Task allocation methods and electronic devices

Abstract

This application proposes a task allocation method and electronic device. The task allocation method includes: acquiring production data from a vehicle manufacturing system; constructing a task feature vector for a calibration task in the vehicle manufacturing system based on the production data; determining a capability matrix corresponding to each workstation based on workstation data corresponding to multiple workstations in the vehicle manufacturing system; determining a fit score between the calibration task and each workstation based on the task feature vector and the capability matrix of each workstation; determining a priority score for each workstation to execute the calibration task based on the task urgency of the calibration task, the fit score between the calibration task and each workstation, and the load index of each workstation; determining a target workstation among the multiple workstations based on the priority score, and allocating the calibration task to the target workstation. This application can improve the accuracy of vehicle task allocation.

Description

Technical Field

[0001] This application belongs to the field of vehicle manufacturing, and relates to the field of task allocation technology, and in particular to a task allocation method and electronic device. Background Technology

[0002] With the increasing demand for motor vehicles, automated production lines are now commonly used in vehicle manufacturing to improve production efficiency. Currently, automated production lines typically employ static scheduling strategies to allocate tasks within the vehicle manufacturing process. For example, tasks are usually managed using a first-come, first-served queue system or ordered according to pre-set priority rules. However, this approach cannot adjust task allocation strategies in real time based on changes in production plans, fluctuations in equipment status, and complex dependencies between tasks. It lacks the ability to dynamically respond to and make detailed decisions regarding changes in the manufacturing system's operating conditions, leading to uneven workloads between workstations, low equipment resource utilization, and consequently, low vehicle manufacturing efficiency. Summary of the Invention

[0003] In view of the above, it is necessary to propose a task allocation method and electronic equipment to solve the technical problem of low efficiency in vehicle production.

[0004] This application provides a task allocation method, the method comprising: constructing a task feature vector for a calibration task; the task feature vector including at least the sensor type of the vehicle, the vehicle model complexity, the estimated calibration time of the calibration task, and the dependency identifier of the calibration task; determining a capability matrix corresponding to each workstation based on workstation data corresponding to multiple workstations; the capability matrix corresponding to any workstation including at least an equipment configuration vector and the performance history record of the workstation, the equipment configuration vector indicating the sensor type, equipment model, and software version corresponding to the workstation, and the performance history record indicating the calibration success rate and average time consumption for different sensor types and vehicle models corresponding to the workstation; determining a fit score between the calibration task and each workstation based on the task feature vector and the capability matrix of each workstation; determining a priority score for each workstation to execute the calibration task based on the task urgency of the calibration task, the fit score between the calibration task and each workstation, and the load index of each workstation; determining a target workstation among the multiple workstations based on the priority score, and allocating the calibration task to the target workstation.

[0005] In some embodiments, determining the priority score for each workstation to execute the calibration task based on the task urgency of the calibration task, the fit score between the calibration task and each workstation, and the load index of each workstation includes: determining the task urgency based on the vehicle delivery time, the system time of the vehicle manufacturing system, the task fault identifier, and the task dependency indicated by the dependency relationship identifier; determining the load index of any workstation based on the estimated calibration time of the calibration task, the equipment configuration vector of any workstation, the fit score, and the performance history of any workstation; determining the fit coefficient between the calibration task and any workstation based on the type of the calibration task; determining the urgency amplification coefficient of the calibration task based on the task urgency of all tasks in the vehicle manufacturing system; and determining the priority score based on the ratio between the task urgency and the load index, and the product of the fit coefficient and the urgency amplification coefficient.

[0006] In some embodiments, determining the task urgency based on the vehicle delivery time, the vehicle manufacturing system time, the task fault identifier, and the task dependency indicated by the dependency identifier includes: determining the time difference between the delivery time and the system time; determining the fault priority of the calibrated task based on the task fault identifier; and performing a weighted summation of the time difference, the fault priority, and the task dependency to obtain the task urgency.

[0007] In some embodiments, determining the load index of an arbitrary workstation based on the estimated calibration time of the calibration task, the device configuration vector of any workstation, the fit score, and the performance history of the arbitrary workstation includes: determining a first ratio of the sum of the estimated times of all tasks corresponding to the arbitrary workstation to the maximum working time indicated by the device configuration vector; performing nonlinear mapping processing on the fit score to obtain a fit mapping value; determining the variance of the time taken for the arbitrary workstation to execute tasks within a preset period based on the performance history; and performing a weighted summation of the first ratio, the fit mapping value, and the variance to obtain the load index.

[0008] In some embodiments, determining the fit coefficient between the calibration task and any one workstation based on the type of the calibration task includes: determining the success rate of the arbitrary workstation in handling other tasks of the same type as the calibration task based on the type of the calibration task; normalizing the success rate based on the average success rate of all workstations in the vehicle manufacturing system to obtain a normalized success rate; and determining the fit coefficient based on the sum of the normalized success rate and a preset constant.

[0009] In some embodiments, determining the urgency amplification factor of the calibration task based on the urgency of all tasks in the vehicle manufacturing system includes: determining an average urgency based on the urgency of all tasks; determining a maximum urgency and a minimum urgency from the urgency of all tasks; normalizing the urgency of the calibration task based on the difference between the average urgency, the maximum urgency, and the minimum urgency to obtain a normalized urgency; and determining the urgency amplification factor based on the sum of the normalized urgency and a preset constant.

[0010] In some embodiments, the method further includes: after determining the task urgency and the load index of any workstation, weighting the task urgency based on the task acceleration factor of the calibration task to obtain an updated task urgency; the task acceleration factor indicates the degree of influence of the scheduling time of the calibration task on the task urgency; weighting the load index based on the penalty term of the calibration task to obtain an updated load index; the penalty term indicates the degree of influence of the fit between the calibration task and the any workstation on the load index.

[0011] In some embodiments, the method for determining the task acceleration factor includes: determining the average scheduling time of all tasks in the vehicle manufacturing system; determining a second ratio of the scheduling time of the calibrated task to the average; determining a first difference between the second ratio and a preset first threshold; and determining the minimum value between the first difference and the preset second threshold as the task acceleration factor.

[0012] In some embodiments, the method for determining the penalty item includes: when the task requirements of the calibration task and the workstation capability of any workstation meet preset conditions, determining a second difference between the fit score and a preset third threshold; determining the maximum value between the second difference and a preset fourth threshold as the penalty item; when the task requirements of the calibration task and the workstation capability of any workstation do not meet preset conditions, determining the fourth threshold as the penalty item; the preset conditions include: the requirement accuracy indicated by the task requirement is higher than the equipment accuracy indicated by the workstation capability; or, the software version indicated by the task requirement does not match the software version indicated by the workstation capability.

[0013] This application also provides an electronic device, which includes: a memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the task allocation method.

[0014] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the task allocation method described above.

[0015] As can be seen from the above technical solutions, the embodiments of this application use task urgency as the core positive factor of the priority score, directly related to the remaining delivery time of the task. This can solve the problems of queuing for urgent tasks and resource occupation by non-urgent tasks caused by the first-come, first-served mechanism in traditional task allocation strategies, ensuring the on-time rate of key nodes in vehicle production and reducing compensation costs and capacity losses caused by task delays. By using index quantification and weighted calculation, scheduling decisions are transformed into automatically executable numerical calculations, enabling real-time dynamic scheduling of calibrated tasks, adapting to the flexible production needs of vehicle manufacturing systems, and improving the response efficiency of vehicle production processes. Using workstation suitability as the core positive factor of the priority score can avoid resource mismatch between workstations and tasks, improving the utilization rate of manufacturing resources. Using the workstation load index as a negative factor of the priority score can achieve global balance of the load of each workstation, improve the overall capacity of the production line, and reduce operation and maintenance costs. Furthermore, the priority score is composed of a weighted average of three dimensions: task urgency, suitability score, and load index, rather than a single indicator. This enhances the resilience of task allocation decisions, avoids production line fluctuations caused by local data anomalies, and further improves the efficiency of vehicle production and manufacturing. Attached Figure Description

[0016] Figure 1 This is an application scenario diagram of a task allocation method provided in an embodiment of this application.

[0017] Figure 2 This is a flowchart of a task allocation method provided in an embodiment of this application.

[0018] Figure 3 This is a flowchart of a method for determining the priority score of each workstation according to an embodiment of this application.

[0019] Figure 4 This is a flowchart of a method for determining the urgency of a task according to an embodiment of this application.

[0020] Figure 5 This is a flowchart of a method for determining the load index of any workstation according to an embodiment of this application.

[0021] Figure 6 This is a flowchart of a method for determining the fit coefficient of any workstation according to an embodiment of this application.

[0022] Figure 7 This is a flowchart of a method for determining the urgency amplification factor of a calibration task according to an embodiment of this application.

[0023] Figure 8 This is a flowchart of a method for updating task urgency and load index provided in an embodiment of this application.

[0024] Figure 9 This is a flowchart of a method for determining a task acceleration factor provided in an embodiment of this application.

[0025] Figure 10 This is a flowchart of a method for determining penalty items provided in an embodiment of this application.

[0026] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0027] To better understand the purpose, features, and advantages of this application, a detailed description of the application is provided below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of this application can be combined with each other. Numerous specific details are set forth in the following description to provide a thorough understanding of this application; the described embodiments are only a part of the embodiments of this application, and not all of them.

[0028] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0030] This application provides a task allocation method that can be applied to one or more electronic devices. An electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0031] Electronic devices can be any electronic product that allows human-computer interaction with a customer, such as personal computers, tablets, smartphones, personal digital assistants (PDAs), game consoles, interactive network television (IPTV), smart wearable devices, etc.

[0032] Electronic devices may also include network devices and / or client devices. The network devices include, but are not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0033] The networks in which electronic devices are located include, but are not limited to, the Internet, wide area networks, metropolitan area networks, local area networks, and virtual private networks (VPNs).

[0034] like Figure 1 The diagram illustrates an application scenario of a task allocation method provided in an embodiment of this application. This task allocation method can be applied to an electronic device 100. The electronic device 100 can be a central processing unit in a vehicle manufacturing system 200. The electronic device 100 is used to acquire production data from the vehicle manufacturing system 200 and allocate tasks from the vehicle manufacturing system 200 to multiple workstations based on the production data.

[0035] The vehicle manufacturing system 200 includes multiple workstations, and the electronic equipment 100 is communicatively connected to these workstations. For example, the multiple workstations may include... Figure 1 Workstations 210, 220, 230, and 240 are shown. It is understood that the vehicle manufacturing system 200 of this application may contain fewer or more workstations, and this application does not limit the specific number of workstations.

[0036] Each workstation corresponds to a production device in the vehicle manufacturing system 200. For example, workstation 210 may correspond to a workstation for assembling vehicle sensors, workstation 220 may correspond to a workstation for manufacturing vehicle drive shafts, and workstation 230 may correspond to a workstation for assembling vehicle gearboxes.

[0037] In this application, the electronic device 100 stores pre-acquired production data. This production data includes information such as the delivery time of the vehicles to be manufactured by the vehicle manufacturing system 200 and task fault identifiers. To improve the production efficiency of the vehicle manufacturing system 200, the electronic device 100 constructs a task feature vector for a calibration task in the vehicle manufacturing system 200 and a capability matrix corresponding to multiple workstations based on the production data. The calibration task can be any vehicle manufacturing task to be evaluated in the vehicle manufacturing system 200. The task feature vector indicates the attributes of the calibration task, and the capability matrix indicates the working conditions of the workstations and their ability to handle the task.

[0038] To improve the accuracy of matching workstations with calibration tasks, the electronic device 100 determines the fit score between the calibration task and each workstation based on the task feature vector and the capability matrix of each workstation. Furthermore, it determines the priority score for each workstation to execute the calibration task based on the task urgency, the fit score between the calibration task and each workstation, and the load index of each workstation. Finally, multiple workstations are sorted in descending order of priority score to identify the target workstation and assign the calibration task to it. This multi-dimensional data-driven approach to prioritizing workstation task processing enhances the resilience of task allocation decisions, avoids production line fluctuations caused by localized data anomalies, and further improves the efficiency of vehicle manufacturing.

[0039] like Figure 2 The diagram shown is a flowchart of a task allocation method according to an embodiment of this application. The order of the steps in the flowchart can be changed, and some steps can be omitted, depending on different requirements. The task allocation method provided in this embodiment includes the following steps.

[0040] S20, acquire production data from the vehicle manufacturing system, including vehicle delivery time and task fault identifier.

[0041] In one embodiment of this application, multiple workstations in a vehicle manufacturing system perform different manufacturing tasks to complete the assembly and production of vehicles. The production data of the vehicle manufacturing system may include the planned production start time of the vehicles, the delivery time of the vehicles, task fault indicators, planned output per unit time, and planned process duration, etc. Production data can characterize the rationality of the production scheduling of the vehicle manufacturing system, and can indicate the degree of matching between planned output and actual capacity per unit time, order delivery priority strategies, production line load rate, etc.

[0042] Production data also includes production execution data. Specifically, production execution data can be a real-time record of the production process, characterizing the efficiency of the manufacturing system's workflow and the level of schedule control.

[0043] For example, production execution data may include process execution data, which may include any one or more of the following: process number, process name, actual start and finish time of each process, process processing time, work-in-process quantity, and process flow batches. This data can reflect the production efficiency of each process, such as the processing time per machine in a welding process; it can also reflect the smoothness of the connection between processes, such as the backlog of work-in-process reflecting bottleneck processes; and it can also reflect production schedule deviations, such as the difference between the actual completion time and the planned completion time.

[0044] For example, production execution data may include production cycle time data, which may include any one or a combination of several of the following: actual production cycle time, bottleneck process cycle time, production line downtime / number of downtimes, and changeover time. This data can reflect the overall operating efficiency of the production line; for example, the closer the actual cycle time is to the design cycle time, the higher the efficiency. It can also reflect capacity constraints; for example, the cycle time of the bottleneck process determines the maximum capacity of the entire line. Furthermore, it can reflect flexible production capabilities; for example, the shorter the changeover time, the more flexible the model switching.

[0045] Production data also includes process quality data, which is the core guarantee of product qualification and characterizes the process stability and quality control capabilities of the manufacturing system.

[0046] For example, process quality data may include process parameter data, which may include any one or more of the following: welding current / voltage, coating film thickness, final assembly torque, stamping die pressure, and coating baking temperature / duration. This data can reflect the standardization of process execution, such as whether parameters are within preset tolerances; it can also reflect the rationality of the process plan, such as whether the film thickness meets corrosion protection requirements; and it can reflect product consistency, for example, the smaller the parameter fluctuation, the higher the consistency.

[0047] For example, process quality data can also include quality inspection data. Specifically, it can include any one or more of the following: quality inspection process name, inspection items, inspection results, defect type, defect level, and rework / repair records. This data can characterize the product's pass rate; reflect the defect distribution across processes; reflect the severity of quality problems; and reflect rework costs, for example, rework costs can be characterized based on rework duration and material loss.

[0048] Production data also includes equipment resource data. Specifically, equipment resource data can refer to the hardware support for production activities, characterizing the health status and maintenance level of the equipment in the manufacturing system.

[0049] For example, equipment resource data can be equipment operation data, including any one or more of the following: equipment number, equipment type, equipment runtime, equipment uptime, equipment load rate, and equipment fault code / fault type. This data can reflect equipment utilization efficiency, equipment load status, and equipment types with high failure rates.

[0050] For example, equipment operation and maintenance data may also include any one or more of the following: equipment maintenance plans / execution records, maintenance duration, fault repair duration, spare parts replacement records, mean time between failures (MTBF), and mean time to repair (MTBT). This data can characterize the timeliness of equipment maintenance, the response efficiency of the operation and maintenance team, equipment reliability, and the rationality of spare parts inventory.

[0051] S21, Based on the production data, construct a task feature vector for the calibration task in the vehicle manufacturing system; the task feature vector includes at least the vehicle's sensor type, the vehicle's model complexity, the estimated calibration time of the calibration task, and the dependency identifier of the calibration task.

[0052] In one embodiment of this application, a task feature vector corresponding to any calibration task can be constructed based on the production data. The task feature vector includes data from multiple dimensions, specifically, the multiple dimensions include at least one or more combinations of sensor type encoding, vehicle model complexity coefficient, estimated calibration time, task dependency identifier, and equipment calibration status.

[0053] The sensor type code is used to identify the type of sensor that the calibration task needs to process. For example, the sensor type code can be the code corresponding to LiDAR, the code corresponding to a camera, or the code corresponding to millimeter-wave radar.

[0054] The vehicle model complexity coefficient is used to characterize the complexity of the vehicle to be produced. For example, the vehicle model complexity coefficient can be calculated based on the vehicle platform and the number of sensor configurations.

[0055] The estimated calibration time is used to indicate the time required to process a calibration task based on historical production records. For example, when a calibration task instructs the processing of a vehicle's sensors, the estimated calibration time can be dynamically predicted based on the sensor type and historical calibration data.

[0056] The task dependency identifier is used to indicate the relationship between the calibration task and other tasks in the vehicle manufacturing system, and can characterize whether the calibration task is a prerequisite task for other tasks. For example, when the task dependency identifier is 1, it can indicate that the calibration task is a prerequisite task for other tasks; when the task dependency identifier is 0, it can indicate that the calibration task is not a prerequisite task for other tasks.

[0057] The equipment calibration status indicates whether the workstation or equipment required for the calibration task is within the valid calibration period. For example, if the equipment calibration status is "not calibrated," it means that the workstation or equipment required for the calibration task is not within the valid calibration period; if the equipment calibration status is "calibrated," it means that the workstation or equipment required for the calibration task is within the valid calibration period.

[0058] S22, based on the workstation data corresponding to each of the multiple workstations in the vehicle manufacturing system, determine the capability matrix corresponding to each workstation; the capability matrix corresponding to any workstation includes at least an equipment configuration vector and the performance history record of the workstation, the equipment configuration vector indicating the sensor type, equipment model and software version corresponding to the workstation, and the performance history record indicating the calibration success rate and average time consumption of different sensor types and vehicle models corresponding to the workstation.

[0059] In one embodiment of this application, a capability matrix for each workstation can be constructed based on workstation data from multiple workstations in a vehicle manufacturing system. The capability matrix for any given workstation includes at least an equipment configuration vector and the performance history record of that workstation. The capability matrix may also include real-time status monitoring data, operator skill levels, etc.

[0060] The device configuration vector indicates the sensor type, device model, and software version supported by the workstation. For example, when the device configuration vector is [1, 001, v123], if the sensor type code corresponding to the LiDAR sensor is 1, it can be determined that the device configuration vector indicates that the sensor type supported by the workstation is LiDAR, the device model supported by the workstation is 001, and the software version supported by the workstation is v123.

[0061] The performance history record stores the historical calibration success rate and average time taken for different sensor types and vehicle models at each workstation. For example, the performance history record could be [Sensor 1: 98%, 120 minutes; Sensor 2: 99%, 100 minutes; Vehicle Model 1: 97%, 200 minutes; Vehicle Model 2: 96%, 180 minutes]. In this case, the historical calibration success rate for Sensor 1 is 98%, and the average time taken to calibrate Sensor 1 is 120 minutes; the historical calibration success rate for Sensor 2 is 99%, and the average time taken to calibrate Sensor 2 is 100 minutes.

[0062] The real-time status monitoring data can include the task queues of all current tasks in the vehicle manufacturing system, the health status index of all equipment in the vehicle manufacturing system, and the temperature and humidity data of the environment in which all equipment is located.

[0063] Among them, the operator skill level is used to indicate the proficiency of the operator at each workstation in the vehicle manufacturing system in handling different types of tasks.

[0064] S23, Based on the task feature vector and the capability matrix of each workstation, determine the fit score between the calibrated task and each workstation.

[0065] In one embodiment of this application, a fit score can be calculated between each task and each workstation. The fit score characterizes the degree of matching between the task feature vector and the workstation's capability matrix, and further characterizes the degree of fit for using the workstation to perform the calibration task.

[0066] The fit score between the calibrated task and each workstation can be determined based on the dot product of the task feature vector and the capability matrix of each workstation. Specifically, the fit score is calculated according to the following formula: ; in, The fit score represents the ratio between the calibration task with index i and the workstation with index j. The feature vector representing the calibration task with index i contains information such as the sensor type and vehicle complexity that the calibration task with index i needs to process. The capability matrix represents the workstation with index j, and includes information on dimensions such as equipment configuration and historical success rate. The fit score can quantitatively measure the execution quality and efficiency of workstation-based calibration tasks. Based on the fit score, high-precision calibration tasks can be avoided from being assigned to workstations that do not have the necessary equipment / skills, thus reducing rework rates and process adjustment costs.

[0067] Specifically, the dot product of the task feature vector and the capability matrix indicates the product of the magnitude and the angle between the task feature vector and the capability matrix. The smaller the angle between the task feature vector and the capability matrix, the higher the directional consistency between the task feature vector and the capability matrix, and the higher the degree of matching.

[0068] Since the matching degree between the task feature vector and the capability matrix is ​​based on the similarity of their directions rather than their magnitudes, the task feature vector and capability matrix can be normalized before calculating the fitness score to obtain normalized task feature vectors and normalized capability matrices.

[0069] Since the normalized task feature vector and the normalized capability matrix have the same dimensions, the magnitude of the dot product between the normalized task feature vector and the normalized capability matrix is ​​equivalent to the degree of matching between the calibrated task and the workstation.

[0070] For example, the closer the dot product between the normalized task feature vector and the normalized capability matrix is ​​to 1, the smaller the angle between them, the higher the directional consistency, and the higher the matching degree. The closer the dot product is to 0, the more orthogonal the directions of the normalized task feature vector and the normalized capability matrix are, and the lower the matching degree. The closer the dot product value is to -1, the more opposite the directions are, and the negative matching degree is.

[0071] S24. Based on the task urgency of the calibration task, the compatibility score between the calibration task and each workstation, and the load index of each workstation, determine the priority score for each workstation to execute the calibration task.

[0072] In one embodiment of this application, in a vehicle manufacturing system, the priority score for a workstation to execute a calibrated task is determined based on task urgency, workstation suitability, and workstation load index. This enables an intelligent scheduling decision-making process for calibrated tasks, which can achieve priority handling of urgent tasks, efficient execution of adapted workstations, and load balancing to avoid congestion.

[0073] Specifically, the priority score of each calibrated task relative to each workstation can be calculated based on the compatibility score between the calibrated task and any workstation, the urgency of the calibrated task, and the load status of any workstation.

[0074] Among them, task urgency is the core priority premise for allocating and scheduling designated tasks. It can avoid non-urgent tasks occupying resources and urgent tasks queuing up, and can avoid delays in vehicle production nodes.

[0075] When determining the urgency of a calibration task, factors with a high degree of influence on the urgency can be identified from production data. Specifically, factors directly related to the constraints of on-time delivery of the calibration task can be selected from production data. For example, the remaining time for task delivery, the failure status of the workstation corresponding to the calibration task, and information on other tasks related to the calibration task can be identified as factors influencing the urgency of the task.

[0076] To eliminate the dimensional differences between different influencing factors and thus improve the accuracy of task urgency, the different influencing factors can be standardized. For example, the values ​​of each influencing factor can be mapped to the interval [0, 1] to eliminate dimensional differences.

[0077] For example, the way the remaining time for task delivery is annotated satisfies the following relationship: ; in, Representative task Vehicle delivery timestamp; Represents the timestamp of the current vehicle manufacturing system; max represents the function to retrieve the maximum value.

[0078] For example, when there is a fault at the workstation corresponding to the calibration task, the fault identifier can be set to 1; when there is no fault at the workstation corresponding to the calibration task, the fault identifier can be set to 0.

[0079] For example, the dependency of a calibration task can be determined based on the task dependency graph data corresponding to all tasks in the vehicle manufacturing system. The dependency of a calibration task indicates the relationship between the calibration task and other tasks. For instance, if there are 10 tasks in a production manufacturing facility, and two of these tasks have calibration tasks as their prerequisites, then 2 / 10 = 0.2 can be determined as the task dependency of the calibration task.

[0080] In one embodiment of this application, the load status of any workstation is the core indicator for achieving workstation load balancing, which can avoid concentrating tasks on high-load workstations, prevent production line bottlenecks, and improve overall scheduling efficiency.

[0081] When determining the load status of any workstation, state influence factors affecting the load status of the workstation can be identified from production data. For example, state influence factors may include any one or more combinations of estimated calibration time and maximum operating time indicated by the equipment configuration vector, fit score, and workstation equipment health.

[0082] Among them, the load index of any workstation can be calculated based on the above-mentioned state influence factors, thereby characterizing the load status of the workstation based on the quantitative data of the load index.

[0083] Specifically, a first ratio can be determined between the estimated calibration time and the maximum working time indicated by the equipment configuration vector. A non-linear mapping process is applied to the fit score to obtain the fit mapping value. Based on historical performance records, the variance of the time taken for any workstation to execute tasks within a preset period is determined; a weighted sum of the first ratio, the fit mapping value, and the variance is then obtained to obtain the load index.

[0084] In one embodiment of this application, the priority score for each workstation to execute the calibrated task can be determined based on the task urgency of the calibrated task, the compatibility score between the calibrated task and each workstation, and the load index of each workstation. The priority score is the final quantitative basis for scheduling decisions; by linearly weighting, multiple dimensions of indicators are integrated into a single value, facilitating automatic task sorting and allocation by the system.

[0085] Specifically, when determining the priority score for any workstation executing a calibration task, the direct proportionality between the task's urgency and priority score can be established, ensuring a positive contribution of urgency to the priority score. Furthermore, the direct proportionality between the fit score between the calibration task and any workstation and the priority score can be established, ensuring a positive contribution of fit score to priority score. Finally, the inverse proportionality between the load index of any workstation and the priority score can be established, ensuring a negative contribution of load index to priority score. Thus, the higher the task urgency, the lower the workstation load index, and the higher the fit score between the calibration task and the workstation, the higher the priority for that workstation to execute the calibration task.

[0086] In one embodiment of this application, the specific method for determining the priority score of each workstation performing the calibration task is described in the following article. Figures 3 to 10 The corresponding detailed explanation.

[0087] S25, based on the priority score, determine the target workstation among the plurality of workstations, and assign the calibrated task to the target workstation.

[0088] In one embodiment of this application, the workstations corresponding to the calibrated tasks can be sorted in descending order of priority scores, and the effectiveness of each workstation is verified sequentially based on preset constraints. When the effectiveness of a workstation meets the constraints and its priority score is the highest, it indicates that the workstation can handle the calibrated tasks and that its efficiency in handling the calibrated tasks is high; therefore, this workstation can be determined as the target workstation. Sorting and verification are the practical steps from theoretical priority to actual executability, avoiding scheduling failures caused by ignoring production constraints and ensuring the engineering practicality of the decision.

[0089] Specifically, constraints may include any one or a combination of the following: whether the workstation is idle; whether the equipment is available during the execution time of the calibrated task.

[0090] In one embodiment of this application, the execution instruction corresponding to the calibration task can be transmitted to the manufacturing equipment corresponding to the target workstation, enabling the equipment at that workstation to process the calibration task. The load index of the workstation is also updated in real time, thereby achieving dynamic scheduling of the vehicle manufacturing system.

[0091] As can be seen from the above technical solutions, the embodiments of this application use task urgency as the core positive factor of the priority score, directly related to the remaining delivery time of the task. This can solve the problems of queuing for urgent tasks and resource occupation by non-urgent tasks caused by the first-come, first-served mechanism in traditional task allocation strategies, ensuring the on-time rate of key nodes in vehicle production and reducing compensation costs and capacity losses caused by task delays. By using index quantification and weighted calculation, scheduling decisions are transformed into automatically executable numerical calculations, enabling real-time dynamic scheduling of calibrated tasks, adapting to the flexible production needs of vehicle manufacturing systems, and improving the response efficiency of vehicle production processes. Using workstation suitability as the core positive factor of the priority score can avoid resource mismatch between workstations and tasks, improving the utilization rate of manufacturing resources. Using the workstation load index as a negative factor of the priority score can achieve global balance of the load of each workstation, improve the overall capacity of the production line, and reduce operation and maintenance costs. Furthermore, the priority score is composed of a weighted average of three dimensions: task urgency, suitability score, and load index, rather than a single indicator. This enhances the resilience of task allocation decisions, avoids production line fluctuations caused by local data anomalies, and further improves the efficiency of vehicle production and manufacturing.

[0092] like Figure 3 The diagram shows a flowchart of a method for determining the priority score of each workstation according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining the priority score of each workstation according to an embodiment of this application includes the following steps.

[0093] S30, the task urgency is determined based on the vehicle delivery time, the vehicle manufacturing system system time, the task fault identifier, and the task dependency indicated by the dependency identifier.

[0094] In one embodiment of this application, task urgency is the core priority prerequisite for allocating and scheduling calibrated tasks. It can avoid the situation where non-urgent tasks occupy resources and urgent tasks are queued, and can avoid the problem of delays in vehicle production nodes.

[0095] When determining the urgency of a calibration task, factors with a high degree of influence on the urgency can be identified from production data. Specifically, factors directly related to the constraints of on-time delivery of the calibration task can be selected from production data. For example, the remaining time for task delivery, the failure status of the workstation corresponding to the calibration task, and information on other tasks related to the calibration task can be identified as factors influencing the urgency of the task.

[0096] To eliminate the dimensional differences between different influencing factors and thus improve the accuracy of task urgency, the different influencing factors can be standardized. For example, the values ​​of each influencing factor can be mapped to the interval [0, 1] to eliminate dimensional differences.

[0097] For example, the way the remaining time for task delivery is annotated satisfies the following relationship: ; in, Representative task Vehicle delivery timestamp; Represents the timestamp of the current vehicle manufacturing system; max represents the function to retrieve the maximum value.

[0098] For example, when there is a fault at the workstation corresponding to the calibration task, the fault identifier can be set to 1; when there is no fault at the workstation corresponding to the calibration task, the fault identifier can be set to 0.

[0099] For example, the dependency of a calibration task can be determined based on the task dependency graph data corresponding to all tasks in the vehicle manufacturing system. The dependency of a calibration task indicates the relationship between the calibration task and other tasks. For instance, if there are 10 tasks in a production manufacturing facility, and two of these tasks have calibration tasks as their prerequisites, then 2 / 10 = 0.2 can be determined as the task dependency of the calibration task.

[0100] For a specific method of determining task urgency in one embodiment of this application, please refer to [link to relevant documentation]. Figure 4 The corresponding detailed explanation.

[0101] S31. Based on the estimated calibration time of the calibration task, the equipment configuration vector of any workstation, the adaptability score, and the performance history of any workstation, determine the load index of any workstation.

[0102] In one embodiment of this application, the load status of any workstation is the core indicator for achieving workstation load balancing, which can avoid concentrating tasks on high-load workstations, prevent production line bottlenecks, and improve overall scheduling efficiency.

[0103] When determining the load status of any workstation, state influence factors affecting the load status of the workstation can be identified from production data. For example, state influence factors may include any one or more combinations of estimated calibration time and maximum operating time indicated by the equipment configuration vector, fit score, and workstation equipment health.

[0104] Among them, the load index of any workstation can be calculated based on the above-mentioned state influence factors, thereby characterizing the load status of the workstation based on the quantitative data of the load index.

[0105] Specifically, a first ratio can be determined between the estimated calibration time and the maximum working time indicated by the equipment configuration vector. A non-linear mapping process is applied to the fit score to obtain the fit mapping value. Based on historical performance records, the variance of the time taken for any workstation to execute tasks within a preset period is determined; a weighted sum of the first ratio, the fit mapping value, and the variance is then obtained to obtain the load index.

[0106] In one embodiment of this application, the specific method for determining the load index of any one workstation is described in the following article. Figure 5 The corresponding detailed explanation.

[0107] S32, Based on the type of the calibration task, determine the compatibility coefficient between the calibration task and any one of the workstations.

[0108] In one embodiment of this application, in order to improve the accuracy of assessing the fit between workstations and calibration tasks, the fit coefficient between the calibration task and any workstation can be determined based on the type of calibration task.

[0109] Based on the type of the calibrated task, determine the success rate of any workstation processing other tasks of the same type as the calibrated task; based on the average success rate of all workstations processing tasks in the vehicle manufacturing system, normalize the success rate to obtain a normalized success rate; based on the sum of the normalized success rate and a preset constant, determine the fit coefficient.

[0110] In one embodiment of this application, for the specific method of determining the fit coefficient between the calibration task and any one of the workstations, please refer to [link to relevant documentation]. Figure 6 The corresponding detailed explanation.

[0111] S33, Based on the urgency of all tasks in the vehicle manufacturing system, determine the urgency amplification factor of the calibration task.

[0112] In one embodiment of this application, in order to improve the accuracy of assessing the urgency of the calibration task, the urgency amplification factor of the calibration task can be determined based on the urgency of all tasks in the vehicle manufacturing system.

[0113] Specifically, the average urgency can be determined based on the urgency of all tasks; the maximum and minimum urgency can be determined from the urgency of all tasks; the urgency of the calibrated task can be normalized based on the difference between the average urgency, maximum urgency and minimum urgency to obtain a normalized urgency; and the urgency amplification factor can be determined based on the sum of the normalized urgency and a preset constant.

[0114] In one embodiment of this application, the specific method for determining the urgency amplification factor of the calibration task can be found in [link to relevant documentation]. Figure 7 The corresponding detailed explanation.

[0115] S34. The priority score is determined based on the ratio between the task urgency and the load index, and the product of the adaptability coefficient and the urgency amplification coefficient.

[0116] like Figure 4 The diagram shown is a flowchart of a method for determining task urgency according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining task urgency provided in this embodiment includes the following steps.

[0117] S40, determine the time difference between the delivery time and the system time.

[0118] In one embodiment of this application, the larger the time difference between the delivery time of the calibration task and the system time, the more time is left to complete the calibration task, and the lower the urgency of the calibration task; the smaller the time difference between the delivery time of the calibration task and the system time, the less time is left to complete the calibration task, and the higher the urgency of the calibration task.

[0119] S41, Based on the task fault identifier, determine the fault priority of the calibrated task.

[0120] In one embodiment of this application, when the task fault identifier indicates that the device performing the calibration task has a fault, it means that the calibration task needs to be executed first, and the fault priority of the calibration task is higher; when the task fault identifier indicates that the device performing the calibration task does not have a fault, it means that the calibration task does not need to be executed first, and the fault priority of the calibration task is lower.

[0121] For example, when the task fault identifier indicates that the device performing the calibration task is faulty, the fault priority can be 1; when the task fault identifier indicates that the device performing the calibration task is not faulty, the fault priority can be 0.

[0122] S42, perform a weighted summation of the time difference, the fault priority, and the task dependency to obtain the task urgency.

[0123] In one embodiment of this application, the specific method for determining the urgency of a task satisfies the following relationship: ; in, This represents the task urgency of the calibration task at index i. The larger the task urgency value, the higher the priority of the corresponding calibration task. Representative task Vehicle delivery time; Represents the current time of the vehicle manufacturing system; This represents the fault priority flag. The fault priority can be 1 when the equipment malfunctions, and 0 when the equipment is working properly. This represents the task dependency of the calibration task at index i. For example, when the calibration task at index i is a prerequisite for other tasks. The value of can be 1, otherwise The value of is 0; This represents the set of other tasks that depend on the calibration task at index i. The dependency weight represents the relationship between the calibration task at index i and the calibration task at index k. This dependency weight is used to indicate the degree of association between the calibration task and other tasks, and its value can be between 0 and 1. The weighting factor representing delivery time; for example, the default value for the weighting factor of delivery time can be 1. The weighting coefficient represents the fault priority. For example, the default value for the weighting coefficient of fault priority can be 5. The weighting coefficient represents the degree of task dependency. For example, the default value for the weighting coefficient of task dependency can be 3. The weighting coefficient represents the strength of the dependency. The default value for the weighting coefficient of the dependency strength can be 2.

[0124] like Figure 5 The diagram shows a flowchart of a method for determining the load index of any workstation according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining the load index of any workstation according to an embodiment of this application includes the following steps.

[0125] S50, determine a first ratio of the sum of the estimated times of all tasks corresponding to any given workstation to the maximum working time indicated by the equipment configuration vector.

[0126] In one embodiment of this application, in order to evaluate the load caused by the tasks undertaken by any workstation to the workstation with quantitative data, the estimated time of all tasks corresponding to the workstation can be determined from the task queue of any workstation, and the maximum working time of the workstation can be determined according to the equipment configuration vector in the capability matrix of the workstation.

[0127] A first ratio can be determined between the sum of estimated times and the maximum working time of the workstation. The higher this first ratio, the longer it takes for the workstation to process the assigned tasks, and the higher the workload of the workstation.

[0128] S51, perform nonlinear mapping processing on the fitness score to obtain the fitness mapping value.

[0129] In one embodiment of this application, to improve the accuracy of evaluating the load index based on the fit score, the fit score can be subjected to nonlinear mapping processing to obtain a fit mapping value. The load index of the workstation can then be evaluated based on the fit mapping value.

[0130] For example, the fitness score can be nonlinearly mapped based on the hyperbolic tangent function, or it can be nonlinearly mapped based on the sigmoid function. This application does not limit the specific method of nonlinear mapping.

[0131] S52, based on the performance history record, determine the variance of the time taken for any workstation to perform a task within a preset period.

[0132] In one embodiment of this application, the time spent processing a task at any workstation can be determined based on historical performance records, and the variance of the time taken by that workstation to execute the task within a preset period can be determined. This allows for a quantitative assessment of the fluctuation in the time taken by that workstation to execute the task based on the variance. Specifically, a larger variance indicates a higher degree of fluctuation in the time taken by that workstation to execute the task, resulting in lower performance stability and a higher workload for that workstation; conversely, a smaller variance indicates a lower degree of fluctuation in the time taken by that workstation to execute the task, resulting in higher performance stability and a lower workload for that workstation.

[0133] S53, the first ratio, the fit mapping value and the variance are weighted and summed to obtain the load index.

[0134] In one embodiment of this application, the specific method for determining the load index of any workstation satisfies the following relationship: ; in, The load index represents the workstation with index j. The higher the value of the load index, the higher the load of the workstation with index j. This represents the current task queue for workstation with index j. This represents the estimated completion time of the task with index m in the task queue. This represents the maximum working time for the workstation with index j. Representative task The fit score with the workstation at index j; The variance of the time taken for the workstation with index j to complete its task within a preset period can reflect the stability of the workstation with index j. This represents the adaptation factor; for example, the default value could be 0.3. This represents the stability impact coefficient, with a default value of 0.2.

[0135] like Figure 6 The diagram shown is a flowchart of a method for determining the adaptability coefficient of any workstation according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining the adaptability coefficient of any workstation according to an embodiment of this application includes the following steps.

[0136] S60, based on the type of the calibrated task, determine the success rate of any workstation in handling other tasks of the same type as the calibrated task.

[0137] In one embodiment of this application, in order to determine the success rate of any workstation performing a calibration task, the success rate of any workstation handling other tasks of the same type as the calibration task can be determined based on the type of the calibration task.

[0138] S61, based on the average success rate of all workstations in the vehicle manufacturing system, the success rate is normalized to obtain a normalized success rate.

[0139] In one embodiment of this application, in order to improve the accuracy of the fit coefficient of the workstation and the calibration task based on the success rate, the success rate can be normalized based on the average success rate of the tasks processed by all workstations in the vehicle manufacturing system to obtain a normalized success rate.

[0140] For example, the normalized success rate is calculated according to the following relationship: ; in, Representative workstation For the task Success rate of similar tasks This represents the average success rate of all tasks in the vehicle manufacturing system.

[0141] S62, determine the fit coefficient based on the sum of the normalization success rate and the preset constant.

[0142] In one embodiment of this application, the specific method for determining the fit coefficient satisfies the following relationship: ; in, The fit coefficient represents the compatibility between the calibration task with index i and the workstation with index j; This represents the historical success rate of similar tasks for workstation with index j and calibration task with index i. This represents the average success rate of all tasks in the vehicle manufacturing system.

[0143] like Figure 7 The diagram shown is a flowchart of a method for determining the urgency amplification factor of a calibration task according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining the urgency amplification factor of a calibration task provided in this embodiment of the application includes the following steps.

[0144] S70, determine the average urgency based on the urgency of all the tasks.

[0145] S71, determine the maximum and minimum urgency from the urgency of all the tasks.

[0146] S72, based on the difference between the average urgency, maximum urgency and minimum urgency, the urgency of the calibrated task is normalized to obtain the normalized urgency.

[0147] In one embodiment of this application, the specific method for determining the normalized urgency satisfies the following relationship: ; in, This represents the average urgency of all tasks in the vehicle manufacturing system. This represents the maximum urgency of a task within the vehicle manufacturing system. This represents the minimum urgency of a task within the vehicle manufacturing system. This adaptation factor combines the historical success rate of the workstation with the calibration efficiency of the current cycle for a comprehensive evaluation, improving the accuracy of subsequent workstation priority assignments.

[0148] S73, Based on the sum of the normalized urgency and the preset constant, determine the urgency amplification factor.

[0149] In one embodiment of this application, the specific method for determining the urgency amplification factor satisfies the following relationship: ; in, This represents the urgency amplification factor for the i-th calibration task; The weight representing the urgency amplification factor; for example, the default value for this weight can be 0.5. This represents the average urgency of all tasks in the vehicle manufacturing system. This represents the maximum urgency of a task within the vehicle manufacturing system. This represents the minimum urgency of a task within the vehicle manufacturing system. This adaptation factor combines the historical success rate of the workstation with the calibration efficiency of the current cycle for a comprehensive evaluation, improving the accuracy of subsequent workstation priority assignments.

[0150] In one embodiment of this application, to further improve the accuracy of calculating the priority score of the calibrated tasks for each workstation, the task urgency of the calibrated tasks can be updated based on the scheduling duration of the calibrated tasks, and the load index of any workstation can be updated based on the adaptability score. For example... Figure 8 The diagram shown is a flowchart of a method for updating task urgency and load index according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for updating task urgency and load index provided in this embodiment includes the following steps.

[0151] S80, after determining the task urgency and the load index of any workstation, the task urgency is weighted based on the task acceleration factor of the calibrated task to obtain an updated task urgency; the task acceleration factor indicates the degree of influence of the scheduling time of the calibrated task on the task urgency.

[0152] In one embodiment of this application, in order to enhance the contribution of the scheduling time of the calibrated task to the priority score and ensure that the longer the task scheduling time is, the higher the priority score, a task acceleration factor can be determined based on the scheduling time of the calibrated task, and the task urgency can be weighted based on the task acceleration factor of the calibrated task to obtain the updated task urgency.

[0153] The task acceleration factor indicates the degree to which the scheduling time of the calibrated task affects the urgency of the task. The higher the value of the task acceleration factor, the greater the influence of the task scheduling time on the urgency of the task.

[0154] S81, the load index is weighted based on the penalty term of the calibration task to obtain an updated load index; the penalty term indicates the degree of influence of the fit between the calibration task and any workstation on the load index.

[0155] In one embodiment of this application, in order to improve the influence of the fit between the calibration task and the workstation on the load index, the load index can be weighted based on the penalty term of the calibration task to obtain an updated load index.

[0156] The penalty item indicates the degree to which the fit between the calibrated task and any workstation affects the load index. The higher the value of the penalty item, the greater the influence of the fit between the calibrated task and any workstation on the load index, which in turn increases the influence of the workstation's load index on the priority score.

[0157] like Figure 9 The diagram shown is a flowchart of a method for determining a task acceleration factor according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining a task acceleration factor provided in this embodiment includes the following steps.

[0158] S90, determine the average scheduling time of all tasks in the vehicle manufacturing system.

[0159] S91, determine a second ratio of the scheduling time of the calibration task to the average value.

[0160] S92, determine the first difference between the second ratio and the preset first threshold.

[0161] In one embodiment of this application, a higher first difference indicates that the scheduling time of the task is of a higher order among the scheduling times corresponding to all tasks in the vehicle manufacturing system.

[0162] S93, the minimum value between the first difference and the preset second threshold is determined as the task acceleration factor.

[0163] In one embodiment of this application, the specific method for determining the task acceleration factor satisfies the following relationship: ; in, The task acceleration factor represents the calibration task at index i; This represents the scheduling time for the task with index i. This represents the average scheduling time of all tasks in the vehicle manufacturing system. The first threshold can be 1; the second threshold can be 0.5. This application does not limit the values ​​of the first and second thresholds.

[0164] like Figure 10The diagram shown is a flowchart of a method for determining penalty items according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining penalty items provided in this embodiment of the application includes the following steps.

[0165] S100, when the task requirements of the calibrated task and the workstation capability of any workstation meet the preset conditions, determine the second difference between the fit score and the preset third threshold.

[0166] In one embodiment of this application, the preset conditions include: the requirement accuracy of the task requirement indication is higher than the equipment accuracy of the workstation capability indication; or, the software version of the task requirement indication does not match the software version of the workstation capability indication.

[0167] S110, the maximum value between the second difference and the preset fourth threshold is determined as the penalty item.

[0168] In one embodiment of this application, the specific method for determining the penalty term satisfies the following relationship: ; in, The penalty term represents the fit score between the calibration task with index i and the workstation with index j; S120, if the task requirements of the calibrated task and the workstation capacity of any workstation do not meet the preset conditions, the fourth threshold is determined as the penalty item.

[0169] In one embodiment of this application, when the task requirements of the calibrated task and the workstation capability of any one of the workstations do not meet the preset conditions, it indicates that the workstation can handle the calibrated task. Therefore, there is no need to suppress the priority score based on the penalty term, and the fourth threshold can be directly determined as the penalty term. For example, the fourth threshold can be 0.

[0170] In one embodiment of this application, when determining the updated task urgency and load indicators, the specific method for determining the priority score of each workstation executing the calibrated task satisfies the following relationship: ; in, The dynamic priority score represents the workstation with index j processing the calibration task with index i. The higher the value of the dynamic priority score, the higher the priority of processing the calibration task using that workstation.

[0171] Please see Figure 11This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 100 includes a memory 12 and a processor 13. The memory 12 is used to store computer-readable instructions, and the processor 13 executes the computer-readable instructions stored in the memory to implement a task allocation method described in any of the above embodiments.

[0172] In one embodiment of this application, the electronic device 100 further includes a bus and a computer program, such as a task assignment program, stored in the memory 12 and executable on the processor 13.

[0173] Figure 11 Only an electronic device 100 with memory 12 and processor 13 is shown; those skilled in the art will understand that... Figure 11 The structure shown does not constitute a limitation on the electronic device 100, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0174] Combination Figure 2 The memory 12 in the electronic device 100 stores a plurality of computer-readable instructions to implement the task allocation method, and the processor 13 can execute the plurality of instructions to achieve: constructing a task feature vector for a calibration task; the task feature vector includes at least the vehicle's sensor type, the vehicle's model complexity, the estimated calibration time of the calibration task, and the dependency identifier of the calibration task; determining a capability matrix corresponding to each workstation based on the workstation data corresponding to each of the multiple workstations; the capability matrix corresponding to any workstation includes at least an equipment configuration vector and the performance history record of the any workstation, the equipment configuration vector indicating the performance of the any workstation on the target system. The corresponding sensor type, device model, and software version; the performance history record indicates the calibration success rate and average time for different sensor types and vehicle models corresponding to any one workstation; based on the task feature vector and the capability matrix of each workstation, determine the fit score between the calibration task and each workstation; based on the task urgency of the calibration task, the fit score between the calibration task and each workstation, and the load index of each workstation, determine the priority score for each workstation to execute the calibration task; based on the priority score, determine the target workstation among the multiple workstations, and assign the calibration task to the target workstation.

[0175] Specifically, the processor 13's implementation method for the above instructions can be found in [reference needed]. Figure 2 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0176] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 100 and does not constitute a limitation on the electronic device 100. The electronic device 100 may be a bus-type structure or a star-type structure. The electronic device 100 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, the electronic device 100 may also include input / output devices, network access devices, etc.

[0177] It should be noted that electronic device 100 is only an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0178] The memory 12 includes at least one type of readable storage medium, which can be non-volatile or volatile. The readable storage medium includes flash memory, portable hard drives, multimedia cards, card-type memory (e.g., SD or DX memory), magnetic storage, magnetic disks, optical disks, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 100, such as the portable hard drive of the electronic device 100. In other embodiments, the memory 12 can also be an external storage device of the electronic device 100, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 100. The memory 12 can be used not only to store application software and various types of data installed on the electronic device 100, such as the code of a task allocation program, but also to temporarily store data that has been output or will be output.

[0179] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 13 is the control unit of the electronic device 100, connecting to various components of the electronic device 100 via various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., task allocation programs) and calls data stored in the memory 12 to perform various functions of the electronic device 100 and process data.

[0180] The processor 13 executes the operating system of the electronic device 100 and various installed applications. The processor 13 executes the applications to implement the steps in the above-described task allocation method embodiments, for example... Figure 2 The steps are shown.

[0181] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete this application. The one or more modules / units may be a series of computer-readable instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device 100.

[0182] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute a portion of the task allocation method described in the various embodiments of this application.

[0183] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0184] The computer program includes computer program code, which may be in the form of source code, foreground object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, and other memory.

[0185] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0186] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 11 The symbol is represented by only one arrow, but this does not indicate that there is only one bus or one type of bus. The bus is configured to enable communication between the memory 12 and at least one processor 13, etc.

[0187] This application also provides a computer-readable storage medium (not shown), which stores computer-readable instructions that are executed by a processor in an electronic device to implement the task allocation method described in any of the above embodiments.

[0188] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0189] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0190] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in the specification may also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0191] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A task allocation method, characterized in that, The method includes: Construct a task feature vector for the calibration task; the task feature vector includes at least the vehicle's sensor type, the vehicle's model complexity, the estimated calibration time of the calibration task, and the dependency identifier of the calibration task; Based on the workstation data corresponding to each of the multiple workstations, a capability matrix corresponding to each workstation is determined; the capability matrix corresponding to any workstation includes at least an equipment configuration vector and the performance history of that workstation, the equipment configuration vector indicating the sensor type, equipment model and software version corresponding to that workstation, and the performance history indicating the calibration success rate and average time consumption for different sensor types and vehicle models corresponding to that workstation. Based on the task feature vector and the capability matrix of each workstation, the fit score between the calibrated task and each workstation is determined; Based on the task urgency of the calibrated task, the compatibility score between the calibrated task and each workstation, and the load index of each workstation, the priority score for each workstation to execute the calibrated task is determined. Based on the priority score, a target workstation is determined among the plurality of workstations, and the calibrated task is assigned to the target workstation.

2. The task allocation method according to claim 1, characterized in that, The step of determining the priority score for each workstation to execute the calibrated task based on the task urgency of the calibrated task, the compatibility score between the calibrated task and each workstation, and the load index of each workstation includes: The urgency of the task is determined based on the vehicle delivery time, the system time of the vehicle manufacturing system, the task fault identifier, and the task dependency degree indicated by the dependency relationship identifier. Based on the estimated calibration time of the calibration task, the equipment configuration vector of any workstation, the adaptability score, and the performance history of any workstation, the load index of any workstation is determined. Based on the type of the calibration task, determine the compatibility coefficient between the calibration task and any one of the workstations; Based on the urgency of all tasks in the vehicle manufacturing system, the urgency amplification factor of the calibration task is determined; The priority score is determined based on the ratio between the task urgency and the load index, and the product of the adaptability coefficient and the urgency amplification coefficient.

3. The task allocation method according to claim 2, characterized in that, The determination of the task urgency based on the vehicle's delivery time, the vehicle manufacturing system's system time, the task fault identifier, and the task dependency indicated by the dependency relationship identifier includes: Determine the time difference between the delivery time and the system time; Based on the task fault identifier, the fault priority of the calibrated task is determined; The task urgency is obtained by weighted summation of the time difference, the fault priority, and the task dependency.

4. The task allocation method according to claim 2, characterized in that, The determination of the load index of any workstation based on the estimated calibration time of the calibration task, the equipment configuration vector of any workstation, the adaptability score, and the performance history of any workstation includes: Determine a first ratio of the sum of the estimated times of all tasks corresponding to any given workstation to the maximum working time indicated by the equipment configuration vector; The fitness score is subjected to nonlinear mapping to obtain the fitness mapping value; Based on the performance history records, determine the variance of the time taken for any workstation to perform a task within a preset period; The load index is obtained by weighted summation of the first ratio, the fit mapping value, and the variance.

5. The task allocation method according to claim 2, characterized in that, The determination of the fit coefficient between the calibration task and any given workstation based on the type of the calibration task includes: Based on the type of the calibrated task, determine the success rate of any workstation in handling other tasks of the same type as the calibrated task; Based on the average success rate of all workstations in the vehicle manufacturing system, the success rate is normalized to obtain a normalized success rate. The fit coefficient is determined based on the sum of the normalization success rate and a preset constant.

6. The task allocation method according to claim 2, characterized in that, The determination of the urgency amplification factor for the calibrated task based on the urgency of all tasks in the vehicle manufacturing system includes: Based on the task urgency of all the tasks, determine the average urgency. Determine the maximum and minimum urgency from the urgency of all the tasks mentioned; Based on the difference between the average urgency, maximum urgency and minimum urgency, the urgency of the calibrated task is normalized to obtain the normalized urgency. The urgency amplification factor is determined based on the sum of the normalized urgency and a preset constant.

7. The task allocation method according to claim 2, characterized in that, The method further includes: After determining the task urgency and the load index of any workstation, the task urgency is weighted based on the task acceleration factor of the calibrated task to obtain the updated task urgency; the task acceleration factor indicates the degree of influence of the scheduling time of the calibrated task on the task urgency. The load index is weighted based on the penalty term of the calibration task to obtain the updated load index; the penalty term indicates the degree of influence of the fit between the calibration task and any workstation on the load index.

8. The task allocation method according to claim 7, characterized in that, The method for determining the task acceleration factor includes: Determine the average scheduling time of all tasks in the vehicle manufacturing system; Determine a second ratio between the scheduling time of the calibrated task and the average value; Determine the first difference between the second ratio and the preset first threshold; The minimum value between the first difference and the preset second threshold is determined as the task acceleration factor.

9. The task allocation method according to claim 7, characterized in that, The method for determining the penalty item includes: If the task requirements of the calibrated task and the workstation capability of any workstation meet the preset conditions, determine the second difference between the fit score and the preset third threshold; and determine the maximum value between the second difference and the preset fourth threshold as the penalty item. If the task requirements of the calibrated task and the workstation capabilities of any workstation do not meet the preset conditions, the fourth threshold is determined as the penalty item. The preset conditions include: the requirement accuracy of the task requirement indication is higher than the equipment accuracy of the workstation capability indication; or, the software version of the task requirement indication does not match the software version of the workstation capability indication.

10. An electronic device, characterized in that, The electronic device includes a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement the task allocation method as described in any one of claims 1 to 9.

Images