Dynamic task distribution method and apparatus
By using a task distribution intelligent model based on a random forest model, which is trained with historical data and monitors task progress in real time, the problem of low efficiency in traditional task distribution methods is solved, and efficient and accurate task allocation and adaptive adjustment are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- RICHFIT INFORMATION TECH
- Filing Date
- 2024-11-29
- Publication Date
- 2026-05-29
AI Technical Summary
Traditional task distribution methods are inefficient, struggle to handle complex business needs, and rely on human experience, resulting in inaccurate and inefficient task allocation.
A task distribution intelligent model based on a random forest model is adopted. The model is trained using historical task data to predict task allocation targets and progress, and the execution progress is monitored in real time to generate intervention suggestions to optimize task allocation.
It improves the accuracy and efficiency of task allocation, reduces labor costs, and enables adaptive adjustment of dynamic task allocation.
Smart Images
Figure CN122114418A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, and in particular to a dynamic task distribution method and apparatus. Background Technology
[0002] In the enterprise regulatory dynamic reporting platform, task distribution is a crucial step in ensuring timely and accurate data reporting. Through task distribution, each task has a clearly defined responsible person and execution time, strengthening work collaboration and communication, and improving work quality and efficiency. Traditional task distribution methods typically rely on manual arrangement or simple rule settings, such as distributing tasks based on task category or executor category. This is not only inefficient but also struggles to handle complex business needs. Furthermore, the reliance on human experience in task allocation leads to imprecise and inefficient task assignment. Therefore, a more intelligent and efficient task distribution method is needed. Summary of the Invention
[0003] This invention provides a dynamic task distribution method to improve the accuracy and efficiency of task allocation and reduce labor costs. The method includes:
[0004] Acquire multiple task data to be assigned; the task data to be assigned includes one or any combination of task type, task requirements, and task quantity.
[0005] Multiple task data to be assigned are input into a trained intelligent task distribution model, which outputs the assignment object and progress prediction information for each task to be assigned. The intelligent task distribution model is trained in advance using historical task data, task execution objects, and task execution records to train a random forest model. The progress prediction information includes the predicted progress at future time points.
[0006] Send each task to be assigned to the corresponding assignment object;
[0007] Real-time collection of task execution records from multiple assigned objects; task execution records include actual execution progress;
[0008] By comparing the task execution records and progress prediction information for the same task, when the actual execution progress lags behind the predicted progress, intervention suggestion information is generated; the intervention suggestion information includes prompting progress information to the assigned object, increasing task execution resources, and reallocating the task.
[0009] In one embodiment, acquiring multiple task data to be assigned includes: acquiring the original data of multiple tasks to be assigned; performing data preprocessing on the original data of each task to be assigned to obtain preprocessed data; and performing feature selection on the preprocessed data to obtain one or any combination of task type, task requirements, and task quantity.
[0010] In one embodiment, feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task quantity, including: based on mutual information method, feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task quantity.
[0011] In one embodiment, the task distribution intelligent model is trained as follows:
[0012] A training set is constructed using historical task data, task execution objects, and task execution records.
[0013] Construct a random forest model; the random forest model consists of multiple decision trees; each decision tree is used to predict the input data;
[0014] The random forest model is trained using the training set to obtain a trained intelligent model for task distribution.
[0015] In one embodiment, training a random forest model using a training set includes: determining the optimal parameters of the model using a cross-validation method; the optimal parameters of the model include the number of decision trees and the maximum depth.
[0016] In one embodiment, after generating intervention suggestion information, the method further includes: receiving feedback data during task execution and dynamically adjusting progress prediction information.
[0017] This invention also provides a dynamic task distribution device to improve the accuracy and efficiency of task allocation and reduce labor costs. The device includes:
[0018] The task data acquisition module is used to acquire multiple task data to be assigned; the task data to be assigned includes one or any combination of task type, task requirements, and task quantity.
[0019] The task distribution processing module is used to input multiple task data to be assigned into a trained intelligent task distribution model, and output the allocation object and progress prediction information for each task to be assigned; the intelligent task distribution model is pre-trained on a random forest model using historical task data, task execution objects, and task execution records; the progress prediction information includes the predicted progress at future time points; and each task to be assigned is sent to the corresponding allocation object.
[0020] The task monitoring and early warning module is used to collect task execution records of multiple assigned objects in real time. The task execution records include the actual execution progress. The module compares the task execution records and progress prediction information of the same task. When the actual execution progress lags behind the predicted progress, intervention suggestion information is generated. The intervention suggestion information includes prompting progress information to the assigned object, increasing task execution resources, and reallocating the task.
[0021] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described dynamic task distribution method.
[0022] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described dynamic task distribution method.
[0023] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described dynamic task distribution method.
[0024] In this embodiment of the invention, historical task data, task execution objects, and task execution records are used in advance to train a random forest model to obtain a task distribution intelligent model. This intelligent model is then used to determine the allocation object and predict the progress of each task to be assigned. Compared with existing technologies, this method effectively utilizes historical data and fully considers various factors, such as task type, task requirements, and task volume, thereby improving the efficiency of task allocation and reducing labor costs. Furthermore, this method continuously monitors the actual execution of tasks and proposes intervention suggestions based on the deviation between the actual execution and the predicted progress, effectively improving the accuracy of task allocation. Attached Figure Description
[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:
[0026] Figure 1 This is a flowchart illustrating the dynamic task distribution method in an embodiment of the present invention;
[0027] Figure 2 This is a specific example diagram of the dynamic task distribution method in an embodiment of the present invention;
[0028] Figure 3This is another specific example diagram of the dynamic task distribution method in the embodiments of the present invention;
[0029] Figure 4 This is a schematic diagram of the dynamic task distribution device in an embodiment of the present invention;
[0030] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention. Detailed Implementation
[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.
[0032] The acquisition, transmission, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.
[0033] Figure 1 This is a flowchart illustrating the dynamic task distribution method in an embodiment of the present invention, such as... Figure 1 As shown, the method includes:
[0034] Step 101: Obtain multiple task data to be assigned; the task data to be assigned includes one or any combination of task type, task requirements, and task quantity;
[0035] Step 102: Input multiple task data to be assigned into the trained task distribution intelligent model, and output the assignment object and progress prediction information for each task to be assigned; the task distribution intelligent model is trained in advance using historical task data, task execution objects, and task execution records to train a random forest model; the progress prediction information includes the predicted progress at future time points.
[0036] Step 103: Send each task to be assigned to the corresponding assignment object;
[0037] Step 104: Collect task execution records from multiple assigned objects in real time; the task execution records include the actual execution progress.
[0038] Step 105: Compare the task execution records and progress prediction information for the same task. When the actual execution progress lags behind the predicted progress, generate intervention suggestion information. The intervention suggestion information includes prompting the allocation object with progress information, increasing task execution resources, and reallocating the task.
[0039] from Figure 1As shown in the flowchart, in this embodiment of the invention, historical task data, task execution objects, and task execution records are used in advance to train a random forest model to obtain a task distribution intelligent model. This intelligent model is then used to determine the allocation object and predict the progress of each task to be assigned. Compared with existing technologies, this method effectively utilizes historical data and fully considers various factors, such as task type, task requirements, and task volume, thereby improving the efficiency of task allocation and reducing labor costs. At the same time, this method continuously monitors the actual execution of tasks and proposes intervention suggestions based on the deviation between the actual execution and the predicted progress, effectively improving the accuracy of task allocation.
[0040] The dynamic task distribution method in the embodiments of the present invention will be explained in detail below.
[0041] First, in step 101, data on multiple tasks to be assigned is obtained.
[0042] For example, when a business system generates tasks A and B to be executed, these tasks can exist in the form of unstructured or semi-structured data. Based on these tasks, multiple data sets of tasks to be assigned are obtained. The data set of tasks to be assigned must include at least one of the following, or any combination thereof: task type, task requirements, and task quantity. Task types may include, for example, R&D tasks, testing tasks, or marketing tasks. Task requirements may include, for example, time requirements, quality requirements, and resource requirements. Task quantity generally refers to the scale and complexity of the task, reflecting the working time, number of workers, workload, and skill level requirements needed to complete the task.
[0043] Figure 2 This is a specific example diagram of the dynamic task distribution method in an embodiment of the present invention, such as... Figure 2 As shown, obtaining multiple task data to be assigned can include:
[0044] Step 201: Obtain the raw data of multiple tasks to be assigned;
[0045] Step 202: Perform data preprocessing on the raw data of each task to be assigned to obtain preprocessed data;
[0046] Step 203: Perform feature selection on the preprocessed data to obtain one or any combination of task type, task requirements, and task quantity.
[0047] For example, the raw data for the tasks to be assigned is first obtained, such as text data, video data, image data, or semi-structured data in formats like XML, JSON, and HTML. Preprocessing is then performed on the raw data, including handling missing values, correcting errors, deleting duplicates, extracting keywords and semantics from text data, text recognition from image data, and standardization. Afterward, feature selection is performed; in this embodiment, feature selection yields one or any combination of task type, task requirements, and task volume.
[0048] In one embodiment, feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task quantity. This may include: performing feature selection on the preprocessed data based on mutual information to obtain one or any combination of task type, task requirements, and task quantity.
[0049] Preprocessed data exhibits some correlations and may contain significant amounts of redundant information. Mutual information methods can measure the interdependence between two sets of data and help identify and eliminate redundant information. In implementation, the task execution object and execution progress are used as target variables. Features to be selected are formed from the preprocessed data. An appropriate mutual information calculation method is chosen to calculate the mutual information, and suitable features are selected through sorting or thresholding. For example, the task execution object is represented by vector A, the execution progress by vector B, and the preprocessed data is represented by set C = {C1, C2, ..., C}. n} indicates that C is calculated according to the following formula. i Mutual information I(C) with A and B i (i is an integer between 1 and n):
[0050] I(C i )=w1×I(C i ;A)+(1-w1)×I(C i ;B);
[0051] w1 is a weight parameter reflecting the importance of A and B, I(C i A) represents C i Mutual information between A and I(C) i B) represents C i The mutual information between B and B can be calculated using the joint probability distribution function and the marginal probability distribution function.
[0052] For all I(C i Sort the results and take the C that is at the first preset position. i Or select C based on the preset threshold. i The corresponding preprocessed data serves as the final feature selection result.
[0053] In step 102, multiple task data to be assigned are input into the trained task distribution intelligent model, and the assignment object and progress prediction information of each task to be assigned are output. The task distribution intelligent model is trained in advance using historical task data, task execution objects, and task execution records to train a random forest model. The progress prediction information includes the predicted progress at future time points.
[0054] In this embodiment of the invention, a task distribution intelligent model is pre-built and trained.
[0055] Figure 3 This is another specific example diagram of the dynamic task distribution method in this embodiment of the invention, as shown below. Figure 3 As shown, the task distribution intelligent model can be trained in the following manner:
[0056] Step 301: Construct a training set using historical task data, task execution objects, and task execution records;
[0057] Step 302: Construct a random forest model; the random forest model consists of multiple decision trees; each decision tree is used to predict the input data;
[0058] Step 303: Train the random forest model using the training set to obtain a trained task distribution intelligent model.
[0059] During implementation, historical task data is first collected, including task type, workload, completion time, and assignment recipients. The collected data undergoes preprocessing, including cleaning and normalization. The random forest algorithm is then used to train the model. The specific steps are as follows:
[0060] a. Data preparation: Divide historical task data into training set, test set and validation set.
[0061] b. Feature selection: Select features such as task type, task volume, completion time, and assignment target.
[0062] c. Model training: Train the random forest model using the training set data, and test the random forest model using the test set.
[0063] d. Model evaluation: Use test set and validation set data to evaluate the model performance and ensure its accuracy and generalization ability.
[0064] Finally, the model outputs the optimal allocation object for each task and its predicted completion time.
[0065] In one embodiment, training a random forest model using a training set includes: determining the optimal parameters of the model through cross-validation; the optimal parameters of the model include, but are not limited to, the number of decision trees and the maximum depth.
[0066] For example, using the K-fold cross-validation method, the training set D is divided into K equal-sized subsets D1, D2, ..., D... k The size of each subset is n i = n / K (When n is not divisible by K, the size of each subset may vary slightly), where n is the number of samples in the training set D. Then, the partitioned dataset is used for iterative training and validation. During training, the union of K-1 subsets is used as the training set each time, and the remaining subset is used as the validation set. This process is repeated K times, ensuring that each subset has a chance to serve as the validation set. Specifically:
[0067] During the k-th training iteration (k = 1, ..., K):
[0068] 1) The training set is The validation set is
[0069] 2) Using the training set Train the model using the optimal parameter combination of the current model;
[0070] 3) Then, using the validation set The evaluation model calculates multiple evaluation indicators M. k (such as accuracy, mean squared error, etc.);
[0071] 4) Calculate the average evaluation index M of the current model's optimal parameter combination after K validations:
[0072]
[0073] 5) Next, change the optimal parameter combination of the model. For each optimal parameter combination, perform the above K cross-validations to obtain the average evaluation index for each optimal parameter combination. Compare these average evaluation indices and select the parameter combination that makes the evaluation index optimal (e.g., the highest accuracy or the lowest mean squared error) as the optimal parameters.
[0074] In this example, the cross-validation method reduces overfitting through multiple training and validation cycles, ensuring that the model performs well on multiple data subsets, improving the model's generalization ability, and making the model's performance on new data more stable and reliable.
[0075] Then, in step 103, each task to be assigned is sent to the corresponding assignment object.
[0076] In this embodiment of the invention, an automated task distribution system is used to acquire data on tasks to be assigned and to distribute tasks externally. This automated task distribution system provides a user-friendly interface, allowing users to easily create, assign, and track tasks. It integrates multiple API interfaces to achieve data acquisition and task distribution.
[0077] In step 104, task execution records of multiple assigned objects are collected in real time; the task execution records include the actual execution progress.
[0078] During implementation, task progress data is collected in real time, including current completion status and remaining workload. Task execution records can also be collected based on an automated task distribution system. This system offers rich functionality to track task status, assign responsibility, record completion time and notes, and can also obtain detailed execution information for each task from the user terminal through logging tools, including start time, end time, and error messages.
[0079] In step 105, the task execution records and progress prediction information of the same task are compared. When the actual execution progress lags behind the predicted progress, intervention suggestion information is generated. The intervention suggestion information includes prompting progress information to the assigned object, increasing task execution resources, and reallocating the task.
[0080] During implementation, the collected real-time data is compared with the model's predictions to detect any discrepancies. If a significant lag in task progress compared to the predictions is detected, an early warning is generated, along with intervention suggestions such as task reallocation or increased resources.
[0081] In one embodiment, after generating intervention suggestion information, the dynamic task distribution method may further include: receiving feedback data during task execution and dynamically adjusting progress prediction information.
[0082] During implementation, the historical dataset can be updated based on the task execution results. The model can be retrained, and the task allocation strategy and warning thresholds can be adjusted to optimize the model's predictive performance.
[0083] In summary, the embodiments of the present invention have the following advantages:
[0084] 1) Intelligent task distribution model trained based on historical task data: A random forest model is trained using historical task completion data to automatically predict the best allocation target for each task, thereby optimizing task allocation.
[0085] 2) Real-time task monitoring and early warning mechanism: Combining real-time data and predictive models, monitor task progress and issue early warnings when potential delays are detected so that timely measures can be taken.
[0086] 3) Adaptive adjustment mechanism: Based on feedback data during task execution, the task allocation strategy and early warning threshold are dynamically adjusted to continuously optimize the performance of dynamic task distribution.
[0087] This invention also provides a dynamic task distribution device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to that of the dynamic task distribution method, the implementation of this device can refer to the implementation of the dynamic task distribution method; repeated details will not be elaborated further.
[0088] Figure 4 This is a schematic diagram of the dynamic task distribution device in an embodiment of the present invention, such as... Figure 4 As shown, the device 400 includes:
[0089] The task data acquisition module 401 is used to acquire multiple task data to be assigned; the task data to be assigned includes one or any combination of task type, task requirements, and task quantity.
[0090] The task distribution processing module 402 is used to input multiple task data to be assigned into a trained task distribution intelligent model, and output the allocation object and progress prediction information of each task to be assigned; the task distribution intelligent model is trained in advance using historical task data, task execution objects, and task execution records to train a random forest model; the progress prediction information includes the predicted progress at future time points; and each task to be assigned is sent to the corresponding allocation object.
[0091] The task monitoring and early warning module 403 is used to collect task execution records of multiple assigned objects in real time; the task execution records include the actual execution progress; compare the task execution records and progress prediction information of the same task, and generate intervention suggestion information when the actual execution progress lags behind the predicted progress; the intervention suggestion information includes prompting progress information to the assigned object, increasing task execution resources, and reallocating the task.
[0092] In one embodiment, the task data acquisition module 401 is specifically used for:
[0093] Obtain raw data for multiple tasks to be assigned;
[0094] The raw data for each task to be assigned is preprocessed to obtain preprocessed data.
[0095] Feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task volume.
[0096] In one embodiment, the task data acquisition module 401 is specifically used for:
[0097] Based on the mutual information method, feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task quantity.
[0098] In one embodiment, the task distribution intelligent model is trained as follows:
[0099] A training set is constructed using historical task data, task execution objects, and task execution records.
[0100] Construct a random forest model; the random forest model consists of multiple decision trees; each decision tree is used to predict the input data;
[0101] The random forest model is trained using the training set to obtain a trained intelligent model for task distribution.
[0102] In one embodiment, training a random forest model using a training set includes:
[0103] The optimal parameters of the model are determined by cross-validation; the optimal parameters of the model include the number of decision trees and the maximum depth.
[0104] In one embodiment, the device 400 further includes:
[0105] The dynamic adjustment module is used to receive feedback data during task execution and dynamically adjust the progress prediction information after the task monitoring and early warning module 403 generates intervention suggestion information.
[0106] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention, such as... Figure 5 As shown, this embodiment of the invention also provides a computer device 500, including a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, it implements the above-described dynamic task distribution method.
[0107] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described dynamic task distribution method.
[0108] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described dynamic task distribution method.
[0109] In this embodiment of the invention, historical task data, task execution objects, and task execution records are used in advance to train a random forest model to obtain a task distribution intelligent model. This intelligent model is then used to determine the allocation object and predict the progress of each task to be assigned. Compared with existing technologies, this method effectively utilizes historical data and fully considers various factors, such as task type, task requirements, and task volume, thereby improving the efficiency of task allocation and reducing labor costs. Furthermore, this method continuously monitors the actual execution of tasks and proposes intervention suggestions based on the deviation between the actual execution and the predicted progress, effectively improving the accuracy of task allocation.
[0110] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0111] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0114] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A dynamic task distribution method, characterized in that, include: Retrieve data for multiple tasks to be assigned; The data of tasks to be assigned includes one or any combination of task type, task requirements, and task quantity. Multiple task data to be assigned are input into a trained intelligent task distribution model, which outputs the assignment object and progress prediction information for each task to be assigned. The intelligent task distribution model is trained in advance using historical task data, task execution objects, and task execution records to train a random forest model. The progress prediction information includes the predicted progress at future time points. Send each task to be assigned to the corresponding assignment object; Real-time collection of task execution records from multiple assigned objects; task execution records include actual execution progress; By comparing the task execution records and progress prediction information for the same task, when the actual execution progress lags behind the predicted progress, intervention suggestion information is generated; the intervention suggestion information includes prompting progress information to the assigned object, increasing task execution resources, and reallocating the task.
2. The dynamic task distribution method as described in claim 1, characterized in that, Retrieve data for multiple tasks to be assigned, including: Obtain raw data for multiple tasks to be assigned; The raw data for each task to be assigned is preprocessed to obtain preprocessed data. Feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task volume.
3. The dynamic task distribution method as described in claim 2, characterized in that, Feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task volume, including: Based on the mutual information method, feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task quantity.
4. The dynamic task distribution method as described in claim 1, characterized in that, The task distribution intelligent model is trained as follows: A training set is constructed using historical task data, task execution objects, and task execution records. Construct a random forest model; the random forest model consists of multiple decision trees; each decision tree is used to predict the input data; The random forest model is trained using the training set to obtain a trained intelligent model for task distribution.
5. The dynamic task distribution method as described in claim 4, characterized in that, The random forest model is trained using the training set, including: The optimal parameters of the model are determined by cross-validation; the optimal parameters of the model include the number of decision trees and the maximum depth.
6. The dynamic task distribution method as described in claim 1, characterized in that, After generating intervention recommendation information, it also includes: Receive feedback data during task execution and dynamically adjust progress prediction information.
7. A dynamic task distribution device, characterized in that, include: The task data acquisition module is used to acquire multiple task data to be assigned; the task data to be assigned includes one or any combination of task type, task requirements, and task quantity. The task distribution processing module is used to input multiple task data to be assigned into a trained task distribution intelligent model, and output the allocation object and progress prediction information for each task to be assigned; the task distribution intelligent model is pre-trained on a random forest model using historical task data, task execution objects, and task execution records; the progress prediction information includes the predicted progress at future time points; and each task to be assigned is sent to the corresponding allocation object. The task monitoring and early warning module is used to collect task execution records of multiple assigned objects in real time. The task execution records include the actual execution progress. The module compares the task execution records and progress prediction information of the same task. When the actual execution progress lags behind the predicted progress, intervention suggestion information is generated. The intervention suggestion information includes prompting progress information to the assigned object, increasing task execution resources, and reallocating the task.
8. The dynamic task distribution device as described in claim 7, characterized in that, The task data acquisition module is specifically used for: Obtain raw data for multiple tasks to be assigned; The raw data for each task to be assigned is preprocessed to obtain preprocessed data. Feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task volume.
9. The dynamic task distribution device as described in claim 8, characterized in that, The task data acquisition module is specifically used for: Based on the mutual information method, feature selection is performed on the preprocessed data to obtain one or any combination of task type, task requirements, and task quantity.
10. The dynamic task distribution device as described in claim 7, characterized in that, The task distribution intelligent model is trained as follows: A training set is constructed using historical task data, task execution objects, and task execution records. Construct a random forest model; the random forest model consists of multiple decision trees; each decision tree is used to predict the input data; The random forest model is trained using the training set to obtain a trained intelligent model for task distribution.
11. The dynamic task distribution device as described in claim 10, characterized in that, The random forest model is trained using the training set, including: The optimal parameters of the model are determined by cross-validation; the optimal parameters of the model include the number of decision trees and the maximum depth.
12. The dynamic task distribution device as described in claim 7, characterized in that, Also includes: The dynamic adjustment module is used to dynamically adjust the progress prediction information after the task monitoring and early warning module generates intervention suggestion information and receives feedback data during the task execution process.
13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the dynamic task distribution method according to any one of claims 1 to 6.
14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the dynamic task distribution method according to any one of claims 1 to 6.
15. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the dynamic task distribution method according to any one of claims 1 to 6.