depends on the preoperative norm respiratory rhythm of children, and is usually set between 20 breaths / minute and 30 breaths / minute. In this embodiment, it is set to 25 breaths / minute, which can identify anxiety manifestations with increased respiratory rate.

[0044] By combining the analysis of three types of physiological indicators, a refined assessment of children's preoperative anxiety state can be achieved. When the abnormal discharge index increases, the photovolume vibration index decreases, and the respiratory rate increases, an abnormal anxiety state can be promptly identified, effectively avoiding misjudgments that may arise from relying on a single physiological indicator. Based on this, the deviation of each indicator from preset thresholds is calculated to quantify the magnitude of the anxiety state, and the degree of anxiety is determined based on the relative deviation. This comprehensively reflects the contribution of different physiological signals to the overall anxiety state, generating a state abnormality score, thus providing a scientific and quantitative basis for intervention. Real-time, dynamic monitoring of the anxiety state is possible, enabling intervention strategies to be adaptively adjusted based on individual child physiological feedback, improving the intervention's targeting and responsiveness.

[0045] Specifically, the degree determination unit includes: The degree calculation subunit is used to perform a weighted summation of the index deviation, the vibration deviation, and the breathing deviation to obtain the degree of anxiety; A degree determination subunit, which is connected to the degree calculation subunit, is used to calculate the relative deviation between the anxiety level and the preset anxiety threshold when the anxiety level is greater than the preset anxiety threshold, so as to obtain the state abnormality degree.

[0046] In this embodiment, during the weighted summation of the index deviation, vibration deviation, and respiratory deviation, the weight corresponding to the index deviation is an importance coefficient assigned to the abnormal EEG discharge index deviation when calculating the anxiety level through weighted summation. This weight depends on the correlation strength between each physiological parameter and the anxiety state, as well as the reliability of its signal, and is typically set between 0.3 and 0.5. In this embodiment, it is set to 0.4, ensuring that the judgment of the anxiety state of patients with brain diseases focuses more on direct evidence of brain activity. The weight corresponding to the vibration deviation is used to calculate the contribution of the optical volume vibration index to the anxiety level, depending on the influence of cardiovascular fluctuations in anxiety determination. This weight is typically set between 0.2 and 0.4, and in this embodiment, it is set to 0.3, reflecting the role of changes in vascular pulsation. The weight corresponding to the respiratory deviation is used to calculate the contribution of respiratory rate to the anxiety level, depending on the sensitivity of respiration to the anxiety state. This weight is typically set between 0.2 and 0.4, and in this embodiment, it is set to 0.3, reasonably reflecting the degree of abnormality in respiratory rhythm.

[0047] The preset anxiety threshold is a reference value used to determine whether the overall anxiety level has reached an abnormal state. It depends on the combined performance of the abnormal discharge index, photovolume vibration index and respiratory rate, and is usually set between 0.5 and 0.7. In this embodiment, it is set to 0.6, which can accurately trigger the determination of the abnormality of the state.

[0048] By weighted and integrated deviations in the abnormal discharge index, photovolume vibration index, and respiratory index, a quantitative assessment of preoperative anxiety levels in children about to undergo neurosurgical procedures is achieved. This reflects the relative contribution of each physiological indicator to the overall anxiety state, avoiding the excessive influence of a single indicator on the assessment results. When the anxiety level exceeds a preset threshold, an abnormality level is generated through relative deviations, achieving a continuous and quantitative representation of the anxiety state. This reflects the dynamic changes in the child's physiological and psychological state, allowing intervention strategies to adaptively adjust according to individual differences, improving the targeting and response speed of interventions. Simultaneously, quantifying the relationship between anxiety levels and abnormal states enhances the scientific rigor, controllability, and efficiency of preoperative interventions.

[0049] Specifically, the intervention module includes: The change calculation unit is used to determine the intervention intensity based on the state anomaly degree and the preset rule base, and after the intervention is initiated, calculate the relative deviation between the transient amplitude of the skin conductance and the preset amplitude threshold at each time within the preset intervention duration to obtain several skin conductance deviations; calculate the relative deviation between the dispersion deviation degree and the preset dispersion threshold at each time within the preset intervention duration to obtain several dispersion deviations; and calculate the relative deviation between the respiratory rate and the preset respiratory rate threshold at each time within the preset intervention duration to obtain several respiratory rate deviations. A trend statistics unit, connected to the change calculation unit, is used to calculate the proportion of the number of times when the skin conductance deviation is less than a preset change threshold, the dispersion deviation is less than a preset change threshold, and the call frequency deviation is less than a preset change threshold, relative to the total number of times of the preset intervention duration, so as to obtain the trend consistency. A collaborative statistics unit, connected to the change calculation unit, is used to calculate the proportion of the number of times when the skin conductance deviation is greater than a preset deflection threshold, the dispersion deviation is greater than a preset dispersion threshold, and the respiratory frequency deviation is greater than a preset respiratory deviation threshold, relative to the total number of times of the preset intervention duration, so as to obtain the degree of collaborative improvement. An intervention unit, which is connected to the trend statistics unit and the collaborative statistics unit respectively, is used to calculate the weighted geometric average of the trend consistency degree and the collaborative improvement degree to obtain the intervention response degree, where D=(T^β×C^γ)^[1 / (β+γ)], where D is the intervention response degree, T is the trend consistency degree, C is the collaborative improvement degree, β is the preset trend weight, and γ is the preset collaborative weight.

[0050] The preset intervention duration is a parameter used to control the duration of the intervention. It typically depends on the specific requirements of the intervention and the condition of the target patient, and is usually set between 5 and 20 minutes. In this embodiment, it is set to 10 minutes, allowing for timely adjustment of the intervention intensity based on actual anxiety responses. The preset amplitude threshold is a reference value used to measure changes in the amplitude of skin conductance transients. It is usually related to the range of physiological response fluctuations in children and depends on the natural fluctuations of skin conductance responses. It is usually set between 5 μS and 50 μS, and in this embodiment, it is set to 20 μS, ensuring accurate capture of improvements in skin conductance responses during intervention. The preset dispersion threshold is a reference value used to measure the deviation of the eyeball's dispersion from the normal range, and is usually set between 0.1 and 0.5. In this embodiment, it is set to 0.3. It can effectively identify the ocular manifestations of anxiety improvement during intervention; the preset respiratory rate threshold is a reference value for assessing respiratory rate, usually depending on the child's physiological respiratory rhythm, typically set between 10 and 40 breaths / minute, and in this embodiment set to 20 breaths / minute, which can be used to identify the increased respiratory rate caused by anxiety; the preset change threshold is set to 0, in which case the deviation calculation is based on the zero standard of change amplitude, that is, when the changes in skin conductance deviation, dispersion deviation, and respiratory rate deviation all show negative changes, it is considered a signal that the anxiety state is improving, which can effectively screen out the moments when the deviations of skin conductance, dispersion, and respiratory rate are gradually decreasing during the intervention process; the preset electrical bias threshold is used to determine whether the decrease in skin conductance transient amplitude reaches the threshold. The absolute magnitude criterion for significant improvement depends on the baseline amplitude of the eye movement conductance and the sensor resolution, and is typically set between 5 μS and 20 μS. In this embodiment, it is set to 10 μS, which can screen out moments when the decrease in eye movement conductance during the intervention is sufficient to reflect a significant reduction in sympathetic activation. The preset divergence threshold is a relative magnitude criterion used to determine whether the decrease in eye movement divergence has reached a significant improvement. It depends on the accuracy of eye movement measurement and the individual fixation baseline, and is typically set between 0.05 and 0.30. In this embodiment, it is set to 0.10, which can identify time points where fixation concentration has clinically significant improvement. The preset respiratory deviation threshold is an absolute magnitude criterion used to determine whether the decrease in respiratory rate has reached a significant improvement. It depends on the resting respiratory baseline of the child's age group and the clinically acceptable... The fluctuation range of the respiratory rhythm is typically set between 1 and 6 breaths per minute, and in this embodiment, it is set to 3 breaths per minute, which can identify the moment when the respiratory rhythm reliably slows down within a short-term intervention. The preset trend weight is a weighting coefficient used to weight the trend consistency when calculating the intervention response, reflecting the impact of trend consistency on the intervention effect. It is typically set between 0.1 and 1.0, and in this embodiment, it is set to 0.5, which can balance the importance of trend consistency and synergistic improvement in the intervention response. The preset synergistic weight is a weighting coefficient used to weight the synergistic improvement when calculating the intervention response, and it is typically set between 0.1 and 1.0. In this embodiment, it is set to 0.5, which can ensure that the synergistic improvement of various physiological parameters can have a balanced impact on the intervention response.

[0051] In this embodiment, the preset rule base is used by the intervention module to map state anomaly levels to specific intervention configurations, such as intervention intensity. Its construction first integrates classic physiological thresholds that are significantly correlated with multiple physiological indicators and anxiety levels, as well as grading standards from preoperative anxiety research in children, constructing a structured mapping relationship of "state anomaly level—physiological deviation level—intervention configuration." Based on this, the system also uses pattern recognition and cluster analysis, based on a large number of preoperative intervention samples in children, to extract typical multi-parameter collaborative change patterns in the anxiety rise, maintenance, and relief stages, forming intervention strategy items applicable to different ages, physical conditions, and anxiety response patterns, strictly adhering to the principle of "quantifying intensity first, then matching the scenario." The rule base adopts a dual expression method of production rules and data statistical models: on the one hand, it solidifies interpretable decision logic with rules in the form of "IF state anomaly level ∈ a certain interval THEN, use a specific intervention intensity / stimulus rhythm"; on the other hand, it obtains dynamic threshold adjustment factors through modeling the distribution of training data, enabling the intervention configuration to be adaptively fine-tuned according to the actual intervention situation. During system runtime, the rule base maps the anomaly level of the input state to its corresponding intervention level and outputs the appropriate intervention intensity for the current child. Based on this intensity level, it intelligently calls the optimal combination of scenarios and initialization parameters from a pre-built and continuously optimized virtual training scenario library. In terms of its operational mechanism, the rule base adopts a hybrid architecture of "generative rules + dynamic adapter": the base layer consists of explicit rules such as "IF intensity = a certain level THEN call scenario A, set basic parameter set B"; the execution layer embeds a real-time fine-tuning algorithm that dynamically optimizes stimulus details within the scenario, such as adjusting the rhythm of brightness changes in the virtual environment and the gradient of task difficulty, based on real-time feedback on intervention responsiveness within a given intensity framework. This achieves refined individual adaptation while maintaining consistency in the intervention direction. This design ensures that the closed loop from physiological assessment to immersive intervention possesses both the reliability of clinical decision-making and the data-driven flexibility for personalization.

[0052] By employing dynamic deviation analysis and composite statistical methods across multiple physiological indicators, a refined quantitative assessment of the intervention's effectiveness was achieved, thereby enhancing the system's sensitivity and reliability in monitoring the anxiety improvement process. By tracking the improvement trends of the three indicators at each time step in the form of relative deviations, subtle physiological changes during the intervention process could be continuously monitored. Furthermore, the stability of the synchronous decline in overall physiological load was measured by the proportion of times with deviations less than zero, reflecting whether the intervention was consistently effective. In addition, the proportion of times when all three indicators achieved significant improvement was further identified to capture the synergistic physiological recovery effect of the intervention during the high-intensity phase. A weighted geometric average was then used to integrate long-term trends and transient synergistic improvements into an intervention responsiveness score, avoiding the dominance of a single indicator and reflecting the comprehensive effectiveness of the intervention in actual anxiety relief.

[0053] Specifically, the determination module includes: An adjustment unit is used to increase the intervention intensity when the intervention response is less than a preset response threshold; A response determination unit, connected to the adjustment unit, is used to determine the intervention response result when the intervention response degree, which is re-determined after increasing the intervention intensity, is greater than the preset response threshold. A determination unit, connected to the response determination unit, is used to determine whether the preoperative state target has been met based on the abnormal discharge index and blood oxygen saturation of the target when the intervention response result is determined, so as to generate a stop intervention signal.

[0054] The preset response threshold is the minimum acceptable standard for judging whether virtual training intervention produces the expected effect. It depends on the minimum clinical requirements for the intervention effect and the stability of the system measurement. It is usually set between 0.5 and 0.7. In this embodiment, it is set to 0.6, which can effectively distinguish whether the intervention has reached the basic effective level and provide a clear basis for whether the intervention intensity needs to be adjusted.

[0055] By establishing a closed-loop control mechanism of "response degree, intensity adjustment, and physiological verification", the intervention intensity is automatically increased when insufficient intervention response is detected. Once the response reaches the target, the key physiological indicators of abnormal discharge index and blood oxygen saturation are immediately verified. Through dynamic adjustment and dual verification mechanism, the problems of fixed intervention intensity and single evaluation indicators in traditional methods are effectively overcome. This ensures that the intervention measures are always in the optimal intensity range, and the authenticity and stability of anxiety relief can be finally confirmed through physiological parameters, thereby significantly improving the reliability and success rate of preoperative psychological preparation.

[0056] Please continue reading. Figure 4 As shown, this is the logic diagram for determining whether the preoperative condition meets the standards by the determination unit in this embodiment. In this embodiment, the determination unit includes: The frequency determination subunit is used to determine that the abnormal discharge index is normal when the abnormal discharge index is less than the preset index threshold, so as to obtain a normal discharge result. An intensity determination subunit, connected to the frequency determination subunit, is used to determine that the preoperative state has met the standard when the blood oxygen saturation is greater than a preset saturation threshold, based on the normal discharge result, so as to generate a stop intervention signal.

[0057] The preset saturation threshold is a critical value for determining whether the prefrontal cortex blood oxygen saturation has returned to a stable relaxed state. It depends on the typical cortical blood oxygen saturation baseline of the target population in a relaxed state and is usually set between 72% and 78%. In this embodiment, it is set to 75%, which can further confirm that the brain's metabolism and blood flow have also returned to stability after the brain electrical activity has returned to normal, thus serving as a basis for stopping intervention.

[0058] By establishing a dual verification mechanism of abnormal discharge index and blood oxygen saturation, the two key physiological indicators are evaluated as a final assessment after the intervention response is achieved. This cross-validation method effectively overcomes the accidental risks that may occur with single parameter judgment. It ensures that anxiety relief is manifested in the motor dimension as a decrease in muscle tension, i.e., a reduction in tremor frequency, and in the vascular dimension as an improvement in peripheral circulation, i.e., the recovery of blood oxygen saturation. This significantly improves the accuracy and reliability of the preoperative condition assessment and provides dual protection for the safe implementation of surgery.

[0059] Specifically, the number of corrections is determined based on the number of times the intervention intensity is corrected according to the intervention responsiveness before the stop intervention signal is generated, as recorded by the recording module.

[0060] By quantifying the number of intensity corrections during the intervention process, a key indicator is provided for assessing the individual's anxiety resistance and the effectiveness of the intervention strategy. The more corrections, the worse the stability of the anxiety state. This not only enables refined quantitative management of the intervention process, but also provides data support for the system to adaptively optimize threshold parameters, significantly improving the system's intelligence level and intervention accuracy.

[0061] Specifically, the adjustment module includes: The correction analysis unit is used to calculate the linear regression slope of the number of corrections corresponding to each time within the preset historical period, so as to obtain the correction slope. A fluctuation calculation unit is used to calculate the standard deviation of the number of corrections corresponding to each time within the preset historical period, so as to obtain the corrected fluctuation value. A threshold adjustment unit, which is connected to the correction analysis unit and the fluctuation calculation unit respectively, is used to increase the preset abnormal threshold when the correction slope is greater than the preset slope threshold and the correction fluctuation value is less than the preset fluctuation threshold. Here, G' = G + h × |H - H0| / (H + H0) + m × |M - M0| / (M + M0), where G' is the adjusted preset abnormal threshold, G is the original preset abnormal threshold, h is the preset threshold slope adjustment coefficient, H is the correction slope, H0 is the preset slope threshold, m is the preset threshold fluctuation adjustment coefficient, M is the correction fluctuation value, and M0 is the preset fluctuation threshold. The duration adjustment unit is connected to the correction analysis unit and the fluctuation calculation unit respectively, and is used to increase the preset observation duration when the correction slope is less than or equal to the preset slope threshold and the correction fluctuation value is greater than or equal to the preset fluctuation threshold. Here, N'=N+p×|H-H0| / (H+H0)+q×|M-M0| / (M+M0), where N' is the adjusted preset observation duration, N is the original preset observation duration, p is the preset duration slope adjustment coefficient, and q is the preset duration fluctuation adjustment coefficient.

[0062] The preset slope threshold is a critical slope value used to determine whether the number of corrections shows a continuous upward trend. It depends on the system's requirements for intervention stability and the distribution characteristics of historical data, and is typically set between 0.1 and 0.3. In this embodiment, it is set to 0.2, which can effectively identify continuous growth patterns that require adjustment of the abnormal threshold. The preset fluctuation threshold is a critical variation value used to determine whether the fluctuation of the number of corrections is too large. It depends on the system's requirements for data stability and the normal operating fluctuation range, and is typically set between 0.15 and 0.35. In this embodiment, it is set to 0.25, which can reliably identify abnormal fluctuation states that require extended observation time. The preset threshold slope adjustment coefficient is a coefficient that controls the influence of the correction slope on the adjustment range of the abnormal threshold. It depends on the adjustable range of the abnormal threshold and the system stability requirements, and is typically set between 0.05 and 0.15. In this embodiment, it is set to 0.1, which can reasonably adjust the slope deviation on the threshold adjustment. The contribution of the data acquisition process is as follows: The preset threshold fluctuation adjustment coefficient controls the influence of the corrected fluctuation value on the adjustment range of the abnormal threshold. It depends on the sensitivity and fluctuation tolerance of the abnormal threshold and is usually set between 0.02 and 0.08. In this embodiment, it is set to 0.05, which can moderately balance the role of fluctuation factors in threshold adjustment. The preset duration slope adjustment coefficient controls the influence of the corrected slope on the adjustment range of the observation duration. It depends on the scalability range and real-time requirements of the observation duration and is usually set between 0.1 and 0.3. In this embodiment, it is set to 0.2, which can appropriately reflect the weight of the slope factor in duration adjustment. The preset duration fluctuation adjustment coefficient controls the influence of the corrected fluctuation value on the adjustment range of the observation duration and depends on the balance between the stability requirements and efficiency of data acquisition. It is usually set between 0.3 and 0.7. In this embodiment, it is set to 0.5, which can effectively enhance the system's response sensitivity to fluctuation characteristics.

[0063] By intelligently analyzing the temporal characteristics of the number of corrections, a parameter optimization mechanism based on slope-fluctuation dual-modal analysis was established. Specifically, when the number of corrections exhibits a high slope and low fluctuation characteristic, the system's anomaly judgment criteria are identified as overly sensitive, and an anomaly threshold is increased through an adaptive formula to reduce false alarms. When it exhibits a low slope and high fluctuation characteristic, baseline instability caused by insufficient observation time is diagnosed, and the observation time is dynamically extended to improve data reliability. This self-optimization system based on dynamic feedback overcomes the limitations of fixed parameter systems in the face of individual differences and state changes, enabling the system to continuously iterate and upgrade, significantly improving the accuracy of personalized interventions and the long-term adaptability of the system.

[0064] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A virtual training system for anxiety disorders based on multiple parameters, characterized in that, include: The acquisition module is used to acquire in real time the target's prefrontal cortex blood oxygen saturation, abnormal discharge index of electroencephalography, optical volume vibration index of the heart, transient amplitude of skin conductance, dispersion deviation of pupils and respiratory rate within a preset observation period. The state determination module is used to determine whether the state is abnormal based on the time-series characteristics of the abnormal discharge index and the blood oxygen saturation and a preset abnormal threshold, so as to obtain a state abnormality result. The degree determination module is used to determine the degree of anxiety based on the state abnormality result, according to the abnormal discharge index, the photovolume vibration index and the respiratory rate, so as to obtain the state abnormality degree. An intervention module is used to initiate intervention based on the intervention intensity corresponding to the state abnormality, and to determine the state change trend and improvement degree based on the skin conductance transient amplitude, the dispersion deviation and the respiratory rate, so as to determine the intervention response degree; The determination module is used to adjust the intervention intensity based on the intervention response rate, and to determine whether the preoperative status meets the standard based on the threshold comparison result of the intervention response rate, the abnormal discharge index and the blood oxygen saturation after adjusting the intervention intensity, so as to generate a stop intervention signal; A recording module is used to record the number of times the intervention intensity is corrected based on the intervention responsiveness before the stop intervention signal is generated, so as to obtain the number of corrections; The adjustment module is used to adjust the preset anomaly threshold or the preset observation duration based on the temporal characteristics of the number of corrections within a preset historical period.

2. The virtual training system for anxiety disorders based on multiple parameters according to claim 1, characterized in that, The status determination module includes: An extraction unit is used to determine an index time series vector based on the abnormal discharge index within the preset observation period, and to determine a blood oxygen time series vector based on the blood oxygen saturation within the preset observation period. A local construction unit, connected to the extraction unit, is used to determine local index elements based on the exponential time series vector and a preset exponential vector to obtain an exponential local matrix, and to determine local blood oxygen elements based on the blood oxygen time series vector and a preset blood oxygen vector to obtain a blood oxygen local matrix. An accumulation building unit, connected to the local building unit, is used to build an exponential accumulation matrix based on the distance between the local exponential element and the starting local exponential element, and to build a blood oxygen accumulation matrix based on the distance between the local blood oxygen element and the starting local blood oxygen element. A state determination unit, connected to the cumulative construction unit, is used to determine the abnormality similarity based on the exponential cumulative matrix and the blood oxygen cumulative matrix, and to determine whether the target state is abnormal based on the abnormality similarity and the preset abnormality threshold, so as to obtain a state abnormality result.

3. The virtual training system for anxiety disorders based on multiple parameters according to claim 2, characterized in that, The state determination unit includes: A distance calculation subunit is used to obtain the exponential cumulative distance based on the distance between the beginning and end of the local exponential elements in the exponential cumulative matrix, and to obtain the blood oxygen cumulative distance based on the distance between the beginning and end of the local blood oxygen elements in the blood oxygen cumulative matrix. A similarity calculation subunit, connected to the distance calculation subunit, is used to calculate exponential similarity based on the exponential cumulative distance, and to calculate blood oxygen similarity based on the blood oxygen cumulative distance; An anomaly determination subunit, connected to the similarity calculation subunit, is used to perform a weighted summation calculation on the exponential similarity and the blood oxygen similarity to obtain the anomaly similarity, and to obtain a state anomaly result based on the comparison result of the anomaly similarity and the preset anomaly threshold.

4. The virtual training system for anxiety disorders based on multiple parameters according to claim 5, characterized in that, The degree determination module includes: The determination unit is used to determine an abnormal anxiety state when the abnormal discharge index is greater than a preset index threshold, the photovolume vibration index is less than a preset vibration threshold, and the respiratory rate is greater than a preset respiratory threshold. A deviation calculation unit, connected to the determination unit, is used to calculate the relative deviation between the abnormal discharge index and the preset index threshold to obtain the index deviation, and to calculate the relative deviation between the photovolume vibration index and the preset vibration threshold to obtain the vibration deviation, and to calculate the relative deviation between the respiratory rate and the preset respiratory threshold to obtain the respiratory deviation. A degree determination unit, connected to the deviation calculation unit, is used to determine the degree of anxiety based on the index deviation, the vibration deviation, and the breathing deviation, in order to obtain the state abnormality degree.

5. The virtual training system for anxiety disorders based on multiple parameters according to claim 4, characterized in that, The degree determination unit includes: The degree calculation subunit is used to perform a weighted summation of the index deviation, the vibration deviation, and the breathing deviation to obtain the degree of anxiety; A degree determination subunit, which is connected to the degree calculation subunit, is used to obtain the state abnormality degree based on the comparison result between the anxiety degree and the preset anxiety threshold.

6. The virtual training system for anxiety disorders based on multiple parameters according to claim 5, characterized in that, The intervention module includes: The change calculation unit is used to determine the intervention intensity based on the state abnormality degree and the preset rule base. After the intervention is initiated, it determines several skin conductance deviations based on the skin conductance transient amplitude and the preset amplitude threshold at each time within the preset intervention duration, and determines several dispersion deviations based on the dispersion deviation degree and the preset dispersion threshold at each time within the preset intervention duration, and determines several respiratory rate deviations based on the respiratory rate and the preset respiratory rate threshold at each time within the preset intervention duration. A trend statistics unit, connected to the change calculation unit, is used to calculate the proportion of the number of times when the skin conductance deviation is less than a preset change threshold, the dispersion deviation is less than a preset change threshold, and the call frequency deviation is less than a preset change threshold, relative to the total number of times of the preset intervention duration, so as to obtain the trend consistency. A collaborative statistics unit, connected to the change calculation unit, is used to calculate the proportion of the number of times when the skin conductance deviation is greater than a preset deflection threshold, the dispersion deviation is greater than a preset dispersion threshold, and the respiratory frequency deviation is greater than a preset respiratory deviation threshold, relative to the total number of times of the preset intervention duration, so as to obtain the degree of collaborative improvement. An intervention unit, which is connected to the trend statistics unit and the collaborative statistics unit respectively, is used to calculate the weighted geometric mean of the trend consistency degree and the collaborative improvement degree to obtain the intervention response degree.

7. The virtual training system for anxiety disorders based on multiple parameters according to claim 6, characterized in that, The determination module includes: An adjustment unit is used to increase the intervention intensity when the intervention response is less than a preset response threshold; A response determination unit, connected to the adjustment unit, is used to determine the intervention response result when the intervention response degree, which is re-determined after increasing the intervention intensity, is greater than the preset response threshold. A determination unit, connected to the response determination unit, is used to determine whether the preoperative state target has been met based on the abnormal discharge index and blood oxygen saturation of the target when the intervention response result is determined, so as to generate a stop intervention signal.

8. The virtual training system for anxiety disorders based on multiple parameters according to claim 7, characterized in that, The determination unit includes: The frequency determination subunit is used to obtain the normal discharge result based on the comparison result between the abnormal discharge index and the preset index threshold. An intensity determination subunit, connected to the frequency determination subunit, is used to generate a stop intervention signal based on the comparison between the blood oxygen saturation and a preset saturation threshold, according to the normal discharge result.

9. The virtual training system for anxiety disorders based on multiple parameters according to claim 8, characterized in that, The number of corrections is determined based on the number of times the intervention intensity was corrected according to the intervention responsiveness before the stop intervention signal was generated, as recorded by the recording module.

10. The virtual training system for anxiety disorders based on multiple parameters according to claim 9, characterized in that, The adjustment module includes: The correction analysis unit is used to calculate the linear regression slope of the number of corrections corresponding to each time within the preset historical period, so as to obtain the correction slope. A fluctuation calculation unit is used to calculate the standard deviation of the number of corrections corresponding to each time within the preset historical period, so as to obtain the corrected fluctuation value. A threshold adjustment unit, which is connected to the correction analysis unit and the fluctuation calculation unit respectively, is used to adjust the preset abnormal threshold according to the comparison result of the correction slope and the preset slope threshold and the comparison result of the correction fluctuation value and the preset fluctuation threshold. The duration adjustment unit is connected to the correction analysis unit and the fluctuation calculation unit respectively, and is used to adjust the preset observation duration according to the comparison results of the correction slope and the preset slope threshold and the comparison results of the correction fluctuation value and the preset fluctuation threshold.

Images