CN117541021A - Pipeline task management system - Google Patents
Pipeline task management system Download PDFInfo
- Publication number
- CN117541021A CN117541021A CN202410008452.8A CN202410008452A CN117541021A CN 117541021 A CN117541021 A CN 117541021A CN 202410008452 A CN202410008452 A CN 202410008452A CN 117541021 A CN117541021 A CN 117541021A
- Authority
- CN
- China
- Prior art keywords
- task
- staff
- node
- working
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007405 data analysis Methods 0.000 claims abstract description 60
- 238000005457 optimization Methods 0.000 claims abstract description 28
- 238000009826 distribution Methods 0.000 claims abstract description 27
- 238000013480 data collection Methods 0.000 claims abstract description 8
- 238000007726 management method Methods 0.000 claims description 56
- 238000012797 qualification Methods 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 23
- 238000012417 linear regression Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 15
- 238000004519 manufacturing process Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 230000006872 improvement Effects 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000001934 delay Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of pipeline task management, in particular to a pipeline task management system which comprises a data collection module, a capability assessment module, a node personnel model library, a matching distribution module, a task state tracking module and a data analysis optimization module. According to the invention, by collecting the data information of the staff and evaluating the working capacity value of the staff, the system can be matched with the optimal staff to complete the task, and the progress and the efficiency of the task are monitored in real time. Meanwhile, the system can also perform data analysis and optimization, can find and solve the problems in task execution, and improves the task execution efficiency and quality, so that the optimization and improvement of a pipeline task management system are realized, the working efficiency of low-efficiency nodes is improved, and the task can be ensured to be properly allocated to staff with corresponding skills, so that the task execution efficiency and quality are improved.
Description
Technical Field
The invention relates to the technical field of pipeline task management, in particular to a pipeline task management system.
Background
In today's industrial production environment, pipeline task management systems are widely used in many industrial fields due to their high efficiency, automation and reliability characteristics.
Publication No.: the CN116452141a patent discloses a task management system comprising: a task management workbench, a task management pipeline and a database; the task management workbench comprises a credential management module, a task template module, a task management module and a task monitoring module; the credential management module is used for managing the access rights of the third party system based on the access credentials; the task template module is used for configuring task management task information and task management pipeline information; the task management module is used for creating a task management task according to the task management task information and the task management pipeline information and triggering the task management pipeline to call a third-party system to execute the task management task; the task monitoring module is used for displaying the execution state and the execution result of the task management task; the database is used for storing the execution state and the execution result.
It follows that the task management system has the following problems:
in the traditional pipeline task management, the problems of low efficiency, human error and resource waste are easy to occur.
Disclosure of Invention
Therefore, the invention provides a pipeline task management system, which is used for solving the problems of low efficiency, human error and resource waste in the traditional pipeline task management in the prior art.
To achieve the above object, the present invention provides a pipeline task management system, including:
the data collection module is used for collecting the working years, skill levels and qualification certification levels of the staff to be distributed in the production line;
the capacity evaluation module is connected with the data collection module and used for evaluating the working capacity value of the staff to be distributed according to the working years, the skill level and the qualification authentication level of the staff to be distributed;
a node personnel model library for providing skill requirement values for each node on the pipeline;
the matching distribution module is respectively connected with the capability evaluation module and the node personnel model library and is used for distributing the work task of each node to the optimal personnel according to the work capability value and the skill requirement value so as to form a pipeline array;
the task state tracking module is connected with the data collecting module and the matching distribution module and used for monitoring the working efficiency of the optimal staff in the assembly line array in real time in the working process;
the data analysis optimization module is respectively connected with the task state tracking module and the capability assessment module and is used for carrying out data analysis on the working efficiency to acquire the task output efficiency of each node, and staff distributed to update any node in the pipeline array according to the task output efficiency and a preset target output efficiency.
Further, the capability assessment module includes:
the extraction unit is used for extracting the collected experience characteristics of the working years, skill level and qualification authentication level of the staff;
the training unit is connected with the extraction unit and is used for establishing a model with an estimated working capacity value by using the experience characteristics;
the calculation unit is connected with the training unit and is used for inputting the acquired data and the extracted experience characteristics thereof into the model with the estimated working capacity value and calculating the working capacity value score of the working personnel;
and the output unit is connected with the calculation unit and is used for outputting the scoring result of the working capacity value.
Further, the extraction unit includes:
a normalization subunit for normalizing the empirical feature of the working years by maximum-minimum normalization, normalized working years= (actual working years-minimum working years)/(maximum working years-minimum working years);
the coding subunit is used for performing single-heat coding on the skill level and the qualification certification level respectively and creating binary characteristics on the skill level and the qualification certification level respectively;
and the splicing subunit is used for splicing the experience characteristics of the working years, the experience characteristics of the skill level and the experience characteristics of the qualification certification level in columns to form a characteristic vector.
Further, the training unit includes:
a model selection subunit for selecting a linear regression algorithm model: y=β0+β1×x1+β2×x2+ & βn×xn, where Y is the outcome of the work capacity scoring, X1, X2, & gt, xn are empirical features, β0, β1, & gt, βn are coefficients of the linear regression algorithm model;
the data preprocessing subunit is used for dividing the collected experience feature set into a training set and a testing set, 80% of experience features are used for training the linear regression algorithm model, the missing value of numerical data of the training set is filled by an average value, the missing value of a classification variable is filled by a mode, the coefficient of the linear regression algorithm model is initialized, and the initial value is set to be 0;
a first data operation subunit for calculating a predicted value Y' =β0+β1×x1+β2×x2+, +βn×xn according to the current coefficient of the linear regression algorithm model,
a data operation second subunit, configured to calculate, using a mean square error Loss function, loss= (1/m) x Σ (Y '-Y) 2, where Loss is the mean square error Loss function, m is the number of samples, and Y' is a predicted value of the working capacity scoring result;
and a third data operation subunit, configured to calculate a gradient of the linear regression algorithm model coefficient to the loss according to the value of the mean square error loss function, where β=β -learning_rate×g, where learning_rate is a step learning rate for updating the control parameter, and G is a gradient.
Further, the matching allocation module includes:
the matching unit is used for comparing skill requirement values of all nodes obtained from the node personnel model library, obtaining a working capacity value grading result of the staff from the capacity evaluation module according to task requirements, and matching the working capacity value grading result to the best matched staff of the task according to the comparison result;
the distribution unit is connected with the matching unit and is used for distributing tasks to the best matching staff;
if the scoring result of the working capacity value of the staff is smaller than the skill requirement value of the node, the matching unit judges that the staff does not meet the working condition of the node;
and if the scoring result of the working capacity value of the staff is greater than or equal to the skill requirement value of the node, the matching unit judges that the staff meets the working condition of the node.
Further, the data analysis optimization module includes:
the data analysis unit is used for processing the acquired operation efficiency data, observing and analyzing the graph and calculating the processed data, and analyzing the task execution time, the task completion rate and the task delay index obtained by calculation;
the optimizing unit is connected with the data analyzing unit and is used for carrying out staff redistribution on each node according to the data analyzing result;
the data analysis unit is further configured to fill the missing values of the numerical data of the acquired operation efficiency data by using an average value, and fill the missing values of the classification variables by using a mode;
the data analysis unit calculates the average execution time, the minimum execution time, the maximum execution time and the standard deviation of the execution time, and shows the distribution condition of the task execution time obtained by calculation by using a histogram;
the data analysis unit calculates the percentage of task completion, and displays the calculated percentage of task completion by using a pie chart;
and the data analysis unit calculates the average value and the maximum value of the task delay, and displays the calculated distribution situation of the task delay by using a box diagram.
Further, the data analysis unit is also used for ranking the nodes according to the comparison results of the task execution time, the task completion rate and the task delay index among different nodes, the data analysis unit is internally provided with a ranking preset value,
and if the node rank is lower than the rank preset value, marking the node as a low-efficiency node by the data analysis unit, and reallocating staff to the low-efficiency node by the optimization unit.
Further, the data analysis unit obtains a comprehensive index based on the weighted summation according to the task execution time, the task completion rate and the task delay index between the different nodes, and compares and ranks the nodes according to the obtained comprehensive index, wherein the comprehensive index=the completion rate weight×the task completion rate+the delay weight×the average task delay time+the execution time weight×the average task execution time.
Further, the sorting subunit is configured to sort the low-efficiency nodes according to the low-efficiency node list, so as to ensure that the target node with the first current rank is the lowest-efficiency node, and sort the staff from high to low according to the staff list and the task list;
the allocation subunit is connected with the sequencing subunit and used for selecting the first staff member with the highest capacity grading value in the staff member list as the target staff member of the task, removing the task from the original staff member list and allocating the task to the target staff member;
and the output subunit is connected with the distribution subunit and used for outputting the redistributed staff list.
Further, a pipeline task management method comprises the following steps:
s1, collecting working years, skill levels and qualification certification levels of workers to be distributed in a production line;
s2, evaluating the working capacity value of the staff to be distributed according to the working years, skill level and qualification authentication level of the staff to be distributed;
s3, distributing the work task of each node to an optimal worker by comparing the work capacity value with the skill requirement value of each node recorded in the node personnel model library so as to form a pipeline array;
s4, monitoring the working efficiency of the optimal staff in the assembly line array in real time in the working process;
s5, performing data analysis on the operation efficiency obtained by the real-time monitoring of the task state tracking module to obtain task output efficiency of each node, and adjusting personnel allocation according to the task output efficiency and a preset target output efficiency to update staff of any node in the pipeline array.
Compared with the prior art, the invention has the beneficial effects that,
by collecting, evaluating and matching the capabilities of the staff, and combining the skill requirements of the nodes, the system can distribute tasks to the most suitable staff, and the task execution efficiency and quality are improved. Meanwhile, the real-time monitoring and data analysis of the task state enable the system to perform optimization adjustment according to actual conditions, and the running efficiency and the production capacity of the whole assembly line are improved.
Further, by inputting the collected data information of the staff member into the model, the capacity assessment model calculates the work capacity score of the staff member, and outputs the assessment result. Such a capability assessment module can help the pipeline task management system accurately assess the capability level of the staff, thereby better distributing tasks and improving work efficiency.
Further, feature fusion is carried out on the experience features of the working years, the skill level and the qualification level through the capability evaluation module, and the experience features are spliced in columns to form a feature vector. Such feature fusion may provide more comprehensive information for assessing work capacity. In this way, the capability assessment module is able to more accurately assess the capability and experience level of the staff, providing a beneficial guide for the allocation of pipeline tasks.
Furthermore, the capacity assessment model training process provided by the invention can gradually optimize the capacity assessment model, and finally obtain an accurate working capacity scoring result. Through such a capability assessment model, the pipelined task management system is able to more accurately assess the capability level of the staff providing beneficial guidance for task allocation.
Further, by calculating the optimal matching degree to perform optimal personnel matching, tasks can be more accurately distributed to suitable staff, and the working efficiency and quality are improved.
Further, the data analysis optimization module researches the distribution situation of task execution time, task completion rate and task delay indexes by observing and analyzing the chart and the calculated indexes. The average value and standard deviation of task execution time are particularly concerned, the percentage and the change trend of the task completion rate are observed, and the average condition and the maximum delay of task delay are analyzed. These analysis results provide critical insight and information that helps to understand the efficiency and quality of task execution, and thus optimize and improve.
Furthermore, through data analysis and optimization, the data analysis optimization module can timely identify low-efficiency nodes and perform optimization adjustment so as to improve the operation efficiency and the production capacity of the whole assembly line. This helps to achieve a reduction in task execution time, an increase in task completion rate, and a reduction in task latency, thereby improving overall efficiency of the pipeline.
Further, by comparing and ranking the comprehensive indexes of the nodes, the data analysis optimization module can know the performance of the different nodes in terms of task execution efficiency, task completion rate and task delay, and determine the relative quality degree of the nodes.
Furthermore, the data analysis optimization module can effectively optimize the staff allocation of the low-efficiency nodes through the optimization unit, and improve the execution efficiency and quality of tasks, so that the purposes of optimizing the pipeline operation and improving the overall performance are achieved.
Furthermore, the pipeline task management method improves the operation efficiency of the pipeline and the accuracy of task allocation by collecting, evaluating, distributing, monitoring and optimizing.
Drawings
FIG. 1 is a schematic diagram of a pipeline task management system according to the present invention;
FIG. 2 is a schematic diagram of a capability assessment module of the pipeline task management system according to the present invention;
FIG. 3 is a schematic diagram of a matching and distributing module of the pipeline task management system according to the present invention;
FIG. 4 is a schematic diagram of a data analysis optimization module of the pipeline task management system according to the present invention;
fig. 5 is a flow chart of a pipeline task management method according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1-4, fig. 1 is a schematic structural diagram of a pipeline task management system according to an embodiment of the present invention; FIG. 2 is a schematic diagram of a capability assessment module of the pipeline task management system according to an embodiment of the present invention; FIG. 3 is a schematic structural diagram of a matching and distributing module of the pipeline task management system according to the present invention; FIG. 4 is a schematic structural diagram of a data analysis optimization module of the pipeline task management system according to an embodiment of the present invention; fig. 5 is a flow chart of a pipeline task management method according to an embodiment of the present invention.
As shown in fig. 1, a pipeline task management system provided by an embodiment of the present invention includes:
the data collection module 1 is used for collecting the working years, skill levels and qualification certification levels of the staff to be distributed in the production line;
the capacity evaluation module 2 is connected with the data collection module and is used for evaluating the working capacity value of the staff to be distributed according to the working years, the skill level and the qualification authentication level of the staff to be distributed;
a node personnel model library 3 for providing skill requirement values for each node on the pipeline;
the matching distribution module 4 is respectively connected with the capability evaluation module and the node personnel model library and is used for distributing the work task of each node to the optimal personnel according to the work capability value and the skill requirement value so as to form a pipeline array;
the task state tracking module 5 is connected with the data collecting module and the matching distribution module and used for monitoring the working efficiency of the optimal staff in the assembly line array in real time in the working process;
the data analysis optimizing module 6 is respectively connected with the task state tracking module and the capability evaluating module and is used for carrying out data analysis on the working efficiency to obtain the task output efficiency of each node, and adjusting personnel allocation according to the task output efficiency and a preset target output efficiency so as to update the staff of any node in the pipeline array.
The data collection module collects working years, skill levels and qualification levels of workers to be distributed in a production line, the capacity assessment module assesses the working capacities of the workers to be distributed according to the working years, skill levels and qualification levels of the workers to be distributed, the matching distribution module distributes working tasks of each node to optimal workers by comparing the working capacities with skill requirement values of each node recorded in a node personnel model base to form a production line array, the task state tracking module monitors the working efficiency of the optimal workers in the production line array in real time in the working process, the data analysis optimization module analyzes the obtained working efficiency monitored in real time by the task state tracking module to obtain the task output efficiency of each node, and adjusts the personnel distribution according to the task output efficiency and preset target output efficiency so as to update the workers of any node in the production line array.
By collecting, evaluating and matching the capability values of the staff, and combining the skill requirements of the nodes, the system can distribute the tasks to the most suitable staff, and the task execution efficiency and quality are improved. Meanwhile, the real-time monitoring and data analysis of the task state enable the system to perform optimization adjustment according to actual conditions, and the running efficiency and the production capacity of the whole assembly line are improved.
Further, as shown in fig. 2, the capability assessment module 2 includes an extraction unit 21, a training unit 22, a calculation unit 23 and an output unit 24,
the extracting unit 21 is used for extracting the collected experience characteristics of the working years, skill level and qualification level of the staff;
the training unit 22 is connected with the extracting unit and is used for establishing a model with evaluation working capacity by using the experience characteristics;
the calculating unit 23 is connected with the training unit and is used for inputting the acquired data and the extracted experience characteristics thereof into the model with the estimated working capacity and calculating the working capacity score of the working personnel;
the output unit 24 is connected to the calculating unit, and is configured to output the performance scoring result.
The extraction unit extracts the collected empirical features of the working years, skill levels and qualification levels of the staff, the training unit builds a model with the estimated working capacity by using the empirical features, and the calculation unit calculates the working capacity score of the staff by inputting the collected data and the extracted empirical features into the model with the estimated working capacity.
The capability assessment model calculates the working capability scores of the staff members by inputting the data information of the re-collected staff members into the model, and outputs the assessment results. Such a capability assessment module can help the pipeline task management system accurately assess the capability level of the staff, thereby better distributing tasks and improving work efficiency.
Further, the extraction unit comprises a normalization subunit, a coding subunit and a splicing subunit,
the normalization subunit is configured to normalize the empirical feature of the working period by maximum-minimum normalization, where normalized working period= (actual working period-minimum working period)/(maximum working period-minimum working period);
the encoding subunit is used for performing single-heat encoding on the skill level and the qualification authentication level respectively, and creating binary characteristics for the skill and the qualification respectively;
and the splicing subunit is used for splicing the experience characteristics of the working years, the experience characteristics of the skill level and the experience characteristics of the qualification authentication level in columns to form a feature vector.
The standardized subunit normalizes the empirical feature of the working period through maximum-minimum standardization, the standardized working period= (actual working period-minimum working period)/(maximum working period-minimum working period), the encoding subunit performs single-heat encoding on the skill level and the qualification level respectively, and creates binary features on the skill level and the qualification level respectively, and the splicing subunit splices the empirical feature of the working period, the empirical feature of the skill level and the empirical feature of the qualification level in columns to form a feature vector.
And carrying out feature fusion on the experience features of the working years, the skill level and the qualification authentication level through the capability evaluation module, and splicing the experience features into a feature vector according to the columns. Such feature fusion may provide more comprehensive information for assessing work capacity. In this way, the capability assessment module is able to more accurately assess the capability and experience level of the staff, providing a beneficial guide for the allocation of pipeline tasks.
Further, the training unit comprises a model selection subunit, a data preprocessing subunit, a data operation first subunit, a data operation second subunit and a data operation third subunit;
the model selection subunit is configured to select a linear regression algorithm model: y=β0+β1×x1+β2×x2+ & βn×xn, where Y is the outcome of the work capacity scoring, X1, X2, & gt, xn are empirical features, β0, β1, & gt, βn are coefficients of the linear regression algorithm model;
the data preprocessing subunit is used for dividing the collected experience feature set into a training set and a testing set, 80% of experience features are used for training the linear regression algorithm model, the missing value of numerical data of the training set is filled by an average value, the missing value of a classification variable is filled by a mode, the coefficient of the linear regression algorithm model is initialized, and the initial value is set to be 0;
a first subunit of data operation for calculating a predicted value Y' =β0+β1×x1+β2×x2+ & ltβn×xn according to the current coefficient of the linear regression algorithm model,
the data operation second subunit 224 is configured to calculate, using a mean square error Loss function, loss= (1/m) ×Σ (Y '-Y)/(2), where Loss is the mean square error Loss function, m is the number of samples, and Y' is a predicted value of the performance scoring result;
the data operation third subunit is configured to calculate a gradient of the linear regression algorithm model coefficient to the loss according to the value of the mean square error loss function, where β=β -learning_rate×g, where learning_rate is a step learning rate for controlling parameter update, and G is a gradient;
and repeating the data operation first subunit to calculate the predicted value, the data operation second subunit to calculate the mean square error loss function and the data operation third subunit to calculate the gradient of the linear regression algorithm model coefficient pair loss until the number of iterations of training is completed.
The training process of the capacity assessment model provided by the invention can gradually optimize the capacity assessment model, and finally obtain an accurate working capacity scoring result. Through such a capability assessment model, the pipelined task management system is able to more accurately assess the capability level of the staff providing beneficial guidance for task allocation.
Further, as shown in fig. 3, the matching distribution module 4 includes a matching unit 41 and a distribution unit 42,
the matching unit 41 is configured to compare the skill requirement values of each node obtained from the node personnel model library with the working capability scoring results of the staff obtained from the capability assessment module according to the task requirements, and match the best matching staff to the task according to the comparison results;
the allocation unit 42 is connected with the matching unit and is used for allocating tasks to the best matching staff;
if the result of the staff capacity score is smaller than the skill requirement value of the node, the matching unit 41 determines that the staff does not meet the working condition of the node;
if the working ability scoring result of the staff member is greater than or equal to the skill requirement value of the node, the matching unit 41 determines that the staff member meets the working condition of the node;
the matching unit 41 calculates the matching degree of the staff meeting the working condition of the node using the euclidean distance,
euclidean distance =Wherein An represents the capability assessment value of the nth dimension of the staff member, and Bn represents the skill requirement value of the nth dimension of the node;
the matching unit 41 uses the formula: matching degree score=1/(1+euclidean distance) converting euclidean distance into matching degree score;
the matching unit 41 finds the worker whose matching score is closest to 1 as the best matching worker based on the matching score.
The optimal personnel matching is performed by calculating the optimal matching degree, so that tasks can be more accurately distributed to suitable working personnel, and the working efficiency and quality are improved.
Further, as shown in fig. 4, the data analysis optimizing module 6 includes a data analysis unit 61 and an optimizing unit 62,
the data analysis unit 61 is configured to process the acquired work efficiency data, observe and analyze graphs and calculations on the processed data, and analyze task execution time, task completion rate, and task delay index obtained by calculation;
the optimizing unit 62 is connected with the data analyzing unit and is used for carrying out staff redistribution on each node according to the data analysis result;
the data analysis unit 61 fills in the missing values of the numerical data of the acquired work efficiency data by using the average value, and fills in the missing values of the classification variables by using the mode;
the data analysis unit 61 calculates the average execution time, the minimum execution time, the maximum execution time and the standard deviation of the execution time, and uses a histogram to show the distribution of the task execution time obtained by calculation;
the data analysis unit 61 calculates the percentage of task completion, and displays the calculated percentage of task completion using a pie chart;
the data analysis unit 61 calculates the average value and the maximum value of the task delays, displays the calculated distribution situation of the task delays by using a box diagram, and observes, analyzes and calculates the processed data, wherein the main tasks are as follows:
filling the missing value: the missing values of the numerical data are filled with the average values, and the missing values of the classification variables are filled with the mode values.
Task execution time analysis: and calculating the average execution time, the minimum execution time, the maximum execution time and the standard deviation of the execution time of the research task so as to know the distribution condition of the execution time of the task. The calculation results can be displayed through a bar graph, so that a user can intuitively understand the change of task execution time.
Task completion rate analysis: the percentage of task completion is calculated to understand the task completion rate. These calculations can be presented in a pie chart to allow the user to clearly understand the percentage of task completion.
Task delay index analysis: the average and maximum values of the task delays are calculated to learn about the task delays. The calculation results can be displayed through a box diagram, so that a user can intuitively know the distribution condition of task delay.
The optimizing unit 62 redistributes staff to each node according to the data analysis result, and a specific optimizing strategy can be determined according to the data analysis result, for example, the number of staff of a certain node is increased or decreased, so as to achieve better task execution efficiency and resource utilization rate.
The data analysis optimization module researches the distribution situation of task execution time, task completion rate and task delay indexes by observing and analyzing the chart and the calculated indexes. The average value and standard deviation of task execution time are particularly concerned, the percentage and the change trend of the task completion rate are observed, and the average condition and the maximum delay of task delay are analyzed. These analysis results provide critical insight and information that helps to understand the efficiency and quality of task execution, and thus optimize and improve.
Further, the data analysis unit 61 compares task execution time, task completion rate and task delay index between different nodes, ranks the nodes to obtain node rank W, a rank preset value Q is set in the data analysis unit,
if W < Q, the data analysis unit 61 marks the node as a low efficiency node, and the optimization unit 42 performs staff reassignment to the low efficiency node.
Through data analysis and optimization, the data analysis optimization module can timely identify low-efficiency nodes and perform optimization adjustment so as to improve the operation efficiency and the production capacity of the whole assembly line. This helps to achieve a reduction in task execution time, an increase in task completion rate, and a reduction in task latency, thereby improving overall efficiency of the pipeline.
Further, the data analysis unit 61 compares and ranks the comprehensive indexes obtained by comparing the task execution time, the task completion rate, and the task delay index between the different nodes by using a weighted summation method, the comprehensive indexes=the completion rate weight×the task completion rate+the delay weight×the average task delay time+the execution time weight×the average task execution time.
By comparing and ranking the comprehensive indexes of the nodes, the data analysis optimization module can know the performance of the different nodes in terms of task execution efficiency, task completion rate and task delay, and determine the relative quality degree of the nodes.
Further, the optimizing unit 62 includes:
the sequencing subunit is used for sequencing the low-efficiency nodes according to the low-efficiency node list so as to ensure that the target node with the first current ranking is the lowest-efficiency node, and sequencing the staff from high to low according to the staff list and the task list;
the allocation subunit is connected with the sequencing subunit and used for selecting the first staff member with the highest capacity grading value in the staff member list as the target staff member of the task, removing the task from the original staff member list and allocating the task to the target staff member;
and the output subunit is connected with the distribution subunit and used for outputting the redistributed staff list.
The sorting subunit sorts the low-efficiency nodes according to the low-efficiency node list to ensure that the target node with the first current rank is the lowest-efficiency node, sorts the workers from high to low according to the worker list and the task list, then the distribution subunit selects the worker with the highest capability score value in the first worker list as the target worker of the task, removes the task from the original worker list, distributes the task to the target worker, and finally the output subunit outputs the redistributed worker list.
Through the optimizing unit, the data analysis optimizing module can effectively optimize the staff allocation of the low-efficiency nodes, and improve the execution efficiency and quality of tasks, so that the purposes of optimizing the pipeline operation and improving the overall performance are achieved.
Further, as shown in fig. 5, an embodiment of the present invention further provides a pipeline task management method, based on the pipeline task management system, the method includes the following steps:
s1, collecting working years, skill levels and qualification certification levels of workers to be distributed in a production line;
s2, evaluating the working capacity of the staff to be distributed according to the working years, skill levels and qualification authentication levels of the staff to be distributed;
s3, distributing the work task of each node to an optimal worker by comparing the work capacity with the skill requirement value of each node recorded in the node personnel model library so as to form a pipeline array;
s4, monitoring the working efficiency of the optimal staff in the assembly line array in real time in the working process;
s5, performing data analysis on the operation efficiency obtained by the real-time monitoring of the task state tracking module to obtain task output efficiency of each node, and adjusting personnel allocation according to the task output efficiency and a preset target output efficiency to update staff of any node in the pipeline array.
The pipeline task management method improves the operation efficiency of the pipeline and the accuracy of task allocation by collecting, evaluating, distributing, monitoring and optimizing.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A pipelined task management system comprising:
the data collection module is used for collecting the working years, skill levels and qualification certification levels of the staff to be distributed in the production line;
the capacity evaluation module is connected with the data collection module and used for evaluating the working capacity value of the staff to be distributed according to the working years, the skill level and the qualification authentication level of the staff to be distributed;
a node personnel model library for providing skill requirement values for each node on the pipeline;
the matching distribution module is respectively connected with the capability evaluation module and the node personnel model library and is used for distributing the work task of each node to the optimal personnel according to the work capability value and the skill requirement value so as to form a pipeline array;
the task state tracking module is connected with the data collecting module and the matching distribution module and used for monitoring the working efficiency of the optimal staff in the assembly line array in real time in the working process;
the data analysis optimization module is respectively connected with the task state tracking module and the capability assessment module and is used for carrying out data analysis on the working efficiency to acquire the task output efficiency of each node, and staff distributed to update any node in the pipeline array according to the task output efficiency and a preset target output efficiency.
2. The pipelined task management system of claim 1, wherein the capability assessment module comprises:
the extraction unit is used for extracting the collected experience characteristics of the working years, skill level and qualification authentication level of the staff;
the training unit is connected with the extraction unit and is used for establishing a model with an estimated working capacity value by using the experience characteristics;
the calculation unit is connected with the training unit and is used for inputting the acquired data and the extracted experience characteristics thereof into the model with the estimated working capacity value and calculating the working capacity value score of the working personnel;
and the output unit is connected with the calculation unit and is used for outputting the scoring result of the working capacity value.
3. The pipeline task management system of claim 2, wherein the fetch unit comprises:
a normalization subunit for normalizing the empirical feature of the working years by maximum-minimum normalization, normalized working years= (actual working years-minimum working years)/(maximum working years-minimum working years);
the coding subunit is used for performing single-heat coding on the skill level and the qualification certification level respectively and creating binary characteristics on the skill level and the qualification certification level respectively;
and the splicing subunit is used for splicing the experience characteristics of the working years, the experience characteristics of the skill level and the experience characteristics of the qualification certification level in columns to form a characteristic vector.
4. A pipeline task management system according to claim 3, wherein the training unit comprises:
a model selection subunit for selecting a linear regression algorithm model: y=β0+β1×x1+β2×x2+ & βn×xn, where Y is the outcome of the work capacity scoring, X1, X2, & gt, xn are empirical features, β0, β1, & gt, βn are coefficients of the linear regression algorithm model;
the data preprocessing subunit is used for dividing the collected experience feature set into a training set and a testing set, 80% of experience features are used for training the linear regression algorithm model, the missing value of numerical data of the training set is filled by an average value, the missing value of a classification variable is filled by a mode, the coefficient of the linear regression algorithm model is initialized, and the initial value is set to be 0;
a first data operation subunit for calculating a predicted value Y' =β0+β1×x1+β2×x2+, +βn×xn according to the current coefficient of the linear regression algorithm model,
a data operation second subunit, configured to calculate, using a mean square error Loss function, loss= (1/m) x Σ (Y '-Y) 2, where Loss is the mean square error Loss function, m is the number of samples, and Y' is a predicted value of the working capacity scoring result;
and a third data operation subunit, configured to calculate a gradient of the linear regression algorithm model coefficient to the loss according to the value of the mean square error loss function, where β=β -learning_rate×g, where learning_rate is a step learning rate for updating the control parameter, and G is a gradient.
5. The pipelined task management system of claim 4, wherein the match assignment module comprises:
the matching unit is used for comparing skill requirement values of all nodes obtained from the node personnel model library, obtaining a working capacity value grading result of the staff from the capacity evaluation module according to task requirements, and matching the working capacity value grading result to the best matched staff of the task according to the comparison result;
the distribution unit is connected with the matching unit and is used for distributing tasks to the best matching staff;
if the scoring result of the working capacity value of the staff is smaller than the skill requirement value of the node, the matching unit judges that the staff does not meet the working condition of the node;
and if the scoring result of the working capacity value of the staff is greater than or equal to the skill requirement value of the node, the matching unit judges that the staff meets the working condition of the node.
6. The pipeline task management system of claim 5, wherein the data analysis optimization module comprises:
the data analysis unit is used for processing the acquired operation efficiency data, observing and analyzing the graph and calculating the processed data, and analyzing the task execution time, the task completion rate and the task delay index obtained by calculation;
the optimizing unit is connected with the data analyzing unit and is used for carrying out staff redistribution on each node according to the data analyzing result;
the data analysis unit is further configured to fill the missing values of the numerical data of the acquired operation efficiency data by using an average value, and fill the missing values of the classification variables by using a mode;
the data analysis unit calculates the average execution time, the minimum execution time, the maximum execution time and the standard deviation of the execution time, and shows the distribution condition of the task execution time obtained by calculation by using a histogram;
the data analysis unit calculates the percentage of task completion, and displays the calculated percentage of task completion by using a pie chart;
and the data analysis unit calculates the average value and the maximum value of the task delay, and displays the calculated distribution situation of the task delay by using a box diagram.
7. The pipeline task management system of claim 6, wherein the data analysis unit is further configured to rank the nodes according to a comparison result of task execution time, task completion rate, and task delay index between different nodes, a ranking preset value is set in the data analysis unit,
and if the node rank is lower than the rank preset value, marking the node as a low-efficiency node by the data analysis unit, and reallocating staff to the low-efficiency node by the optimization unit.
8. The pipeline task management system of claim 7, wherein the data analysis unit obtains a comprehensive index based on a weighted sum according to task execution time, task completion rate, and task delay index between the different nodes, and compares and ranks the respective nodes according to the obtained comprehensive index, wherein comprehensive index = completion rate weight x task completion rate + delay weight x average task delay time + execution time weight x average task execution time.
9. The pipeline task management system of claim 8, wherein the optimization unit comprises:
the sequencing subunit is used for sequencing the low-efficiency nodes according to the low-efficiency node list so as to ensure that the target node with the first current ranking is the lowest-efficiency node, and sequencing the staff from high to low according to the staff list and the task list;
the allocation subunit is connected with the sequencing subunit and used for selecting the first staff member with the highest capacity grading value in the staff member list as the target staff member of the task, removing the task from the original staff member list and allocating the task to the target staff member;
and the output subunit is connected with the distribution subunit and used for outputting the redistributed staff list.
10. A pipeline task management method based on the pipeline task management system according to any one of claims 1-9, characterized by comprising the steps of:
s1, collecting working years, skill levels and qualification certification levels of workers to be distributed in a production line;
s2, evaluating the working capacity value of the staff to be distributed according to the working years, skill level and qualification authentication level of the staff to be distributed;
s3, distributing the work task of each node to an optimal worker by comparing the work capacity value with the skill requirement value of each node recorded in the node personnel model library so as to form a pipeline array;
s4, monitoring the working efficiency of the optimal staff in the assembly line array in real time in the working process;
s5, performing data analysis on the operation efficiency obtained by the real-time monitoring of the task state tracking module to obtain task output efficiency of each node, and adjusting personnel allocation according to the task output efficiency and a preset target output efficiency to update staff of any node in the pipeline array.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410008452.8A CN117541021A (en) | 2024-01-04 | 2024-01-04 | Pipeline task management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410008452.8A CN117541021A (en) | 2024-01-04 | 2024-01-04 | Pipeline task management system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117541021A true CN117541021A (en) | 2024-02-09 |
Family
ID=89788385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410008452.8A Pending CN117541021A (en) | 2024-01-04 | 2024-01-04 | Pipeline task management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117541021A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829561A (en) * | 2024-03-06 | 2024-04-05 | 贵州黔聚龙科技有限公司 | Construction state self-analysis-based high-standard farmland constructor distribution method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015181904A1 (en) * | 2014-05-28 | 2015-12-03 | 株式会社 日立製作所 | Personnel planning system and personnel planning method |
| CN109190929A (en) * | 2018-08-14 | 2019-01-11 | 中国平安人寿保险股份有限公司 | A kind of workload methodology, device, computer equipment and storage medium |
| CN110378598A (en) * | 2019-07-20 | 2019-10-25 | 湖南科技学院 | A kind of producing line intelligent evaluation system based on cloud computing technology |
| CN111626616A (en) * | 2020-05-27 | 2020-09-04 | 深圳莫比嗨客数据智能科技有限公司 | Crowdsourcing task recommendation method |
| CN114240071A (en) * | 2021-11-25 | 2022-03-25 | 南京南瑞信息通信科技有限公司 | Emergency scheduling device and method based on dynamic personnel bearing capacity |
| CN117114359A (en) * | 2023-09-27 | 2023-11-24 | 河北久维电子科技有限公司 | Electric power metering operation safety on-line monitoring system and method thereof |
| CN117132171A (en) * | 2023-10-26 | 2023-11-28 | 江苏工小兔信息科技有限公司 | Automatic office information management system |
-
2024
- 2024-01-04 CN CN202410008452.8A patent/CN117541021A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015181904A1 (en) * | 2014-05-28 | 2015-12-03 | 株式会社 日立製作所 | Personnel planning system and personnel planning method |
| CN109190929A (en) * | 2018-08-14 | 2019-01-11 | 中国平安人寿保险股份有限公司 | A kind of workload methodology, device, computer equipment and storage medium |
| CN110378598A (en) * | 2019-07-20 | 2019-10-25 | 湖南科技学院 | A kind of producing line intelligent evaluation system based on cloud computing technology |
| CN111626616A (en) * | 2020-05-27 | 2020-09-04 | 深圳莫比嗨客数据智能科技有限公司 | Crowdsourcing task recommendation method |
| CN114240071A (en) * | 2021-11-25 | 2022-03-25 | 南京南瑞信息通信科技有限公司 | Emergency scheduling device and method based on dynamic personnel bearing capacity |
| CN117114359A (en) * | 2023-09-27 | 2023-11-24 | 河北久维电子科技有限公司 | Electric power metering operation safety on-line monitoring system and method thereof |
| CN117132171A (en) * | 2023-10-26 | 2023-11-28 | 江苏工小兔信息科技有限公司 | Automatic office information management system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829561A (en) * | 2024-03-06 | 2024-04-05 | 贵州黔聚龙科技有限公司 | Construction state self-analysis-based high-standard farmland constructor distribution method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699913B (en) | Method and device for diagnosing abnormal relationship of household transformer in transformer area | |
| Garg | A hybrid GA-GSA algorithm for optimizing the performance of an industrial system by utilizing uncertain data | |
| CN108364106A (en) | A kind of expense report Risk Forecast Method, device, terminal device and storage medium | |
| CN117541021A (en) | Pipeline task management system | |
| CN108491991B (en) | Constraint condition analysis system and method based on industrial big data product construction period | |
| TW201615844A (en) | Method and system of cause analysis and correction for manufacturing data | |
| CN111292020B (en) | Power grid real-time operation risk assessment method and system based on random forest | |
| CN116760772B (en) | Control system and method for converging flow divider | |
| CN117389236B (en) | Propylene oxide production process optimization method and system | |
| CN109711707B (en) | Comprehensive state evaluation method for ship power device | |
| CN110476158A (en) | Data analysis equipment, data analysing method and data analysis program | |
| CN111178537A (en) | Feature extraction model training method and device | |
| JP2019028834A (en) | Abnormal value diagnostic device, abnormal value diagnostic method, and program | |
| CA2034492A1 (en) | Method of monitoring the operational state of a system | |
| CN115640860A (en) | Electromechanical equipment remote maintenance method and system for industrial cloud service | |
| CN108846489A (en) | A kind of large scale equipment health Evaluation method based on SVM | |
| CN117290462A (en) | Intelligent decision system and method for large data model | |
| CN114528764A (en) | Soft measurement modeling method and device based on integral optimization and instant learning | |
| CN113570180A (en) | Plant control support device, program, and plant control support method | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| Rao | Flexible manufacturing system selection using an improved compromise ranking method | |
| CN110955700A (en) | 4D mode-based engineering cost lean control method and system | |
| Singer et al. | The funnel experiment: The Markov‐based SPC approach | |
| CN117592789B (en) | Power grid environment fire risk assessment method and equipment based on time sequence analysis | |
| CN115114983B (en) | Method for acquiring and analyzing electric quantity data based on big data equipment and computer system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |