Cancer survivor work adaptation method and system

Abstract

The invention relates to the technical field of work adaptation, in particular to a cancer surviver work adaptation method and system, and the method comprises the following steps: based on the occupational data of cancer survivors, uniformly processing a data format, carrying out the occupational path analysis of a data set, and recognizing key occupational path change nodes. According to the invention, by analyzing the occupational data of cancer survivors, the identification capability of occupational path change nodes is improved, and occupational transition periods related to health condition changes are screened more accurately, so that personalized occupational planning suggestions are provided for the cancer survivors, and through a time window and sliding window technology, the cancer survivors can be more accurately planned. According to the method, career change frequency and amplitude are finely calculated, and career change trend characteristics are extracted, so that prediction of future career paths is more accurate, analysis of work adaptability problems is further refined, association between work performance and health data is clarified, and a scientific basis is provided for dynamic work allocation and configuration.

Description

Technical Field

[0001] The present invention relates to the technical field of work adaptability, and in particular to a work adaptation method and system for cancer survivors. Background Art

[0002] Work adaptability technology mainly studies how to improve individuals' adaptability in the work environment so that they can better cope with the challenges and changes they may encounter in their careers. This field involves multiple disciplines, including psychology, occupational health, human resource management and labor science, and aims to develop effective strategies and tools to help individuals optimize their career paths and improve work efficiency.

[0003] Among them, the work adaptation method for cancer survivors is how to help cancer survivors readapt to the work environment and resume their careers after treatment. It focuses on providing necessary support systems and adjusting the work environment to meet the special needs of cancer survivors. Its purpose is to help this group overcome the physical and psychological barriers caused by cancer and its treatment, so that they can reintegrate into the workplace, maintain their professional identity and improve their quality of life. By implementing adaptive strategies such as flexible working hours, adjustments to job responsibilities and mental health support, it can effectively promote the work adaptability and career development of cancer survivors.

[0004] Existing technologies fail to provide sufficiently targeted support, especially in terms of detailed analysis of the interactive impact of career paths and health status. This generalized approach does not fully consider individual differences, resulting in limited application of support. For example, the relationship between career path change nodes and treatment recovery stages has not been deeply analyzed, resulting in the inability of the provided work adjustment plans to accurately meet the actual needs of cancer survivors at different recovery stages, affecting their work adaptability and career development, which not only limits the efficiency of career recovery, but also increases the psychological burden of cancer survivors when returning to work. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and to propose a work adaptation method and system for cancer survivors.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solution: a method for work adaptation of cancer survivors, comprising the following steps:

[0007] S1: Based on the career data of cancer survivors, the data format was standardized and career path analysis was performed on the dataset. Key career path change nodes were identified and the key information of each change node was refined. The career transition periods associated with changes in health status were screened to obtain career path change information.

[0008] S2: Based on the career path change information, a sliding window technique is used to set a time window, calculate the frequency and magnitude of career changes within each window, extract the trend characteristics of career changes, and make trend predictions for future career paths. Based on the prediction results, job adaptability issues are analyzed to obtain an overview of adaptability issues.

[0009] S3: Based on the adaptability problem overview, perform time series analysis on the work data, calculate the correlation between work performance and health data, obtain work performance analysis results, and compare them with the work adaptability problem to determine the adjustment direction of work allocation and obtain a dynamic work allocation configuration;

[0010] S4: Based on the dynamic work allocation configuration, collect implementation effect data after work adjustment, analyze key performance indicators in the data, and optimize the work adjustment direction based on the analysis results to match the work requirements of cancer adaptors and obtain optimized work adaptation results.

[0011] The present invention is improved in that the step of identifying the key career path change nodes is specifically as follows:

[0012] S111: Based on the occupational data of cancer survivors, perform data cleaning and format standardization, and verify the consistency and usability of each data record to obtain a purified occupational dataset;

[0013] S112: Based on the purified occupational dataset, the similarity between occupational type and time is evaluated using the formula:

[0014] ;

[0015] Identify the patterns and frequencies of career transitions and obtain career transition pattern analysis results, among which, represents the weighted Euclidean distance between the occupation data point and the cluster center, The first character vector representing the occupational feature A quantity, Indicates the first cluster center of the corresponding occupation category A quantity, is assigned to The weight of each occupational characteristic, represents the total number of features;

[0016] S113: Based on the career transition pattern analysis results, key change nodes in the career path are determined, including key periods or events of the survivor's career transition, to obtain key career path change nodes.

[0017] The present invention is improved in that the steps of obtaining the career path change information are specifically as follows:

[0018] S121: Analyze the key career path change nodes, refine the key information of each change node, including the occupation category before and after the career change, the nature of the work, and the time period of the change, and obtain change node description information;

[0019] S122: Based on the change node description information, the relationship between career path changes and changes in health status of cancer survivors is evaluated using the formula:

[0020] ;

[0021] Filter the career transition information related to health to obtain career path change information, among which, represents the correlation coefficient between occupational change and health status change, Indicates the criticality score of a single career change event, represents the health status change score corresponding to each occupational change, represents the average of all career change criticality scores, Represents the average of all health status change scores.

[0022] The present invention is improved in that the steps of extracting the trend characteristics of occupational changes are specifically as follows:

[0023] S211: Based on the career path change information, use a sliding window technique to set a time window length, calculate the career change frequency and magnitude within each window, and obtain change frequency and magnitude information;

[0024] S212: Based on the frequency and amplitude information of the change, the formula is used:

[0025] ;

[0026] Extract the trend characteristics of career changes, among which, represents the exponentially weighted moving average, is the magnitude or frequency of career changes in the current window, is the exponentially weighted moving average of the previous window, is the smoothing constant.

[0027] The present invention is improved in that the steps of obtaining the adaptability problem overview are specifically as follows:

[0028] S221: Based on the trend characteristics of the career change, predict the future career path trend, analyze the matching degree between the career change trend and the existing career environment, and obtain preliminary matching analysis results;

[0029] S222: Based on the preliminary matching analysis results, identify adaptability issues caused by career changes, including increased work stress or skills mismatch, and assess potential impacts on cancer survivors to obtain an overview of adaptability issues.

[0030] The present invention is improved in that the steps of obtaining the work performance analysis results are specifically as follows:

[0031] S311: Based on the adaptability problem overview, work performance data and health data are collected, and the autocorrelation and partial autocorrelation between the work performance and health data are calculated using the formula:

[0032] ;

[0033] and

[0034] ;

[0035] The preliminary statistical correlation results are obtained, among which, Indicates at a point in time The performance data points are normalized to the values ​​of Represents the raw performance data point, at the time point The monitoring value of represent The average value of represent The standard deviation of represents the total number of data points;

[0036] S312: Based on the preliminary statistical correlation results, perform correlation strength calculation to determine the correlation between work performance and health data, and obtain work performance analysis results.

[0037] The present invention is improved in that the step of obtaining the dynamic work allocation configuration is specifically as follows:

[0038] S321: Based on the work performance analysis results, compare with the work adaptability question, analyze the impact of the current work assignment on health and work efficiency, identify work tasks that increase health risks, and obtain a work adaptability comparison result;

[0039] S322: Based on the work adaptability comparison result, determine the adjustment direction of work allocation, including reducing workload, rearranging work time and rest period, and obtain dynamic work allocation configuration.

[0040] The present invention is improved in that the steps for obtaining the optimized work adaptation result are specifically as follows:

[0041] S411: Based on the dynamic work allocation configuration, collect implementation effect data after work adjustment, analyze key performance indicators in the implementation effect data, determine average work efficiency and health improvement rate, and obtain preliminary indicator analysis results;

[0042] S412: Based on the preliminary indicator analysis results, the degree of match between the work adjustment and the work requirements of the cancer adaptor is evaluated using the formula:

[0043] ;

[0044] Optimize the work adjustment direction and obtain the optimized work adaptation results, among which, Indicates the matching degree, Indicates the The value of the key performance indicator, Indicates the The weight of the key performance indicators, is the total number of KPIs.

[0045] A cancer survivor work adaptation system, comprising:

[0046] The career path analysis module analyzes the career path of cancer survivors based on their career data, identifies key career path change nodes, and screens career transition periods associated with changes in health status to obtain career path change information.

[0047] The trend prediction module calculates the frequency and magnitude of career changes within each window based on the career path change information, extracts the trend characteristics of career changes, and makes trend predictions for future career paths. It then analyzes job adaptability issues based on the prediction results to obtain an overview of adaptability issues.

[0048] The work adaptability assessment module performs a time series analysis on the work data based on the adaptability problem overview, calculates the correlation between work performance and health data, compares it with the work adaptability problem, determines the adjustment direction of work allocation, and obtains a dynamic work allocation configuration;

[0049] The dynamic work allocation module collects the implementation effect data after the work adjustment based on the dynamic work allocation configuration, analyzes the key performance indicators in the data, and optimizes the work adjustment direction according to the analysis results to obtain the optimized work adaptation result.

[0050] Compared with the prior art, the advantages and positive effects of the present invention are:

[0051] In the present invention, by analyzing the career data of cancer survivors, unified data format processing and career path analysis are achieved, and the ability to identify career path change nodes is improved, so as to more accurately screen career transition periods related to changes in health status, thereby providing cancer survivors with personalized career planning suggestions. Through time window and sliding window technology, the frequency and amplitude of career changes are precisely calculated, and the trend characteristics of career changes are extracted, making the prediction of future career paths more accurate. The analysis of work adaptability issues is further refined, and the relationship between work performance and health data is clarified, thereby providing a scientific basis for dynamic work allocation and configuration, ensuring that career path planning is highly matched with the actual needs of cancer survivors, and improving work adaptability and quality of life. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A flowchart of a method for work adaptation of cancer survivors proposed by the present invention;

[0053] Figure 2 A flowchart for identifying key career path change nodes in the present invention;

[0054] Figure 3 A flowchart for obtaining career path change information in the present invention;

[0055] Figure 4 A flowchart for extracting trend features of occupational changes in the present invention;

[0056] Figure 5 A flowchart for obtaining an overview of the adaptability problem in the present invention;

[0057] Figure 6 A flowchart for obtaining work performance analysis results in the present invention;

[0058] Figure 7 A flowchart for obtaining a dynamic work allocation configuration in the present invention;

[0059] Figure 8 The flowchart for obtaining the optimized working adaptation results in the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to 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.

[0061] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0062] Example

[0063] See also Figure 1 The present invention provides a technical solution: a method for work adaptation of cancer survivors, comprising the following steps:

[0064] S1: Based on the career data of cancer survivors, the data format was standardized and career path analysis was performed on the dataset. Key career path change nodes were identified and the key information of each change node was refined. The career transition periods associated with changes in health status were screened to obtain career path change information.

[0065] S2: Based on career path change information, we use sliding window technology to set time windows, calculate the frequency and magnitude of career changes within each window, extract the trend characteristics of career changes, and predict future career paths. We then analyze job adaptability issues based on the prediction results to obtain an overview of adaptability issues.

[0066] S3: Based on the adaptability problem overview, perform time series analysis on work data, calculate the correlation between work performance and health data, obtain work performance analysis results, and compare them with the work adaptability problem to determine the adjustment direction of work allocation and obtain dynamic work allocation configuration;

[0067] S4: Based on dynamic work allocation configuration, collect implementation effect data after work adjustment, analyze key performance indicators in the data, and optimize the work adjustment direction based on the analysis results to match the work requirements of cancer adaptors and obtain optimized work adaptation results.

[0068] Career path change information includes change cycles, key decision points, and health influencing factors. The adaptability problem overview specifically includes adaptation difficulty, impact scope, and prediction accuracy. Dynamic work allocation configuration includes allocation principles, priority settings, and resource allocation details. The optimized work adaptation results specifically include adaptability improvement and feedback satisfaction rate.

[0069] See also Figure 2 The specific steps for identifying key career path change nodes are:

[0070] S111: Based on the occupational data of cancer survivors, perform data cleaning and format standardization, and verify the consistency and usability of each data record to obtain a purified occupational dataset;

[0071] Extract the core fields of each data record from the data source, including occupation name, occupation category, occupation duration, and occupation change time node, screen according to the completeness of the field content, eliminate data records with empty values ​​or missing fields, and unify the occupation names into a specified coding format through data standardization. For example, synonymous occupation names are mapped to a unified occupation code through dictionary mapping. At the same time, timestamp formatting is used for the occupation time field to ensure the comparability of the time dimension, deduplicate redundant data records, and screen outliers through logical verification of occupation duration. For example, setting the occupation duration within a reasonable range and removing records outside the range. Finally, the integrity of the cleaned data is verified to ensure the consistency and accuracy of all fields.

[0072] S112: Based on the purified occupational dataset, evaluate the similarity between occupational type and time using the formula:

[0073] ;

[0074] Identify the patterns and frequencies of career transitions and obtain career transition pattern analysis results, among which, Represents the weighted Euclidean distance between the occupational data point and the cluster center, which is used to determine the cluster center of which occupational category the data point belongs to. The first character vector representing the occupational feature components, such as occupational category or occupational duration, Indicates the first cluster center of the corresponding occupation category Components, that is, the average or central value of all data points in the occupation category, is assigned to The weight of each occupational feature adjusts the influence of the feature in the distance calculation. represents the total number of features;

[0075] Occupational category and time characteristics of a data point in the purified occupational dataset They are , the corresponding cluster center value is , the weight coefficients are , calculation process:

[0076] ;

[0077] ;

[0078] ;

[0079] ;

[0080] ;

[0081] The results show that the weighted distance between the current occupational data point and the cluster center is 1, indicating that the occupational data point is relatively close to the center value of the category and can be classified into this category. Further analysis of the clustering results can reveal the pattern and frequency of occupational transitions and obtain the analysis results of the occupational transition pattern.

[0082] S113: Based on the analysis results of the career transition pattern, determine the key change nodes in the career path, including the key periods or events of the survivor's career transition, and obtain the key career path change nodes;

[0083] The time information of career transition nodes is extracted to compile a time series of career changes. By counting the career categories at each time node, the time periods with higher frequency of career changes are identified. The frequency of career changes and the time series are jointly analyzed to extract the main career categories and change characteristics within the time period. Combined with the detailed records of the survivors' career changes, the distribution of career categories at key nodes in the time series is gradually classified and sorted. At the same time, by comparing the career time span and the change interval, the time points with more obvious career transition frequency and span are screened out, and the occupational category change pattern at the key time points is further refined and analyzed, and finally the key period or event of the survivors' career transition is determined.

[0084] See also Figure 3 ,The specific steps for obtaining career path change information are:

[0085] S121: Analyze key career path change nodes, refine key information of each change node, including the occupation category before and after the career change, the nature of the work, and the time period of the change, and obtain change node description information;

[0086] First, extract the information data of the change nodes, including the occupational category, nature of work, and time period before and after the occupational change. Encode the occupational category according to the standard occupational classification system. For example, a four-level occupational classification coding method is used to classify different occupations into a unified coding type. At the same time, the data on the nature of work is quantified, and the working hours, occupational skill requirements, occupational physical requirements and other characteristics are given numerical representations. The data on the time period is unified, and the time information of the original record is converted into a continuous time span of days. The specific content of each change node is extracted into a separate record item through classification and organization. The extracted records are checked for consistency and duplicates are eliminated to ensure the independence and accuracy of the information of each change node. Finally, the change node description information including the category before and after the occupational change, the nature of work characteristics and the time span is generated.

[0087] S122: Based on the description information of the change nodes, the relationship between career path changes and changes in health status of cancer survivors was evaluated using the formula:

[0088] ;

[0089] Filter the career transition information related to health to obtain career path change information, among which, The correlation coefficient between occupational change and health status changes ranges from -1 to +1, where +1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation. The criticality score of a single career change event can be a quantitative value calculated based on the scale, impact or other importance indicators of the career change. The score of health status change corresponding to each occupational change can be a quantitative value based on the degree of improvement or deterioration of health status. represents the average of all career change criticality scores, represents the mean of all health status change scores;

[0090] Extract relevant records of career path changes, and screen out career change data that match the health status change score. First, associate and match the node information of each career change record with the corresponding health score data. Then classify the career change records according to the health status change score, and group the health scores into three levels: improvement, no change, and deterioration. Combined with the characteristics of the categories before and after the career change and the time span, cross-search is performed. Career transition nodes are screened by health score improvement data with a time span exceeding a certain number of days. At the same time, the node classification characteristics of the change records are aggregated and statistically analyzed to screen out health-related career change events with higher frequency. The screened node data are sorted to obtain career path change information containing career transition information with significant health correlation.

[0091] There are three career change events with criticality scores: , , , the health status change scores were , , , substitute into the formula to calculate:

[0092] calculate and :

[0093] ;

[0094] ;

[0095] Calculate the molecular part:

[0096] ;

[0097] ;

[0098] ;

[0099] Calculate the denominator:

[0100] ;

[0101] ;

[0102] ;

[0103] ;

[0104] calculate :

[0105] ;

[0106] The results show that the correlation coefficient between career path changes and health status changes is 0.998, indicating that there is a strong positive correlation between the two. This result clarifies the important role of specific career changes in health improvement and can further deduce health-related career transition information.

[0107] See also Figure 4 ,The specific steps for extracting the trend features of career changes are as follows:

[0108] S211: Based on the career path change information, use the sliding window technology to set the time window length, calculate the career change frequency and magnitude within each window, and obtain the change frequency and magnitude information;

[0109] Determine the overall time range of the career change records, extract the start time and end time of each career change record from the data set, and sort them to clarify the boundaries of the time range. Then use the sliding window technology to set the time window length, select a fixed-length time period as a window, for example, every three months can be a time period, and set the overlap ratio between windows as needed. Each window is divided in turn through a loop processing method, and the total number of career change events in each time window is counted. The total number of times is calculated by the ratio of the length of the time window to obtain the career change frequency. At the same time, the career change amplitude data is quantified. The weight value can be assigned according to the change level of the occupational category. The product of the weight and the number of events is used as the numerical representation of the career change amplitude. The career change frequency and amplitude of all windows are sorted to obtain complete change frequency and amplitude information.

[0110] S212: Based on the frequency and amplitude information of the change, the formula is used:

[0111] ;

[0112] Extract the trend characteristics of career changes, among which, Represents the exponentially weighted moving average, which is used to output the trend characteristics of the current window. is the magnitude or frequency of career changes in the current window, indicating the actual statistical data of career changes in the current time window. is the exponentially weighted moving average of the previous window, Is a smoothing constant that determines the weight of newly received data (current window data) relative to old data (EWMA value of the previous window). The larger the value, the greater the impact of the latest data on the trend;

[0113] There are three consecutive windows of occupational change frequency data: ,initial , smoothing constant , calculate the first window:

[0114] ;

[0115] ;

[0116] ;

[0117] Calculate the second window:

[0118] ;

[0119] ;

[0120] ;

[0121] Calculate the third window:

[0122] ;

[0123] ;

[0124] ;

[0125] The results show that the trend feature output of the third window is , combining the data weight of the historical window and the occupational change frequency of the current window, reflecting the continuity trend information of occupational change, by calculating the , the complete characteristic data of career change trends can be extracted for further prediction or analysis.

[0126] See also Figure 5 , the steps to obtain the adaptability problem overview are as follows:

[0127] S221: Based on the trend characteristics of career change, predict the future career path trend, analyze the matching degree between career change trend and existing career environment, and obtain preliminary matching analysis results;

[0128] First, the historical frequency and amplitude of career changes are used as input data. Combined with the short-term and long-term change trends in the career path trend characteristics, the time window of career changes is divided into fixed-interval prediction time periods. Then, the historical change trend characteristics are adjusted through a smoothing function as the initial value of the prediction model, and the distribution of change amplitudes in each time period is fitted and analyzed. The trend of future career change paths is simulated and calculated by superimposing short-term and long-term trends. At the same time, combined with existing career environment data, such as the availability of jobs, the degree of matching of occupational categories, and the intensity of changes in individual career experiences, the output results of career path trends are subjected to environmental matching analysis, and finally preliminary matching analysis results are obtained.

[0129] S222: Based on the results of the preliminary matching analysis, identify adaptation issues caused by career changes, including increased work stress or skills mismatch, and assess the potential impact on cancer survivors to obtain an overview of adaptation issues;

[0130] Identify adaptability issues caused by career changes, including the analysis of the match between changes in individual work stress and skill requirements. First, extract records of mismatch between career changes and the environment from the matching analysis results. Classify the career change amplitude, frequency, and time interval in the records, and focus on marking records with larger amplitudes or higher frequencies. At the same time, combine health status records to evaluate psychological stress and physical health indicators after career changes. For example, for indicators of deteriorating health status, such as blood pressure fluctuations and decreased job satisfaction, calculate the potential impact score of the change on health, compare health indicators with changes in occupational skill requirements, identify specific reasons for skill insufficiency or mismatch, and finally obtain an overview of adaptability issues.

[0131] See also Figure 6 , the specific steps for obtaining work performance analysis results are:

[0132] S311: Based on the adaptability problem overview, collect work performance data and health data, and calculate the autocorrelation and partial autocorrelation between work performance and health data using the formula:

[0133] ;

[0134] and

[0135] ;

[0136] The preliminary statistical correlation results are obtained, among which, Indicates at a point in time The performance data points are normalized to the values ​​of Represents the raw performance data point, at the time point The monitoring value of represent The average value of represent The standard deviation of represents the total number of data points;

[0137] Collect work performance data and health data, clean and normalize the physiological parameters (such as heart rate, blood pressure, etc.) and mental health parameters (such as anxiety score, stress index, etc.) in the health data, and perform the same processing on the work performance data (such as completion rate, efficiency, etc.). Calculate the correspondence between health data and work performance data at each time point, segment the data, and compare the health data and work performance data of each segment to obtain the cleaned autocorrelation and partial autocorrelation analysis input data. The original work performance data at time point is , calculate the average :

[0138] ;

[0139] Calculating standard deviation :

[0140] ;

[0141] ;

[0142] Calculation time point The standardized value of :

[0143] ;

[0144] The results showed that the time point The standardized value of work performance is , indicating that the work performance at this time point is much lower than the average. By calculating the , a standardized time series of work performance data can be obtained for subsequent analysis of the statistical correlation between work performance and health data.

[0145] S312: Based on the preliminary statistical correlation results, calculate the correlation strength to determine the correlation between the work performance and the health data, and obtain the work performance analysis results;

[0146] First, the correlation index between health data and work performance data is calculated, and the data is split into local data blocks in the time series window. The data in each data block is normalized, and the matching degree between each health parameter (such as heart rate fluctuation amplitude, blood pressure stability) and work performance index (such as task completion time, error rate) in the time series window is calculated. The correlation interval between health data and work performance data is obtained by item-by-item comparison. After averaging the correlation intervals in all time windows, the overall correlation strength index is summarized to obtain the correlation between work performance and health data and the work performance analysis results.

[0147] See also Figure 7 ,The specific steps for obtaining dynamic work allocation configuration are:

[0148] S321: Based on the work performance analysis results, compare them with the work adaptability questions, analyze the impact of the current work assignment on health and work efficiency, and identify work tasks that increase health risks to obtain work adaptability comparison results;

[0149] Extract the health data and work efficiency data involved in the work performance analysis results, perform time series processing on the physiological parameters in the health data (such as heart rate, blood pressure, sleep quality, etc.), segment the data into daily or weekly averages, calculate the fluctuation range and change trend of health parameters under different work task conditions, normalize the task completion time, accuracy, productivity and other parameters in the work efficiency data, match and compare the health fluctuation range with the normalized work efficiency data, identify work tasks with health fluctuations outside the normal range or abnormal work efficiency fluctuations, mark them as potential health risk sources and classify them, and finally obtain the work adaptability comparison results.

[0150] S322: Based on the work adaptability comparison results, determine the adjustment direction of work allocation, including reducing workload, rearranging work time and rest cycles, and obtaining a dynamic work allocation configuration;

[0151] First, a list of tasks that may pose health risks or reduce efficiency due to the characteristics of the work tasks is screened out from the adaptability comparison results. High-risk tasks in the task list are sorted according to the risk level of health parameters. For example, tasks with high heart rates are given priority to employees with long rest times. Tasks that take a long time to complete are rearranged with supporting resources and the order of task execution. Employees who are not adaptable to the working time period are given priority to off-peak hours, and tasks and rest cycles are reset. By matching and optimizing task priorities with employee health data, a new task allocation plan is formed, and ultimately a dynamic work allocation configuration is obtained.

[0152] See also Figure 8 ,The steps for obtaining the optimized work adaptation results are as follows:

[0153] S411: Based on the dynamic work allocation configuration, collect the implementation effect data after the work adjustment, analyze the key performance indicators in the implementation effect data, determine the average work efficiency and health improvement rate, and obtain preliminary indicator analysis results;

[0154] First, clarify the data source, including three key indicators: work completion time, error rate, and task completion rate. Obtain data through regular collection and recording methods, pre-process the data, screen out data sets that meet the set standards, delete extreme data that is obviously inconsistent with reality, and supplement missing data. Then, classify and store the data according to task type, calculate the average data of each category according to task completion time, error rate, and task completion rate, classify and record the results of each type of task, and set different weights for each type of data to highlight its importance in the overall efficiency calculation, such as giving a higher weight to the task completion rate. Then, perform time series analysis on the task data, combine short-term changes (such as 7 days) with long-term trends (such as 30 days), analyze the overall law of efficiency fluctuations, further simulate the work distribution effects under different conditions by building a model, summarize all processed key data and trend changes, and determine the overall average work efficiency and health improvement rate.

[0155] S412: Based on the preliminary indicator analysis results, evaluate the match between work adjustments and the work requirements of cancer adaptors using the formula:

[0156] ;

[0157] Optimize the work adjustment direction and obtain the optimized work adaptation results, among which, Indicates the matching degree, Indicates the The value of a key performance indicator, such as work efficiency, health improvement rate or work performance index, Indicates the The weight of the key performance indicators, is the total number of key performance indicators;

[0158] There are 3 key performance indicators, and their corresponding values ​​are , , , the weights are , , , calculate the weighted numerator part:

[0159] ;

[0160] ;

[0161] ;

[0162] The sum of the weighted numerators is:

[0163] ;

[0164] Calculate the weight denominator:

[0165] ;

[0166] Calculate the matching degree:

[0167] ;

[0168] The results show that the current job adjustment matches employee needs with a score of 81, indicating that each adjustment has a high adaptability after comprehensively considering the weights of each key performance indicator. Through the matching score, the performance of specific indicators can be further analyzed to optimize the direction of job adjustments.

[0169] A cancer survivor work adaptation system, comprising:

[0170] The career path analysis module analyzes the career path of cancer survivors based on their career data, identifies key career path change nodes, and screens career transition periods associated with changes in health status to obtain career path change information.

[0171] The trend prediction module calculates the frequency and magnitude of career changes within each window based on career path change information, extracts trend characteristics of career changes, and makes trend predictions for future career paths. It then analyzes job adaptability issues based on the prediction results and obtains an overview of adaptability issues.

[0172] The work adaptability assessment module conducts time series analysis on work data based on the adaptability problem overview, calculates the correlation between work performance and health data, compares it with the work adaptability problem, determines the adjustment direction of work allocation, and obtains dynamic work allocation configuration;

[0173] The dynamic work allocation module is based on the dynamic work allocation configuration, collects the implementation effect data after work adjustment, analyzes the key performance indicators in the data, and optimizes the work adjustment direction according to the analysis results to obtain optimized work adaptation results.

[0174] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for work adaptation for cancer survivors, characterized by: The following steps are involved: S1: Based on the career data of cancer survivors, the data format was standardized and career path analysis was performed on the dataset. Key career path change nodes were identified and the key information of each change node was refined. The career transition periods associated with changes in health status were screened to obtain career path change information. S2: Based on the career path change information, a sliding window technique is used to set a time window, calculate the frequency and magnitude of career changes within each window, extract the trend characteristics of career changes, and make trend predictions for future career paths. Based on the prediction results, job adaptability issues are analyzed to obtain an overview of adaptability issues. S3: Based on the adaptability problem overview, perform time series analysis on the work data, calculate the correlation between work performance and health data, obtain work performance analysis results, and compare them with the work adaptability problem to determine the adjustment direction of work allocation and obtain a dynamic work allocation configuration; S4: Based on the dynamic work allocation configuration, collect implementation effect data after work adjustment, analyze key performance indicators in the data, and optimize the work adjustment direction based on the analysis results to match the work requirements of cancer adaptors and obtain optimized work adaptation results.

2. The method for cancer survivor work adaptation according to claim 1, wherein: The steps for identifying the key career path change nodes are as follows: S111: Based on the occupational data of cancer survivors, perform data cleaning and format standardization, and verify the consistency and usability of each data record to obtain a purified occupational dataset; S112: Based on the purified occupational dataset, the similarity between occupational type and time is evaluated using the formula: ； Identify the patterns and frequencies of career transitions and obtain career transition pattern analysis results, among which, represents the weighted Euclidean distance between the occupation data point and the cluster center, The first character vector of occupation A quantity, Indicates the first cluster center of the corresponding occupation category A quantity, is assigned to The weight of each occupational characteristic, represents the total number of features; S113: Based on the career transition pattern analysis results, key change nodes in the career path are determined, including key periods or events of the survivor's career transition, to obtain key career path change nodes.

3. The method for cancer survivor work adaptation according to claim 1, wherein: The steps for obtaining the career path change information are as follows: S121: Analyze the key career path change nodes, refine the key information of each change node, including the occupation category, job nature, and change period before and after the career change, and obtain change node description information; S122: Based on the change node description information, the relationship between career path changes and changes in health status of cancer survivors is evaluated using the formula: ； Filter the career transition information related to health to obtain career path change information, among which, represents the correlation coefficient between occupational change and health status change, Indicates the criticality score of a single career change event, represents the health status change score corresponding to each occupational change, represents the average of all career change criticality scores, Represents the average of all health status change scores.

4. The method for cancer survivor work adaptation according to claim 1, wherein: The steps for extracting the trend characteristics of occupational changes are specifically as follows: S211: Based on the career path change information, use a sliding window technique to set a time window length, calculate the career change frequency and magnitude within each window, and obtain change frequency and magnitude information; S212: Based on the change frequency and amplitude information, use the formula: ； Extract the trend characteristics of career changes, among which, represents the exponentially weighted moving average, is the magnitude or frequency of career changes in the current window, is the exponentially weighted moving average of the previous window, is the smoothing constant.

5. The method for cancer survivor work adaptation according to claim 1, wherein: The steps for obtaining the adaptability problem overview are as follows: S221: Based on the trend characteristics of the career change, predict the future career path trend, analyze the matching degree between the career change trend and the existing career environment, and obtain preliminary matching analysis results; S222: Based on the preliminary matching analysis results, identify adaptability issues caused by career changes, including increased work stress or skills mismatch, and assess potential impacts on cancer survivors to obtain an overview of adaptability issues.

6. The method for work adaptation of cancer survivors according to claim 1, wherein: The steps for obtaining the work performance analysis results are specifically as follows: S311: Based on the adaptability problem overview, collect work performance data and health data, and calculate the autocorrelation and partial autocorrelation between work performance and health data using the formula: ； and ； The preliminary statistical correlation results are obtained, among which, Indicates at a point in time The performance data points are normalized to the values ​​of Represents the raw performance data point, at the time point The monitoring value of represent The average value of represent The standard deviation of represents the total number of data points; S312: Based on the preliminary statistical correlation results, perform correlation strength calculation to determine the correlation between work performance and health data, and obtain work performance analysis results.

7. The method for work adaptation of cancer survivors according to claim 1, characterized in that: The steps for obtaining the dynamic work allocation configuration are specifically as follows: S321: Based on the work performance analysis results, compare with the work adaptability question, analyze the impact of the current work assignment on health and work efficiency, identify work tasks that increase health risks, and obtain a work adaptability comparison result; S322: Based on the work adaptability comparison result, determine the adjustment direction of work allocation, including reducing workload, rearranging work time and rest period, and obtain dynamic work allocation configuration.

8. The method for work adaptation of cancer survivors according to claim 1, wherein: The steps for obtaining the optimized work adaptation result are specifically as follows: S411: Based on the dynamic work allocation configuration, collect implementation effect data after work adjustment, analyze key performance indicators in the implementation effect data, determine average work efficiency and health improvement rate, and obtain preliminary indicator analysis results; S412: Based on the preliminary indicator analysis results, the degree of match between the work adjustment and the work requirements of the cancer adaptor is evaluated using the formula: ； Optimize the work adjustment direction and obtain the optimized work adaptation results, among which, Indicates the matching degree, Indicates the The value of the key performance indicator, Indicates the The weight of the key performance indicators, is the total number of KPIs.

9. A cancer survivor work adaptation system, characterized by: The method for cancer survivor work adaptation according to any one of claims 1 to 8 is implemented, wherein the system comprises: The career path analysis module analyzes the career path of cancer survivors based on their career data, identifies key career path change nodes, and screens career transition periods associated with changes in health status to obtain career path change information. The trend prediction module calculates the frequency and magnitude of career changes within each window based on the career path change information, extracts the trend characteristics of career changes, and makes trend predictions for future career paths. It then analyzes job adaptability issues based on the prediction results to obtain an overview of adaptability issues. The work adaptability assessment module performs a time series analysis on the work data based on the adaptability problem overview, calculates the correlation between work performance and health data, compares it with the work adaptability problem, determines the adjustment direction of work allocation, and obtains a dynamic work allocation configuration; The dynamic work allocation module collects the implementation effect data after the work adjustment based on the dynamic work allocation configuration, analyzes the key performance indicators in the data, and optimizes the work adjustment direction according to the analysis results to obtain the optimized work adaptation result.

Images