Workload prediction method and system based on task model, and storage medium

Abstract

The invention discloses a workload load prediction method and system based on a task model, and a storage medium, and the method comprises the steps: obtaining a plan task filled by an engineer, and carrying out the date processing based on the plan task, and obtaining prediction source data; inputting the prediction source data into the workload multidimensional prediction model to obtain an initial prediction result of each model; performing combination and correction based on the initial prediction results of the models to obtain a target prediction workload; and performing visual display based on the target prediction workload, and synchronously generating a target suggestion for display, the target suggestion being related to the target prediction workload. According to the method, the workload of an engineer in a period of time in the future can be predicted, prediction adjustment can be carried out according to actual demands, and the superior of the engineer can clearly and quickly understand and master the workload condition in each application scene by outputting improvement suggestions, so that the superior of the engineer can carry out work adjustment and arrangement in advance, and the working efficiency is improved. And the working efficiency and quality are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and more specifically, to a workload load prediction method, system and storage medium based on a task model. Background Art

[0002] In the existing task management systems of enterprises, in order to allow superiors to understand the specific work and completion status of engineers in a timely manner, engineers will fill in their own working hours in the system every day. Superiors can log in to the task management system to view the workload details of engineers.

[0003] However, through long-term work performance, this practice currently has the following problems. For example, the working hours filled in by engineers are generally filled in in the form of accounting (that is, filled in and completed on the same day), without filling in the form of planning for the next week or longer period of time, or the workload of the day filled in according to the accounting model cannot predict the workload of engineers in the future, and superiors cannot predict the workload of engineers in the future based on the workload filled in this accounting model, which leads to unreasonable arrangements of work plans and resource allocation. Summary of the invention

[0004] The purpose of the present invention is to provide a workload load prediction method, system and storage medium based on a task model, which can not only predict the workload of engineers in the future, but also make prediction adjustments according to actual needs. By outputting improvement suggestions, their superiors can clearly and quickly understand and grasp the workload load conditions in various application scenarios, thereby facilitating their superiors to adjust their work in advance and improve work efficiency and quality.

[0005] A first aspect of the present invention provides a method for workload load prediction based on a task model, comprising the following steps: Obtain the planned tasks filled in by the engineer, and perform date processing based on the planned tasks to obtain forecast source data; Inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model; The initial prediction results based on each model are combined and corrected to obtain a target prediction workload; A visual display is performed based on the target predicted workload, and a target suggestion is simultaneously generated for display, wherein the target suggestion is related to the target predicted workload.

[0006] In this solution, the planned tasks filled in by the engineer are obtained, including: Acquire the filled-in data input by the engineer, wherein the filled-in data is input by the engineer according to a preset text format; The planned task is obtained based on the preset data type combined with the filled-in data, wherein the planned task at least includes name, department, project number, task title, task content, start date, end date and work task.

[0007] In this solution, date processing is performed based on the planned task to obtain forecast source data, specifically including: Initialize the number of working days and calculate the date range based on the start date and end date in the scheduled task; Traversing the date range, filtering out based on characteristic dates to obtain a set of working day dates, wherein the characteristic dates include weekends and / or statutory holidays; The forecast source data is obtained after screening out the date of the planned task.

[0008] In this solution, the prediction source data is input into the workload multidimensional prediction model to obtain the initial prediction results of each model, specifically including: The workload multidimensional prediction model includes a personnel capability maturity model, a task standard working time model, a project standard working time model and a periodic work efficiency model; The prediction source data is input into the workload multidimensional prediction model to obtain the initial prediction result, wherein the initial prediction result is obtained by combining the personnel capability maturity model coefficient, task standard working hours, project standard working hours and periodic work efficiency model coefficient with the corresponding work task.

[0009] In this solution, the initial prediction results based on each model are combined and corrected to obtain the target prediction workload, which specifically includes: Obtain a corrected calculation formula, wherein the corrected calculation formula is as follows: S = O*(H t / Hs)*(T p / T O ) *A i *B w ; Wherein, S represents the modified target prediction workload, O represents the initial prediction result, and A i Represents the coefficient of personnel capability maturity model, H t represents the standard working time corresponding to the standard working time model of the task, Hs represents the estimated workload corresponding to the current work task, T p Indicates the standard working hours corresponding to the project standard working hours model, T O Indicates the estimated workload of the project corresponding to the current work task, B w represents the coefficient of the periodic work efficiency model; The initial prediction result is corrected based on the correction calculation formula to obtain the target prediction workload.

[0010] In this solution, the workload based on the target prediction is visualized and the target suggestion is generated and displayed simultaneously, specifically including: Generate a data set based on the date range in the target forecast workload and its corresponding scenario type for visual display, wherein the scenario type includes name, group, department and project; The set workload prediction index is obtained, and compared with the data set to generate the target suggestion, wherein the target suggestion is extracted and synchronously displayed with the corresponding scenario type.

[0011] The second aspect of the present invention further provides a workload load prediction system based on a task model, comprising a memory and a processor, wherein the memory comprises a workload load prediction method program based on a task model, and when the workload load prediction method program based on a task model is executed by the processor, the following steps are implemented: Obtain the planned tasks filled in by the engineer, and perform date processing based on the planned tasks to obtain forecast source data; Inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model; The initial prediction results based on each model are combined and corrected to obtain a target prediction workload; A visual display is performed based on the target predicted workload, and a target suggestion is simultaneously generated for display, wherein the target suggestion is related to the target predicted workload.

[0012] In this solution, the planned tasks filled in by the engineer are obtained, including: Acquire the filled-in data input by the engineer, wherein the filled-in data is input by the engineer according to a preset text format; The planned task is obtained based on the preset data type combined with the filled-in data, wherein the planned task at least includes name, department, project number, task title, task content, start date, end date and work task.

[0013] In this solution, date processing is performed based on the planned task to obtain forecast source data, specifically including: Initialize the number of working days and calculate the date range based on the start date and end date in the scheduled task; Traversing the date range, filtering out based on characteristic dates to obtain a set of working day dates, wherein the characteristic dates include weekends and / or statutory holidays; The forecast source data is obtained after screening out the date of the planned task.

[0014] In this solution, the prediction source data is input into the workload multidimensional prediction model to obtain the initial prediction results of each model, specifically including: The workload multidimensional prediction model includes a personnel capability maturity model, a task standard working time model, a project standard working time model and a periodic work efficiency model; The prediction source data is input into the workload multidimensional prediction model to obtain the initial prediction result, wherein the initial prediction result is obtained by combining the personnel capability maturity model coefficient, task standard working hours, project standard working hours and periodic work efficiency model coefficient with the corresponding work task.

[0015] In this solution, the initial prediction results based on each model are combined and corrected to obtain the target prediction workload, which specifically includes: Obtain a corrected calculation formula, wherein the corrected calculation formula is as follows: S = O*(H t / Hs)*(T p / T O ) *A i *B w ; Wherein, S represents the modified target prediction workload, O represents the initial prediction result, and A i Represents the coefficient of personnel capability maturity model, H t represents the standard working time corresponding to the standard working time model of the task, Hs represents the estimated workload corresponding to the current work task, T p Indicates the standard working hours corresponding to the project standard working hours model, T O Indicates the estimated workload of the project corresponding to the current work task, B w represents the coefficient of the periodic work efficiency model; The initial prediction result is corrected based on the correction calculation formula to obtain the target prediction workload.

[0016] In this solution, the workload based on the target prediction is visualized and the target suggestion is generated and displayed simultaneously, specifically including: Generate a data set based on the date range in the target forecast workload and its corresponding scenario type for visual display, wherein the scenario type includes name, group, department and project; The set workload prediction index is obtained, and compared with the data set to generate the target suggestion, wherein the target suggestion is extracted and synchronously displayed with the corresponding scenario type.

[0017] The third aspect of the present invention provides a computer-readable storage medium, which includes a machine's workload load prediction method program based on a task model. When the workload load prediction method program based on a task model is executed by a processor, the steps of a workload load prediction method based on a task model as described in any one of the above items are implemented.

[0018] The present invention discloses a workload load prediction method, system and storage medium based on a task model, which can not only predict the workload of engineers in the future, but also make prediction adjustments according to actual needs. By outputting improvement suggestions, their superiors can clearly and quickly understand and grasp the workload load conditions in various application scenarios, thereby facilitating their superiors to adjust and arrange their work in advance and improve work efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of a workload load prediction method based on a task model of the present invention is shown; Figure 2 A schematic diagram of a model pool of a workload multi-dimensional prediction model of a workload load prediction method based on a task model of the present invention is shown; Figure 3 A schematic diagram showing visualization of prediction results of a workload load prediction method based on a task model of the present invention is shown; Figure 4 A block diagram of a workload load prediction system based on a task model of the present invention is shown. DETAILED DESCRIPTION

[0020] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0022] Figure 1 A flowchart of a workload load prediction method based on a task model of the present application is shown.

[0023] like Figure 1 As shown, the present application discloses a workload load prediction method based on a task model, comprising the following steps: S102, obtaining the planned tasks filled in by the engineer, and performing date processing based on the planned tasks to obtain forecast source data; S104, inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model; S106, combining and correcting the initial prediction results of each model to obtain a target prediction workload; S108, performing visual display based on the target predicted workload, and synchronously generating target suggestions for display, wherein the target suggestions are related to the target predicted workload.

[0024] It should be noted that the idea of ​​this application is to perform workload forecasting processing through a multi-dimensional workload model based on the planned tasks filled out by engineers, and load and display the results of the forecast processing on the front end to support display in different application scenarios, such as: display by individual / group / department / project and other scenarios, and output improvement suggestions with one click based on different display results, and support multiple output methods (such as: corporate WeChat, email, etc.). In addition, it can also support forecast adjustments. After the adjustment is reviewed and approved, the forecast will be re-performed according to the workload forecast algorithm.

[0025] Specifically, in this embodiment, it is first necessary to obtain the planned tasks filled in by the engineer, and accordingly, perform data processing on the planned tasks to obtain prediction source data, so that the prediction source data can be input into the workload multidimensional prediction model to obtain the initial prediction results of each model, and the initial prediction results of each model are combined and corrected to obtain the target predicted workload, and finally, a visualization display is performed based on the target predicted workload, and target suggestions can be generated synchronously for display, and accordingly, the target suggestions are related to the target predicted workload.

[0026] According to an embodiment of the present invention, obtaining the planned tasks filled in by the engineer specifically includes: Acquire the filled-in data input by the engineer, wherein the filled-in data is input by the engineer according to a preset text format; The planned task is obtained based on the preset data type combined with the filled-in data, wherein the planned task at least includes name, department, project number, task title, task content, start date, end date and work task.

[0027] It should be noted that in this embodiment, when engineers fill in the work plan, there will be a special page for them to fill in, so the filled-in data entered by the engineer can be obtained. Correspondingly, since there is a corresponding dialog box or form on the filling-in page, the filled-in data is obtained by the engineer input according to a preset text format. After obtaining the filled-in data, the planned task is obtained based on the preset data type and combined with the filled-in data, wherein the planned task includes at least name, department, project number, task title, task content, start date, end date and work task.

[0028] According to an embodiment of the present invention, performing date processing based on the planned task to obtain forecast source data specifically includes: Initialize the number of working days and calculate the date range based on the start date and end date in the scheduled task; Traversing the date range, filtering out based on characteristic dates to obtain a set of working day dates, wherein the characteristic dates include weekends and / or statutory holidays; The forecast source data is obtained after screening out the date of the planned task.

[0029] It should be noted that in this embodiment, when performing workload prediction, multiple rules need to be met, including: 1) The estimated workload of each planned task is allocated to each day of the task interval (only working days) by default on an average basis; 2) The daily predicted workload cannot be greater than the upper limit and cannot be less than the lower limit; 3) The forecast date excludes weekends and statutory holidays; Therefore, it is necessary to filter out weekends and statutory holidays from the dates of the planned tasks in order to obtain the forecast source data. Specifically, the number of working day dates is initialized, and the date range is calculated based on the start date and end date in the planned tasks, thereby traversing the date range and filtering out based on feature dates to obtain a set of working day dates, wherein feature dates include weekends and / or statutory holidays.

[0030] According to an embodiment of the present invention, the step of inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model specifically includes: The workload multidimensional prediction model includes a personnel capability maturity model, a task standard working time model, a project standard working time model and a periodic work efficiency model; The prediction source data is input into the workload multidimensional prediction model to obtain the initial prediction result, wherein the initial prediction result is obtained by combining the personnel capability maturity model coefficient, task standard working hours, project standard working hours and periodic work efficiency model coefficient with the corresponding work task.

[0031] It should be noted that, in this embodiment, Figure 2 As shown, the model pool of the workload multidimensional prediction model includes at least a personnel capability maturity model, a task standard working time model, a project standard working time model and a periodic work efficiency model, wherein models of different dimensions are defined to form the model pool of the workload multidimensional prediction model, which supports expansion during application and can introduce more models.

[0032] Specifically, for the personnel capability maturity model, employees of different job levels have different work efficiency. Theoretically, the higher the job level, the stronger the work ability, and the time taken to complete the same task will also be different. Therefore, the corresponding work efficiency coefficient A is defined according to different job levels. i , where i corresponds to the job level; and for the task standard working time model, the corresponding standard working time H is defined according to different types of tasks. t , where t corresponds to different task types; and the project standard working time model, specifically defining the corresponding standard working time T according to different types of projects p , other Ps correspond to different project types; finally, the periodic work efficiency model, that is, the work efficiency coefficient B corresponding to each day of the week is defined w , w corresponds to the day of the week, where the work efficiency is different from Monday to Friday. Generally speaking, when going to work on Monday, the work efficiency is low because the weekend has just passed and the work has not yet entered the state. As the work progresses, the state recovers. The work efficiency will rise on Tuesday and reach the peak on Wednesday. As the weekend approaches, the work efficiency on Thursday will be lower than that on Wednesday, and will continue to decrease to the lowest point on Friday, and the cycle will continue every week.

[0033] According to an embodiment of the present invention, the initial prediction results based on each model are combined and corrected to obtain a target prediction workload, specifically including: Obtain a corrected calculation formula, wherein the corrected calculation formula is as follows: S = O*(H t / Hs)*(T p / T O ) *A i *B w ; Wherein, S represents the modified target prediction workload, O represents the initial prediction result, and A i Represents the coefficient of personnel capability maturity model, H t represents the standard working time corresponding to the standard working time model of the task, Hs represents the estimated workload corresponding to the current work task, T p Indicates the standard working hours corresponding to the project standard working hours model, T OIndicates the estimated workload of the project corresponding to the current work task, B w represents the coefficient of the periodic work efficiency model; The initial prediction result is corrected based on the correction calculation formula to obtain the target prediction workload.

[0034] It should be noted that in this embodiment, different model combinations are selected and saved as solutions, which are convenient for quick selection next time and avoid re-selecting each time. The workload forecast is corrected in real time according to the coefficients and standard working hours corresponding to the selected model. The corrected calculation formula is: S = O*(H t / Hs)*(T p / T O ) *A i *B w , where S represents the revised forecast workload, O represents the original forecast workload, and A i Represents the coefficient of personnel capability maturity model, H t represents the standard working time corresponding to the standard working time model of the task, Hs represents the estimated workload corresponding to the current task, T p Indicates the standard working hours corresponding to the project standard working hours model, T O Indicates the estimated workload of the project corresponding to the current task, B w Represents the coefficient of the periodic work efficiency model.

[0035] When performing workload forecasting, the specific implementation process is as follows: Step 1: Define a workday date set R1 and a date day variable D1; Step2: Clear R1, set D1 to 0, and calculate the date range based on the start date and end date in step 2; Step 3: Process the date range in step 2, traverse each date in the date range in turn, and determine whether the date is a weekend or a statutory holiday. If the judgment is true, skip and proceed to the next date judgment. If not, write the current date into R1 and add 1 to D1. Step 4: After the date processing is completed, the average predicted workload LAVG is calculated based on the estimated workload L1 in the planned task, divided by D1. At the same time, the upper limit LMAX and lower limit LMIN of the daily predicted workload are defined, and the number of days D2 is assigned. Step 5: If LAVG>LMAX is true, it will prompt that the predicted workload exceeds the upper limit and end; If LAVG<=LMAX is true, continue to judge LAVG <LMIN, a) If true, proceed as follows: 1) LAVG = LMIN, D2 = 0; 2) Traverse each date in R1 and assign LAVG, and add 1 to D2; 3) After each date is assigned, check whether L1-LAVG*D2>LMIN. If true, assign LAVG to the current date. If it is false, the current date is assigned L1-LAVG*D2, and the remaining dates are assigned 0.

[0036] b) If it is false, proceed as follows: Traverse each date in R1 and assign LAVG; Step 6: Assign a value to each date in R1 to form a forecast record and write it into the forecast workload record table of the database. The content of the forecast record includes: name, department, project number, task id, forecast date, and forecast workload. At this point, the workload forecast processing of a single task is completed.

[0037] According to an embodiment of the present invention, the visual display of the target predicted workload and the synchronous generation of target suggestions for display specifically include: Generate a data set based on the date range in the target forecast workload and its corresponding scenario type for visual display, wherein the scenario type includes name, group, department and project; The set workload prediction index is obtained, and compared with the data set to generate the target suggestion, wherein the target suggestion is extracted and synchronously displayed with the corresponding scenario type.

[0038] It should be noted that, in this embodiment, Figure 3 As shown, it is displayed as a visual schematic diagram, which includes Step 1 selecting the date: corresponding to the range and scenario type (scenario 1. By name; scenario 2. By group; scenario 3. By department; scenario 4. By project); and Step 2 data screening processing: corresponding to using the date range and the corresponding scenario dimensions (name / group / department / project) as query conditions, filtering out data from the forecast workload record table of the database, and summarizing it according to the date and scenario dimensions; and Step 3: corresponding to generating a data set from the processing results in step 2; and Step 4: the front end loads the data set in step 3 for display.

[0039] Furthermore, improvement suggestions can be output with one click based on the prediction results, where: Step 1: Set workload forecast indicators for individuals / groups / departments / projects. For example, the individual / project dimension can define the upper and lower limits of daily workload; the group / department dimension needs to define indicators based on the number of people it contains, that is, the upper and lower limits of individual workload * the number of people; define the output format of improvement suggestions: date (yyyyMMdd) + individual / group / department / project + fixed text; Step 2: Traverse the data set generated in the fourth step and compare it with the workload prediction index. Based on the date, when the predicted workload exceeds the upper limit, it will prompt: yyyyMMdd The predicted workload of the individual / group / department / project exceeds the standard, and it is recommended to reduce resource input; when the predicted workload is less than the lower limit, it will prompt: yyyyMMdd The predicted workload of the individual / group / department / project is lower than the lower limit, and it is recommended to increase resource input; when the predicted workload is between the upper and lower limits, it will prompt: yyyyMMdd The predicted workload of the individual / group / department / project is normal; the improvement suggestions generated by the above traversal are recorded in the workload prediction suggestion table in the database.

[0040] Step 3: The front end loads the workload forecast suggestion table in the second step for display; the improvement suggestions generated in the second step can also be pushed to designated personnel by calling the email service or the enterprise WeChat message push service.

[0041] Figure 4 A block diagram of a workload load prediction system based on a task model of the present invention is shown.

[0042] like Figure 4 As shown, the present invention discloses a workload load prediction system based on a task model, including a memory and a processor, wherein the memory includes a workload load prediction method program based on a task model, and when the workload load prediction method program based on a task model is executed by the processor, the following steps are implemented: Obtain the planned tasks filled in by the engineer, and perform date processing based on the planned tasks to obtain forecast source data; Inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model; The initial prediction results based on each model are combined and corrected to obtain a target prediction workload; A visual display is performed based on the target predicted workload, and a target suggestion is simultaneously generated for display, wherein the target suggestion is related to the target predicted workload.

[0043] It should be noted that the idea of ​​this application is to perform workload forecasting processing through a multi-dimensional workload model based on the planned tasks filled out by engineers, and load and display the results of the forecast processing on the front end to support display in different application scenarios, such as: display by individual / group / department / project and other scenarios, and output improvement suggestions with one click based on different display results, and support multiple output methods (such as: corporate WeChat, email, etc.). In addition, it can also support forecast adjustments. After the adjustment is reviewed and approved, the forecast will be re-performed according to the workload forecast algorithm.

[0044] Specifically, in this embodiment, it is first necessary to obtain the planned tasks filled in by the engineer, and accordingly, perform data processing on the planned tasks to obtain prediction source data, so that the prediction source data can be input into the workload multidimensional prediction model to obtain the initial prediction results of each model, and the initial prediction results of each model are combined and corrected to obtain the target predicted workload, and finally, a visualization display is performed based on the target predicted workload, and target suggestions can be generated synchronously for display, and accordingly, the target suggestions are related to the target predicted workload.

[0045] According to an embodiment of the present invention, obtaining the planned tasks filled in by the engineer specifically includes: Acquire the filled-in data input by the engineer, wherein the filled-in data is input by the engineer according to a preset text format; The planned task is obtained based on the preset data type combined with the filled-in data, wherein the planned task at least includes name, department, project number, task title, task content, start date, end date and work task.

[0046] It should be noted that in this embodiment, when engineers fill in the work plan, there will be a special page for them to fill in, so the filled-in data entered by the engineer can be obtained. Correspondingly, since there is a corresponding dialog box or form on the filling-in page, the filled-in data is obtained by the engineer input according to a preset text format. After obtaining the filled-in data, the planned task is obtained based on the preset data type and combined with the filled-in data, wherein the planned task includes at least name, department, project number, task title, task content, start date, end date and work task.

[0047] According to an embodiment of the present invention, performing date processing based on the planned task to obtain forecast source data specifically includes: Initialize the number of working days and calculate the date range based on the start date and end date in the scheduled task; Traversing the date range, filtering out based on characteristic dates to obtain a set of working day dates, wherein the characteristic dates include weekends and / or statutory holidays; The forecast source data is obtained after screening out the date of the planned task.

[0048] It should be noted that in this embodiment, when performing workload prediction, multiple rules need to be met, including: 1) The estimated workload of each planned task is allocated to each day of the task interval (only working days) by default on an average basis; 2) The daily predicted workload cannot be greater than the upper limit and cannot be less than the lower limit; 3) The forecast date excludes weekends and statutory holidays; Therefore, it is necessary to filter out weekends and statutory holidays from the dates of the planned tasks in order to obtain the forecast source data. Specifically, the number of working day dates is initialized, and the date range is calculated based on the start date and end date in the planned tasks, thereby traversing the date range and filtering out based on feature dates to obtain a set of working day dates, wherein feature dates include weekends and / or statutory holidays.

[0049] According to an embodiment of the present invention, the step of inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model specifically includes: The workload multidimensional prediction model includes a personnel capability maturity model, a task standard working time model, a project standard working time model and a periodic work efficiency model; The prediction source data is input into the workload multidimensional prediction model to obtain the initial prediction result, wherein the initial prediction result is obtained by combining the personnel capability maturity model coefficient, task standard working hours, project standard working hours and periodic work efficiency model coefficient with the corresponding work task.

[0050] It should be noted that, in this embodiment, Figure 2 As shown, the model pool of the workload multidimensional prediction model includes at least a personnel capability maturity model, a task standard working time model, a project standard working time model and a periodic work efficiency model, wherein models of different dimensions are defined to form the model pool of the workload multidimensional prediction model, which supports expansion during application and can introduce more models.

[0051] Specifically, for the personnel capability maturity model, employees of different job levels have different work efficiency. Theoretically, the higher the job level, the stronger the work ability, and the time taken to complete the same task will also be different. Therefore, the corresponding work efficiency coefficient A is defined according to different job levels. i , where i corresponds to the job level; and for the task standard working time model, the corresponding standard working time H is defined according to different types of tasks. t, where t corresponds to different task types; and the project standard working time model, specifically defining the corresponding standard working time T according to different types of projects p , other Ps correspond to different project types; finally, the periodic work efficiency model, that is, the work efficiency coefficient B corresponding to each day of the week is defined w , w corresponds to the day of the week, where the work efficiency is different from Monday to Friday. Generally speaking, when going to work on Monday, the work efficiency is low because the weekend has just passed and the work has not yet entered the state. As the work progresses, the state recovers. The work efficiency will rise on Tuesday and reach the peak on Wednesday. As the weekend approaches, the work efficiency on Thursday will be lower than that on Wednesday, and will continue to decrease to the lowest point on Friday, and the cycle will continue every week.

[0052] According to an embodiment of the present invention, the initial prediction results based on each model are combined and corrected to obtain a target prediction workload, specifically including: Obtain a corrected calculation formula, wherein the corrected calculation formula is as follows: S = O*(H t / Hs)*(T p / T O ) *A i *B w ; Wherein, S represents the modified target prediction workload, O represents the initial prediction result, and A i Represents the coefficient of personnel capability maturity model, H t represents the standard working time corresponding to the standard working time model of the task, Hs represents the estimated workload corresponding to the current work task, T p Indicates the standard working hours corresponding to the project standard working hours model, T O Indicates the estimated workload of the project corresponding to the current work task, B w represents the coefficient of the periodic work efficiency model; The initial prediction result is corrected based on the correction calculation formula to obtain the target prediction workload.

[0053] It should be noted that in this embodiment, different model combinations are selected and saved as solutions, which are convenient for quick selection next time and avoid re-selecting each time. The workload forecast is corrected in real time according to the coefficients and standard working hours corresponding to the selected model. The corrected calculation formula is: S = O*(H t / Hs)*(T p / T O ) *A i *B w , where S represents the revised forecast workload, O represents the original forecast workload, and A iRepresents the coefficient of personnel capability maturity model, H t represents the standard working time corresponding to the standard working time model of the task, Hs represents the estimated workload corresponding to the current task, T p Indicates the standard working hours corresponding to the project standard working hours model, T O Indicates the estimated workload of the project corresponding to the current task, B w Represents the coefficient of the periodic work efficiency model.

[0054] When performing workload forecasting, the specific implementation process is as follows: Step 1: Define a workday date set R1 and a date day variable D1; Step2: Clear R1, set D1 to 0, and calculate the date range based on the start date and end date in step 2; Step 3: Process the date range in step 2, traverse each date in the date range in turn, and determine whether the date is a weekend or a statutory holiday. If the judgment is true, skip and proceed to the next date judgment. If not, write the current date into R1 and add 1 to D1. Step 4: After the date processing is completed, the average predicted workload LAVG is calculated based on the estimated workload L1 in the planned task, divided by D1. At the same time, the upper limit LMAX and lower limit LMIN of the daily predicted workload are defined, and the number of days D2 is assigned. Step 5: If LAVG>LMAX is true, it will prompt that the predicted workload exceeds the upper limit and end; If LAVG<=LMAX is true, continue to judge LAVG <LMIN, c) If true, proceed as follows: 4) LAVG = LMIN, D2 = 0; 5) Traverse each date in R1 and assign LAVG, and add 1 to D2; 6) After each date is assigned, check whether L1-LAVG*D2>LMIN. If true, assign LAVG to the current date. If it is false, the current date is assigned L1-LAVG*D2, and the remaining dates are assigned 0.

[0055] d) If it is false, proceed as follows: Traverse each date in R1 and assign LAVG; Step 6: Assign a value to each date in R1 to form a forecast record and write it into the forecast workload record table of the database. The content of the forecast record includes: name, department, project number, task id, forecast date, and forecast workload. At this point, the workload forecast processing of a single task is completed.

[0056] According to an embodiment of the present invention, the visual display of the target predicted workload and the synchronous generation of target suggestions for display specifically include: Generate a data set based on the date range in the target forecast workload and its corresponding scenario type for visual display, wherein the scenario type includes name, group, department and project; The set workload prediction index is obtained, and compared with the data set to generate the target suggestion, wherein the target suggestion is extracted and synchronously displayed with the corresponding scenario type.

[0057] It should be noted that, in this embodiment, Figure 3 As shown, it is displayed as a visual schematic diagram, which includes Step 1 selecting the date: corresponding to the range and scenario type (scenario 1. By name; scenario 2. By group; scenario 3. By department; scenario 4. By project); and Step 2 data screening processing: corresponding to using the date range and the corresponding scenario dimensions (name / group / department / project) as query conditions, filtering out data from the forecast workload record table of the database, and summarizing it according to the date and scenario dimensions; and Step 3: corresponding to generating a data set from the processing results in step 2; and Step 4: the front end loads the data set in step 3 for display.

[0058] Furthermore, improvement suggestions can be output with one click based on the prediction results, where: Step 1: Set workload forecast indicators for individuals / groups / departments / projects. For example, the individual / project dimension can define the upper and lower limits of daily workload; the group / department dimension needs to define indicators based on the number of people it contains, that is, the upper and lower limits of individual workload * the number of people; define the output format of improvement suggestions: date (yyyyMMdd) + individual / group / department / project + fixed text; Step 2: Traverse the data set generated in the fourth step and compare it with the workload prediction index. Based on the date, when the predicted workload exceeds the upper limit, it will prompt: yyyyMMdd The predicted workload of the individual / group / department / project exceeds the standard, and it is recommended to reduce resource input; when the predicted workload is less than the lower limit, it will prompt: yyyyMMdd The predicted workload of the individual / group / department / project is lower than the lower limit, and it is recommended to increase resource input; when the predicted workload is between the upper and lower limits, it will prompt: yyyyMMdd The predicted workload of the individual / group / department / project is normal; the improvement suggestions generated by the above traversal are recorded in the workload prediction suggestion table in the database.

[0059] Step 3: The front end loads the workload forecast suggestion table in the second step for display; the improvement suggestions generated in the second step can also be pushed to designated personnel by calling the email service or the enterprise WeChat message push service.

[0060] The third aspect of the present invention provides a computer-readable storage medium, which includes a workload load prediction method program based on a task model. When the workload load prediction method program based on a task model is executed by a processor, the steps of a workload load prediction method based on a task model as described in any one of the above items are implemented.

[0061] The present invention discloses a workload load prediction method, system and storage medium based on a task model, which can not only predict the workload of engineers in the future, but also make prediction adjustments according to actual needs. By outputting improvement suggestions, their superiors can clearly and quickly understand and grasp the workload load conditions in various application scenarios, thereby facilitating their superiors to adjust and arrange their work in advance and improve work efficiency and quality.

[0062] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0063] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0064] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0065] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0066] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A workload load prediction method based on a task model, characterized in that: The following steps are involved: Obtain the planned tasks filled in by the engineer, and perform date processing based on the planned tasks to obtain forecast source data; Inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model; The initial prediction results based on each model are combined and corrected to obtain a target prediction workload; A visual display is performed based on the target predicted workload, and a target suggestion is simultaneously generated for display, wherein the target suggestion is related to the target predicted workload.

2. The workload load prediction method based on task model according to claim 1 is characterized in that: Get the planned tasks filled in by the engineer, including: Acquire the filled-in data input by the engineer, wherein the filled-in data is input by the engineer according to a preset text format; The planned task is obtained based on the preset data type combined with the filled-in data, wherein the planned task at least includes name, department, project number, task title, task content, start date, end date and work task.

3. The method for predicting workload based on task model according to claim 2, characterized in that: The date processing based on the planned task is performed to obtain the forecast source data, specifically including: Initialize the number of working days and calculate the date range based on the start date and end date in the scheduled task; Traversing the date range, filtering out based on characteristic dates to obtain a set of working day dates, wherein the characteristic dates include weekends and / or statutory holidays; The forecast source data is obtained after screening out the date of the planned task.

4. The method for predicting workload based on task model according to claim 3, characterized in that: The step of inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model specifically includes: The workload multidimensional prediction model includes a personnel capability maturity model, a task standard working time model, a project standard working time model and a periodic work efficiency model; The prediction source data is input into the workload multidimensional prediction model to obtain the initial prediction result, wherein the initial prediction result is obtained by combining the personnel capability maturity model coefficient, task standard working hours, project standard working hours and periodic work efficiency model coefficient with the corresponding work task.

5. The method for predicting workload based on task model according to claim 4, characterized in that: The initial prediction results based on each model are combined and corrected to obtain a target prediction workload, specifically including: Obtain a corrected calculation formula, wherein the corrected calculation formula is as follows: S = O*(H t / Hs)*(T p / T O ) *A i *B w ; Wherein, S represents the modified target prediction workload, O represents the initial prediction result, and A i Represents the personnel capability maturity model coefficient, H t represents the standard working time corresponding to the standard working time model of the task, Hs represents the estimated workload corresponding to the current work task, T p Indicates the standard working hours corresponding to the project standard working hours model, T O Indicates the estimated workload of the project corresponding to the current work task, B w represents the coefficient of the periodic work efficiency model; The initial prediction result is corrected based on the correction calculation formula to obtain the target prediction workload.

6. The method for workload prediction based on task model according to claim 5, characterized in that: The visual display of the target predicted workload and the synchronous generation of target suggestions for display specifically include: Generate a data set based on the date range in the target forecast workload and its corresponding scenario type for visual display, wherein the scenario type includes name, group, department and project; The set workload prediction index is obtained, and compared with the data set to generate the target suggestion, wherein the target suggestion is extracted and synchronously displayed with the corresponding scenario type.

7. A workload load prediction system based on task model, characterized in that: The system comprises a memory and a processor, wherein the memory comprises a workload load prediction method program based on a task model, and when the workload load prediction method program based on a task model is executed by the processor, the following steps are implemented: Obtain the planned tasks filled in by the engineer, and perform date processing based on the planned tasks to obtain forecast source data; Inputting the prediction source data into the workload multidimensional prediction model to obtain the initial prediction results of each model; The initial prediction results based on each model are combined and corrected to obtain a target prediction workload; A visual display is performed based on the target predicted workload, and a target suggestion is simultaneously generated for display, wherein the target suggestion is related to the target predicted workload.

8. The workload load prediction system based on task model according to claim 7, characterized in that: Get the planned tasks filled in by the engineer, including: Acquire the filled-in data input by the engineer, wherein the filled-in data is input by the engineer according to a preset text format; The planned task is obtained based on the preset data type combined with the filled-in data, wherein the planned task at least includes name, department, project number, task title, task content, start date, end date and work task.

9. A workload load prediction system based on task model according to claim 8, characterized in that: The date processing based on the planned task is performed to obtain the forecast source data, specifically including: Initialize the number of working days and calculate the date range based on the start date and end date in the scheduled task; Traversing the date range, filtering out based on characteristic dates to obtain a set of working day dates, wherein the characteristic dates include weekends and / or statutory holidays; The forecast source data is obtained after screening out the date of the planned task.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a workload load prediction method program based on a task model. When the workload load prediction method program based on a task model is executed by a processor, the steps of a workload load prediction method based on a task model as described in any one of claims 1 to 6 are implemented.

Images