Personalized work task management method and device, storage medium and server

Abstract

The embodiment of the invention discloses a personalized work task management method and device, a storage medium and a server, and relates to the field of logistics management. The method comprises the following steps: acquiring a work task set of a user and distributing a plurality of tasks; quantitatively calculating the complexity score of each to-be-processed task; analyzing user historical data to establish daily efficiency fluctuation information, and dividing working time into a plurality of time slices associated with effective coefficients; the matching degree of the time slice efficiency coefficient and the task complexity score is calculated, and the task with the highest matching degree is dynamically mapped to the corresponding time slice to be executed; and finally, personalized work optimization suggestions are pushed to the user according to a mapping result. According to the method, accurate matching of task difficulty and personal working efficiency fluctuation is realized through a data driving mode, the randomness of task arrangement depending on artificial experience is effectively overcome, and the task execution efficiency and the resource utilization rate are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of logistics management, and in particular to a personalized work task management method and device, a storage medium and a server. BACKGROUND

[0002] With the continuous expansion of the business scale of logistics enterprises, the number of work tasks that employees need to handle daily has increased significantly, and the complexity of work has also increased. In the current work mode, employees usually arrange the daily work order and rhythm according to personal experience and subjective habits. This task arrangement method relying on personal intuition cannot adapt to the dynamic changes of daily work state, which easily leads to large fluctuations in work efficiency and uneven task completion quality, thereby restricting the improvement of overall organizational effectiveness. SUMMARY

[0003] Embodiments of the present application provide a personalized work task management method, device, storage medium and server, which can solve the problem of low efficiency caused by employees arranging work plans by themselves in the prior art. The technical solution is as follows: In a first aspect, the embodiments of the present application provide a personalized work task management method, which comprises: obtaining a work task set of a user; selecting multiple work tasks in the work task set and assigning them to the user; calculating the complexity score of each pending task of the user; determining the daily efficiency fluctuation information of the user; the daily efficiency fluctuation information indicates that the working time period of the user is divided into multiple time slices, and each time slice is associated with an efficiency coefficient; mapping the time slice and the pending task with the highest matching degree between the efficiency coefficient of the time slice and the complexity score of the pending task according to the matching degree; pushing work optimization suggestions to the user according to the mapping result of the pending task and the time slice.

[0004] In a second aspect, the embodiments of the present application provide a personalized work task management device, which comprises: an obtaining unit configured to obtain a work task set of a user; an assigning unit configured to select multiple work tasks in the work task set and assign them to the user; a calculating unit configured to calculate the complexity score of each pending task of the user; a determining unit configured to determine the daily efficiency fluctuation information of the user; the daily efficiency fluctuation information indicates that the working time period of the user is divided into multiple time slices, and each time slice is associated with an efficiency coefficient; mapping unit, configured to map a time slice and a to-be-processed task with the highest matching degree according to matching degrees between efficiency coefficients of the time slice and complexity scores of the to-be-processed tasks; pushing unit, configured to push a work optimization suggestion to the user according to a mapping result of the to-be-processed task and the time slice.

[0005] In a third aspect, an embodiment of the present application provides a computer storage medium, which stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and performing the method steps described above.

[0006] In a fourth aspect, an embodiment of the present application provides a terminal device, which can include a processor and a memory, wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and performing the method steps described above.

[0007] The technical scheme provided by some embodiments of the present application has at least the following beneficial effects: The present application divides the user's working time into time slices with different efficiency coefficients by establishing a daily efficiency fluctuation model based on historical data, and dynamically maps tasks with quantified complexity scores to the most suitable time slices. This matching mechanism can ensure that high-complexity tasks are executed during the user's high-efficiency period, and low-complexity tasks are processed during the low-efficiency period, thereby significantly improving the efficiency and quality of task completion.

[0008] The present application quantitatively analyzes the complexity of tasks and the efficiency curve of the user, and changes the task arrangement from subjective experience judgment to data-driven objective decision-making. This method overcomes the randomness and blindness in manual arrangement, effectively avoids the waste of resources caused by task and state mismatch, and makes the work arrangement more reasonable and predictable.

[0009] The present application not only completes the initial task mapping, but also continuously pushes personalized work optimization suggestions according to the actual execution. This dynamic adjustment mechanism enables the system to continuously adapt to changes in the user's working state, promotes continuous improvement of the working mode, and thus realizes the spiral rise of individual and organizational effectiveness.

[0010] In summary, the present application improves the rationality and execution efficiency of work task arrangement through intelligent and personalized task scheduling mechanism, and provides reliable technical support for optimizing human resource allocation. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0012] Figure 1 is a network architecture schematic diagram provided by the embodiments of the present application; Figure 2 is a flowchart of a personalized work task management method provided by the embodiments of the present application; Figure 3 is a structural schematic diagram of a personalized work task management device provided by the present application; Figure 4 is a schematic diagram of a computer storage medium provided by the embodiments of the present application; Figure 5 is a structural schematic diagram of a server provided by the present application. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solutions and advantages of the present application more clear, the following will further describe the embodiments of the present application in combination with the drawings.

[0014] It should be noted that the personalized work task management method provided by the present application is generally executed by a server, and correspondingly, the personalized work task management device is generally arranged in the server.

[0015] Figure 1 An exemplary system architecture that can be applied to the personalized work task management method or the personalized work task management device of the present application is shown.

[0016] As shown in Figure 1 , the system architecture can include a terminal device 101 and a server 102. The terminal device 101 and the server 102 can communicate through a network, and the network is a medium for providing a communication link between the above-mentioned units. The network can include various types of wired communication links or wireless communication links, for example, the wired communication links include optical fiber, twisted pair or coaxial cable, etc., and the wireless communication links include Bluetooth communication link, wireless fidelity (WIreless-FIdelity, Wi-Fi) communication link or microwave communication link, etc.

[0017] Among them, the employees of the enterprise log in to the server 102 through the terminal device 101, the server 102 schedules the to-be-processed tasks of the employees, pushes personalized work optimization suggestions to the employees through short messages, AI private assistants, incoming calls or other ways, helps the employees to continuously grow and progress in work, and thus improves the overall operation efficiency of the enterprise.

[0018] It should be noted that the terminal device 101 and the server 102 can be hardware or software. When the terminal device 101 and the server 102 are hardware, they can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the terminal device 101 and the server 102 are software, they can be implemented as multiple software or software modules (for example, to provide distributed services), or as a single software or software module, which is not specifically limited here.

[0019] Various communication client applications can be installed on the terminal device of the present application, such as video recording applications, video playing applications, voice interaction applications, search applications, instant messaging tools, mailbox clients, social platform software, etc.

[0020] The terminal device can be hardware or software. When the terminal device is hardware, it can be various terminal devices with display screens, including but not limited to smart phones, tablet computers, laptop computers and desktop computers, etc. When the terminal device is software, it can be installed in the terminal devices listed above. It can be implemented as multiple software or software modules (for example, to provide distributed services), or as a single software or software module, which is not specifically limited here.

[0021] When the terminal device is hardware, it can also be installed with a display device and a camera. The display device can be various devices that can realize display functions, and the camera is used to collect video streams; for example, the display device can be a cathode ray tube display (CR), a light-emitting diode display (LED), an electronic ink screen, a liquid crystal display (LCD), a plasma display panel (PDP), etc. Users can use the display device on the terminal device to view displayed text, pictures, videos, etc.

[0022] It should be understood that Figure 1 The number of terminal devices, networks and servers in the above-mentioned system is only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks and servers.

[0023] The embodiments of the present application will be described below with reference to the accompanying drawings. Figure 2 The personalized work task management method provided by the embodiments of the present application will be described in detail. The personalized work task management device in the embodiments of the present application can be a server as shown in the figure. Figure 1

[0024] Please refer to Figure 2 A flowchart of a personalized work task management method provided by the embodiments of the present application is shown. As shown in the figure, the method of the present application can include the following steps: Figure 2 S201, obtaining a user's work task set.

[0025] Among them, the server performs the operation of obtaining the user's work task set. The process starts with the server receiving a request from the client or an internal scheduling module, which contains the user's unique identifier, such as user ID or session token. The server first verifies the legality of the request and the user's identity, ensuring that the access rights meet the security policy.

[0026] Subsequently, the server is connected to the backend data storage system, which is usually a relational database or a distributed storage service. The server constructs a query statement to filter the relevant work task records based on the user identifier. The query may involve multiple data tables or collections, including task basic information, assignment status and user association data. The server executes the query operation to retrieve the matching task entries from the storage system.

[0027] During the retrieval process, the server may apply data preprocessing steps such as filtering invalid tasks, deduplication or sorting to ensure the integrity and consistency of the set. The data obtained includes task attributes such as task name, description, priority, deadline and current status. The server encapsulates these data into a structured work task set, ready for subsequent processing.

[0028] Finally, the server temporarily stores the obtained work task set in memory or cache to improve the access efficiency of subsequent steps. The entire execution process focuses on performance and reliability, and the server may implement a timeout mechanism or a retry strategy to cope with network delays or storage system failures.

[0029] For example: Suppose the server needs to obtain the work task set of user Zhang San. The unique identifier of user Zhang San is UID_1001. After receiving the request to obtain the task set, the server first verifies the validity of UID_1001 and confirms that the user has access rights.

[0030] ​​The server then connects to the configured MySQL database, which stores all user's task data. The server constructs a SQL query statement to filter task records from the task table with user ID equal to UID_1001 and status as pending or in progress. After the query is executed, the database returns three task data, which are task A, task B and task C, each record contains task ID, name and priority, etc.

[0031] S202, select a plurality of work tasks in the set of work tasks to assign to the user.

[0032] In step S202, the server performs the operation of selecting specific tasks from the acquired set of work tasks to assign to the current user. This process is the core decision-making link of task scheduling, and the goal is to filter a subset from all available tasks for the user that is most suitable for the user to execute in the current period.

[0033] The server first loads the complete set of work tasks obtained in step S201. Then, the server starts a multi-dimensional evaluation process to comprehensively analyze each task in the set according to the preset assignment strategy. The key attributes for evaluation usually include the urgency of the task, the preset priority label, the time to the final deadline, the approximate man-hours required to complete the task, the matching degree of the skill field required by the task and the user's own skill profile, and the total workload currently undertaken by the user.

[0034] The server may maintain a weighted scoring algorithm internally to assign appropriate weights to each evaluation dimension. For example, the urgency and priority of the task may have higher weights. The server calculates a comprehensive score for each task in the set, which quantifies the suitability of the task for the user at this moment.

[0035] Based on the comprehensive score, the server sorts the tasks and selects a specified number of tasks from the top of the sorted list according to the daily work capacity defined in the system configuration or user preferences, for example, a maximum of five tasks. These selected tasks constitute the work task list assigned to the user this time. The server then updates the status of these tasks, marking them as assigned to the user, and persists the assignment result to the database to ensure state consistency. This assignment decision aims to optimize the balance between overall work efficiency and user work experience.

[0036] For example, assume that the server has obtained a set of work tasks for user Li Si, which contains seven tasks, numbered from T1 to T7. The server needs to select three tasks to assign to Li Si for processing today.

[0037] The server initiates an evaluation process to examine the attributes of each task. For example, task T1 has a high priority and a deadline today, but the required skills only partially match Li's skills. Task T2 has a medium priority and a deadline in two days, with a complete match of required skills to Li's skills. Task T3 has a low priority and a deadline in a week. Task T4 has a high priority but is expected to take 8 hours, far exceeding Li's available work hours today.

[0038] After weighted scoring calculation, task T2 scores the highest due to perfect skill match and moderate deadline, task T1 scores second due to high priority and urgent deadline, and task T5 scores third due to good load balancing. Task T4 is excluded due to excessive time consumption, and task T3 is excluded due to low priority.

[0039] Therefore, the server finally selects tasks T2, T1, and T5 to form the allocation list. The server updates the status of these three tasks as assigned to user Li and records this allocation decision in the task management database. In this way, Li will clearly see these three assigned tasks in his work list today.

[0040] S203, calculate the complexity score of each pending task of the user.

[0041] Among them, the server performs the operation of calculating the complexity score of each pending task of the user. This process aims to quantitatively evaluate the difficulty of the task, providing accurate data basis for subsequent task scheduling.

[0042] The server first extracts the key attributes of each task from the list of assigned pending tasks of the user. These attributes form the basic dimensions of complexity evaluation, usually including the estimated time consumption of the task, the types and levels of required skills, the inherent difficulty coefficient of the task type, the number of external factors involved, the average completion time of historical similar tasks, and the clarity of task instructions, etc.

[0043] Subsequently, the server calls the built-in complexity calculation model. This model may be a scoring system based on a rule engine or a lightweight machine learning model trained using historical data. The model assigns appropriate weights to each evaluation dimension, such as task time consumption or environmental uncertainty, which may occupy a larger weight. The server inputs the multi-dimensional attribute data of each task into the model, which performs comprehensive operations through internal algorithms to output a quantitative complexity score. This score is usually normalized to a pre-set numerical range, such as 0 to 10 points, to facilitate subsequent comparison and matching.

[0044] After calculation, the server establishes a mapping relationship between each pending task and its corresponding complexity score, and stores these data in a cache or memory data structure to ensure efficient access in subsequent steps.

[0045] For example, assume the user is a delivery man named Li Si from a logistics company, and there are two tasks to be handled, Task A and Task B.

[0046] The server first analyzes the attributes of Task A. Task A is to deliver a batch of high-priority packages to the downtown business district, with an estimated working time of 3 hours, requiring skills in navigating complex urban routes and handling unexpected traffic conditions, and the task type is urgent delivery (with a higher difficulty coefficient built into the system). It needs to handle multiple recipient sign-offs and possible route adjustments. Historical data shows that the average completion time for similar tasks is 2.5 hours.

[0047] Next, the server analyzes the attributes of Task B. Task B is to perform daily package sorting and scanning in the warehouse, with an estimated working time of 1 hour, requiring basic operation skills and concentration, and the task type is routine operation (with a lower difficulty coefficient built into the system). The working environment is stable and the process is standardized.

[0048] The server inputs the attribute data of Task A and Task B into the complexity calculation model. The model calculates the overall complexity according to the weight of each dimension. Finally, Task A gets a higher complexity score, for example 8.0, due to its longer time-consuming, high skill requirements, and many environmental variables. Task B gets a lower complexity score, for example 2.5, due to its simplicity and repetition. The server associates these two scores with Task A and Task B respectively, preparing for the next step of efficiency matching.

[0049] S204, determine the user's daily efficiency fluctuation information; the daily efficiency fluctuation information indicates that the user's working time period is divided into multiple time slices, and each time slice is associated with an efficiency coefficient.

[0050] Among them, the server performs the operation of determining the user's daily efficiency fluctuation information. This process aims to establish a model of the user's personal work efficiency changes within a day, providing a time dimension basis for fine task scheduling.

[0051] The server first obtains the user's historical work efficiency data. These data come from the historical records of the task management system, including the user's past start time, end time, task type, and completion quality of each task. The server preprocesses these raw data, including data cleaning to exclude outliers and invalid records, and formats the time stamp according to a unified standard.

[0052] Next, the server divides the user's standard work period into several consecutive time slices. The division strategy is usually based on business needs, for example, taking one hour or half an hour as a basic unit. After the division is complete, the server analyzes the user's task completion in the corresponding time period on all historical working days for each time slice. The analysis indicators mainly include the average task completion speed, task accuracy rate, and output per unit time.

[0053] Based on these analysis indicators, the server calculates an efficiency coefficient for each time slice. The calculation process may use standardization methods to convert the original data into relative values between 0 and 1, where 1 represents the user's highest efficiency in that time period. The determination of the efficiency coefficient may combine statistical methods, such as calculating the ratio of the time period indicator value to the average value of the whole day, or applying simple regression analysis to fit the efficiency change curve.

[0054] Finally, the server generates the user's daily efficiency fluctuation information, which is a data structure composed of a sequence of time slices and their corresponding efficiency coefficients. These information is stored and can be used for real-time query, forming the user's personal work efficiency portrait.

[0055] For example: Take a courier of a logistics company, Mr. Zhang, as an example. The server needs to determine his daily efficiency fluctuation information on working days. Mr. Zhang's standard working time is from 8 am to 6 pm.

[0056] The server first retrieves Mr. Zhang's work data in the past three months, including the delivery records of thousands of packages, each record has the delivery start time, completion time and customer feedback score. The server divides the 10 hours of work time into 10 one-hour time slices.

[0057] Subsequently, the server analyzes the data of each time slice. The analysis found that during the period from 9 am to 11 am (time slices 2 and 3), Mr. Zhang delivered the most packages, with the shortest average time and the highest customer rating. While at 1 pm to 2 pm (time slice 6), due to the decline in energy after lunch, the indicators slightly decreased. By 4 pm to 5 pm (time slice 9), the efficiency indicators again showed a significant decline due to the proximity to the end of the workday and the evening traffic peak.

[0058] Based on this, the server assigns an efficiency coefficient to each time slice. The efficiency coefficient from 9 am to 11 am is set to the highest, at 0.95 and 0.98. The efficiency coefficient from 1 pm to 2 pm is 0.85. The efficiency coefficient from 4 pm to 5 pm is 0.75. And other time periods are assigned coefficients between 0.8 and 0.9 according to specific data. In this way, the server successfully builds Mr. Zhang's daily efficiency fluctuation model, clearly depicting the ups and downs of his work efficiency throughout the day.

[0059] S205, according to the matching degree between the efficiency coefficient of the time slice and the complexity score of the to-be-processed task, mapping the time slice and the to-be-processed task with the highest matching degree.

[0060] Among them, the server performs the operation of task mapping based on the matching degree between the time slice efficiency coefficient and the to-be-processed task complexity score. This process is a dynamic iterative scheduling loop, aiming to optimize task allocation in real time to adapt to the fluctuations in user work efficiency.

[0061] The server first initializes the scheduling process at the start of the user's working time. At this time, the server obtains the efficiency coefficient of the current time slice, which comes from the pre-determined daily efficiency fluctuation information. At the same time, the server loads the complexity score list of all to-be-processed tasks.

[0062] Next, the server calculates the matching degree between the efficiency coefficient of the current time slice and the complexity score of each to-be-processed task. The matching degree calculation usually adopts a numerical comparison method, such as calculating the absolute difference between the efficiency coefficient and the complexity score. The smaller the absolute difference, the higher the degree of adaptation between the two, i.e. the better the matching degree. The server generates a matching degree value for each task.

[0063] Specifically, the process of calculating the matching degree between the to-be-processed task and the time slice includes: The server first obtains the efficiency coefficient of the current time slot, which comes from the pre-determined daily efficiency fluctuation information, and is a value between 0 and 1, representing the relative work efficiency of the user in that time period. At the same time, the server loads the list of all to-be-processed tasks, each task associated with a complexity score, which is usually between 0 and 10, quantifying the difficulty level of the task.

[0064] The matching degree calculation is realized by a numerical comparison method. The server calculates the absolute difference between the complexity score of each to-be-processed task and the efficiency coefficient of the current time slot. The calculation method of the absolute difference is the absolute value of the efficiency coefficient minus the complexity score. The smaller the value, the closer the efficiency coefficient and the complexity score, and the higher the matching degree. The server generates an absolute difference value for each task, and then compares the absolute difference values of all tasks to identify the task with the smallest absolute value, which is the task with the highest matching degree.

[0065] Then, the server compares the matching degree values of all to-be-processed tasks and identifies the task with the optimal matching degree, i.e. the task with the smallest absolute difference. The server binds and maps this task to the current time slice, which means that the task is scheduled to be executed within this time slice. The server updates the task status to in progress and starts monitoring the execution progress of the task.

[0066] When the server detects that the task is completed, it records the specific time when the task is finished. The server queries the time slice to which this time belongs and takes it as the new current time slice. Then, the server repeats the matching degree calculation and selection process described above, but this time only for the remaining tasks to be processed. The server calculates the matching degree between the efficiency coefficient of the new time slice and the complexity score of the remaining tasks, and selects the task with the best matching degree again for mapping.

[0067] S206, according to the mapping result of the task to be processed and the time slice, and push the work optimization suggestion to the user.

[0068] Among them, the server performs the operation of generating work optimization suggestions according to the mapping result of the task to be processed and the time slice and pushing to the user. This process is the end of the task scheduling process, aiming to improve the user's work efficiency through data analysis.

[0069] The server first loads the task and time slice mapping records completed in step S205. These records describe in detail the tasks executed within each time slice and their corresponding complexity scores and efficiency coefficients. The server systematically analyzes these mapping data, focusing on the quality of the mapping matching degree, the timing rationality of task execution, and the utilization of efficiency coefficients. For example, the server assesses whether high-complexity tasks are successfully allocated to the user's high-efficiency time slices or whether there are mapping deviations that result in resource waste.

[0070] Based on the analysis results, the server starts the suggestion generation logic. This logic may be based on a predefined rule base or statistical analysis model. The server identifies potential optimization points, such as opportunities for adjusting task order, suggestions for improving time slice division, or optimization prompts for user work habits. The suggestion content is specific, such as recommending to prioritize complex tasks during specific high-efficiency periods, or scheduling breaks or simple transactions during low-efficiency periods. When generating suggestions, the server considers historical performance data and current mapping effects to ensure the practicality and individualization of the suggestions.

[0071] After the suggestion is generated, the server sends the optimization suggestion to the user through the integrated message push service. The push channel may include enterprise internal communication systems, email, or mobile application notifications. The server ensures that the message format is clear and easy to read, and includes necessary context information such as related time slices or task details. The entire push process focuses on timeliness and non-intrusiveness, avoiding interference with the user's normal work.

[0072] Finally, the server records the log of this suggestion push, including the push time, suggestion content, and user feedback mechanism, to optimize the suggestion generation algorithm for subsequent optimization. This step closes the task scheduling process, achieving continuity from execution to improvement.

[0073] For example, take Zhao Ming, a sales staff of a logistics company. Suppose in step S205, the server has completed the mapping of Zhao Ming's daily tasks and time slices. The mapping result shows that the efficiency coefficient of the time slice from 9 am to 10 am is 0.9, and task A (complexity score 8 points) is assigned to this time slice, i.e. contacting major customers to negotiate contracts; the efficiency coefficient of the time slice from 3 pm to 4 pm is 0.7, and task B (complexity score 4 points) is assigned to this time slice, i.e. handling daily email replies.

[0074] The server analyzes the mapping result and finds that task A matches the high-efficiency time slice well, but task B is assigned to a low-efficiency time slice, which may not fully utilize the peak period. In addition, the server compares historical data and finds that Zhao Ming's efficiency is generally low in the afternoon, but the current mapping does not take into account rest adjustments.

[0075] Based on this, the server generates a work optimization suggestion. The suggestion includes: first, it recommends that simple tasks like task B be concentrated in the afternoon low-efficiency period, and suggests adding a short break in the afternoon to restore energy; second, it suggests that Zhao Ming reserve more time for complex sales tasks in the morning high-efficiency period to improve overall output.

[0076] The server pushes this optimization suggestion to Zhao Ming's office computer and mobile application in the form of a text message through the company's instant messaging tool. The message clearly lists the main points of the suggestion and includes a summary of the daily mapping results for Zhao Ming's reference. In this way, Zhao Ming can adjust his work plan for the next day according to the suggestion and gradually optimize his personal work efficiency.

[0077] In some embodiments, the mapping method between the tasks to be processed and the time slices includes: When the start time of the work period arrives, calculate the matching degree between the efficiency coefficient of the first time slice and the complexity score of each task to be processed of the user, determine the task to be processed with the largest matching degree according to the calculation result, map the task to be processed to the first time slice, set the task to be processed as a processed task when it is detected to be completed, determine the end time of the processed task, query the time slice corresponding to the end time in the work period, calculate the matching degree between the efficiency coefficient of the time slice and the complexity score of each task to be processed of the user, determine the task to be processed with the largest matching degree according to the calculation result, map the task to be processed to the queried time slice, and set the task to be processed as a processed task when it is detected to be completed; until the work period ends or all tasks to be processed of the user are completed.

[0078] Specifically, the server performs a dynamic task scheduling process that maps tasks to time slices in real-time based on the matching degree between the efficiency coefficient of a time slice and the complexity score of a pending task. The entire process runs in an iterative manner, ensuring that task allocation is synchronized with user productivity fluctuations.

[0079] The server first starts the scheduling loop at the beginning of the user's work hours. At this time, the server obtains the efficiency coefficient of the first time slice, which is derived from pre-computed daily productivity fluctuation information. Meanwhile, the server loads a list of all pending tasks, each associated with a calculated complexity score.

[0080] Next, the server calculates the matching degree between the efficiency coefficient of the first time slice and the complexity scores of each pending task. The matching degree is determined through numerical comparison methods, such as calculating the absolute difference between the efficiency coefficient and the complexity score. The smaller the absolute difference, the higher the matching degree, indicating better suitability of the task for the time slice. The server generates a matching degree value for each task and compares these values to select the task with the highest matching degree, i.e., the task with the smallest absolute difference.

[0081] The server maps the selected task to the first time slice, meaning the task is officially scheduled to be executed within this time slice. The server updates the task's status to in progress and initiates a monitoring mechanism to continuously detect the task's execution progress. Monitoring can be achieved through user input or system automatic feedback.

[0082] When the server detects that the task has completed execution, it records the end time of the task. The server queries the time slice to which the end time belongs within the user's work hours and takes it as the new current time slice. Subsequently, the server repeats the matching degree calculation process, but this time only for the remaining pending tasks. The server calculates the matching degree between the efficiency coefficient of the new time slice and the complexity scores of the remaining tasks and again selects the task with the highest matching degree for mapping.

[0083] This iterative process continues, with each task completion triggering a re-evaluation and re-allocation. The server ensures that each mapping is based on the latest time slice and task status. The loop terminates when the user's work hours end or all pending tasks have been executed. In this way, the server implements an adaptive scheduling mechanism that optimizes task execution order to improve overall efficiency.

[0084] Taking a courier of a logistics company as an example, assume that his working hours are from 8:00 am to 5:00 pm, and the server has divided this period into 9 one-hour time slices. The daily efficiency fluctuation information shows that the efficiency coefficient of time slice 1 is 0.9, that of time slice 2 is 1.0, and that of time slice 3 is 0.9, and the efficiency coefficients of subsequent time slices gradually decrease. The courier currently has 3 tasks to be processed, task 1 is to deliver a batch of urgent parcels, the complexity score is 9 points; task 2 is to arrange the daily route, the complexity score is 5 points; and task 3 is to handle customer inquiries, the complexity score is 3 points.

[0085] At the start time of 8:00 am, the server starts scheduling. The current time slice is time slice 1, and the efficiency coefficient is 0.9. The server calculates the matching degree, that is, the absolute difference between the efficiency coefficient and the task complexity score. The difference of task 1 is 8.1, that of task 2 is 4.1, and that of task 3 is 6.1. The difference of task 2 is the smallest, and the matching degree is the highest, so the server maps task 2 to time slice 1.

[0086] Suppose task 2 is completed at 9:30 am, and the server records the end time. This time belongs to time slice 2, and the efficiency coefficient is 1.0. The server calculates the matching degree of the efficiency coefficient of time slice 2 and the remaining tasks 1 and 3. The difference of task 1 is 8.0, and that of task 3 is 7.0. The difference of task 3 is smaller, and the matching degree is higher, so the server maps task 3 to time slice 2.

[0087] Task 3 is completed at 10:40 am, and time slice 3 is entered, with an efficiency coefficient of 0.9. The server calculates the matching degree with the only remaining task 1, the difference is 8.1, and then maps task 1. This process continues until all tasks are completed or the workday ends, thereby achieving efficient task allocation.

[0088] In some embodiments, the selecting a plurality of work tasks from the set of work tasks to assign to the user comprises: According to the historical work records of the user, the daily average work amount of the user is counted; According to the daily average work amount, a plurality of work tasks are selected from the set of work tasks, and the selected work tasks are assigned to the user.

[0089] Specifically, when the server performs work task allocation, it first needs to quantitatively evaluate the work capacity of the user. This process begins with a deep analysis of the user's historical work records. The server extracts the complete work data of this user in the past statistical period from the historical database of the task management system, which includes the number of tasks completed each day, task type, actual time consumption, and completion quality, and other key indicators.

[0090] Based on these historical data, the server initiates a statistical analysis process to calculate the user's daily average workload. This calculation is not a simple arithmetic mean, but a weighted average algorithm, with more recent data being given a higher weight to reflect the user's latest work status. At the same time, the server will perform data cleaning to exclude records of holidays or abnormal working days, ensuring the representativeness and accuracy of the statistical results. The final daily average workload is a comprehensive value that quantifies the total amount of work the user can usually complete in a standard working day.

[0091] After obtaining the daily average workload, the server enters the task selection phase. The server converts each task in the user's current task set into a standard workload unit, which is based on factors such as the estimated man-hours, complexity, and resource requirements of the task. Subsequently, the server performs workload matching calculations to select a group of tasks from the task set, so that the total standard workload of this group of tasks is basically consistent with the user's daily average workload. The selection process also considers the priority attributes of the tasks, the urgency of the deadlines, and the logical association between tasks to ensure that the assigned task combination is not only moderate in total amount but also reasonable in structure.

[0092] Finally, the server formally assigns the selected task set to the user, updates the task status to assigned, and persists the assignment result. The entire assignment decision is automatically completed by the server, forming a data-driven task assignment mechanism.

[0093] This embodiment realizes personalized task assignment through a data-driven approach, effectively avoiding excessive or insufficient user workload, improving task completion efficiency and quality, and optimizing human resource allocation.

[0094] In some embodiments, the task to be processed is a package delivery task. The calculation of the complexity score of each task to be processed by the user includes: The complexity score of the package delivery task = (w_d * d + w_n * n + w_w * w + w_t * t); where d represents the delivery distance of the task, n represents the number of packages of the task, w represents the average weight of the packages of the task, and t represents the traffic factor of the task, with a value range of 1-10, where 1 represents smooth traffic and 10 represents traffic congestion; w_d, w_n, w_w, and w_t represent weight coefficients, used to adjust the contribution of each factor, and the sum of the weights is 1.

[0095] Specifically, when the server performs the operation of calculating the complexity score of a package delivery task, it first obtains the attribute data of each pending task from the task management system. These data include the delivery distance, the number of packages, the average package weight, and the traffic factor. The delivery distance is usually in kilometers and is derived from a geographic information system; the number of packages and the average weight come from the warehouse database; and the traffic factor is obtained through real-time traffic APIs or historical data analysis, with a value ranging from 1 to 10, where 1 represents smooth traffic and 10 represents heavy traffic.

[0096] The server is pre-configured with a set of weight coefficients, including the delivery distance weight, the number of packages weight, the average weight weight, and the traffic factor weight. The sum of these weight coefficients is 1, and their values are set based on business rules or historical optimization models to balance the contribution of each factor to the complexity. The server normalizes the attribute values of each task to ensure that data of different dimensions are comparable, such as converting distance, quantity, weight, and traffic factor to a unified scale.

[0097] Subsequently, the server applies a weighted summation algorithm to calculate the complexity score. Specifically, the server multiplies the delivery distance by the corresponding weight, the number of packages by the corresponding weight, the average package weight by the corresponding weight, and the traffic factor by the corresponding weight, and then adds the four products to obtain the final complexity score. This score is a continuous value that quantifies the difficulty of the task.

[0098] This multi-factor weighted complexity score calculation method adopted by the embodiment can more accurately reflect the actual difficulty of the task, improve the scientificity of task allocation, and thus optimize resource utilization efficiency, enhance the reliability of delivery services, and improve user satisfaction.

[0099] In some embodiments, the server periodically updates the user's daily efficiency fluctuation information, and the updating method includes: Periodically collecting the user's work situation data on multiple historical working days using a sliding window method, the work situation data including: task start time, task end time, task type, and task quality score; According to a preset division rule, the working time period of the user is divided into multiple time slices; For each historical working day, the total workload of the historical working day is counted, and the workload completed in each time slice is counted; The workload completed in the time slice is divided by the total workload of the historical working day to obtain the efficiency coefficient of the time slice.

[0100] The server performs a calculation process of daily efficiency fluctuation information. First, it periodically collects historical work data of the user using a sliding window mechanism. The sliding window covers multiple historical workdays, such as the last thirty workdays. The server retrieves task records for each workday from a task management database or a work log system. These records include task start time, task end time, task type, and task quality score. The server cleans and verifies the data, excluding abnormal or invalid records to ensure data quality.

[0101] Next, the server divides the user's standard working time period into multiple consecutive time slices according to a preset division rule. The division rule is based on business needs, such as uniformly dividing the workday from start time to end time into fixed-length intervals, such as one time slice per hour. Each time slice represents a specific time period, and the server assigns a unique identifier to each time slice.

[0102] For each historical workday, the server calculates the total workload of that day. The workload is calculated based on task attributes, which may consider the number of tasks, task duration, or weighted combination of task quality scores. For example, the total workload can be defined as the sum of the quality scores of all tasks. At the same time, the server calculates the workload completed in each time slice, which is the sum of the workloads of the tasks that end within that time slice. The workload calculation process involves time matching, where the server maps the end time of a task to the corresponding time slice.

[0103] Then, the server calculates the efficiency coefficient for each time slice. The efficiency coefficient is obtained by dividing the workload completed in the time slice by the total workload of that historical workday. This coefficient represents the relative efficiency contribution of that time slice in the workday. The server repeats this process for all historical workdays and calculates the average efficiency coefficient for each time slice to form the user's daily efficiency fluctuation model. The final result is stored in the server cache for subsequent task scheduling.

[0104] This embodiment can accurately quantify the daily changes in user work efficiency, providing a scientific basis for dynamic task allocation, thereby optimizing the work process and improving overall performance.

[0105] In some embodiments, the pushing of the work optimization suggestion to the user includes: According to the user's account login state, the corresponding message push channel is queried; the message push channel includes: the push message of the AI private assistant, the short message, or the loudspeaker of the place where the user is located; According to the message push channel, the work optimization suggestion is pushed to the user.

[0106] Specifically, the server performs the operation of pushing work optimization suggestions to the user. The process begins with the server determining the most appropriate message push channel based on the user's account login status. The server first queries the user's current login status, which is achieved by checking the authentication service or session management system, to confirm whether the user is online, the type of device being used, and geographic location information.

[0107] Based on the login status query result, the server retrieves the pre-set message push channel configuration. These channels include push messages from AI personal assistants, short message services, or speaker systems in the user's location. The server intelligently selects the channel based on the user's status, for example, if the user is online and active in the mobile application, the AI personal assistant's push message is preferred; if the user is offline or the device is unreachable, the short message channel is switched to; if the user is located in a fixed workplace such as a warehouse or office, the use of the location speaker for audio prompts is considered.

[0108] After determining the push channel, the server formats the work optimization suggestion content. The suggestion text is generated based on the task mapping analysis result, ensuring that the information is concise and clear. The server sends the message by integrating the API interface of the corresponding channel, such as calling the push service provider interface to send mobile notifications, or sending text messages through the SMS gateway, or controlling the Internet of Things device to trigger the speaker broadcast.

[0109] This embodiment ensures that work optimization suggestions can be timely and accurately delivered to users through this multi-channel adaptive push mechanism, improving task execution efficiency, enhancing system usability and user experience.

[0110] In some embodiments, the obtaining the set of work tasks of the user comprises: Obtaining the identity information of the user, querying the corresponding post type information according to the identity information, and querying the corresponding set of work tasks according to the post type information.

[0111] Specifically, in step S201, the server performs the operation of obtaining the set of work tasks of the user. The process begins with the server receiving a task scheduling request, which contains the user's identity identifier, such as the user ID or login token. The server first verifies the validity and authority of the identity information to ensure that the request comes from a legitimate source.

[0112] Subsequently, the server connects to the user information database and uses the identity identifier as a query key to retrieve the corresponding post type information. Post type information is usually stored in a user profile table or organizational structure table, including post name, responsibility description, and associated attributes. The server performs the query operation to extract the user's post type.

[0113] After obtaining the job type information, the server further connects to the work task management system or task database. The server constructs query conditions based on the job type information to filter work task records related to the job. The query may involve task assignment tables, task type mapping tables, and other data sources to ensure that the returned task set matches the job responsibilities. The server integrates the query results to form a structured work task set, including basic information such as task name, priority, and status.

[0114] This embodiment precisely filters tasks by job type, ensuring that task assignments are highly matched with user responsibilities, improving work relevance and efficiency, and reducing irrelevant task interference.

[0115] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the apparatus embodiments of the present application, please refer to the method embodiments of the present application.

[0116] Please refer to Figure 3 , which shows a structural schematic diagram of a personalized work task management apparatus provided by one exemplary embodiment of the present application, hereinafter referred to as apparatus 3. The apparatus 3 can be realized by software, hardware, or a combination of both to become all or part of a server. The apparatus 3 includes: The acquisition unit 301 is configured to acquire a work task set of a user. The assignment unit 302 is configured to select multiple work tasks in the work task set and assign them to the user. The calculation unit 303 is configured to calculate a complexity score of each pending task of the user. The determination unit 304 is configured to determine day efficiency fluctuation information of the user. The day efficiency fluctuation information indicates that the working time period of the user is divided into multiple time slices, and each time slice is associated with an efficiency coefficient. The mapping unit 305 is configured to map a time slice and a pending task with the highest matching degree according to the matching degree between the efficiency coefficient of the time slice and the complexity score of the pending task. The push unit 306 is configured to push work optimization suggestions to the user according to the mapping result of the pending task and the time slice.

[0117] In one or more possible embodiments, the mapping of a time slice and a pending task with the highest matching degree according to the matching degree between the efficiency coefficient of the time slice and the complexity score of the pending task includes: At the beginning of the working time period, the matching degree between the efficiency coefficient of the first time slice and the complexity score of each to-be-processed task of the user is calculated, the to-be-processed task with the maximum matching degree is determined according to the calculation result, the to-be-processed task is mapped to the first time slice, the to-be-processed task is set as a processed task when the to-be-processed task is detected to be executed, the end time of the processed task is determined, the time slice corresponding to the end time in the working time period is queried, the matching degree between the efficiency coefficient of the time slice and the complexity score of each to-be-processed task of the user is calculated, the to-be-processed task with the maximum matching degree is determined according to the calculation result, the to-be-processed task is mapped to the queried time slice, and the to-be-processed task is set as a processed task when the to-be-processed task is detected to be executed, until the working time period ends or all to-be-processed tasks of the user are executed.

[0118] In one or more possible embodiments, the selecting a plurality of working tasks from the set of working tasks and assigning the selected working tasks to the user comprises: According to the historical working records of the user, the daily average working amount of the user is counted; According to the daily average working amount, a plurality of working tasks are selected from the set of working tasks, and the selected working tasks are assigned to the user.

[0119] In one or more possible embodiments, the to-be-processed task is a package delivery task. The complexity score of each to-be-processed task of the user is calculated, comprising: The complexity score of the package delivery task is (w_d*d+w_n*n+w_w*w+w_t*t), wherein d represents the delivery distance of the task, n represents the number of packages of the task, w represents the average weight of the packages of the task, and t represents the traffic factor of the task, and the value range of t is 1-10, 1 represents smooth traffic, and 10 represents traffic congestion; w_d, w_n, w_w, and w_t represent weight coefficients, respectively, for adjusting the contribution degree of each factor, and the sum of the weights is 1.

[0120] In one or more possible embodiments, further comprising: An updating unit is configured to periodically collect working condition data of the user on a plurality of historical working days by using a sliding window method, wherein the working condition data comprises: task start time, task end time, task type, and task quality score; The working time period of the user is divided into a plurality of time slices according to a preset division rule; For each historical working day, the total working amount of the historical working day is counted, and the working amount completed in each time slice is counted. The amount of work completed within a time slice is divided by the total amount of work of historical workdays to obtain an efficiency coefficient of the time slice.

[0121] In one or more possible embodiments, the pushing the work optimization suggestion to the user comprises: According to the account login state of the user, a corresponding message pushing channel is queried; the message pushing channel comprises a push message of an AI private assistant, a short message, or a loudspeaker of a place where the user is located; According to the message pushing channel, the work optimization suggestion is pushed to the user.

[0122] In one or more possible embodiments, the obtaining the work task set of the user comprises: Obtaining identity information of the user, querying corresponding post type information according to the identity information, and querying a corresponding work task set according to the post type information.

[0123] It should be noted that the apparatus 3 provided in the above embodiments is used to execute the personalized work task management method, and only the division of the above functional modules is used as an example for illustration. In actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above functions. In addition, the personalized work task management apparatus and the personalized work task management method provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments. Therefore, the detailed description is not repeated here.

[0124] The serial numbers of the above embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0125] Referring to Figure 4 , a schematic diagram of a computer storage medium provided by an embodiment of the present application is shown. The computer storage medium can store a plurality of instructions (i.e. Figure 4 , a computer program shown), which are suitable for being loaded and executed by a processor to implement the method steps of the above embodiments. The specific execution process can be referred to the specific description of the above embodiments, and thus is not repeated here. Figure 2 Figure 2 The specific execution process can be referred to the specific description of the above embodiments, and thus is not repeated here.

[0126] The present application also provides a computer program product, which stores at least one instruction. The at least one instruction is loaded and executed by the processor to implement the personalized work task management method described in each of the above embodiments.

[0127] Referring to Figure 5 , a structural schematic diagram of a server provided by an embodiment of the present application is shown. As Figure 5 ​As shown, the server 500 can include at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502.

[0128] The communication bus 502 is configured to realize the connection and communication between the components.

[0129] The user interface 503 can include a mouse, a keyboard, and the like input units.

[0130] The network interface 504 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface).

[0131] The processor 501 can include one or more processing cores. The processor 501 connects various parts in the server 500 through various interfaces and lines, executes various functions of the server 500 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be realized in at least one of the hardware forms of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 501 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU is mainly used to process the operating system, the user interface, and the application program; the GPU is used to render and draw the content to be displayed on the display screen; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 501, but can be realized by a separate chip.

[0132] The memory 505 may include random access memory (RAM) or read-only memory. Optionally, the memory 505 may include a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 505 may also be at least one storage device located remotely from the aforementioned processor 501. Figure 5 As shown, the memory 505, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs.

[0133] exist Figure 5 In the server 500 shown, the user interface 503 is mainly used to provide an input interface for users and obtain user input data; while the processor 501 can be used to call the application program stored in the memory 505 and specifically execute, such as Figure 2 The method shown can be referred to for details. Figure 2 As shown, it will not be elaborated further here.

[0134] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0135] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A personalized work task management method, characterized in that, include: Obtain the user's set of work tasks; Select multiple work tasks from the set of work tasks and assign them to the user; Calculate the complexity score of each task to be processed for the user; Determine the user's daily efficiency fluctuation information; the daily efficiency fluctuation information indicates that the user's working time period is divided into multiple time segments, and each time segment is associated with an efficiency coefficient; Based on the matching degree between the efficiency coefficient of time partitioning and the complexity score of the task to be processed, the time partitioning is mapped to the task to be processed with the highest matching degree. Based on the mapping results of pending tasks and time slices, work optimization suggestions are pushed to the user.

2. The method according to claim 1, characterized in that, The process of mapping time slices to the tasks with the highest matching degree based on the matching degree between the efficiency coefficient of time slices and the complexity score of the tasks to be processed includes: When the start time of the work period arrives, the matching degree between the efficiency coefficient of the first time slice and the complexity score of each pending task of the user is calculated. Based on the calculation result, the pending task with the highest matching degree is determined, and this pending task is mapped to the first time slice. When the pending task is detected to have been completed, it is set as a completed task. The end time of the completed task is determined, and the time slice corresponding to the end time in the work period is queried. The matching degree between the efficiency coefficient of this time slice and the complexity score of each pending task of the user is calculated. Based on the calculation result, the pending task with the highest matching degree is determined, and this pending task is mapped to the queried time slice. When the pending task is detected to have been completed, it is set as a completed task. This process continues until the work period ends or all pending tasks of the user are completed.

3. The method according to claim 1 or 2, characterized in that, The step of selecting multiple work tasks from the set of work tasks and assigning them to the user includes: The user's average daily workload is calculated based on their historical work records. Based on the average daily workload, select multiple work tasks from the set of work tasks, and assign the selected work tasks to the user.

4. The method according to claim 3, characterized in that, The pending tasks are parcel delivery tasks; The calculation of the complexity score of each pending task of the user includes: The complexity score of a package delivery task is calculated as follows: (w_d*d + w_n*n + w_w*w + w_t*t); where d represents the delivery distance, n represents the number of packages, w represents the average weight of the packages, and t represents the traffic factor, with a value ranging from 1 to 10, where 1 represents smooth traffic and 10 represents congested traffic. w_d, w_n, w_w, and w_t represent weighting coefficients used to adjust the contribution of each factor, and the sum of all weights is 1.

5. The method according to claim 4, characterized in that, Also includes: The system uses a sliding window to periodically collect user work data over multiple historical workdays. This work data includes: task start time, task end time, task type, and task quality score. The user's work time period is divided into multiple time segments according to the preset segmentation rules; For each historical workday, calculate the total workload for that workday, as well as the workload completed within each time segment; The efficiency coefficient of a time slice is obtained by dividing the amount of work completed within that time slice by the total amount of work done over historical working days.

6. The method according to claim 4 or 5, characterized in that, The step of pushing the work optimization suggestions to the user includes: The corresponding message push channel is queried based on the user's account login status; the message push channel includes: push messages from the AI ​​personal assistant, short messages, or speakers in the user's location; The work optimization suggestions are pushed to the user through the message push channel.

7. The method according to claim 6, characterized in that, The set of user work tasks obtained includes: Obtain the user's identity information, query the corresponding job type information based on the identity information, and query the corresponding set of work tasks based on the job type information.

8. A personalized work task management device, characterized in that, include: The acquisition unit is used to acquire the user's set of work tasks. An allocation unit is configured to select multiple work tasks from the set of work tasks and allocate them to the user. A calculation unit is used to calculate the complexity score of each task to be processed by the user; A determining unit is used to determine the user's daily efficiency fluctuation information; the daily efficiency fluctuation information indicates that the user's working time period is divided into multiple time segments, and each time segment is associated with an efficiency coefficient; The mapping unit is used to map time slices to the tasks with the highest matching degree based on the matching degree between the efficiency coefficient of time slices and the complexity score of the tasks to be processed. The push unit is used to push work optimization suggestions to the user based on the mapping results of the tasks to be processed and time slicing.

9. A computer storage medium, characterized in that, The computer storage medium stores a plurality of instructions adapted for loading by a processor and executing the steps of the method as described in any one of claims 1 to 7.

10. A server, characterized in that, include: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the steps of the method as described in any one of claims 1 to 7.

Images