Cancer survivor working pressure monitoring system based on big data

Abstract

The invention relates to the technical field of health monitoring, in particular to a cancer surviver working pressure monitoring system based on big data, which comprises a physiological parameter analysis module, a pressure inducement analysis module, a working load distribution module and an abnormal pressure monitoring module. According to the method, through difference analysis of heart rate fluctuation, skin conductance and blood pressure ranges, sensitivity and accuracy of data analysis are improved, data points with large fluctuation are screened and classified, abnormal data capture and classification efficiency is optimized, pressure inducement recognition precision and distribution law insight are improved, key pressure factors are clarified through sensitivity sorting, and the accuracy of data analysis is improved. The pressure assessment is more scientific and quantitative, priority dynamic adjustment, working pressure distribution optimization, abnormal pressure point monitoring enhancement and grading judgment are realized in load classification and grouping, pressure abnormity grade fine monitoring is realized, data quantification and dynamic monitoring capability is enhanced, pressure management efficiency is improved, and the method is suitable for large-scale popularization and application. And targeted data support is provided for personalized health intervention.

Description

Technical Field

[0001] The present invention relates to the technical field of health monitoring, and in particular to a work stress monitoring system for cancer survivors based on big data. Background Art

[0002] The field of health monitoring technology includes technologies for monitoring, recording and analyzing human health status through computer technology, data analysis technology and information processing technology. The core content of this technology field is based on the collaborative application of big data, sensor technology and information technology, which is used to collect and process personal health data in real time, thereby realizing comprehensive monitoring and evaluation of individual health-related status. The overall technology field mainly covers the collection, storage, management and analysis of health data, including stress monitoring, sleep monitoring, exercise monitoring, etc. Through precise data processing and dynamic monitoring, it provides data support and decision-making reference for health management.

[0003] Among them, the cancer survivor work stress monitoring system refers to a system that monitors and analyzes the psychological and physiological stress status of individuals in the workplace during the cancer recovery stage. The patent subject is mainly aimed at the special needs of cancer survivors. Through big data collection technology, multi-dimensional data collection of stress factors in work scenarios is carried out, including work environment data, task load data and physiological status data. Specifically, it is based on the collection of individual physiological parameters such as heart rate and skin conductance by sensors, combined with data analysis technology to dynamically quantify work stress, and use data mining technology to identify the patterns and influencing factors of individual stress changes, ultimately forming a panoramic monitoring and analysis of the stress status.

[0004] Existing technologies lack the ability to accurately capture and deeply analyze the range of changes and fluctuations of physiological parameters in stress monitoring. They can only make basic records of physiological parameters, and it is difficult to effectively identify drastic fluctuations and abnormal states in a short period of time. Since stress cause analysis mainly relies on a single-dimensional data source and ignores the interactive effects of multiple stress factors such as physiological parameters and task intensity, the identification of stress sources is one-sided and key stress causes cannot be accurately located. In terms of workload management, existing technologies find it difficult to dynamically adjust load priorities, and the matching degree between work tasks and stress is low. It is impossible to optimize the work allocation model according to the individual needs of cancer survivors. In terms of abnormal pressure monitoring, existing technologies are mostly static threshold warnings, which cannot dynamically evaluate the fluctuation amplitude and distribution characteristics of node pressure, resulting in delayed monitoring of abnormal pressure and failure to promptly detect and intervene in high-risk stress states, resulting in insufficient monitoring accuracy, missing identification of key causes, and delayed abnormal pressure management, thereby affecting the comprehensiveness and timeliness of health management. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and propose a work stress monitoring system for cancer survivors based on big data.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A cancer survivor work stress monitoring system based on big data comprises:

[0007] The physiological parameter analysis module performs differential analysis on the heart rate variation range and skin conductance fluctuation amplitude within a time period based on the heart rate fluctuation, skin conductance and blood pressure range of cancer survivors, and screens and classifies the data points with large fluctuations to generate physiological parameter fluctuation characteristic results;

[0008] The stress inducement analysis module compares the heart rate fluctuation amplitude, skin conductance difference and task intensity in the data points one by one based on the physiological parameter fluctuation characteristic results, generates a stress inducement difference set, sorts the parameter fluctuation range in the stress inducement difference set by sensitivity, and generates a stress inducement key distribution result;

[0009] The workload distribution module classifies and groups the task intensity, working time and stress peak of the cancer survivors item by item based on the key distribution results of the stress inducers to obtain workload classification data, and prioritizes the load intensity of the classification intervals in the workload classification results to generate a load adjustment path result;

[0010] Based on the load adjustment path results, the abnormal pressure monitoring module analyzes the task intensity distribution of the node pressure and the distribution of the pressure fluctuation amplitude, generates an abnormal pressure distribution data set, and classifies the distribution and fluctuation amplitude of the abnormal pressure points to generate pressure abnormality grade classification monitoring results.

[0011] As a further solution of the present invention, the steps of obtaining the physiological parameter fluctuation characteristic results are specifically as follows:

[0012] Based on the heart rate fluctuations, skin conductance, and blood pressure ranges of cancer survivors, the range of heart rate in each time period was analyzed, and the standard deviation was calculated through skin conductance data to obtain a characteristic data table of heart rate variation range and skin conductance fluctuation amplitude;

[0013] The heart rate variation range and the skin conductance fluctuation amplitude characteristic data table are analyzed for differences using the formula:

[0014]

[0015] Calculate the difference index value;

[0016] Among them, D represents the difference index value, HR max Represents the maximum heart rate during the monitoring period, HR minRepresents the minimum value of the heart rate during the monitoring period, σ SC represents the standard deviation of skin conductance fluctuation amplitude, w1 and w2 are weight parameters;

[0017] Based on the difference index value, a threshold parameter is set, a logical judgment is made on the difference index, fluctuation data points satisfying the difference index being greater than the threshold are screened, data points meeting the conditions are counted and classified, and a physiological parameter fluctuation characteristic result is generated.

[0018] As a further solution of the present invention, the step of obtaining the stress-inducing factor difference set is specifically:

[0019] Based on the physiological parameter fluctuation characteristic results, extract the heart rate fluctuation amplitude values ​​in the data points, sort the values ​​and classify them into a set, extract the skin conductance difference values ​​and the task intensity values ​​and sort them, and obtain the physiological parameter sorting results;

[0020] Based on the physiological parameter sorting results, the heart rate fluctuation amplitude is selected, the difference between adjacent data points is analyzed, the skin conductance difference is processed according to the difference calculation rule of adjacent data points, the task intensity value change is counted, and a parameter change difference set is obtained;

[0021] Based on the parameter change difference set, the heart rate fluctuation and skin conductance difference set are read, the regions are divided according to the value range, the number of data points in the region is counted, the related data region is filtered, and the stress inducement difference set is obtained.

[0022] As a further solution of the present invention, the steps for obtaining the key distribution results of the pressure inducement are specifically as follows:

[0023] According to each parameter in the stress-inducing difference set, by statistically analyzing the fluctuation range of the parameter, identifying the standard deviation and mean of the fluctuation amplitude, analyzing the parameter fluctuation characteristics, using the standard deviation to reflect the discreteness of the fluctuation degree, judging the corresponding size of the fluctuation level, and generating a fluctuation characteristic set;

[0024] Based on the fluctuation feature set, the sensitivity of each parameter is weighted and sorted according to the weight. The calculation formula is:

[0025]

[0026] Generate a ranked list of stress-inducing sensitivities;

[0027] Among them, S represents the sensitivity ranking value, M i represents the weight coefficient of parameter i, σ i represents the standard deviation of parameter i, μ i represents the mean of parameter i, n represents the total number of parameters, and ∑ represents the summation symbol;

[0028] Based on the sorted stress inducer sensitivity list, by comparing the impact of each parameter sensitivity on the stress inducer distribution, the fluctuation characteristics of the weight parameters in the sensitivity sorting are screened, the sensitivity parameters are selected as key stress inducers, and the stress inducer key distribution results are established.

[0029] As a further solution of the present invention, the step of acquiring the workload classification data is specifically as follows:

[0030] Based on the key distribution results of the stress inducers, the task intensity impact range analysis is performed, the working hours and stress peaks are compared and classified respectively, and the correlation parameters are calculated, and the low-correlation task intensity data are eliminated to obtain the workload distribution parameters;

[0031] For the workload distribution parameters, the task intensity, working time and pressure peak data are grouped and classified, the mean value, standard deviation and coefficient of variation of the characteristic value of each group of data are identified, and the load distance is calculated using the formula:

[0032]

[0033] Obtaining workload characteristic distance parameters;

[0034] Where L represents the load distance, T a represents the single task intensity, T m represents the overall mean of task intensity, W a Represents the single-task working time, W m represents the overall mean of working time, and P represents the peak stress of a single task;

[0035] According to the workload characteristic distance parameters, group analysis and load distance screening are performed, task intensity, working time and pressure peak load distance are sorted and the screening characteristic values ​​are marked, and classification is performed according to load distance to obtain workload classification data.

[0036] As a further solution of the present invention, the step of obtaining the load adjustment path result is specifically:

[0037] Based on the workload classification result, extract the load intensity of the classification interval, sort the load intensity values ​​and check them one by one, record the corresponding order and value of the load intensity of the classification interval after sorting, and generate the load intensity sorting result;

[0038] Based on the load intensity sorting result, priority is allocated in sequence, priority numbers are set for each load intensity value and corresponded, the distribution order of the priority numbers is recorded, the mapping relationship between the priority numbers and the load intensity of the classification interval is analyzed, and the load priority allocation result is obtained;

[0039] Based on the load priority allocation result, the load intensity of the classification interval is adjusted item by item, the adjustment path is determined in combination with the priority number, the adjusted load intensity value is compared with the load intensity value before the adjustment, the adjustment path parameter changes and the adjustment range are recorded, and the load adjustment path result is generated.

[0040] As a further solution of the present invention, the step of acquiring the abnormal pressure distribution data set is specifically:

[0041] Based on the load adjustment path result, the time series information in the node pressure data is called, the task intensity distribution and the pressure fluctuation amplitude are normalized, the time series data is divided into fixed intervals and the fluctuation amplitude is compared to see whether it exceeds a threshold value, and the pressure fluctuation classification result is obtained;

[0042] The task intensity distribution and pressure fluctuation amplitude data in the pressure fluctuation classification results are analyzed using the formula:

[0043]

[0044] The pressure anomaly distribution coefficient is calculated;

[0045] Among them, Q represents the pressure anomaly distribution coefficient, P max Represents the maximum pressure, P avg represents the average value of pressure, σ P Represents the standard deviation of pressure, T max Represents the maximum value of task intensity, T min represents the minimum value of task intensity;

[0046] According to the pressure anomaly distribution coefficient, the screened abnormal node pressure data is reclassified, the pressure fluctuation amplitude of the abnormal node is linked to the corresponding task intensity for analysis, the abnormal data is marked according to the amplitude of the task intensity change, and an abnormal pressure distribution data set is generated.

[0047] As a further solution of the present invention, the steps for obtaining the pressure abnormality level classification monitoring result are specifically as follows:

[0048] Based on the abnormal pressure distribution data set, the pressure value and fluctuation amplitude of the pressure point data are extracted, the data is classified and processed, and the pressure mean and standard deviation are calculated, and the data with a standard deviation lower than the set threshold are eliminated to obtain a preliminary screening result of the pressure value;

[0049] Based on the preliminary screening results of the pressure values, the pressure points are graded and judged, and the pressure level of each pressure point is analyzed using the formula:

[0050]

[0051] Calculate the pressure level score and generate the pressure point level judgment result;

[0052] Among them, Y represents the pressure level score, H represents the pressure value, μ P is the mean value of pressure, N is the standard deviation of pressure, ΔP represents the pressure change rate, and λ is the weight coefficient adjusted according to the self-matching of data distribution;

[0053] The level judgment results of the pressure points are summarized, and the data set is classified and statistically analyzed according to the number and distribution characteristics of the differentiated level pressure points, the pressure range and typical fluctuation characteristics are marked, and the pressure abnormality level classification monitoring results are generated.

[0054] Compared with the prior art, the advantages and positive effects of the present invention are:

[0055] In the present invention, by analyzing the difference of heart rate fluctuation, skin conductance and blood pressure range, the change range and fluctuation amplitude of physiological parameters within a time period are accurately quantified, the sensitivity and accuracy of data analysis are significantly improved, the data points with large fluctuations are screened and classified, and the capture efficiency and classification accuracy of abnormal data are optimized. By comparing the results of physiological parameter fluctuations item by item and analyzing them in multiple dimensions, combined with the correlation analysis of indicators such as heart rate fluctuation amplitude, skin conductance difference and task intensity, the recognition accuracy and insight into the distribution law of stress inducers are improved. Based on the sensitivity sorting of the stress inducement difference set, the key influencing factors in stress changes are clarified, making stress assessment more scientific and quantitative. In terms of load classification and grouping of task intensity, working time and stress peak, the work pressure distribution is optimized through dynamic adjustment of load intensity priority, providing more reasonable workload suggestions for cancer survivors, strengthening the monitoring ability of abnormal pressure points through comprehensive analysis of node pressure distribution and pressure fluctuation amplitude, and realizing refined monitoring of abnormal pressure levels through graded judgment of abnormal pressure points. The overall processing logic optimizes the full-link processing flow from physiological data to stress status, enhances the ability to accurately quantify data and dynamically monitor stress status, significantly improves the efficiency of stress management in the work environment of cancer survivors, and provides more targeted data support for personalized health interventions. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a system flow chart of the present invention;

[0057] Figure 2 It is a flow chart of the physiological parameter fluctuation characteristic results in the present invention;

[0058] Figure 3 A flow chart of the differential set of stress inducers in the present invention;

[0059] Figure 4It is a flow chart of the key distribution results of the pressure inducement in the present invention;

[0060] Figure 5 A flow chart for workload classification data in the present invention;

[0061] Figure 6 A flow chart showing the load adjustment path results in the present invention;

[0062] Figure 7 A flow chart of an abnormal pressure distribution data set in the present invention;

[0063] Figure 8 It is a flow chart of the pressure anomaly level classification monitoring results in the present invention. DETAILED DESCRIPTION

[0064] 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.

[0065] 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" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the 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, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0066] See also Figure 1 The big data-based work stress monitoring system for cancer survivors includes:

[0067] The physiological parameter analysis module performs differential analysis on the heart rate variation range and skin conductance fluctuation amplitude within a time period based on the heart rate fluctuation, skin conductance and blood pressure range of cancer survivors, and screens and classifies the data points with large fluctuations to generate physiological parameter fluctuation characteristic results;

[0068] Based on the results of physiological parameter fluctuation characteristics, the stress cause analysis module compares the heart rate fluctuation amplitude, skin conductance difference and task intensity in the data points one by one, generates a stress cause difference set, sorts the sensitivity of the parameter fluctuation range in the stress cause difference set, and generates the key distribution results of stress causes;

[0069] Based on the key distribution results of stress factors, the workload distribution module classifies and groups the task intensity, working hours and stress peak of cancer survivors item by item to obtain workload classification data, and prioritizes the load intensity of the classification intervals in the workload classification results to generate load adjustment path results.

[0070] The abnormal pressure monitoring module analyzes the task intensity distribution of node pressure and the distribution of pressure fluctuation amplitude based on the load adjustment path results, generates an abnormal pressure distribution data set, and classifies the distribution and fluctuation amplitude of abnormal pressure points to generate pressure abnormality grade classification monitoring results.

[0071] The results of physiological parameter fluctuation characteristics include differences in heart rate variation range, differences in skin conductance fluctuation amplitude, and classification of fluctuation data points. The set of stress inducer differences includes differences in heart rate fluctuation amplitude, skin conductance, and task intensity. The key distribution results of stress inducers include sensitive parameter sorting, stress inducer distribution location, and fluctuation range characteristics. Workload classification data includes task intensity classification, working time classification, and pressure peak classification. The load adjustment path results include classification interval load priority, load adjustment optimization path, and load distribution optimization plan. The abnormal pressure distribution data set includes task intensity distribution, pressure fluctuation amplitude distribution, and abnormal pressure point distribution. The pressure abnormality level classification monitoring results include abnormal pressure classification, pressure fluctuation amplitude classification, and pressure level division.

[0072] See also Figure 2 , the specific steps for obtaining the physiological parameter fluctuation characteristic results are:

[0073] Based on the heart rate fluctuations, skin conductance, and blood pressure ranges of cancer survivors, the range of heart rate in each time period was analyzed, and the standard deviation was calculated through skin conductance data to obtain a characteristic data table of heart rate variation range and skin conductance fluctuation amplitude;

[0074] The heart rate variation range and skin conductance fluctuation amplitude data of cancer survivors during the monitoring period were extracted. The monitoring data were recorded with time as the axis, and abnormal data points were removed through preprocessing. For the heart rate data, the valid interval of the data was first set according to the physiological range, and all data points beyond the valid interval were marked and deleted. After deletion, the interpolation method was used to supplement the vacant areas in the data to ensure the integrity of the time series. For the skin conductance data, it was segmented into fixed time periods, and the skin conductance values ​​in each time period were statistically analyzed for distribution. The average and maximum values ​​in the time period were extracted, and the degree of fluctuation was quantified by calculating its standard deviation. After the time series data was segmented, the fluctuation trend between different time periods could be further analyzed according to the length of the designated time period. The processing results of the heart rate data and the skin conductance fluctuation amplitude data were summarized to construct the heart rate variation range and skin conductance fluctuation amplitude feature data table. The feature data table uses the time period as the sequence index, and lists the maximum and minimum values ​​of the heart rate data and the fluctuation amplitude of the skin conductance in each time period, providing complete feature data support for subsequent difference analysis and screening.

[0075] The heart rate variation range and skin conductance fluctuation amplitude characteristic data table are analyzed by using the formula:

[0076]

[0077] Calculate the difference index value;

[0078] Among them, D represents the difference index value, HR max Represents the maximum heart rate during the monitoring period, HR min Represents the minimum value of the heart rate during the monitoring period, σ SC represents the standard deviation of skin conductance fluctuation amplitude, w1 and w2 are weight parameters;

[0079] The benefit of the formula is that by combining two different types of data, the heart rate variation range and the skin conductance fluctuation amplitude, into a single indicator and adjusting the relative influence of the two through the weight parameter, it can more intuitively reflect the fluctuation differences in individual physiological states. At the same time, the denominator smoothing function is used to effectively reduce the impact of extreme data points on the results, thereby increasing the robustness of the indicator.

[0080] Assume that the maximum heart rate during the monitoring period is 140, the minimum heart rate is 70, the standard deviation of skin conductance fluctuation is 2.5, and the weight parameters are 1.5 and 0.8 respectively. Substitute them into the formula and calculate as follows:

[0081] Calculate heart rate difference: |HR max -HR min |=|140-70|=70;

[0082] Calculate the molecular part: |HRmax -HR min |+w1·σ SC =70+1.5·2.5=70+3.75=73.75;

[0083] Calculate the denominator:

[0084] Calculate the difference index:

[0085] The result shows that the difference index value is 27.61, indicating that the individual heart rate changes and skin conductance fluctuations in the current time period are relatively different. The value will be used as a screening basis in subsequent steps to determine the significance of the individual fluctuation state.

[0086] Based on the difference index value, the threshold parameter is set, the difference index is logically judged, the fluctuation data points that meet the difference index greater than the threshold are screened, the data points that meet the conditions are counted and classified, and the physiological parameter fluctuation characteristic results are generated;

[0087] First, the screening logic is set. The logic judgment process needs to be based on the predefined difference threshold, and the difference indicators are grouped and processed. The threshold is used as the distinction standard to determine whether the difference indicator of each time period is greater than or less than the threshold. If the difference indicator is greater than the threshold, the time period is marked as a significant fluctuation interval. The difference indicators of the significant fluctuation interval are further analyzed, and the specific characteristic values ​​of the heart rate changes and skin conductance fluctuations in each significant fluctuation interval are compared. They are divided into different categories by summarizing similar characteristics. The specific classification rules are set based on the range of heart rate changes and the level of skin conductance fluctuations. At the same time, in order to ensure the classification accuracy, the characteristic values ​​of adjacent time periods are compared. If the characteristic value change trends of consecutive time periods are consistent, the time periods are merged into the same category. Through point-by-point analysis and classification operations, the physiological parameter fluctuation characteristic results are generated, and the classification attribution, characteristic value range and difference indicator status of each time period are recorded in detail.

[0088] See also Figure 3 , the specific steps for obtaining the pressure-induced difference set are:

[0089] Based on the results of physiological parameter fluctuation characteristics, the heart rate fluctuation amplitude values ​​in the data points are extracted, the values ​​are sorted and classified into a set, the skin conductance difference values ​​and task intensity values ​​are extracted and sorted, and the physiological parameter sorting results are obtained;

[0090] First, determine the upper and lower limits of the heart rate fluctuation amplitude, and divide the fluctuation amplitude interval into intervals of 5bpm. For example, for a heart rate fluctuation amplitude in the range of 50 to 150bpm, it can be divided into 20 intervals. After each data point is classified into the corresponding interval, the number of data points in each interval is counted, and the average heart rate fluctuation amplitude of each interval is calculated. The degree of dispersion of the data points in each interval is evaluated by variance analysis, and the skin conductance difference value and task intensity value are extracted and sorted. For the skin conductance data, the difference value of adjacent time points is calculated based on the continuous data sampled per second, and the mean and fluctuation range of the difference value are recorded. At the same time, the task intensity value is segmented and classified. For example, the task intensity is divided into three levels: low (0-3), medium (4-7) and high (8-10). The matching degree of the average skin conductance difference value and the heart rate fluctuation amplitude corresponding to each level of task intensity is calculated respectively, and finally the physiological parameter sorting result is formed.

[0091] Based on the results of physiological parameter sorting, the heart rate fluctuation amplitude is selected, the difference between adjacent data points is analyzed, the skin conductance difference is processed according to the difference calculation rules of adjacent data points, the numerical changes of task intensity are counted, and the parameter change difference set is obtained;

[0092] First, the difference set between two consecutive data points of the heart rate fluctuation amplitude is extracted according to the time series. For example, for the heart rate fluctuation amplitude data points [60, 65, 70, 68], the difference between adjacent points is calculated as [5, 5, -2], and the average value and change direction of the difference are recorded. For the skin conductance difference value, according to the difference calculation rule of adjacent data points, the absolute value threshold of the difference is set to 0.05μS, and the proportion of data points exceeding this threshold is counted. At the same time, the difference set exceeding the threshold is classified into the high change group, and the rest is classified into the low change group. The average difference and maximum difference of the two groups of data are calculated, and the numerical change of task intensity is counted. According to the time series of task intensity, the standard deviation of task intensity is calculated in a sliding window manner (for example, every 10 minutes), and the corresponding analysis is performed with the change trend of heart rate fluctuation and skin conductance difference. Finally, a parameter change difference set containing the linkage relationship between heart rate, skin conductance and task intensity is obtained.

[0093] Based on the parameter change difference set, read the heart rate fluctuation and skin conductance difference set, divide the area according to the value range, count the number of data points in the area, filter the related data area, and obtain the stress inducement difference set;

[0094] First, the difference set of heart rate fluctuations is divided into low-amplitude interval (0-5bpm), medium-amplitude interval (6-10bpm) and high-amplitude interval (>10bpm) according to the fluctuation amplitude. The skin conductance difference set is divided into low-difference interval (0-0.05μS), medium-difference interval (0.06-0.1μS) and high-difference interval (>0.1μS) according to the absolute value. The number of data points in each interval is counted. For example, there are 50 data points recorded in the low-amplitude interval. The proportion of data points in each interval is calculated respectively, and the data points with significant changes in task intensity are further screened to extract the corresponding heart rate fluctuation and skin conductance difference interval ranges. When screening the associated data area, the threshold condition is set as the simultaneous occurrence of events when the heart rate fluctuation difference exceeds 6bpm and the skin conductance difference is higher than 0.05μS. This is used to mark the stress-inducing area, and the number of regional data points is counted. The average heart rate fluctuation difference and skin conductance difference in the area are recorded to form a stress-inducing difference set for further analysis of subsequent work stress monitoring.

[0095] See also Figure 4 , the specific steps for obtaining the key distribution results of pressure inducers are:

[0096] According to each parameter in the pressure-induced difference set, the fluctuation range of the parameter is statistically analyzed, the standard deviation and mean of the fluctuation range are identified, the parameter fluctuation characteristics are analyzed, the standard deviation is used to reflect the discreteness of the fluctuation degree, the corresponding size of the fluctuation level is determined, and the fluctuation characteristic set is generated;

[0097] First, the historical data set of each parameter is collected, the data is arranged in chronological order, and its changing trend is fitted through a linear regression model to obtain the fluctuation range of each parameter in the entire time period. Then, the standard deviation and mean of each parameter are calculated respectively. The standard deviation reflects the discreteness of the fluctuation value of each parameter, and the mean reflects the concentration level of the parameter. By comparing the ratio of the standard deviation to the mean, the parameter set with a larger fluctuation range is further identified, and the parameter fluctuation range is correlated with the corresponding time point for analysis. Through time series analysis, the parameters with significant fluctuation characteristics are further extracted to generate a fluctuation feature set, which represents the fluctuation range and distribution trend of each parameter.

[0098] Based on the fluctuation feature set, the sensitivity of each parameter is weighted and ranked according to the weight. The calculation formula is:

[0099]

[0100] Generate a ranked list of stress-inducing sensitivities;

[0101] Among them, S represents the sensitivity ranking value, M i represents the weight coefficient of parameter i, σ i represents the standard deviation of parameter i, μ irepresents the mean of parameter i, n represents the total number of parameters, and ∑ represents the summation symbol;

[0102] The benefit of the formula is that by introducing the weight coefficient w of the parameter i and the standard deviation of the fluctuation characteristics σ i and mean μ i The ratio of can accurately weight the fluctuation sensitivity of each parameter to highlight the role of high-volatility and important parameters in the ranking;

[0103] First, the parameter i in the pressure-induced difference set is collected, its historical data is extracted, and the standard deviation of each parameter is calculated. and mean where x ij represents the observed value of parameter i at time point j, represents the mean value of parameter i, m represents the number of observations, and then it is calculated according to the above formula The ratio of and assign weight w to each parameter i (The weights are set according to the importance of the parameters, which are determined by expert ratings or historical data analysis), and the sensitivity rankings after weight adjustment are compared to calculate the final sensitivity ranking value S;

[0104] For example, for three parameters A, B, and C, assuming that σ is obtained through monitoring data A =3,μ A =15,M A =0.4,σ B =2,μ B =10,M B =0.3,σ C =5,μ C =20,M C =0.3;

[0105] Substituting the values ​​into the formula:

[0106] The results show that the sensitivity ranking values ​​obtained by comprehensively considering parameter volatility and importance can reflect the comprehensive influence of each parameter in stress inducers, and finally generate a ranked stress inducer sensitivity list.

[0107] Based on the sorted stress inducer sensitivity list, by comparing the impact of each parameter sensitivity on the stress inducer distribution, the fluctuation characteristics of the weight parameter in the sensitivity sorting are screened, the sensitivity parameter is selected as the key stress inducer, and the key distribution result of the stress inducer is established;

[0108] First, a set of parameters with higher sensitivity values ​​is extracted, and the sensitivity ranking values ​​are mapped to the corresponding parameters. A screening threshold is set based on the distribution range of the sensitivity ranking values, and parameters with sensitivity values ​​exceeding the threshold are screened. The screened parameter set is further cross-analyzed with the fluctuation feature set. Combined with the time series fluctuation trend of the parameters in the fluctuation feature set, the parameters with higher sensitivity values ​​and significant fluctuations are focused on. By comparing the fluctuation effects of different parameters one by one, the parameter set with the highest sensitivity ranking is selected as the key stress inducer, and finally the key distribution result of the stress inducer is established.

[0109] See also Figure 5 ,The specific steps for obtaining workload classification data are:

[0110] Based on the key distribution results of stress inducers, the task intensity impact range analysis was conducted, the working hours and stress peaks were compared and classified, and the correlation parameters were calculated. The low-correlation task intensity data were eliminated to obtain the workload distribution parameters.

[0111] Task intensity is determined by extracting the number of executions and time proportion of a single task, establishing a data sequence with time as the horizontal axis, and calculating the average number of executions and deviation amplitude of each task in the sequence. Working time is divided into intervals by collecting the start and end times of work within a unit cycle, defining the interval length as the working time, and evaluating the distribution range and fluctuation of each working interval within the cycle. Peak stress is calculated by calculating the fluctuation rate of physiological parameters per unit time during the monitoring process, calculating the maximum rate of change of physiological parameters and taking the rate as the peak value, and quantitatively evaluating the correlation between task intensity, working time and peak stress, constructing the coordinated change relationship between each parameter, and eliminating low-correlation items that do not meet the requirements through the correlation threshold. Finally, the parameter value range that meets the correlation requirements in task intensity, working time and peak stress is screened to obtain the workload distribution parameters.

[0112] For workload distribution parameters, task intensity, working time and pressure peak data are grouped and classified, the mean, standard deviation and coefficient of variation of each group of data characteristic values ​​are identified, and the load distance is calculated using the formula:

[0113]

[0114] Obtaining workload characteristic distance parameters;

[0115] Where L represents the load distance, T a represents the single task intensity, T m represents the overall mean of task intensity, W a Represents the single-task working time, W m represents the overall mean of working time, and P represents the peak stress of a single task;

[0116] The benefit of the formula is that by jointly considering the mean deviation of task intensity and working time, combined with the normalization of stress peak, it can simultaneously evaluate the joint load characteristics of work tasks and stress, thereby improving the accuracy and adaptability of classification;

[0117] Among them, the task intensity data is calculated by the average value of the time series distribution. Assuming that 5 sets of task intensity data are collected, which are 2.4, 3.1, 2.8, 3.6, and 3.0 respectively, the mean value of the task intensity is:

[0118]

[0119] The single-task intensity deviation is calculated according to the formula:

[0120] (T a -T m ) 2 =(2.4-3.0) 2 =0.36;

[0121] Assume that the five sets of pressure peak values ​​are 120, 135, 125, 140, and 130. Calculate the parameter P by normalizing the pressure peak values:

[0122]

[0123] For the working time data, its mean and single-task deviation are calculated using the same method and substituted into the formula:

[0124]

[0125] Assume that the average working time is 8 hours and the single task working time is 7 hours, then:

[0126]

[0127] The result shows that the smaller the load distance quantification result L is, the lower the deviation of task intensity and working time relative to the pressure peak is, which meets the load balance requirements.

[0128] According to the workload characteristic distance parameters, group analysis and load distance screening are performed, task intensity, working time and pressure peak load distance are sorted and the screening characteristic values ​​are marked, and classification is performed according to load distance to obtain workload classification data;

[0129] First, the calculated task intensity, working time and load distance of stress peak are sorted, and the tasks and working time are associated and labeled according to each group of load distance range. The labeling process divides the group range according to the upper and lower limits of the load distance. The group with a load distance less than 0.2 is defined as "low load", the group with a load distance greater than 0.2 and less than 0.5 is defined as "medium load", and the group with a load distance greater than 0.5 is defined as "high load". When the task intensity is labeled by the grouping of load distance, the task feature data in the corresponding group is called, and the stress peak is re-divided into intervals based on the median of the load distance. Finally, combined with the data characteristics after grouping, the labeling results of the load grouping are generated and the feature values ​​of each group are reclassified to obtain the workload classification data.

[0130] See also Figure 6 , the steps for obtaining the load adjustment path result are as follows:

[0131] Based on the workload classification results, extract the load intensity of the classification interval, sort the load intensity values ​​and check them one by one, record the corresponding order and value of the load intensity of the classification interval after sorting, and generate the load intensity sorting result;

[0132] First, the workload data is divided into three levels: hourly, daily, and weekly according to different time intervals, and the load intensity values ​​of each level are extracted. For example, the load intensity is calculated from the number of task completions recorded every hour. The load intensity is normalized to the range of 0-100 to ensure the comparability of different data sources. The normalized load intensity values ​​are sorted from high to low, and the values ​​are checked one by one to ensure the accuracy of the sorting results. The order and values ​​of the load intensity of the sorted classification intervals are recorded. For example, within a week, the daily load intensity is recorded in sequence as [85, 78, 72, 65, 50, 45, 30], and the basis for the division of high, medium, and low load intervals is marked, for example, the high load interval is 70-100, the medium load interval is 40-69, and the low load interval is 0-39. The load intensity sorting results are generated, and the mean, maximum, and minimum values ​​of the load intensity of each classification interval are counted and sorted separately to provide data support for subsequent priority allocation analysis.

[0133] Based on the load intensity sorting results, priorities are assigned in sequence, priority numbers are set for each load intensity value and corresponded, the priority number distribution order is recorded, the mapping relationship between the priority number and the load intensity of the classification interval is analyzed, and the load priority allocation result is obtained;

[0134] Set priority numbers for each load intensity value and make corresponding correspondences. Assign priority numbers in descending order according to the load intensity sorting results. For example, mark the classification interval with the highest load intensity as priority 1, and the second highest as priority 2, and so on, until all classification intervals are assigned priority numbers. Record the distribution order of priority numbers, and clarify the correspondence between priority and load intensity. For example, in the load data of one week, if the sorted load intensity is [85, 78, 72, 65, 50, 45, 30], the corresponding priority numbers are 1 to 7. Analyze the mapping relationship between priority numbers and classification interval load intensity. By calculating the proportion of load intensity corresponding to each priority number, for example, the proportion of load intensity of priority 1 to the total load intensity is 85 / 425≈20%, evaluate the concentration of high-priority tasks, and further combine the work characteristics of cancer survivors to identify key data points that cause stress in the high-load interval, mark the positions of these data points in the sorting, and form a load priority allocation result to guide the formulation of subsequent load adjustment strategies.

[0135] Based on the load priority allocation result, adjust the load intensity of the classification interval item by item, determine the adjustment path based on the priority number, compare the load intensity value after adjustment with that before adjustment, record the change of adjustment path parameters and adjustment range, and generate the load adjustment path result;

[0136] First, the load intensity intervals corresponding to high priority numbers are extracted. For example, in the interval of priority 1 to 3, the time distribution trend and maximum fluctuation range of the load intensity are recorded, and whether there is an obvious overload in the interval is analyzed. The adjustment path is achieved by introducing a buffer zone in the high-load interval, and part of the load in the high-load interval is moved to the medium-load interval. For example, in daily work, the task volume in the high-load interval is controlled to less than 30% of the total load intensity, and the medium-load interval is filled at the same time. The adjusted load intensity value is compared with the value before and after the adjustment. The adjustment effect is evaluated by calculating the load mean change, standard deviation change and high-load interval proportion change before and after the adjustment. The adjustment path parameter changes and adjustment amplitude, such as the buffer amount, adjustment step size and target value difference of the adjustment path, are recorded. Finally, the load adjustment path result is generated. The result provides a specific data basis for load optimization, supports personalized stress intervention for cancer survivors, and provides a reference for adjustment strategies for further work stress monitoring.

[0137] See also Figure 7 , the specific steps for obtaining the abnormal pressure distribution data set are:

[0138] Based on the load adjustment path results, the time series information in the node pressure data is called, the task intensity distribution and the pressure fluctuation amplitude are normalized, the time series data is divided into fixed intervals and the fluctuation amplitude is compared to see whether it exceeds the threshold, and the pressure fluctuation classification result is obtained;

[0139] The time series information of node pressure data needs to be first split into multiple intervals according to the monitoring time period. A distribution model is established within the interval based on the differentiated characteristics of node pressure changes. The node pressure fluctuation range is calculated by extracting the maximum and minimum values ​​in each interval. The mean and standard deviation in the time series are further calculated for this fluctuation range. The mean is used to reflect the overall trend of the node pressure, and the standard deviation is used to indicate the degree of discreteness of the node pressure fluctuation. The pressure fluctuation amplitude of each interval is normalized to unify the dimensions. The normalized results are classified according to the preset threshold, and the intervals with higher fluctuation amplitudes are selected. Finally, the pressure fluctuation classification results are generated by comparing the interval change trends of the fluctuation amplitude.

[0140] The task intensity distribution and pressure fluctuation amplitude data in the pressure fluctuation classification results are analyzed using the formula:

[0141]

[0142] The pressure anomaly distribution coefficient is calculated;

[0143] Among them, Q represents the pressure anomaly distribution coefficient, P max Represents the maximum pressure, P avg represents the average value of pressure, σ P Represents the standard deviation of pressure, T max Represents the maximum value of task intensity, T min represents the minimum value of task intensity;

[0144] The benefit of the formula is that it can accurately reflect the distribution characteristics of node pressure anomalies and improve the accuracy of data screening by comprehensively considering the amplitude deviation of pressure fluctuation and the extreme value ratio of task intensity, normalizing the pressure deviation with the pressure standard deviation, and combining the nonlinear ratio of task intensity.

[0145] Maximum value of node pressure P max is 120, and the time series data of pressure obtained through monitoring are 100, 110, 120, 90, and 105 respectively. The average value P is calculated. avg :

[0146]

[0147] Pressure standard deviation σ P Calculated by the standard deviation formula:

[0148]

[0149] The maximum value of task intensity T max and the minimum value T min Set it to 20 and 10, and substitute it into the formula:

[0150]

[0151] The result shows that the pressure anomaly distribution coefficient Q is 2.121, which means that the pressure fluctuation of the current node is large and the extreme value difference of task intensity is significant, which is an abnormal node.

[0152] According to the pressure anomaly distribution coefficient, the screened abnormal node pressure data is reclassified, the pressure fluctuation amplitude of the abnormal node is linked to the corresponding task intensity for analysis, the abnormal data is marked according to the amplitude of the task intensity change, and the abnormal pressure distribution data set is generated;

[0153] To screen out abnormal node pressure data, it is necessary to reclassify them according to the interval division method. By calculating the distribution characteristics of abnormal nodes in the time series, the mean and extreme value statistics of the pressure fluctuation amplitude of the abnormal nodes are first performed, and then the correlation coefficient between the abnormal nodes and the task intensity is calculated by the interval division of the pressure fluctuation amplitude. The correlation coefficient is calculated by the ratio of the median of the pressure fluctuation amplitude to the task intensity change trend. Finally, the abnormal nodes are labeled with their abnormal categories according to the magnitude of the task intensity change amplitude. The results of the correlation analysis between the abnormal pressure fluctuation amplitude and the task intensity are integrated to generate an abnormal pressure distribution data set.

[0154] See also Figure 8 , the specific steps for obtaining the pressure abnormality level classification monitoring results are as follows:

[0155] Based on the abnormal pressure distribution data set, the pressure value and fluctuation amplitude of the pressure point data are extracted, the data is classified and processed, and the pressure mean and standard deviation are calculated. The data with a standard deviation lower than the set threshold are eliminated to obtain the preliminary screening results of the pressure value;

[0156] The pressure point data is decomposed into time series, and the pressure data of each node is divided into intervals according to fixed time intervals. The mean and standard deviation of the pressure points in each time interval are calculated respectively. The standard deviation is used as a quantitative indicator of the fluctuation amplitude. By normalizing the data distribution of all nodes, it is convenient to conduct a unified analysis of nodes in different pressure ranges, and screen out nodes whose mean and fluctuation amplitude exceed the preset threshold range as abnormal pressure points. By further refining the time distribution characteristics of the abnormal pressure points, the pressure fluctuation amplitudes in the time interval are grouped and classified, and finally the preliminary screening results of the pressure values ​​are obtained.

[0157] Based on the preliminary screening results of the pressure values, the pressure points are graded and the pressure level of each pressure point is analyzed using the formula:

[0158]

[0159] Calculate the pressure level score and generate the pressure point level judgment result;

[0160] Among them, Y represents the pressure level score, H represents the pressure value, μ P is the mean value of pressure, N is the standard deviation of pressure, ΔP represents the pressure change rate, and λ is the weight coefficient adjusted according to the self-matching of data distribution;

[0161] The benefit of the formula is that, by comprehensively considering the relative deviation degree of the pressure point value and the dynamic influence of the volatility, it provides higher accuracy and flexibility for the classification judgment of pressure anomalies, so that the classification results can better reflect the distribution characteristics of the pressure points;

[0162] The initial value of the pressure value H is 120. The pressure point values ​​obtained from the data set are 110, 120, 125, 115, and 130 respectively. The mean pressure value μ P Calculated as:

[0163]

[0164] The pressure standard deviation N is calculated as follows:

[0165]

[0166] The pressure change rate ΔP is the average of the pressure difference between two consecutive time points and is calculated as follows:

[0167]

[0168] Assuming that the weight coefficient λ is adjusted to be proportional to the fluctuation range, that is, λ = 0.1·N, calculate λ:

[0169] λ = 0.1 7.07 = 0.707;

[0170] Substitute the above results into the formula to calculate the pressure level score Y:

[0171]

[0172] The result shows that the pressure level score is 7.07, indicating that the pressure point of this node has a large fluctuation and belongs to the higher abnormal level range.

[0173] Summarize the level judgment results of the pressure points, classify and statistically analyze the data set according to the number and distribution characteristics of the differentiated level pressure points, annotate the pressure range and typical fluctuation characteristics, and generate the pressure abnormality level classification monitoring results;

[0174] First, the abnormal level values ​​of pressure points are sorted, and the pressure levels are divided into three categories: low, medium, and high. The number of pressure points in each category is recounted based on the grading results. The pressure value range of each type of pressure point is counted, and the mean and fluctuation range are calculated respectively. The data is further compared with the abnormal fluctuation range within the time interval, and the correlation characteristics between the pressure value and the fluctuation range in each level classification are analyzed. Finally, the characteristic annotation of the pressure points in each level classification is obtained, and the pressure abnormality level classification monitoring results are generated.

[0175] 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. A cancer survivor work stress monitoring system based on big data, characterized by: The system comprises: The physiological parameter analysis module performs differential analysis on the heart rate variation range and skin conductance fluctuation amplitude within a time period based on the heart rate fluctuation, skin conductance and blood pressure range of cancer survivors, and screens and classifies the data points with large fluctuations to generate physiological parameter fluctuation characteristic results; The stress inducement analysis module compares the heart rate fluctuation amplitude, skin conductance difference and task intensity in the data points one by one based on the physiological parameter fluctuation characteristic results, generates a stress inducement difference set, sorts the parameter fluctuation range in the stress inducement difference set by sensitivity, and generates a stress inducement key distribution result; The workload distribution module classifies and groups the task intensity, working time and stress peak of the cancer survivors item by item based on the key distribution results of the stress inducers to obtain workload classification data, and prioritizes the load intensity of the classification intervals in the workload classification data to generate a load adjustment path result; Based on the load adjustment path results, the abnormal pressure monitoring module analyzes the task intensity distribution of the node pressure and the distribution of the pressure fluctuation amplitude, generates an abnormal pressure distribution data set, and classifies the distribution and fluctuation amplitude of the abnormal pressure points to generate pressure abnormality grade classification monitoring results.

2. The cancer survivor work stress monitoring system based on big data according to claim 1, characterized in that: The steps for obtaining the physiological parameter fluctuation characteristic result are specifically as follows: Based on the heart rate fluctuations, skin conductance, and blood pressure ranges of cancer survivors, the range of heart rate in each time period was analyzed, and the standard deviation was calculated through skin conductance data to obtain a characteristic data table of heart rate variation range and skin conductance fluctuation amplitude; The heart rate variation range and the skin conductance fluctuation amplitude characteristic data table are analyzed for differences using the formula: Calculate the difference index value; Among them, D represents the difference index value, HR max Represents the maximum heart rate during the monitoring period, HR min Represents the minimum value of the heart rate during the monitoring period, σ SC represents the standard deviation of skin conductance fluctuation amplitude, w1 and w2 are weight parameters; Based on the difference index value, a threshold parameter is set, a logical judgment is made on the difference index, fluctuation data points satisfying the difference index being greater than the threshold are screened, data points meeting the conditions are counted and classified, and a physiological parameter fluctuation characteristic result is generated.

3. The cancer survivor work stress monitoring system based on big data according to claim 2, characterized in that: The steps for obtaining the stress-inducing factor difference set are specifically as follows: Based on the physiological parameter fluctuation characteristic results, extract the heart rate fluctuation amplitude values ​​in the data points, sort the values ​​and classify them into a set, extract the skin conductance difference values ​​and the task intensity values ​​and sort them, and obtain the physiological parameter sorting results; Based on the physiological parameter sorting results, the heart rate fluctuation amplitude is selected, the difference between adjacent data points is analyzed, the skin conductance difference is processed according to the difference calculation rule of adjacent data points, the task intensity value change is counted, and a parameter change difference set is obtained; Based on the parameter change difference set, the heart rate fluctuation and skin conductance difference set are read, the regions are divided according to the value range, the number of data points in the region is counted, the related data region is filtered, and the stress inducement difference set is obtained.

4. The cancer survivor work stress monitoring system based on big data according to claim 3 is characterized in that: The steps for obtaining the key distribution results of the pressure inducement are specifically as follows: According to each parameter in the stress-inducing difference set, by statistically analyzing the fluctuation range of the parameter, identifying the standard deviation and mean of the fluctuation amplitude, analyzing the parameter fluctuation characteristics, using the standard deviation to reflect the discreteness of the fluctuation degree, judging the corresponding size of the fluctuation level, and generating a fluctuation characteristic set; Based on the fluctuation feature set, the sensitivity of each parameter is weighted and sorted according to the weight. The calculation formula is: Generate a ranked list of stress-inducing sensitivities; Among them, S represents the sensitivity ranking value, M i represents the weight coefficient of parameter i, σ i represents the standard deviation of parameter i, μ i represents the mean of parameter i, n represents the total number of parameters, and ∑ represents the summation symbol; Based on the sorted stress inducer sensitivity list, by comparing the impact of each parameter sensitivity on the stress inducer distribution, the fluctuation characteristics of the weight parameters in the sensitivity sorting are screened, the sensitivity parameters are selected as key stress inducers, and the stress inducer key distribution results are established.

5. The cancer survivor work stress monitoring system based on big data according to claim 4 is characterized in that: The steps for obtaining the workload classification data are specifically as follows: Based on the key distribution results of the stress inducers, the task intensity impact range analysis is performed, the working hours and stress peaks are compared and classified respectively, and the correlation parameters are calculated, and the low-correlation task intensity data are eliminated to obtain the workload distribution parameters; For the workload distribution parameters, the task intensity, working time and pressure peak data are grouped and classified, the mean value, standard deviation and coefficient of variation of the characteristic value of each group of data are identified, and the load distance is calculated using the formula: Obtaining workload characteristic distance parameters; Where L represents the load distance, T a represents the single task intensity, T m represents the overall mean of task intensity, W a Represents the single-task working time, W m represents the overall mean of working time, and P represents the peak stress of a single task; According to the workload characteristic distance parameters, group analysis and load distance screening are performed, task intensity, working time and pressure peak load distance are sorted and the screening characteristic values ​​are marked, and classification is performed according to load distance to obtain workload classification data.

6. The cancer survivor work stress monitoring system based on big data according to claim 5, characterized in that: The steps of obtaining the load adjustment path result are specifically as follows: Based on the workload classification result, extract the load intensity of the classification interval, sort the load intensity values ​​and check them one by one, record the corresponding order and value of the load intensity of the classification interval after sorting, and generate the load intensity sorting result; Based on the load intensity sorting result, priority is allocated in sequence, priority numbers are set for each load intensity value and corresponded, the distribution order of the priority numbers is recorded, the mapping relationship between the priority numbers and the load intensity of the classification interval is analyzed, and the load priority allocation result is obtained; Based on the load priority allocation result, the load intensity of the classification interval is adjusted item by item, the adjustment path is determined in combination with the priority number, the adjusted load intensity value is compared with the load intensity value before the adjustment, the adjustment path parameter changes and the adjustment range are recorded, and the load adjustment path result is generated.

7. The cancer survivor work stress monitoring system based on big data according to claim 6, characterized in that: The steps for acquiring the abnormal pressure distribution data set are specifically as follows: Based on the load adjustment path result, the time series information in the node pressure data is called, the task intensity distribution and the pressure fluctuation amplitude are normalized, the time series data is divided into fixed intervals and the fluctuation amplitude is compared to see whether it exceeds a threshold value, and the pressure fluctuation classification result is obtained; The task intensity distribution and pressure fluctuation amplitude data in the pressure fluctuation classification results are analyzed using the formula: The pressure anomaly distribution coefficient is calculated; Among them, Q represents the pressure anomaly distribution coefficient, P max Represents the maximum pressure, P avg represents the average value of pressure, σ P Represents the standard deviation of pressure, T max Represents the maximum value of task intensity, T min represents the minimum value of task intensity; According to the pressure anomaly distribution coefficient, the screened abnormal node pressure data is reclassified, the pressure fluctuation amplitude of the abnormal node is linked to the corresponding task intensity for analysis, the abnormal data is marked according to the amplitude of the task intensity change, and an abnormal pressure distribution data set is generated.

8. The cancer survivor work stress monitoring system based on big data according to claim 7, characterized in that: The steps for obtaining the pressure abnormality level classification monitoring result are specifically as follows: Based on the abnormal pressure distribution data set, the pressure value and fluctuation amplitude of the pressure point data are extracted, the data is classified and processed, and the pressure mean and standard deviation are calculated, and the data with a standard deviation lower than the set threshold are eliminated to obtain a preliminary screening result of the pressure value; Based on the preliminary screening results of the pressure values, the pressure points are graded and judged, and the pressure level of each pressure point is analyzed using the formula: Calculate the pressure level score and generate the pressure point level judgment result; Among them, Y represents the pressure level score, H represents the pressure value, μ P is the mean value of pressure, N is the standard deviation of pressure, ΔP represents the pressure change rate, and λ is the weight coefficient adjusted according to the self-matching of data distribution; The level judgment results of the pressure points are summarized, and the data set is classified and statistically analyzed according to the number and distribution characteristics of the differentiated level pressure points, the pressure range and typical fluctuation characteristics are marked, and the pressure abnormality level classification monitoring results are generated.

Images