Task allocation method, task allocation system, and computer-readable storage medium

Abstract

The application discloses a task allocation method, a task allocation system and a computer readable storage medium. The task allocation method comprises the following steps: determining at least one subtask according to a matter graph, the matter graph comprising event nodes and event relationships corresponding to the subtasks, and sequentially publishing a plurality of subtasks according to corresponding priorities; allocating the published subtasks to at least one participant according to corresponding features between the subtasks and the participants; and in the case that at least one task answer is obtained, determining a target answer according to the at least one task answer, the task answer being a result of the participant answering the allocated subtask, and each participant corresponding to one task answer. The task allocation method determines the subtasks through the matter graph, and allocates the subtasks to corresponding participants according to corresponding features, so that the participants have sufficient ability to answer the subtasks, thereby being beneficial to improving the processing speed and accuracy of the subtasks.

Description

Technical Field

[0001] This invention relates to the field of event graph technology, and in particular to a task allocation method, a task allocation system, and a computer-readable storage medium. Background Technology

[0002] A knowledge graph is a logical knowledge base used to describe the evolutionary patterns between events. In related technologies, crowdsourcing platforms use knowledge graphs for task allocation. However, this approach has problems with its recommendation mechanism, easily assigning tasks to participants with the necessary abilities, leading to slow task processing. Furthermore, the knowledge graph exhibits low correlation in the evolution of events; forced associations can easily cause serious conflicts between tasks, making it difficult to apply knowledge graphs to task allocation. Summary of the Invention

[0003] The present invention provides a task allocation method, a task allocation system, and a computer-readable storage medium.

[0004] An embodiment of the present invention provides a task allocation method, comprising:

[0005] At least one subtask is determined based on the event graph, which includes event nodes and event relationships corresponding to the subtask, and multiple subtasks are released sequentially according to their corresponding priorities;

[0006] Based on the characteristics corresponding to the subtasks and participants, the published subtasks are assigned to at least one of the participants;

[0007] If at least one task answer is obtained, the target answer is determined based on the at least one task answer. The task answer is the result of the participant solving the assigned sub-task, and each participant corresponds to one task answer.

[0008] The above task allocation method determines sub-tasks through a causal graph and can issue them sequentially according to their priority. This corresponds to the causal graph's formation in chronological order according to the evolutionary laws of things, and sub-tasks are assigned to corresponding participants based on their characteristics. This ensures that participants have sufficient ability to solve sub-tasks, thereby improving the processing speed and accuracy of sub-tasks.

[0009] In some implementations, the task allocation method includes:

[0010] Based on the event nodes and event relationships corresponding to the subtasks in the event graph, generate an adjacency matrix;

[0011] The adjacency matrix is ​​subjected to eigenvalue decomposition to obtain eigenvalues ​​and eigenvectors. Each eigenvalue has a corresponding eigenvector, and the eigenvector includes at least one element.

[0012] The priority of a subtask is determined based on the element corresponding to its event node in the feature vector. This resolves the serious conflicts and repeated modifications that may occur when applying event graphs.

[0013] In some implementations, assigning the published subtask to at least one participant based on the corresponding characteristics between the subtask and the participant includes:

[0014] The profile features of the participant are determined by means of the participant's personal information, organizational structure information, and historical behavior information;

[0015] The category characteristics of the sub-task are determined by the event nodes of the sub-task in the event graph;

[0016] Based on the participant's profile characteristics and the sub-task's category characteristics, the participant designated as the target for sub-task assignment is determined. This allows sub-tasks to be assigned to appropriate participants, improving user experience.

[0017] In some implementations, the task allocation method includes:

[0018] Construct a test question library associated with the subtask, the test question library including at least one test question;

[0019] The test question is sent to the participant before the participant provides the answer to the task;

[0020] If the test answer is determined to be consistent with the test results, the task answer sent by the participant is received; the test answer is the participant's solution to the test question. This saves manpower and improves work efficiency.

[0021] In some implementations, determining the target answer based on the at least one task answer includes:

[0022] If at least two task answers are obtained, these two answers are integrated to obtain the target answer. This further improves work efficiency.

[0023] In some implementations, integrating the answers to the at least two tasks includes:

[0024] The target answer is determined by voting on at least two task answers based on the discrete values ​​of the task answers, where the discrete values ​​include the event nodes and event relationships of the sub-tasks; or

[0025] Based on the continuous values ​​of the task answers, the average value of at least two task answers is obtained and used to determine the target answer. In this way, task answers can be quickly integrated, corrected, and recorded on the platform.

[0026] In some implementations, the task allocation method includes:

[0027] Based on the at least one task answer and the target answer, multiple different levels of contribution are determined, with each task answer having a corresponding level of contribution.

[0028] The task reward for each participant is determined based on the level of contribution corresponding to their task answer. This can increase user engagement.

[0029] An embodiment of the present invention provides a task allocation system, which includes a task publishing module, a task allocation module, and a task integration module.

[0030] The task publishing module is used for:

[0031] At least one subtask is determined based on the event graph, which includes event nodes and event relationships corresponding to the subtask, and multiple subtasks are released sequentially according to their corresponding priorities;

[0032] The task allocation module is used for:

[0033] Based on the characteristics corresponding to the subtasks and participants, the published subtasks are assigned to at least one of the participants;

[0034] The task integration module is used for:

[0035] If at least one task answer is obtained, the target answer is determined based on the at least one task answer. The task answer is the result of the participant solving the assigned sub-task, and each participant corresponds to one task answer.

[0036] The aforementioned task allocation system determines sub-tasks through a causal graph and can issue them sequentially according to their priority. This corresponds to the causal graph's formation in chronological order according to the evolutionary laws of things, and assigns sub-tasks to corresponding participants based on their characteristics. This ensures that participants have sufficient ability to solve the sub-tasks, thereby improving the processing speed and accuracy of sub-tasks.

[0037] An embodiment of the present invention provides a task allocation system, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the task allocation method described in any of the above embodiments.

[0038] The aforementioned task allocation system determines sub-tasks through a causal graph and can issue them sequentially according to their priority. This corresponds to the causal graph's formation in chronological order according to the evolutionary laws of things, and assigns sub-tasks to corresponding participants based on their characteristics. This ensures that participants have sufficient ability to solve the sub-tasks, thereby improving the processing speed and accuracy of sub-tasks.

[0039] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the steps of the task allocation method described in any of the above embodiments.

[0040] The aforementioned computer-readable storage medium determines sub-tasks through a causal graph and can sequentially issue them according to their priority. This corresponds to the causal graph being formed in chronological order according to the evolutionary laws of things, and sub-tasks are assigned to corresponding participants based on their respective characteristics. This ensures that participants have sufficient ability to solve the sub-tasks, thereby improving the processing speed and accuracy of the sub-tasks.

[0041] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0042] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0043] Figure 1 This is a flowchart of the task allocation method according to an embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram of the task allocation system according to an embodiment of the present invention;

[0045] Figure 3 This is a schematic diagram of another module of the task allocation system according to an embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram illustrating task issuance and task allocation according to an embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram illustrating the deception behavior identification method according to an embodiment of the present invention;

[0048] Figure 6This is a schematic diagram illustrating the acquisition of the target answer and task reward according to an embodiment of the present invention;

[0049] Figure 7 This is a schematic diagram of another module of the task allocation system according to an embodiment of the present invention.

[0050] Figure label:

[0051] 100. Task Assignment System; 18. Task Set; 22. Subtask; 24. Participant; 36. Task Issuance Module; 38. Task Assignment Module; 40. Task Integration Module; 46. Deceptive Behavior Detection Module;

[0052] 56. Memory; 58. Processor. Detailed Implementation

[0053] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0054] Please refer to Figure 1 and Figure 2 One embodiment of the task allocation method of the present invention includes:

[0055] Step 12: Determine at least one subtask 22 based on the event graph. The event graph includes the event nodes and event relationships of the corresponding subtask 22. Multiple subtasks 22 are released sequentially according to their corresponding priorities.

[0056] Step 14: Assign the published subtask 22 to at least one participant 24 based on the corresponding characteristics between subtask 22 and participant 24;

[0057] Step 16: If at least one task answer is obtained, determine the target answer based on the at least one task answer. The task answer is the result of participant 24 solving the assigned sub-task 22. Each participant 24 corresponds to one task answer.

[0058] The task allocation method of this invention can be implemented by the task allocation system 100 of this invention. Specifically, please refer to... Figure 2The task allocation system 100 includes a task publishing module 36, a task allocation module 38, and a task integration module 40. The task publishing module 36 is used to: determine at least one sub-task 22 based on a process graph, which includes event nodes and event relationships corresponding to the sub-task 22; and publish multiple sub-tasks 22 sequentially according to their respective priorities. The task allocation module 38 is used to: allocate the published sub-tasks 22 to at least one participant 24 based on the corresponding characteristics between the sub-tasks 22 and the participants 24. The task integration module 40 is used to: determine the target answer based on at least one task answer when at least one task answer is obtained; the task answer is the result of the participant 24 solving the assigned sub-task 22, and each participant 24 corresponds to one task answer.

[0059] The aforementioned task allocation method and task allocation system 100 determine sub-tasks 22 through a causal graph and can issue them sequentially according to their priority. This corresponds to the causal graph and forms in chronological order according to the evolutionary laws of things. Sub-tasks 22 are then assigned to corresponding participants 24 based on their respective characteristics, ensuring that participants 24 have sufficient ability to solve sub-tasks 22. This helps to improve the processing speed and accuracy of sub-tasks 22.

[0060] Specifically, in Figure 4 In the event graph, there is a task set 18. The task set 18 includes multiple subtasks 22. In one implementation, the event nodes and event relationships of the corresponding subtasks 22 can be extracted from the event graph, and the dependencies between the multiple subtasks 22 can be constructed. Then, priority sorting is performed to determine the priority of each subtask, so that they can be published on the platform in sequence according to the priority of the multiple subtasks 22.

[0061] In one implementation, the features of subtask 22 and the features of participant 24 can be linked based on the relevant information of subtask 22, the input information and historical information of participant 24, etc., so that the published subtask 22 can be assigned to the corresponding participant 24.

[0062] In one implementation, participant 24 can participate in solving subtask 22 and provide a task answer. With all task answers obtained, the target answer is determined based on all the task answers, thereby enabling the subtask to be solved by a participant 24 with sufficient ability, thus improving the processing speed and accuracy of subtask 22.

[0063] In one embodiment, the task allocation system 100 may include a task publishing module 36, a task allocation module 38, and a task integration module 40. The task publishing module 36 can be used to determine at least one sub-task 22 based on a context graph, where the context graph includes event nodes and event relationships corresponding to the sub-task 22. Multiple sub-tasks 22 are published sequentially according to their corresponding priorities. In one example, the task publishing format should include, but is not limited to, the input of the context graph, error correction of the event graph, and completion of the context graph. In one example, the task priority ranking for task publishing should also include small sample annotation methods such as manual annotation, pre-trained model annotation, and remote unsupervised annotation, as well as importance metrics such as degree centrality, betweenness centrality, and tight centrality, and supervised and semi-supervised machine learning classification algorithms.

[0064] The task allocation module 38 is used to allocate the published subtask 22 to at least one of the participants 24 based on the corresponding features between the subtask 22 and the participant 24. In one example, the task allocation has a recommendation system mechanism, which includes related recommendation methods such as Bayesian network models, latent semantic models, ensemble models, and Wide&Deep models.

[0065] The task integration module 40 is used to determine the target answer based on at least one task answer, where the task answer is the result of participant 24's solution to the assigned sub-task 22, with each participant 24 corresponding to one task answer. The task integration module 40 has the functions of result quality assessment and answer integration. Result quality assessment can be submitted to the platform through the deception behavior detection module 46, which may include identification methods such as intelligent question answering systems and dynamic common sense bases. Answer integration may include models that can achieve result fusion, such as weighted average methods, Bayesian average methods, and the EM algorithm.

[0066] In some implementations, the task allocation method includes:

[0067] Generate an adjacency matrix based on the event nodes and event relationships corresponding to subtask 22 in the event graph;

[0068] Eigenvalues ​​and eigenvectors are obtained by performing eigendecomposition on the adjacency matrix. Each eigenvalue has a corresponding eigenvector, and the eigenvector includes at least one element.

[0069] The priority of subtask 22 is determined based on the element corresponding to the event node in the feature vector.

[0070] In this way, the serious conflicts and repeated modifications that may occur when applying the principle graph can be resolved.

[0071] Specifically, based on the event nodes and event relationships corresponding to subtask 22 in the event graph, an adjacency matrix A can be generated. Eigenvalues ​​and eigenvectors can be obtained by performing eigenvalue decomposition on the adjacency matrix. The specific formula is as follows:

[0072] Ax = λx,

[0073] Here, A represents the graph adjacency matrix, the event graph can be represented by A, x represents a corresponding eigenvector, and λ represents the eigenvalue. x can be [x1 x2…xi] T xi represents the i-th element in the eigenvector.

[0074] Based on the above, at least one eigenvalue can be obtained through the event graph. Each eigenvalue has a corresponding eigenvector, which includes at least one element. In one embodiment, after determining the eigenvalue and eigenvector, the centrality of the corresponding event node can be determined based on the i-th element in the eigenvector corresponding to the largest eigenvalue. Based on the element corresponding to the centrality of the event node of subtask 22 in the eigenvector, the centrality of the event node can represent the importance of the event node. Multiple subtasks 22 can be prioritized according to their centrality to determine their priority. In one embodiment, the higher the centrality of the event nodes contained in subtask 22, the higher the priority of subtask 22.

[0075] In some implementations, step 14 (assigning the published subtask 22 to at least one participant 24 based on the corresponding characteristics between the subtask 22 and the participant 24) includes:

[0076] The profile characteristics of participant 24 were determined by analyzing participant 24's personal information, organizational affiliation information, and historical behavioral information.

[0077] Determine the category characteristics of subtask 22, which are determined by the event nodes of subtask 22 in the event graph;

[0078] Based on the profile characteristics of participant 24 and the category characteristics of subtask 22, participant 24 is identified as the subject of assignment for subtask 22.

[0079] In this way, subtask 22 can be assigned to the appropriate participant 24, improving the user experience.

[0080] Specifically, in one implementation, determining the profile features of participant 24 requires constructing a multi-label system for participant 24's profile. This involves using structured or unstructured data such as participant 24's personal information, organizational affiliation information, and historical behavior information to build a user profile model, predict the user profile, and thus determine the profile features of participant 24. In another implementation, determining the category features of subtask 22 requires constructing a label system for subtask 22. This involves classifying subtask 22 based on its event nodes in the event graph, thereby determining the category features of subtask 22.

[0081] In one implementation, based on the profile features of participant 24 and the category features of subtask 22, content-based collaborative filtering or model-based collaborative filtering is used to match subtask 22 and participant 24, thereby determining the participant 24 as the assignment object of subtask 22, which is beneficial to improving the user's answering experience.

[0082] In some implementations, the task allocation method includes:

[0083] Construct a test question library associated with subtask 22, which includes at least one test question;

[0084] Send a test question to participant 24 before participant 24 provides the answer to the task;

[0085] If the test answer is found to be consistent with test result 26, the task answer sent by participant 24 is received. The test answer is the result of participant 24's solution to the test question.

[0086] This saves manpower and improves work efficiency.

[0087] Specifically, in one implementation, after multiple participants 24 complete subtask 22, participants 24 may be required to undergo a deception verification process. Only after successful verification can the task answers provided by participants 24 be submitted to the platform. In one implementation, a test question library associated with subtask 22 may be pre-built. The test question library may include at least one test question, and the answers to the test questions are known. Test questions are sent to participants 24 before they submit their feedback task answers.

[0088] Please combine Figure 5 ,exist Figure 5 In this process, based on participant 24's answers to the test questions, it can be determined whether the test answer matches test result 26. If the test answer matches test result 26, the task answer sent by participant 24 will be accepted. If the test answer does not match test result 26, the task answer sent by participant 24 will be rejected. Additionally, in... Figure 3In this system, the deception behavior identification module 46 can solve the problems of inefficiency and waste of manpower caused by relying entirely on manual review of deception behavior.

[0089] In some implementations, determining the target answer based on at least one task answer includes:

[0090] If at least two task answers are obtained, the answers are integrated to obtain the target answer.

[0091] This further improves work efficiency.

[0092] Specifically, please combine Figure 6 When multiple task answers are obtained, it is necessary to integrate the answers. The answer integration module can automatically integrate the answers, thereby solving the problem of low speed caused by directly using the principle graph, and thus further improving work efficiency.

[0093] In some implementations, answer integration of at least two task answers includes:

[0094] Based on the discrete values ​​of the task answers, at least two task answers are voted on to determine the target answer. The discrete values ​​include the event nodes and event relationships of subtask 22; or

[0095] Based on the continuous values ​​of the task answers, the average value of at least two task answers is obtained and used to determine the target answer.

[0096] In this way, the answers to the tasks can be quickly integrated, corrected, and recorded on the platform.

[0097] Specifically, in one implementation, the target answer can be determined by voting on all task answers based on their discrete values. Discrete values ​​may include event nodes and event relationships of subtask 22, such as event names and entities included in the events. By combining the discrete values ​​of the task answers and adopting the principle of majority rule, the task answer with the highest frequency of discrete values ​​can be determined as the final target answer. Multiple levels of contribution can also be determined, and the target answer and contribution levels are recorded on the platform.

[0098] In one implementation, based on the continuous values ​​of the task answers, all task answers can be assigned corresponding weights, and an averaging method can be used to average all task answers to obtain an average value for determining the target answer. The contribution is recorded according to the degree of deviation from the average value, and the target answer and contribution are recorded on the platform.

[0099] In some implementations, please refer to Figure 6 Task allocation methods include:

[0100] Based on at least one task answer and one objective answer, determine multiple different levels of contribution, with each task answer having a corresponding contribution level;

[0101] The task reward for participant 24 is determined based on the contribution level corresponding to the task answer.

[0102] This can increase user engagement.

[0103] Specifically, in one implementation, task rewards can be determined based on the importance and difficulty of the task. Multiple levels of contribution can be determined based on all task and objective answers, and a corresponding level of contribution can be determined for each participant 24 based on their task answer; each task answer can have a corresponding contribution level. Based on the level of contribution recorded for each task answer, the task reward for participant 24 corresponding to that answer can be determined and distributed to participant 24.

[0104] Please refer to Figure 7 A task allocation system 100 according to an embodiment of the present invention includes a memory 56 and a processor 58. The memory 56 stores a computer program. When the processor 58 executes the computer program, it implements the steps of the task allocation method of any of the above embodiments.

[0105] For example, when a computer program is executed, the following steps can be achieved:

[0106] Step 12: Determine at least one subtask 22 based on the event graph. The event graph includes the event nodes and event relationships of the corresponding subtask 22. Multiple subtasks 22 are released sequentially according to their corresponding priorities.

[0107] Step 14: Assign the published subtask 22 to at least one participant 24 based on the corresponding characteristics between subtask 22 and participant 24;

[0108] Step 16: If at least one task answer is obtained, determine the target answer based on the at least one task answer. The task answer is the result of participant 24 solving the assigned sub-task 22. Each participant 24 corresponds to one task answer.

[0109] The aforementioned task allocation system 100 determines sub-tasks 22 through a causal graph and can issue them sequentially according to their priority. This corresponds to the causal graph and forms in chronological order according to the evolutionary laws of things. Sub-tasks 22 are then assigned to corresponding participants 24 based on their respective characteristics, ensuring that participants 24 have sufficient ability to solve sub-tasks 22. This helps to improve the processing speed and accuracy of sub-tasks 22.

[0110] An embodiment of the present invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the task allocation method of any of the above embodiments.

[0111] For example, when a computer program is executed, the following steps can be achieved:

[0112] Step 12: Determine at least one subtask 22 based on the event graph. The event graph includes the event nodes and event relationships of the corresponding subtask 22. Multiple subtasks 22 are released sequentially according to their corresponding priorities.

[0113] Step 14: Assign the published subtask 22 to at least one participant 24 based on the corresponding characteristics between subtask 22 and participant 24;

[0114] Step 16: If at least one task answer is obtained, determine the target answer based on the at least one task answer. The task answer is the result of participant 24 solving the assigned sub-task 22. Each participant 24 corresponds to one task answer.

[0115] The aforementioned computer-readable storage medium determines subtask 22 through a causal graph and can issue subtask 22 sequentially according to its priority. This corresponds to the causal graph forming in chronological order according to the evolutionary laws of things, and assigns subtask 22 to the corresponding participants 24 according to their respective characteristics. This ensures that participants 24 have sufficient ability to solve subtask 22, thereby improving the processing speed and accuracy of subtask 22.

[0116] The computer-readable storage medium can be located in the control system or in other terminals, and the control system can communicate with other terminals to obtain the corresponding program.

[0117] It is understood that computer-readable storage media can include: any entity or device capable of carrying computer programs, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc. Computer programs include computer program code. Computer program code can be in the form of source code, object code, executable files, or certain intermediate forms, etc. Computer-readable storage media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media.

[0118] In some embodiments of the present invention, the control system may be a microcontroller chip integrating a processor, memory, communication module, etc. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0119] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0120] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a system including a processing module or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0121] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0122] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A task allocation method, characterized in that, include: At least one subtask is determined based on the event graph, which includes event nodes and event relationships corresponding to the subtask, and multiple subtasks are released sequentially according to their corresponding priorities; Based on the characteristics corresponding to the subtasks and participants, the published subtasks are assigned to at least one of the participants; If at least one task answer is obtained, the target answer is determined based on the at least one task answer, wherein the task answer is the result of the participant solving the assigned sub-task, and each participant corresponds to one task answer; The task allocation method includes: Based on the event nodes and event relationships corresponding to the subtasks in the event graph, generate an adjacency matrix; The adjacency matrix is ​​subjected to eigenvalue decomposition to obtain eigenvalues ​​and eigenvectors. Each eigenvalue has a corresponding eigenvector, and the eigenvector includes at least one element. The priority of the subtask is determined based on the element in the feature vector corresponding to the event node of the subtask. Specifically, the eigenvector corresponding to the largest eigenvalue is selected, and the centrality of each event node is determined based on the element value of each event node in the eigenvector. The centrality is used to characterize the importance of the event node. The priority of a subtask is determined based on the centrality of the event nodes it contains, wherein the higher the centrality of the event nodes, the higher the priority of the corresponding subtask; the published subtask is assigned to at least one participant based on the characteristics corresponding to the subtask and the participant, including: The profile features of the participant are determined by means of the participant's personal information, organizational structure information, and historical behavior information; The category characteristics of the sub-task are determined by the event nodes of the sub-task in the event graph; Based on the participant's profile characteristics and the sub-task's category characteristics, the participant who is assigned to the sub-task is determined; The task allocation method includes: Based on the at least one task answer and the target answer, multiple different levels of contribution are determined, with each task answer having a corresponding level of contribution. The task reward for the participant is determined based on the level of contribution corresponding to the task answer.

2. The task allocation method according to claim 1, characterized in that, The task allocation method includes: Construct a test question library associated with the subtask, the test question library including at least one test question; The test question is sent to the participant before the participant provides the answer to the task; If the test answer is found to be consistent with the test result, the task answer sent by the participant is received, wherein the test answer is the result of the participant's solution to the test question.

3. The task allocation method according to claim 1, characterized in that, Determining the target answer based on at least one task answer includes: If at least two task answers are obtained, the at least two task answers are integrated to obtain the target answer.

4. The task allocation method according to claim 3, characterized in that, Integrating the answers to the at least two tasks includes: The target answer is determined by voting on at least two task answers based on the discrete values ​​of the task answers, where the discrete values ​​include the event nodes and event relationships of the sub-tasks; or The average value of the at least two task answers is obtained by averaging the consecutive values ​​of the task answers to determine the target answer.

5. A task allocation system, characterized in that, To implement the method as described in any one of claims 1-4, the task allocation system includes a task publishing module, a task allocation module, and a task integration module. The task publishing module is used for: At least one subtask is determined based on the event graph, which includes event nodes and event relationships corresponding to the subtask, and multiple subtasks are released sequentially according to their corresponding priorities; The task allocation module is used for: Based on the characteristics corresponding to the subtasks and participants, the published subtasks are assigned to at least one of the participants; The task integration module is used for: If at least one task answer is obtained, the target answer is determined based on the at least one task answer. The task answer is the result of the participant solving the assigned sub-task, and each participant corresponds to one task answer.

6. A task allocation system, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the task allocation method according to any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the task allocation method according to any one of claims 1-4.

Images