A method and system for identifying the degree of labor capacity limitation

Abstract

The application belongs to the technical field of labor capacity limitation degree identification, and specifically discloses a labor capacity limitation degree identification analysis method and system, which comprises the following steps: periodically acquiring physical examination and wearable device data, constructing historical health time series data, establishing individualized labor capacity index benchmark values based on the historical health time series data, calculating the trend deviation degree and data stability of the current measured value relative to the benchmark, performing labor capacity limitation risk judgment, and when there is a risk, combining the dependence of different work types on the index to evaluate the labor capacity limitation grade. The application periodically acquires occupational health physical examination and wearable device monitoring data, processes the data through standardization and time series fusion to construct historical health time series data, realizes dynamic and continuous monitoring of multiple labor capacity indexes, effectively overcomes the lagging defect of traditional static physical examination, and significantly improves the timeliness and data integrity of health status evaluation.

Description

Technical Field

[0001] This invention belongs to the technical field of assessment of the degree of limitation of labor capacity, and relates to a method and system for assessing and analyzing the degree of limitation of labor capacity. Background Technology

[0002] With increasing societal demands for occupational health and safety, the continuous and stable assessment of employees' work capacity is becoming increasingly important for enterprises. Currently, traditional methods of work capacity assessment primarily rely on periodic, static occupational health examinations. These methods suffer from significant time lag, only obtaining limited health and work capacity indicator data at specific points in time, making it difficult to achieve dynamic monitoring and continuous tracking of employees' work capacity status.

[0003] For example, Chinese invention patent CN109726596A discloses a work capacity assessment platform system. This system integrates a platform business function system, multiple subsystems, and a platform security construction system, and achieves interconnection and interoperability between the systems through a data bus, thus realizing the digitalization of the assessment process to a certain extent. Specifically, the system covers multiple management links from expert selection, workflow management, online payment to conclusion delivery, aiming to improve the convenience and controllability of services by optimizing the process.

[0004] The existing technologies mentioned above have the following shortcomings: 1. The system mainly focuses on the informatization and process optimization of the identification business process, and fails to conduct objective, quantitative and continuous dynamic assessment of the employee's labor capacity itself. At the same time, the system does not involve the use of wearable devices and other continuous monitoring data, nor does it build a health benchmark model based on individual historical data. The accurate and reliable implementation of the system still highly depends on process specifications and expert experience judgment, and lacks data-driven automated analysis capabilities.

[0005] 2. The evaluation basis of the system mainly relies on traditional one-time physical examination reports and expert reviews, which belongs to a static and post-event assessment model. Due to the lack of the ability to integrate and analyze multi-cycle and multi-source heterogeneous health data, it is unable to effectively capture the gradual change trend of employees' work capacity, making it difficult to achieve early warning and level assessment before risks occur. Its evaluation process still has obvious lag and passivity, and cannot meet the actual needs of enterprises to conduct real-time and forward-looking risk management of employees' health status. Summary of the Invention

[0006] In view of this, in order to solve the problems mentioned in the background art above, a method and system for identifying and analyzing the degree of limitation of labor capacity is proposed.

[0007] The objective of this invention can be achieved through the following technical solution: This invention provides a method for identifying and analyzing the degree of limitation of labor capacity, including: S1, periodically acquiring occupational health examination data of target employees, and simultaneously acquiring monitoring data from wearable devices in the corresponding period, performing standardization and time-series fusion processing, and constructing historical health time-series data.

[0008] S2. Based on the historical health time series data, determine the baseline values ​​of the target employees under each labor capacity indicator through statistical analysis.

[0009] S3. Obtain the measured values ​​of each labor capacity indicator of the target employee within the current monitoring window from historical health time series data, and calculate the trend deviation and data stability of the target employee in each labor capacity indicator in combination with the benchmark value.

[0010] S4. Based on the trend deviation and data stability of each labor capacity indicator, determine whether the target employee has a risk of limited labor capacity.

[0011] S5. When it is determined that there is a risk of limited labor capacity, the level of limited labor capacity of the target employee is assessed based on the trend deviation of each labor capacity indicator and the pre-defined dependence of different job types on each labor capacity indicator.

[0012] The present invention also provides a system for identifying and analyzing the degree of limitation of labor capacity, including: a multi-source data fusion module, which periodically acquires occupational health examination data of target employees and simultaneously acquires monitoring data of wearable devices in the corresponding period, performs standardization and time-series fusion processing, and constructs historical health time-series data.

[0013] The benchmark analysis and calculation module determines the benchmark values ​​of target employees under various labor capacity indicators through statistical analysis based on the historical health time series data.

[0014] The trend stability assessment module obtains the measured values ​​of each labor capacity indicator of the target employee within the current monitoring window from historical health time series data, and calculates the trend deviation and data stability of the target employee in each labor capacity indicator in combination with the benchmark value.

[0015] The risk assessment and identification module determines whether the target employee has a risk of limited labor capacity based on the trend deviation and data stability of various labor capacity indicators.

[0016] The rating and analysis module assesses the level of limited work capacity of target employees when a risk of limited work capacity is identified. Based on the trend deviation of each work capacity indicator and the pre-defined dependence of different job types on each work capacity indicator, the module evaluates the level of limited work capacity of target employees.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention acquires occupational health examination and wearable device monitoring data periodically, and constructs historical health time series data through standardization and time series fusion processing, thereby realizing dynamic and continuous monitoring of multiple labor capacity indicators, effectively overcoming the lag defects of traditional static physical examination, and significantly improving the timeliness and data integrity of health status assessment.

[0018] (2) This invention establishes personalized benchmark values ​​based on individual historical health data and combines trend deviation and data stability as dual indicators to determine risk. It can sensitively identify the gradual decline and abnormal fluctuations in labor capacity, thereby achieving early and accurate risk warning and avoiding misjudgment or omission caused by general benchmarks.

[0019] (3) By introducing the dependence weight of each indicator on different job types when assessing the level of limited labor capacity, this invention combines health deviation with the physiological requirements of the job, making the assessment results more job-specific and providing a scientific basis and precise decision support for subsequent personnel allocation and health management.

[0020] (4) By adopting standardized integration and blockchain evidence storage technology from the data collection stage, this invention ensures the authenticity and immutability of multi-source data, and constructs a full-link credible traceability system from original data to evaluation conclusion, which greatly enhances the legal effect and credibility of the identification results.

[0021] (5) This invention effectively filters out false alarms caused by single measurement errors by coupling the judgment of data stability and trend deviation. Furthermore, it dynamically links the risk assessment results with the physiological requirements of the job, realizing a closed-loop assessment system from health monitoring to job suitability. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram showing the connections between the steps of the method of the present invention.

[0024] Figure 2 This is a schematic diagram showing the connection steps for calculating the coefficient of variation in this invention.

[0025] Figure 3 This is a schematic diagram showing the connections of the various modules in the system of the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] Please see Figure 1 As shown, the present invention provides a method for identifying and analyzing the degree of limitation of labor capacity. The method includes: S1, periodically acquiring occupational health examination data of target employees, and simultaneously acquiring monitoring data of wearable devices in the corresponding period, performing standardization and time-series fusion processing, and constructing historical health time-series data.

[0028] For example, the construction of historical health time-series data includes: performing timestamp alignment processing on the acquired occupational health examination data and wearable device monitoring data to obtain timestamp aligned data.

[0029] The timestamp-aligned data is uniformly converted to standard units and frequencies.

[0030] It's important to add that standardizing units is crucial to eliminate discrepancies in measurement units across different data sources, enabling calculations and comparisons within a unified numerical system. First, identify work capacity indicators representing the same physiological or functional dimension from all occupational health examination data and wearable device monitoring data. For example, heart rate work capacity indicators are expressed in beats per minute in examination reports and recorded as BPM in wearable devices; although the meaning is the same, consistent terminology is necessary. For all identified work capacity indicators, convert their raw data values ​​to standard units using a pre-defined conversion coefficient. Normalization further eliminates fundamental differences between individuals. After unit standardization, normalization can be applied to some work capacity indicators, such as using Z-score standardization to convert the data into a distribution with a mean of 0 and a standard deviation of 1, facilitating subsequent cross-sectional comparisons and model calculations.

[0031] Standardizing the frequency aims to align data sequences from different acquisition frequencies onto the same timeline, constructing well-organized time-series data and laying the foundation for subsequent time-series fusion and analysis. Based on the monitoring objectives and data characteristics, a standard acquisition frequency is preset. For high-frequency data, an aggregation method is used, aggregating and calculating high-frequency data according to a reference frequency window. For low-frequency and gently changing labor capacity indicators, linear interpolation is used. For low-frequency but highly fluctuating indicators, forward padding is used to generate a smoother sequence. After frequency standardization, all data have timestamps consistent with the reference frequency, thus achieving precise alignment and splicing of different data sources at the same point in time.

[0032] By using a unified timestamp, the standardized data is aligned and stitched together to generate a fused dataset with a consistent time series structure.

[0033] The fused dataset, along with its timestamp, is stored in the blockchain as a key data entry to obtain historical health time-series data. The blockchain notarization adopts a consortium blockchain architecture, which distributes the data hash value across multiple nodes and ensures that the data time sequence is tamper-proof through a timestamp service.

[0034] S2. Based on the historical health time series data, determine the baseline values ​​of the target employees under each labor capacity indicator through statistical analysis.

[0035] It should be added that the labor capacity indicators include, but are not limited to, cardiopulmonary function indicators, muscle function indicators, skeletal function indicators, and neurological function indicators.

[0036] For example, determining the benchmark value of the target employee under each work capacity indicator includes: obtaining the target employee's health time series data within the historical benchmark window from historical health time series data, and dividing it into each benchmark assessment window according to a preset time interval. The historical benchmark window refers to a specific, continuous time interval. The system will extract the target employee's historical health data from this interval to calculate a personalized benchmark value representing the employee's stable health status.

[0037] The historical baseline window is obtained by setting the start time of the current monitoring window as the end time of the historical baseline window. Using this end time as a benchmark, a preset fixed duration is traced backward to determine the start time of the historical baseline window. This ensures that historical baseline data and current monitoring data are seamlessly connected in time but never overlap, guaranteeing both the timeliness of the benchmark and strictly defining the boundary between the historical baseline window and the current monitoring window.

[0038] For each benchmark assessment window, the average value and coefficient of variation of each labor capacity indicator are calculated within each benchmark assessment window.

[0039] Please see Figure 2 As shown, further, the calculation of the coefficient of variation of each labor capacity indicator within each benchmark assessment window includes: calculating the average value of all monitored values ​​of each labor capacity indicator within each benchmark assessment window, and simultaneously calculating the standard deviation of each labor capacity indicator within each benchmark assessment window, wherein the standard deviation is an absolute labor capacity indicator that measures the degree of dispersion of each monitored value within the dataset relative to the average value.

[0040] Dividing the standard deviation by the mean yields the coefficient of variation for each labor capacity indicator within each benchmark assessment window.

[0041] The average value and coefficient of variation of each labor capacity indicator within each benchmark assessment window are compared with the preset average threshold and coefficient of variation threshold for the health direction, respectively.

[0042] It should be added that the preset health orientation average threshold is a critical benchmark value used to determine whether the average level of a specific work capacity indicator within a certain benchmark assessment window reaches the ideal state of health. The threshold is set considering the health orientation of the work capacity indicator: for indicators where an increase in value indicates health, the health orientation average threshold is the lower limit, meaning the average value should be greater than or equal to the threshold. For indicators where a decrease in value indicates health, the health orientation average threshold is the upper limit, meaning the average value should be less than or equal to the threshold. The specific values ​​of the thresholds follow the principle of authoritative basis, mainly based on national or industry-issued occupational health medical guidelines, large-scale epidemiological survey consensus, or publicly released mandatory health standards, and are set separately for each work capacity indicator.

[0043] The preset coefficient of variation threshold is a critical benchmark value used to determine whether the data fluctuation of a specific labor capacity indicator within a certain benchmark assessment window is within an acceptable stable range. This threshold is set using a historical data-driven principle, and the acquisition process is as follows: From a representative historical employee sample database, the coefficient of variation data of all employees across all benchmark assessment windows is extracted. For each labor capacity indicator, the 85th percentile of all its coefficient of variation data is calculated, and this value is set as the preset coefficient of variation threshold for that labor capacity indicator.

[0044] The core logic is that this value means that in historical data, the data fluctuation level is below this threshold for approximately 85% of the time periods. By setting this value as the screening threshold, we can ensure that the time series used to calculate the benchmark value has a high degree of data stability, thereby guaranteeing the reliability and representativeness of the obtained benchmark value.

[0045] The benchmark assessment windows that have an average value that meets the preset health orientation average threshold and a coefficient of variation that is less than or equal to the preset coefficient of variation threshold are selected to form a set of effective benchmark assessment windows for each labor capacity indicator.

[0046] Calculate the overall average value of each labor capacity indicator in the set of effective benchmark assessment windows within each benchmark assessment window to obtain the benchmark value of the target employee under each labor capacity indicator.

[0047] It should be added that the core design principle of using the overall average value of each time period within the effective benchmark assessment window set as the final benchmark value is: through dual screening of the average value and the coefficient of variation, it ensures that the benchmark value originates from a period in the employee's history when they simultaneously met the criteria of excellent health and minimal data fluctuations, thus accurately representing their individual optimal stable state. Integrating data from multiple time periods for overall averaging can effectively smooth out occasional fluctuations and improve the benchmark value's resistance to interference and long-term stability. The method establishes a highly personalized dynamic benchmark, which differs from both general group health standards and the all-historical average value including abnormal periods. It provides a scientifically reasonable individualized comparison benchmark for subsequent trend deviation calculations and is key to achieving accurate early warning.

[0048] S3. Obtain the measured values ​​of each labor capacity indicator of the target employee within the current monitoring window from historical health time series data, and calculate the trend deviation and data stability of the target employee in each labor capacity indicator in combination with the benchmark value.

[0049] For example, the calculation of the trend deviation of the target employee in each labor capacity indicator includes: for each labor capacity indicator, obtaining the preset deterioration direction of the labor capacity indicator, wherein the deterioration direction is used to indicate whether an increase or decrease in the value of the labor capacity indicator indicates a deterioration in labor capacity.

[0050] The measured value is compared with the corresponding benchmark value. If the labor capacity index is a negative index and the measured value is greater than the benchmark value, or if the labor capacity index is a positive index and the measured value is less than the benchmark value, then the relative deviation between the measured value and the benchmark value is taken as the trend deviation. Otherwise, the trend deviation is 0. Here, a negative index means that an increase in value represents a decline in health status, and a positive index means that a decrease in value represents a decline in health status.

[0051] For example, the calculation of the data stability of the target employee under each labor capacity indicator includes: obtaining all time-series measured values ​​of the target employee under a certain labor capacity indicator within the current monitoring window, forming a sequence of measured values.

[0052] Calculate the standard deviation and mean of the measured value sequence, and calculate the coefficient of variation of the labor capacity index accordingly.

[0053] It should be added that the coefficient of variation is obtained by dividing the standard deviation by the mean, which is the coefficient of variation of the labor capacity index within the current monitoring window.

[0054] The coefficient of variation is matched and compared with the coefficient of variation range corresponding to the data stability of each data in its labor capacity index to obtain the data stability of the target employee in each labor capacity index. The smaller the coefficient of variation, the higher the data stability.

[0055] It's important to note that the coefficient of variation (CV) range for each labor capacity indicator's data stability is a criterion that maps the CV range to a qualitative stability level. This range transforms the calculated CV value into an intuitive data stability level for subsequent risk assessment. A large sample set is formed by extracting CV data for all employees across all monitoring windows from the historical employee dataset. For each labor capacity indicator, the statistical distribution of the sample is analyzed independently. The interval boundaries are typically defined using the percentile method.

[0056] S4. Based on the trend deviation and data stability of each labor capacity indicator, determine whether the target employee has a risk of limited labor capacity.

[0057] For example, determining whether a target employee has a risk of limited work capacity includes comparing the trend deviation and data stability of each work capacity indicator with their preset trend deviation threshold and data stability threshold, respectively.

[0058] It should be added that the preset trend deviation threshold is a critical value used to determine whether the current measured value of a certain work capacity indicator has reached a significant level of deterioration relative to its individual baseline value. It is a percentage value of relative deviation, and its core function is to distinguish between random normal fluctuations and significant adverse deviations that require attention. The trend deviation values ​​of each work capacity indicator calculated for all employees in each monitoring period are extracted from the historical employee dataset to form a large trend deviation sample set.

[0059] For each labor capacity indicator, the distribution of all non-zero trend deviation data is analyzed. The 90th or 95th percentile is then selected as the initial threshold for that indicator. This indicates that approximately 90%-95% of observed positive adverse deviations in historical data are below this threshold. Setting this value as the threshold allows for the filtering out of the few cases with the most significant deviations, thus focusing on labor capacity indicators with clear signs of deterioration.

[0060] The preset data stability threshold is a critical level used to determine whether the data fluctuation of a certain labor capacity indicator within the current monitoring window has exceeded the acceptable stability range. It should be noted that in this invention, data stability is defined as a positive indicator; that is, the higher the value or level, the better the data stability. Therefore, the preset data stability threshold can be a specific coefficient of variation critical value, or a coefficient of variation interval boundary used to divide stability levels. Essentially, it is a benchmark for determining whether data fluctuation exceeds the stable range. When the data stability of a certain indicator is lower than this threshold, the indicator is determined to be in an unstable state.

[0061] The number of labor capacity indicators whose statistical trend deviation is greater than a preset trend deviation threshold and whose data stability is lower than a preset data stability threshold is denoted as the number of risk indicators.

[0062] If the number of risk indicators is greater than or equal to the preset threshold, the target employee is determined to have a risk of limited work capacity; otherwise, the target employee is determined not to have a risk of limited work capacity.

[0063] It should be added that the preset quantity threshold refers to the minimum number of abnormal labor capacity indicators required to trigger a risk conclusion during the assessment of labor capacity limitation risk. This threshold is a positive integer, and its core function is to assess the degree of health risk diffusion from a systemic perspective: an abnormality in a single labor capacity indicator may stem from temporary factors, while a situation where multiple key labor capacity indicators simultaneously show significant deterioration and instability indicates a potential systemic risk of health deterioration.

[0064] The preset quantity threshold is obtained by extracting a large number of employee samples from historical employee health datasets. Each sample contains the trend deviation and data stability status of all its labor capacity indicators at a certain assessment time point, and each sample carries a judgment result indicating whether there is a risk of labor capacity limitation or not.

[0065] For each employee sample in the historical dataset, calculate the number of risk indicators, which is the number of labor capacity indicators whose trend deviation is greater than its threshold and whose data stability is lower than its threshold.

[0066] Using receiver operating characteristic (ROC) curve analysis, with the number of risk indicators as the diagnostic variable and the judgment result as the gold standard, the sensitivity and specificity corresponding to each candidate number were calculated, and then the number of risk indicators that maximized the Youden index was selected as the preset number threshold.

[0067] It is worth noting that a dual filtering mechanism was constructed by coupling the analysis of trend deviation and data stability to determine risk. This mechanism can effectively identify genuine and persistent health deterioration signals, thereby avoiding false alarms caused by single measurement errors or temporary physiological fluctuations, and significantly improving the accuracy and robustness of risk assessment. Upgrading risk identification from a simple matter of whether a level is exceeded to a multidimensional analysis of trends and stability not only better aligns with the objective laws of health risk evolution, but also provides high-quality and highly reliable input for subsequent level assessment steps.

[0068] S5. When it is determined that there is a risk of limited labor capacity, the level of limited labor capacity of the target employee is assessed based on the trend deviation of each labor capacity indicator and the pre-defined dependence of different job types on each labor capacity indicator.

[0069] For example, the preset dependency relationship between different job types on various labor capacity indicators includes: obtaining historical employee datasets for each job type, and then constructing a labor capacity indicator value sequence from the average value of long-term monitoring data of employees corresponding to each job type on various labor capacity indicators. The historical employee dataset includes, but is not limited to, employee identifiers, job types, time-series monitoring values ​​of various labor capacity indicators in historical time periods, and corresponding historical work performance scores.

[0070] The historical work performance scores of all employees on each labor capacity indicator are extracted from the dataset to form a performance score sequence.

[0071] Calculate the Pearson correlation coefficient between the labor capacity index value series and the performance score series, and use it as the correlation coefficient between each labor capacity index and work performance.

[0072] The correlation coefficients are normalized, and the normalized results are used as the dependency weights of each labor capacity indicator, thereby obtaining the dependency relationship between different job types and each labor capacity indicator.

[0073] It should be added that the purpose of normalizing the correlation coefficients is to transform a set of correlation coefficients, which may contain both positive and negative values, into a set of dependency weights where all elements are non-negative and sum to 1. The following method is used: First, the absolute values ​​of the Pearson correlation coefficients between each labor capacity indicator and work performance are taken to eliminate the interference of negative correlations on the positive contribution of the weights. The sum of the absolute values ​​of all labor capacity indicators is then calculated. Finally, the absolute value of each labor capacity indicator is divided by the sum of its absolute values ​​to obtain the dependency weight of each labor capacity indicator.

[0074] For example, the assessment of the target employee's level of limited work capacity includes: obtaining the trend deviation of each work capacity indicator, and obtaining the dependence weight of the target employee's work type on each work capacity indicator from the dependence relationship of different work types on each work capacity indicator.

[0075] The trend deviation and the corresponding dependency weights are weighted and fused to obtain the overall deviation of the target employee.

[0076] It should be added that the formula for calculating the overall deviation is: .

[0077] in, For the overall deviation, For the first The degree of trend deviation of the labor capacity indicators For the first The weighting of each labor capacity indicator The number of labor capacity indicators, Among them, the dependency weight is used to quantify the degree of influence of different labor capacity indicators on the overall deviation.

[0078] By using weighted fusion to calculate the overall deviation of target employees, on the one hand, the allocation of dependent weights can reflect the actual importance of different labor capacity indicators on work capacity, and reflect the different contributions of deviations in each labor capacity indicator to the overall limitation of labor capacity. On the other hand, it can directly integrate information on the trend deviation of multiple labor capacity indicators, and comprehensively consider the impact of health changes in various dimensions on labor capacity.

[0079] The overall deviation is matched with the overall deviation range corresponding to each level of work capacity limitation to obtain the work capacity limitation level of the target employee.

[0080] It should be added that the aforementioned comprehensive deviation range is a quantitative standard that maps the calculated comprehensive deviation value to a specific level of work capacity limitation. This standard consists of multiple consecutive numerical ranges, each corresponding to a specific level of limitation, and follows the principle that the higher the comprehensive deviation, the higher the corresponding level of limitation.

[0081] The specific steps are as follows: A large sample of employees who have completed work capacity assessments is selected from the historical employee health database. Each sample includes its final calculated overall deviation and the gold standard limitation level determined by the Occupational Health Expert Committee based on a comprehensive clinical assessment and job suitability analysis. All historical samples are grouped according to their gold standard limitation level. For each level group, the actual distribution of the overall deviation among its members is analyzed. Statistical methods are used to determine the range of overall deviation for each level.

[0082] Please see Figure 3 As shown, the present invention provides a system for identifying and analyzing the degree of limitation of labor capacity. The system includes: a multi-source data fusion module, a benchmark analysis and calculation module, a trend stability assessment module, a risk determination and identification module, and a level assessment and analysis module.

[0083] In the above, the multi-source data fusion module is connected to the benchmark analysis and calculation module and the trend stability assessment module, respectively. The trend stability assessment module is connected to the benchmark analysis and calculation module, the risk determination and identification module and the level assessment and analysis module, respectively. The risk determination and identification module is also connected to the level assessment and analysis module.

[0084] The multi-source data fusion module periodically acquires occupational health examination data of target employees and simultaneously acquires monitoring data from wearable devices in the corresponding period, performs standardization and time-series fusion processing, and constructs historical health time-series data.

[0085] The benchmark analysis and calculation module determines the benchmark values ​​of target employees under various labor capacity indicators through statistical analysis based on the historical health time series data.

[0086] The trend stability assessment module obtains the measured values ​​of each labor capacity indicator of the target employee within the current monitoring window from historical health time series data, and calculates the trend deviation and data stability of the target employee in each labor capacity indicator in combination with the benchmark value.

[0087] The risk assessment and identification module determines whether the target employee has a risk of limited labor capacity based on the trend deviation and data stability of each labor capacity indicator.

[0088] When the rating assessment and analysis module determines that there is a risk of limited work capacity, it assesses the level of limited work capacity of the target employee based on the trend deviation of each work capacity indicator and the pre-set dependence of different job types on each work capacity indicator.

[0089] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0090] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0091] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0092] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0093] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for assessing and analyzing the degree of limitation in work capacity, characterized in that: The method includes: S1. Periodically acquire occupational health examination data of target employees and simultaneously acquire monitoring data from wearable devices in the corresponding period, perform standardization and time-series fusion processing, and construct historical health time-series data; S2. Based on the historical health time series data, determine the baseline values ​​of the target employees under each labor capacity indicator through statistical analysis; S3. Obtain the measured values ​​of each labor capacity indicator of the target employee within the current monitoring window from historical health time series data, and calculate the trend deviation and data stability of the target employee in each labor capacity indicator in combination with the benchmark value. S4. Based on the trend deviation and data stability of each labor capacity indicator, determine whether the target employee is at risk of limited labor capacity. S5. When it is determined that there is a risk of limited labor capacity, the level of limited labor capacity of the target employee is assessed based on the trend deviation of each labor capacity indicator and the pre-set dependence of different job types on each labor capacity indicator. The dependencies of the different preset job types on various labor capacity indicators include: Obtain historical employee datasets for each job type, and then construct a sequence of labor capacity index values ​​by averaging the long-term monitoring data of employees for each job type on each labor capacity index. Extract all employees' historical work performance scores on each labor capacity indicator from the dataset to form a performance score sequence; Calculate the Pearson correlation coefficient between the labor capacity index value series and the performance score series, and use it as the correlation coefficient between each labor capacity index and work performance; The correlation coefficients are normalized, and the normalized results are used as the dependency weights of each labor capacity indicator, thereby obtaining the dependency relationship between different job types and each labor capacity indicator.

2. The method for assessing and analyzing the degree of limitation of work capacity according to claim 1, characterized in that: The constructed historical health time-series data includes: The acquired occupational health examination data and wearable device monitoring data are time-stamped to obtain the time-stamped data. Convert the timestamp-aligned data to standard units and frequencies; By using a unified timestamp, the standardized data is aligned and stitched together to generate a fusion dataset with a consistent time series structure; The fused dataset, along with its timestamp, is stored in the blockchain as a key data entry to obtain historical health time-series data.

3. The method for assessing and analyzing the degree of limitation of work capacity according to claim 1, characterized in that: The benchmark values ​​for determining the target employee under each work capacity indicator include: Obtain the target employee's health time series data within the historical baseline window from historical health time series data, and divide it into each baseline assessment window according to the preset time interval; For each benchmark assessment window, calculate the average value and coefficient of variation of each labor capacity indicator within each benchmark assessment window; The average value and coefficient of variation of each labor capacity indicator in each benchmark assessment window are compared with the preset average threshold and coefficient of variation threshold of the health direction, respectively. The benchmark assessment windows that meet the preset health orientation average threshold and whose coefficient of variation is less than or equal to the preset coefficient of variation threshold are selected to form a set of effective benchmark assessment windows for each labor capacity indicator. Calculate the overall average value of each labor capacity indicator in the set of effective benchmark assessment windows within each benchmark assessment window to obtain the benchmark value of the target employee under each labor capacity indicator.

4. The method for assessing and analyzing the degree of limitation of work capacity according to claim 3, characterized in that: The calculation of the coefficient of variation of each labor capacity indicator within each benchmark assessment window includes: Calculate the average value of all monitored values ​​for each labor capacity indicator within each benchmark assessment window, and also calculate the standard deviation of each labor capacity indicator within each benchmark assessment window. Dividing the standard deviation by the mean yields the coefficient of variation for each labor capacity indicator within each benchmark assessment window.

5. The method for assessing and analyzing the degree of limitation of work capacity according to claim 1, characterized in that: The calculation of the trend deviation of target employees in each work capacity indicator includes: For each labor capacity indicator, obtain the preset deterioration direction of that labor capacity indicator; The measured value is compared with the corresponding benchmark value. If the labor capacity index is a negative index and the measured value is greater than the benchmark value, or if the labor capacity index is a positive index and the measured value is less than the benchmark value, then the relative deviation between the measured value and the benchmark value is taken as the trend deviation. Otherwise, the trend deviation is 0.

6. The method for assessing and analyzing the degree of limitation of work capacity according to claim 1, characterized in that: The data stability of the target employee in each work capacity indicator includes: Obtain all time-series measured values ​​of the target employee under a certain labor capacity indicator within the current monitoring window, and form a sequence of measured values. Calculate the standard deviation and mean of the measured value sequence, and calculate the coefficient of variation of the labor capacity index accordingly; The coefficient of variation is matched and compared with the range of coefficients of variation corresponding to the data stability of each data in the labor capacity index to obtain the data stability of the target employee in each labor capacity index.

7. The method for assessing and analyzing the degree of limitation of work capacity according to claim 1, characterized in that: The determination of whether a target employee has a risk of limited work capacity includes: The trend deviation and data stability of each labor capacity indicator are compared with their preset trend deviation threshold and data stability threshold, respectively. The number of labor capacity indicators whose statistical trend deviation is greater than a preset trend deviation threshold and whose data stability is lower than a preset data stability threshold is denoted as the number of risk indicators. If the number of risk indicators is greater than or equal to the preset threshold, the target employee is determined to have a risk of limited work capacity; otherwise, the target employee is determined not to have a risk of limited work capacity.

8. The method for assessing and analyzing the degree of limitation of work capacity according to claim 1, characterized in that: The assessment of the target employee's level of work capacity limitation includes: Obtain the trend deviation of each labor capacity indicator, and obtain the dependence weight of the target employee's work type on each labor capacity indicator from the dependence relationship of different work types on each labor capacity indicator. The trend deviation and the corresponding dependency weights are weighted and fused to obtain the overall deviation of the target employee. The overall deviation is matched with the overall deviation range corresponding to each level of work capacity limitation to obtain the work capacity limitation level of the target employee.

9. A system for assessing and analyzing the degree of limitation in work capacity, characterized in that: The system includes: The multi-source data fusion module periodically acquires occupational health examination data of target employees and simultaneously acquires monitoring data from wearable devices in the corresponding period, performs standardization and time-series fusion processing, and constructs historical health time-series data; The benchmark analysis and calculation module determines the benchmark values ​​of the target employee under each labor capacity indicator through statistical analysis based on the historical health time series data. The trend stability assessment module obtains the measured values ​​of each labor capacity indicator of the target employee within the current monitoring window from historical health time series data, and calculates the trend deviation and data stability of the target employee in each labor capacity indicator in combination with the benchmark value. The risk assessment and identification module determines whether the target employee has a risk of limited work capacity based on the trend deviation and data stability of various work capacity indicators. The rating and analysis module assesses the level of limited work capacity of target employees when a risk of limited work capacity is identified. Based on the trend deviation of each work capacity indicator and the pre-defined dependence of different job types on each work capacity indicator, the module evaluates the level of limited work capacity of target employees.

Images