An intelligent cervical vertebra status data monitoring system

Abstract

The present invention relates to the field of state monitoring technology, specifically to an intelligent cervical state data monitoring system, the system including a data monitoring prediction module, a cervical risk analysis module, a cervical intervention formulation module and an intervention effect evaluation module. The present invention realizes highly sensitive tracking of the health status of the cervical spine through real-time data analysis and continuous monitoring of the posture and pressure changes of the cervical spine. The system adopts dynamic probability estimation, can update the health status in real time, and improve the accuracy of abnormal identification. By integrating posture and pressure data analysis, the system can identify potential health risks in the initial stage. Early warning of risk factors allows medical intervention to be carried out more timely and effectively, reducing the demand and cost of long-term treatment. Targeted intervention plans are adjusted according to real-time data to ensure that each intervention measure accurately matches the patient's current needs, optimize the intervention process, and improve the speed and effect of cervical rehabilitation.

Description

Technical Field

[0001] The present invention relates to the technical field of status monitoring, and in particular to an intelligent cervical vertebra status data monitoring system. Background Art

[0002] Condition monitoring technology focuses on achieving health management and fault prevention through methods and equipment that continuously or periodically detect the status of equipment, systems or the human body. In the medical field, condition monitoring technology pays particular attention to real-time tracking of human health status, ranging from basic physiological parameter measurements (such as heart rate, blood pressure) to more professional biomarkers and physiological function monitoring. This technology uses various sensors and data processing technologies to achieve continuous monitoring of individual health status, aiming to identify health problems early.

[0003] Among them, the intelligent cervical status data monitoring system refers to a system used to evaluate and monitor the health status of the cervical spine. It contains a variety of sensors that can capture information about the movement, posture, pressure, etc. of the cervical spine, and analyze the data through intelligent algorithms to identify abnormal cervical spine activity or potential health problems. Its main uses include helping doctors diagnose cervical spine-related diseases such as cervical spondylosis, providing feedback on rehabilitation training, and providing users with a reference for daily neck health management.

[0004] Existing technologies fail to fully utilize the correlation data between cervical spine posture and pressure, resulting in limited application effects in cervical spine health management. This limitation is mainly reflected in the tracking and immediate feedback of dynamic health status. Existing technologies cannot provide sufficient data support to facilitate real-time identification of health risks or adjustment of intervention plans, which affects the timeliness and targeting of interventions. For example, the lack of accurate risk assessment and timely health status updates can easily lead to the early symptoms of cervical spine problems being ignored, which in turn evolve into more serious health problems. In addition, existing technologies also have deficiencies in the implementation of targeted intervention configurations. They are often unable to provide patients with the most suitable intervention plans due to delayed responses or insufficient data analysis, which limits the efficiency of cervical spine rehabilitation and patient satisfaction. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an intelligent cervical vertebra status data monitoring system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an intelligent cervical vertebra status data monitoring system, the system comprising:

[0007] The data monitoring and prediction module sets the cervical status monitoring parameters based on the posture angle and pressure data, makes a preliminary estimate of the health status by associating the change rate of the two, obtains the preliminary health probability, and monitors the change values ​​of the cervical posture and pressure in real time, updates the probability estimation, and obtains the health status dynamic index;

[0008] The cervical risk analysis module monitors the fluctuation of posture angle and pressure data based on the health status dynamic index, performs attribution analysis based on the fluctuation amplitude change and data trend, compares with the health alarm threshold, identifies the key risk factors affecting cervical health, and obtains risk factor alarm signals;

[0009] The cervical spine intervention formulation module analyzes the change trend of the current cervical spine posture angle and pressure data based on the risk factor alarm signal, determines the pertinence and criticality of the intervention, obtains the intervention demand results, formulates the intervention process according to the intervention demand results, including posture adjustment and physical therapy, and obtains the cervical spine health intervention configuration;

[0010] The intervention effect evaluation module is based on the cervical spine health intervention configuration, continuously monitors the posture angle and pressure data of the cervical spine, collects the data difference before and after the intervention, and evaluates the intervention effect in real time, optimizes the adjustment direction of the intervention process, matches the healthy cervical spine state, and obtains the intervention effect response result.

[0011] The present invention is improved in that the step of performing preliminary probability estimation is specifically as follows:

[0012] Based on the attitude angle and pressure data, normalization processing is performed to optimize the measurement error and data deviation to obtain the attitude angle sequence and pressure sequence;

[0013] Based on the posture angle sequence and the pressure sequence, a sliding window method is applied to calculate the real-time correlation coefficient, matching the data timeliness and the reaction speed to obtain a correlation coefficient sequence;

[0014] Based on the correlation coefficient sequence, the formula is adopted:

[0015] ;

[0016] Perform a preliminary probability estimate of the health status and obtain a preliminary health probability, where: is the conditional probability, which means that given the data In case of health status The probability of represents an instance of the real-time correlation coefficient sequence, indicating the instantaneous correlation between the attitude angle sequence and the pressure sequence. and are the coefficients in the logistic regression model, represents the bias term, yes The weight of .

[0017] The present invention is improved in that the steps of obtaining the health status dynamic index are specifically as follows:

[0018] Based on the preliminary health probability, real-time monitoring data is performed to collect new measurements of posture angle and pressure data to obtain health probability update data;

[0019] Based on the health probability update data, the probability estimate of the health state is updated according to the known health probability and the new measurement data to obtain a weighted health probability;

[0020] Combined with the weighted health probability in continuous time, the formula is adopted:

[0021] ;

[0022] Calculate the dynamic index of health status, where Represents at time The dynamic index of health status, is the adjustment factor used to scale the calculated health index, Indicates at a point in time The probability of health, is the weight coefficient, for each time point Probability of health The weight assigned, is the time window length.

[0023] The present invention is improved in that the steps of performing attribution analysis are specifically as follows:

[0024] Based on the health status dynamic index, the posture angle and pressure data are monitored, and the data value of each measurement time point is recorded in real time to obtain time series data of posture and pressure;

[0025] Based on the time series data of the posture and pressure, the fluctuation amplitude changes and trends are extracted, the average value and standard deviation in each window period are calculated, the key fluctuation patterns of the data are identified, and the fluctuation characteristic indicators are obtained;

[0026] An attribution analysis is performed on the fluctuation characteristic index, the correlation between the data characteristics and the health index is explored, and the attribution analysis result is obtained.

[0027] The present invention is improved in that the step of obtaining the risk factor alarm signal is specifically as follows:

[0028] Based on the attribution analysis results, identify key risk factors affecting cervical spine health and obtain a risk factor list;

[0029] Based on the risk factor list, according to the cervical spine health standards and known health data, the health alert threshold is set using the formula:

[0030] ;

[0031] Get the risk factor threshold, where Indicates Health alert thresholds for key risk factors Representative The historical averages of the key risk factors Indicates The standard deviation of the risk factor, is the safety factor, used to adjust the sensitivity of the threshold;

[0032] Based on the risk factor threshold, a comparison is made with the real-time value of each key risk factor, and if the real-time value exceeds the threshold, a risk factor alarm signal is obtained.

[0033] The present invention is improved in that the step of obtaining the intervention demand result is specifically as follows:

[0034] Based on the risk factor alarm signal, monitor the current cervical vertebrae posture angle and pressure data, record the data value at each time point, and obtain the cervical vertebrae data time series;

[0035] Performing statistical analysis on the cervical vertebra data time series, applying an autoregressive moving average model, evaluating the short-term and long-term trends of the data, determining the key change points of the cervical vertebra condition, and obtaining key change point analysis results;

[0036] Based on the analysis results of the key change points, the current health status and potential risks of the cervical spine are evaluated using the formula:

[0037] ;

[0038] Determine the necessity and urgency of intervention and obtain intervention demand results, among which, represents the need index for intervention, Indicates The degree of deviation of the data points, It is The weight of the data point, is the number of key data points.

[0039] The present invention is improved in that the steps of obtaining the cervical health intervention configuration are specifically as follows:

[0040] Based on the intervention demand results, determining the required intervention type, including posture adjustment or physical therapy, and obtaining an intervention type table;

[0041] Based on the intervention type table, combined with the patient's cervical spine condition and intervention urgency, the intervention frequency, treatment course time and physical therapy equipment are formulated to obtain the cervical spine health intervention configuration.

[0042] The present invention is improved in that the step of obtaining the intervention effect response result is specifically as follows:

[0043] Based on the cervical health intervention configuration, the posture angle and pressure data of the cervical spine are continuously monitored, and the data difference before and after the intervention is collected to obtain the cervical status change data;

[0044] The cervical vertebra status change data is evaluated in real time, and the data changes before and after the intervention are analyzed using the formula:

[0045] ;

[0046] The results of intervention effect analysis were obtained, among which, represents the average response change rate before and after the intervention, Indicates The data value after the measurement intervention, Indicates The data value before the intervention was measured. Indicates the total number of measurements;

[0047] Based on the intervention effect analysis results, the intervention effect is evaluated, the adjustment direction of the intervention process is optimized, the healthy cervical spine state is matched, and the intervention effect response result is obtained.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In the present invention, through real-time data analysis and continuous monitoring of the posture and pressure changes of the cervical spine, highly sensitive tracking of the health status of the cervical spine is achieved. The system adopts dynamic probability estimation, which can instantly update the health status and improve the accuracy of abnormal identification. By integrating posture and pressure data analysis, the system can identify potential health risks in the initial stage. Early warning of risk factors allows medical intervention to be carried out more promptly and effectively, reducing the need and cost of long-term treatment. Targeted intervention plans are adjusted according to real-time data to ensure that each intervention measure accurately matches the patient's current needs, optimize the intervention process, and improve the speed and effect of cervical spine rehabilitation. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a system flow chart of the present invention;

[0051] Figure 2 A flowchart for performing preliminary probability estimation in the present invention;

[0052] Figure 3 This is a flow chart for obtaining the health status dynamic index in the present invention;

[0053] Figure 4 A flowchart for attribution analysis in the present invention;

[0054] Figure 5is a flow chart for obtaining the risk factor alarm signal in the present invention;

[0055] Figure 6 A flowchart for obtaining intervention demand results in the present invention;

[0056] Figure 7 A flowchart for obtaining the cervical health intervention configuration in the present invention;

[0057] Figure 8 This is a flow chart for obtaining intervention effect response results in the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0060] Example

[0061] See also Figure 1 The present invention provides a technical solution: an intelligent cervical vertebra status data monitoring system comprises:

[0062] The data monitoring and prediction module sets the cervical status monitoring parameters based on the posture angle and pressure data, makes a preliminary estimate of the health status by associating the change rate of the two, obtains the preliminary health probability, and monitors the change values ​​of the cervical posture and pressure in real time, updates the probability estimation, and obtains the health status dynamic index;

[0063] The cervical risk analysis module monitors the fluctuation of posture angle and pressure data based on the dynamic index of health status, performs attribution analysis based on the fluctuation amplitude and data trend, compares it with the health alarm threshold, identifies the key risk factors affecting cervical health, and obtains risk factor alarm signals;

[0064] The cervical spine intervention planning module analyzes the change trend of the current cervical spine posture angle and pressure data based on the risk factor alarm signal, determines the pertinence and criticality of the intervention, obtains the intervention demand results, and formulates the intervention process based on the intervention demand results, including posture adjustment and physical therapy, to obtain the cervical spine health intervention configuration;

[0065] The intervention effect evaluation module is based on the cervical health intervention configuration, continuously monitors the posture angle and pressure data of the cervical spine, collects the data difference before and after the intervention, and conducts real-time evaluation of the intervention effect, optimizes the adjustment direction of the intervention process, matches the healthy cervical spine state, and obtains the intervention effect response result.

[0066] The dynamic index of health status includes the rate of change indicator, status prediction value, and risk assessment coefficient. The risk factor alarm signal includes the risk level determination result, alarm trigger indicator, and key risk parameters. The cervical health intervention configuration includes intervention direction, intervention direction selection, and response time indicator. The intervention effect response result specifically refers to the effect change degree and evaluation indicator.

[0067] See also Figure 2 , the steps for making a preliminary probability estimate are as follows:

[0068] Based on the attitude angle and pressure data, normalization processing is performed to optimize the measurement error and data deviation to obtain the attitude angle sequence and pressure sequence;

[0069] The collected original attitude angle data can be measured by a three-axis accelerometer and a gyroscope, and the pressure data can be obtained in real time through a flexible pressure sensor array. The collected attitude angle data and pressure data are preprocessed respectively, and a filtering method is used to remove the noise interference in the acquisition process. Then the data is normalized by setting a unified standardized range, such as linearly scaling the data to the interval of 0 to 1, so as to optimize the measurement error and data deviation. In the normalization process, the maximum and minimum value ranges are called to calculate the normalized specific values. By processing each group of attitude angle data and pressure data one by one, it is ensured that the data are comparable within a unified scale, and finally the normalized attitude angle sequence and pressure sequence are obtained.

[0070] Based on the posture angle sequence and pressure sequence, the sliding window method is used to calculate the real-time correlation coefficient, match the data timeliness and reaction speed, and obtain the correlation coefficient sequence;

[0071] The sliding window method is used to segment the two sets of data. A fixed window length and sliding step size are set to segment the entire time series data into multiple continuous time periods. Each time period corresponds to a specific data subset. Then, the correlation between the posture angle sequence and the pressure sequence in each time period is calculated. In this process, the mean and deviation of the two sets of data in each time period need to be solved separately, and the correlation between the two sets of data in the same time period is calculated. The correlation results are arranged one by one in chronological order to generate a correlation coefficient sequence used to describe the dynamic relationship between the posture angle and pressure. This sequence can represent the changes in the correlation between the two sets of data in different time periods for subsequent analysis and probability estimation.

[0072] Based on the correlation coefficient sequence, the formula is used:

[0073] ;

[0074] Perform a preliminary probability estimate of the health status and obtain a preliminary health probability, where: is the conditional probability, which means that given the data In case of health status The probability of represents an instance of the real-time correlation coefficient sequence, indicating the instantaneous correlation between the attitude angle sequence and the pressure sequence. and are the coefficients in the logistic regression model, represents the bias term, yes The weight of

[0075] If the real-time correlation coefficient (calculated by sliding window method), bias and weight coefficient (obtained by fitting historical data), substitute into the formula:

[0076] ;

[0077] Calculate the exponent part between brackets:

[0078] ;

[0079] Calculate the index:

[0080] ;

[0081] Calculate the denominator:

[0082] ;

[0083] Calculate the probability:

[0084] ;

[0085] This result shows that given the data The individual's current health status The probability is 0.627, or 62.7%, indicating that there is a certain risk in the health status and further monitoring is needed to obtain more data to support subsequent evaluation results.

[0086] See also Figure 3 , the specific steps for obtaining the health status dynamic index are:

[0087] Based on the preliminary health probability, real-time monitoring data is used to collect new measurements of posture angle and pressure data to obtain updated health probability data;

[0088] New measurements of attitude angle data and pressure data are extracted. The attitude angle data obtains angles in different directions through a three-axis accelerometer, and the gyroscope is combined to record the angular velocity to compensate for dynamic changes. The pressure data is measured in real time at the neck contact point through a flexible pressure sensor. The collected data is preprocessed. First, a low-pass filter method is used to filter out high-frequency noise. After removing outliers, the data is standardized. The standardization process requires determining the maximum and minimum values ​​of the collected data, scaling each data point according to its proportion within the range so that the data has a unified unit of measurement, and inputting the standardized new data into the health probability update module to match the health probability of the previous moment, calculating the rate of change between the new measurement value and the value of the previous moment, and adjusting the preliminary health probability data according to the calculated rate of change to generate updated data of the health probability.

[0089] Based on the health probability update data, the probability estimate of the health state is updated according to the known health probability and the new measurement data to obtain the weighted health probability;

[0090] The health probability of each time point and the real-time measured posture angle and pressure data are extracted from the updated data, and a weight is assigned to the health probability of each time point. According to the distance between each time point and the current time point, the closer the time point is to the current moment, the higher the weight. The weight value is determined by calculating the time interval between each time point and the current time point. Subsequently, the health probability of each time point is multiplied by its corresponding weight to obtain a weighted result. The weighted results of all time points are accumulated to obtain a sum. In order to ensure the rationality of the result, the sum of the weight values ​​is normalized, and the accumulated weighted results are divided by the sum of the weights to complete the normalization operation. Finally, a weighted health probability is calculated, which comprehensively considers the time correlation between the historical probability and the current measurement data.

[0091] Combined with the weighted health probability in continuous time, the formula is adopted:

[0092] ;

[0093] Calculate the dynamic index of health status, where Represents at time The dynamic index of health status, is the adjustment factor used to scale the calculated health index, Indicates at a point in time The probability of health, is the weight coefficient, for each time point Probability of health The weight assigned, is the time window length;

[0094] If the time window length (represents data from the last five time points), adjustment factor (According to the exponential trend fitting in historical monitoring data), health probability series , weight sequence (Weights are assigned based on the proximity of the time points, the closer to the current time point, the higher the weight). Substitute each parameter into the formula:

[0095] ;

[0096] Compute the weighted sum inside the brackets:

[0097] ;

[0098] Calculate the dynamic index of health status:

[0099] ;

[0100] The results show that at the current time point ,The dynamic index of health status is 0.888, indicating that the current health status is good after comprehensive consideration of short-term and long-term health probabilities. The dynamic index provides an overall evaluation of the health status, which can be used for subsequent health trend analysis and risk assessment.

[0101] See also Figure 4 , the specific steps for attribution analysis are:

[0102] Based on the dynamic index of health status, the posture angle and pressure data are monitored, and the data value of each measurement time point is recorded in real time to obtain the time series data of posture and pressure;

[0103] Attitude angle data and pressure data are collected in real time, and the measurement data at each time point is recorded through multi-axis accelerometers and flexible pressure sensors. The collected raw data will be preprocessed, including removing noise interference and extreme outliers in the data. At the same time, the data will be standardized, and the attitude angle and pressure values ​​will be linearly scaled to the same dimensional range to ensure the comparability and consistency of the data in the time series. The processed data will be arranged in time order to form a time series. The attitude and pressure data at each time point are uniformly stored and managed to ensure continuity and integrity, and finally the attitude and pressure time series data are obtained.

[0104] Based on the time series data of posture and pressure, the fluctuation amplitude changes and trends are extracted, the average value and standard deviation in each window period are calculated, the key fluctuation patterns of the data are identified, and the fluctuation characteristic indicators are obtained;

[0105] First, the window partitioning method is called to segment the time series data. Each segment of data is statistically analyzed according to the set window period. For the data in each time period, the fluctuation amplitude of the posture angle and pressure data is calculated, and the data volatility is calculated by the standard deviation formula. At the same time, the average value of each segment of data is calculated to characterize the trend change. The statistical values ​​are classified and compared, and characteristic indicators with significant fluctuations and changing trends are extracted. At the same time, the time span of the characteristic indicators is further analyzed, and their occurrence frequency and duration are recorded. Finally, the fluctuation characteristic indicators are formed to identify potential key fluctuation patterns in the data.

[0106] Conduct attribution analysis on the fluctuation characteristic indicators, explore the correlation between data characteristics and health index, and obtain attribution analysis results;

[0107] An attribution analysis was conducted on the fluctuation characteristic indicators. By comparing the correlation between the health status dynamic index and each fluctuation characteristic indicator, a linear regression model was used to estimate the impact of each characteristic indicator on the health status. First, the fluctuation characteristic indicators and the health status dynamic index were mapped to the same time point and paired in chronological order. On this basis, the correlation coefficients of each fluctuation characteristic were evaluated through regression analysis, and the correlation coefficients were further tested for significance. The fluctuation characteristic indicators that were highly correlated with the health status dynamic index were extracted. At the same time, combined with the impact of the characteristic indicators, their driving force for changes in health status was analyzed, and finally the attribution analysis results were obtained.

[0108] See also Figure 5 , the steps for obtaining the risk factor warning signal are as follows:

[0109] Based on the attribution analysis results, identify the key risk factors affecting cervical spine health and obtain a list of risk factors;

[0110] Extract key risk factors from posture angle and pressure data, screen each factor one by one according to the identified risk factors, evaluate the significance of each factor through the contribution parameters (such as correlation coefficient or regression coefficient) calculated in the attribution analysis, and take the factors with higher significance as key risk factors. Then perform statistical analysis on the historical data of key risk factors, including calculating the mean, standard deviation and fluctuation range of each factor. Finally, generate a list of risk factors based on the significance ranking of risk factors and mark the statistical characteristics of each risk factor.

[0111] Based on the risk factor list, according to the cervical spine health standards and known health data, the health alert threshold is set using the formula:

[0112] ;

[0113] Get the risk factor threshold, where Indicates Health alert thresholds for key risk factors Representative The historical averages of the key risk factors Indicates The standard deviation of the risk factor, is the safety factor, used to adjust the sensitivity of the threshold;

[0114] Set thresholds for key risk factors (such as pressure fluctuations) and historical averages (The average value is calculated by the pressure fluctuation data of the past month), standard deviation (obtained by calculating the dispersion of data fluctuations), safety factor (Set according to industry standards and monitoring requirements), substitute each parameter into the formula:

[0115] ;

[0116] ;

[0117] The results show that for this risk factor (pressure fluctuation), when the real-time monitoring value exceeds the threshold When the risk factor is detected, a health alert will be triggered, indicating that the risk factor poses a threat to the health of the cervical spine.

[0118] Based on the risk factor threshold, the real-time value of each key risk factor is compared. If the real-time value exceeds the threshold, a risk factor alarm signal is obtained;

[0119] The real-time value of each risk factor is compared with the set alarm threshold one by one, and the changing trend of posture angle and pressure data is monitored in real time. For each key risk factor, the current value in the real-time monitoring data is called and the difference with the threshold is calculated to determine whether the real-time value exceeds the threshold. For all risk factors that exceed the threshold, they are marked as risks that trigger alarms, and corresponding alarm signals are generated. At the same time, the time corresponding to the alarm signal, the triggered risk factors, their real-time values ​​and thresholds are recorded. Finally, the triggered alarm signals are summarized to form a complete risk factor alarm signal set.

[0120] See also Figure 6 , the specific steps for obtaining intervention demand results are:

[0121] Based on the risk factor alarm signal, the current cervical spine posture angle and pressure data are monitored, and the data value at each time point is recorded to obtain the cervical spine data time series;

[0122] The posture angle and pressure data of the cervical spine are monitored in real time, the measured values ​​at each time point are recorded, and the data are organized into a complete time series in chronological order. The posture angle data is acquired through a gyroscope, accurate to the angle values ​​in the three-axis directions. The pressure data is recorded through a flexible pressure sensor and annotated with a timestamp. The posture angle and pressure value at each time point are used as a joint data point to generate a multidimensional time series. At the same time, the noise points in the time series are filtered and corrected to ensure the continuity and accuracy of the data, and finally the cervical spine data time series is obtained.

[0123] Perform statistical analysis on the cervical spine data time series, apply the autoregressive moving average model, evaluate the short-term and long-term trends of the data, determine the key change points of the cervical spine condition, and obtain the key change point analysis results;

[0124] The autoregressive moving average model is called to model the posture angles and pressure values ​​in the time series. The stationarity of the time series is analyzed by calculating the short-term fluctuations and long-term trends in a certain time window in the past, and the key feature points in the sequence are extracted. The rate of change of the posture angle is correlated with the fluctuation amplitude of the pressure value to identify the key points that cause cervical abnormalities. The specific data features of each key feature point are compared with the trend prediction value, and the key change points of the cervical condition are marked. Finally, the key change point analysis results are obtained.

[0125] Based on the results of the key change point analysis, the current health status and potential risks of the cervical spine are evaluated using the formula:

[0126] ;

[0127] Determine the necessity and urgency of intervention and obtain intervention demand results, among which, The intervention need index is used to determine whether intervention is needed for the cervical spine and the urgency of the intervention. Indicates The degree of deviation of a data point reflects the impact of the data point on the health status of the cervical spine. It is The weight of each data point reflects its importance to the overall health status. is the number of key data points;

[0128] Five key data points are obtained from the key change point analysis results, and their deviation degrees are as follows: The degree of deviation is obtained by calculating the difference between the actual state of each point and the reference value, and the weights are , the weight distribution is calculated according to the importance of each point, and the formula is:

[0129] ;

[0130] Calculate the numerator part:

[0131] ;

[0132] Calculate the denominator:

[0133] ;

[0134] Calculation results:

[0135] ;

[0136] The results show that the intervention need index is 19.75, indicating that there are significant deviations and risks in the health status of the cervical spine and immediate intervention measures are required. The index is directly used to judge the necessity and urgency of intervention in the future, thereby providing a basis for the recovery of cervical spine health.

[0137] See also Figure 7 , the specific steps for obtaining the cervical health intervention configuration are:

[0138] Based on the intervention need results, determine the type of intervention required, including posture adjustment or physical therapy, and obtain an intervention type table;

[0139] The degree of health deviation and weight parameters of the cervical spine involved in the intervention need index were analyzed, and the necessity and type of intervention measures were determined in combination with the range value of the health need index. For posture adjustment, the deviation degree index (such as pressure unevenness and angle deviation) was used to determine whether the sitting or standing posture needed to be adjusted, and the intervention priority was evaluated in combination with the areas with higher weights. For physical therapy, the cervical spine area that needed to be focused on was determined through the cumulative deviation value and the comprehensive impact range of the cervical spine health status, and the analyzed intervention types and their parameters were recorded one by one to form a tabular intervention type table.

[0140] Based on the intervention type table, combined with the patient's cervical spine condition and intervention urgency, the intervention frequency, treatment course time and physical therapy equipment (cervical traction device, cervical massage related equipment, electric heating pad and cervical corrector, etc.) are formulated to obtain the cervical health intervention configuration;

[0141] The required intervention information is extracted one by one from the two major categories of posture adjustment and physical therapy, combined with the patient's cervical spine status data, including health monitoring records of key parts and related intervention urgency analysis, and the corresponding intervention frequency and treatment course time are set. The specific time interval and execution time of each treatment course are determined according to the recovery cycle of the pressure deviation value, and the specification parameters of the equipment required for the corresponding physical therapy are called. By matching the patient's cervical spine treatment needs and equipment performance standards, a complete cervical spine health intervention configuration plan including intervention frequency, treatment course time and equipment configuration is finally obtained to ensure the feasibility and standardization of subsequent implementation and obtain the cervical spine health intervention configuration.

[0142] See also Figure 8 , the specific steps for obtaining the intervention effect response results are:

[0143] Based on the cervical health intervention configuration, the posture angle and pressure data of the cervical spine are continuously monitored, and the data difference before and after the intervention is collected to obtain the cervical status change data;

[0144] Continuously monitor the posture angle and pressure data of the cervical spine, obtain the posture angle data and pressure value data from the monitoring equipment respectively, record the data points before and after the intervention in real time, extract the difference in posture angle change and pressure change before and after the intervention by comparing and calculating the data at each time point, arrange them in time series, form two columns of data tables with the posture angle difference and pressure difference respectively, mark the corresponding time points as index values, associate the two columns of data, and form a comprehensive table containing the data difference before and after the intervention and the corresponding time points, which is used for further analysis of cervical spine state changes to obtain cervical spine state change data.

[0145] The cervical spine status change data was evaluated in real time, and the data changes before and after the intervention were analyzed using the formula:

[0146] ;

[0147] The results of intervention effect analysis were obtained, among which, represents the average response change rate before and after the intervention, Indicates The data value after the measurement intervention, Indicates The data value before the intervention was measured. Indicates the total number of measurements;

[0148] During the monitoring process, 4 pre- and post-intervention measurements were collected:

[0149] The data values ​​after intervention are:

[0150] , , , ;

[0151] The data values ​​before intervention are:

[0152] , , , ;

[0153] Substitute into the formula to calculate:

[0154] ;

[0155] ;

[0156] ;

[0157] The results show that the average response change at each measurement point after the intervention was 5, which means that the intervention measures have improved the cervical spine condition as a whole. The response change indicates that the intervention is effective. This result will be used to subsequently adjust the intervention direction or confirm the completion status of the intervention.

[0158] Based on the results of intervention effect analysis, the intervention effect is evaluated, the adjustment direction of the intervention process is optimized, the healthy cervical spine state is matched, and the intervention effect response results are obtained;

[0159] Call the cervical status change data table generated above, extract the difference information before and after the intervention, and calculate the deviation between the current difference and the ideal target value in combination with the ideal target value of the cervical health status. According to the size and direction of the deviation, determine whether the intervention process needs to be optimized and adjusted. The adjustment direction includes shrinking or expanding the range of posture angle changes and correcting the upper or lower limit of pressure changes. Generate a list of adjustment parameters and append them to the existing intervention configuration to ensure that the adjusted intervention measures are closer to matching the healthy cervical status, and finally form an intervention effect response result.

[0160] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent cervical vertebra status data monitoring system, characterized in that: The system comprises: The data monitoring and prediction module sets the cervical status monitoring parameters based on the posture angle and pressure data, makes a preliminary estimate of the health status by associating the change rate of the two, obtains the preliminary health probability, and monitors the change values ​​of the cervical posture and pressure in real time, updates the probability estimation, and obtains the health status dynamic index; The steps for making a preliminary probability estimate are as follows: Based on the attitude angle and pressure data, normalization processing is performed to optimize the measurement error and data deviation to obtain the attitude angle sequence and pressure sequence; Based on the posture angle sequence and the pressure sequence, a sliding window method is applied to calculate the real-time correlation coefficient, matching the data timeliness and the reaction speed to obtain a correlation coefficient sequence; Based on the correlation coefficient sequence, the formula is adopted: ； Perform a preliminary probability estimate of the health status and obtain a preliminary health probability, where: is the conditional probability, which means that given the data In case of health status The probability of represents an instance of the real-time correlation coefficient sequence, indicating the instantaneous correlation between the attitude angle sequence and the pressure sequence. and are the coefficients in the logistic regression model, represents the bias term, yes The weight of The steps for obtaining the health status dynamic index are specifically as follows: Based on the preliminary health probability, real-time monitoring data is performed to collect new measurements of posture angle and pressure data to obtain health probability update data; Based on the health probability update data, the probability estimate of the health state is updated according to the known health probability and the new measurement data to obtain a weighted health probability; Combined with the weighted health probability in continuous time, the formula is adopted: ； Calculate the dynamic index of health status, where Represents at time The dynamic index of health status, is the adjustment factor used to scale the calculated health index, Indicates at a point in time The probability of health, is the weight coefficient, for each time point Probability of health The weight assigned, is the time window length; The cervical risk analysis module monitors the fluctuation of posture angle and pressure data based on the health status dynamic index, performs attribution analysis based on the fluctuation amplitude change and data trend, compares with the health alarm threshold, identifies the key risk factors affecting cervical health, and obtains risk factor alarm signals; The cervical spine intervention formulation module analyzes the change trend of the current cervical spine posture angle and pressure data based on the risk factor alarm signal, determines the pertinence and criticality of the intervention, obtains the intervention demand results, formulates the intervention process according to the intervention demand results, including posture adjustment and physical therapy, and obtains the cervical spine health intervention configuration; The intervention effect evaluation module is based on the cervical spine health intervention configuration, continuously monitors the posture angle and pressure data of the cervical spine, collects the data difference before and after the intervention, and evaluates the intervention effect in real time, optimizes the adjustment direction of the intervention process, matches the healthy cervical spine state, and obtains the intervention effect response result.

2. The intelligent cervical vertebra status data monitoring system according to claim 1, characterized in that: The steps of performing attribution analysis are specifically as follows: Based on the health status dynamic index, the posture angle and pressure data are monitored, and the data value of each measurement time point is recorded in real time to obtain time series data of posture and pressure; Based on the time series data of the posture and pressure, the fluctuation amplitude changes and trends are extracted, the average value and standard deviation in each window period are calculated, the key fluctuation patterns of the data are identified, and the fluctuation characteristic indicators are obtained; An attribution analysis is performed on the fluctuation characteristic index, the correlation between the data characteristics and the health index is explored, and the attribution analysis result is obtained.

3. The intelligent cervical vertebra status data monitoring system according to claim 2, characterized in that: The steps of obtaining the risk factor warning signal are specifically as follows: Based on the attribution analysis results, identify key risk factors affecting cervical spine health and obtain a risk factor list; Based on the risk factor list, according to the cervical spine health standards and known health data, the health alert threshold is set using the formula: ； Get the risk factor threshold, where Indicates Health alert thresholds for key risk factors Representative The historical averages of the key risk factors Indicates The standard deviation of the risk factor, is the safety factor, used to adjust the sensitivity of the threshold; Based on the risk factor threshold, a comparison is made with the real-time value of each key risk factor, and if the real-time value exceeds the threshold, a risk factor alarm signal is obtained.

4. The intelligent cervical vertebra status data monitoring system according to claim 1, characterized in that: The steps for obtaining the intervention demand results are specifically as follows: Based on the risk factor alarm signal, monitor the current cervical vertebrae posture angle and pressure data, record the data value at each time point, and obtain the cervical vertebrae data time series; Performing statistical analysis on the cervical vertebra data time series, applying an autoregressive moving average model, evaluating the short-term and long-term trends of the data, determining the key change points of the cervical vertebra condition, and obtaining key change point analysis results; Based on the analysis results of the key change points, the current health status and potential risks of the cervical spine are evaluated using the formula: ； Determine the necessity and urgency of intervention and obtain intervention demand results, among which, represents the need index for intervention, Indicates The degree of deviation of the data points, It is The weight of the data point, is the number of key data points.

5. The intelligent cervical vertebra status data monitoring system according to claim 1, characterized in that: The steps for obtaining the cervical health intervention configuration are specifically as follows: Based on the intervention demand results, determining the required intervention type, including posture adjustment or physical therapy, and obtaining an intervention type table; Based on the intervention type table, combined with the patient's cervical spine condition and intervention urgency, the intervention frequency, treatment course time and physical therapy equipment are formulated to obtain the cervical spine health intervention configuration.

6. The intelligent cervical vertebra status data monitoring system according to claim 1, characterized in that: The steps for obtaining the intervention effect response result are specifically as follows: Based on the cervical health intervention configuration, the posture angle and pressure data of the cervical spine are continuously monitored, and the data difference before and after the intervention is collected to obtain the cervical status change data; The cervical vertebra status change data is evaluated in real time, and the data changes before and after the intervention are analyzed using the formula: ； The results of intervention effect analysis were obtained, among which, represents the average response change rate before and after the intervention, Indicates The data value after the measurement intervention, Indicates The data value before the intervention was measured. Indicates the total number of measurements; Based on the intervention effect analysis results, the intervention effect is evaluated, the adjustment direction of the intervention process is optimized, the healthy cervical spine state is matched, and the intervention effect response result is obtained.

Images