A task scheduling method and system based on spectral clustering and auction algorithm

Abstract

This invention relates to the field of task scheduling technology, and discloses a task scheduling method and system based on spectral clustering and auction algorithms. The method includes: acquiring registered resource information and task information to be scheduled; performing spectral clustering on the resource information and task information respectively to form resource group sets and task group sets; based on the auction algorithm, performing inter-group matching and task allocation on the resource group sets and task group sets to generate an initial allocation scheme; performing global balance adjustment on the initial allocation scheme to obtain a final allocation scheme, and performing task scheduling according to the final allocation scheme. This invention solves the problems of complex process scheduling easily getting trapped in local optima and insufficient dynamic response and cross-departmental collaboration in large-scale continuous task input scenarios, improving the global balance of resource allocation, real-time accuracy of scheduling, and business continuity assurance capabilities.

Description

Technical Field

[0001] This invention relates to the field of task scheduling technology, and in particular to a task scheduling method and system based on spectral clustering and auction algorithms. Background Technology

[0002] As domestic enterprises deepen their digital transformation, while achieving phased digital results, their need for improved business efficiency and continuous cost optimization is becoming increasingly urgent. Against this backdrop, business process optimization and reengineering, along with the construction of data monitoring and analysis systems, have become crucial pathways to achieving cost reduction and efficiency improvement goals. However, deep digital transformation presents new challenges to internal task allocation and scheduling: First, process complexity has significantly increased, with multi-system and multi-tool collaboration leading to escalating task scheduling difficulties; second, data dependence has greatly increased, with the real-time nature and accuracy of task allocation highly dependent on data quality; third, cross-departmental collaboration requirements have risen, necessitating comprehensive consideration of multi-dimensional collaborative factors in scheduling decisions; and fourth, the need for dynamic human resource allocation is urgent, with changes in job structures caused by digitalization placing higher demands on flexible scheduling. To address these issues, in addition to strengthening data governance and personnel training, building intelligent scheduling systems and collaborative platforms has become a key solution, especially in scenarios with large-scale resources and continuous task input, where achieving globally reasonable scheduling becomes the core of efficiency assurance.

[0003] To address enterprise task scheduling needs, existing technologies have proposed various solutions. For example, the patent CN202010066812.1, "Task Scheduling Method, Device, and Electronic Equipment Based on Graph Database," achieves efficient allocation of a single task by constructing the shortest path between task entities and resource entities. The patent CN202111186576.8, "Multi-UAV Task Allocation and Scheduling Method, Device, System, and Storage Medium," uses an auction algorithm to allocate the decomposed sub-tasks, both improving scheduling efficiency to some extent. However, these technologies still have significant limitations: while the former is suitable for single-task scheduling, in scenarios with large-scale resources and continuous task input, the shortest path calculation is prone to getting trapped in local optima, making it difficult to achieve globally optimal resource allocation within a limited time window; while the latter completes sub-task allocation through an auction mechanism, it lacks global optimality analysis and is mainly aimed at static task scenarios, unable to effectively cope with continuously increasing task flows.

[0004] Currently, the focus of digital transformation is concentrated on leading enterprises, whose business scale and resource allocation are characterized by large scale and high dynamism. Traditional scheduling algorithms based on static and local conditions are no longer sufficient to meet their dual requirements of dynamism and global optimization. Therefore, there is an urgent need to provide a technical solution to address these issues. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a task scheduling method and system based on spectral clustering and auction algorithms.

[0006] Firstly, this invention provides a task scheduling method based on spectral clustering and auction algorithms, the technical solution of which is as follows: Obtain registered resource information and task information to be scheduled; Spectral clustering is performed on the resource information and the task information respectively to form resource group sets and task group sets; Based on the auction algorithm, inter-group matching and task allocation are performed on the resource group set and the task group set to generate an initial allocation scheme; The initial allocation scheme is globally balanced to obtain the final allocation scheme, and task scheduling is performed according to the final allocation scheme.

[0007] The beneficial effects of the task scheduling method based on spectral clustering and auction algorithm of the present invention are as follows: The method of this invention forms a group set by performing spectral clustering on resource and task information, completes inter-group matching and task allocation based on the auction algorithm, and combines global balance adjustment. It solves the problems of complex process scheduling easily getting trapped in local optima and insufficient dynamic response and cross-departmental collaboration in large-scale continuous task input scenarios, and improves the global balance of resource allocation, real-time accuracy of scheduling and business continuity assurance capabilities.

[0008] Based on the above scheme, the task scheduling method of the present invention based on spectral clustering and auction algorithm can be further improved as follows.

[0009] In one alternative approach, the step of obtaining the registered resource information and the task information to be scheduled includes: Receive newly arrived or changed resource information, and complete the creation of resource nodes and the registration of resource information based on the resource information; Receive newly arrived or changed task information, and complete the creation of task nodes and the registration of task information based on the task information.

[0010] The beneficial effects of adopting the above optional methods are: to further realize the dynamic registration mechanism of resource and task information, to improve the ability of the scheduling process to perceive real-time changes by receiving newly arrived or changed resource and task information and creating corresponding nodes, and to provide an accurate data foundation for subsequent clustering and allocation.

[0011] In one optional approach, the step of performing spectral clustering on the resource information and the task information respectively to form a resource group set and a task group set includes: Based on the resource attributes in the resource information, a first similarity matrix representing the similarity between resources is constructed, and the first similarity matrix is ​​graph-segmented to form the resource group set; Based on the task attributes in the task information, a second similarity matrix representing the similarity between tasks is constructed, and the second similarity matrix is ​​graph-segmented to form the task group set.

[0012] The advantages of adopting the above-mentioned optional approach are as follows: by constructing a similarity matrix between resource and task information and performing graph segmentation, scientific grouping based on multi-dimensional attributes can be achieved, enhancing the rationality and matching degree of resource and task grouping, and providing high-quality input data for the auction algorithm.

[0013] In one alternative approach, the step of performing inter-group matching and task allocation on the resource group set and the task group set based on an auction algorithm to generate an initial allocation scheme includes: Select a resource representative group from the resource group set, and select a task representative group from the task group set; Based on the auction algorithm, bidding and matching are performed between the resource representative group and the task representative group to determine the matching relationship between the representative groups; Based on the matching relationship between the representative groups, the overall inter-group association range between the resource group set and the task group set is generated by mapping. Based on the overall inter-group association range, tasks are allocated between resource groups and task groups with association relationships to generate the initial allocation scheme.

[0014] The advantages of adopting the above optional method are: further determining the overall inter-group association range through auction matching between representative groups, allocating tasks between associated resource groups and task groups, reducing the computational complexity of large-scale matching, and improving the execution speed of the auction algorithm in inter-group scheduling.

[0015] In one alternative approach, the step of performing a global balance adjustment on the initial allocation scheme to obtain the final allocation scheme includes: Evaluate the allocation efficiency corresponding to the initial allocation scheme; When the allocation efficiency is lower than a preset threshold, the combination of resource attributes used to form the resource group set or the combination of task attributes used to form the task group set is adjusted. The resource information is re-clustered according to the adjusted resource attribute combination to form an updated resource group set, and / or the task information is re-clustered according to the adjusted task attribute combination to form an updated task group set. Based on the updated resource group set and / or the updated task group set, the steps of inter-group matching and task allocation are re-executed to generate the final allocation scheme.

[0016] The beneficial effects of adopting the above-mentioned optional methods are as follows: by further evaluating the allocation benefits and dynamically adjusting the combination of resource or task attributes, the spectral clustering and auction matching process is re-executed, the initial allocation scheme is optimized, avoiding getting trapped in local optima, and improving the global balance of resource allocation.

[0017] In one alternative approach, the step of scheduling tasks according to the final allocation scheme includes: Based on the final allocation scheme, determine the task groups associated with the resource groups in the resource group set; Within the resource group, tasks in the task group are allocated according to a preset secondary scheduling strategy; Schedule resources within the resource group to execute the assigned tasks and receive feedback on the task execution results; Based on the feedback of the task execution results, update the attribute status of the corresponding resource in the resource information.

[0018] The advantages of adopting the above-mentioned optional methods are: further refining task allocation by using a secondary scheduling strategy within the resource group, updating resource attribute status by combining the feedback of task execution results, forming a scheduling closed loop, and enhancing the adaptability of the scheduling process to the actual execution situation.

[0019] In one alternative approach, the secondary scheduling strategy includes at least one of the following: first-come, first-served strategy, shortest job first strategy, and priority scheduling strategy.

[0020] The advantages of adopting the above-mentioned optional methods are: to further provide a variety of secondary scheduling strategy options such as first-come-first-served, shortest job first, and priority scheduling, so that the task allocation within the resource group can be flexibly selected according to actual business needs, thereby improving the adaptability of scheduling.

[0021] Secondly, this invention provides a task scheduling system based on spectral clustering and auction algorithms. The technical solution of this system is as follows: The acquisition module is used to acquire registered resource information and task information to be scheduled. The clustering module is used to perform spectral clustering on the resource information and the task information respectively to form resource group sets and task group sets; The generation module is used to perform inter-group matching and task allocation on the resource group set and the task group set based on the auction algorithm, and generate an initial allocation scheme; The scheduling module is used to perform global balancing adjustments on the initial allocation scheme to obtain the final allocation scheme, and to schedule tasks according to the final allocation scheme.

[0022] The beneficial effects of the task scheduling system based on spectral clustering and auction algorithm of the present invention are as follows: The system of this invention forms group sets by performing spectral clustering on resource and task information, completes inter-group matching and task allocation based on auction algorithm, and combines global balance adjustment. It solves the problems of complex process scheduling easily getting trapped in local optima and insufficient dynamic response and cross-departmental collaboration in large-scale continuous task input scenarios, and improves the global balance of resource allocation, real-time accuracy of scheduling and business continuity assurance capabilities.

[0023] Thirdly, the technical solution of an electronic device according to the present invention is as follows: It includes a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps of the task scheduling method based on spectral clustering and auction algorithm of the present invention.

[0024] Fourthly, the technical solution of a computer-readable storage medium provided by the present invention is as follows: The computer-readable storage medium stores instructions that, when read, cause the computer-readable storage medium to perform the steps of the task scheduling method based on spectral clustering and auction algorithm of the present invention.

[0025] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0026] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a flowchart illustrating an embodiment of a task scheduling method based on spectral clustering and auction algorithm according to the present invention. Figure 2 This is a schematic diagram illustrating the overall structure of a task scheduling method based on spectral clustering and auction algorithms. Figure 3 A schematic diagram of the complete scheduling process after a new task arrives; Figure 4 This is a schematic diagram of the node structure formed in the graph database through resource registration and task registration; Figure 5This is a schematic diagram showing the effect of multiple groupings of resources and tasks after spectral clustering is completed; Figure 6 This is a schematic diagram of an embodiment of a task scheduling system based on spectral clustering and auction algorithm according to the present invention; Figure 7 This is a schematic diagram of an embodiment of an electronic device according to the present invention. Detailed Implementation

[0027] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0028] Figure 1 This diagram illustrates a flowchart of an embodiment of a task scheduling method based on spectral clustering and auction algorithms provided by the present invention. This task scheduling method can be executed by electronic devices such as terminal devices or servers. The terminal device can be any fixed or mobile terminal, such as user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, or wearable device. The server can be a single server or a server cluster consisting of multiple servers. Any electronic device can implement the task scheduling method based on spectral clustering and auction algorithms by having its processor call computer-readable instructions stored in memory. Figure 1 As shown, it includes the following steps: S1. Obtain registered resource information and task information to be scheduled.

[0029] Resource information refers to descriptive data about various entities or capabilities that can be allocated to perform tasks during the task scheduling process. For example, in a large customer service center scheduling scenario, resource information includes the customer service employee's employee ID, skills, skill level, team, and current service status. Task information refers to descriptive data about work units or business requests that need to be scheduled and executed. For example, in the same customer service center scenario, task information includes the caller ID, the type of question, the priority defined by the urgency of the question, and the customer's level.

[0030] S2. Perform spectral clustering on the resource information and the task information respectively to form a resource group set and a task group set.

[0031] Spectral clustering refers to a graph-based clustering algorithm that constructs a matrix by calculating the similarity between data points and then uses matrix eigenvalue analysis to segment the graph, thereby grouping similar data points into the same group. For example, using all customer service employees as data points, similarity is calculated based on skill combinations, and then spectral clustering is used to divide all customer service employees into multiple groups such as "English Skills Group" and "Product Expert Group." A resource group set refers to the total number of resource groups formed after processing all resource information using the spectral clustering algorithm. For example, after spectral clustering, "English Skills Group," "Product Expert Group," and "General Skills Group" are obtained, and these three groups together constitute the resource group set. A task group set refers to the total number of task groups formed after processing all task information using the spectral clustering algorithm. For example, after spectral clustering, "English Service Task Group," "Product-Related Issues Group," and "Routine Consultation Task Group" are obtained, and these three groups together constitute the task group set.

[0032] S3. Based on the auction algorithm, perform inter-group matching and task allocation on the resource group set and the task group set to generate an initial allocation scheme.

[0033] Auction algorithm refers to a coordination mechanism where participants compete by calculating and submitting virtual prices for the subject matter, and the system determines the allocation based on the price and rules. For example, after determining that the "English Skills Group" needs to handle the "English Service Task Group," customer service employees within the group calculate their "bids" for specific English tasks based on their availability and skill level, and the highest bidder wins the task. Inter-group matching refers to the process of establishing associations between resource groups and task groups; for example, the scheduling process determines the association between the "English Skills Group" and the "English Service Task Group," and between the "Product Expert Group" and the "Product-Related Issues Group." Task allocation refers to the process of assigning specific tasks to specific resources; for example, the English consultation task numbered T123 is ultimately assigned to customer service employee E005 in the "English Skills Group." The initial allocation scheme refers to the result formed after inter-group matching and preliminary task allocation based on the auction algorithm, which has not yet undergone global optimization and adjustment; for example, it is initially determined through auction that E005 will handle task T123 and S002 will handle task T456, but this scheme may not take into account the load balancing of each group.

[0034] S4. Perform a global balance adjustment on the initial allocation scheme to obtain the final allocation scheme, and perform task scheduling according to the final allocation scheme.

[0035] Global balancing adjustment refers to the process of evaluating the initial allocation plan and recalculating it by adjusting relevant parameters to achieve optimal overall system efficiency. For example, if the evaluation finds that the initial allocation leads to an overload on the "Product Expert Group," an adjustment process is triggered. The final allocation plan refers to the scheduling result output after global balancing adjustment, used for actual execution. For example, after adjustment, some basic product consultation tasks are reassigned to the "General Skills Group," resulting in a more balanced task allocation list. Task scheduling refers to the entire process of driving and managing resource execution of tasks based on the final allocation plan. For example, the scheduling system pushes the processing interface of task T123 to the customer service employee E005's work terminal and monitors its status according to the final plan.

[0036] The technical solution of this embodiment forms a group set by performing spectral clustering on resource and task information, completes inter-group matching and task allocation based on the auction algorithm, and combines global balance adjustment. This solves the problems of complex process scheduling easily getting trapped in local optima and insufficient dynamic response and cross-departmental collaboration in large-scale continuous task input scenarios, and improves the global balance of resource allocation, real-time accuracy of scheduling and business continuity assurance capabilities.

[0037] In one alternative approach, S1 specifically includes: Receive newly arrived or changed resource information, and complete the creation of resource nodes and the registration of resource information based on the resource information.

[0038] Newly arrived or changed resource information refers to resource data that is newly added or updated during system operation; for example, the information of a new employee with both English and product skills is entered; or the skill level of employee S002 is updated from "intermediate" to "advanced".

[0039] Receive newly arrived or changed task information, and complete the creation of task nodes and the registration of task information based on the task information.

[0040] Newly arrived or changed task information refers to: newly generated or changed task data to be scheduled during system operation; for example, a VIP customer submits a new urgent technical fault report; or an assigned consultation task is given higher priority because the customer has exceeded the waiting time.

[0041] Among the above optional methods, a dynamic registration mechanism for resource and task information is further implemented. By receiving newly arrived or changed resource and task information and creating corresponding nodes, the scheduling process's ability to perceive real-time changes is improved, providing an accurate data foundation for subsequent clustering and allocation.

[0042] In one alternative approach, S2 specifically includes: Based on the resource attributes in the resource information, a first similarity matrix representing the similarity between resources is constructed, and the first similarity matrix is ​​graph-segmented to form the resource group set.

[0043] Resource attributes refer to dimensions describing the characteristics and state of a resource; for example, a customer service employee's skills, skill level, department, and current status are all resource attributes. The first similarity matrix is ​​a mathematical matrix calculated based on resource attributes during spectral clustering, representing the degree of similarity between each pair of resources; for example, in a system with 50 employees, a 50x50 matrix is ​​calculated, where the value in the 2nd row and 5th column represents the similarity score between employee 2 and employee 5 in terms of skills and skill level. Graph segmentation refers to the operation of dividing the graph structure constructed based on the similarity matrix into several subgraphs to form groups during spectral clustering; for example, after constructing an employee relationship graph based on the first similarity matrix, the 50 employees can be segmented into three internally connected subgraphs, i.e., three resource groups.

[0044] Based on the task attributes in the task information, a second similarity matrix representing the similarity between tasks is constructed, and the second similarity matrix is ​​graph-segmented to form the task group set.

[0045] The task attributes refer to the dimensions that describe the characteristics and requirements of the task itself; for example, the type, priority, related products, and required language of a customer task are all task attributes. The second similarity matrix refers to a mathematical matrix calculated based on task attributes during spectral clustering of tasks, representing the degree of similarity between each pair of tasks; for example, in a system with 100 tasks to be processed, a 100-row, 100-column matrix is ​​calculated, where the value in the 10th row and 20th column represents the similarity between task 10 and task 20 in terms of type and priority.

[0046] In the above-mentioned optional methods, a similarity matrix of resource and task information is further constructed and graph segmentation is performed to achieve scientific grouping based on multi-dimensional attributes, thereby enhancing the rationality and matching degree of resource and task grouping and providing high-quality input data for the auction algorithm.

[0047] In one alternative approach, S3 specifically includes: Select a resource representative group from the resource group set, and select a task representative group from the task group set.

[0048] In this context, a resource representative group refers to a resource group selected from the set of resource groups to participate in higher-level auction matching; for example, from the sets "English Skills Group," "Product Expert Group," and "General Skills Group," the "English Skills Group" is selected as the resource representative group to participate in the auction. Similarly, a task representative group refers to a task group selected from the set of task groups to participate in higher-level auction matching; for example, from the sets "English Service Task Group," "Product Related Issues Group," and "Regular Consultation Task Group," the "English Service Task Group" is selected as the task representative group to participate in the auction.

[0049] Based on the auction algorithm, bids are placed and matched between the resource representative group and the task representative group to determine the matching relationship between the representative groups.

[0050] In this context, bidding and matching refer to the process in the auction algorithm where resource representatives calculate and submit virtual prices for task representatives based on a predetermined value assessment function, and the system determines the assignment of task representatives based on all bids. For example, the "English Skills Group" bids 90 points for the "English Service Task Group," while the "General Skills Group" bids 60 points; the "English Skills Group" wins the match due to its higher bid. The matching relationship between representative groups refers to the pairing relationship established between resource representative groups and task representative groups through the auction; for example, the matching relationship determined after the auction might be "English Skills Group" corresponding to "English Service Task Group," and "Product Expert Group" corresponding to "Product Related Issues Group."

[0051] Based on the matching relationship between the representative groups, the overall inter-group association range between the resource group set and the task group set is generated by mapping.

[0052] The overall inter-group association scope refers to all possible valid matching relationships between the resource group set and the task group set, derived from the matching relationships between representative groups. For example, based on the matching relationships between representative groups, the overall association scope is derived as follows: "English Skills Group" is associated with all English service tasks, and "Product Expert Group" is associated with all product-related issues.

[0053] Based on the overall inter-group association range, tasks are allocated between resource groups and task groups with association relationships to generate the initial allocation scheme.

[0054] In the above-mentioned optional methods, the overall inter-group association range is further determined by auction matching between representative groups, and tasks are allocated between associated resource groups and task groups to reduce the computational complexity of large-scale matching and improve the execution speed of the auction algorithm in inter-group scheduling.

[0055] In one alternative approach, the step of performing a global balance adjustment on the initial allocation scheme to obtain the final allocation scheme includes: Evaluate the allocation efficiency corresponding to the initial allocation scheme.

[0056] Among them, allocation efficiency refers to one or more comprehensive quantitative indicators used to measure the quality of the initial allocation plan; for example, allocation efficiency can be a comprehensive score calculated by weighting the expected completion time of the task, resource utilization rate, and skill matching degree.

[0057] When the allocation efficiency is lower than a preset threshold, the combination of resource attributes used to form the resource group set or the combination of task attributes used to form the task group set is adjusted.

[0058] The preset threshold refers to the critical value for allocation benefits pre-set to trigger global balance adjustments; for example, setting the threshold for the comprehensive benefit score to 80 points, and initiating adjustments if the initial allocation scheme's benefit score is below 80 points. The resource attribute combination refers to a set of resource attributes and their respective weight configurations selected during resource spectrum clustering; for example, the initial resource attribute combination might be "skill type weight 0.6, skill level weight 0.3, team weight 0.1". The task attribute combination refers to a set of task attributes and their respective weight configurations selected during task spectrum clustering; for example, the initial task attribute combination might be "task type weight 0.5, priority weight 0.3, related product weight 0.2".

[0059] The resource information is re-clustered based on the adjusted resource attribute combinations to form an updated resource group set, and / or the task information is re-clustered based on the adjusted task attribute combinations to form an updated task group set.

[0060] The adjusted resource attribute combination refers to the modification of the initial resource attribute combination during the global balancing adjustment process to optimize grouping effects; for example, adjusting the combination to "skill type weight 0.4, skill level weight 0.4, current load weight 0.2" to better emphasize level and real-time load. The updated resource group set refers to the new resource group set obtained after re-clustering using the adjusted resource attribute combination; for example, after re-clustering with the new attribute combination, the number of resource groups increases from 3 to 4, and the personnel composition of the groups changes. The adjusted task attribute combination refers to the modification of the initial task attribute combination during the global balancing adjustment process to optimize grouping effects; for example, to better distinguish urgency, the combination is adjusted to "task type weight 0.4, priority weight 0.5, customer level weight 0.1". The updated task group set refers to the new task group set obtained after re-clustering using the adjusted task attribute combination; for example, after re-clustering, the task groups become "urgent product issue group", "routine product consultation group", and "general service group".

[0061] Based on the updated resource group set and / or the updated task group set, the steps of inter-group matching and task allocation are re-executed to generate the final allocation scheme.

[0062] Among the above-mentioned optional methods, the initial allocation scheme can be optimized by further evaluating the allocation benefits and dynamically adjusting the combination of resource or task attributes, re-executing the spectral clustering and auction matching process, avoiding getting trapped in local optima, and improving the global balance of resource allocation.

[0063] In one alternative approach, the step of scheduling tasks according to the final allocation scheme includes: Based on the final allocation scheme, task groups associated with resource groups in the resource group set are determined.

[0064] In this context, a task group refers to an element in a set of task groups that contains multiple tasks with similar attributes; for example, the "English service task group" is a task group that contains all customer consultation tasks that require English services.

[0065] Within the resource group, tasks in the task group are allocated according to a preset secondary scheduling strategy.

[0066] The preset secondary scheduling strategy refers to the scheduling rules used when reassigning tasks within a resource group in a fine-grained manner. For example, within the English skills group, a "priority scheduling strategy" is used to determine the execution order of specific task queues to be assigned within the group.

[0067] The system schedules resources within the resource group to execute assigned tasks and receives feedback on the task execution results.

[0068] The feedback of task execution results refers to the information collected by the system about the execution process and results after the task is completed by the resource; for example, after customer service employee E005 completes task T123, the system records the task resolution status, actual processing time and customer satisfaction score.

[0069] Based on the feedback of the task execution results, update the attribute status of the corresponding resource in the resource information.

[0070] Among them, attribute status refers to the attribute values ​​in resource information that are dynamically updated as task execution feedback occurs; for example, the "historical average processing time" and "positive feedback rate" of customer service employee E005 will be recalculated based on the results of newly completed tasks.

[0071] Among the above-mentioned optional methods, a secondary scheduling strategy is further adopted within the resource group to refine the task allocation, and the resource attribute status is updated in combination with the feedback of task execution results to form a scheduling closed loop, thereby enhancing the adaptability of the scheduling process to the actual execution situation.

[0072] In one alternative approach, the secondary scheduling strategy includes at least one of the following: first-come, first-served strategy, shortest job first strategy, and priority scheduling strategy.

[0073] The "First-Come, First-Served" (FCFS) strategy refers to a secondary scheduling strategy that allocates tasks according to the order in which they arrive at the resource group's internal queue. For example, in the general skills group, all tasks are queued in order of entry time, and customer service staff take the earliest tasks that entered the queue. The "Shortest Job First" (SJF) strategy is a secondary scheduling strategy that prioritizes tasks with the shortest estimated processing time to be allocated to resources. For example, in the product expert group, the processing time for each task is estimated, and the task with the shortest estimated processing time is always assigned to the next available expert. The "Priority Scheduling" strategy is a secondary scheduling strategy that allocates tasks according to their priority, with higher priority tasks given priority. For example, in the English skills group, English tasks marked "urgent" are always assigned first, followed by "normal" priority tasks.

[0074] Among the above-mentioned optional methods, a variety of secondary scheduling strategy options are further provided, such as first-come-first-served, shortest job first, and priority scheduling, so that the task allocation within the resource group can be flexibly selected according to actual business needs, thereby improving the adaptability of scheduling.

[0075] like Figure 2 As shown, the technical solution of this embodiment includes three parts: resource and task registration, task scheduling, and task execution and effect evaluation. The resource and task registration part is responsible for receiving newly arrived or changed resource and task information, and completing the creation and information registration of resource nodes and task nodes in the graph database. The task scheduling part includes task batch splitting, task auction, and global task balancing, and is responsible for spectral clustering of task and resource information, inter-group matching and allocation based on auction algorithms, and global optimization and adjustment of the initial allocation scheme. The task execution and effect evaluation part handles the final execution drive of tasks, execution result feedback, task archiving, and dynamic updates of resource information.

[0076] like Figure 3As shown, the complete scheduling process after a new task arrives begins with the production process startup, completing resource and task registration to form resource and task nodes that can participate in scheduling. Subsequently, tasks and resources are batch-split, and spectral clustering is used to cluster available resources and registered tasks respectively, forming resource and task group sets. Next, the task group scheduling phase begins, where bidding and matching are performed between selected resource and task representative groups based on an auction algorithm to determine the inter-group association range and generate an initial allocation scheme. Then, global task balancing is performed to evaluate the allocation efficiency of the initial scheme. If the efficiency is lower than a preset threshold, the attribute combinations used for clustering are adjusted, and spectral clustering and auction matching are re-executed to generate a final allocation scheme. Then, tasks are executed according to the final allocation scheme, allocating specific tasks within resource groups according to a preset secondary scheduling strategy and driving resource completion. Finally, task performance is evaluated, and the attribute status in the resource information is updated based on the task execution results, providing a basis for subsequent dynamic scheduling.

[0077] like Figure 4 As shown, through the resource registration and task registration processes, a graph structure consisting of resource nodes and task nodes is formed in the graph database. Resource nodes include basic attributes such as name, skill, skill level, department, responsibility, shift, and region, while task nodes include basic information such as identifier, source, type, priority, associated customers, and associated products. The registration process simultaneously evaluates the nodes, adding information such as schedulable status, available working time period, and unit work cost to resource nodes, and adding value information and scheduling constraints to task nodes.

[0078] like Figure 5 As shown in the diagram, the spectral clustering grouping results demonstrate that resources and tasks are divided into multiple groups with high internal similarity. Resources are clustered into different resource groups based on attributes such as skill, level, department, region, and available working hours. Tasks are clustered into different task groups based on attributes such as source, type, priority, customer level, and associated products. This grouping structure provides a foundation for subsequent inter-group matching based on auction algorithms, enabling efficient scheduling at the grouping level to handle large-scale resource and task scheduling scenarios.

[0079] Figure 6 This diagram illustrates the structure of an embodiment of a task scheduling system 200 based on spectral clustering and auction algorithms provided by the present invention. Figure 6 As shown, the task scheduling system 200 based on spectral clustering and auction algorithms includes: The acquisition module 201 is used to acquire registered resource information and task information to be scheduled; Clustering module 202 is used to perform spectral clustering on the resource information and the task information respectively to form a resource group set and a task group set; The generation module 203 is used to perform inter-group matching and task allocation on the resource group set and the task group set based on the auction algorithm, and generate an initial allocation scheme. The scheduling module 204 is used to perform global balancing adjustments on the initial allocation scheme to obtain the final allocation scheme, and to perform task scheduling according to the final allocation scheme.

[0080] In one alternative embodiment, the acquisition module 201 is specifically used for: Receive newly arrived or changed resource information, and complete the creation of resource nodes and the registration of resource information based on the resource information; Receive newly arrived or changed task information, and complete the creation of task nodes and the registration of task information based on the task information.

[0081] In one alternative embodiment, the clustering module 202 is specifically used for: Based on the resource attributes in the resource information, a first similarity matrix representing the similarity between resources is constructed, and the first similarity matrix is ​​graph-segmented to form the resource group set; Based on the task attributes in the task information, a second similarity matrix representing the similarity between tasks is constructed, and the second similarity matrix is ​​graph-segmented to form the task group set.

[0082] In an alternative embodiment, the generation module 203 is specifically used for: Select a resource representative group from the resource group set, and select a task representative group from the task group set; Based on the auction algorithm, bidding and matching are performed between the resource representative group and the task representative group to determine the matching relationship between the representative groups; Based on the matching relationship between the representative groups, the overall inter-group association range between the resource group set and the task group set is generated by mapping. Based on the overall inter-group association range, tasks are allocated between resource groups and task groups with association relationships to generate the initial allocation scheme.

[0083] In an alternative embodiment, the scheduling module 204 is specifically used for: Evaluate the allocation efficiency corresponding to the initial allocation scheme; When the allocation efficiency is lower than a preset threshold, the combination of resource attributes used to form the resource group set or the combination of task attributes used to form the task group set is adjusted. The resource information is re-clustered according to the adjusted resource attribute combination to form an updated resource group set, and / or the task information is re-clustered according to the adjusted task attribute combination to form an updated task group set. Based on the updated resource group set and / or the updated task group set, the steps of inter-group matching and task allocation are re-executed to generate the final allocation scheme.

[0084] In an alternative embodiment, the scheduling module 204 is specifically used for: Based on the final allocation scheme, determine the task groups associated with the resource groups in the resource group set; Within the resource group, tasks in the task group are allocated according to a preset secondary scheduling strategy; Schedule resources within the resource group to execute the assigned tasks and receive feedback on the task execution results; Based on the feedback of the task execution results, update the attribute status of the corresponding resource in the resource information.

[0085] In one alternative approach, the secondary scheduling strategy includes at least one of the following: first-come, first-served strategy, shortest job first strategy, and priority scheduling strategy.

[0086] It should be noted that the beneficial effects of the task scheduling system 200 based on spectral clustering and auction algorithms provided in the above embodiments are the same as those of the task scheduling method based on spectral clustering and auction algorithms described above, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0087] The task scheduling system 200 based on spectral clustering and auction algorithm of the present invention can be a computer program (including program code) running on a computer device. For example, the task scheduling system 200 based on spectral clustering and auction algorithm of the present invention is an application software that can be used to execute the corresponding steps in the task scheduling method based on spectral clustering and auction algorithm of the present invention.

[0088] In some embodiments, the task scheduling system 200 based on spectral clustering and auction algorithms of the present invention can be implemented in a combination of hardware and software. As an example, the task scheduling system 200 based on spectral clustering and auction algorithms of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the task scheduling method based on spectral clustering and auction algorithms of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0089] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0090] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned task scheduling methods based on spectral clustering and auction algorithms. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the task scheduling method based on spectral clustering and auction algorithm shown in any embodiment of the present invention by calling the computer program.

[0091] In one alternative embodiment, an electronic device is provided, such as Figure 7 As shown, Figure 7 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0092] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0093] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0094] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0095] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0096] Among them, electronic devices can also be terminal devices. A terminal device can be any terminal device that can install applications and access web pages through applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0097] It should be noted that, Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0098] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-mentioned task scheduling methods based on spectral clustering and auction algorithms.

[0099] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0100] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the task scheduling method based on spectral clustering and auction algorithms described above.

[0101] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0102] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0103] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0104] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0105] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0106] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0107] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0108] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A task scheduling method based on spectral clustering and auction algorithms, characterized in that, include: Obtain registered resource information and task information to be scheduled; Spectral clustering is performed on the resource information and the task information respectively to form resource group sets and task group sets; Based on the auction algorithm, inter-group matching and task allocation are performed on the resource group set and the task group set to generate an initial allocation scheme; The initial allocation scheme is globally balanced to obtain the final allocation scheme, and task scheduling is performed according to the final allocation scheme.

2. The task scheduling method based on spectral clustering and auction algorithm according to claim 1, characterized in that, The steps of obtaining registered resource information and task information to be scheduled include: Receive newly arrived or changed resource information, and complete the creation of resource nodes and the registration of resource information based on the resource information; Receive newly arrived or changed task information, and complete the creation of task nodes and the registration of task information based on the task information.

3. The task scheduling method based on spectral clustering and auction algorithm according to claim 1, characterized in that, The step of performing spectral clustering on the resource information and the task information respectively to form resource group sets and task group sets includes: Based on the resource attributes in the resource information, a first similarity matrix representing the similarity between resources is constructed, and the first similarity matrix is ​​graph-segmented to form the resource group set; Based on the task attributes in the task information, a second similarity matrix representing the similarity between tasks is constructed, and the second similarity matrix is ​​graph-segmented to form the task group set.

4. The task scheduling method based on spectral clustering and auction algorithm according to claim 3, characterized in that, The step of performing inter-group matching and task allocation on the resource group set and the task group set based on the auction algorithm to generate an initial allocation scheme includes: Select a resource representative group from the resource group set, and select a task representative group from the task group set; Based on the auction algorithm, bidding and matching are performed between the resource representative group and the task representative group to determine the matching relationship between the representative groups; Based on the matching relationship between the representative groups, the overall inter-group association range between the resource group set and the task group set is generated by mapping. Based on the overall inter-group association range, tasks are allocated between resource groups and task groups with association relationships to generate the initial allocation scheme.

5. The task scheduling method based on spectral clustering and auction algorithm according to claim 4, characterized in that, The step of performing a global balance adjustment on the initial allocation scheme to obtain the final allocation scheme includes: Evaluate the allocation efficiency corresponding to the initial allocation scheme; When the allocation efficiency is lower than a preset threshold, the combination of resource attributes used to form the resource group set or the combination of task attributes used to form the task group set is adjusted. The resource information is re-clustered according to the adjusted resource attribute combination to form an updated resource group set, and / or the task information is re-clustered according to the adjusted task attribute combination to form an updated task group set. Based on the updated resource group set and / or the updated task group set, the steps of inter-group matching and task allocation are re-executed to generate the final allocation scheme.

6. The task scheduling method based on spectral clustering and auction algorithm according to any one of claims 1 to 5, characterized in that, The step of scheduling tasks according to the final allocation scheme includes: Based on the final allocation scheme, determine the task groups associated with the resource groups in the resource group set; Within the resource group, tasks in the task group are allocated according to a preset secondary scheduling strategy; Schedule resources within the resource group to execute the assigned tasks and receive feedback on the task execution results; Based on the feedback of the task execution results, update the attribute status of the corresponding resource in the resource information.

7. The task scheduling method based on spectral clustering and auction algorithm according to claim 6, characterized in that, The secondary scheduling strategy includes at least one of the following: first-come, first-served strategy, shortest job first strategy, and priority scheduling strategy.

8. A task scheduling system based on spectral clustering and auction algorithms, characterized in that, include: The acquisition module is used to acquire registered resource information and task information to be scheduled. The clustering module is used to perform spectral clustering on the resource information and the task information respectively, to form resource group sets and task group sets; The generation module is used to perform inter-group matching and task allocation on the resource group set and the task group set based on the auction algorithm, and generate an initial allocation scheme; The scheduling module is used to perform global balancing adjustments on the initial allocation scheme to obtain the final allocation scheme, and to schedule tasks according to the final allocation scheme.

9. An electronic device, characterized in that, The electronic device includes a processor coupled to a memory, the memory storing at least one computer program, which is loaded and executed by the processor to enable the electronic device to implement the task scheduling method based on spectral clustering and auction algorithm as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which, when executed by a processor, implements the task scheduling method based on spectral clustering and auction algorithm as described in any one of claims 1 to 7.

Images