Production workshop task intelligent allocation method based on big data

Abstract

The invention relates to the technical field of production workshop task intelligent allocation based on big data, and discloses a production workshop task intelligent allocation method based on big data. Through a dynamic production process model, the system performs multi-dimensional analysis on task characteristics, resource states and environmental factors, and optimizes task priorities and resource allocation. The task priority is combined with the task difficulty, the priority, the equipment and the personnel state, the matching of the task and the resource is accurately evaluated, and the scheduling efficiency is improved. A resource state function ensures that high-priority tasks are allocated to proper resources, and equipment overload or idling is avoided. The equipment utilization rate function adjusts task allocation according to the real-time utilization rate, resource waste is avoided, and the production efficiency is improved. Comprehensive analysis ensures that the system flexibly deals with equipment faults and personnel load changes, task allocation is adjusted in real time, production delay and resource waste are reduced, and smooth production process is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent task allocation in a production workshop based on big data, and specifically provides an intelligent task allocation method for a production workshop based on big data. Background Art

[0002] As the manufacturing industry enters the stage of intelligent and automated development, the task allocation problem in the production workshop has become the key to improving production efficiency and resource utilization rate. In traditional production workshops, task allocation usually relies on manual scheduling or automated systems based on fixed rules, lacking adaptability and flexibility to the dynamic production environment. With the rapid development of big data, Internet of Things, and artificial intelligence technologies, data-driven intelligent production scheduling methods have become a popular direction for improving workshop production efficiency and reducing production delays.

[0003] Traditional task scheduling methods usually rely on experienced schedulers or allocate tasks through simple preset rules. This method ignores the real-time data and dynamic changes in the production process, and the scheduling effect usually has large fluctuations. Especially when facing complex and changeable production tasks, traditional methods are difficult to handle problems such as real-time adjustment of task priorities, changes in equipment load, and matching of employee skills with tasks. In addition, traditional methods also have problems such as uneven resource allocation, low equipment utilization rate, and excessive employee load, resulting in the failure to maximize production efficiency. Traditional production scheduling systems lack the ability of dynamic adjustment. Due to frequent equipment failures, changes in production tasks, or fluctuations in employee status during the production process, existing systems usually cannot adjust task allocation strategies in a timely manner according to these dynamic changes. Therefore, the production workshop cannot respond flexibly to changes, resulting in low production efficiency and resource utilization rate. Existing technologies usually cannot effectively integrate real-time data from the production workshop, such as the current status of employees and the operating conditions of equipment. These information is crucial for task scheduling, but the real-time feedback mechanism in existing technologies is relatively weak, making it difficult to optimize task allocation in real time, thus affecting production efficiency.

[0004] In summary, this case provides an intelligent task allocation method for a production workshop based on big data. By fully considering factors such as task complexity, employee skills, and equipment capabilities, and combining real-time data feedback, it ensures the dynamic and accurate task allocation, thereby effectively improving the overall efficiency and flexibility of the production workshop, and solving the problems of task scheduling lag and uneven resource allocation existing in the prior art. Summary of the Invention

[0005] The present invention provides an intelligent task allocation method for a production workshop based on big data, which helps to solve the problems mentioned in the above background art.

[0006] The present invention provides the following technical solution: An intelligent task allocation method for a production workshop based on big data, including: Obtain device status data denoted as Rdev, personnel status data denoted as Rpers, task status data denoted as Ttask, and production environment data denoted as Eenv; The device status data specifically includes: Ridev is the current status of device i, and the available status of device i is denoted as 1, and the failure status is denoted as 0; Uidev is the utilization rate of device i, and the utilization rate of device i is represented by 0 - 1, where 0 means not in use, 1 means running at full load, and the rest means normal operation; Tidev is the remaining service life of device i, in hours; The personnel status data specifically includes: Sjpers is the working status of employee j, and the status when employee j is working is denoted as 1, and the idle status is denoted as 0; Wjpers is the skill level of employee j, and the skill level of employee j is represented by 0 - 1, where 0 means no ability, 1 means the highest ability, and Hjpers is the current workload of employee j, represented by the number of tasks; The task status data specifically includes: Dktask is the difficulty score of task k, and the difficulty of task k is scored using 0 - 1, where 0 means very simple, 1 means very complex; Pktask is the priority of task k, and the priority of task k is represented by 0 - 1, where 0 means low priority, 1 means high priority; Tktask is the estimated completion time of task k, in hours; The production environment data specifically includes: Tenv is the temperature in the production workshop; Henv is the humidity in the production workshop; Use a dynamic production process model to represent the state of the production system: ; Among them, P(t) is the production process state at time t; Ti is the characteristic of task i; Rj is the state of resource j, including device status and personnel status; Ek is the environmental characteristic; Ui is the utilization rate of device i; Among them, the f() function is specifically: ; Among them, f1(Ti) is the task characteristic function, specifically: , Dktask is the difficulty score of task k, and Pktask is the priority score of task k; f2(Rj) is the resource status function, specifically: , Rkdev is the state of device k, and Skpers is the working status of employee k; f3(Ek) is the environmental status function, specifically: , where Tenv is the temperature in the production workshop and Henv is the humidity in the production workshop; f4(Ui) is the equipment utilization rate function, specifically: , where Uidev is the utilization rate of equipment i; Among them, α1, α2, α3, and α4 are the relative influence weight coefficients of each factor on the production process, satisfying ; β1 and β2 are the task characteristic weight coefficients; g1 and g2 are the resource status weight coefficients; d1 and d2 are the environmental status weight coefficients; l1 is the weight coefficient of the equipment utilization rate; Perform multi-dimensional task characteristic analysis and task priority calculation.

[0007] Optionally, the multi-dimensional task characteristic analysis and task priority calculation specifically include: S1. Definition of multi-dimensional task characteristics; S2. Task priority calculation method; Assign different weights to each characteristic; Record the comprehensive priority of each task as Pktask: ; Among them, α3, α4, α5, and α6 are the weight coefficients of the characteristics, representing the relative importance of task difficulty, resource requirements, urgency, and environmental adaptability in the total priority calculation, satisfying ; S3. Priority dynamic adjustment; The priority dynamic adjustment formula is: ; Among them, Pktask,adj is the priority of task k after dynamic adjustment; DTkfeedback is the feedback time difference, specifically the time difference from the last priority adjustment of task k to the present; β3 is the sensitivity factor of priority adjustment, used to control the amplitude of priority dynamic adjustment; Use an intelligent task allocation strategy to allocate tasks.

[0008] Optionally, the definition of multi-dimensional task characteristics specifically includes: S11. Task difficulty characteristic Dktask: The difficulty score of task k, evaluated based on the complexity of the task, the number of required operation steps, and the execution time, and deduced through historical data and task models: ; Among them, Nksteps is the number of operation steps of task k; Tkduration is the estimated execution time of task k, in hours; α1 and α2 are empirical weight coefficients, reflecting the influence of the number of steps and time on the task difficulty; S12. Task resource requirement feature Rktask: The resource requirement of task k, obtained through data analysis and resource allocation model: ; Among them, Rktask,i is the requirement of task k for resource i, including equipment, personnel, and environmental conditions; Nresources is the number of types of resources required for task k; S13. Task urgency feature Ektask: The urgency of the task is evaluated based on the delivery time of the task and the deadline of the project: ; Among them, Tkdue is the deadline of task k; Tcurrent is the current time; S14. Task environment adaptation feature Aktask: The influence of the environmental temperature and humidity where the task is located on task execution: ; Among them, Tkenv is the influence of the current environmental temperature and humidity on task k, and Toptimal is the optimal environmental temperature and humidity for task k, obtained through historical data.

[0009] Optionally, the intelligent task allocation strategy specifically includes: Obtain the task with the highest priority and allocate resources to it. The matching degree calculation formula is: ; Among them, Tktask is the estimated completion time of task k, in hours; Rjdev is the availability of device j. The availability of the device is represented by 0 - 1, where 0 means the device is unavailable and 1 means the device is fully available; Sjpers is the working status of employee j; For each task, select the resource with the maximum matching degree M(tk,Rj) for allocation and update the resource status Rj; Perform dynamic scheduling on the entire production process and obtain real - time feedback.

[0010] Optionally, the performing dynamic scheduling on the entire production process and obtaining real - time feedback specifically includes: S4. Dynamic adjustment strategy; When problems occur during task execution, adjust task allocation through real - time monitoring data feedback. The feedback function is: ; Among them, Tkreal is the actual execution time of task k, in hours; Tkexpected is the expected execution time of task k, in hours; When Fkexpected > 1, the system will adjust the task priority or reallocate resources; S5. Scheduling adjustment: S51. Set the dynamic scheduling adjustment objective function, specifically: ; Among them, Tdowntime is the downtime in the current production process, in hours; Udev is the current utilization rate of the equipment; Eefficiency is the task completion efficiency score, with the score ranging from 0 to 1, where 0 represents the lowest efficiency and 1 represents the highest efficiency; l1, l2, and l3 are the weight coefficients for each item, used to control the relative importance of the objectives, satisfying ; S52. Constraints for scheduling adjustment; Adjust the priority of the task, and the adjustment function is: ; Among them, Pktask(t) is the priority of task k at time t; Pktask(t - 1) is the priority of task k at the previous time; α5 is the weight coefficient for priority adjustment; Tiresponse is the response time of task k on device i; Dktask is the difficulty score of task k; Perform personalized task allocation for employees and equipment.

[0011] Optionally, the constraints for the scheduling adjustment specifically include: S521. Equipment status constraint; Set the failure probability threshold Pthresh; For each device i, if the failure probability Pifault of device i exceeds Pthresh, then this device cannot be allocated anymore; ; Among them, Pifault is the failure rate of device i; Pthresh is the failure probability threshold. If the failure probability of the device is higher than this value, the device cannot continue to work; S522. Personnel ability constraint; The skill level Wjpers of employee j must meet the skill requirement Wktask of task k: ; Among them, Wjpers is the skill level of employee j; Wktask is the skill requirement of task k; S523. Production compliance constraint; The load of each device i at a certain moment cannot exceed its maximum working capacity Cidev, that is, the current load Lidev of the device must satisfy: ; where Lidev is the current working load of device i; Cidev is the maximum working load of device i; S524. Scheduling adjustment strategy; After each task assignment, the operation status of devices and personnel is monitored in real time through a feedback mechanism, the task assignment and production order are adjusted, and the response time of tasks and devices is set: ; where Tbase is the basic response time of the device in the idle state, obtained from historical production data; Lidev and Cidev are the current load and maximum load of device i respectively; Dktask is the difficulty score of task k; Ridev is the status of device i, represented by 1 for available and 0 for faulty; β1 is the influence factor of task difficulty on the response time; β2 is the influence factor of device status on the response time; If the working load of the device is close to the maximum value after task assignment, part of the tasks are reassigned to device i' with a smaller load, so that the working load Lidev of each device is close to the maximum load Cidev. The adjustment formula is: ; where Lidev is the working load of the current device i; Li'dev is the working load of device i' after the new task assignment; DL is the task load of the reassignment.

[0012] Optionally, the personalized task assignment for employees specifically includes: The task-employee and task-equipment matching degree model is: ; where Si(tk,ej) is the matching degree of task tk on given employee ej and device ei; f1(tk,ej) is the matching degree of the complexity of task tk and the skill of employee ej, specifically: , is the complexity of task tk, is the skill level of employee ej; f2(tk,ej) is the matching degree of the priority of task tk and the working load of employee ej, specifically: , is the priority of task tk, is the current working load of employee ej; f3(tk, ej, ei) is the matching degree between the requirements of task tk for device ei and the current load of the device, specifically: , is the total capacity of device ei, is the current load of device ei, is the time requirement of task tk; f4(ej, ei) is the cooperation efficiency between employee ej and device ei, specifically: , the historical efficiency of employee ej using device ei, is the average efficiency of employee ej working on all devices; α1, α2, α3, and α4 are weight coefficients used to control the relative importance of each factor; For each task tk, calculate the matching degree Si(tk, ej) of all employee and device combinations; For task tk, select the employee ej and device ei with the highest matching degree, specifically: ; Allocate task tk to the selected employee and device , and update the load status of the employee and the device.

[0013] The present invention has the following beneficial effects: Through the task feature function, the difficulty score and priority of a task are associated with task features. By combining with the resource status function to accurately analyze the status of equipment and personnel, it can help the system dynamically evaluate the matching of task priorities and resources. Specifically, the priority of a task and the status of resources, such as the idle status of equipment, the skill level and workload of employees, jointly determine the task allocation. It solves the problem in the prior art that task priorities cannot accurately consider resource conditions, improves the efficiency and accuracy of task scheduling, ensures that high-priority tasks can be quickly allocated to appropriate resources for execution, and reduces production delays. In the resource status function, the real-time status of equipment and personnel is comprehensively considered, such as the availability and utilization rate of equipment, the working status and workload of employees, to achieve an efficient match between equipment and personnel. Through this analysis, the system can dynamically adjust the usage of resources, avoiding the problem of reduced production efficiency caused by overloading of equipment or personnel in the prior art. When equipment fails or an employee's workload is too high, the system will automatically select resources with better status to ensure the continuity and efficiency of production. In the environmental status function, the impact of environmental data such as temperature and humidity in the production workshop on the production process is considered. This solves the problem that traditional task scheduling methods ignore production environment factors. Changes in environmental temperature and humidity directly affect the work efficiency of equipment and personnel. Real-time monitoring of this data and incorporating it into task allocation decisions enable the production process to be adjusted in real time according to environmental conditions, thereby improving the operating stability of equipment and the work comfort of personnel. Through the equipment utilization rate function, the utilization rate of equipment is incorporated into task allocation decisions, and tasks can be reasonably allocated according to the current usage status of the equipment. This step solves the problem of overuse or idleness of equipment resources, optimizes the operating load of equipment, and thus improves the overall production efficiency. During the production process, the equipment utilization rate no longer depends on a single rule, but is dynamically adjusted according to real-time data, avoiding the double waste of equipment idleness and overuse. Through the multi-dimensional comprehensive analysis of task features, resource status, and environmental factors, the system can dynamically adjust tasks and resources according to real-time data. This adjustment method greatly enhances the flexibility and adaptability of production scheduling. Especially in the face of emergencies such as equipment failures or changes in personnel status, it can respond quickly, reducing waiting time and resource waste in production. By introducing a dynamic production process model, task scheduling not only depends on static rules, but can be adjusted in real time to adapt to changes in the production environment, ensuring the smooth operation of the production process.

[0014] Through the multi-dimensional task feature definition and task priority calculation method, multi-dimensional features such as task difficulty, resource requirements, urgency, and environmental adaptability are taken into consideration, ensuring the accurate calculation of the comprehensive priority of tasks. In traditional task scheduling methods, the calculation of task priority often relies on single features or static rules and cannot dynamically reflect the changes in actual task execution. This multi-dimensional analysis can consider the complexity of tasks, the actual requirements of resources, the timeliness of tasks, and the adaptability of the production environment, ensuring that the priority calculation results are more in line with actual production needs. In the dynamic adjustment of priorities, the priority adjustment formula realizes the flexible and dynamic adjustment of task priorities through the feedback time difference and the sensitivity factor. By introducing the feedback time difference, the priority of tasks can be automatically adjusted according to the information that changes in real time during task execution, thus solving the limitation of traditional task allocation methods that cannot respond to changes in the production environment in a timely manner. For example, factors such as equipment failures, changes in employee status, and fluctuations in the production environment can be fed back to the calculation of task priorities in real time, ensuring that changes in production requirements can be responded to in a timely manner during task allocation, minimizing production delays and resource waste to the greatest extent. By assigning different weights to each feature, the relative impact of task difficulty, resource requirements, urgency, and environmental adaptability on the priority is clarified in the task priority calculation. This weighted calculation method can effectively avoid the influence of a single dimension and reduce the deviation in task scheduling. For example, when a task requires high-difficulty operations and equipment or personnel are in short supply, the improvement of the priority will give priority to the availability of resources to ensure that high-priority tasks can obtain appropriate resource support. This optimization method ensures that tasks can be reasonably scheduled under the constraints of resources and the environment, avoiding resource conflicts and over-concentration of resources that exist in traditional methods. By introducing an intelligent task allocation strategy and combining the dynamic priority of tasks and resource requirements, the optimal allocation of tasks in the production workshop can be effectively achieved. This strategy solves the problems of low efficiency and lack of flexibility in traditional task allocation methods, especially in the face of a dynamic production environment, and can automatically adjust the task priority and allocation strategy. During the production process, it can not only respond to situations such as equipment failures and changes in employee status in a timely manner, but also optimize resource allocation according to real-time production data, thus greatly improving production efficiency and flexibility. The environmental adaptability factor in the task priority calculation can effectively consider changes in the production environment. This strategy of considering the adaptability of the production environment avoids the problem that traditional scheduling methods ignore the impact of the production environment on task execution. The impact of environmental changes on task execution is fully reflected, ensuring the adaptability of equipment and personnel in the production process, thus reducing the negative impact of environmental changes on production efficiency and resource waste.

[0015] Through the task difficulty feature, the difficulty of a task is not only based on intuitive perception, but is comprehensively evaluated by combining the number of task operation steps and the estimated execution time with an empirical weight coefficient. This method solves the problem of inaccurate task difficulty assessment in traditional task allocation, ensuring that the actual complexity of the task can be more precisely considered during task allocation. The accuracy of task difficulty improves the matching degree of resources and avoids the situation of unreasonable resource allocation. For example, tasks with higher complexity will not be assigned to employees with insufficient skills or resources, avoiding inefficient execution. In the analysis of task resource requirement features, the requirements of different resources for a task are dynamically evaluated and optimized in combination with the resource allocation model. This evaluation method solves the defect of ignoring the diversity of resource requirements in traditional methods, can effectively identify the types of resources required for a task, and make precise allocation according to the actual situation. For instance, when a task requires specific equipment or employees with specific skills, the system will adjust according to the actual resource situation to ensure that the task can receive appropriate support and improve production efficiency. By introducing the task urgency feature, the urgency of a task is evaluated by the deadline and the current time, and this evaluation is incorporated into the calculation of task priority. This method avoids the phenomenon of ignoring task time limits in traditional scheduling, ensuring that urgent tasks can be processed first. The urgency of a task is not only based on the requirements of the task itself, but can also dynamically adjust the task priority, thus avoiding bottlenecks and lags on the production line, reducing the delay time of tasks, and improving the timeliness of task completion. In the analysis of task environment adaptation features, the comparison between the temperature and humidity conditions of the production environment where the task is located and the optimal environment for the task can accurately evaluate the impact of the production environment on task execution. By establishing an adaptation model between tasks and the environment through historical data, tasks can be executed under optimal environmental conditions, thereby improving the execution efficiency and quality of tasks. This solves the problem of ignoring the impact of environmental factors in traditional task allocation methods, ensuring that environmental changes can be incorporated into the decision-making process of task allocation in real time, and reducing the inefficiency and errors of task execution caused by environmental factor changes. By comprehensively considering multiple dimensional features such as task difficulty, resource requirements, urgency, and environment adaptability, the system can conduct a more comprehensive and accurate analysis during task allocation. This multi-dimensional analysis not only ensures the rationality of task allocation, but also, by dynamically adjusting priorities, ensures that it can efficiently and quickly respond to changes in the production process in a complex production environment, optimize resource allocation, and improve the overall production efficiency of the production workshop.

[0016] By obtaining the task with the highest priority and allocating resources to it, the system can ensure that the most urgent and important tasks in the production process are prioritized. This strategy addresses the issues of unclear priorities or unreasonable task sequencing in traditional task scheduling, avoids delays in high-priority tasks, and ensures that the production schedule matches the customer delivery requirements. The dynamic adjustment of task priorities and resource allocation guarantee the efficiency and real-time nature of task scheduling, especially in high-load or emergency situations where it can quickly respond and adjust task priorities. In the resource matching degree calculation, the estimated completion time of the task, the availability of equipment, and the working status of employees are combined to ensure that tasks can receive the most appropriate resource support. Through the matching degree calculation between tasks and resources, the system can accurately select resources based on the actual resource status and task requirements, avoiding waste and shortage of resources. This method solves the problem of inaccurate resource allocation in traditional scheduling and avoids low task execution efficiency caused by equipment failures or employee overload, thus ensuring the smooth completion of tasks. After each task allocation, the system updates the resource status. This real-time update mechanism can dynamically reflect the usage status of resources, such as the availability of equipment and the working status of employees. This mechanism solves the problem of static management of resource status in traditional task allocation and ensures that resources in the production process always maintain the latest available status. When a resource is allocated, the system automatically updates the status of that resource, avoiding duplicate allocation of occupied resources or ignoring resource idle situations, and optimizing the utilization rate of production resources. By dynamically scheduling the entire production process and obtaining real-time feedback, the system can monitor changes in the production process in real time and adjust the task allocation strategy promptly. This mechanism can solve the problems of lagging feedback and inability to adapt to unexpected events in traditional production scheduling. When equipment failures, personnel idleness, or production line changes occur, the system can quickly obtain feedback and adjust task allocation to ensure that the production process is not interrupted by unforeseen changes, enhancing the flexibility and continuity of production.

[0017] Through dynamic adjustment strategies, the system can monitor the execution status of tasks in real time and make timely adjustments to tasks. When problems occur during task execution, such as equipment failures or employee overload, the system can automatically calculate the difference between the actual execution time and the expected execution time of the task based on real-time feedback, thereby determining whether to adjust the task priority or reallocate resources. Specifically, if the task delay exceeds the set threshold, the system will make up for the delay by adjusting the task priority or reallocating resources, avoiding task backlogs or delays in important tasks during the production process. This process solves the problem of task execution delays in traditional production scheduling due to equipment failures, excessive personnel loads, or production interruptions, improving the flexibility and response speed of production scheduling. By setting a dynamic scheduling objective function that takes into account factors such as downtime, equipment utilization, and task completion efficiency, the optimal task allocation in the production process is ensured. By assigning different weight coefficients to each factor, the system can dynamically adjust the scheduling strategy according to the current production status, making task allocation more flexible and adaptable. This objective function solves the problem in traditional scheduling that downtime, equipment load, and production efficiency cannot be accurately quantified, thus optimizing the utilization of resources, reducing the time of downtime and inefficient operations during the production process, and enhancing the overall production efficiency. Through real-time feedback adjustment, the system can continuously obtain real-time data during task execution and adjust the task execution plan in a timely manner according to the feedback. This mechanism avoids the drawback of inflexible adjustment after task allocation in traditional methods. Especially in the case of sudden situations such as equipment failures and excessive personnel loads, it can quickly respond and reallocate tasks and resources. This not only optimizes the resource utilization in the production process but also reduces the negative impact of factors such as equipment failures and excessive personnel loads on the production progress, ensuring that tasks are completed on time and reducing unplanned downtime in production. In personalized task allocation, the system makes personalized task allocations based on the difficulty score of the task, the task priority, and the working status of employees and equipment. Through comprehensive analysis of the capabilities, loads, and status of employees and equipment, the system ensures that each task is assigned to the most suitable resource, thereby reducing production delays caused by resource mismatches. This strategy improves the collaborative work efficiency of employees and equipment, ensuring the rational use of resources and the smooth progress of production tasks.

[0018] In the equipment status constraint, the system automatically monitors the failure rate of equipment by setting a threshold for the equipment failure probability. When the failure rate of the equipment exceeds the threshold, the equipment will be marked as unavailable, thus preventing the equipment from being assigned tasks continuously. This constraint solves the risk in traditional production scheduling that tasks are still assigned to equipment after equipment failures occur due to the neglect of equipment status, and avoids situations such as production line downtime, inefficiency or even inability to complete tasks caused by equipment failures. By reasonably restricting the assignment of equipment, the reliability of task assignment and the safety of equipment use can be improved during the production process, and the impact of faulty equipment on the production plan can be reduced. In the personnel ability constraint, task assignment only considers the skill level of employees and the skill requirements of tasks. If the skills of an employee do not meet the task requirements, the task will not be assigned to this employee. This constraint effectively solves the problem of mismatch between personnel skills and task requirements in traditional scheduling, ensures that each task can be assigned to the most suitable employee, and thus improves the quality and efficiency of task completion. In this way, the use of personnel resources can be optimized, and task delays or quality problems caused by skill mismatches can be avoided. In the production load constraint, the current working load of equipment cannot exceed its maximum working capacity. This constraint prevents the performance degradation or failure of equipment due to overload by monitoring the load of equipment in real time. At the same time, it also avoids production bottlenecks and resource waste caused by excessive equipment load, ensures that the load of equipment is within a reasonable range, and effectively extends the long-term service life of equipment. Through the setting of the real-time feedback mechanism and response time, it is ensured that the equipment can be ready to execute tasks at an appropriate time after task assignment. The feedback mechanism can dynamically monitor the status of equipment and adjust task assignment according to the difficulty of tasks, the load and status of equipment, thus avoiding overloaded equipment and resource waste. If the working load of the equipment approaches the maximum value, the system will reassign tasks according to the equipment load situation, making the load of the equipment tend to be balanced and reaching the maximum working capacity. This adjustment strategy solves the problems of uneven load, overloading of equipment or resource waste that may occur in production scheduling, maximizes the utilization efficiency of equipment and personnel resources, and improves the overall efficiency and response ability of production.

[0019] In the task-employee-equipment matching model, the system can ensure that each task is assigned to the most suitable combination of employees and equipment by calculating the comprehensive matching degree of tasks with employees and equipment. Through the matching degree calculation formula, the system comprehensively considers factors such as task complexity, employee skill level, employee workload, equipment load, and the cooperation efficiency between employees and equipment. This personalized task assignment strategy solves the problem of unreasonable resource allocation in traditional production scheduling, avoids the situation where unmatched employees and equipment undertake tasks, and thus improves production efficiency and the quality of task completion. In terms of the matching degree between task complexity and employee skills, by calculating the matching degree between task complexity and employee skill level, the system ensures that employees with higher skill levels can handle tasks with greater complexity. It avoids the assignment of complex tasks to employees with insufficient skill levels, reduces the error rate and time delay during task execution. This strategy effectively solves the problem of unstable task execution quality and ensures that high-difficulty tasks can be completed in a timely and accurate manner. In terms of the matching degree between task priority and employee workload, the system matches the priority of tasks with the workload of employees, avoiding the over-assignment of tasks to employees with heavy workloads, thereby reducing the risk of employee fatigue and declining work quality. This strategy optimizes task scheduling, ensures that high-priority tasks can be processed in a timely manner without delay due to excessive workload. The workload of employees is reasonably controlled, thus enhancing the overall production efficiency. In terms of the matching degree between tasks and equipment load, the system comprehensively considers the total capacity of the equipment, the current load, and the requirements of the task for the equipment, ensuring that the load status of the equipment and the time requirements of the task are taken into account when assigning tasks. If the load of the equipment is close to the maximum value, the system will select equipment with a lower load to assign tasks, avoiding overloading the equipment. This strategy effectively improves equipment utilization, avoids the situation of equipment idleness or overload, increases production efficiency, and extends the service life of the equipment. In terms of the cooperation efficiency between employees and equipment, the system preferentially selects combinations with a good cooperation record between employees and equipment based on the historical cooperation efficiency between employees and equipment. This strategy ensures more efficient cooperation between employees and equipment, reduces the time waste caused by poor adaptability and unskilled operation. This not only improves the execution efficiency of individual tasks but also promotes the optimization of the entire production process. By comprehensively considering multiple factors such as task complexity, employee skills, workload, equipment load, and the cooperation efficiency between employees and equipment, the system can select the best combination of employees and equipment for each task, maximizing the utilization rate of resources. The resource update mechanism after task assignment ensures real-time feedback and adjustment of resource status, avoids the situation of resource idleness or overuse, and thus realizes the optimal allocation of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0021] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0022] Embodiment, an intelligent task allocation method for a production workshop based on big data, including: Obtain device status data denoted as Rdev, personnel status data denoted as Rpers, task status data denoted as Ttask, and production environment data denoted as Eenv; The device status data specifically includes: Ridev is the current status of device i, and the available status of device i is denoted as 1, and the failure status is denoted as 0; Uidev is the utilization rate of device i, and the utilization rate of device i is represented by 0-1, where 0 means not in use, 1 means full-load operation, and the rest means normal operation; Tidev is the remaining service life of device i, in hours; The personnel status data specifically includes: Sjpers is the working status of employee j, and the status when employee j is working is denoted as 1, and the idle status is denoted as 0; Wjpers is the skill level of employee j, and the skill level of employee j is represented by 0-1, where 0 means incapable, 1 means the highest ability, and Hjpers is the current workload of employee j, represented by the number of tasks; The task status data specifically includes: Dktask is the difficulty score of task k, and the difficulty of task k is scored using 0-1, where 0 means very simple and 1 means very complex; Pktask is the priority of task k, and the priority of task k is represented by 0-1, where 0 means low priority and 1 means high priority; Tktask is the estimated completion time of task k, in hours; The production environment data specifically includes: Tenv is the temperature in the production workshop; Henv is the humidity in the production workshop; Use a dynamic production process model to represent the state of the production system: ; Among them, P(t) is the production process state at time t; Ti is the characteristic of task i; Rj is the state of resource j, including device status and personnel status; Ek is the environmental characteristic; Ui is the utilization rate of device i; Among them, the f() function is specifically: ; Among them, f1(Ti) is the task feature function, which describes the influence of the features of task k on the production process. Specifically: , Dktask is the difficulty score of task k, and Pktask is the priority score of task k; f2(Rj) is the resource status function, which describes the influence of the status of equipment and personnel on the production process. Specifically: , Rkdev is the status of equipment k, and Skpers is the working status of employee k; f3(Ek) is the environmental status function, which describes the influence of the temperature and humidity of the production environment on the production process. Specifically: , Tenv is the temperature in the production workshop, and Henv is the humidity in the production workshop; f4(Ui) is the equipment utilization rate function, which describes the influence of the current utilization rate of equipment on the production process. Specifically: , Uidev is the utilization rate of equipment i; Among them, α1, α2, α3, and α4 are the relative influence weight coefficients of each factor on the production process, satisfying ; β1 and β2 are the task feature weight coefficients; g1 and g2 are the resource status weight coefficients; d1 and d2 are the environmental status weight coefficients; l1 is the weight coefficient of the equipment utilization rate; Perform multi-dimensional task feature analysis and task priority calculation.

[0023] Through the task feature function, the difficulty score and priority of the task are associated with the task features, and combined with the resource status function to accurately analyze the status of equipment and personnel, which can help the system dynamically evaluate the matching of task priorities and resources. Specifically, the priority of the task and the status of the resources, such as the idle status of the equipment, the skill level and workload of the employees, etc., jointly determine the task allocation. It solves the problem in the prior art that the task priority cannot accurately consider the resource status, improves the efficiency and accuracy of task scheduling, ensures that high-priority tasks can be quickly allocated to appropriate resources for execution, and reduces production delays. In the resource status function, the real-time status of equipment and personnel is comprehensively considered, such as the availability and utilization rate of the equipment, the working status and workload of the employees, to achieve an efficient match between equipment and personnel. Through this analysis, the system can dynamically adjust the use of resources, avoiding the problem of reduced production efficiency caused by overloading of equipment or personnel in the prior art. When equipment fails or an employee's workload is too large, the system will automatically select resources with better status to ensure the continuity and efficiency of production. In the environmental status function, the impact of environmental data such as temperature and humidity in the production workshop on the production process is considered. This solves the problem that traditional task scheduling methods ignore production environment factors. The change of environmental temperature and humidity directly affects the work efficiency of equipment and personnel. Real-time monitoring of these data and incorporating them into task allocation decisions enables the production process to be adjusted in real time according to environmental conditions, thereby improving the operation stability of equipment and the work comfort of personnel. Through the equipment utilization rate function, the utilization rate of the equipment is incorporated into the task allocation decision, and tasks can be reasonably allocated according to the current use status of the equipment. This step solves the problem of overuse or idleness of equipment resources, optimizes the operation load of the equipment, and thus improves the overall production efficiency. During the production process, the equipment utilization rate no longer depends on a single rule, but is dynamically adjusted according to real-time data, avoiding the double waste of equipment idle and overuse. Combining the multi-dimensional comprehensive analysis of task features, resource status and environmental factors, the system can dynamically adjust tasks and resources according to real-time data. This adjustment method greatly enhances the flexibility and adaptability of production scheduling. Especially in the face of emergencies such as equipment failures or changes in personnel status, it can respond quickly, reducing waiting time and resource waste in production. By introducing a dynamic production process model, task scheduling not only depends on static rules, but can be adjusted in real time to adapt to changes in the production environment, ensuring the smooth operation of the production process.

[0024] Refer to Figure 1 , the multi-dimensional task feature analysis and task priority calculation specifically include: S1. Definition of multi-dimensional task features; S2. Task priority calculation method; Assign different weights to each feature; Record the comprehensive priority of each task as Pktask: ; Among them, α3, α4, α5, and α6 are the weight coefficients of the features, representing the relative importance of task difficulty, resource requirements, urgency, and environmental adaptability in the calculation of the total priority, and satisfy ; S3, priority dynamic adjustment; The priority dynamic adjustment formula is: ; Among them, Pktask,adj is the priority of task k after dynamic adjustment; DTkfeedback is the feedback time difference, specifically the time difference from the last priority adjustment of task k to the present; β3 is the sensitivity factor for priority adjustment, used to control the amplitude of priority dynamic adjustment; Use an intelligent task allocation strategy to allocate tasks.

[0025] Through the multi-dimensional task feature definition and task priority calculation method, multi-dimensional features such as task difficulty, resource requirements, urgency, and environmental adaptability are taken into account, ensuring the accurate calculation of the comprehensive priority of tasks. In traditional task scheduling methods, the calculation of task priority often relies on a single feature or static rules and cannot dynamically reflect the changes in actual task execution. This multi-dimensional analysis can consider the complexity of tasks, the actual resource requirements, the timeliness of tasks, and the adaptability of the production environment, ensuring that the priority calculation results are more in line with actual production needs. In the dynamic adjustment of priorities, the priority adjustment formula realizes the flexible and dynamic adjustment of task priorities through the feedback time difference and the sensitivity factor. By introducing the feedback time difference, the priority of tasks can be automatically adjusted according to the real-time changing information during task execution, thus solving the limitation of traditional task allocation methods that cannot respond to changes in the production environment in a timely manner. For example, factors such as equipment failures, changes in employee status, and fluctuations in the production environment can be fed back to the calculation of task priorities in real time, ensuring that changes in production requirements can be responded to in a timely manner during task allocation, minimizing production delays and resource waste. By assigning different weights to each feature, the relative impacts of task difficulty, resource requirements, urgency, and environmental adaptability on the priority are clarified in the task priority calculation. This weighted calculation method can effectively avoid the influence of a single dimension and reduce the deviation in task scheduling. For example, when a task requires high-difficulty operations and equipment or personnel are in short supply, the improvement of the priority will give priority to the availability of resources to ensure that high-priority tasks can obtain appropriate resource support. This optimization method ensures that tasks can be reasonably scheduled under the constraints of resources and the environment, avoiding resource conflicts and over-concentration of resources in traditional methods. By introducing an intelligent task allocation strategy and combining the dynamic priority of tasks with resource requirements, the optimal allocation of tasks in the production workshop can be effectively achieved. This strategy solves the problems of low efficiency and lack of flexibility in traditional task allocation methods, especially in the face of a dynamic production environment, and can automatically adjust the task priority and allocation strategy. During the production process, it can not only respond to situations such as equipment failures and changes in employee status in a timely manner, but also optimize resource allocation according to real-time production data, thus greatly improving production efficiency and flexibility. The environmental adaptability factor in task priority calculation can effectively consider changes in the production environment. This strategy of considering production environment adaptability avoids the problem that traditional scheduling methods ignore the impact of the production environment on task execution. The impact of environmental changes on task execution is fully reflected, ensuring the adaptability of equipment and personnel in the production process, thereby reducing the negative impact of environmental changes on production efficiency and resource waste.

[0026] The above-mentioned multi-dimensional task feature definition specifically includes: S11. Task difficulty characteristic Dktask: The difficulty score of task k, which is evaluated based on the complexity of the task, the number of required operation steps, and the execution time, and is derived through historical data and task models: ; Among them, Nksteps is the number of operation steps of task k; Tkduration is the estimated execution time of task k, in hours; α1 and α2 are empirical weight coefficients, reflecting the impact of the number of steps and time on task difficulty. S12. Task resource requirement characteristic Rktask: The resource requirements of task k, which are obtained through data analysis and resource allocation models: ; Among them, Rktask,i is the requirement of task k for resource i, including equipment, personnel, and environmental conditions; Nresources is the number of types of resources required for task k. S13. Task urgency characteristic Ektask: The urgency of the task is evaluated based on the delivery time of the task and the project deadline. The higher the urgency of the task, the higher its priority: ; Among them, Tkdue is the deadline of task k; Tcurrent is the current time. S14. Task environment adaptation characteristic Aktask: The impact of the environmental temperature and humidity where the task is located on task execution. Changes in environmental conditions will affect the execution efficiency of the task, so it needs to be evaluated: ; Among them, Tkenv is the impact of the current environmental temperature and humidity on task k, and Toptimal is the optimal environmental temperature and humidity for task k, which is obtained through historical data.

[0027] Through the task difficulty feature, the difficulty of a task is not only based on intuitive perception, but is comprehensively evaluated by combining the number of task operation steps and the estimated execution time with an empirical weight coefficient. This method solves the problem of inaccurate task difficulty evaluation in traditional task allocation, ensuring that the actual complexity of the task can be more precisely considered when allocating tasks. The accuracy of task difficulty improves the matching degree of resources and avoids the situation of unreasonable resource allocation. For example, tasks with higher complexity will not be assigned to employees with insufficient skills or resources, avoiding inefficient execution. In the analysis of task resource requirement features, the requirements of tasks for different resources are dynamically evaluated and optimized in combination with the resource allocation model. This evaluation method solves the defect of ignoring the diversity of resource requirements in traditional methods, can effectively identify the types of resources required for tasks, and make precise allocations according to the actual situation. For instance, when a task requires specific equipment or employees with specific skills, the system will adjust according to the actual resource situation to ensure that the task can receive appropriate support and improve production efficiency. By introducing the task urgency feature, the urgency of a task is evaluated by the deadline and the current time, and this evaluation is incorporated into the calculation of task priority. This method avoids the phenomenon of ignoring task time limits in traditional scheduling, ensuring that urgent tasks can be processed first. The urgency of a task is not only based on the requirements of the task itself, but also can dynamically adjust the task priority, thus avoiding bottlenecks and lags on the production line, reducing the delay time of tasks, and improving the timeliness of task completion. In the analysis of task environment adaptation features, the comparison between the temperature and humidity conditions of the production environment where the task is located and the optimal environment for the task can accurately evaluate the impact of the production environment on task execution. By establishing an adaptation model between tasks and the environment through historical data, tasks can be executed under optimal environmental conditions, thereby improving the execution efficiency and quality of tasks. This solves the problem of ignoring the impact of environmental factors in traditional task allocation methods, ensuring that environmental changes can be incorporated into the decision-making process of task allocation in real time, and reducing the low execution efficiency and errors caused by environmental factor changes. By comprehensively considering multiple dimensional features such as task difficulty, resource requirements, urgency, and environment adaptability, the system can conduct a more comprehensive and accurate analysis when allocating tasks. This multi-dimensional analysis not only ensures the rationality of task allocation, but also, through dynamically adjusting priorities, ensures that it can efficiently and quickly respond to changes in the production process in a complex production environment, optimizes the allocation of resources, and improves the overall production efficiency of the production workshop.

[0028] The intelligent task allocation strategy specifically includes: Obtain the task with the highest priority and allocate resources to it. The matching degree calculation formula is: ; Among them, Tktask is the estimated completion time of task k, with the unit of hour; Rjdev is the availability of device j. The availability of the device is represented by 0 - 1, where 0 means the device is unavailable and 1 means the device is fully available; Sjpers is the working status of employee j. For each task, select the resource with the maximum matching degree M(tk, Rj) for allocation and update the resource status Rj. Conduct dynamic scheduling for the entire production process and obtain real-time feedback.

[0029] By obtaining the task with the highest priority and allocating resources to it, the system can ensure that the most urgent and important tasks in the production process are processed first. This strategy solves the problems of unclear priorities or unreasonable task sorting in traditional task scheduling, avoids delays in high-priority tasks, and ensures the matching of the production schedule with customer delivery requirements. The dynamic adjustment of task priorities and resource allocation ensures the efficiency and real-time nature of task scheduling, especially being able to quickly respond and adjust task priorities in high-load or emergency situations. In the calculation of resource matching degree, the estimated completion time of the task, the availability of the device, and the working status of the employee are combined to ensure that the task can obtain the most suitable resource support. Through the calculation of the matching degree between tasks and resources, the system can accurately select resources according to the actual resource status and task requirements, avoiding waste and shortage of resources. This method solves the problem of inaccurate resource allocation in traditional scheduling and avoids the low task execution efficiency caused by equipment failures or employee overloading, thus ensuring the smooth completion of tasks. After each task allocation, the system updates the resource status. This real-time update mechanism can dynamically reflect the usage status of resources, such as the availability of devices and the working status of employees. This mechanism solves the problem of static management of resource status in traditional task allocation and ensures that resources in the production process always maintain the latest available status. When a certain resource is allocated, the system automatically updates the status of this resource, avoiding the repeated allocation of occupied resources or ignoring the idle situation of resources, and optimizing the utilization rate of production resources. By conducting dynamic scheduling for the entire production process and obtaining real-time feedback, the system can monitor the changes in the production process in real time and adjust the task allocation strategy in a timely manner. This mechanism can solve the problems of lagging feedback and inability to adapt to emergencies in traditional production scheduling. When equipment failures, personnel idleness, or production line changes occur, the system can quickly obtain feedback and adjust task allocation to ensure that the production process will not be interrupted due to unforeseen changes, improving the flexibility and continuity of production.

[0030] The dynamic scheduling for the entire production process and obtaining real-time feedback specifically includes: S4. Dynamic adjustment strategy; When problems occur during task execution, such as equipment failures or personnel overloading, the task allocation is adjusted through real-time monitoring data feedback. The feedback function is as follows: ; where Tkreal is the actual execution time of task k, in hours; Tkexpected is the expected execution time of task k, in hours; When Fkexpected > 1, it indicates that the task is delayed, and the system will adjust the task priority or reallocate resources; S5. Scheduling adjustment: S51. Set the dynamic scheduling adjustment objective function, specifically: ; where Tdowntime is the downtime in the current production process, in hours; Udev is the current utilization rate of the equipment; Eefficiency is the task completion efficiency score, with the score ranging from 0 to 1, where 0 represents the lowest efficiency and 1 represents the highest efficiency; l1, l2, and l3 are the weight coefficients for each item, used to control the relative importance of the objectives, satisfying ; S52. Constraints for scheduling adjustment; Adjust the priority of the task. The adjustment function is: ; where Pktask(t) is the priority of task k at time t; Pktask(t - 1) is the priority of task k at the previous time; α5 is the weight coefficient for priority adjustment; Tiresponse is the response time of task k on equipment i; Dktask is the difficulty score of task k; Perform personalized task allocation for employees and equipment.

[0031] Through a dynamic adjustment strategy, the system can monitor the execution status of tasks in real time and make timely adjustments to tasks. When problems occur during task execution, such as equipment failures or employee overload, the system can automatically calculate the difference between the actual execution time and the expected execution time of the task based on real-time feedback, so as to determine whether it is necessary to adjust the task priority or reallocate resources. Specifically, if the task delay exceeds the set threshold, the system will make up for the delay by adjusting the task priority or reallocating resources, avoiding task backlog or delay of important tasks in the production process. This process solves the problem of task execution delay caused by equipment failures, overloaded personnel or production interruptions in traditional production scheduling, and improves the flexibility and response speed of production scheduling. By setting a dynamic scheduling objective function, factors such as downtime, equipment utilization rate and task completion efficiency are considered to ensure the optimal task allocation in the production process. By assigning different weight coefficients to each factor, the system can dynamically adjust the scheduling strategy according to the current production status, making the task allocation more flexible and adaptable. This objective function solves the problem in traditional scheduling that downtime, equipment load and production efficiency cannot be accurately quantified, thereby optimizing the utilization of resources, reducing the time of downtime and inefficient operations in the production process, and improving the overall production efficiency. Through real-time feedback adjustment, the system can continuously obtain real-time data during task execution and adjust the task execution plan in a timely manner according to the feedback. This mechanism avoids the drawback of inflexible adjustment after task allocation in traditional methods. Especially in the case of sudden situations such as equipment failures and overloaded personnel, it can quickly respond and reallocate tasks and resources. This not only optimizes the utilization of resources in the production process, but also reduces the negative impact of factors such as equipment failures and overloaded personnel on the production progress, ensuring that tasks are completed on time and reducing unplanned downtime in production. In personalized task allocation, the system makes personalized task allocation based on the difficulty score of the task, the task priority, and the working status of employees and equipment. By comprehensively analyzing the capabilities, loads and status of employees and equipment, the system ensures that each task is assigned to the most suitable resources, thereby reducing production delays caused by resource mismatches. This strategy improves the collaborative work efficiency of employees and equipment, ensuring the reasonable utilization of resources and the smooth progress of production tasks.

[0032] The constraint conditions for the said scheduling adjustment specifically include: S521. Equipment status constraint; Set a failure probability threshold Pthresh; For each equipment i, if the failure probability Pifault of equipment i exceeds Pthresh, then this equipment cannot be allocated anymore; ; Among them, Pifault is the failure rate of device i; Pthresh is the failure probability threshold. If the failure probability of a device is higher than this value, the device cannot continue to work. S522. Personnel ability constraint; The skill level Wjpers of employee j must meet the skill requirement Wktask of task k: ; Among them, Wjpers is the skill level of employee j; Wktask is the skill requirement of task k. S523. Production compliance constraint; The load of each device i at a certain moment cannot exceed its maximum working capacity Cidev, that is, the current load Lidev of the device must satisfy: ; Among them, Lidev is the current working load of device i; Cidev is the maximum working load of device i. S524. Scheduling adjustment strategy; After each task assignment, the operating status of devices and personnel is monitored in real time through a feedback mechanism, the task assignment and production order are adjusted, and the response time of tasks and devices is set, that is, the time when the device is ready to execute the task after the task is assigned: ; Among them, Tbase is the basic response time of the device in the idle state, obtained through historical production data; Lidev and Cidev are the current load and maximum load of device i respectively; Dktask is the difficulty score of task k; Ridev is the status of device i, represented by 1 for available and 0 for faulty; β1 is the influence factor of task difficulty on the response time; β2 is the influence factor of device status on the response time, indicating the increase amplitude of the response time when the device is unavailable. If the working load of the device is close to the maximum value after the task is assigned, part of the task is reassigned to a device i' with a smaller load, so that the working load Lidev of each device is close to the maximum load Cidev, thereby improving resource utilization rate. The adjustment formula is: ; Among them, Lidev is the working load of the current device i; Li'dev is the working load of device i' after the new task assignment; DL is the task load of the reassignment.

[0033] In equipment status constraints, the system automatically monitors the failure rate of equipment by setting a threshold for the equipment failure probability. When the failure rate of the equipment exceeds the threshold, the equipment will be marked as unavailable, thus preventing the equipment from continuing to be assigned tasks. This constraint solves the risk in traditional production scheduling that tasks are still assigned to equipment after equipment failures due to the neglect of equipment status, and avoids situations such as production line downtime, inefficiency, or even failure to complete tasks due to equipment failures. By reasonably restricting the allocation of equipment, the reliability of task allocation and the safety of equipment use can be improved during the production process, and the impact of faulty equipment on the production plan can be reduced. In personnel ability constraints, task allocation only considers the skill level of employees and the skill requirements of tasks. If an employee's skills do not meet the task requirements, the task will not be assigned to that employee. This constraint effectively solves the problem of mismatch between personnel skills and task requirements in traditional scheduling, ensures that each task can be assigned to the most suitable employee, and thus improves the quality and efficiency of task completion. In this way, the use of human resources can be optimized, and task delays or quality problems caused by skill mismatches can be avoided. In production load constraints, the current working load of equipment cannot exceed its maximum working capacity. This constraint prevents the performance degradation or failure of equipment due to overload by monitoring the load of equipment in real time. At the same time, it also avoids production bottlenecks and resource waste caused by excessive equipment load, ensures that the load of equipment is within a reasonable range, and effectively extends the long-term service life of equipment. Through the setting of a real-time feedback mechanism and response time, it is ensured that the equipment can be ready to execute tasks at the appropriate time after task allocation. The feedback mechanism can dynamically monitor the status of equipment and adjust task allocation according to the difficulty of tasks, the load and status of equipment, so as to avoid overloaded equipment and resource waste. If the working load of equipment is close to the maximum value, the system will reallocate tasks according to the equipment load situation, making the load of equipment tend to be balanced and reaching the maximum working capacity. This adjustment strategy solves the problems of uneven load, overloading of equipment, or resource waste that may occur in production scheduling, maximizes the utilization efficiency of equipment and human resources, and improves the overall efficiency and response ability of production.

[0034] The personalized task allocation for employees specifically includes: The task-employee-equipment matching degree model is: ; Among them, Si(tk,ej) is the matching degree of task tk on given employee ej and equipment ei; f1(tk,ej) is the matching degree between the complexity of task tk and the skills of employee ej, specifically: , is the complexity of task tk, is the skill level of employee ej; f2(tk, ej) represents the matching degree between the priority of task tk and the workload of employee ej, specifically as follows: , is the priority of task tk, is the current workload of employee ej, such as the assigned task volume and completion status; f3(tk, ej, ei) represents the matching degree between the requirements of task tk for device ei and the current load of the device, specifically as follows: , is the total capacity of device ei, is the current load of device ei, is the time requirement of task tk, such as the task needs to be completed within a specific time period; f4(ej, ei) represents the cooperation efficiency between employee ej and device ei, considering the adaptability of the employee's work experience and the device, and is expressed as the historical efficiency of the employee using a specific device, specifically as follows: , The historical efficiency of employee ej using device ei, is the average efficiency of employee ej working on all devices; α1, α2, α3, and α4 are weight coefficients used to control the relative importance of each factor; For each task tk, calculate the matching degree Si(tk, ej) of all employee and device combinations; For task tk, select the employee ej and device ei with the highest matching degree, specifically as follows: ; Assign task tk to the selected employee and device , and update the load status of the employee and the device.

[0035] In the task-employee-equipment matching degree model, by calculating the comprehensive matching degree of tasks with employees and equipment, the system can ensure that each task is assigned to the most suitable combination of employees and equipment. Through the matching degree calculation formula, the system comprehensively considers factors such as task complexity, employee skill level, employee workload, equipment load, and the cooperation efficiency between employees and equipment. This personalized task assignment strategy solves the problem of unreasonable resource allocation in traditional production scheduling, avoids the situation where unmatched employees and equipment undertake tasks, and thus improves production efficiency and the quality of task completion. In terms of the matching degree between task complexity and employee skills, by calculating the matching degree between task complexity and employee skill level, the system ensures that employees with higher skill levels can handle tasks with greater complexity. It avoids the assignment of complex tasks to employees with insufficient skill levels, reduces the error rate and time delay during task execution. This strategy effectively solves the problem of unstable task execution quality and ensures that high-difficulty tasks can be completed in a timely and accurate manner. In terms of the matching degree between task priority and employee workload, the system matches the priority of tasks with the workload of employees, avoiding the over-allocation of tasks to employees with heavy workloads, thereby reducing the risk of employee fatigue and declining work quality. This strategy optimizes task scheduling, ensures that high-priority tasks can be processed in a timely manner without delays due to excessive workload. The workload of employees is reasonably controlled, thus improving the overall production efficiency. In terms of the matching degree between tasks and equipment load, the system comprehensively considers the total capacity of the equipment, the current load, and the requirements of the task for the equipment, ensuring that when tasks are assigned, the load status of the equipment and the time requirements of the tasks are taken into account. If the load of the equipment is close to the maximum value, the system will select equipment with a lower load to assign tasks, avoiding overloading of the equipment. This strategy effectively improves equipment utilization, avoids the situation of equipment idleness or overload, improves production efficiency, and extends the service life of the equipment. In terms of the cooperation efficiency between employees and equipment, the system preferentially selects combinations with good cooperation records between employees and equipment based on the historical cooperation efficiency between employees and equipment. This strategy ensures more efficient cooperation between employees and equipment, reduces time waste caused by poor adaptability and unskilled operation. This not only improves the execution efficiency of individual tasks but also promotes the optimization of the entire production process. By comprehensively considering multiple factors such as task complexity, employee skills, workload, equipment load, and the cooperation efficiency between employees and equipment, the system can select the best combination of employees and equipment for each task, maximizing the utilization rate of resources. The resource update mechanism after task assignment ensures real-time feedback and adjustment of resource status, avoids the situation of resource idleness or overuse, and thus realizes the optimal allocation of resources.

[0036] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0037] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for intelligently allocating tasks in a production workshop based on big data, characterized in that: include: The acquired equipment status data is recorded as Rdev, the personnel status data is recorded as Rpers, the task status data is recorded as Ttask and the production environment data is recorded as Eenv; The device status data specifically includes: Ridev is the current status of device i, where the available status of device i is recorded as 1 and the fault status is recorded as 0; Uidev is the utilization rate of device i, where the utilization rate of device i is represented by 0-1, where 0 represents unused, 1 represents full load operation, and the rest represents normal operation; Tidev is the remaining service life of device i, in hours; The personnel status data specifically includes: Sjpers is the working status of employee j, where the status of employee j is recorded as 1 when working and 0 when idle; Wjpers is the skill level of employee j, where the skill level of employee j is represented by 0-1, where 0 represents no ability and 1 represents the highest ability; Hjpers is the current workload of employee j, represented by the number of tasks; The task status data specifically includes: Dktask is the difficulty score of task k, and the difficulty of task k is scored using 0-1, where 0 represents very simple and 1 represents very complex; Pktask is the priority of task k, and the priority of task k is represented using 0-1, where 0 represents low priority and 1 represents high priority; Tktask is the estimated completion time of task k, in hours; The production environment data specifically include: Tenv is the temperature in the production workshop; Henv is the humidity in the production workshop; Use a dynamic production process model to represent the state of the production system: ； Among them, P(t) is the state of the production process at time t; Ti is the characteristics of task i; Rj is the state of resource j, including equipment status and personnel status; Ek is the environmental characteristics; Ui is the utilization rate of equipment i; The f() function is as follows: ； Among them, f1(Ti) is the task characteristic function, specifically: , Dktask is the difficulty score of task k, and Pktask is the priority score of task k; f2(Rj) is the resource state function, specifically: , Rkdev is the status of device k, Skpers is the working status of employee k; f3(Ek) is the environmental state function, specifically: , Tenv is the temperature in the production workshop, Hev is the humidity in the production workshop; f4(Ui) is the equipment utilization function, specifically: , Uidev is the utilization rate of device i; Among them, α1, α2, α3 and α4 are the relative influence weight coefficients of each factor on the production process, satisfying ; β1 and β2 are task feature weight coefficients; g1 and g2 are resource status weight coefficients; d1 and d2 are environment status weight coefficients; l1 is the equipment utilization weight coefficient; Conduct multi-dimensional task feature analysis and task priority calculation.

2. According to the method of intelligent allocation of production workshop tasks based on big data in claim 1, it is characterized in that: The multi-dimensional task feature analysis and task priority calculation specifically include: S1, multi-dimensional task feature definition; S2, task priority calculation method; Assign different weights to each feature; The combined priority of each task is recorded as Pktask: ； Among them, α3, α4, α5 and α6 are the weight coefficients of the features, which represent the relative importance of task difficulty, resource demand, urgency and environmental adaptability in the total priority calculation, satisfying ; S3, dynamic adjustment of priority; The priority dynamic adjustment formula is: ； Among them, Pktask,adj is the priority of task k after dynamic adjustment; DTkfeedback is the feedback time difference, specifically the time difference between the last priority adjustment of task k and now; β3 is the sensitivity factor of priority adjustment, which is used to control the amplitude of dynamic adjustment of priority; Assign tasks using intelligent task assignment strategies.

3. The method for intelligently allocating tasks in a production workshop based on big data according to claim 2 is characterized in that: The multi-dimensional task feature definition specifically includes: S11. Task difficulty feature Dktask: The difficulty score of task k is evaluated based on the complexity of the task, the number of required operation steps and the execution time, and is derived from historical data and task models: ； Among them, Nksteps is the number of operation steps of task k; Tkduration is the expected execution time of task k, in hours; α1 and α2 are empirical weight coefficients, reflecting the impact of the number of steps and time on task difficulty; S12, Task resource demand characteristics Rktask: The resource demand of task k, obtained through data analysis and resource allocation model: ； Among them, Rktask,i is the demand of task k for resource i, including equipment, personnel and environmental conditions; Nresources is the number of resource types required by task k; S13. Task urgency feature Ektask: The urgency of the task is evaluated based on the task delivery time and the project deadline: ； Among them, Tkdue is the deadline of task k; Tcurrent is the current time; S14, Task environment adaptation feature Aktask: The impact of the ambient temperature and humidity of the task on task execution: ； Among them, Tkenv is the impact of the current ambient temperature and humidity on task k, and Toptimal is the optimal ambient temperature and humidity of task k, which is obtained through historical data.

4. The method for intelligently allocating tasks in a production workshop based on big data according to claim 3 is characterized in that: The intelligent task allocation strategy specifically includes: Get the task with the highest priority and allocate resources to it. The matching degree calculation formula is: ； Where, Tktask is the estimated completion time of task k, in hours; Rjdev is the availability of device j, which is represented by 0-1, where 0 means the device is unavailable and 1 means the device is fully available; Sjpers is the working status of employee j; For each task, select the resource with the largest matching degree M(tk,Rj) for allocation and update the resource status Rj; Dynamically schedule the entire production process and obtain real-time feedback.

5. The method for intelligently allocating tasks in a production workshop based on big data according to claim 4 is characterized in that: The dynamic scheduling of the entire production process and obtaining real-time feedback specifically includes: S4, dynamic adjustment strategy; When problems occur during task execution, task allocation is adjusted through real-time monitoring data feedback. The feedback function is: ； Where, Tkreal is the actual execution time of task k, in hours; Tkexpected is the expected execution time of task k, in hours; When Fkexpected>1, the system will adjust the task priority or reallocate resources; S5. Scheduling adjustment: S51, setting the dynamic scheduling adjustment objective function, specifically: ； Among them, Tdowntime is the downtime in the current production process, in hours; Udev is the current utilization rate of the equipment; Eefficiency is the task completion efficiency score, which is expressed in 0-1, 0 represents the lowest efficiency, and 1 represents the highest efficiency; l1, l2 and l3 are the weight coefficients of each item, which are used to control the relative importance of the target and meet the requirements. ; S52, constraints for scheduling adjustment; Adjust the priority of the task, the adjustment function is: ； Where Pktask(t) is the priority of task k at time t; Pktask(t-1) is the priority of task k at the previous moment; α5 is the weight coefficient of priority adjustment; Tiresponse is the response time of task k on device i; Dktask is the difficulty score of task k; Personalize task assignments for employees and equipment.

6. The method for intelligently allocating tasks in a production workshop based on big data according to claim 5 is characterized in that: The constraints of the scheduling adjustment specifically include: S521, device status constraint; Set the fault probability threshold Pthresh; For each device i, if the failure probability Pifault of device i exceeds Pthresh, the device can no longer be allocated; ； Where Pifault is the failure rate of device i; Pthresh is the failure probability threshold. If the failure probability of a device is higher than this value, the device cannot continue to work. S522, personnel capacity constraints; The skill level Wjpers of employee j must meet the skill requirement Wktask of task k: ； Where Wjpers is the skill level of employee j; Wktask is the skill requirement of task k; S523, production complies with constraints; The load of each device i at a certain moment cannot exceed its maximum working capacity Cidev, that is, the current load Lidev of the device must satisfy: ； Where Lidev is the current workload of device i; Cidev is the maximum workload of device i; S524, scheduling adjustment strategy; After each task is assigned, the feedback mechanism is used to monitor the operating status of equipment and personnel in real time, adjust the task assignment and production sequence, and set the response time of tasks and equipment: ； Among them, Tbase is the basic response time of the device in idle state, which is obtained through historical production data; Lidev and Cidev are the current load and maximum load of device i respectively; Dktask is the difficulty score of task k; Ridev is the status of device i, with 1 indicating availability and 0 indicating failure; β1 is the impact factor of task difficulty on response time; β2 is the impact factor of device status on response time; If the workload of the device is close to the maximum after task allocation, some tasks will be reallocated to the device i' with a smaller load, so that the workload Lidev of each device is close to the maximum load Cidev. The adjustment formula is: ； Where Lidev is the current workload of device i; Li'dev is the workload of device i' after the new task is assigned; DL is the reallocated task load.

7. The method for intelligently allocating tasks in a production workshop based on big data according to claim 6 is characterized in that: The personalized task allocation to employees specifically includes: The matching model between tasks, employees and equipment is: ； Among them, Si(tk,ej) is the matching degree of task tk on the given employee ej and equipment ei; f1(tk,ej) is the matching degree between the complexity of task tk and the skills of employee ej, specifically: , is the complexity of task tk, The skill level of the employee ej; f2(tk,ej) is the matching degree between the priority of task tk and the workload of employee ej, specifically: , is the priority of task tk, Current workload for employee ej; f3(tk,ej,ei) is the matching degree between the requirement of task tk for device ei and the current load of the device, specifically: , is the total capability of the device ei, is the current load of the device ei, The time requirement for task tk; f4(ej,ei) is the collaboration efficiency between employee ej and equipment ei, specifically: , The historical efficiency of employee ej using equipment ei, Average efficiency of employees working on all devices; α1, α2, α3, and α4 are weight coefficients used to control the relative importance of each factor; For each task tk, calculate the matching degree Si(tk,ej) of all combinations of employees and equipment; For task tk, select the employee ej and equipment ei with the highest matching degree, specifically: ； Assign task tk to the selected employee and equipment , and update the load status of employees and equipment.

Images