Task scheduling method and device, equipment, storage medium and program product

Abstract

The invention provides a task scheduling method and device, equipment, a storage medium and a product, and relates to the field of financial science and technology or other related fields. The method comprises the steps of obtaining at least one target task to be scheduled and candidate resources to be scheduled; obtaining first attribute information of candidate resources, second attribute information of the target task and pheromone concentration used by last task scheduling from a database; based on first attribute information of candidate resources, second attribute information of the target tasks and pheromone concentration used by last task scheduling, a target resource scheduling scheme of the at least one target task is obtained by utilizing a swarm intelligence optimization algorithm; and scheduling the target task based on the target resource scheduling scheme, and updating the pheromone concentration corresponding to the target resource scheduling scheme to a database. According to the method, the task scheduling accuracy and efficiency are improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other related fields, and in particular to a task scheduling method, electronic device, storage medium and program product. Background Art

[0002] In the banking system, there are a large number of tasks that need to be assigned to staff (such as bank tellers, account managers, etc.) for processing. These tasks may include customer account inquiries, deposit withdrawals, loan approvals, etc. With the continuous expansion of banking business and the increase in the number of customers, the efficiency and accuracy of task scheduling have become important issues that need to be solved urgently. At present, traditional bank task scheduling methods often rely on simple rules or manual experience to assign tasks. However, due to the lack of comprehensive consideration of tasks and staff, unreasonable task allocation may occur. Alternatively, manual allocation is easily affected by subjective factors and may not accurately judge the staff's proficiency in different tasks and the importance of the tasks, resulting in unreasonable allocation. Therefore, there are problems with low accuracy and efficiency in task scheduling in the current banking system.

[0003] Therefore, how to improve the accuracy and efficiency of task scheduling is an urgent problem to be solved. Summary of the invention

[0004] The present application provides a task scheduling method, device, equipment, storage medium and product to solve the technical problems of low accuracy and efficiency of task scheduling in current banking systems.

[0005] In a first aspect, the present application provides a task scheduling method, comprising:

[0006] Obtain at least one target task to be scheduled and candidate resources to be scheduled;

[0007] Acquire the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling from the database; the pheromone concentration is related to the proficiency of the candidate resource in the task;

[0008] Based on the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling, a target resource scheduling scheme of the at least one target task is obtained by using a swarm intelligence optimization algorithm; the swarm intelligence optimization algorithm searches for the target scheduling scheme according to the pheromone concentration;

[0009] The target task is scheduled based on the target resource scheduling scheme, and the pheromone concentration corresponding to the target resource scheduling scheme is updated in a database.

[0010] In a second aspect, the present application provides a task scheduling device, comprising:

[0011] A first acquisition module, used to acquire at least one target task to be scheduled and candidate resources to be scheduled;

[0012] A second acquisition module is used to acquire the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling from the database; the pheromone concentration is related to the proficiency of the candidate resource in the task;

[0013] A processing module, configured to obtain a target resource scheduling solution for the at least one target task by using a swarm intelligence optimization algorithm based on the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling; the swarm intelligence optimization algorithm searches for the target scheduling solution according to the pheromone concentration;

[0014] The control module is used to schedule the target task based on the target resource scheduling scheme, and update the pheromone concentration corresponding to the target resource scheduling scheme into the database.

[0015] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0016] The memory stores computer-executable instructions;

[0017] The processor executes the computer-executable instructions stored in the memory to implement the method as described in the first aspect.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0019] In a fifth aspect, the present application provides a computer program product, which, when executed by a processor, is used to implement the method as described in the first aspect.

[0020] The task scheduling method, apparatus, equipment, storage medium and product provided by the present application obtain at least one target task to be scheduled and candidate resources to be scheduled, obtain first attribute information of the candidate resources, second attribute information of the target task, and the pheromone concentration used for the last task scheduling from a database, and based on the first attribute information of the candidate resources, the second attribute information of the target task, and the pheromone concentration used for the last task scheduling, use a swarm intelligence optimization algorithm to obtain a target resource scheduling plan for at least one target task, schedule the target task based on the target resource scheduling plan, and update the pheromone concentration corresponding to the target resource scheduling plan to the database, thereby improving the accuracy and efficiency of task scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0022] Figure 1 A schematic diagram of a task scheduling scenario provided in an embodiment of the present application;

[0023] Figure 2 A flowchart of a task scheduling method provided in an embodiment of the present application;

[0024] Figure 3 A flowchart of another task scheduling method provided in an embodiment of the present application;

[0025] Figure 4 A flowchart of another task scheduling method provided in an embodiment of the present application;

[0026] Figure 5 A schematic diagram of the structure of a task scheduling device provided in an embodiment of the present application;

[0027] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0028] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0030] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0031] In addition, this application involves conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and using artificial intelligence technology to make automated decisions, and making technical solutions that have a significant impact on personal rights and interests based on the results of automated decisions. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered.

[0032] It should be noted that the task scheduling method, apparatus, equipment, storage medium and product provided in this application can be used in the field of financial technology or other related fields, and can also be used in any field other than the field of financial technology or other related fields. The application field of the task scheduling method, apparatus, equipment, storage medium and product in this application is not limited.

[0033] At present, the traditional bank task scheduling method relies on simple rules or manual experience to allocate tasks. However, due to the lack of comprehensive consideration of tasks and staff, or the fact that manual allocation is easily affected by subjective factors and cannot accurately judge the staff's proficiency in different tasks and the importance of tasks, it may lead to unreasonable task allocation, resulting in low accuracy and efficiency of task scheduling.

[0034] Therefore, how to improve the accuracy and efficiency of task scheduling is an urgent problem to be solved.

[0035] In view of this, the present application provides a task scheduling method, which iterates at least one target task to be scheduled and candidate resources to be scheduled through a swarm intelligence optimization algorithm, and obtains a target resource scheduling plan for at least one target task based on the first attribute information of the candidate resources, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling, so as to schedule the target task based on the target resource scheduling plan, thereby improving the accuracy and efficiency of task scheduling.

[0036] Figure 1 A schematic diagram of a task scheduling scenario provided in an embodiment of the present application. Figure 1 As shown, taking task scheduling as dispatching tasks in a banking system to appropriate staff as an example, this scenario includes: a task scheduling device and multiple staff terminal devices.

[0037] The task scheduling device is a terminal device with data processing functions, such as a computer, mobile phone or other computing device with computing functions, or a server of a banking system. The task scheduling device may be deployed with software or program code for running the task scheduling method, and the tasks in the banking system are scheduled through the software or program code. The staff terminal device may be, for example, a computer, mobile phone, tablet computer or other electronic device.

[0038] The task scheduling device schedules the tasks in the bank system and determines which staff terminal devices to schedule the tasks to, so that the staff corresponding to the staff terminal device can process the tasks. Alternatively, the task scheduling device can allocate the tasks in the bank system to the staff terminal devices of each staff member according to the specific situation of each staff member.

[0039] The execution subject of the task scheduling provided in this application can be Figure 1 The task scheduling device mentioned in the above may be a processing chip of the task scheduling device, or may be software or program code for implementing the task scheduling method. When the execution subject is the task scheduling device, the task scheduling device may be equipped with software or program code for running the task scheduling method, and the tasks in the banking system may be scheduled through the software or program code.

[0040] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0041] Figure 2 A flowchart of a task scheduling method provided in an embodiment of the present application is shown below. Figure 2As shown, the method may include:

[0042] S201. Obtain at least one target task to be scheduled and candidate resources to be scheduled.

[0043] The target task is a task that needs to be scheduled and processed by resources. In a banking system, the target task may be, for example, a transfer processing task, an account information query task, a loan approval task, etc. Candidate resources are resources that can be used to process the target task, such as computing resources and storage resources in a server, or human resources such as staff in a bank, or equipment specifically used to process specific business, etc. This application is introduced by taking human resources as an example of candidate resources.

[0044] One possible implementation method is to maintain a task queue. Newly generated tasks will enter this queue and wait for scheduling. These tasks are target tasks. At the same time, the human resources in the banking system can be classified and managed, and resources that are idle or can be assigned tasks can be marked as candidate resources. For example, in the banking system, there are a batch of new loan application tasks (target tasks) that need to be processed, and there are several staff members in the system who are idle (candidate resources). Information about these tasks and resources can be obtained.

[0045] Another possible implementation method is to select tasks to be scheduled as target tasks according to preset task types. Candidate resources can be selected according to the current workload of the resources, and resources with a workload below a certain threshold are considered candidate resources.

[0046] S202: Acquire the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling from the database.

[0047] Among them, the pheromone concentration is related to the candidate resource's proficiency in the task.

[0048] The first attribute information is information related to the characteristics of the candidate resource itself. For human resources, the first attribute information may include staff identification (such as employee number, employee name, etc.), staff skills, staff business type proficiency, staff work efficiency, etc. The second attribute information is information related to the characteristics of the target task itself. Such as the task identification of the target task (such as task code), the skills required for the task, the urgency of the task, the model required for the task, etc.

[0049] The pheromone concentration represents the proficiency of the candidate resource in the task. For example, if a worker is more proficient in the model required for the target task, the corresponding pheromone concentration will be higher when the worker handles the target task.

[0050] Optionally, the business type proficiency of the staff can be determined, for example, based on the historical processing results of different task models. For example, three staff members with the shortest average processing time in the historical processing results are selected from a certain task model. The task model is the model that these three staff members are good at, which represents the business type proficiency of the staff. The work efficiency of the staff can be obtained, for example, based on historical task processing data. For example, the average daily task processing time of all staff members is used as a benchmark, and the ratio of the average time for staff members to process tasks to the benchmark is used as the work efficiency. The smaller the value, the higher the work efficiency. The urgency of the task can be, for example, from high to low, namely, extremely urgent, urgent, general, and not urgent. Each task is general by default. The urgency of the task can be set by the system administrator through the visual interface. The higher the urgency of the task, the more it tends to be assigned to staff with high work efficiency and good at the task model corresponding to the task.

[0051] Specifically, you can directly query the relevant tables in the database to obtain the first attribute information of the candidate resources, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling. For the first attribute information of the candidate resources, there is a special resource information table in the database, and the corresponding attribute information is queried through the unique identifier of the resource (such as the staff identifier). The second attribute information of the target task is stored in the task information table, and is also queried through the unique identifier of the task. The pheromone concentration used in the last task scheduling is stored in a special pheromone concentration table, which is queried with the resource-task combination as the index.

[0052] S203, based on the first attribute information of the candidate resources, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling, using a swarm intelligence optimization algorithm to obtain a target resource scheduling solution for at least one target task.

[0053] Among them, the swarm intelligence optimization algorithm searches for the target scheduling solution based on the pheromone concentration. The swarm intelligence optimization algorithm is an algorithm that finds the optimal solution by simulating the behavior of a group of organisms (such as ant colonies, bird flocks, etc.). For example, it can be an ant colony optimization algorithm, a particle swarm optimization algorithm, etc., and this application does not limit this. This application will later introduce the ant colony optimization algorithm as an example of a swarm intelligence optimization algorithm. Under the ant colony optimization algorithm, task scheduling can be regarded as the way ants choose paths according to the pheromone concentration in the process of searching for food to determine which resource the task is assigned to.

[0054] Specifically, the target task and candidate resources can be regarded as nodes in the ant colony optimization algorithm, and the task allocation behavior can be regarded as ants in the ant colony optimization algorithm. The ants search between the target task and candidate resource nodes according to the information concentration, and give priority to paths with high information concentration as task allocation behavior. That is, when the ants are at the target task node, according to the information concentration corresponding to the path between the target task node and each candidate resource node, the candidate resource nodes corresponding to the path with higher information concentration are given priority as the resources for allocating the target task. In multiple iterations of the ant colony optimization algorithm, the ants select paths according to the pheromone concentration and heuristic information. After completing a round of iterations, the pheromone concentration is updated according to the path conditions of all ants. After multiple rounds of iterations, a scheduling plan that meets expectations is obtained.

[0055] For example, in a banking system, for account information query tasks (target tasks) and staff members (candidate resources), the initial pheromone concentration and heuristic information are determined based on the first attribute information and the second attribute information. In the iterative process, the way ants select paths is simulated, and the staff members are asked to select and process query tasks. The pheromone concentration is updated based on the results of each selection, and the optimal task allocation solution is finally obtained.

[0056] S204: Schedule the target task based on the target resource scheduling scheme, and update the pheromone concentration corresponding to the target resource scheduling scheme into the database.

[0057] According to the task-resource correspondence in the target resource scheduling scheme, the task is directly sent to the corresponding resource for processing. For the update of pheromone concentration, the new pheromone concentration is calculated according to the actual execution of the task on the resource, and then the pheromone concentration table in the database is updated. For example, if the target resource scheduling scheme is to assign a transfer task to a specific staff member, the relevant information of the transfer task is sent to the work terminal of the staff member. If the staff member completes the transfer task quickly and accurately, the new pheromone concentration is calculated based on factors such as the transfer amount and completion time, and the pheromone concentration corresponding to the staff member-transfer task combination in the database is updated.

[0058] Optionally, the target resource scheduling scheme can be verified first to ensure that the availability of resources and other conditions are met before scheduling. For the update of pheromone concentration, a batch update method can be used to uniformly calculate and update the pheromone concentration to the database at a certain time interval or after a batch of tasks are scheduled. For example, for the scheduling scheme of loan approval tasks, you can first check whether the staff corresponding to the loan approval task in the target resource scheduling scheme is online and can receive new tasks. After all loan approval tasks are scheduled within a period of time, the new pheromone concentration is calculated based on the overall execution of this batch of tasks at the staff (such as average approval time, pass rate, etc.), and the pheromone concentration corresponding to the staff-loan approval task combination in the database is updated in batches.

[0059] The method provided in the embodiment of the present application obtains at least one target task to be scheduled and candidate resources to be scheduled, obtains first attribute information of the candidate resources, second attribute information of the target task, and the pheromone concentration used for the last task scheduling from a database, obtains a target resource scheduling plan for at least one target task based on the first attribute information of the candidate resources, the second attribute information of the target task, and the pheromone concentration used for the last task scheduling, and utilizes a swarm intelligence optimization algorithm, schedules the target task based on the target resource scheduling plan, and updates the pheromone concentration corresponding to the target resource scheduling plan to the database, thereby improving the accuracy and efficiency of task scheduling.

[0060] Next, a detailed description is given of how to obtain a target resource scheduling solution for at least one target task using a swarm intelligence optimization algorithm based on the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the previous task scheduling in the aforementioned step S203. Figure 3 A flowchart of another task scheduling method provided in an embodiment of the present application. Figure 3 As shown, the aforementioned step S203 may include:

[0061] S301. In iteration cycle t, based on the pheromone concentration in iteration cycle t and a first parameter, determine the probability of allocating a target task to a candidate resource.

[0062] The pheromone concentration is used to characterize the candidate resource's proficiency in the task, and the first parameter characterizes the urgency of the target task. For example, the first parameter can be represented by the priority of the task (such as 1-5, with 1 being the most urgent), or the remaining time of the task from the specified completion time, etc.

[0063] Specifically, target tasks, candidate resources, the current candidate resource is the node in the ant colony optimization model , the current target task is node For example, the probability of allocating the current target task to the current candidate resource can be expressed by the following formula (1):

[0064] (1)

[0065] in, The probability of assigning the current target task to the current candidate resource, For Node and nodes The pheromone concentration on the path between , that is, the proficiency of the current candidate resource in the current target task. The better the candidate resource is at a certain task, the higher the probability that the candidate resource will be assigned to the target task. For example, it can be initialized to 5 and continuously updated in t model iterations. For Node and nodes The heuristic information on the path between represents the urgency of the current target task. The higher the urgency of the task, the more likely it is to be given priority to candidate resources who are better at this type of task. is an important indicator of pheromone concentration, It is an indicator of the importance of heuristic information. The higher the value, the more likely the ant is to choose this direction. and It can be set according to actual needs. For example, in task scheduling that depends more on the matching degree between candidate resources and target tasks, Set it larger. is a set of candidate resources, The representation will Target tasks are assigned to candidate resources.

[0066] S302: Determine at least one candidate resource scheduling scheme for at least one target task in iteration period t based on the allocation probability.

[0067] In this step, the selection can be sorted according to the allocation probability. The candidate resources are sorted from large to small according to their allocation probability to the target task. For each target task, the candidate resource with the highest allocation probability is selected for allocation. If the candidate resource has been assigned enough tasks (reaching its processing capacity limit or other restrictions), the next candidate resource with a higher allocation probability is selected. For example, for loan approval tasks and staff, the staff are sorted according to their allocation probability to loan approval tasks, and the loan approval tasks are sequentially assigned to the staff who are ranked first and meet the conditions, and the scheduling plan of loan approval tasks-staff is obtained.

[0068] S303: Determine whether an iteration end condition is met based on at least one candidate resource scheduling solution.

[0069] One possible implementation method is to set a fixed upper limit of the number of iterations as the iteration end condition. The number of current iterations is recorded, and when the number of iterations reaches the preset upper limit, the iteration end condition is considered to be met.

[0070] Another possible implementation method can be determined based on the convergence of the objective function. The server calculates the objective function value corresponding to each candidate resource scheduling solution (such as comprehensive indicators such as resource utilization, average task processing time, etc.). If the change in the objective function value in several consecutive iterations is less than a set threshold (indicating convergence), it is considered that the iteration end condition is met.

[0071] If the convergence of the objective function is used to determine whether the iteration end condition is met, it can be achieved through the following steps:

[0072] S3031. Based on currently available candidate resources among the candidate resources and the priority of the target task, the candidate resource scheduling scheme is modified to obtain at least one preliminary resource scheduling scheme.

[0073] The currently available candidate resources refer to the candidate resources that can be assigned to perform the target task at the current moment, such as currently idle workers or workers whose workloads are not yet saturated within the target task completion deadline, etc. The priority of the target task represents the attribute of the importance or urgency of the task.

[0074] A possible implementation method is to sort the tasks in descending order according to the priority of the target task. Then, traverse the candidate resource scheduling scheme corresponding to each target task. For each task, if the corresponding candidate resource is a currently available candidate resource, it will not be processed; if not, find a resource among the currently available candidate resources that can handle the task and has a relatively high processing efficiency (which can be judged based on data such as the average time for historical processing of such tasks), and reallocate the task to this resource, thereby obtaining a preliminary resource scheduling scheme. For example, assume that there are three staff members (staff member A, staff member B, and staff member C), and there are currently three target tasks: large transfer (high priority), account query (medium priority), and credit card application (low priority). The initial candidate resource scheduling scheme is that large transfer is assigned to staff member A (but staff member A is currently processing other businesses and is unavailable), account query is assigned to staff member B, and credit card application is assigned to staff member C. In this implementation method, tasks are first sorted by priority. For large-value transfer business, since staff A is unavailable, it is found that staff B has sufficient capacity to handle large-value transfer while handling account query business (assuming that the historical average time for staff B to handle large-value transfer is shorter), so the large-value transfer business is reallocated to staff B. The resources corresponding to the account query and credit card application business remain unchanged, so the preliminary resource scheduling plan is obtained.

[0075] Another possible implementation is to sort the scheduling results of the target task based on the currently available candidate resources in the candidate resources and the priority of the target task. For tasks with a priority higher than the preset priority, the candidate resources corresponding to the task are adjusted based on the remaining available time ratio of the candidate resources corresponding to the scheduling result, and the priority and remaining available time ratio of the tasks to be scheduled corresponding to other candidate resources, to obtain a preliminary resource scheduling plan.

[0076] In this implementation, the preset priority is used to distinguish target tasks of different importance or urgency. For example, tasks involving large transactions can be preset as high priority, and tasks such as ordinary account inquiries can be set as lower priority. The preset priority can be set according to actual needs, and this application does not limit this. The remaining available time ratio refers to the proportion of the remaining time available for processing new tasks to the total available time of the candidate resource considering the existing task arrangement. For example, assuming that the staff works 8 hours (480 minutes) a day and has arranged 3 hours (180 minutes) of tasks, then the remaining available time is 300 minutes, and the remaining available time ratio is about 62.5%. All target tasks and their corresponding candidate resource scheduling results can be obtained first, and they are sorted from high to low according to the priority of the target tasks. For tasks with a priority higher than the preset priority, check the remaining available time ratio of the candidate resources corresponding to their scheduling results. If the ratio is lower than the first preset threshold (for example, 30%), traverse other candidate resources. For each other candidate resource, check the priority of the corresponding task to be scheduled and the remaining available time ratio. Select a candidate resource whose priority of the task to be scheduled is lower than the current task and whose remaining available time ratio is higher than a second preset threshold (e.g., 50%). Reallocate the current task to the selected candidate resource, thereby obtaining a preliminary resource scheduling solution.

[0077] S3032. Determine the objective function of the preliminary resource scheduling scheme for iteration cycle t based on the estimated execution time of the preliminary resource scheduling scheme corresponding to iteration cycle t, the difference between the estimated execution time of iteration cycle t and the estimated execution time of iteration cycle t-1, and the resource utilization rate corresponding to the preliminary resource scheduling scheme for iteration cycle t.

[0078] Among them, corresponding weights can be set for the estimated execution time corresponding to the preliminary resource scheduling scheme in iteration cycle t, the difference between the estimated execution time of iteration cycle t and the estimated execution time of iteration cycle t-1, and the resource utilization rate corresponding to the preliminary resource scheduling scheme in iteration cycle t, so as to determine the objective function of the preliminary resource scheduling scheme in iteration cycle t. Among them, these weights can be set according to different actual needs to represent different emphasis directions on resource scheduling.

[0079] Exemplarily, the objective function of the preliminary resource scheduling solution of iteration period t can be expressed by the following formula (2):

[0080] (2)

[0081] in, It is the initial resource scheduling plan in the iteration cycle The corresponding estimated execution time, i.e. the iteration cycle The total estimated time required for all target tasks in for The weight of . is the difference between the estimated execution time of iteration cycle t and the estimated execution time of iteration cycle t-1, for The weight of . is the resource utilization rate corresponding to the preliminary resource scheduling solution of iteration period t, for By calculating the value of the objective function, it can be determined whether to use the preliminary resource scheduling solution as the target resource scheduling solution.

[0082] It should be understood that the above is only an exemplary introduction to an objective function for ease of understanding. The specific setting of the objective function can be determined according to actual needs, and this application does not impose any restrictions on this.

[0083] S3033. Based on the objective function of the preliminary resource scheduling solution of iteration period t, determine whether to use the preliminary resource scheduling solution as the target resource scheduling solution.

[0084] According to the value of the objective function, it is determined whether the objective function reaches the target threshold that meets the resource scheduling expectations. If so, the preliminary resource scheduling solution is used as the target resource scheduling solution. Continuing with the above formula (2) as an example, the smaller the value of the objective function, the better the scheduling strategy that characterizes the preliminary resource scheduling solution. By setting a target threshold that meets the resource scheduling expectations, when the value of the objective function is less than or equal to the target threshold, it is determined that the preliminary resource scheduling solution is used as the target resource scheduling solution.

[0085] If not, and the iteration period t does not reach the preset threshold, the pheromone concentration of the iteration period t is updated to obtain the pheromone concentration of the iteration period t+1, and the process returns to step S301.

[0086] The preset threshold is set according to actual needs and is used to limit the maximum number of iterations of the swarm intelligence optimization algorithm. When the iteration cycle t reaches the preset threshold, even if the iteration end condition is not met, the iteration needs to be stopped to avoid the problem of infinite iteration of the swarm intelligence optimization algorithm.

[0087] According to the pheromone volatilization rate and the total amount of pheromone deposited by all ants on a certain path within iteration period t, the pheromone concentration of the path within iteration period t can be updated to obtain the pheromone concentration of iteration period t+1.

[0088] The method provided in the embodiment of the present application determines the allocation probability of the target task for the candidate resource based on the pheromone concentration in iteration period t and the first parameter in iteration period t, and determines at least one candidate resource scheduling scheme for at least one target task in iteration period t based on the allocation probability. Determine whether the iteration end condition is met based on at least one candidate resource scheduling scheme. If not and the iteration period t does not reach the preset threshold, the pheromone concentration in iteration period t is updated to obtain the pheromone concentration in iteration period t+1, and the allocation probability of the target task for the candidate resource in iteration period t+1 is obtained until the number of iterations reaches the preset threshold or the iteration end condition is met to obtain the resource scheduling scheme, thereby improving the accuracy of resource scheduling and the completion efficiency of the target task, and reducing the resource cost and time cost of the target task.

[0089] Next, the scheduling results of the target task are sorted based on the currently available candidate resources in the candidate resources and the priority of the target task. For tasks with a priority higher than the preset priority, the candidate resources corresponding to the task are adjusted based on the remaining available time ratio of the candidate resources corresponding to the scheduling result, as well as the priority and remaining available time ratio of the tasks to be scheduled corresponding to other candidate resources, to obtain a preliminary resource scheduling plan. This is an example of how to adjust the candidate resources corresponding to the task based on the remaining available time ratio of the candidate resources corresponding to the scheduling result, as well as the priority and remaining available time ratio of the tasks to be scheduled corresponding to other candidate resources, to obtain a preliminary resource scheduling plan. Figure 4 A flowchart of another task scheduling method provided in an embodiment of the present application is shown below. Figure 4 As shown, the implementation may include:

[0090] S401. When the remaining available time ratio of the candidate resource corresponding to the scheduling result is less than the first preset threshold, search from other candidate resources for target other candidate resources that have no tasks with a priority higher than the preset priority and whose remaining available time ratio is higher than the second preset threshold.

[0091] When the proportion of the remaining available time of the candidate resources corresponding to the scheduling result is less than the first preset threshold, it indicates that the remaining available time of the candidate resources corresponding to the scheduling result is insufficient, that is, the remaining available time of the staff corresponding to the scheduling result cannot meet the target task assigned to them in the scheduling result.

[0092] At this time, it is possible to find out from other candidate resources whether there is any target other candidate resource with no task with a priority higher than the preset priority and whose remaining available time ratio is higher than the second preset threshold, so as to preferentially adjust the tasks with higher importance to the target other candidate resource for processing. The second preset threshold is a threshold set according to actual needs, and is used to identify whether there is a candidate resource with a remaining available time that meets the time required for processing the tasks with higher importance.

[0093] S402: Allocate a first proportion of the tasks to be allocated to the candidate resource to other target candidate resources to obtain a preliminary resource scheduling plan.

[0094] If there are other candidate resources for the target, the first proportion of tasks to be allocated to the candidate resource is allocated to the other candidate resources for the target, so as to increase the remaining available time of the candidate resource, and the increased remaining available time is the sum of the processing time required for the tasks of the first proportion. The first proportion can be set according to actual needs, for example, it can be a fixed number of tasks, or it can be determined according to the ratio of the remaining available time required to be increased and the total available time of the candidate resource.

[0095] By allocating the first proportion of tasks to be allocated to the candidate resource to the target other candidate resources, the remaining available time of the candidate resource is increased to be able to accept the corresponding tasks allocated to the candidate resource in the scheduling result. Then, according to the corresponding tasks allocated to the candidate resource in the scheduling result and the first proportion of tasks to be allocated to the target other candidate resources, the original scheduling result is adjusted accordingly to obtain a preliminary resource scheduling plan.

[0096] The method provided in the embodiment of the present application searches for target other candidate resources from other candidate resources that have no tasks with a priority higher than a preset priority and a remaining available time ratio higher than a second preset threshold value when the remaining available time ratio of the candidate resources corresponding to the scheduling result is less than a first preset threshold value. The tasks of the first proportion to be allocated to the candidate resources are allocated to the target other candidate resources to obtain a preliminary resource scheduling plan, so that the preliminary resource scheduling plan can be correctly matched with the remaining available time of each candidate resource through secondary adjustment, thereby improving the accuracy of task scheduling and reducing the probability of unreasonable task scheduling.

[0097] Next, the content of how to update the pheromone concentration of the generation period t described in the above embodiment is introduced in detail.

[0098] Based on the total amount of pheromone deposited on all target tasks in iteration period t, and / or the estimated execution time of the target task, the pheromone concentration of iteration period t is updated.

[0099] Specifically, after the iteration cycle t is completed, the pheromone is updated according to the resource scheduling scheme generated in the iteration cycle t to obtain the pheromone concentration required for the iteration cycle t+1, and to provide an optimized path for the task scheduling of the iteration cycle t+1. When the pheromone concentration increases, the probability of the ant choosing the path also increases. Exemplarily, the pheromone update can be performed by the following formula (3):

[0100] (3)

[0101] in, is the pheromone volatilization rate, which can be set according to actual needs, for example, it can be set to 0.8, so that the ant colony optimization algorithm can perform more path exploration. is the number of ants on the path in iteration cycle t The total amount of pheromones deposited on the is the path within iteration period t The pheromone concentration on.

[0102] Furthermore, the estimated execution time of the target task can be used to calculate the number of ants on the path. The total amount of pheromone deposited on , the specific calculation method can refer to the following formula (4):

[0103] (4)

[0104] in, It is a constant set according to actual needs, for example, it can be a constant between 0.2-1, and can be set to 0.5. For Ants The total processing time of all task targets within iteration period t.

[0105] Optionally, after scheduling the target task based on the target resource scheduling scheme, the method provided in the embodiment of the present application may also include updating the actual processing time of the target task and / or updating the remaining available time of the candidate resources, so as to further improve the accuracy of the actual time for processing the target task and / or the remaining available time of the candidate resources according to the actual task processing situation, and further improve the accuracy of resource scheduling according to the actual time of the target task and / or the remaining available time of the candidate resources that are more in line with the actual situation.

[0106] Optionally, the swarm intelligence optimization algorithm may also be updated according to the actual duration of the target task processed by the resources corresponding to the target task, and / or the user's update instructions.

[0107] For example, the first attribute information (e.g., the work efficiency of the staff, the proficiency of the staff in the business type, etc.), the second attribute information (e.g., the urgency of the target task to be scheduled, the skills required for the task, etc.), the objective function weight information, etc. used by the swarm intelligence optimization algorithm in the subsequent iteration cycle can be updated according to the actual duration of the target task processed by the resources corresponding to the target task, so as to update the parameters of the swarm intelligence optimization algorithm, thereby improving the accuracy of the resource scheduling scheme output by the swarm intelligence optimization algorithm. Alternatively, the manually assigned target task can be added to the swarm intelligence optimization algorithm according to the user's update instructions, and in the case of including the manually assigned target task, the swarm intelligence optimization algorithm is used to perform resource scheduling on the tasks other than the manually assigned target task, so as to achieve accurate and efficient resource scheduling of all tasks to be assigned in the case of including the manually assigned task.

[0108] Figure 5 A schematic diagram of the structure of a task scheduling device provided in an embodiment of the present application. Figure 5 As shown, the task scheduling device may include: a first acquisition module 11 , a second acquisition module 12 , a processing module 13 , and a control module 14 .

[0109] The first acquisition module 11 is used to acquire at least one target task to be scheduled and candidate resources to be scheduled.

[0110] The second acquisition module 12 is used to acquire the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling from the database. The pheromone concentration is related to the proficiency of the candidate resource in the task.

[0111] The processing module 13 is used to obtain a target resource scheduling solution for at least one target task using a swarm intelligence optimization algorithm based on the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling. The swarm intelligence optimization algorithm searches for the target scheduling solution according to the pheromone concentration.

[0112] The control module 14 is used to schedule the target task based on the target resource scheduling scheme, and update the pheromone concentration corresponding to the target resource scheduling scheme into the database.

[0113] Optionally, the processing module 13 is specifically used to: A. In iteration cycle t, based on the pheromone concentration in iteration cycle t and the first parameter, determine the allocation probability of allocating the target task to the candidate resource. The pheromone concentration is used to characterize the proficiency of the candidate resource in the task, and the first parameter characterizes the task urgency of the target task. B. Based on the allocation probability, determine at least one candidate resource scheduling scheme for at least one target task in iteration cycle t. C. Based on at least one candidate resource scheduling scheme, determine whether the iteration end condition is met. D. If not, and the iteration cycle t does not reach the preset threshold, update the pheromone concentration in iteration cycle t to obtain the pheromone concentration in iteration cycle t+1, and return to execute step A.

[0114] Optionally, the processing module 13 is specifically used to: modify the candidate resource scheduling scheme based on the currently available candidate resources in the candidate resources and the priority of the target task to obtain at least one preliminary resource scheduling scheme. Determine the objective function of the preliminary resource scheduling scheme for iteration period t based on the estimated execution time corresponding to the preliminary resource scheduling scheme in iteration period t, the difference between the estimated execution time of iteration period t and the estimated execution time of iteration period t-1, and the resource utilization rate corresponding to the preliminary resource scheduling scheme for iteration period t. Based on the objective function of the preliminary resource scheduling scheme for iteration period t, determine whether to use the preliminary resource scheduling scheme as the target resource scheduling scheme.

[0115] Optionally, the candidate resource scheduling scheme includes the scheduling result of the target task. Optionally, the processing module 13 is specifically used to sort the scheduling results of the target task based on the currently available candidate resources in the candidate resources and the priority of the target task. For tasks with a priority higher than a preset priority, based on the remaining available time ratio of the candidate resources corresponding to the scheduling result, and the priority and remaining available time ratio of the tasks to be scheduled corresponding to other candidate resources, the candidate resources corresponding to the task are adjusted to obtain a preliminary resource scheduling scheme.

[0116] Optionally, the processing module 13 is specifically used to: when the remaining available time ratio of the candidate resource corresponding to the scheduling result is less than the first preset threshold, search for other target candidate resources from other candidate resources that have no tasks with a priority higher than the preset priority and whose remaining available time ratio is higher than the second preset threshold. Allocate the first proportion of tasks to be allocated to the candidate resource to the target other candidate resources to obtain a preliminary resource scheduling plan.

[0117] Optionally, the processing module 13 is specifically configured to update the pheromone concentration of iteration period t based on the total amount of pheromones deposited on all target tasks in iteration period t and / or the estimated execution time of the target tasks.

[0118] Optionally, after scheduling the target task based on the target resource scheduling scheme, the processing module 13 is also used to: update the actual duration of the target task processed by the resources corresponding to the target task after the target task is completed, and / or update the remaining available duration of the candidate resources after each task allocation is completed.

[0119] Optionally, the processing module 13 is further used to update the swarm intelligence optimization algorithm according to the actual duration of processing the target task by the resources corresponding to the target task and / or the user's update instructions.

[0120] The task scheduling device provided in the embodiment of the present application can execute the task scheduling method in the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0121] Figure 6 The structure diagram of an electronic device provided in an embodiment of the present application. The electronic device is used to execute the task scheduling method mentioned above, for example, it can be the electronic device with data processing function mentioned above. Figure 6 As shown, the electronic device 600 may include: at least one processor 601 , a memory 602 , and a communication interface 603 .

[0122] The memory 602 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer operation instructions.

[0123] The memory 602 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0124] The processor 601 is used to execute the computer-executable instructions stored in the memory 602 to implement the method described in the above method embodiment. The processor 601 may be a CPU, or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0125] The processor 601 can communicate and interact with external devices through the communication interface 603, and the external device can be, for example, the aforementioned database. In a specific implementation, if the communication interface 603, the memory 602, and the processor 601 are implemented independently, the communication interface 603, the memory 602, and the processor 601 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0126] Optionally, in a specific implementation, if the communication interface 603, the memory 602 and the processor 601 are integrated on a chip, the communication interface 603, the memory 602 and the processor 601 can communicate through an internal interface.

[0127] The present application also provides a computer-readable storage medium, which may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes. Specifically, the computer-readable storage medium stores program instructions, and the program instructions are used for the methods in the above embodiments.

[0128] The present application also provides a program product, which includes an execution instruction, which is stored in a readable storage medium. At least one processor of a computing device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the computing device implements the above-mentioned task scheduling method.

[0129] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0130] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0131] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0132] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0133] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc.

[0134] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0135] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0137] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A task scheduling method, characterized in that: The method comprises: Obtain at least one target task to be scheduled and candidate resources to be scheduled; Acquire the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling from the database; the pheromone concentration is related to the proficiency of the candidate resource in the task; Based on the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling, a target resource scheduling scheme of the at least one target task is obtained by using a swarm intelligence optimization algorithm; the swarm intelligence optimization algorithm searches for the target scheduling scheme according to the pheromone concentration; The target task is scheduled based on the target resource scheduling scheme, and the pheromone concentration corresponding to the target resource scheduling scheme is updated in a database.

2. The method according to claim 1, characterized in that: The method of obtaining a target resource scheduling scheme for at least one target task by using a swarm intelligence optimization algorithm based on the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling includes: A. In iteration cycle t, based on the pheromone concentration in iteration cycle t and a first parameter, determine the probability of allocating the target task to the candidate resource; wherein the pheromone concentration is used to characterize the proficiency of the candidate resource in the task, and the first parameter characterizes the task urgency of the target task; B. determining at least one candidate resource scheduling scheme for the at least one target task in iteration period t based on the allocation probability; C. Determine whether an iteration end condition is met based on the at least one candidate resource scheduling scheme; D. If not, and the iteration period t does not reach the preset threshold, the pheromone concentration of the iteration period t is updated to obtain the pheromone concentration of the iteration period t+1, and the process returns to step A.

3. The method according to claim 2, characterized in that The determining whether an iteration end condition is satisfied based on the at least one candidate resource scheduling scheme and the iteration period t includes: Based on currently available candidate resources among the candidate resources and the priority of the target task, the candidate resource scheduling scheme is modified to obtain at least one preliminary resource scheduling scheme; Determine the objective function of the preliminary resource scheduling scheme for iteration period t based on the estimated execution time of the preliminary resource scheduling scheme corresponding to the iteration period t, the difference between the estimated execution time of the iteration period t and the estimated execution time of the iteration period t-1, and the resource utilization rate corresponding to the preliminary resource scheduling scheme for iteration period t; Based on the objective function of the preliminary resource scheduling solution of the iteration period t, it is determined whether to use the preliminary resource scheduling solution as the target resource scheduling solution.

4. The method according to claim 3, characterized in that The candidate resource scheduling scheme includes the scheduling result of the target task; the candidate resource scheduling scheme is modified based on the currently available candidate resources among the candidate resources and the priority of the target task to obtain at least one preliminary resource scheduling scheme, including: Sorting the scheduling results of the target task based on currently available candidate resources among the candidate resources and the priority of the target task; For tasks with a priority higher than the preset priority, the candidate resources corresponding to the task are adjusted based on the proportion of the remaining available time of the candidate resources corresponding to the scheduling result, as well as the priority and the proportion of the remaining available time of the tasks to be scheduled corresponding to other candidate resources, to obtain the preliminary resource scheduling plan.

5. The method according to claim 4, characterized in that The method of adjusting the candidate resources corresponding to the task based on the remaining available time ratio of the candidate resources corresponding to the scheduling result, and the priority and remaining available time ratio of the to-be-scheduled task corresponding to other candidate resources to obtain the preliminary resource scheduling plan includes: When the remaining available time ratio of the candidate resource corresponding to the scheduling result is less than the first preset threshold, searching for other candidate resources from other candidate resources for a target resource that has no task with a priority higher than the preset priority and whose remaining available time ratio is higher than the second preset threshold; The tasks of the first proportion to be allocated to the candidate resource are allocated to other target candidate resources to obtain the preliminary resource scheduling plan.

6. The method according to claim 2, characterized in that Updating the pheromone concentration of the generation period t, comprising: The pheromone concentration of the iteration period t is updated based on the total amount of pheromones deposited on all target tasks in the iteration period t and / or the estimated execution time of the target tasks.

7. The method according to claim 1, characterized in that After scheduling the target task based on the target resource scheduling scheme, the method further includes: After the target task is completed, updating the actual duration of processing the target task by the resources corresponding to the target task; And / or, after each task assignment is completed, the remaining available time of the candidate resources is updated.

8. The method according to claim 1, characterized in that The method further comprises: The swarm intelligence optimization algorithm is updated according to the actual duration of processing the target task by the resources corresponding to the target task and / or the update instruction of the user.

9. A task scheduling device, characterized in that: The device comprises: A first acquisition module, used to acquire at least one target task to be scheduled and candidate resources to be scheduled; A second acquisition module is used to acquire the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling from the database; the pheromone concentration is related to the proficiency of the candidate resource in the task; A processing module, configured to obtain a target resource scheduling solution for the at least one target task by using a swarm intelligence optimization algorithm based on the first attribute information of the candidate resource, the second attribute information of the target task, and the pheromone concentration used in the last task scheduling; the swarm intelligence optimization algorithm searches for the target scheduling solution according to the pheromone concentration; The control module is used to schedule the target task based on the target resource scheduling scheme, and update the pheromone concentration corresponding to the target resource scheduling scheme into the database.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images