A postoperative psychological state evaluation system and method based on MPNFS theory

Abstract

The present application belongs to the technical field of postoperative psychological evaluation, and particularly relates to a postoperative psychological state evaluation system and method based on MPNFS theory. The present application effectively improves the accuracy and reliability of evaluation by monitoring and analyzing the postoperative psychological state data of patients in multiple dimensions, adopts MPNFS theory as the evaluation basis, can fully capture the change characteristics of the psychological state of patients, avoids the subjectivity and one-sidedness of traditional evaluation methods, and fully considers the influence of individual differences of patients on the evaluation results, ensuring the pertinence and effectiveness of the evaluation results. In specific implementation, the trend feature, periodic feature and mutation feature of the combined feature vector are extracted, the confidence evaluation strategy is combined, the trend change amount, periodic fluctuation amount and instantaneous change parameter are evaluated in confidence, and the confidence weight is allocated according to the evaluation results, so as to realize the personalized psychological state evaluation of patients and realize the prediction of the postoperative psychological state of patients.

Description

Technical Field

[0001] This invention belongs to the field of postoperative psychological assessment technology, specifically relating to a postoperative psychological state assessment system and method based on MPNFS theory. Background Technology

[0002] With the advancement of medical technology, the psychological assessment of postoperative patients is receiving increasing attention, enabling them to receive more precise and personalized treatment plans, promote their comprehensive physical and mental recovery, reduce postoperative complications, and improve their quality of life. Traditional psychological assessment methods often rely on subjective judgment and lack systematic and quantitative evidence. In contrast, MPNFS theory can provide objective and multi-dimensional data analysis, effectively making up for the shortcomings of traditional methods, improving the accuracy and reliability of assessments, and providing strong support for clinical decision-making.

[0003] While some existing psychological state assessment methods based on MPNFS theory exist, they generally suffer from problems such as complex data processing and poor real-time performance, making it difficult to meet the needs of rapid clinical response. This leads to delayed assessment results and affects the timing of treatment. In addition, existing psychological state assessment systems often ignore the impact of individual patient differences on the assessment results, resulting in limited accuracy. Different individuals exhibit different patterns of psychological state changes, and the corresponding assessment characteristics also differ. Using a uniform assessment standard obviously cannot fully reflect individual differences. Based on this, this solution provides a postoperative psychological state assessment method based on MPNFS theory to address the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide a postoperative psychological state assessment system and method based on MPNFS theory, which can determine the specific assessment features to be selected according to the individual differences of patients, so as to achieve the purpose of personalized assessment.

[0005] The specific technical solution adopted by this invention is as follows:

[0006] A postoperative psychological state assessment method based on MPNFS theory includes:

[0007] Postoperative psychological status assessment data of patients were collected under the influence of drug treatment, psychological intervention, clinical nursing, family care and social support. The psychological status assessment data included respiratory monitoring data, voice recording data and bioelectrical signal data.

[0008] The system performs time-frequency synchronization processing on respiratory monitoring data, voice recording data, and bioelectric signal data, outputs a joint feature vector, and performs time-series analysis on the joint feature vector through a sliding window mechanism to output the time-series features of the joint feature vector, including trend features, periodic features, and abrupt change features.

[0009] The trend change of the joint feature vector is determined based on the trend characteristics, the periodic fluctuation of the joint feature vector is determined based on the periodic characteristics, and the instantaneous change parameters of the joint feature vector are determined based on the abrupt change characteristics.

[0010] Confidence levels are assessed for trend changes, periodic fluctuations, and instantaneous changes, and confidence weights are assigned to each of these parameters based on the confidence level assessment results.

[0011] Based on the trend change, periodic fluctuation, and instantaneous change parameters, as well as the corresponding confidence weights, the preset prediction nodes are comprehensively compared and predicted, and a psychological state score is output. When the psychological state score exceeds the preset evaluation threshold, an alarm signal is issued and a psychological state evaluation report is generated.

[0012] In a preferred embodiment, during the respiratory monitoring data acquisition, the patient's respiratory rate, respiratory depth, and respiratory rhythm are monitored using a wearable device, which includes a smart bracelet, a chest strap respiratory monitor, and a respiratory sensor attached to the patient's skin. During the voice recording data acquisition, the patient's voice content, including the volume, speed, tone, and emotional tendency of the voice, is recorded using a microphone. During the bioelectrical signal data acquisition, electrocardiogram, electromyogram, and electroencephalogram signals are collected using a bioelectrical sensor attached to the patient's skin.

[0013] In a preferred embodiment, the step of performing time-frequency synchronization processing on respiratory monitoring data, voice recording data, and bioelectrical signal data to output a joint feature vector includes:

[0014] Time-frequency decomposition processing is performed on respiratory monitoring data to extract respiratory fluctuation characteristics from the data;

[0015] Spectral processing is performed on the speech recording data to extract intonation variation features.

[0016] Wavelet transform processing is performed on bioelectric signal data to extract rhythmic variation features from the bioelectric signals;

[0017] Dynamic time alignment technology is used to align the timestamps of respiratory fluctuation features, intonation change features, and rhythm change features to generate a time-frequency synchronized joint feature vector.

[0018] In a preferred embodiment, the step of performing temporal analysis on the joint feature vector using a sliding window mechanism and outputting the temporal features of the joint feature vector includes:

[0019] Set the window length and sliding step of the sliding window. The window length is dynamically adjusted according to the data sampling frequency, and the sliding step is set according to the sensitivity of data changes.

[0020] The difference between adjacent joint feature vectors is calculated within the sliding window. When the difference exceeds a preset difference threshold, the corresponding sliding window is recorded as a mutation window. When the difference does not exceed the preset threshold, it is recorded as a stationary window.

[0021] The number of mutation windows and the mutation amount of the joint feature vector within each mutation window are counted and stored as mutation features.

[0022] Identify the joint feature vectors within each stable window that are within the allowable fluctuation range, and output the fluctuation amplitude and fluctuation period of the joint feature vectors within the allowable fluctuation range as periodic features for storage;

[0023] The average rate of change of the joint eigenvector within the stationary window is analyzed by trend fitting and stored as a trend feature.

[0024] In a preferred embodiment, the steps of determining the trend change amount of the joint feature vector based on trend characteristics, determining the periodic fluctuation amount of the joint feature vector based on periodic characteristics, and determining the instantaneous change parameter of the joint feature vector based on abrupt change characteristics include:

[0025] Collect the joint feature vector under the current evaluation node, as well as the demand forecast interval between the current node and the prediction node, and input the joint feature vector, demand forecast interval and average rate of change under the current node into the trend evaluation function to output the trend change of the joint feature vector.

[0026] Extract the periodic fluctuation amplitude of the joint feature vector under each fluctuation period, perform weighted averaging, and output the periodic fluctuation amount of the joint feature vector.

[0027] Extract the mutation amount and mutation count within each mutation window, determine the distribution segment of the mutation window based on the time interval between mutation windows, perform weighted fusion processing on the mutation amount and mutation count within each distribution segment, and output as instantaneous change parameters.

[0028] Among them, the closer the distribution segment is to the current evaluation node, the greater the corresponding weighting weight.

[0029] In a preferred embodiment, the step of assessing the confidence level of the trend change, periodic fluctuation, and instantaneous change parameters includes:

[0030] Multiple sets of sample data are randomly extracted from existing historical data, and simulation calculations are performed on each set of sample data. The simulated trend change, simulated periodic fluctuation, and simulated instantaneous change parameters are output.

[0031] Calculate the deviation rate between the simulated trend change and the trend change, and record it as the first condition parameter. Then compare the first condition parameter with the preset first threshold. If the first condition parameter is higher than the first threshold, directly determine that the trend change output is wrong, and add sample data to re-simulate and calculate. If the first condition parameter is lower than the first threshold, calculate the excess ratio of the first condition parameter and record it as the first confidence evaluation index.

[0032] Calculate the matching degree between the simulated periodic fluctuation and the periodic fluctuation, and record it as the second condition parameter. Then compare the second condition parameter with the preset second threshold. If the second condition parameter is lower than the second threshold, directly determine that the periodic fluctuation output is wrong, and add sample data to re-simulate and calculate. If the second condition parameter is higher than the second threshold, calculate the excess ratio of the second condition parameter and record it as the second confidence evaluation index.

[0033] The similarity between the simulated instantaneous change parameter and the instantaneous change parameter is calculated and recorded as the third condition parameter. The third condition parameter is then compared with a preset third threshold. If the third condition parameter is lower than the third threshold, sample data is directly added and the simulation is recalculated. If the third condition parameter is still lower than the third threshold after adding samples, the intervention of the instantaneous change parameter is deemed invalid and no further confidence assessment is performed. If the third condition parameter is higher than the third threshold, its excess ratio is calculated and recorded as the third confidence assessment index.

[0034] In a preferred embodiment, the step of assigning confidence weights to trend changes, periodic fluctuations, and instantaneous changes based on the confidence assessment results includes:

[0035] Obtain the first confidence level assessment index, the second confidence level assessment index, and the third confidence level assessment index;

[0036] The first confidence assessment index, the second confidence assessment index, and the third confidence assessment index are input into the preset weight allocation function, and the output of the weight allocation function is used as the confidence weight of the trend change, the periodic fluctuation, and the instantaneous change.

[0037] If the third confidence level assessment indicator is not output, the default value of the third confidence level assessment indicator is zero.

[0038] In a preferred embodiment, the step of comprehensively comparing and predicting preset prediction nodes based on trend change, periodic fluctuation, instantaneous change parameters, and corresponding confidence weights, and outputting a psychological state score, includes:

[0039] Obtain the prediction node timestamp, as well as the historical timestamps that are parallel to the prediction node timestamps;

[0040] The confidence weights of the first, second, and third confidence assessment indicators are collected under historical timestamps. The confidence weights of the first, second, and third confidence assessment indicators are then sorted in descending order, and the confidence weight with the highest ranking is recorded as the primary confidence weight.

[0041] When the primary confidence weight corresponds to the trend change, the predicted patient's psychological state score is calculated based on the time interval between the predicted node timestamp and the historical timestamp.

[0042] When the main confidence weight corresponds to the periodic fluctuation, the predicted fluctuation ratio under the predicted node time stamp will be determined based on the periodic fluctuation under the historical time stamp, and the historical psychological state score under the historical time stamp will be adjusted proportionally based on the predicted fluctuation to obtain the psychological state score under the predicted node time stamp.

[0043] When the primary confidence weight corresponds to the instantaneous change, the historical psychological state score under the historical timestamp is recorded as the psychological state score under the predicted node timestamp.

[0044] This invention also provides a postoperative psychological state assessment system based on MPNFS theory, using the aforementioned postoperative psychological state assessment method based on MPNFS theory, comprising:

[0045] The data acquisition module is used to collect postoperative psychological status assessment data of patients under drug treatment, psychological intervention, clinical nursing, family care and social support. The psychological status assessment data includes respiratory monitoring data, voice recording data and bioelectrical signal data.

[0046] The time-series analysis module is used to perform time-frequency synchronization processing on respiratory monitoring data, voice recording data, and bioelectric signal data, output a joint feature vector, and perform time-series analysis on the joint feature vector through a sliding window mechanism to output the time-series features of the joint feature vector, including trend features, periodic features, and abrupt change features.

[0047] The feature quantization module is used to determine the trend change of the joint feature vector based on trend characteristics, the periodic fluctuation of the joint feature vector based on periodic characteristics, and the instantaneous change parameters of the joint feature vector based on abrupt change characteristics.

[0048] The weight calculation module is used to evaluate the confidence level of trend change, periodic fluctuation and instantaneous change parameters respectively, and to assign confidence weights to trend change, periodic fluctuation and instantaneous change based on the confidence level evaluation results.

[0049] The state prediction module is used to comprehensively compare and predict preset prediction nodes based on trend change, periodic fluctuation, instantaneous change parameters, and corresponding confidence weights, output psychological state scores, and issue alarm signals and generate psychological state assessment reports when the psychological state scores exceed preset assessment thresholds.

[0050] And, an electronic device, the electronic device comprising:

[0051] At least one processor;

[0052] and a memory communicatively connected to the at least one processor;

[0053] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the above-described postoperative psychological state assessment method based on MPNFS theory.

[0054] The technical effects achieved by this invention are as follows:

[0055] This invention effectively improves the accuracy and reliability of postoperative psychological state assessment by monitoring and analyzing patients' psychological state data from multiple dimensions. Employing MPNFS theory as the assessment basis, it comprehensively captures the changing characteristics of patients' psychological states, avoiding the subjectivity and bias of traditional assessment methods. It also fully considers the impact of individual patient differences on the assessment results, ensuring the relevance and effectiveness of the results. In specific implementation, trend characteristics, periodic characteristics, and abrupt change characteristics of the joint feature vector are extracted. Combined with a confidence assessment strategy, confidence levels are assessed for trend changes, periodic fluctuations, and instantaneous changes. Confidence weights are assigned based on the assessment results, enabling personalized psychological state assessment for patients, prediction of postoperative psychological state, and improved timeliness of medical intervention. Attached Figure Description

[0056] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0057] Figure 2 This is a schematic diagram of the system modules of the present invention;

[0058] Figure 3 This is a schematic diagram of the electronic device structure of the present invention. Detailed Implementation

[0059] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0060] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0062] Please see Figure 1 As shown, this invention provides a postoperative psychological state assessment method based on MPNFS theory, including:

[0063] S1. Collect postoperative psychological status assessment data of patients under drug treatment, psychological intervention, clinical nursing, family care and social support. The psychological status assessment data includes respiratory monitoring data, voice recording data and bioelectrical signal data.

[0064] In step S1, when assessing the patient's postoperative psychological state, it is first necessary to collect postoperative psychological state assessment data under the influence of multiple factors such as drug treatment, psychological intervention, clinical nursing, family care, and social support. The psychological state assessment data covers multiple dimensions such as respiratory monitoring data, voice recording data, and bioelectrical signal data to ensure the comprehensiveness and accuracy of the assessment. Specifically, when collecting respiratory monitoring data, the patient's respiratory rate, respiratory depth, and respiratory rhythm are monitored through wearable devices, including smart bracelets, chest strap respiratory monitors, and respiratory sensors attached to the patient's skin. When collecting voice recording data, the patient's voice content is recorded through a microphone, including the volume, speed, tone, and emotional tendency of the voice. When collecting bioelectrical signal data, electrocardiogram, electromyogram, and electroencephalogram signals are collected using bioelectrical sensors attached to the patient's skin.

[0065] Specifically, when collecting respiratory monitoring data, voice recording data, and bioelectrical signal data, in order to ensure the accuracy and integrity of the data, the raw data needs to be preprocessed. The preprocessing steps include denoising the respiratory monitoring data to eliminate the interference of environmental noise and instrument errors on the respiratory data, filtering the voice recording data to improve the clarity and recognizability of the voice signal, and performing baseline correction and artifact removal on the bioelectrical signal data to reduce interference caused by electrode movement or muscle activity. This provides accurate data support for subsequent analysis and ensures the accuracy and reliability of psychological state assessment.

[0066] S2. Perform time-frequency synchronization processing on respiratory monitoring data, voice recording data and bioelectric signal data, output a joint feature vector, and perform time-series analysis on the joint feature vector through a sliding window mechanism to output the time-series features of the joint feature vector, including trend features, periodic features and abrupt change features.

[0067] In step S2, after the respiratory monitoring data, voice recording data, and bioelectrical signal data are output, time-frequency synchronization processing is first performed to ensure the consistency of the respiratory monitoring data, voice recording data, and bioelectrical signal data on the time axis. Then, the synchronized respiratory monitoring data, voice recording data, and bioelectrical signal data are fused into a joint feature vector to comprehensively reflect the changes in the patient's psychological state. Afterward, a sliding window mechanism is used to perform time-series analysis on the joint feature vector to extract its temporal features. These temporal features include trend features, periodic features, and abrupt change features, providing key indicators for subsequent psychological state assessment. Trend features reflect the long-term trend of the patient's psychological state, periodic features reveal the regularity of the psychological state's periodic fluctuations over time, and abrupt change features capture abnormal situations of sudden changes in psychological state within a short period. The step of performing time-frequency synchronization processing on the respiratory monitoring data, voice recording data, and bioelectrical signal data to output the joint feature vector includes:

[0068] Time-frequency decomposition processing is performed on respiratory monitoring data to extract respiratory fluctuation characteristics from the data;

[0069] Spectral processing is performed on the speech recording data to extract intonation variation features.

[0070] Wavelet transform processing is performed on bioelectric signal data to extract rhythmic variation features from the bioelectric signals;

[0071] Dynamic time alignment technology is used to align the timestamps of respiratory fluctuation features, intonation change features, and rhythm change features to generate a time-frequency synchronized joint feature vector;

[0072] Specifically, when outputting the joint feature vector, the respiratory monitoring data undergoes time-frequency decomposition processing. By decomposing different frequency components, respiratory fluctuation features are extracted to reflect the potential connection between the patient's breathing pattern and psychological state. The speech recording data undergoes spectral processing, using methods such as Fourier transform or Mel spectrum analysis to extract intonation variation features such as pitch, speed, and emotional tendency, which helps to understand the patient's emotional state. The bioelectrical signal data undergoes wavelet transform processing to extract rhythm variation features from electrocardiogram, electromyography, and electroencephalogram signals, which can reveal the patient's autonomic nervous system activity and brain activity state. Finally, dynamic time alignment technology is used to align the respiratory fluctuation features, intonation variation features, and rhythm variation features according to timestamps, thereby generating a time-frequency synchronized joint feature vector, providing an accurate data foundation for subsequent psychological state assessment.

[0073] Secondly, the steps for performing temporal analysis on the joint feature vector using a sliding window mechanism and outputting the temporal features of the joint feature vector include:

[0074] Set the window length and sliding step of the sliding window. The window length is dynamically adjusted according to the data sampling frequency, and the sliding step is set according to the sensitivity of data changes.

[0075] The difference between adjacent joint feature vectors is calculated within the sliding window. When the difference exceeds a preset difference threshold, the corresponding sliding window is recorded as a mutation window. When the difference does not exceed the preset threshold, it is recorded as a stationary window.

[0076] The number of mutation windows and the mutation amount of the joint feature vector within each mutation window are counted and stored as mutation features.

[0077] Identify the joint feature vectors within each stable window that are within the allowable fluctuation range, and output the fluctuation amplitude and fluctuation period of the joint feature vectors within the allowable fluctuation range as periodic features for storage;

[0078] The average rate of change of the joint feature vector within the stationary window is analyzed by trend fitting and stored as a trend feature.

[0079] In the above process, when determining the temporal features of the joint feature vectors, it is first necessary to pre-set the parameters of the sliding window, including the window length and the sliding step size. This ensures that the window length matches the data sampling frequency, and the sliding step size is adjusted according to the sensitivity of data changes to guarantee the accuracy of data capture. Within the sliding window, the difference between adjacent joint feature vectors is calculated. This difference reflects the intensity of changes in psychological state over time. When the difference exceeds a preset threshold, it indicates a significant change in the patient's psychological state, and the corresponding sliding window is marked as a mutation window. When the difference does not exceed the preset threshold, it is marked as a stationary window, indicating that the psychological state is relatively stable during this period. For mutation windows, the number of mutation windows and the mutation amount of the joint feature vectors within each mutation window are further counted and stored as mutational features. These mutational features generally reflect the patient's... When a patient experiences strong emotional reactions or psychological fluctuations in a specific situation, the system identifies joint feature vectors within a stable window that fall within the allowable fluctuation range. These joint feature vectors reflect the fluctuations in the patient's psychological state under stable conditions, and their corresponding fluctuation amplitude and period are recorded as periodic features. Periodic features generally reflect the patient's emotional ups and downs and regular changes in daily life. For example, the patient's emotions are more active in the morning and evening, and the fluctuation period coincides with the biological rhythm. Finally, trend fitting analysis is performed on the joint feature vectors within the stable window, and their average rate of change is calculated and stored as trend features. Trend features reflect the long-term trend of the patient's psychological state and help assess the overall direction of the psychological state. Trend features generally reflect the slow changes in the patient's psychological state over a long period of time, such as a gradual decline or recovery in mood.

[0080] S3. Determine the trend change of the joint feature vector based on trend characteristics, determine the periodic fluctuation of the joint feature vector based on periodic characteristics, and determine the instantaneous change parameters of the joint feature vector based on abrupt change characteristics.

[0081] In the above process, after determining the trend characteristics, periodic characteristics, and abrupt change characteristics, the trend change amount of the joint feature vector is determined based on the extracted trend characteristics to help understand the long-term development trend of the patient's psychological state. Based on the periodic characteristics, the periodic fluctuation amount of the joint feature vector is determined to help identify the periodic change pattern of the patient's psychological state. Based on the abrupt change characteristics, the instantaneous change parameters of the joint feature vector are determined to capture sudden changes in the patient's psychological state. The steps of determining the trend change amount of the joint feature vector based on trend characteristics, determining the periodic fluctuation amount of the joint feature vector based on periodic characteristics, and determining the instantaneous change parameters of the joint feature vector based on abrupt change characteristics include:

[0082] Collect the joint feature vector under the current evaluation node, as well as the demand forecast interval between the current node and the prediction node, and input the joint feature vector, demand forecast interval and average rate of change under the current node into the trend evaluation function to output the trend change of the joint feature vector.

[0083] Extract the periodic fluctuation amplitude of the joint feature vector under each fluctuation period, perform weighted averaging, and output the periodic fluctuation amount of the joint feature vector.

[0084] Extract the mutation amount and mutation count within each mutation window, determine the distribution segment of the mutation window based on the time interval between mutation windows, perform weighted fusion processing on the mutation amount and mutation count within each distribution segment, and output as instantaneous change parameters.

[0085] Among them, the closer the distribution segment is to the current evaluation node, the greater the corresponding weighting weight;

[0086] Specifically, when determining the trend change of the joint feature vector based on trend characteristics, the joint feature vector at the current assessment node is first collected. Considering the inertia of the patient's psychological state development, the demand prediction interval between the current node and the prediction node is also obtained. The demand prediction interval reflects the time span from the current psychological state to a future predicted state. Then, the joint feature vector at the current node, the demand prediction interval, and the average rate of change obtained through trend fitting analysis are input into the trend evaluation function to predict and output the trend change of the joint feature vector. The expression of the trend evaluation function is: Trend change = Average rate of change × Demand prediction interval + Current joint feature vector. In the calculation of periodic fluctuations, the periodic fluctuation amplitude of the joint feature vector under each fluctuation period is extracted and analyzed. The periodic fluctuation amplitude is processed by weighted averaging. The weights of the averaging can be determined comprehensively based on factors such as the stability and frequency of the fluctuation cycle, and are set according to the actual situation. This outputs the periodic fluctuation amount of the joint feature vector. In the process of determining the instantaneous change parameters, the mutation amount and mutation number in each mutation window are extracted. The mutation amount reflects the intensity of the change in psychological state in a short period of time, and the mutation number reflects the frequency of psychological state changes. At the same time, the distribution segment of the mutation window is determined according to the time interval between mutation windows (the distribution segment can be determined by interval partitioning or clustering algorithm). The closer the distribution segment is to the current evaluation node, the greater its influence on the instantaneous change parameters, and therefore the greater the corresponding weight. Then, the mutation amount and mutation number in each distribution segment are weighted and fused to output the instantaneous change parameters.

[0087] S4. Calculate the confidence level of the trend change, periodic fluctuation, and instantaneous change parameters respectively, and assign confidence weights to the trend change, periodic fluctuation, and instantaneous change parameters according to the confidence level assessment results.

[0088] In step S4, after the trend change, periodic fluctuation, and instantaneous change parameter are determined, the corresponding confidence levels are calculated respectively, and the confidence weights of the trend change, periodic fluctuation, and instantaneous change parameter in the subsequent evaluation process are determined based on the confidence level assessment results. The steps of evaluating the confidence levels of the trend change, periodic fluctuation, and instantaneous change parameter respectively include:

[0089] Multiple sets of sample data are randomly extracted from existing historical data, and simulation calculations are performed on each set of sample data. The simulated trend change, simulated periodic fluctuation, and simulated instantaneous change parameters are output.

[0090] Calculate the deviation rate between the simulated trend change and the trend change, and record it as the first condition parameter. Then compare the first condition parameter with the preset first threshold. If the first condition parameter is higher than the first threshold, directly determine that the trend change output is wrong, and add sample data to re-simulate and calculate. If the first condition parameter is lower than the first threshold, calculate the excess ratio of the first condition parameter and record it as the first confidence evaluation index.

[0091] Calculate the matching degree between the simulated periodic fluctuation and the periodic fluctuation, and record it as the second condition parameter. Then compare the second condition parameter with the preset second threshold. If the second condition parameter is lower than the second threshold, directly determine that the periodic fluctuation output is wrong, and add sample data to re-simulate and calculate. If the second condition parameter is higher than the second threshold, calculate the excess ratio of the second condition parameter and record it as the second confidence evaluation index.

[0092] The similarity between simulated instantaneous change parameters and instantaneous change parameters is calculated and recorded as the third conditional parameter. The third conditional parameter is then compared with a preset third threshold. If the third conditional parameter is lower than the third threshold, sample data is added and the simulation is recalculated. If the third conditional parameter is still lower than the third threshold after adding samples, the intervention of instantaneous change parameters is deemed invalid, and no further confidence assessment is performed. If the third conditional parameter is higher than the third threshold, its excess ratio is calculated and recorded as the third confidence assessment index.

[0093] Specifically, when assessing the confidence level of trend change, periodic fluctuation, and instantaneous change parameters, multiple sets of sample data are first randomly extracted from the existing historical database. These sample data include psychological state assessment records of different patients. Then, simulation calculations are performed on each set of sample data. The simulation calculation process is consistent with the actual assessment process, including preprocessing, time-frequency synchronization processing, and time-series analysis of respiratory monitoring data, voice recording data, and bioelectrical signal data. This outputs the simulated trend change, simulated periodic fluctuation, and simulated instantaneous change parameters. Next, the deviation rate between the simulated trend change and the trend change obtained through the actual assessment process is calculated. The deviation rate reflects the degree of difference between the simulated and actual results and is recorded as the first conditional parameter. The first conditional parameter is then compared with a preset first threshold. If the first conditional parameter is higher than the first threshold, it indicates that the difference between the simulated and actual results is too large. In this case, it is directly determined that there is an error in the output of the trend change, and additional sample data is added for re-simulation to improve the accuracy of the assessment. If a conditional parameter is below the first threshold, it indicates that the simulation result is close to the actual result. In this case, the excess ratio of the first conditional parameter is calculated and recorded as the first confidence assessment index. Similarly, the matching degree between simulated periodic fluctuations and the similarity between simulated instantaneous change parameters are also calculated. The matching degree and similarity are recorded as the second and third conditional parameters, respectively. Then, the second and third conditional parameters are compared with the preset second and third thresholds, respectively. Based on the comparison results, corresponding processing is performed, including determining output errors, adding sample data to recalculate, and calculating the excess ratio, etc., to determine the second and third confidence assessment indices. For instantaneous change parameters, if the third conditional parameter is still below the third threshold after adding samples, the intervention of instantaneous change parameters is deemed invalid. Specifically, in certain specific situations, the patient's psychological state changes are too complex or abnormal, making it impossible to accurately assess using the current assessment method. In this case, confidence assessment will no longer be performed to avoid misleading subsequent assessment results.

[0094] In addition, the steps of assigning confidence weights to trend changes, periodic fluctuations, and instantaneous changes based on the confidence assessment results include:

[0095] Obtain the first confidence level assessment index, the second confidence level assessment index, and the third confidence level assessment index;

[0096] The first confidence assessment index, the second confidence assessment index, and the third confidence assessment index are input into the preset weight allocation function, and the output of the weight allocation function is used as the confidence weight of the trend change, the periodic fluctuation, and the instantaneous change.

[0097] If the third confidence level assessment indicator is not output, the default value of the third confidence level assessment indicator is zero.

[0098] Specifically, after the first, second, and third confidence level assessment indicators are determined, a preset weighting function is used to assign corresponding confidence weights to the trend change, periodic fluctuation, and instantaneous change, ensuring a reasonable proportion of each parameter in the comprehensive assessment. The expression for the weighting function is as follows: In the formula, Indicates the first The confidence weights corresponding to the confidence assessment indicators. Indicates the first Confidence assessment indicators This represents the sum of the first confidence level assessment index, the second confidence level assessment index, and the third confidence level assessment index. In addition, it should be noted that when the third confidence level assessment index is zero, the weight allocation function will automatically adjust the weight ratio of the other two indices to ensure the balance of the assessment results.

[0099] S5. Based on the trend change, periodic fluctuation, and instantaneous change parameters, as well as the corresponding confidence weights, perform a comprehensive comparison and prediction of the preset prediction nodes, output a psychological state score, and issue an alarm signal and generate a psychological state assessment report when the psychological state score exceeds the preset assessment threshold.

[0100] In step S5, when calculating the psychological state score, trend change, periodic fluctuation, and instantaneous change parameters, along with corresponding confidence weights, are comprehensively considered. If the output psychological state score exceeds a pre-set assessment threshold, an alarm mechanism is immediately triggered to alert relevant personnel to monitor changes in the patient's psychological state. The step of comprehensively comparing and predicting preset prediction nodes based on trend change, periodic fluctuation, instantaneous change parameters, and corresponding confidence weights to output the psychological state score includes:

[0101] Obtain the prediction node timestamp, as well as the historical timestamps that are parallel to the prediction node timestamps;

[0102] The confidence weights of the first, second, and third confidence assessment indicators are collected under historical timestamps. The confidence weights of the first, second, and third confidence assessment indicators are then sorted in descending order, and the confidence weight with the highest ranking is recorded as the primary confidence weight.

[0103] When the primary confidence weight corresponds to the trend change, the predicted patient's psychological state score is calculated based on the time interval between the predicted node timestamp and the historical timestamp.

[0104] When the main confidence weight corresponds to the periodic fluctuation, the predicted fluctuation ratio under the predicted node time stamp will be determined based on the periodic fluctuation under the historical time stamp, and the historical psychological state score under the historical time stamp will be adjusted proportionally based on the predicted fluctuation to obtain the psychological state score under the predicted node time stamp.

[0105] When the primary confidence weight corresponds to the instantaneous change, the historical psychological state score under the historical timestamp is recorded as the psychological state score under the predicted node timestamp.

[0106] Specifically, when outputting the psychological state score, the first step is to determine the preset prediction node timestamp. This timestamp represents the time point at which the patient's psychological state will be assessed at a future moment. Then, historical timestamps parallel to the prediction node timestamp are searched. Next, the confidence weights of the first, second, and third confidence assessment indicators under the historical timestamps are collected and sorted in descending order to determine the primary confidence weight. The primary confidence weight determines the calculation method of the psychological state score. If the primary confidence weight corresponds to a trend change, the patient's psychological state score is predicted based on the time interval between the prediction node timestamp and the historical timestamp, as well as the value of the trend change. Specifically, the trend change rate between the two is calculated and weighted according to the historical psychological state scores to ultimately obtain the psychological state score under the prediction node timestamp. The weight corresponds to the periodic fluctuation amount. The predicted fluctuation ratio at the predicted node time stamp is determined based on the periodic fluctuation amount under the historical time stamp. Then, the historical psychological state score under the historical time stamp is proportionally adjusted based on this predicted fluctuation amount to obtain the psychological state score at the predicted node time stamp. If the primary confidence weight corresponds to the instantaneous change amount, since the instantaneous change amount reflects the sudden change in the patient's psychological state, the historical psychological state score under the historical time stamp will be directly recorded as the psychological state score at the predicted node time stamp. This serves as a rapid response to sudden changes in the current psychological state. When the output psychological state score exceeds the preset assessment threshold, an alarm mechanism will be immediately triggered. Various methods such as sound, light, and electricity will be used to alert relevant personnel to pay attention to the changes in the patient's psychological state and generate a corresponding psychological state assessment report to provide relevant reference for medical staff.

[0107] Please see Figure 2 A postoperative psychological state assessment system based on MPNFS theory, using the aforementioned postoperative psychological state assessment method based on MPNFS theory, includes:

[0108] The data acquisition module is used to collect postoperative psychological status assessment data of patients under drug treatment, psychological intervention, clinical nursing, family care and social support. The psychological status assessment data includes respiratory monitoring data, voice recording data and bioelectrical signal data.

[0109] The time-series analysis module is used to perform time-frequency synchronization processing on respiratory monitoring data, voice recording data, and bioelectric signal data, output a joint feature vector, and perform time-series analysis on the joint feature vector through a sliding window mechanism to output the time-series features of the joint feature vector, including trend features, periodic features, and abrupt change features.

[0110] The feature quantization module is used to determine the trend change of the joint feature vector based on trend characteristics, the periodic fluctuation of the joint feature vector based on periodic characteristics, and the instantaneous change parameters of the joint feature vector based on abrupt change characteristics.

[0111] The weight calculation module is used to evaluate the confidence level of trend change, periodic fluctuation and instantaneous change parameters respectively, and to assign confidence weights to trend change, periodic fluctuation and instantaneous change based on the confidence level evaluation results.

[0112] The state prediction module is used to comprehensively compare and predict preset prediction nodes based on trend change, periodic fluctuation, instantaneous change parameters, and corresponding confidence weights, output psychological state scores, and issue alarm signals and generate psychological state assessment reports when the psychological state scores exceed preset assessment thresholds.

[0113] In the above, the data acquisition module is responsible for collecting patients' psychological state assessment data from multiple dimensions. This data originates from various aspects, including drug treatment, psychological intervention, clinical nursing, family care, and social support. Specifically, it includes respiratory monitoring data, voice recording data, and bioelectrical signal data. The time-series analysis module performs time-frequency synchronization processing on the collected psychological state assessment data, extracts joint feature vectors, and analyzes their time-series characteristics using a sliding window mechanism. These time-series characteristics are specifically classified into trend characteristics, periodic characteristics, and abrupt changes. The feature quantification module determines the trend change of the joint feature vector based on the trend characteristics and the periodic characteristics based on the trend characteristics. The system determines the periodic fluctuation amount and the instantaneous change parameter based on the abrupt change characteristics. The weight calculation module evaluates the confidence level of the trend change amount, periodic fluctuation amount, and instantaneous change parameter, and assigns confidence weights according to the evaluation results. The state prediction module performs a comprehensive comparison and prediction of the psychological state at preset prediction nodes based on the quantified trend change amount, periodic fluctuation amount, and instantaneous change parameter, and finally outputs a psychological state score. If the psychological state score exceeds the preset evaluation threshold, an alarm mechanism will be triggered to remind relevant personnel to pay attention to the patient's psychological state changes and generate a corresponding psychological state evaluation report, providing a scientific basis for subsequent intervention by medical staff.

[0114] Please see Figure 3 An electronic device, comprising:

[0115] At least one processor;

[0116] and memory that is communicatively connected to at least one processor;

[0117] The memory stores a computer program that can be executed by at least one processor, which enables the processor to perform the aforementioned postoperative psychological state assessment method based on MPNFS theory.

[0118] The processor of the aforementioned electronic device can be a central processing unit (CPU), a graphics processing unit (GPU), or a digital signal processor (DSP), or a processor cluster composed of multiple processors. The memory can be random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, hard disk, or solid-state drive, etc. The memory is used to store computer programs that can be executed by the processor. When the electronic device is running, the processor executes the computer programs stored in the memory to implement the postoperative psychological state assessment method based on MPNFS theory. The electronic device may also include input devices such as a keyboard and a touch screen for receiving user instructions; output devices such as a display screen and a printer for displaying assessment results; and an arithmetic logic unit (ALU) for performing data processing.

[0119] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0120] The above description is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained in this invention are implemented according to conventional methods in the art unless otherwise specified or limited.

Claims

1. A postoperative psychological state assessment method based on MPNFS theory, characterized in that: include: Postoperative psychological status assessment data of patients were collected under the influence of drug treatment, psychological intervention, clinical nursing, family care and social support. The psychological status assessment data included respiratory monitoring data, voice recording data and bioelectrical signal data. The system performs time-frequency synchronization processing on respiratory monitoring data, voice recording data, and bioelectric signal data, outputs a joint feature vector, and performs time-series analysis on the joint feature vector through a sliding window mechanism to output the time-series features of the joint feature vector, including trend features, periodic features, and abrupt change features. The trend change of the joint feature vector is determined based on the trend characteristics, the periodic fluctuation of the joint feature vector is determined based on the periodic characteristics, and the instantaneous change parameters of the joint feature vector are determined based on the abrupt change characteristics. Confidence levels are assessed for trend changes, periodic fluctuations, and instantaneous changes, and confidence weights are assigned to each of these parameters based on the confidence level assessment results. Based on the trend change, periodic fluctuation, and instantaneous change parameters, as well as the corresponding confidence weights, the preset prediction nodes are comprehensively compared and predicted, and a psychological state score is output. When the psychological state score exceeds the preset evaluation threshold, an alarm signal is issued and a psychological state evaluation report is generated.

2. The postoperative psychological state assessment method based on MPNFS theory according to claim 1, characterized in that: During the respiratory monitoring data collection, the patient's respiratory rate, respiratory depth, and respiratory rhythm are monitored through wearable devices, including smart bracelets, chest strap respiratory monitors, and respiratory sensors attached to the patient's skin. During the voice recording data collection, the patient's voice content is recorded through a microphone, including the volume, speed, tone, and emotional tendency of the voice. During the bioelectrical signal data collection, electrocardiogram, electromyogram, and electroencephalogram signals are collected using bioelectrical sensors attached to the patient's skin.

3. The postoperative psychological state assessment method based on MPNFS theory according to claim 1, characterized in that: The step of performing time-frequency synchronization processing on respiratory monitoring data, voice recording data, and bioelectrical signal data to output a joint feature vector includes: Time-frequency decomposition processing is performed on respiratory monitoring data to extract respiratory fluctuation characteristics from the data; Spectral processing is performed on the speech recording data to extract intonation variation features. Wavelet transform processing is performed on bioelectric signal data to extract rhythmic variation features from the bioelectric signals; Dynamic time alignment technology is used to align the timestamps of respiratory fluctuation features, intonation change features, and rhythm change features to generate a time-frequency synchronized joint feature vector.

4. The postoperative psychological state assessment method based on MPNFS theory according to claim 1, characterized in that: The step of performing time-series analysis on the joint feature vector using a sliding window mechanism and outputting the time-series features of the joint feature vector includes: Set the window length and sliding step of the sliding window. The window length is dynamically adjusted according to the data sampling frequency, and the sliding step is set according to the sensitivity of data changes. The difference between adjacent joint feature vectors is calculated within the sliding window. When the difference exceeds a preset difference threshold, the corresponding sliding window is recorded as a mutation window. When the difference does not exceed the preset threshold, it is recorded as a stationary window. The number of mutation windows and the mutation amount of the joint feature vector within each mutation window are counted and stored as mutation features. Identify the joint feature vectors within each stable window that are within the allowable fluctuation range, and output the fluctuation amplitude and fluctuation period of the joint feature vectors within the allowable fluctuation range as periodic features for storage; The average rate of change of the joint eigenvector within the stationary window is analyzed by trend fitting and stored as a trend feature.

5. The postoperative psychological state assessment method based on MPNFS theory according to claim 4, characterized in that: The steps of determining the trend change amount of the joint feature vector based on trend characteristics, determining the periodic fluctuation amount of the joint feature vector based on periodic characteristics, and determining the instantaneous change parameter of the joint feature vector based on abrupt change characteristics include: Collect the joint feature vector under the current evaluation node, as well as the demand forecast interval between the current node and the prediction node, and input the joint feature vector, demand forecast interval and average rate of change under the current node into the trend evaluation function to output the trend change of the joint feature vector. Extract the periodic fluctuation amplitude of the joint feature vector under each fluctuation period, perform weighted averaging, and output the periodic fluctuation amount of the joint feature vector. Extract the mutation amount and mutation count within each mutation window, determine the distribution segment of the mutation window based on the time interval between mutation windows, perform weighted fusion processing on the mutation amount and mutation count within each distribution segment, and output as instantaneous change parameters. Among them, the closer the distribution segment is to the current evaluation node, the greater the corresponding weighting weight.

6. The postoperative psychological state assessment method based on MPNFS theory according to claim 1, characterized in that: The steps for assessing the confidence level of trend changes, periodic fluctuations, and instantaneous change parameters include: Multiple sets of sample data are randomly extracted from existing historical data, and simulation calculations are performed on each set of sample data. The simulated trend change, simulated periodic fluctuation, and simulated instantaneous change parameters are output. Calculate the deviation rate between the simulated trend change and the trend change, and record it as the first condition parameter. Then compare the first condition parameter with the preset first threshold. If the first condition parameter is higher than the first threshold, directly determine that the trend change output is wrong, and add sample data to re-simulate and calculate. If the first condition parameter is lower than the first threshold, calculate the excess ratio of the first condition parameter and record it as the first confidence evaluation index. Calculate the matching degree between the simulated periodic fluctuation and the periodic fluctuation, and record it as the second condition parameter. Then compare the second condition parameter with the preset second threshold. If the second condition parameter is lower than the second threshold, directly determine that the periodic fluctuation output is wrong, and add sample data to re-simulate and calculate. If the second condition parameter is higher than the second threshold, calculate the excess ratio of the second condition parameter and record it as the second confidence evaluation index. The similarity between the simulated instantaneous change parameter and the instantaneous change parameter is calculated and recorded as the third condition parameter. The third condition parameter is then compared with a preset third threshold. If the third condition parameter is lower than the third threshold, sample data is directly added and the simulation is recalculated. If the third condition parameter is still lower than the third threshold after adding samples, the intervention of the instantaneous change parameter is deemed invalid and no further confidence assessment is performed. If the third condition parameter is higher than the third threshold, its excess ratio is calculated and recorded as the third confidence assessment index.

7. The postoperative psychological state assessment method based on MPNFS theory according to claim 6, characterized in that: The step of assigning confidence weights to trend changes, periodic fluctuations, and instantaneous changes based on the confidence assessment results includes: Obtain the first confidence level assessment index, the second confidence level assessment index, and the third confidence level assessment index; The first confidence assessment index, the second confidence assessment index, and the third confidence assessment index are input into the preset weight allocation function, and the output of the weight allocation function is used as the confidence weight of the trend change, the periodic fluctuation, and the instantaneous change. If the third confidence level assessment indicator is not output, the default value of the third confidence level assessment indicator is zero.

8. The postoperative psychological state assessment method based on MPNFS theory according to claim 6, characterized in that: The step of comprehensively comparing and predicting preset prediction nodes based on trend changes, periodic fluctuations, instantaneous change parameters, and corresponding confidence weights, and outputting a psychological state score, includes: Obtain the prediction node timestamp, as well as the historical timestamps that are parallel to the prediction node timestamps; The confidence weights of the first, second, and third confidence assessment indicators are collected under historical timestamps. The confidence weights of the first, second, and third confidence assessment indicators are then sorted in descending order, and the confidence weight with the highest ranking is recorded as the primary confidence weight. When the primary confidence weight corresponds to the trend change, the predicted patient's psychological state score is calculated based on the time interval between the predicted node timestamp and the historical timestamp. When the main confidence weight corresponds to the periodic fluctuation, the predicted fluctuation ratio under the predicted node time stamp will be determined based on the periodic fluctuation under the historical time stamp, and the historical psychological state score under the historical time stamp will be adjusted proportionally based on the predicted fluctuation to obtain the psychological state score under the predicted node time stamp. When the primary confidence weight corresponds to the instantaneous change, the historical psychological state score under the historical timestamp is recorded as the psychological state score under the predicted node timestamp.

9. A postoperative psychological state assessment system based on MPNFS theory, characterized in that: The postoperative psychological state assessment method based on MPNFS theory as described in any one of claims 1 to 8 includes: The data acquisition module is used to collect postoperative psychological status assessment data of patients under drug treatment, psychological intervention, clinical nursing, family care and social support. The psychological status assessment data includes respiratory monitoring data, voice recording data and bioelectrical signal data. The time-series analysis module is used to perform time-frequency synchronization processing on respiratory monitoring data, voice recording data, and bioelectric signal data, output a joint feature vector, and perform time-series analysis on the joint feature vector through a sliding window mechanism to output the time-series features of the joint feature vector, including trend features, periodic features, and abrupt change features. The feature quantization module is used to determine the trend change of the joint feature vector based on trend characteristics, the periodic fluctuation of the joint feature vector based on periodic characteristics, and the instantaneous change parameters of the joint feature vector based on abrupt change characteristics. The weight calculation module is used to evaluate the confidence level of trend change, periodic fluctuation and instantaneous change parameters respectively, and to assign confidence weights to trend change, periodic fluctuation and instantaneous change based on the confidence level evaluation results. The state prediction module is used to comprehensively compare and predict preset prediction nodes based on trend change, periodic fluctuation, instantaneous change parameters, and corresponding confidence weights, output psychological state scores, and issue alarm signals and generate psychological state assessment reports when the psychological state scores exceed preset assessment thresholds.

10. An electronic device, characterized in that: The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the postoperative psychological state assessment method based on MPNFS theory as described in any one of claims 1 to 8.

Images