Intelligent calculation and payment system for migrant workers' wages based on digital twins

Abstract

The present invention discloses an intelligent accounting and payment system for migrant workers' wages based on digital twins, which relates to the technical field of intelligent accounting and payment of migrant workers' wages, including an initial collection setting module, a data collection window module, a data analysis and feature extraction module, a task change classification module and a dynamic collection and control module; the initial collection setting module sets an initial collection interval duration to collect data on workers' work tasks according to the work arrangement of the construction site and the initial complexity of the workers' tasks. The present invention optimizes the data collection method according to the complexity and change pattern of the workers' work tasks through intelligent dynamic control of the collection interval. For complex and changeable tasks, the system shortens the collection interval, accurately records the switching of high and low intensity tasks, and ensures the fairness of wage accounting. For single tasks, the collection interval is extended, redundant data is reduced, resource utilization is improved, and the accuracy of wage accounting and system operation efficiency are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent calculation and payment of migrant workers' wages, and specifically to an intelligent calculation and payment system for migrant workers' wages based on digital twins. Background Art

[0002] The digital twin-based intelligent wage calculation and payment system for migrant workers is a comprehensive solution that combines the Internet of Things, artificial intelligence, and the Internet of Things (IoT). This system creates a digital twin model of the construction site to collect real-time work data on migrant workers, including attendance, workload, and job type. AI algorithms are used for data analysis and wage calculation, ensuring accuracy and fairness, enabling transparent and traceable wage payments, preventing wage arrears and disputes, and safeguarding the legitimate rights and interests of migrant workers. This intelligent system improves construction site management efficiency while enhancing the transparency and timeliness of migrant worker wage payments.

[0003] The digital twin account system tool leverages digital banking technology to establish a virtual model for contract evidence, process management, fund account management, fund transactions, and fund settlements in real-world transaction scenarios. This model maps each transaction to the actual transaction and records it. After migrant workers' wages are calculated, they are subsequently paid. This primarily relies on the "migrant worker wage special account" (enterprise-level master account) and project twin accounts established by the enterprise. The enterprise first opens an enterprise-level master account at a bank equipped with digital twin account technology and then establishes a project twin account for each project on the platform. When wages are disbursed, the construction company transfers them to the project twin account. After verifying the payroll, the general contractor completes the payment of wages to the workers through the platform. Wages are transferred from the project twin account to the worker's personal twin account, and the worker can withdraw them to a physical bank card through the digital twin personal mini-program. The platform uses three-factor authentication (worker name, ID number, and bank card number) to ensure payment accuracy. The system also supports a retry mechanism for failed withdrawals, ensuring fund security and smooth payment completion. Relying on the transaction funds supervision system of the head office, we provide comprehensive financial services including online membership identity authentication, fund account management, payment settlement, interest management, end-of-day reconciliation, and online printing of electronic vouchers to eligible corporate and individual users.

[0004] In terms of virtual account management, we strictly adhere to bank risk management requirements, implementing four-factor verification of corporate business records and online verification of personal public security information, as well as authentication of linked settlement accounts. Furthermore, we set single / daily / annual cumulative limits for virtual account withdrawals, and implemented multi-dimensional monitoring and early warning mechanisms at the system level to further mitigate transaction risks. We utilize a leading microservices architecture design and dynamic load balancing to meet merchants' high-frequency transaction processing needs and ensure stable system operation.

[0005] When intelligently calculating migrant workers' wages based on digital twins, existing technology typically identifies migrant workers' work tasks at fixed collection intervals throughout the work process. The goal is to accurately and in real time record workers' work status, including key data such as the type of tasks they perform, work intensity, and working hours. This approach ensures that the construction site management system can automatically collect and update workers' labor data, reducing errors and omissions in manual recording and providing an accurate data foundation for wage calculations. Through this real-time data collection, the system can effectively track workers' work progress and efficiency, timely adjust work schedules, optimize resource allocation, and fairly reflect workers' actual work results and contributions during wage settlement.

[0006] The existing technology has the following shortcomings:

[0007] If the worker's work tasks are relatively complex and the collection interval is set to a long time, the system may confuse or merge the high-intensity tasks completed by the worker with the low-intensity tasks, and calculate the salary according to the lower-intensity task standards. This will cause the time the worker completed the high-intensity tasks to be underestimated, resulting in the actual salary being lower than the deserved level. If the worker's work tasks are relatively simple and the collection interval is set to a short time, frequent data collection will lead to the generation of a large amount of redundant data. These data do not add effective information to the record of a single task, but instead increase the burden of data storage and processing.

[0008] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0009] The purpose of the present invention is to provide an intelligent wage accounting and payment system for migrant workers based on digital twins. By intelligently controlling the collection interval, the system effectively solves the data confusion and redundancy problems caused by improper collection methods. For complex and changeable work tasks, the system will shorten the collection interval to accurately capture task switching, prevent high-intensity task time from being underestimated, and ensure the fairness and accuracy of wage accounting. For single tasks, the system will extend the collection interval, reduce unnecessary data collection, reduce the burden of data storage and processing, and improve resource utilization. By dynamically adjusting the collection strategy, the system can adapt to different task modes, improve the accuracy of wage accounting and the efficiency of system operation, so as to solve the problems in the above-mentioned background technology.

[0010] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent calculation and payment system for migrant workers' wages based on digital twins, comprising an initial collection and setting module, a data collection window module, a data analysis and feature extraction module, a task change classification module, and a dynamic collection and control module;

[0011] The initial collection setting module sets an initial collection interval to collect data on workers' work tasks based on the work schedule at the construction site and the initial complexity of the workers' tasks;

[0012] The data collection window module establishes a fixed-length collection window when collecting initial data. During this collection window, the worker's work task data is continuously collected and recorded.

[0013] The data analysis and feature extraction module analyzes the work task data collected by workers after the initial data collection is completed in the collection window, extracts key features that represent changes in workers' work tasks, and uses a pre-trained machine learning model to evaluate the extracted features and identify the changing patterns of workers' work tasks;

[0014] The task change classification module categorizes workers' task changes within the collection window into three types: complex and variable, normal and simple, based on the evaluation results of the machine learning model.

[0015] The dynamic collection and control module dynamically adjusts the initial collection interval based on the evaluation results of the machine learning model for complex and variable work tasks and simple and variable work tasks, and adjusts the actual collection interval of migrant workers' work task identification to adapt to different task changes.

[0016] Preferably, the initial collection interval refers to the time interval initially set for collecting worker work task data when identifying worker work tasks based on digital twin technology. Secondly, the initial collection interval must meet the requirements of effectively monitoring the worker's work status without excessively consuming system resources.

[0017] Preferably, the extracted key features representing the changes in workers' work tasks include the frequency of workers switching from one task to another and the differences in the time spent to complete various tasks. After analyzing the frequency of workers switching from one task to another and the differences in the time spent to complete various tasks, a task switching frequency index and a task duration variation index are generated respectively. The task switching frequency index and the task duration variation index are input into a pre-trained machine learning model to generate a task change coefficient, and the task change coefficient is used to intelligently evaluate the change pattern of workers' work tasks.

[0018] Preferably, the task change coefficient generated after evaluation using the machine learning model is compared and analyzed with a preset reference threshold range of the task change coefficient to divide the worker's task change situation within the collection window. The specific division steps are as follows:

[0019] If the task change coefficient is within the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as normal change type;

[0020] If the task change coefficient is less than the minimum value of the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as a simple change type;

[0021] If the task change coefficient is greater than the maximum value of the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as a complex change type.

[0022] Preferably, after analyzing the frequency of workers switching from one task to another within the collection window, the specific steps for generating the task switching frequency index are as follows:

[0023] In the collection window, all task sequences performed by workers are recorded. The task sequence is represented by T. The task sequence represents the tasks recorded in chronological order in the collection window. Then: , among which represents the i-th task;

[0024] By analyzing the task sequence T, the number of different task types is counted. The statistical expression is: , where is the task type count, which represents the set of different task types that appear in the task sequence. It means to perform a deduplication operation on the tasks in the task sequence T to obtain a set of non-repeating tasks. Unique means to remove duplicate items and only retain different and unique elements.

[0025] The degree of task switching is measured by calculating the difference between adjacent tasks within the acquisition window. The calculation expression is: , Indicates the difference between adjacent tasks, measuring the extent to which workers switch from one task to another. Indicates a task With the task The difference between ,in, and Represents tasks and tasks Number, represents the absolute difference between task numbers, represents the maximum difference between all task pairs;

[0026] Count by task type The difference between adjacent tasks Calculate the task switching frequency index. The calculation expression is: , where represents the task switching frequency index, which measures the diversity and dispersion of workers in task switching. The logarithmic transformation of the task type count represents the logarithmic scaling of task diversity, and n represents the total length of the task sequence, that is, the number of tasks within the acquisition window.

[0027] Preferably, in the acquisition window, after analyzing the differences in the time taken to complete various tasks, the specific steps of generating the task duration variation index are as follows:

[0028] In the collection window, the time data of all tasks completed by workers are collected, including the start time, end time and task type of each task. represents the time it takes a worker to complete the kth task, and N represents the total number of tasks completed within the acquisition window;

[0029] Calculate the mean and standard deviation of the time it takes workers to complete all tasks. The calculation expression is: , , where Represents the average task time, which means the average time workers spend on each task. It represents the standard deviation of task time, which reflects the discreteness of task time, that is, the difference in the time workers spend on different tasks;

[0030] Calculate the task time difference coefficient. The calculation expression is: , where represents the task time variance coefficient,

[0031] The task duration variation index is calculated based on the task time difference coefficient and the task time standard deviation. It is used to describe the degree of variation of the task time. The calculation expression is: , where represents the task duration variation index, reflecting the complexity and variability of workers' task time allocation. Use the natural logarithm function to adjust the task time difference coefficient. The standard deviation of task time is combined with the total number of tasks to further quantify the impact of the dispersion of task time on the task duration variation index.

[0032] Preferably, for complex and variable tasks and simple and variable tasks, the initial collection interval is dynamically adjusted based on the evaluation results of the machine learning model. The specific steps are as follows:

[0033] Calculate the deviation between the task variation coefficient and the reference threshold range of the task variation coefficient. The calculation expression is: , where Indicates the task change coefficient, which reflects the degree of change of the current work task. and Respectively represent the minimum and maximum values ​​of the reference threshold range of the task variation coefficient, represents the task variation coefficient deviation;

[0034] Based on the task variation coefficient deviation, the initial control factor is calculated to preliminarily adjust the initial collection interval. The calculation expression is: , where Represents the initial control factor, which is used to adjust the initial degree of the initial collection interval length. represents an exponential decay term to avoid over-regulation, It is used to evaluate the nonlinear offset of the task variation coefficient relative to the reference threshold range of the task variation coefficient, providing a more sensitive regulatory response;

[0035] Based on the initial control factor, the control factor adjustment item is calculated to adapt to the specific needs of different task change modes. The calculation expression is: , where represents the control factor adjustment term, which is based on the initial control factor and introduces a sine function to increase the sensitivity to the task change pattern. By introducing periodic changes through the sine function, the flexibility of the initial control factor is further enhanced, enabling it to better adapt to various change patterns.

[0036] Preferably, the adjustment ratio of the initial collection interval is calculated according to the control factor adjustment item, and the calculation expression is: , where Indicates the adjustment ratio of the initial collection interval, reflecting the specific adjustment range of the initial collection interval. According to the ratio of the control factor adjustment item and the task change coefficient, the initial collection interval duration is adjusted nonlinearly;

[0037] Adjust the ratio based on the initial interval length and the actual interval length, and update the actual collection interval length to adapt to the changes in the worker's current tasks. The expression for updating the actual collection interval length is: , where Indicates the actual collection interval after update, reflecting the optimal collection frequency based on the task change pattern. Indicates the initial collection interval duration.

[0038] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0039] The present invention intelligently and dynamically adjusts the collection interval according to the complexity and change pattern of the workers' work tasks, effectively solving the data confusion and redundancy problems caused by improper collection frequency. When the workers' work tasks are complex and changeable, the system can shorten the collection interval, accurately capture the switching of high-intensity and low-intensity tasks, avoid underestimating the time of high-intensity tasks, and thus ensure the fairness and accuracy of wage accounting; when the workers' work tasks are relatively simple, the system can extend the collection interval, reduce unnecessary data collection, reduce the burden of data storage and processing, and optimize system resource utilization. Through this intelligent control mechanism, the system can dynamically adjust the collection strategy according to task changes, adapt to different work task modes, and improve the accuracy of wage accounting and the operation efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 This is a module schematic diagram of the intelligent calculation and payment system for migrant workers' wages based on digital twins in the present invention. DETAILED DESCRIPTION

[0042] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0043] The present invention provides Figure 1 The digital twin-based intelligent calculation and payment system for migrant workers' wages shown in the figure includes an initial collection setting module, a data collection window module, a data analysis and feature extraction module, a task change classification module, and a dynamic collection and control module;

[0044] The initial collection setting module sets an initial collection interval to collect data on workers' work tasks based on the work schedule of the construction site and the initial complexity of the workers' tasks;

[0045] At this stage, the collected data mainly includes the worker's location, task type, task duration, work intensity, etc. These data lay the foundation for subsequent analysis and evaluation.

[0046] The initial collection interval is the time interval set by the system for initially collecting worker task data when identifying worker tasks using digital twin technology. This interval defines how frequently the system collects data during the work process. For example, collecting data every 15 or 30 minutes aims to obtain detailed information about workers' current work status. This initial interval is typically determined based on an understanding of the construction site's work schedule and a preliminary assessment of the complexity of the workers' tasks.

[0047] The initial collection interval should be frequent enough to capture any changes in tasks that may occur during the worker's work process, ensuring that it accurately reflects the actual work situation. Secondly, the interval should not be too short to avoid generating excessive redundant data and increasing the burden of data storage and processing. Therefore, the selection of the initial collection interval length needs to strike a balance between data capture accuracy and efficient use of system resources, ensuring that the worker's work status can be effectively monitored without excessively consuming system resources.

[0048] The data collection window module establishes a fixed-length collection window (e.g., 1 hour) when collecting initial data. During this collection window, the worker's work task data is continuously collected and recorded.

[0049] A fixed-length window can help the system accumulate sufficient data in the initial stage and provide a complete information perspective for subsequent analysis.

[0050] When collecting initial data, establishing a fixed-length collection window (e.g., one hour) means the system will continuously collect and record workers' work task data over a preset period of time. This allows the system to obtain sufficient data samples in a relatively short period of time, capturing the various tasks performed by workers and their changes during that period. A fixed-length collection window helps establish a basic understanding of workers' work patterns and facilitates analysis of characteristics such as the temporal distribution of different tasks, intensity variations, and task switching frequency. Continuous collection within this window also ensures data integrity and continuity, reducing information gaps and errors caused by intermittent collection. This allows the system to maintain a comprehensive and accurate record of workers' work status at an early stage, laying the foundation for subsequent feature extraction and model evaluation.

[0051] The data analysis and feature extraction module analyzes the work task data collected by workers after the initial data collection is completed in the collection window, extracts key features that represent changes in workers' work tasks, and uses a pre-trained machine learning model to evaluate the extracted features and identify the changing patterns of workers' work tasks;

[0052] The key features extracted to represent the changes in workers' work tasks include the frequency of workers switching from one task to another and the differences in the time spent to complete various tasks. After analyzing the frequency of workers switching from one task to another and the differences in the time spent to complete various tasks, a task switching frequency index and a task duration variation index are generated respectively. The task switching frequency index and the task duration variation index are input into a pre-trained machine learning model to generate a task change coefficient. The task change coefficient is used to intelligently evaluate the change pattern of workers' work tasks.

[0053] A pre-trained machine learning model refers to an algorithm model that has been trained and optimized using a large amount of historical data. These data include various change patterns of workers' work tasks and their related characteristics, such as differences in task switching frequency and task duration. The training process usually involves inputting these feature data and using supervised learning, unsupervised learning, or reinforcement learning methods to allow the model to learn how to accurately predict or classify task change patterns based on these features. In the present invention, the pre-trained model has learned how to map the input data of the task switching frequency index and the task duration variation index into task change coefficients, thereby being able to effectively evaluate the complexity and variability of workers' work tasks. Because the model has been verified and tuned through historical data, it can predict newly input data with high accuracy and efficiency, providing a basis for intelligently evaluating changes in workers' work tasks.

[0054] A high frequency of worker switching from one task to another during the collection window typically indicates a complex pattern of changes in their work tasks. This high frequency of task switching means that workers are required to perform multiple different types of tasks within a short period of time. This not only requires workers to possess a wide range of skills and adaptability, but may also involve varying work intensity and operational processes. Frequent task switching increases the dynamic nature and uncertainty of work, making task management more complex. This situation often requires more detailed monitoring and analysis to accurately reflect workers' workload and labor contribution, ensuring fair and accurate wage calculations. A high frequency of task switching is a key indicator of the complexity and variability of workers' work tasks, indicating a highly dynamic and challenging work environment.

[0055] After analyzing the frequency of workers switching from one task to another in the collection window, the specific steps for generating the task switching frequency index are as follows:

[0056] In the collection window, all task sequences performed by workers are recorded. The task sequence is represented by T. The task sequence represents the tasks recorded in chronological order in the collection window. Then: , among which represents the i-th task;

[0057] Each task (such as moving, installation, inspection, etc.) is recorded in chronological order, which can reflect the actual task switching of workers.

[0058] By analyzing the task sequence T, the number of different task types is counted. The statistical expression is: , where is the task type count, which represents the set of different task types that appear in the task sequence. It means to perform a deduplication operation on the tasks in the task sequence T to obtain a set of non-repeating tasks. Unique means to remove duplicate items and only retain different and unique elements.

[0059] This step helps to understand the diversity of tasks that workers are involved in within the acquisition window and how many different tasks there are.

[0060] The degree of task switching is measured by calculating the difference between adjacent tasks within the acquisition window. The calculation expression is: , Indicates the difference between adjacent tasks, measuring the extent to which workers switch from one task to another. Indicates a task With the task The difference between ,in, and Represents tasks and tasks Number, represents the absolute difference between task numbers, represents the maximum difference between all task pairs;

[0061] It plays a normalizing role, making the task switching breadth vary between 0 and 1. A larger difference indicates that the task switching is more extensive and diverse, reflecting the complexity of the task.

[0062] Count by task type The difference between adjacent tasks Calculate the task switching frequency index. The calculation expression is: , where represents the task switching frequency index, which measures the diversity and dispersion of workers in task switching. The logarithmic transformation of the task type count represents the logarithmic scaling of task diversity, and n represents the total length of the task sequence, that is, the number of tasks within the acquisition window.

[0063] The Task Switching Frequency Index (TSF) shows that, within the acquisition window, the frequency with which workers switch from one task to another is analyzed. A higher TSF value indicates that workers frequently switch between different tasks within a short period of time. This suggests that workers have a complex pattern of task changes, involving multiple task types and frequent task transitions. This high frequency of task switching likely requires workers to possess diverse skills and the ability to adapt quickly, thus suggesting that their work environment and task schedules are relatively dynamic and diverse. Conversely, a lower TSF indicates that workers have fewer and more stable task types within a given period, with infrequent changes. This suggests that workers have a relatively simple and consistent pattern of task changes, with relatively single task types.

[0064] Large variations in the time it takes to complete various tasks often indicate a complex and volatile pattern of tasks. When workers are required to complete multiple tasks within a short period of time, and the time required for each task varies significantly, this reflects the diversity and imbalance of tasks, indicating that workers face the challenge of frequent task switching and adapting to varying task requirements. This large time variation often means that workers must constantly adjust their work pace and methods to meet the demands of various tasks, indicating the complexity and variability of work tasks. Therefore, large task-time variations are a key indicator of the complexity and variability of workers' work tasks.

[0065] In the collection window, after analyzing the differences in the time taken to complete various tasks, the specific steps for generating the task duration variation index are as follows:

[0066] In the collection window, the time data of all tasks completed by workers are collected, including the start time, end time and task type of each task. represents the time (in minutes) it takes a worker to complete the kth task, and N represents the total number of tasks completed within the acquisition window;

[0067] Calculate the mean and standard deviation of the time it takes workers to complete all tasks. The calculation expression is: , , where Represents the average task time, which means the average time workers spend on each task. It represents the standard deviation of task time, which reflects the discreteness of task time, that is, the difference in the time workers spend on different tasks;

[0068] The task time variance coefficient is calculated to measure the relative change of task time. Unlike directly using the task time standard deviation, the task time variance coefficient takes into account the influence of the task time average value, so that the change of task time is evaluated relative to the average value, which more accurately reflects the relative change of task time. The calculation expression of the task time variance coefficient is: , where represents the coefficient of variation of task time, which is used to express the relative variability of task time and standardizes the fluctuation of task time;

[0069] According to the task time variation coefficient and task time standard deviation Calculate the task duration variation index. The task duration variation index is a quantitative indicator used to describe the degree of variation in task time. The calculation expression is: , where represents the task duration variation index, reflecting the complexity and variability of workers' task time allocation. The natural logarithm function is used to adjust the task time difference coefficient so that the growth of the task duration variation index slows down as the task time difference coefficient increases, preventing the exponential growth from being too fast. The standard deviation of task time is combined with the total number of tasks to further quantify the impact of the dispersion of task time on the task duration variation index.

[0070] The Task Duration Variation Index (TDV), generated by analyzing the differences in time spent completing various tasks within the acquisition window, shows that larger values ​​generally indicate a more complex pattern of variation in workers' work tasks. This is because a higher TDV reflects greater variability in the time workers spend between tasks, frequent task switching, and uneven variations in task intensity and duration, demonstrating the complexity and variability of work tasks. Conversely, a lower TDV indicates less variability in the time workers spend on various tasks, less frequent task switching, or relatively consistent task durations, suggesting a relatively simple and stable pattern of variation in workers' work tasks. Therefore, the TDV can serve as an effective indicator for assessing the variability and complexity of workers' tasks.

[0071] The machine learning model is not specifically limited here, and can achieve the task switching frequency index and task duration variation index Conduct comprehensive analysis to generate task variation coefficients In order to implement the technical solution of the present invention, the present invention provides a specific implementation method;

[0072] Task variation coefficient The resulting calculation formula is: , where 、 Task switching frequency index and task duration variation index The preset scaling factor of 、 Both are greater than 0.

[0073] It can be seen from the task variation coefficient that, within the collection window, the greater the performance value of the task switching frequency index generated after analyzing the frequency of workers switching from one task to another, and the greater the performance value of the task duration variation index generated after analyzing the differences in the time spent to complete various tasks, that is, the greater the performance value of the task variation coefficient generated after evaluation using the machine learning model, the more complex the change pattern of the worker's work tasks, and vice versa, the less complex the change pattern of the worker's work tasks.

[0074] The task change classification module categorizes workers' task changes within the collection window into three types: complex and variable, normal and simple, based on the evaluation results of the machine learning model.

[0075] The task change coefficient generated by the machine learning model is compared with the pre-set reference threshold range of the task change coefficient to classify the workers' task changes within the collection window. The specific classification steps are as follows:

[0076] If the task change coefficient is within the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as normal change type;

[0077] If the task change coefficient is less than the minimum value of the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as a simple change type;

[0078] If the task change coefficient is greater than the maximum value of the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as a complex change type.

[0079] Complex and variable tasks refer to situations in which workers' work tasks frequently change within the collection window, with significant variations in the duration, intensity, and type of each task. This type typically includes frequent task switching, diverse task types, and significant fluctuations in task intensity, indicating that workers need to constantly adapt to new tasks and work environments. This highly dynamic and complex task pattern can lead to a high workload and require workers to possess strong multitasking skills and flexibility to cope with various challenges on the job.

[0080] Normal variation describes a worker's work task changes within the collection window, with relatively stable frequency and type of changes. Switching between tasks is regular and predictable. This type of task change doesn't frequently disrupt the worker's work rhythm, and the intensity and duration of tasks remain roughly the same or vary slightly. This situation typically reflects a common work pattern, where workers have time to adjust to task changes and the tasks themselves don't require rapid adaptation to new work requirements. Workers are able to complete tasks methodically and don't experience fatigue or excessive stress from frequent changes.

[0081] Simple Variation refers to a situation where workers' tasks rarely change within the collection window, or even just perform a single task throughout the entire window. Task type, intensity, and duration are remarkably consistent. This type of task pattern reflects the monotony and repetitive nature of the worker's work, with task switching being almost nonexistent or extremely slow. This work pattern generally does not require workers to possess high adaptability, as the tasks are fixed and regular, allowing workers to develop proficiency and efficiency through repetitive operations. This type of task may be suitable for work environments with simple operations or those that do not require frequent adjustments.

[0082] The dynamic data collection and control module dynamically adjusts the initial data collection interval based on the evaluation results of the machine learning model for complex and variable work tasks and simple and variable work tasks, and adjusts the actual data collection interval for migrant workers' work task identification to adapt to different task changes;

[0083] In response to complex and variable tasks, as well as simple and variable tasks, the initial collection interval is dynamically adjusted based on the evaluation results of the machine learning model. The specific steps are as follows:

[0084] Calculate the deviation between the task variation coefficient and the reference threshold range of the task variation coefficient. The calculation expression is: , where Indicates the task change coefficient, which reflects the degree of change of the current work task. and Respectively represent the minimum and maximum values ​​of the reference threshold range of the task variation coefficient, represents the task variation coefficient deviation;

[0085] This step helps determine the deviation of the task change degree from the expected range, providing a basis for the subsequent adjustment of the collection interval length.

[0086] Based on the task change coefficient deviation, the initial control factor is calculated to preliminarily adjust the initial collection interval to ensure that it can quickly respond to the needs of different task change types. The calculation expression is: , where Represents the initial control factor, which is used to adjust the initial degree of the initial collection interval length. Represents an exponential decay term, ensuring that the initial control factor gradually levels off in extreme cases (such as when the task change coefficient is extremely large or extremely small) to avoid over-adjustment. It is used to evaluate the nonlinear offset of the task variation coefficient relative to the reference threshold range of the task variation coefficient, providing a more sensitive regulatory response;

[0087] The initial degree used to adjust the initial collection interval refers to the process of dynamically adjusting the interval for worker task data collection. The system first determines the initial adjustment amount or direction based on a preliminary assessment of task changes. This initial adjustment is based on the task change coefficient and task change coefficient deviation of the current task change, aiming to quickly respond to the needs of task changes.

[0088] Specifically, when the task variation pattern is assessed as complex and variable or simple and variable, the initial control factor determines how the initial collection interval should be adjusted (increased or decreased). If the task variation is assessed as complex and variable, the initial control factor tends to shorten the initial collection interval to collect data more frequently to capture rapidly changing task conditions. Conversely, if the task variation is assessed as simple and variable, the initial control factor tends to lengthen it, potentially reducing the frequency of data collection and reducing unnecessary data redundancy and system resource consumption.

[0089] Based on the initial control factor, the control factor adjustment item is calculated to adapt to the specific needs of different task change modes. The calculation expression is: , where represents the control factor adjustment term, which is based on the initial control factor and introduces a sine function to increase the sensitivity to the task change pattern. By introducing periodic changes through the sine function, the flexibility of the initial control factor is further enhanced, making it better able to adapt to various change patterns;

[0090] According to the control factor adjustment item, the adjustment ratio of the initial collection interval is calculated. The calculation expression is: , where Indicates the adjustment ratio of the initial collection interval, reflecting the specific adjustment range of the initial collection interval. According to the ratio of the control factor adjustment item and the task variation coefficient, the initial collection interval is adjusted nonlinearly to ensure that the frequency is increased in high-complexity tasks and reduced in low-complexity tasks;

[0091] Adjust the ratio based on the initial interval length and the actual interval length, and update the actual collection interval length to adapt to the changes in the worker's current tasks. The expression for updating the actual collection interval length is: , where Indicates the actual collection interval after update, reflecting the optimal collection frequency based on the task change pattern. Indicates the initial collection interval duration.

[0092] The present invention intelligently and dynamically adjusts the collection interval according to the complexity and change pattern of the workers' work tasks, effectively solving the data confusion and redundancy problems caused by improper collection frequency. When the workers' work tasks are complex and changeable, the system can shorten the collection interval, accurately capture the switching of high-intensity and low-intensity tasks, avoid underestimating the time of high-intensity tasks, and thus ensure the fairness and accuracy of wage accounting; when the workers' work tasks are relatively simple, the system can extend the collection interval, reduce unnecessary data collection, reduce the burden of data storage and processing, and optimize system resource utilization. Through this intelligent control mechanism, the system can dynamically adjust the collection strategy according to task changes, adapt to different work task modes, and improve the accuracy of wage accounting and the operation efficiency of the system.

[0093] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0094] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0095] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. The intelligent calculation and payment system for migrant workers’ wages based on digital twins is characterized by: It includes the initial acquisition setting module, data acquisition window module, data analysis and feature extraction module, task change classification module and dynamic acquisition control module; The initial collection setting module sets an initial collection interval to collect data on workers' work tasks based on the work schedule of the construction site and the initial complexity of the workers' tasks; The data collection window module establishes a fixed-length collection window when collecting initial data. During this collection window, the worker's work task data is continuously collected and recorded. The data analysis and feature extraction module analyzes the work task data collected by workers after the initial data collection is completed in the collection window, extracts key features that represent changes in workers' work tasks, and uses a pre-trained machine learning model to evaluate the extracted features and identify the changing patterns of workers' work tasks; The task change classification module categorizes workers' task changes within the collection window into three types: complex and variable, normal and simple, based on the evaluation results of the machine learning model. The dynamic data collection and control module dynamically adjusts the initial data collection interval based on the evaluation results of the machine learning model for complex and variable work tasks and simple and variable work tasks, and adjusts the actual data collection interval for migrant workers' work task identification to adapt to different task changes; The key features extracted to represent changes in workers' work tasks include the frequency with which workers switch from one task to another and the differences in the time it takes to complete each type of task. After analyzing the frequency with which workers switch from one task to another and the differences in the time it takes to complete each type of task, a task switching frequency index and a task duration variation index are generated, respectively. These are then input into a pre-trained machine learning model to generate a task variation coefficient, which is used to intelligently evaluate the changing pattern of workers' work tasks. After analyzing the frequency of workers switching from one task to another in the collection window, the specific steps for generating the task switching frequency index are as follows: In the collection window, all task sequences performed by workers are recorded. The task sequence is represented by T. The task sequence represents the tasks recorded in chronological order in the collection window. Then: ,in represents the i-th task; By analyzing the task sequence T, the number of different task types is counted. The statistical expression is: , where is the task type count, which represents the set of different task types that appear in the task sequence. It means to perform a deduplication operation on the tasks in the task sequence T to obtain a set of non-repeating tasks. Unique means to remove duplicate items and only retain different and unique elements. The degree of task switching is measured by calculating the difference between adjacent tasks within the acquisition window. The calculation expression is: , Indicates the difference between adjacent tasks, measuring the extent to which workers switch from one task to another. Indicates a task With the task The difference between ,in, and Represents tasks and tasks Number, represents the absolute difference between task numbers, represents the maximum difference between all task pairs; Count by task type The difference between adjacent tasks Calculate the task switching frequency index. The calculation expression is: , where represents the task switching frequency index, which measures the diversity and dispersion of workers in task switching. The logarithmic transformation of the task type count represents the logarithmic scaling of task diversity, and n represents the total length of the task sequence, that is, the number of tasks within the acquisition window.

2. The intelligent calculation and payment system for migrant workers' wages based on digital twins according to claim 1 is characterized in that: The initial collection interval refers to the time interval initially set for collecting worker work task data when identifying worker work tasks based on digital twin technology. Secondly, the initial collection interval must meet the requirements of effectively monitoring the worker's work status without excessively consuming system resources.

3. The intelligent calculation and payment system for migrant workers' wages based on digital twins according to claim 1 is characterized in that: The task change coefficient generated by the machine learning model is compared with the pre-set reference threshold range of the task change coefficient to classify the workers' task changes within the collection window. The specific classification steps are as follows: If the task change coefficient is within the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as normal change type; If the task change coefficient is less than the minimum value of the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as a simple change type; If the task change coefficient is greater than the maximum value of the task change coefficient reference threshold range, the worker's task change situation within the collection window is classified as a complex change type.

4. The intelligent calculation and payment system for migrant workers' wages based on digital twins according to claim 1 is characterized in that: In the collection window, after analyzing the differences in the time taken to complete various tasks, the specific steps for generating the task duration variation index are as follows: In the collection window, the time data of all tasks completed by workers are collected, including the start time, end time and task type of each task. represents the time it takes a worker to complete the kth task, and N represents the total number of tasks completed within the acquisition window; Calculate the mean and standard deviation of the time it takes workers to complete all tasks. The calculation expression is: , , where Represents the average task time, which means the average time workers spend on each task. It represents the standard deviation of task time, which reflects the degree of dispersion of task time, that is, the difference in the time workers spend on different tasks; Calculate the task time difference coefficient. The calculation expression is: , where represents the task time variance coefficient, The task duration variation index is calculated based on the task time difference coefficient and the task time standard deviation. It is used to describe the degree of variation of the task time. The calculation expression is: , where represents the task duration variation index, reflecting the complexity and variability of workers' task time allocation. Use the natural logarithm function to adjust the task time difference coefficient. The standard deviation of task time is combined with the total number of tasks to further quantify the impact of the dispersion of task time on the task duration variation index.

5. The intelligent calculation and payment system for migrant workers' wages based on digital twins according to claim 3 is characterized in that: In response to complex and variable tasks, as well as simple and variable tasks, the initial collection interval is dynamically adjusted based on the evaluation results of the machine learning model. The specific steps are as follows: Calculate the deviation between the task variation coefficient and the reference threshold range of the task variation coefficient. The calculation expression is: , where Indicates the task change coefficient, which reflects the degree of change of the current work task. and Respectively represent the minimum and maximum values ​​of the reference threshold range of the task variation coefficient, represents the task variation coefficient deviation; Based on the task variation coefficient deviation, the initial control factor is calculated to preliminarily adjust the initial collection interval. The calculation expression is: , where Represents the initial control factor, which is used to adjust the initial degree of the initial collection interval length. represents an exponential decay term to avoid over-regulation, It is used to evaluate the nonlinear offset of the task variation coefficient relative to the reference threshold range of the task variation coefficient, providing a more sensitive regulatory response; Based on the initial control factor, the control factor adjustment item is calculated to adapt to the specific needs of different task change modes. The calculation expression is: , where represents the control factor adjustment term, which is based on the initial control factor and introduces a sine function to increase the sensitivity to the task change pattern. The flexibility of the initial control factors is further enhanced by introducing periodic changes through the sine function.

6. The intelligent calculation and payment system for migrant workers' wages based on digital twins according to claim 5 is characterized in that: According to the control factor adjustment item, the adjustment ratio of the initial collection interval is calculated. The calculation expression is: , where Indicates the adjustment ratio of the initial collection interval, reflecting the specific adjustment range of the initial collection interval. According to the ratio of the control factor adjustment item and the task change coefficient, the initial collection interval duration is adjusted nonlinearly; Adjust the ratio based on the initial interval length and the actual interval length, and update the actual collection interval length to adapt to the changes in the worker's current tasks. The expression for updating the actual collection interval length is: , where Indicates the actual collection interval after update, reflecting the optimal collection frequency based on the task change pattern. Indicates the initial collection interval duration.

Images