A task allocation method, device, equipment and product

Abstract

The present invention provides a task allocation method, device, equipment and product, which relates to the field of task processing technology. The method comprises the following steps: obtaining evaluation parameters of personnel to be assigned; inputting the evaluation parameters into a task allocation model to obtain evaluation parameters output by the task allocation model; wherein the evaluation parameters include a comprehensive evaluation value of the personnel to be assigned, a first time-consuming evaluation value and a first number evaluation value, the first time-consuming evaluation value is the time-consuming evaluation value of the task completed at that time, the first number evaluation value is the number evaluation value of the task completed at that time, the timeliness value is inversely proportional to the actual operation time, and the accuracy value is inversely proportional to the number of cycles; based on the evaluation parameters, tasks are allocated. The present invention can allocate tasks to business personnel with high completion quality and fast completion speed, avoiding the backlog of tasks and the task processing quality not meeting the requirements.

Description

Technical Field

[0001] The present invention relates to the field of task processing technology, and in particular to a task allocation method, device, equipment and product. Background Art

[0002] In enterprise management, there are many work tasks that need to be assigned. In the existing task assignment or scheduling method, managers assign or schedule tasks to business personnel. In some cases, business personnel take the initiative to accept tasks based on their personal circumstances. However, this method is mainly based on the subjective judgment of managers and business personnel. Therefore, it will cause some tasks to be assigned unreasonably. Some tasks need to be handled by business personnel with stronger business capabilities and higher business qualities. However, these tasks are not assigned to business personnel with the above-mentioned capabilities, resulting in low quality of task completion.

[0003] In summary, it is necessary to provide a task allocation method that can improve the quality of task completion. Summary of the invention

[0004] The present invention provides a task allocation method, device, equipment and product, which are used to solve the defect in the prior art that tasks cannot be allocated to business personnel with stronger business capabilities and higher business qualities for processing, and can allocate tasks to business personnel with high completion quality and fast completion speed, avoiding backlog of tasks and task processing quality that does not meet requirements, and is also conducive to obtaining targeted business personnel training programs.

[0005] The present invention provides a task allocation method, comprising the following steps:

[0006] Obtaining evaluation parameters of the personnel to be assigned; wherein the evaluation parameters include actual operation time and number of cycles, the number of cycles being the number of rounds used to pass the inspection when the task is completed, and the actual operation time being the sum of the actual operation time corresponding to each round when the task is completed;

[0007] The evaluation parameters are input into the task allocation model to obtain the evaluation parameters output by the task allocation model; wherein the evaluation parameters include a comprehensive evaluation value of the personnel to be assigned, a first time-consuming evaluation value and a first number evaluation value, the first time-consuming evaluation value is the time-consuming evaluation value of the task to be completed, the first number evaluation value is the number evaluation value of the task to be completed, the first time-consuming evaluation value is obtained based on the timeliness value, and the first number evaluation value is obtained based on the accuracy value; the task allocation model is trained based on the sample operation time and sample cycle number of the sample personnel completing the task at that time, as well as the second time-consuming evaluation value and the second number evaluation value of the personnel to be assigned, the second time-consuming evaluation value is the time-consuming evaluation value of the last completion of the task, the second number evaluation value is the number evaluation value of the last completion of the task, the timeliness value is inversely proportional to the actual operation time, and the accuracy value is inversely proportional to the number of cycles;

[0008] Based on the evaluation parameters, tasks are assigned; wherein, the higher the value of the evaluation parameter corresponding to the person to be assigned is, the higher the priority of the person to be assigned is in task assignment.

[0009] According to the task allocation method provided by the present invention, the task allocation model includes a timeliness processing layer, an accuracy processing layer and an evaluation layer;

[0010] The timeliness processing layer is used to perform timeliness processing on the actual operation time based on the sample operation time and the second time evaluation value, so as to obtain the timeliness value; the accuracy processing layer is used to perform accuracy processing on the number of cycles based on the sample number of cycles and the second number evaluation value, so as to obtain the accuracy value; the evaluation layer is used to perform evaluation processing on the timeliness value obtained from the timeliness processing by the timeliness processing layer and the accuracy value obtained from the accuracy processing by the accuracy processing layer, so as to obtain the evaluation parameters.

[0011] According to the task allocation method provided by the present invention, the evaluation layer includes a comprehensive evaluation layer, a time-consuming evaluation processing layer and a number of evaluation processing layer;

[0012] The comprehensive evaluation layer is used to perform weighted processing on the timeliness value obtained by the timeliness processing layer and the accuracy value obtained by the accuracy processing layer to obtain the comprehensive evaluation value;

[0013] The time consumption evaluation processing layer is used to process the timeliness value obtained from the timeliness processing layer based on the third weight to obtain the first time consumption evaluation value; the number evaluation processing layer is used to process the accuracy value obtained from the accuracy processing layer based on the fourth weight to obtain the first number evaluation value.

[0014] According to the task allocation method provided by the present invention, the inputting of the evaluation parameters into the task allocation model to obtain the evaluation parameters output by the task allocation model specifically comprises the following steps:

[0015] The evaluation parameters are input into the timeliness processing layer to obtain the timeliness value corresponding to the completion of the current task output by the timeliness processing layer; the evaluation parameters are input into the accuracy processing layer to obtain the accuracy value corresponding to the completion of the current task output by the accuracy processing layer; the timeliness value and the accuracy value are input into the evaluation layer to obtain the comprehensive evaluation value, the first time-consuming evaluation value and the first number of evaluation values ​​corresponding to the completion of the current task output by the evaluation layer.

[0016] According to the task assignment method provided by the present invention, the timeliness value and the accuracy value are input into the comprehensive evaluation layer to obtain the comprehensive evaluation value corresponding to the completion of the task output by the comprehensive evaluation layer, which specifically includes the following steps:

[0017] The timeliness value and the accuracy value are input into the comprehensive evaluation layer of the evaluation layer to obtain the comprehensive evaluation value corresponding to the completion of the current task output by the comprehensive evaluation layer; the timeliness value is input into the time consumption evaluation processing layer of the evaluation layer to obtain the first time consumption evaluation value corresponding to the completion of the current task output by the time consumption evaluation processing layer; the accuracy value is input into the number evaluation processing layer of the evaluation layer to obtain the first number evaluation value corresponding to the completion of the current task output by the number evaluation processing layer.

[0018] According to the task allocation method provided by the present invention, the task allocation model is trained by the following steps:

[0019] Obtain the sample operation time and the sample cycle number of the sample personnel completing the task, as well as the second time evaluation value and the second number evaluation value of the personnel to be assigned; determine the first weight, the second weight, the third weight, the fourth weight, the fifth weight and the sixth weight; use the sample operation time, the sample cycle number, the second time evaluation value and the second number evaluation value as input data for training, adopt a machine learning training method, and obtain the task allocation model for generating the evaluation parameters of the personnel to be assigned.

[0020] The present invention also provides a task allocation device, comprising:

[0021] An acquisition module is used to acquire the evaluation parameters of the personnel to be assigned; wherein the evaluation parameters include actual operation time and number of cycles, the number of cycles is the number of rounds used to pass the inspection when the task is completed, and the actual operation time is the sum of the actual operation time corresponding to each round of the task completed;

[0022] An evaluation module is used to input the evaluation parameters into a task allocation model to obtain evaluation parameters output by the task allocation model; wherein the evaluation parameters include a comprehensive evaluation value of the personnel to be assigned, a first time-consuming evaluation value and a first number evaluation value, wherein the first time-consuming evaluation value is a time-consuming evaluation value for completing the current task, and the first number evaluation value is a number evaluation value for completing the current task, wherein the first time-consuming evaluation value is obtained based on a timeliness value, and wherein the first number evaluation value is obtained based on an accuracy value; the task allocation model is obtained by training based on the sample operation time and sample cycle number of the sample personnel completing the current task, as well as the second time-consuming evaluation value and the second number evaluation value of the personnel to be assigned, wherein the second time-consuming evaluation value is a time-consuming evaluation value for the last completion of the current task, and the second number evaluation value is a number evaluation value for the last completion of the current task, wherein the timeliness value is inversely proportional to the actual operation time, and wherein the accuracy value is inversely proportional to the number of cycles;

[0023] The allocation module is used to allocate tasks based on the evaluation parameters; wherein, the higher the value of the evaluation parameter corresponding to the person to be allocated, the higher the priority of the person to be allocated in task allocation.

[0024] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned task allocation methods when executing the program.

[0025] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned task allocation methods are implemented.

[0026] The task allocation method, device, equipment and product provided by the present invention reflect the influence of human cognitive factors and non-cognitive factors on their operation behavior through two state variables, namely, the time consumption evaluation value and the number of evaluation value of the personnel to be assigned, so that the trained task allocation model can more accurately describe the human operation behavior, thereby objectively and comprehensively evaluating the task completion quality of relevant business personnel;

[0027] The evaluation parameters of the personnel to be assigned are used as the evaluation results of the task completion quality, and the comprehensive evaluation value, time-consuming evaluation value and number of evaluation values ​​are included in the indicators for enterprise task allocation. Tasks are allocated based on the evaluation parameters, which can realize the scientific, refined and standardized allocation of tasks by the enterprise, and give priority to allocating tasks to business personnel with higher comprehensive evaluation values. Tasks can be allocated to business personnel with high completion quality and fast completion speed, avoiding backlog of tasks and task processing quality that does not meet requirements, and is also conducive to obtaining targeted business personnel training programs. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 It is a flowchart of the task allocation method provided by the present invention;

[0030] Figure 2 It is a schematic diagram of the application of the task allocation method provided by the present invention in the field of enterprise management;

[0031] Figure 3 It is a specific structural diagram of the task allocation model in the task allocation method provided by the present invention;

[0032] Figure 4 It is a specific structural diagram of the evaluation layer in the task allocation method provided by the present invention;

[0033] Figure 5 It is a structural schematic diagram of the task allocation device provided by the present invention;

[0034] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] Compared with the subjective allocation or active task acceptance method, it is obvious that if the task allocation or scheduling can be handed over to business personnel with stronger business capabilities and higher business quality, the quality of task completion will be significantly improved. Business capabilities and business quality can be reflected by parameters such as the time and quality when business personnel complete one or more tasks. The time can reflect the degree of effort of the business personnel to a certain extent, and the quality can reflect the ability and quality of the business personnel to a certain extent.

[0037] Robotic Process Automation (RPA) is widely used in the business process automation system of enterprises. However, machines and even artificial intelligence cannot completely replace people. Some key steps in the business process automation system must require human participation, operation, or decision-making. In the field of enterprise management, if an enterprise enables the RPA system, the time and quality of business personnel when completing tasks need to be completed by collecting the operation behavior of business personnel on the RPA system. Although the RPA system has a monitoring function, it cannot monitor the operation behavior of business personnel. In the all-round management of enterprises, the management of business personnel in this type of human-machine interactive business process automation system (referred to as human-machine interactive system) is a blind spot.

[0038] At the same time, since humans are complex individuals, their operational behaviors are affected by various cognitive factors, such as perception, representation, memory, thinking, and non-cognitive factors, such as emotion, will, motivation, interest, and other non-cognitive factors. Taking the field of enterprise management as an example, how to comprehensively consider multiple factors including cognitive factors and non-cognitive factors, quantitatively describe the operational behaviors of business personnel, and comprehensively evaluate the quality of business personnel completing tasks is a technical problem that needs to be solved in the field of enterprise management.

[0039] In order to overcome the above problems in the prior art, Figure 1 The task allocation method of the present invention is described. The method can be applied to the field of enterprise management. It should be noted that, depending on the specific application situation, the method can also be applied to other task processing fields.

[0040] The method specifically comprises the following steps:

[0041] S100, obtaining evaluation parameters of the personnel to be assigned. In this method, the evaluation parameters include actual operation time and number of cycles, the number of cycles is the number of rounds used to pass the inspection when the task is completed, and the actual operation time is the sum of the actual operation time corresponding to each round when the task is completed.

[0042] It should be noted that when a task is completed, it can be a single task or multiple tasks.

[0043] S200, input the evaluation parameters into the trained task allocation model to obtain the evaluation parameters output by the task allocation model. In this method, the evaluation parameters include the comprehensive evaluation value of the personnel to be assigned, the first time-consuming evaluation value and the first number evaluation value, the first time-consuming evaluation value is the time-consuming evaluation value of the personnel to be assigned to complete the current task, the first number evaluation value is the number of times the personnel to be assigned to complete the current task, the first time-consuming evaluation value is obtained based on the timeliness value, the first number evaluation value is obtained based on the accuracy value, the timeliness value is inversely proportional to the actual operation time, and the accuracy value is inversely proportional to the number of cycles.

[0044] The task allocation model provided in the method is trained based on the sample operation time and sample cycle times of the sample personnel completing the task, as well as the second time evaluation value and second number evaluation value of the personnel to be assigned. The second time evaluation value is the time evaluation value of the last completion of the task by the personnel to be assigned, and the second number evaluation value is the number evaluation value of the last completion of the task by the personnel to be assigned.

[0045] It should be noted that the last completion of the current task refers to the single task or multiple tasks completed at the time in step S100, and also the various results corresponding to the last completion by the person to be assigned.

[0046] S300. Allocate tasks based on evaluation parameters. For example, the higher the value of the evaluation parameter corresponding to the person to be assigned, the higher the priority of the person to be assigned in task allocation, that is, the higher the value of the evaluation parameter, the higher the priority of assigning the task to the person to be assigned.

[0047] In this method, the evaluation parameters include three parameters, namely, a comprehensive evaluation value, a first time-consuming evaluation value and a first number evaluation value.

[0048] In some possible embodiments, when assigning tasks, multiple preset values ​​can be set in advance, and the comprehensive evaluation value of the person to be assigned when the task is completed can be compared with these preset values, so that the priority of the person to be assigned in the next task assignment or scheduling can be obtained accordingly. In some cases, such as when the comprehensive ability of the business personnel needs to be considered, the higher the priority, the higher the priority of the person to be assigned in the next task assignment; when assigning tasks, the difference between the first time-consuming evaluation value and the second time-consuming evaluation value of the person to be assigned is obtained. When the difference is a positive value, it indicates that the work effort of the person to be assigned has increased, and when the difference is a negative value, it indicates that the work effort of the person to be assigned has decreased. The difference can indicate the performance of the work effort of the person to be assigned when completing the task, and the higher the positive value of the difference, the higher the , indicating that the higher the priority of the person to be assigned in the next task assignment or scheduling, in some cases, such as when it is necessary to give priority to the work effort of the business personnel, it means that the person to be assigned will be assigned with higher priority in the next task assignment; when assigning tasks, the difference between the first evaluation value and the second evaluation value of the person to be assigned is obtained. When the difference is a positive value, it indicates that the ability and quality of the person to be assigned has improved. When the difference is a negative value, it indicates that the work ability and quality of the person to be assigned has decreased. The difference can indicate the performance of the ability and quality of the person to be assigned when completing the task, and the higher the positive difference is, the higher the priority of the person to be assigned in the next task assignment or scheduling. In some cases, such as when it is necessary to give priority to the ability and quality, it means that the person to be assigned will be assigned with higher priority in the next task assignment.

[0049] Taking the application of the task allocation method of the present invention in the task management platform of an enterprise as an example, please refer to Figure 2 , the enterprise's task management platform includes M fully automatic systems and N human-computer interaction systems, forming M+N business process automation processing systems. The task management platform can monitor the operation of all business process automation systems, especially the operation behavior of business personnel in the human-computer interaction system to complete manual tasks. The task management platform can also share data with the data warehouse and other application systems of the enterprise.

[0050] Assume that in the i-th (i = 1, 2, ..., N, i is a positive integer) human-computer interaction system, in order to achieve a specific goal, it is necessary to execute J in a set order according to a pre-defined business process. i tasks, then there exists a task set T i It is the system that automatically completes the task set TS i And business personnel manually complete the task set TH i The union of , that is:

[0051]

[0052] Among them, T i It's J i A collection of tasks,

[0053] Assume that in the i-th human-computer interaction system, the tasks completed by the business personnel are Tasks ( is a positive integer) and is completed independently by K (k = 1, 2, ..., K, K is a positive integer) business personnel. In addition, the tasks completed by business personnel have been broken down into basic units and are all completed by a single person. There are no tasks that require collaboration among multiple people.

[0054] Then, when K = 1, it means that Each task is completed by the same business person alone. At this time, the i-th human-computer interaction system has only one interaction interface between the human-computer interaction system and the business person. When the task process reaches a certain node, the human-computer interaction system transmits data or documents to the business person through the interaction interface, that is, it is transferred to manual processing; after the manual task is completed, the processing result of the task is transmitted from the business person to the human-computer interaction system. Until the whole process is completed. Therefore, it is necessary to complete the task for this business person. Comprehensively evaluate the quality of each task.

[0055] When K>1, it indicates that Each task is completed by K salesmen. Correspondingly, there are K interactive interfaces between the human-computer interaction system and the salesmen in the i-th human-computer interaction system. According to the task allocation, the tasks that each of the K salesmen needs to complete independently have been determined. The total number of tasks completed by the k-th (k = 1, 2, ..., K, k is a positive integer) salesman is ( is a positive integer) item, and When the task process reaches a certain node, the human-computer interaction system transmits data or documents to the pre-set kth business personnel end, which is transferred to manual processing; after the kth business personnel completes the task, the processing result of the task is transmitted from the same business personnel end to the human-computer interaction system until the whole process is completed. Therefore, at this time, it is necessary to conduct a comprehensive evaluation of the task completion quality of the K business personnel.

[0056] If the i-th human-computer interaction system encounters a manual task during operation Then jump to the corresponding The manual processing sub-process of the task is completed, and other automatically completed tasks continue to be completed by the system until the entire process is completed.

[0057] When the process of the i-th human-computer interaction system reaches the When a task is completed, the sub-process starts. The task should be transferred to which business personnel end, and then forwarded to the corresponding business personnel end, at this time the number of cycles is 1. When the business personnel of a task are operating, the time starts. After the completion, it is uploaded to the main process of the enterprise's task management platform and enters the If the inspection passes, the sub-process ends, the number of cycles is 1, the timing ends, and the actual operation time is the actual operation time of the business personnel in this round. If the inspection fails, it is returned to the business personnel to continue processing the next round. The task is completed, and the number of cycles is increased by 1. The business personnel will continue to operate and the timing will continue until the inspection is passed. The timing ends, the sub-process ends, and the number of cycles is the first The rounds used when a task passes the inspection, the actual operation time is the sum of the actual operation time of the business personnel in each round, that is, the cumulative sum of the actual operation time in each round.

[0058] Depend on Figure 1 and Figure 2 As shown in the figure, the business personnel, i.e. the personnel to be assigned, are a component of the i-th human-computer interaction system. When the k-th business personnel perceives the information of a certain task, the central nervous system and the human execution system start to work until the business personnel complete the task. The business personnel end transmits the corresponding processing result of the task completion to the corresponding human-computer interaction system. In the above-mentioned task processing process, human perception, thinking, and execution together constitute the human operation behavior process, which is affected by both cognitive factors and non-cognitive factors.

[0059] Assume that the kth business person in the i-th human-computer interaction system completes the nth The comprehensive evaluation value after each task is

[0060] Assume that the kth business person in the i-th human-computer interaction system completes the nth The first time-consuming evaluation value after the task is (n=1,2,3,……, n is a positive integer), The range of is defined as the interval [0,1]. is a discrete time function, and the rate of change of the timeliness value is used as The independent variable that changes.

[0061] The time-consuming evaluation value indicates the work performance of the business personnel and reflects the work effort of the business personnel. A value of 1 indicates that the business person works very hard. A value of 0 means that the business person does not work hard. The value can be a linear function in the interval [0,1] or a function of other forms. It can be obtained based on an evaluation of a business person's past work performance.

[0062] Assume that the kth business person in the i-th human-computer interaction system completes the nth The first evaluation value after the task is The range of is defined in the interval [0,1]. is a discrete time function, and the rate of change of the accuracy value is used as The independent variable that changes.

[0063] The frequency evaluation value indicates the professional background and work experience of the business personnel, and reflects the ability and quality of the business personnel. 1 means that the business person has a strong professional background and rich work experience. A value of 0 indicates that the business person has a poor professional background and insufficient work experience. When different values ​​are taken, it reflects the different professional backgrounds and work experiences of business personnel. The value can be a linear function in the interval [0,1] or a function of other forms. It can be obtained based on a comprehensive assessment of a business person’s professional background and work experience.

[0064] The task allocation method of the present invention evaluates the task completion quality of the personnel to be assigned through a trained task allocation model, and uses the evaluation parameters output by the task allocation model to reflect the task completion quality of the personnel to be assigned when completing the task.

[0065] The task allocation method of the present invention reflects the influence of cognitive factors and non-cognitive factors on the operation behavior of the personnel to be assigned through two state variables, namely, the time evaluation value and the number evaluation value of the personnel to be assigned. These two state variables will directly participate in the evaluation calculation of the quality of the completed tasks, so that the trained task allocation model can more accurately describe the operation behavior of the personnel, thereby objectively and comprehensively evaluating the task completion quality of the relevant business personnel;

[0066] The evaluation parameters of the personnel to be assigned obtained by the task assignment method of the present invention are used as the evaluation results of the task completion quality, and the comprehensive evaluation value, time-consuming evaluation value and number of evaluation values ​​are included in the indicators for enterprise task assignment. Tasks are assigned based on the evaluation parameters, which can realize the scientific, refined and standardized assignment of tasks by the enterprise, and give priority to assigning tasks to business personnel with higher comprehensive evaluation values. Tasks can be assigned to business personnel with high completion quality and fast completion speed, which avoids the backlog of tasks and the task processing quality not meeting the requirements, and is also conducive to obtaining targeted business personnel training programs.

[0067] Combine the following Figure 3 The task allocation method of the present invention is described, in which the task allocation model includes a timeliness processing layer, an accuracy processing layer and an evaluation layer.

[0068] Among them, the timeliness processing layer is used to perform timeliness processing on the actual operation time based on the sample operation time completed by the sample personnel to complete the task, the second time consumption evaluation value and the first weight; the accuracy processing layer is used to perform accuracy processing on the number of cycles based on the sample number of cycles completed by the sample personnel to complete the task, the second number evaluation value and the second weight; the evaluation layer is used to evaluate the timeliness value obtained from the timeliness processing layer and the accuracy value obtained from the accuracy processing layer based on the first weight, the second weight, the third weight and the fourth weight.

[0069] Combine the following Figure 4 The task assignment method of the present invention is described, and the evaluation layer specifically includes a comprehensive evaluation layer, a time-consuming evaluation processing layer and a number evaluation processing layer, wherein the comprehensive evaluation layer is used to perform weighted processing on the timeliness value obtained by timeliness processing from the timeliness processing layer and the accuracy value obtained by accuracy processing from the accuracy processing layer based on the first weight and the second weight; the time-consuming evaluation processing layer is used to process the timeliness value obtained from the timeliness processing layer based on the third weight; and the number evaluation processing layer is used to process the accuracy value obtained from the accuracy processing layer based on the fourth weight.

[0070] Depend on Figure 3 and Figure 4 As shown in the figure, in this method, the time evaluation value and the number of evaluation values ​​participate in the calculation of the comprehensive evaluation value in the form of weight coefficients, and the task completion quality of the assigned personnel is evaluated from the two dimensions of timeliness and accuracy, which can obtain the work efficiency and operation accuracy data of the relevant salespersons in a more comprehensive and objective manner. The design of calculating the timeliness value and accuracy value is flexible, and the appropriate function expression form can be selected according to the nature of the task. The weight coefficient of the evaluation result can also be adjusted to make the method have better usability and adaptability.

[0071] In this method, since it is also based on the second time evaluation value and second number evaluation value of the task last completed by the person to be assigned, the change rules of the discrete time function time evaluation value and number evaluation value of the person to be assigned are established, and the change rate of the timeliness value and the change rate of the accuracy value are used as independent variables respectively, so that it can reflect the improvement or regression of the person to be assigned on the time axis.

[0072] The operation behavior of business personnel is dynamic and has a certain degree of randomness, and the quality of task completion has the characteristics of continuity. Therefore, the task allocation model does not evaluate a certain operation behavior of a business personnel in isolation, but evaluates, analyzes and saves it in the order of the occurrence of task execution. Specifically, the comprehensive evaluation value of the kth business personnel in the i-th human-computer interaction system is It is a discrete time function. Obtaining the historical evaluation records of the personnel to be assigned helps to analyze the working conditions of the personnel and put forward specific improvement suggestions. This is exactly the actual and real purpose of the task assignment method of the present invention.

[0073] In this method, the timeliness processing layer specifically includes:

[0074] Multiply the second time-consuming evaluation value by its corresponding fifth weight to obtain the first weight corresponding to the completion of the task;

[0075] The timeliness value is obtained through the timeliness function, and the independent variable of the timeliness function is the value of the actual operation time minus the sample operation time;

[0076] The accuracy processing layer specifically includes:

[0077] Multiply the second numerical evaluation value by its corresponding sixth weight to obtain the second weight corresponding to the completion of the task;

[0078] The accuracy value is obtained by using an accuracy function, and the independent variable of the accuracy function is the value of the number of cycles minus the number of sample cycles;

[0079] The comprehensive evaluation layer specifically includes:

[0080] A1) When the task is a single task:

[0081] Multiply the first weight by the timeliness value to obtain a timeliness evaluation value;

[0082] Multiply the second weight by the accuracy value to obtain an accuracy evaluation value;

[0083] The sum of the timeliness evaluation value and the accuracy evaluation value is divided by the sum of the first weight and the second weight to obtain the comprehensive evaluation value corresponding to the completion of the task.

[0084] A2) When the task is multiple tasks:

[0085] The comprehensive evaluation value of each task is obtained by the method A1) above, and then all the obtained comprehensive evaluation values ​​are averaged to obtain the comprehensive evaluation values ​​corresponding to the multiple tasks.

[0086] The time-consuming evaluation processing layer specifically includes:

[0087] B1) When the task is a single task:

[0088] Subtract the timeliness values ​​corresponding to the completion of the current task and the previous completion of the current task, and divide the subtraction of the two timeliness values ​​by the timeliness value of the current task to obtain the change rate of the timeliness value of the single task;

[0089] The change rate of the timeliness value of a single task is multiplied by the third weight, and then added to the second time-consuming evaluation value to obtain the first time-consuming evaluation value. The calculation formula for the first time-consuming evaluation value is:

[0090]

[0091] Among them, γ is the third weight, γ>0, when season When (n-1) = 0, let

[0092] The change rate of the timeliness value of a single task is:

[0093]

[0094] B2) When the task is multiple tasks:

[0095] Obtain the timeliness values ​​corresponding to the completion of the current task and the last completion of the current task for each task through the method of B1). Then, add up the timeliness values ​​of the current task completion of each task and take the average value to obtain the timeliness values ​​corresponding to the completion of the current task for multiple tasks; add up the timeliness values ​​of the last completion of the current task for each task and take the average value to obtain the timeliness values ​​corresponding to the last completion of the current task for multiple tasks;

[0096] Next, subtract the timeliness values ​​corresponding to the completion of the current task and the previous completion of the current task from each other, and divide the subtracted value of the two timeliness values ​​by the timeliness values ​​of the current task to obtain the change rate of the timeliness (mean) value of the multiple tasks;

[0097] The change rate of the timeliness (average) values ​​of multiple tasks is multiplied by the third weight, and then added to the second time consumption evaluation value to obtain the first time consumption evaluation value. At this time, the calculation formula of the first time consumption evaluation value is:

[0098]

[0099] Among them, γ is the third weight, γ>0, when season When (n-1) = 0, let

[0100] The timeliness (average) of completing multiple tasks is:

[0101]

[0102] The timeliness (average) value of the last completed task for multiple tasks is:

[0103]

[0104] The change rate of the (mean) value of timeliness of multiple tasks is:

[0105]

[0106] The frequency evaluation processing layer specifically includes:

[0107] C1) When the task is a single task:

[0108] Subtract the accuracy values ​​corresponding to the current task completion and the previous task completion of the single task, and divide the difference between the two accuracy values ​​by the accuracy value of the current task completion of the single task to obtain the change rate of the accuracy value of the single task;

[0109] The rate of change of the accuracy value of a single task is multiplied by the fourth weight, and then added to the second numerical evaluation value to obtain the first numerical evaluation value.

[0110]

[0111] Among them, δ is the fourth weight, δ>0, when season When (n-1) = 0, let

[0112] The rate of change of accuracy value of a single task is:

[0113]

[0114] C2) When the task is multiple tasks:

[0115] Obtain the accuracy values ​​corresponding to the completion of each task and the last completion of each task through the above C1). Then, add up the accuracy values ​​of each task when it is completed and take the average value to obtain the accuracy values ​​corresponding to the completion of multiple tasks; add up the accuracy values ​​of each task when it is completed and take the average value to obtain the accuracy values ​​corresponding to the last completion of multiple tasks;

[0116] Next, subtract the accuracy values ​​corresponding to the completion of the current task and the previous completion of the current task from each other, and divide the subtraction of the two timeliness values ​​by the accuracy values ​​of the current task to obtain the change rate of the accuracy (mean) values ​​of the multiple tasks;

[0117] The change rate of the accuracy (average) values ​​of multiple tasks is multiplied by the third weight, and then added to the second time-consuming evaluation value to obtain the first time-consuming evaluation value. At this time, the calculation formula of the first time-consuming evaluation value is:

[0118]

[0119] Among them, δ is the fourth weight, δ>0, when season When (N-1) = 0, let

[0120] The accuracy (average) of multiple tasks is:

[0121]

[0122] The accuracy (average) of the last completed task for multiple tasks is:

[0123]

[0124] The change rate of the accuracy (mean) of multiple tasks is:

[0125]

[0126] Therefore, the evaluation parameters are input into the task allocation model to obtain the evaluation parameters output by the task allocation model, which specifically includes the following steps:

[0127] The evaluation parameters are input into the timeliness processing layer to obtain the timeliness value corresponding to the completion of the current task output by the timeliness processing layer; the evaluation parameters are input into the accuracy processing layer to obtain the accuracy value corresponding to the completion of the current task output by the accuracy processing layer; the timeliness value and the accuracy value are input into the evaluation layer to obtain the comprehensive evaluation value, the first time consumption evaluation value and the first number evaluation value corresponding to the completion of the current task output by the evaluation layer.

[0128] The timeliness value and accuracy value are input into the comprehensive evaluation layer to obtain the comprehensive evaluation value corresponding to the completion of the task output by the comprehensive evaluation layer, which specifically includes the following steps:

[0129] The timeliness value and accuracy value are input into the comprehensive evaluation layer of the evaluation layer to obtain the comprehensive evaluation value corresponding to the completion of the current task output by the comprehensive evaluation layer; the timeliness value is input into the time consumption evaluation processing layer of the evaluation layer to obtain the first time consumption evaluation value corresponding to the completion of the current task output by the time consumption evaluation processing layer; the accuracy value is input into the number evaluation processing layer of the evaluation layer to obtain the first number evaluation value corresponding to the completion of the current task output by the number evaluation processing layer.

[0130] The task allocation model is trained through the following steps:

[0131] Obtain the sample operation time and sample cycle times of the sample personnel completing the task, as well as the second time evaluation value and the second number evaluation value of the personnel to be assigned; determine the first weight, the second weight, the third weight, the fourth weight, the fifth weight and the sixth weight; use the sample operation time, the sample cycle times, the second time evaluation value and the second number evaluation value as input data for training, adopt a machine learning training method, and obtain a task allocation model for generating evaluation parameters for the personnel to be assigned.

[0132] The input data of the task allocation model of the kth business person comes from the i-th human-computer interaction system and the task management platform, including the current task of the business person, that is, the nth completion of the kth business person in the i-th human-computer interaction system. The actual operation time, number of cycles, and other information after the task is completed, and the last time the business person completed the task, which is the (n-1) time completed by the kth business person in the i-th human-computer interaction system, recorded and saved by the human-computer interaction system and the task management platform. The second time evaluation value after the task Second evaluation value wait.

[0133] Specifically, the input data of the task allocation model of the kth business person in the i-th human-computer interaction system is:

[0134]

[0135] Where, Id represents the port identifier of the kth business person in the i-th human-computer interaction system; No is the task number; for dimensional column vector, each element is the k-th business person's n-th completion of the i-th human-computer interaction system The actual operation time of the task; for dimensional column vector, the evaluation basis, each element is the number of times a skilled business person, i.e., a sample person, completes the first The sample operation time of each task; for dimensional column vector, each element is the k-th business person's n-th completion of the i-th human-computer interaction system The number of cycles for a task; for dimensional column vector, the basis for evaluation, each element is the number of times a skilled salesperson, i.e., a sample person, completes the first The number of sample cycles for a task;

[0136] for dimensional timeliness vector function;

[0137] for dimensional accuracy vector function;

[0138] for dimensional diagonal matrix, the weight matrix of the timeliness vector function;

[0139] for dimensional diagonal matrix, the weight matrix of the accuracy vector function;

[0140] The kth business person in the i-th human-computer interaction system completes the task for the (N-1)th time The second time-consuming evaluation value after the task; The kth business person in the i-th human-computer interaction system completes the task for the (n-1)th time The second evaluation value after the task.

[0141] Evaluation criteria for the quality of completion of the above tasks Both the timeliness vector function and the accuracy vector function can be set in advance.

[0142] The output of the task allocation model is the task completed by the kth business person in the i-th human-computer interaction system for the nth time The comprehensive evaluation value, the first time evaluation value and the first number evaluation value after the task can be understood as the latest calculated values ​​of the comprehensive evaluation value, time evaluation value and number evaluation value of the business personnel, as well as other necessary information. Specifically, the output data of the task allocation model of the kth business personnel in the i-th human-computer interaction system is:

[0143]

[0144] Where, Id is the kth salesperson port identifier in the i-th human-computer interaction system; D is the nth execution date of the i-th human-computer interaction system; The kth business person in the i-th human-computer interaction system completes the nth The comprehensive evaluation value of the task; The kth business person in the i-th human-computer interaction system completes the nth The first time-consuming evaluation value after the task; The kth business person in the i-th human-computer interaction system completes the nth The first evaluation value after the task.

[0145] In the i-th human-computer interaction system, the skilled salesperson, i.e. the sample person, completes the Tasks Time required As an evaluation benchmark, the actual time taken by the kth business person to complete the same task is The kth salesperson completes The timeliness function of a task is defined as:

[0146]

[0147] Among them, k1, k2 and k3 are all coefficients greater than 0, and within the t value range, the function value In the interval t≥0, as the t value increases, The value decreases; in the interval t<0, as the absolute value of t increases, Increase. It can be set to other forms of functions as needed. Timeliness function The higher the value, the more efficient the salesperson is in completing tasks.

[0148] Accuracy refers to the accuracy of a certain manual task completed by a salesperson in a human-computer interaction system. In a human-computer interaction system, after a manually completed form or other related results are forwarded to the system through the interactive interface between the system and the salesperson, the process will automatically verify the manually completed results. If the verification fails, the system will forward the results to the salesperson from the same interactive interface until the operation results completed by the salesperson pass the verification. That is, when the salesperson's operation is inaccurate, the manual task will be circulated multiple times between the salesperson and the system.

[0149] In the i-th human-computer interaction system, the skilled salesperson, i.e. the sample person, completes the Tasks The number of cycles required As the evaluation benchmark, the number of cycles that the kth business person completes the same task is The kth salesperson completes Tasks The accuracy function is:

[0150]

[0151] Among them, k4 is a coefficient greater than 0. In the r value range, in the interval r≥0, the function value The larger the r value, The smaller the value; in the R<0 range, it means that the actual number of cycles of the salesperson's operation is less than the benchmark The value is increasing. Accuracy function The higher the value, the higher the quality of the salesperson's task completion. Accuracy function It can be set to other functions as needed.

[0152] In this method, skilled salespeople, i.e., sample personnel, complete the first Tasks Time required and the number of cycles As a reference indicator for evaluating the completion of manual tasks by the assigned personnel, its determination should be objective. It can be the test result of the actual operation of skilled salesmen, or it can be obtained through statistical methods.

[0153] If a statistical method is used, the first The manual task is decomposed into several basic operation actions, and the time required for a skilled salesperson to complete each basic action is set. The sum of the time required for all basic actions of a manual task is the time required for a skilled salesperson to complete the first Time required for manual tasks

[0154] This method takes into account the difficulty of quantifying human cognitive factors and non-cognitive factors. Therefore, in some possible embodiments, the weighting coefficient in the comprehensive evaluation value is designed as the second evaluation value of the business personnel. and the second time-consuming evaluation value function, so as to achieve the purpose that the task allocation model can more accurately describe the human operation behavior.

[0155] The timeliness of a business person's task completion is related to his or her work effort. Therefore, suppose that the kth business person in the i-th human-computer interaction system completes the task nth time The weight matrix of the timeliness function of a task is the second time evaluation value of completing the task for the (n-1)th time The function is:

[0156]

[0157] in, is the first weight, is the fifth weight, If (n-1)<0, then set n=0.

[0158] The accuracy of the business personnel in completing the task is related to their professional background and work experience. Therefore, suppose that the kth business personnel in the i-th human-computer interaction system completes the task nth time The weight matrix of the accuracy function of a task is the second evaluation value of the (n-1)th completion of the task The function is

[0159]

[0160] in, is the second weight, is the sixth weight, If (n-1)<0, then set n=0.

[0161] Evaluation method for the kth business person to complete a single task: based on the timeliness function and accuracy function The weighted sum of Tasks The completion quality, the corresponding comprehensive evaluation value is

[0162]

[0163] in, and are the weight coefficients of the timeliness function and the accuracy function, respectively, corresponding to the first weight and the second weight.

[0164] Comprehensive evaluation method for the kth business person completing multiple tasks for the nth time in the i-th human-computer interaction system: In the i-th human-computer interaction system, assuming that the total number of tasks completed by the kth business person for the nth time is Item, satisfy The timeliness function and accuracy function for completing each task can be set separately as needed, and the comprehensive evaluation value is:

[0165]

[0166] In this case, the comprehensive evaluation value It is the nth time that the kth business person completes the task in the i-th human-computer interaction system. The mean of the comprehensive evaluation values ​​corresponding to each task.

[0167] The task allocation device provided by the present invention is described below. The task allocation device described below and the task allocation method described above can be referred to each other.

[0168] Combine the following Figure 5 The task allocation device of the present invention is described. The device can be applied to the field of enterprise management. It should be noted that, depending on the specific application situation, the device can also be applied to other human-computer interaction related fields. The device specifically includes:

[0169] The acquisition module 100 is used to acquire the evaluation parameters of the personnel to be assigned. In the device, the evaluation parameters include the actual operation time and the number of cycles, the number of cycles is the number of rounds used to pass the inspection when the task is completed, and the actual operation time is the sum of the actual operation time corresponding to each round when completing the task.

[0170] It should be noted that when a task is completed, it can be a single task or multiple tasks.

[0171] The evaluation module 200 is used to input the evaluation parameters into the trained task allocation model to obtain the evaluation parameters output by the task allocation model. In the device, the evaluation parameters include the comprehensive evaluation value of the personnel to be assigned, the first time-consuming evaluation value and the first number evaluation value. The first time-consuming evaluation value is the time-consuming evaluation value of the personnel to be assigned to complete the current task, and the first number evaluation value is the number of times the personnel to be assigned to complete the current task. The first time-consuming evaluation value is obtained based on the timeliness value, and the first number evaluation value is obtained based on the accuracy value. The timeliness value is inversely proportional to the actual operation time, and the accuracy value is inversely proportional to the number of cycles.

[0172] The task allocation model provided in the device is trained based on the sample operation time and sample cycle times of the sample personnel completing the task, as well as the second time evaluation value and second number evaluation value of the personnel to be assigned. The second time evaluation value is the time evaluation value of the last completion of the task by the personnel to be assigned, and the second number evaluation value is the number evaluation value of the last completion of the task by the personnel to be assigned.

[0173] The allocation module 300 is used to allocate tasks based on evaluation parameters. For example, the higher the value of the evaluation parameter corresponding to the person to be assigned, the higher the priority of the person to be assigned in task allocation, that is, the higher the value of the evaluation parameter, the higher the priority of assigning the task to the person to be assigned.

[0174] The task allocation device of the present invention reflects the influence of cognitive factors and non-cognitive factors on the operation behavior of the personnel to be assigned through two state variables, namely, the time evaluation value and the number evaluation value of the personnel to be assigned, so that the trained task allocation model can more accurately describe the operation behavior of the personnel, thereby objectively and comprehensively evaluating the task completion quality of the relevant business personnel;

[0175] The evaluation parameters of the personnel to be assigned obtained by the task assignment device of the present invention are used as the evaluation results of the task completion quality, and the comprehensive evaluation value, time-consuming evaluation value and number of evaluation values ​​are included in the indicators for enterprise task assignment. Tasks are assigned based on the evaluation parameters, which can realize the scientific, refined and standardized assignment of tasks by the enterprise, and give priority to assigning tasks to business personnel with higher comprehensive evaluation values. Tasks can be assigned to business personnel with high completion quality and fast completion speed, which avoids the backlog of tasks and the task processing quality not meeting the requirements, and is also conducive to obtaining targeted business personnel training programs.

[0176] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the task allocation method, which includes the following steps:

[0177] S100, obtaining evaluation parameters of the personnel to be assigned; wherein the evaluation parameters include actual operation time and number of cycles, the number of cycles being the number of rounds used to pass the inspection when the task is completed, and the actual operation time being the sum of the actual operation time corresponding to each round when the task is completed;

[0178] S200, input the evaluation parameters into the task allocation model to obtain the evaluation parameters output by the task allocation model; wherein the evaluation parameters include the comprehensive evaluation value of the personnel to be assigned, the first time evaluation value and the first number evaluation value, the first time evaluation value is the time evaluation value of the completion of the current task, the first number evaluation value is the number evaluation value of the completion of the current task, the first time evaluation value is obtained based on the timeliness value, and the first number evaluation value is obtained based on the accuracy value; the task allocation model is trained based on the sample operation time and sample cycle number of the sample personnel completing the current task, as well as the second time evaluation value and the second number evaluation value of the personnel to be assigned, the second time evaluation value is the time evaluation value of the last completion of the current task, the second number evaluation value is the number evaluation value of the last completion of the current task, the timeliness value is inversely proportional to the actual operation time, and the accuracy value is inversely proportional to the number of cycles;

[0179] S300. Allocate tasks based on the evaluation parameters; wherein, the higher the value of the evaluation parameter corresponding to the person to be assigned is, the higher the priority of the person to be assigned is in task allocation.

[0180] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0181] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the task allocation method provided by the above methods is implemented, and the method comprises the following steps:

[0182] S100, obtaining evaluation parameters of the personnel to be assigned; wherein the evaluation parameters include actual operation time and number of cycles, the number of cycles being the number of rounds used to pass the inspection when the task is completed, and the actual operation time being the sum of the actual operation time corresponding to each round when the task is completed;

[0183] S200, input the evaluation parameters into the task allocation model to obtain the evaluation parameters output by the task allocation model; wherein the evaluation parameters include the comprehensive evaluation value of the personnel to be assigned, the first time evaluation value and the first number evaluation value, the first time evaluation value is the time evaluation value of the completion of the current task, the first number evaluation value is the number evaluation value of the completion of the current task, the first time evaluation value is obtained based on the timeliness value, and the first number evaluation value is obtained based on the accuracy value; the task allocation model is trained based on the sample operation time and sample cycle number of the sample personnel completing the current task, as well as the second time evaluation value and the second number evaluation value of the personnel to be assigned, the second time evaluation value is the time evaluation value of the last completion of the current task, the second number evaluation value is the number evaluation value of the last completion of the current task, the timeliness value is inversely proportional to the actual operation time, and the accuracy value is inversely proportional to the number of cycles;

[0184] S300. Allocate tasks based on the evaluation parameters; wherein, the higher the value of the evaluation parameter corresponding to the person to be assigned is, the higher the priority of the person to be assigned is in task allocation.

[0185] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0186] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0187] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A task allocation method, characterized in that: The following steps are involved: Obtaining evaluation parameters of the personnel to be assigned; wherein the evaluation parameters include actual operation time and number of cycles, the number of cycles being the number of rounds used to pass the inspection when the task is completed, and the actual operation time being the sum of the actual operation time corresponding to each round when the task is completed; The evaluation parameters are input into the task allocation model to obtain the evaluation parameters output by the task allocation model; wherein the evaluation parameters include a comprehensive evaluation value of the personnel to be assigned, a first time-consuming evaluation value and a first number evaluation value, the first time-consuming evaluation value is the time-consuming evaluation value of the task to be completed, the first number evaluation value is the number evaluation value of the task to be completed, the first time-consuming evaluation value is obtained based on the timeliness value, and the first number evaluation value is obtained based on the accuracy value; the task allocation model is trained based on the sample operation time and sample cycle number of the sample personnel completing the task at that time, as well as the second time-consuming evaluation value and the second number evaluation value of the personnel to be assigned, the second time-consuming evaluation value is the time-consuming evaluation value of the last completion of the task, the second number evaluation value is the number evaluation value of the last completion of the task, the timeliness value is inversely proportional to the actual operation time, and the accuracy value is inversely proportional to the number of cycles; Based on the evaluation parameters, tasks are assigned; wherein, the higher the value of the evaluation parameter corresponding to the person to be assigned is, the higher the priority of the person to be assigned is in task assignment.

2. The task allocation method according to claim 1, characterized in that: The task allocation model includes a timeliness processing layer, an accuracy processing layer and an evaluation layer; The timeliness processing layer is used to perform timeliness processing on the actual operation time based on the sample operation time and the second time consumption evaluation value to obtain the timeliness value; The accuracy processing layer is used to perform accuracy processing on the number of cycles based on the sample number of cycles and the second number evaluation value to obtain the accuracy value; The evaluation layer is used to evaluate the timeliness value obtained by the timeliness processing layer and the accuracy value obtained by the accuracy processing layer to obtain the evaluation parameter.

3. The task allocation method according to claim 2, characterized in that: The evaluation layer includes a comprehensive evaluation layer, a time-consuming evaluation processing layer and a number of evaluation processing layer; The comprehensive evaluation layer is used to perform weighted processing on the timeliness value obtained by the timeliness processing layer and the accuracy value obtained by the accuracy processing layer to obtain the comprehensive evaluation value; The time consumption evaluation processing layer is used to process the timeliness value obtained from the timeliness processing layer based on the third weight to obtain the first time consumption evaluation value; The number evaluation processing layer is used to process the accuracy value obtained from the accuracy processing layer based on a fourth weight to obtain the first number evaluation value.

4. The task allocation method according to claim 3, characterized in that: The step of inputting the evaluation parameters into the task allocation model to obtain the evaluation parameters output by the task allocation model specifically includes the following steps: Input the evaluation parameter into the timeliness processing layer to obtain the timeliness value corresponding to the completion of the current task output by the timeliness processing layer; Inputting the evaluation parameter into the accuracy processing layer to obtain the accuracy value corresponding to the task completion output by the accuracy processing layer; The timeliness value and the accuracy value are input into the evaluation layer to obtain the comprehensive evaluation value, the first time-consuming evaluation value and the first number of evaluation values ​​corresponding to the completion of the current task output by the evaluation layer.

5. The task allocation method according to claim 4, characterized in that: The step of inputting the timeliness value and the accuracy value into the comprehensive evaluation layer to obtain the comprehensive evaluation value corresponding to the task completion output by the comprehensive evaluation layer specifically includes the following steps: Inputting the timeliness value and the accuracy value into the comprehensive evaluation layer of the evaluation layer to obtain the comprehensive evaluation value corresponding to the task completion output by the comprehensive evaluation layer; Input the timeliness value into the time-consuming evaluation processing layer of the evaluation layer to obtain the first time-consuming evaluation value corresponding to the task completion output by the time-consuming evaluation processing layer; The accuracy value is input into the times evaluation processing layer of the evaluation layer to obtain the first times evaluation value corresponding to the current task completion output by the times evaluation processing layer.

6. The task allocation method according to claim 1, characterized in that: The task allocation model is trained by the following steps: Obtaining the sample operation time and the sample cycle times completed by the sample personnel for the current task, as well as the second time evaluation value and the second cycle evaluation value of the personnel to be assigned; Determine a first weight, a second weight, a third weight, a fourth weight, a fifth weight, and a sixth weight, wherein the first weight and the fifth weight correspond to functions of the second time-consuming evaluation value, the second weight and the sixth weight correspond to functions of the second numerical evaluation value, the third weight corresponds to the timeliness value obtained from the timeliness processing layer, and the fourth weight corresponds to the accuracy value obtained from the accuracy processing layer; The sample operation time, the sample cycle number, the second time evaluation value and the second number evaluation value are used as input data for training, and a machine learning training method is adopted to obtain the task allocation model for generating the evaluation parameters of the personnel to be assigned.

7. A task allocation device, characterized in that: include: An acquisition module is used to acquire the evaluation parameters of the personnel to be assigned; wherein the evaluation parameters include actual operation time and number of cycles, the number of cycles is the number of rounds used to pass the inspection when the task is completed, and the actual operation time is the sum of the actual operation time corresponding to each round when the task is completed; An evaluation module is used to input the evaluation parameters into a task allocation model to obtain evaluation parameters output by the task allocation model; wherein the evaluation parameters include a comprehensive evaluation value of the personnel to be assigned, a first time-consuming evaluation value and a first number evaluation value, wherein the first time-consuming evaluation value is a time-consuming evaluation value for completing the current task, and the first number evaluation value is a number evaluation value for completing the current task, wherein the first time-consuming evaluation value is obtained based on a timeliness value, and wherein the first number evaluation value is obtained based on an accuracy value; the task allocation model is obtained by training based on the sample operation time and sample cycle number of the sample personnel completing the current task, as well as the second time-consuming evaluation value and the second number evaluation value of the personnel to be assigned, wherein the second time-consuming evaluation value is a time-consuming evaluation value for the last completion of the current task, and the second number evaluation value is a number evaluation value for the last completion of the current task, wherein the timeliness value is inversely proportional to the actual operation time, and wherein the accuracy value is inversely proportional to the number of cycles; The allocation module is used to allocate tasks based on the evaluation parameters; wherein, the higher the value of the evaluation parameter corresponding to the person to be allocated, the higher the priority of the person to be allocated in task allocation.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the task allocation method according to any one of claims 1 to 6 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the task allocation method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the task allocation method according to any one of claims 1 to 6 are implemented.

Images