A personnel intelligent scheduling method and system based on big data

Abstract

The present invention discloses a personnel intelligent scheduling method and system based on big data, which relates to the technical field of personnel scheduling, including: collecting real-time status data and task information of staff; cleaning and preprocessing the real-time status data and task information; analyzing the preprocessed real-time status data, identifying the working status of the staff, analyzing and predicting the time taken by the staff to complete the task according to the task information, and automatically adjusting the allocation and task arrangement of the staff; monitoring the real-time status data and task execution of the staff, and setting a threshold, when the real-time status data is greater than the threshold, feedback and adjustment of the staff task arrangement are performed through the intelligent scheduling model. The present invention improves work efficiency and resource utilization, and is suitable for various scenarios that require dynamic scheduling of staff, such as logistics distribution, customer service, production and manufacturing, and other fields.

Description

Technical Field

[0001] The present invention relates to the technical field of personnel scheduling, and more specifically to a personnel intelligent scheduling method and system based on big data. Background Art

[0002] At present, more and more projects involve personnel scheduling issues during operation, such as door-to-door services (such as appointment pickup service, door-to-door delivery service, housekeeping service), cargo transportation, etc.

[0003] Take home delivery as an example. The time spent by the staff not only includes the time to complete the task, but also the time to travel to the task location. This makes the task allocation and work status of the staff an important factor affecting whether the task is completed efficiently.

[0004] Existing technologies usually only allocate tasks to workers manually or through traditional scheduling systems, without considering the real-time status of workers and the time consumption of tasks. This makes the final allocation of tasks to workers unreasonable, resulting in workers being unable to complete tasks in a timely and efficient manner.

[0005] Therefore, how to provide a personnel intelligent scheduling method and system based on big data, automatically adjust personnel allocation and task arrangement according to personnel's real-time status and task duration, and improve work efficiency and resource utilization is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0006] In view of this, the present invention provides a personnel intelligent scheduling method and system based on big data, which automatically adjusts personnel allocation and task arrangement according to the real-time status of the staff and the duration of the task, improves work efficiency and resource utilization, and is suitable for various scenarios that require dynamic scheduling of staff, such as logistics distribution, customer service, production and manufacturing, etc.

[0007] In order to achieve the above object, the present invention adopts the following technical solution: a personnel intelligent scheduling method based on big data, comprising:

[0008] Collect real-time status data and task information of staff;

[0009] Cleaning and preprocessing the real-time status data and the task information;

[0010] Build an intelligent scheduling model to analyze the pre-processed real-time status data, identify the work status of the staff, analyze and predict the time it takes for the staff to complete the task based on the task information, and automatically adjust the staff allocation and task arrangement;

[0011] The real-time status data and task execution status of the staff are monitored, and a threshold is set. When the real-time status data is greater than the threshold, the staff task arrangement is fed back and adjusted through the intelligent scheduling model.

[0012] Preferably, the real-time status data of the staff includes: real-time location information collected by GPS positioning, workload information collected by sensors, and work progress information collected by face recognition and / or voice recognition; and the collected real-time status data is stored on a big data platform.

[0013] Preferably, the real-time status data and the task information are cleaned and preprocessed, including: data deduplication, missing value processing, outlier processing, data format unification, data conversion and data merging processing.

[0014] Preferably, the pre-processed real-time status data is analyzed to identify the working status of the staff, including:

[0015] The preprocessed real-time status data is clustered using cluster analysis method, and a working status classification method based on thermal image matrix eigenvalue matching is proposed;

[0016] Each color area of ​​the thermal image is extracted separately to obtain data matrices of different colors. The norm and spectrum radius of the thermal image matrix of all different working states are solved, matching conditions are established, and iterative operations are performed to obtain the working status of the staff;

[0017] The working status of staff members is divided into five categories: working, resting, busy, idle and abnormal.

[0018] Preferably, the time taken by the staff to complete the task is counted and analyzed based on the task information, including:

[0019] Collect historical data on tasks completed by workers;

[0020] Conduct statistical analysis on the collected historical data and calculate the time it takes for each staff member to complete the task;

[0021] The ARMA autoregressive moving average model algorithm is used as the time series analysis and prediction algorithm to model the time taken by each staff member to complete the task, establish a time series prediction model, and calculate the model parameters;

[0022] Based on the established time series prediction model, the time required for each worker to complete the task in the next task is predicted.

[0023] Preferably, the automatic adjustment of personnel allocation and task arrangement includes:

[0024] Based on the working status of the staff and the predicted working time, the staff are sorted, the tasks are divided into different priorities according to the time consumption of the tasks, and the staff with different working status are arranged.

[0025] Preferably, the intelligent scheduling model is used to provide feedback and adjust the staff task arrangement, including:

[0026] Reassign tasks, adjust task priorities, or provide additional support or resources to staff through intelligent scheduling models;

[0027] And send adjustment notifications to managers in a timely manner so that they can understand the latest task arrangements and adjustments.

[0028] A personnel intelligent dispatching system based on big data, comprising:

[0029] The collection module is used to collect the real-time status data and task information of the staff;

[0030] A preprocessing module, used for cleaning and preprocessing the real-time status data and the task information;

[0031] The model building and analysis module is used to build an intelligent scheduling model, analyze the pre-processed real-time status data, identify the working status of the staff, analyze and predict the time it takes for the staff to complete the task based on the task information, and automatically adjust the staff allocation and task arrangement;

[0032] The feedback adjustment module is used to monitor the real-time status data and task execution status of the staff and set a threshold. When the real-time status data is greater than the threshold, the staff task arrangement is fed back and adjusted through the intelligent scheduling model.

[0033] Through the above technical solutions, it can be known that compared with the prior art, the present invention discloses a method and system for intelligent scheduling of personnel based on big data, including: collecting real-time status data and task information of staff; cleaning and preprocessing the real-time status data and the task information; building an intelligent scheduling model, analyzing the preprocessed real-time status data, identifying the working status of the staff, analyzing and predicting the time taken by the staff to complete the task according to the task information, and automatically adjusting the allocation and task arrangement of the staff; monitoring the real-time status data and task execution of the staff, and setting a threshold, when the real-time status data is greater than the threshold, feedback and adjustment are performed on the task arrangement of the staff through the intelligent scheduling model. The present invention automatically adjusts the allocation and task arrangement of personnel according to the real-time status and task time of the staff, and feedbacks and adjusts the task arrangement of the staff through the intelligent scheduling model, so as to more flexibly respond to the actual working situation and improve work efficiency and task completion quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0035] Figure 1 A schematic flow chart of a method for intelligent personnel scheduling based on big data provided by the present invention.

[0036] Figure 2 A schematic diagram of the structure of a personnel intelligent scheduling system based on big data provided by the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] The embodiment of the present invention discloses a personnel intelligent scheduling method and system based on big data, which automatically adjusts the allocation of personnel and task arrangement according to the real-time status of the personnel and the time consumption of the task, and provides feedback and adjustment to the task arrangement of the personnel through the intelligent scheduling model, so as to respond to the actual work situation more flexibly and improve work efficiency and task completion quality.

[0039] The embodiment of the present invention discloses a method for intelligent personnel scheduling based on big data, such as Figure 1 As shown, including:

[0040] Collect real-time status data and task information of staff;

[0041] Cleaning and preprocessing the real-time status data and the task information;

[0042] Build an intelligent scheduling model to analyze the pre-processed real-time status data, identify the work status of the staff, analyze and predict the time it takes for the staff to complete the task based on the task information, and automatically adjust the staff allocation and task arrangement;

[0043] The real-time status data and task execution status of the staff are monitored, and a threshold is set. When the real-time status data is greater than the threshold, the staff task arrangement is fed back and adjusted through the intelligent scheduling model.

[0044] Specifically, the real-time status data of the staff includes: real-time location information collected by GPS positioning, workload information collected by sensors, and work progress information collected by face recognition and / or voice recognition; and the collected real-time status data is stored on the big data platform. The workload information includes data such as the number of steps, heart rate, sleep time, etc. of the staff; the work progress information includes data such as confirmation of the working time or rest time of the staff.

[0045] Specifically, the real-time status data and the task information are cleaned and preprocessed, including: data deduplication, missing value processing, outlier processing, data format unification, data conversion, and data merging processing. The quality of the real-time status data and task information is ensured, providing a reliable data foundation for subsequent data analysis and intelligent scheduling algorithms.

[0046] Specifically, the pre-processed real-time status data is analyzed to identify the working status of the staff, including:

[0047] The preprocessed real-time status data is clustered using cluster analysis method, and a working status classification method based on thermal image matrix eigenvalue matching is proposed;

[0048] Each color area of ​​the thermal image is extracted separately to obtain data matrices of different colors. The norm and spectrum radius of the thermal image matrix of all different working states are solved, matching conditions are established, and iterative operations are performed to obtain the working status of the staff;

[0049] The working status of staff members is divided into five categories: working, resting, busy, idle and abnormal.

[0050] Specifically, work: means that the staff is carrying out work tasks and is in a normal working state;

[0051] Rest: It means that the staff is taking a break, having a meal or temporarily leaving the work station and is in a resting state;

[0052] Busy: This means that although the staff member does not have specific work tasks, he or she is unable to accept new tasks or communicate due to other reasons;

[0053] Idle: indicates that the staff member has no specific work tasks and can accept new tasks or communicate;

[0054] Abnormal: Indicates that the staff is currently in an abnormal state and needs to rest or stop accepting new tasks.

[0055] Based on the cluster analysis method, cluster analysis is performed on the pre-processed real-time status data to ensure that tasks can be processed in a timely manner according to the real-time status of personnel, while avoiding waste and excessive load of human resources.

[0056] Specifically, the time taken by staff to complete tasks is counted and analyzed based on task information, including:

[0057] Collect historical data on tasks completed by workers, including the start and end time of the task, the type of task, and specific requirements. This data can be obtained through system records, manual input, or sensors.

[0058] Conduct statistical analysis on the collected historical data and calculate the time it takes for each staff member to complete the task; calculate statistical indicators such as average time, longest time, shortest time, and the distribution of task time.

[0059] The ARMA autoregressive moving average model algorithm is used as the time series analysis and prediction algorithm to model the time taken by each staff member to complete the task, establish a time series prediction model, and calculate the model parameters;

[0060] Based on the established time series prediction model, the time required for each worker to complete the task in the next task is predicted.

[0061] Use time series analysis methods to analyze the changing patterns of staff work efficiency and task time consumption, and predict the time it takes for each staff member to complete the task in the next task, providing a basis for further optimizing task allocation, improving production efficiency and improving work processes.

[0062] Specifically, the automatic adjustment of personnel allocation and task arrangement includes:

[0063] Based on the working status of the staff and the predicted working time, the staff are sorted, the tasks are divided into different priorities according to the time consumption of the tasks, and the staff with different working status are arranged.

[0064] Divide tasks into different priorities so that longer tasks are assigned to workers with more available time. For example, workers with more available time and a shorter forecasted time can be assigned high-priority tasks, while workers with heavier workloads or shorter available time can be assigned low-priority tasks.

[0065] Specifically, the intelligent scheduling model is used to provide feedback and adjust the staff task arrangement, including:

[0066] Reassign tasks, adjust task priorities, or provide additional support or resources to staff through intelligent scheduling models;

[0067] And send adjustment notifications to managers in a timely manner so that they can understand the latest task arrangements and adjustments.

[0068] Through the intelligent scheduling model, feedback and adjustments are made to the staff's task arrangements, so as to respond more flexibly to actual work situations and improve work efficiency and task completion quality.

[0069] In a specific embodiment of the present invention, it is applied to the field of logistics distribution to realize intelligent scheduling and monitoring of logistics personnel, which specifically includes the following steps:

[0070] S1. Collect real-time status data and task information of logistics personnel;

[0071] Among them, the high-precision positioning service provided by the 5G network is used in combination with indoor and outdoor positioning technology to realize real-time monitoring and positioning of the location of logistics personnel, collect workload information of logistics personnel through sensors, and collect work progress information of logistics personnel through face recognition and / or voice recognition; and store the collected real-time status data on the big data platform. The workload information includes data such as the number of steps, heart rate, and sleep time of logistics personnel; the work progress information includes: confirming the length of time the logistics personnel have worked or rested, etc. IoT devices, such as sensors, RFID, etc., can also be deployed in logistics scenarios to realize real-time monitoring of goods and equipment.

[0072] S2. Cleaning and preprocessing the real-time status data and the task information.

[0073] S3. Build an intelligent scheduling model to analyze the pre-processed real-time status data, identify the working status of logistics personnel, analyze and predict the time it takes for logistics personnel to complete tasks based on task information, and automatically adjust the allocation and task arrangement of logistics personnel;

[0074] The working status of logistics personnel is analyzed by cluster analysis method, and the time taken by logistics personnel to complete the distribution task is analyzed by time series analysis prediction algorithm, and the time taken for the next task is predicted. Combined with the results of the two analyses, tasks are divided into different priorities according to the time taken, and different logistics personnel are arranged. Logistics personnel with more available time and shorter predicted working time can be assigned high-priority tasks first, while logistics personnel with heavier workload or shorter available time can be assigned low-priority tasks. High-priority tasks are tasks with longer time and higher rewards, while low-priority tasks are tasks with shorter time and lower rewards. This improves logistics efficiency and reduces costs.

[0075] S4. Monitor the real-time status data and task execution status of the logistics personnel and set a threshold. When the real-time status data is greater than the threshold, feedback and adjustment are made to the task arrangement of the logistics personnel through the intelligent scheduling model.

[0076] For example: when the working hours, steps or heart rate of logistics personnel reach the preset threshold, they will be arranged to take a break after completing the current task;

[0077] When the rest time of logistics personnel reaches the preset threshold, new tasks will be arranged for them.

[0078] By real-time monitoring of the location of logistics personnel and the status of goods, and timely adjusting the dispatch strategy according to the real-time status data of logistics personnel, real-time monitoring and dispatch of logistics personnel can be achieved.

[0079] The embodiment of the present invention also discloses a personnel intelligent scheduling system based on big data, such as Figure 2 As shown, including:

[0080] The collection module is used to collect the real-time status data and task information of the staff;

[0081] A preprocessing module, used for cleaning and preprocessing the real-time status data and the task information;

[0082] The model building and analysis module is used to build an intelligent scheduling model, analyze the pre-processed real-time status data, identify the working status of the staff, analyze and predict the time it takes for the staff to complete the task based on the task information, and automatically adjust the staff allocation and task arrangement;

[0083] The feedback adjustment module is used to monitor the real-time status data and task execution status of the staff and set a threshold. When the real-time status data is greater than the threshold, the staff task arrangement is fed back and adjusted through the intelligent scheduling model.

[0084] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0085] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A personnel intelligent scheduling method based on big data, characterized in that: include: Collect real-time status data and task information of staff; Cleaning and preprocessing the real-time status data and the task information; Build an intelligent scheduling model to analyze the pre-processed real-time status data, identify the work status of the staff, analyze and predict the time it takes for the staff to complete the task based on the task information, and automatically adjust the staff allocation and task arrangement; Monitor the real-time status data and task execution status of the staff and set a threshold. When the real-time status data is greater than the threshold, feedback and adjustment of the staff task arrangement are performed through the intelligent scheduling model; The real-time status data of the staff includes: real-time location information collected by GPS positioning, workload information collected by sensors, and work progress information collected by face recognition and / or voice recognition; and the collected real-time status data is stored on the big data platform; The automatic adjustment of staff allocation and task arrangement includes: Based on the working status of the staff and the predicted working time, the staff are sorted, the tasks are divided into different priorities according to the time consumption of the tasks, and the staff with different working status are arranged; Analyze the pre-processed real-time status data to identify the working status of the staff, including: The preprocessed real-time status data is clustered using cluster analysis method, and a working status classification method based on thermal image matrix eigenvalue matching is proposed; Each color area of ​​the thermal image is extracted separately to obtain data matrices of different colors. The norm and spectrum radius of the thermal image matrix of all different working states are solved, matching conditions are established, and iterative operations are performed to obtain the working status of the staff; The working status of staff members is divided into five categories: working, resting, busy, idle and abnormal; Statistics and analysis of the time taken by staff to complete tasks are performed based on task information, including: Collect historical data on tasks completed by workers; Conduct statistical analysis on the collected historical data and calculate the time it takes for each staff member to complete the task; The ARMA autoregressive moving average model algorithm is used as the time series analysis and prediction algorithm to model the time taken by each staff member to complete the task, establish a time series prediction model, and calculate the model parameters; Based on the established time series prediction model, the time required for each worker to complete the task in the next task is predicted.

2. According to the method of intelligent personnel scheduling based on big data in claim 1, it is characterized in that: The real-time status data and the task information are cleaned and preprocessed, including: data deduplication, missing value processing, outlier processing, data format unification, data conversion and data merging processing.

3. According to the big data-based intelligent personnel scheduling method of claim 1, it is characterized in that: Feedback and adjustment of staff task arrangements are performed through the intelligent scheduling model, including: Reassign tasks, adjust task priorities, or provide additional support or resources to staff through intelligent scheduling models; And send adjustment notifications to managers in a timely manner.

4. A personnel intelligent scheduling system based on big data, applying a personnel intelligent scheduling method based on big data as described in any one of claims 1 to 3, characterized in that: include: The collection module is used to collect the real-time status data and task information of the staff; A preprocessing module, used for cleaning and preprocessing the real-time status data and the task information; The model building and analysis module is used to build an intelligent scheduling model, analyze the pre-processed real-time status data, identify the working status of the staff, analyze and predict the time it takes for the staff to complete the task based on the task information, and automatically adjust the staff allocation and task arrangement; The feedback adjustment module is used to monitor the real-time status data and task execution status of the staff and set a threshold. When the real-time status data is greater than the threshold, the staff task arrangement is fed back and adjusted through the intelligent scheduling model.

Images