Artificial intelligence-based task allocation method and system
By analyzing the content of project manager meetings and the information of attendees using artificial intelligence, the task hierarchy is automatically divided, solving the problems of time-consuming, labor-intensive, and subjective task allocation in the past, and achieving efficient and reasonable task allocation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGKETONG SHANGJING TECH SHANGHAI CO LTD
- Filing Date
- 2023-07-12
- Publication Date
- 2026-07-28
AI Technical Summary
Existing task allocation methods consume a lot of time and effort, and the results are highly subjective, leading to unreasonable task allocation and reduced work efficiency and project accuracy.
By analyzing the content of project manager meetings using artificial intelligence models, task levels are divided, and task allocation plans are determined by combining the experience and professional level information of the participants, thus achieving automated and objective task allocation.
It improves the efficiency and accuracy of task allocation, ensures that everyone's abilities are matched with the tasks, improves work efficiency and practicality, and reduces subjective errors.
Smart Images
Figure CN116911541B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of artificial intelligence technology, and in particular to a task allocation method and system based on artificial intelligence. Background Technology
[0002] Currently, with the continuous improvement of people's living standards, people's living needs and the supply of social industries are gradually increasing. As the production department is responsible for more and more products, the production tasks are also increasing. Project managers need to spend a lot of time on how to arrange tasks. Task allocation is used to establish a mapping relationship between the tasks to be completed and the operators to receive the tasks. The accuracy of the matching between tasks and operators directly affects the execution efficiency and effect of all tasks. The existing task allocation method is usually that the project manager receives the customer's requirements, then holds a meeting to discuss, arrange meetings, notify personnel, and allocate tasks. This not only requires a lot of energy and time, but also makes the final personnel allocation result extremely subjective, which can easily lead to unreasonable task allocation, thereby delaying the accuracy of the project and reducing work efficiency and practicality. Summary of the Invention
[0003] To address the problems mentioned above, this invention provides an artificial intelligence-based task allocation method and system to solve the problems mentioned in the background art, such as the fact that project managers need to spend a lot of energy and time on offline meetings, and that the final personnel allocation results are extremely subjective, which can easily lead to unreasonable task allocation, thereby delaying project accuracy and reducing work efficiency and practicality.
[0004] An artificial intelligence-based task allocation method includes the following steps:
[0005] Obtain the meeting content of the project manager and parse out the corresponding voice information. Based on the voice information, obtain multiple tasks to be assigned.
[0006] Each task to be assigned is divided into multi-level sub-tasks based on its task indicators.
[0007] The AI model determines the sub-tasks assigned to each participant based on their experience, company professional level, and the execution complexity of each sub-task.
[0008] The personnel allocation for each task to be assigned is determined based on the hierarchical relationship between each participant's assigned sub-tasks and multiple tasks to be assigned.
[0009] Preferably, the step of obtaining the project manager's meeting content and parsing the corresponding voice information, and obtaining multiple tasks to be assigned based on the voice information, includes:
[0010] Record the project manager's meeting content using pre-set meeting software, extract the audio signal from the meeting content, and enhance it.
[0011] Determine the project manager's audio track information, and extract the project manager's target voice signal from the enhanced voice signal based on the audio track information;
[0012] The speech content corresponding to the target speech signal is converted into text content, and the text content is logically organized.
[0013] Based on the sorted text content, multiple tasks awaiting assignment are obtained.
[0014] Preferably, the step of dividing each task to be assigned into multi-level sub-tasks based on the task indicators of each task to be assigned includes:
[0015] Obtain the total task metrics and sub-task metrics for each task to be assigned, and determine the task hierarchy architecture for each task to be assigned based on the total task metrics and sub-task metrics.
[0016] The total task type of each task to be assigned is determined based on the task hierarchy architecture of that task.
[0017] The maximum division level of each task to be assigned is determined based on the total task type of each task to be assigned, and the ideal division level of the sub-task indicators of each task to be assigned is determined based on the maximum division level.
[0018] Each task to be assigned is divided into multi-level subtasks based on the ideal hierarchical division of the subtask indicators of each task to be assigned.
[0019] Preferably, the step of determining the assigned sub-tasks for each participant using an artificial intelligence model based on the participant's experience information, company professional level information, and the execution complexity of each sub-task includes:
[0020] Obtain historical task completion data for each participant, and determine the experience information of each participant based on the data.
[0021] Obtain the personal identification information of each participant, and retrieve the enterprise professional level information of each participant from the enterprise database based on the personal identification information;
[0022] Obtain the task execution indicators and task evaluation indicators for each subtask, and determine the human, intellectual, and skill requirements for each subtask based on the task execution indicators and task evaluation indicators.
[0023] The execution complexity of each subtask is determined based on the information on the human, intellectual, and skill requirements of each subtask.
[0024] Tasks were categorized based on each participant's company professional level information, from highest to lowest.
[0025] Based on the grading results, an artificial intelligence model assigns each participant an execution sub-task according to their experience and the execution complexity of each sub-task.
[0026] Preferably, determining the personnel allocation for each task to be assigned based on the hierarchical relationship between each participant's assigned sub-tasks and multiple tasks to be assigned includes:
[0027] The service assignment tasks for each participant are determined based on the hierarchical relationship between the sub-tasks assigned to each participant and the multiple tasks to be assigned.
[0028] Based on the service assignments of each participant, all participants were divided into single-task participants and multi-task participants.
[0029] The first person to be assigned for each task is determined based on the first task assignment of the single-task personnel.
[0030] The second personnel allocation for each task to be assigned is determined based on the second task allocation for multi-task personnel.
[0031] The overall personnel allocation for each task to be assigned is determined based on the first and second personnel allocations for each task to be assigned.
[0032] An artificial intelligence-based task allocation system, the system comprising:
[0033] The acquisition module is used to acquire the meeting content of the project manager and parse out the corresponding voice information of the meeting content, and obtain multiple tasks to be assigned based on the voice information;
[0034] The partitioning module is used to divide each task to be assigned into multi-level subtasks based on the task indicators of each task to be assigned.
[0035] The first determination module is used to determine the assigned sub-tasks for each participant based on the participant's experience information, company professional level information, and the execution complexity of each sub-task using an artificial intelligence model.
[0036] The second determination module is used to determine the personnel allocation for each task to be assigned based on the hierarchical relationship between each participant's assigned sub-tasks and multiple tasks to be assigned.
[0037] Preferably, the acquisition module includes:
[0038] The first extraction submodule is used to record the project manager's meeting content through preset meeting software, extract the voice signal in the meeting content and enhance it;
[0039] The second extraction submodule is used to determine the project manager's audio track information and extract the project manager's target audio signal from the enhanced audio signal based on the audio track information.
[0040] The conversion submodule is used to convert the speech content corresponding to the target speech signal into text content and to logically organize the text content.
[0041] The Get submodule is used to retrieve multiple tasks to be assigned based on the sorted text content.
[0042] Preferably, the partitioning module includes:
[0043] The first determination submodule is used to obtain the total task indicators and sub-task indicators for each task to be assigned, and to determine the task hierarchy architecture for each task to be assigned based on the total task indicators and sub-task indicators.
[0044] The second determining submodule is used to determine the total task type of each task to be assigned based on the task hierarchy architecture of each task to be assigned.
[0045] The third determination submodule is used to determine the maximum division level of each task to be assigned based on the total task type of each task to be assigned, and to determine the ideal division level of the sub-task index of each task to be assigned based on the maximum division level.
[0046] The first partitioning submodule is used to divide each task to be assigned into multi-level subtasks based on the ideal partitioning hierarchy of each task's sub-task indicators.
[0047] Preferably, the first determining module includes:
[0048] The fourth submodule is used to obtain the historical completed task indicator data of each participant and determine the experience information of each participant based on the indicator data.
[0049] The retrieval submodule is used to obtain the personal identity information of each participant and retrieve the enterprise professional level information of each participant from the enterprise database based on the personal identity information.
[0050] The fifth determination submodule is used to obtain the task execution indicators and task evaluation indicators for each subtask, and determine the human, intellectual and skill requirements information for each subtask based on the task execution indicators and task evaluation indicators.
[0051] The sixth sub-module is used to determine the execution complexity of each sub-task based on the information on the human, intellectual, and skill requirements of each sub-task.
[0052] The hierarchical submodule is used to classify tasks according to the company's professional level information of each participant, in descending order of level.
[0053] The allocation submodule is used to allocate execution subtasks to each participant based on the experience information of each participant and the execution complexity of each subtask according to the hierarchical results using an artificial intelligence model.
[0054] Preferably, the second determining module includes:
[0055] The seventh submodule is used to determine the service assignment task for each participant based on the hierarchical relationship between the assigned sub-tasks of each participant and multiple tasks to be assigned.
[0056] The second sub-module is used to divide all participants into single-task participants and multi-task participants based on the service assignment tasks of each participant.
[0057] The eighth submodule is used to determine the first person to be assigned for each task based on the first task assignment of the single-task personnel.
[0058] The ninth submodule is used to determine the second personnel allocation for each task to be assigned based on the second task allocation of multi-task personnel.
[0059] The tenth determination submodule is used to determine the comprehensive personnel allocation for each task to be assigned based on the first and second personnel allocation information.
[0060] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.
[0061] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description
[0062] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.
[0063] Figure 1 A flowchart illustrating the workflow of an artificial intelligence-based task allocation method provided by this invention;
[0064] Figure 2 Another flowchart of an artificial intelligence-based task allocation method provided by the present invention;
[0065] Figure 3 This is a schematic diagram of the structure of an artificial intelligence-based task allocation system provided by the present invention;
[0066] Figure 4 This is a schematic diagram of the acquisition module in an artificial intelligence-based task allocation system provided by the present invention. Detailed Implementation
[0067] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0068] Currently, with the continuous improvement of people's living standards, people's living needs and the supply of social industries are gradually increasing. As the production department is responsible for more and more products, the production tasks are also increasing. Project managers need to spend a lot of time on task allocation. Task allocation is used to establish a mapping relationship between tasks to be completed and operators to receive them. The accuracy of the matching between tasks and operators directly affects the execution efficiency and effectiveness of all tasks. Existing task allocation methods usually involve project managers receiving customer requirements, holding meetings, arranging meetings, notifying personnel, and assigning tasks. This not only consumes a lot of energy and time, but also makes the final personnel allocation result highly subjective, which can easily lead to unreasonable task allocation, thereby delaying project accuracy and reducing work efficiency and practicality. To solve the above problems, this embodiment discloses a task allocation method based on artificial intelligence.
[0069] An AI-based task allocation method, such as Figure 1 As shown, it includes the following steps:
[0070] Step S101: Obtain the meeting content of the project manager and parse out the corresponding voice information of the meeting content, and obtain multiple tasks to be assigned based on the voice information;
[0071] Step S102: Divide each task to be assigned into multi-level sub-tasks according to the task indicators of each task to be assigned;
[0072] Step S103: Determine the assigned sub-tasks for each participant based on the participant's experience information, company professional level information, and the execution complexity of each sub-task using an artificial intelligence model.
[0073] Step S104: Determine the personnel allocation for each task to be assigned based on the hierarchical relationship between the sub-tasks assigned to each participant and the multiple tasks to be assigned.
[0074] In this embodiment, the meeting content refers to the recorded content of an internal meeting organized by the project manager through an online meeting app;
[0075] In this embodiment, voice information refers to the meeting information expressed by the project manager's voice content in the meeting content;
[0076] In this embodiment, the task to be assigned refers to the task that requires personnel allocation, which is the main task rather than a sub-task.
[0077] In this embodiment, the task index is represented as the task completion reference index for each task to be assigned;
[0078] In this embodiment, experience information represents each participant's historical experience with different types of tasks;
[0079] In this embodiment, execution complexity is represented by the execution complexity assessed based on the required experience and skills for each subtask;
[0080] In this embodiment, the subtask assigned to each participant is represented as a subtask assigned to each participant, which can be a subtask of one task to be assigned or a subtask of multiple tasks to be assigned.
[0081] The working principle of the above technical solution is as follows: The meeting content of the project manager is acquired and the corresponding voice information is parsed. Multiple tasks to be assigned are obtained based on the voice information. Each task to be assigned is divided into multi-level sub-tasks according to its task indicators. An artificial intelligence model is used to determine the assigned sub-tasks for each participant based on their experience, company professional level, and the execution complexity of each sub-task. The personnel allocation for each task to be assigned is determined based on the hierarchical relationship between each participant's assigned sub-tasks and the multiple tasks to be assigned.
[0082] The beneficial effects of the above technical solution are as follows: By determining the tasks to be assigned by the project manager through online meetings, and then using an artificial intelligence model to allocate sub-tasks based on the experience and job information of each online meeting participant, this approach avoids subjective assignment by the project manager, saves significant time and effort, improves practicality, and ensures the objectivity of task allocation. It matches each individual's abilities with their assigned tasks, guaranteeing reasonable task allocation and reliable task completion, thus improving overall work efficiency and practicality. This solution addresses the problems of existing technologies where project managers spend considerable time and energy on offline meetings, and where the final allocation is highly subjective, easily leading to unreasonable task allocation, delaying project accuracy, and reducing work efficiency and practicality.
[0083] In one embodiment, such as Figure 2 As shown, the process involves obtaining the project manager's meeting content and parsing the corresponding audio information. Based on the audio information, multiple tasks to be assigned are obtained, including:
[0084] Step S201: Record the project manager's meeting content using preset meeting software, extract the audio signal from the meeting content, and enhance it.
[0085] Step S202: Determine the project manager's audio track information, and extract the project manager's target audio signal from the enhanced audio signal based on the audio track information;
[0086] Step S203: Convert the speech content corresponding to the target speech signal into text content, and then logically organize the text content;
[0087] Step S204: Obtain multiple tasks to be assigned based on the sorted text content.
[0088] The beneficial effects of the above technical solution are as follows: it can ensure the auditory clarity of the voice signal, and at the same time, it can quickly and accurately extract the project manager's unique voice signal to quickly determine the tasks to be assigned, thereby further improving work efficiency and stability. Meanwhile, by logically sorting out the text content, it can ensure the rationality and completeness of each assigned task, thereby further improving practicality.
[0089] In one embodiment, dividing each task to be assigned into multi-level sub-tasks based on its task metrics includes:
[0090] Obtain the total task metrics and sub-task metrics for each task to be assigned, and determine the task hierarchy architecture for each task to be assigned based on the total task metrics and sub-task metrics.
[0091] The total task type of each task to be assigned is determined based on the task hierarchy architecture of that task.
[0092] The maximum division level of each task to be assigned is determined based on the total task type of each task to be assigned, and the ideal division level of the sub-task indicators of each task to be assigned is determined based on the maximum division level.
[0093] Each task to be assigned is divided into multi-level subtasks based on the ideal hierarchical division of the subtask indicators of each task to be assigned.
[0094] The beneficial effects of the above technical solution are as follows: by determining the task hierarchy architecture and maximum partitioning level of each task to be assigned, the qualification and objectivity of the subtasks to be divided for each task to be assigned are accurately determined, thereby ensuring that each task to be assigned is completed with maximum efficiency and maximum quality, and improving stability and reliability.
[0095] In one embodiment, the process of determining the assigned sub-tasks for each participant using an artificial intelligence model based on their experience, company professional level, and the execution complexity of each sub-task includes:
[0096] Obtain historical task completion data for each participant, and determine the experience information of each participant based on the data.
[0097] Obtain the personal identification information of each participant, and retrieve the enterprise professional level information of each participant from the enterprise database based on the personal identification information;
[0098] Obtain the task execution indicators and task evaluation indicators for each subtask, and determine the human, intellectual, and skill requirements for each subtask based on the task execution indicators and task evaluation indicators.
[0099] The execution complexity of each subtask is determined based on the information on the human, intellectual, and skill requirements of each subtask.
[0100] Tasks were categorized based on each participant's company professional level information, from highest to lowest.
[0101] Based on the grading results, an artificial intelligence model assigns each participant an execution sub-task according to their experience and the execution complexity of each sub-task.
[0102] The beneficial effects of the above technical solution are: it can ensure the rationality and reliability of the personnel allocation for each sub-task, thereby meeting the basic personnel and skill requirements of each sub-task, ensuring the minimum completion limit of the sub-task, and improving practicality and stability.
[0103] In this embodiment, following the experience information of each participant, the following is also included:
[0104] Analyze the experience information of each participant to determine the clear information and fuzzy information of that participant, and determine the first task type corresponding to the clear information and the second task type corresponding to the fuzzy information respectively;
[0105] Based on the first and second task types, determine the task types that each participant is good at and set task tags for that participant.
[0106] Determine the current task type of each subtask, and determine the expected subtask assignment for each participant based on the task tag of each participant and the current task type of each subtask;
[0107] Based on the clear information of each participant, a task execution decision tree is constructed for that participant using a pre-defined decision tree algorithm;
[0108] Obtain the task execution stage and stage parameters corresponding to the expected sub-tasks assigned to each participant;
[0109] Using the task execution decision tree of each participant, the behavioral parameters of the participant in the expected sub-tasks are predicted based on the task execution stage and stage parameters corresponding to the participant's expected sub-tasks.
[0110] Based on the behavioral parameters and the task qualification evaluation index of each participant's expected sub-task assignment, the first completion qualification of each participant for their expected sub-task assignment is determined.
[0111] Select the target expectation subtask corresponding to the highest second completion qualification among the first completion qualification of each participant as the most suitable expectation subtask for that participant.
[0112] The most suitable expected sub-tasks for each participant are integrated and statistically analyzed to determine whether there are multiple participants assigned to the same most suitable expected sub-task.
[0113] If so, check the preset personnel allocation value range of the most suitable expected sub-task. If the statistical number of multiple assigned participants is within the preset personnel allocation value range, then the multiple assigned participants of the most suitable expected sub-task are taken as the final task executors.
[0114] If the statistical count of multiple assigned participants is not within the preset range of personnel allocation values, the second completion qualification of each assigned participant will be sorted.
[0115] Based on the sorting results, select the target number of participants, which is the same as the maximum value of the preset personnel allocation range, in descending order, as the final task executors.
[0116] In this embodiment, clear information is represented as clearly described experience information of each participant in their area of expertise;
[0117] In this embodiment, fuzzy information is represented as fuzzy descriptions of each participant's experience in areas where they are not proficient.
[0118] In this embodiment, the task tag represents a task function description tag for each participant's area of expertise;
[0119] In this embodiment, the expected subtask allocation is represented as the subtask allocation most suitable for each participant;
[0120] In this embodiment, the task execution decision tree is represented as a decision model tree for each participant when executing a task;
[0121] In this embodiment, the task execution phase and phase parameters are represented as multiple transition phases of task execution and phase execution parameters for each transition phase;
[0122] In this embodiment, the behavioral parameters are represented as evaluation parameters of the performance behavior of each participant in the expected sub-task assignment.
[0123] The beneficial effects of the above technical solution are as follows: it can select the most suitable sub-task for each participant based on their actual experience information, ensuring the rationality of task arrangement and the reliability of subsequent completion. Furthermore, by controlling and screening the number of personnel for each sub-task, it is possible to further select the personnel who can play the greatest role in each sub-task as task assigners, further ensuring the reliability and practicality of task completion and improving the guarantee.
[0124] In one embodiment, determining the personnel allocation for each task to be assigned based on the hierarchical relationship between each participant's assigned sub-tasks and multiple tasks to be assigned includes:
[0125] The service assignment tasks for each participant are determined based on the hierarchical relationship between the sub-tasks assigned to each participant and the multiple tasks to be assigned.
[0126] Based on the service assignments of each participant, all participants were divided into single-task participants and multi-task participants.
[0127] The first person to be assigned for each task is determined based on the first task assignment of the single-task personnel.
[0128] The second personnel allocation for each task to be assigned is determined based on the second task allocation for multi-task personnel.
[0129] The overall personnel allocation for each task to be assigned is determined based on the first and second personnel allocations for each task to be assigned.
[0130] The beneficial effects of the above technical solution are: it can accurately perform intuitive personnel allocation statistics based on the multi-task division or single-task division of each participant, reducing statistical errors, improving statistical efficiency, and further enhancing practicality and stability.
[0131] In one embodiment, this embodiment also discloses an artificial intelligence-based task allocation system, such as... Figure 3 As shown, the system includes:
[0132] The acquisition module 301 is used to acquire the meeting content of the project manager and parse out the corresponding voice information of the meeting content, and acquire multiple tasks to be assigned based on the voice information;
[0133] The partitioning module 302 is used to partition each task to be assigned into multi-level sub-tasks based on the task indicators of each task to be assigned.
[0134] The first determining module 303 is used to determine the assigned sub-tasks for each participant based on the participant's experience information, company professional level information, and the execution complexity of each sub-task using an artificial intelligence model.
[0135] The second determining module 304 is used to determine the personnel allocation for each task to be assigned based on the hierarchical relationship between the assigned sub-tasks of each participant and multiple tasks to be assigned.
[0136] The working principle of the above technical solution is as follows: First, the acquisition module obtains the meeting content of the project manager and parses out the corresponding voice information, and obtains multiple tasks to be assigned based on the voice information; second, the division module divides each task to be assigned into multi-level sub-tasks according to the task indicators of each task to be assigned; then, the first determination module uses an artificial intelligence model to determine the assigned sub-tasks for each participant based on the experience information of the participants, the professional level information of the company, and the execution complexity of each sub-task; finally, the second determination module uses the subordinate relationship between the assigned sub-tasks of each participant and the multiple tasks to be assigned to determine the personnel allocation of each task to be assigned.
[0137] The beneficial effects of the above technical solution are as follows: by determining the tasks to be assigned by the project manager through online meetings, and then using an artificial intelligence model to assign sub-tasks based on the experience and job information of each participant in the online meeting, it can avoid the project manager's subjective allocation of personnel, save a lot of allocation manager and allocation time, improve practicality, and ensure the objectivity of task allocation results. This ensures that each person's personal ability is matched with the assigned tasks, guarantees the rationality of task allocation and the reliability of task completion, and improves overall work efficiency and practicality.
[0138] In one embodiment, such as Figure 4 As shown, the acquisition module 301 includes:
[0139] The first extraction submodule 3011 is used to record the project manager's meeting content through preset meeting software, extract the voice signal in the meeting content and enhance it;
[0140] The second extraction submodule 3012 is used to determine the audio track information of the project manager and extract the target audio signal of the project manager from the enhanced audio signal based on the audio track information.
[0141] The conversion submodule 3013 is used to convert the speech content corresponding to the target speech signal into text content and to logically organize the text content.
[0142] The submodule 3014 is used to obtain multiple tasks to be assigned based on the sorted text content.
[0143] The beneficial effects of the above technical solution are as follows: it can ensure the auditory clarity of the voice signal, and at the same time, it can quickly and accurately extract the project manager's unique voice signal to quickly determine the tasks to be assigned, thereby further improving work efficiency and stability. Meanwhile, by logically sorting out the text content, it can ensure the rationality and completeness of each assigned task, thereby further improving practicality.
[0144] In one embodiment, the partitioning module includes:
[0145] The first determination submodule is used to obtain the total task indicators and sub-task indicators for each task to be assigned, and to determine the task hierarchy architecture for each task to be assigned based on the total task indicators and sub-task indicators.
[0146] The second determining submodule is used to determine the total task type of each task to be assigned based on the task hierarchy architecture of each task to be assigned.
[0147] The third determination submodule is used to determine the maximum division level of each task to be assigned based on the total task type of each task to be assigned, and to determine the ideal division level of the sub-task index of each task to be assigned based on the maximum division level.
[0148] The first partitioning submodule is used to divide each task to be assigned into multi-level subtasks based on the ideal partitioning hierarchy of each task's sub-task indicators.
[0149] The beneficial effects of the above technical solution are as follows: by determining the task hierarchy architecture and maximum partitioning level of each task to be assigned, the qualification and objectivity of the subtasks to be divided for each task to be assigned are accurately determined, thereby ensuring that each task to be assigned is completed with maximum efficiency and maximum quality, and improving stability and reliability.
[0150] In one embodiment, the first determining module includes:
[0151] The fourth submodule is used to obtain the historical completed task indicator data of each participant and determine the experience information of each participant based on the indicator data.
[0152] The retrieval submodule is used to obtain the personal identity information of each participant and retrieve the enterprise professional level information of each participant from the enterprise database based on the personal identity information.
[0153] The fifth determination submodule is used to obtain the task execution indicators and task evaluation indicators for each subtask, and determine the human, intellectual and skill requirements information for each subtask based on the task execution indicators and task evaluation indicators.
[0154] The sixth sub-module is used to determine the execution complexity of each sub-task based on the information on the human, intellectual, and skill requirements of each sub-task.
[0155] The hierarchical submodule is used to classify tasks according to the company's professional level information of each participant, in descending order of level.
[0156] The allocation submodule is used to allocate execution subtasks to each participant based on the experience information of each participant and the execution complexity of each subtask according to the hierarchical results using an artificial intelligence model.
[0157] The beneficial effects of the above technical solution are: it can ensure the rationality and reliability of the personnel allocation for each sub-task, thereby meeting the basic personnel and skill requirements of each sub-task, ensuring the minimum completion limit of the sub-task, and improving practicality and stability.
[0158] In one embodiment, the second determining module includes:
[0159] The seventh submodule is used to determine the service assignment task for each participant based on the hierarchical relationship between the assigned sub-tasks of each participant and multiple tasks to be assigned.
[0160] The second sub-module is used to divide all participants into single-task participants and multi-task participants based on the service assignment tasks of each participant.
[0161] The eighth submodule is used to determine the first person to be assigned for each task based on the first task assignment of the single-task personnel.
[0162] The ninth submodule is used to determine the second personnel allocation for each task to be assigned based on the second task allocation of multi-task personnel.
[0163] The tenth determination submodule is used to determine the comprehensive personnel allocation for each task to be assigned based on the first and second personnel allocation information.
[0164] The beneficial effects of the above technical solution are: it can accurately perform intuitive personnel allocation statistics based on the multi-task division or single-task division of each participant, reducing statistical errors, improving statistical efficiency, and further enhancing practicality and stability.
[0165] Those skilled in the art should understand that the "first" and "second" in this invention simply refer to different application stages.
[0166] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0167] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A task allocation method based on artificial intelligence, characterized in that, Includes the following steps: Obtain the meeting content of the project manager and parse out the corresponding voice information. Based on the voice information, obtain multiple tasks to be assigned. Each task to be assigned is divided into multi-level sub-tasks based on its task indicators. The AI model determines the sub-tasks assigned to each participant based on their experience, company professional level, and the execution complexity of each sub-task. The personnel allocation for each task to be assigned is determined based on the hierarchical relationship between each participant's assigned sub-tasks and multiple tasks to be assigned. The process of dividing each task to be assigned into multi-level sub-tasks based on its task metrics includes: Obtain the total task metrics and sub-task metrics for each task to be assigned, and determine the task hierarchy architecture for each task to be assigned based on the total task metrics and sub-task metrics. The total task type of each task to be assigned is determined based on the task hierarchy architecture of that task. The maximum division level of each task to be assigned is determined based on the total task type of each task to be assigned, and the ideal division level of the sub-task indicators of each task to be assigned is determined based on the maximum division level. Each task to be assigned is divided into multi-level sub-tasks based on the ideal hierarchical division of the sub-task indicators of each task to be assigned. The process involves using an artificial intelligence model to determine the assigned sub-tasks for each participant based on their experience, company professional level, and the execution complexity of each sub-task. This includes: Obtain historical task completion data for each participant, and determine the experience information of each participant based on the data. Obtain the personal identification information of each participant, and retrieve the enterprise professional level information of each participant from the enterprise database based on the personal identification information; Obtain the task execution indicators and task evaluation indicators for each subtask, and determine the human, intellectual, and skill requirements for each subtask based on the task execution indicators and task evaluation indicators. The execution complexity of each subtask is determined based on the information on the human, intellectual, and skill requirements of each subtask. Tasks were categorized based on each participant's company professional level information, from highest to lowest. Based on the grading results, an artificial intelligence model assigns each participant an execution sub-task according to their experience and the execution complexity of each sub-task.
2. The task allocation method based on artificial intelligence according to claim 1, characterized in that, The process involves acquiring the project manager's meeting content and parsing the corresponding audio information. Based on this audio information, multiple tasks to be assigned are obtained, including: Record the project manager's meeting content using pre-set meeting software, extract the audio signal from the meeting content, and enhance it. Determine the project manager's audio track information, and extract the project manager's target voice signal from the enhanced voice signal based on the audio track information; The speech content corresponding to the target speech signal is converted into text content, and the text content is logically organized. Based on the sorted text content, multiple tasks awaiting assignment are obtained.
3. The task allocation method based on artificial intelligence according to claim 1, characterized in that, The process of determining the personnel allocation for each task to be assigned based on the hierarchical relationship between each participant's assigned sub-tasks and multiple tasks to be assigned includes: The service assignment tasks for each participant are determined based on the hierarchical relationship between the sub-tasks assigned to each participant and the multiple tasks to be assigned. Based on the service assignments of each participant, all participants were divided into single-task participants and multi-task participants. The first person to be assigned for each task is determined based on the first task assignment of the single-task personnel. The second personnel allocation for each task to be assigned is determined based on the second task allocation for multi-task personnel. The overall personnel allocation for each task to be assigned is determined based on the first and second personnel allocations for each task to be assigned.
4. A task allocation system based on artificial intelligence, characterized in that, The system includes: The acquisition module is used to acquire the meeting content of the project manager and parse out the corresponding voice information of the meeting content, and obtain multiple tasks to be assigned based on the voice information; The partitioning module is used to divide each task to be assigned into multi-level subtasks based on the task indicators of each task to be assigned. The first determination module is used to determine the assigned sub-tasks for each participant based on the participant's experience information, company professional level information, and the execution complexity of each sub-task using an artificial intelligence model. The second determination module is used to determine the personnel allocation for each task to be assigned based on the hierarchical relationship between each participant's assigned sub-tasks and multiple tasks to be assigned. The partitioning module includes: The first determination submodule is used to obtain the total task indicators and sub-task indicators for each task to be assigned, and to determine the task hierarchy architecture for each task to be assigned based on the total task indicators and sub-task indicators. The second determining submodule is used to determine the total task type of each task to be assigned based on the task hierarchy architecture of each task to be assigned. The third determination submodule is used to determine the maximum division level of each task to be assigned based on the total task type of each task to be assigned, and to determine the ideal division level of the sub-task index of each task to be assigned based on the maximum division level. The first partitioning submodule is used to partition each task to be assigned into multi-level subtasks based on the ideal partitioning level of each task sub-task index. The first determining module includes: The fourth submodule is used to obtain the historical completed task indicator data of each participant and determine the experience information of each participant based on the indicator data. The retrieval submodule is used to obtain the personal identity information of each participant and retrieve the enterprise professional level information of each participant from the enterprise database based on the personal identity information. The fifth determination submodule is used to obtain the task execution indicators and task evaluation indicators for each subtask, and determine the human, intellectual and skill requirements information for each subtask based on the task execution indicators and task evaluation indicators. The sixth sub-module is used to determine the execution complexity of each sub-task based on the information on the human, intellectual, and skill requirements of each sub-task. The hierarchical submodule is used to classify tasks according to the company's professional level information of each participant, in descending order of level. The allocation submodule is used to allocate execution subtasks to each participant based on the experience information of each participant and the execution complexity of each subtask according to the hierarchical results using an artificial intelligence model.
5. The task allocation system based on artificial intelligence according to claim 4, characterized in that, The acquisition module includes: The first extraction submodule is used to record the project manager's meeting content through preset meeting software, extract the voice signal in the meeting content and enhance it; The second extraction submodule is used to determine the project manager's audio track information and extract the project manager's target audio signal from the enhanced audio signal based on the audio track information. The conversion submodule is used to convert the speech content corresponding to the target speech signal into text content and to logically organize the text content. The Get submodule is used to retrieve multiple tasks to be assigned based on the sorted text content.
6. The task allocation system based on artificial intelligence according to claim 4, characterized in that, The second determining module includes: The seventh submodule is used to determine the service assignment task for each participant based on the hierarchical relationship between the assigned sub-tasks of each participant and multiple tasks to be assigned. The second sub-module is used to divide all participants into single-task participants and multi-task participants based on the service assignment tasks of each participant. The eighth submodule is used to determine the first person to be assigned for each task based on the first task assignment of the single-task personnel. The ninth submodule is used to determine the second personnel allocation for each task to be assigned based on the second task allocation of multi-task personnel. The tenth determination submodule is used to determine the comprehensive personnel allocation for each task to be assigned based on the first and second personnel allocation information.