Personnel scheduling method and device, electronic equipment and storage medium

Abstract

The invention provides a personnel scheduling method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining data of to-be-scheduled personnel and a scheduling demand; performing data analysis on the data of the to-be-scheduled personnel and the scheduling demand to obtain a matching score of the to-be-scheduled personnel; determining a personnel scheduling table based on the matching score and a personnel scheduling model; the personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm. According to the method provided by the invention, data analysis is carried out on the data of the to-be-scheduled personnel and the scheduling demand, so that the matching score of the to-be-scheduled personnel is obtained; based on the matching score and the personnel scheduling model, the personnel scheduling table is determined, efficient and reasonable personnel scheduling is achieved, large-scale and complex personnel scheduling can be dealt with, and support with deep internal logic is provided.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a personnel scheduling method, device, electronic equipment and storage medium. Background Art

[0002] Due to the diversity of hospital departments, the abilities of trainees vary greatly. Reasonable scheduling of trainees is the basic guarantee for the normal operation of departments. Currently, staff scheduling is usually based on manual work, and the common practice is to use Excel tables for manual scheduling.

[0003] However, manual scheduling is time-consuming and labor-intensive, and is prone to human errors, resulting in inefficient scheduling and making it difficult to cope with large-scale personnel scheduling needs that require deep internal logic support. Summary of the invention

[0004] The present invention provides a personnel scheduling method, device, electronic device and storage medium, which are used to solve the defect that it is difficult to realize large-scale scheduling with deep internal logic support in the prior art.

[0005] The present invention provides a personnel scheduling method, comprising: Obtain data on personnel to be scheduled and scheduling requirements; Performing data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain matching scores of the personnel to be scheduled; Determining a personnel schedule based on the matching score and the personnel scheduling model; The personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm.

[0006] According to a personnel scheduling method provided by the present invention, the data of the personnel to be scheduled and the scheduling requirements are analyzed to obtain a matching score of the personnel to be scheduled, including: Performing data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain data analysis results; the data analysis results include at least one of personal characteristics, historical performance, and department demand matching degree; Based on the data analysis result, a matching score of the personnel to be scheduled is determined; the matching score corresponds to the data analysis result one by one.

[0007] According to a personnel scheduling method provided by the present invention, determining a personnel scheduling table based on the matching score and the personnel scheduling model includes: Determining an initial personnel schedule based on the matching score and the personnel scheduling model; A user input is received, and the initial staff schedule is adjusted based on the user input to obtain the staff schedule.

[0008] According to a personnel scheduling method provided by the present invention, determining an initial personnel scheduling table based on the matching score and the personnel scheduling model includes: The matching score is input into the personnel scheduling model to combine the personnel to be scheduled using a Bayesian algorithm to obtain the initial personnel scheduling table.

[0009] According to a personnel scheduling method provided by the present invention, the training steps of the personnel scheduling model include: Obtaining the sample scheduling personnel data and the sample scheduling requirements; Performing data analysis on the sample scheduling personnel data and the sample scheduling requirements to obtain a sample matching score of the sample scheduling personnel; Determine a sample schedule based on the sample matching score and the initial staff scheduling model; Determining a scheduling gap based on the sample schedule and the target optimization function; The initial personnel scheduling model is iterated based on the scheduling gap to obtain the personnel scheduling model.

[0010] According to a personnel scheduling method provided by the present invention, the initial personnel scheduling model is iterated based on the scheduling gap to obtain the personnel scheduling model, including: With the goal of reducing the scheduling gap, or when the number of iterations reaches a preset number, the initial personnel scheduling model is iterated to obtain the personnel scheduling model.

[0011] The present invention also provides a personnel scheduling device, comprising: Acquisition unit, obtains data of personnel to be scheduled and scheduling requirements; An analysis unit performs data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain a matching score of the personnel to be scheduled; A scheduling unit, which determines a personnel schedule based on the matching score and a personnel scheduling model; The personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the personnel scheduling methods described above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the personnel scheduling method described in any one of the above methods is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the personnel scheduling method described above is implemented.

[0015] The personnel scheduling method, device, electronic device and storage medium provided by the present invention perform data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain the matching scores of the personnel to be scheduled; based on the matching scores and the personnel scheduling model, the personnel scheduling table is determined, and efficient and reasonable personnel arrangement is achieved, which can cope with large-scale and complex personnel scheduling and provide support with deep internal logic. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the personnel scheduling method provided by the present invention; Figure 2 is a flow chart of a method for determining a matching score provided by the present invention; Figure 3 It is a schematic diagram of the training process of the personnel scheduling model provided by the present invention; Figure 4 It is a structural schematic diagram of the personnel scheduling system provided by the present invention; Figure 5 It is a structural schematic diagram of the personnel scheduling device provided by the present invention; Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0019] In view of the above problems, the present invention provides a personnel scheduling method to achieve efficient and reasonable personnel scheduling in large-scale and complex personnel scheduling scenarios. Figure 1 It is a flow chart of the personnel scheduling method provided by the present invention, such as Figure 1 As shown, the method includes: Step 110, obtaining data of personnel to be scheduled and scheduling requirements; Here, the data of personnel to be scheduled can be used to reflect the personal characteristics, historical performance, scheduling rules and other information of the personnel to be scheduled. Among them, personal characteristics can include information such as major, major ranking, age, working hours, number of trainees in each batch, etc.; historical performance can include historical scheduling information, rewards and penalties received for historical scheduling, etc. In addition, the scheduling needs here can reflect the current needs of each department in terms of personnel, majors, etc.

[0020] Specifically, data can be read from the original form through a data parsing algorithm to obtain the data of personnel to be scheduled and the scheduling requirements. The original form here can include previous forms and new personnel forms.

[0021] Step 120, performing data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain matching scores of the personnel to be scheduled; Here, the matching score of the person to be scheduled can be used to reflect the matching degree between the person to be scheduled and the department. When the matching score is higher, it means that the matching degree between the person to be scheduled and the department is higher; conversely, it means that the matching degree between the person to be scheduled and the department is lower.

[0022] Specifically, data analysis tools can be used to analyze the data of the personnel to be scheduled and the needs of departments, assign values ​​and divide the personnel to be scheduled into pools, and obtain matching scores between the personnel to be scheduled and each department, providing support for personalized scheduling.

[0023] It should be noted that, compared with the automated scheduling tools in the prior art, which are usually based on fixed formulas or simple adaptive models, they fail to fully consider the actual needs of various departments in the hospital and the differences in personnel qualifications. This simple model cannot meet the diverse and dynamically changing clinical needs of the hospital, such as temporary changes in departmental needs or sudden transfers of personnel. The method provided in the embodiment of the present invention performs data analysis on the data of the personnel to be scheduled and the scheduling needs to obtain the matching scores of the personnel to be scheduled, analyzes complex data, and learns from past scheduling experience to obtain the matching scores of the personnel to be scheduled and the departments, fully considering the actual needs of various departments in the hospital and the differences in personnel qualifications, and then can achieve a reasonable combination in the subsequent personnel scheduling to meet the needs of each department and realize the rational use of personnel, and personalized and intelligent scheduling for different trainees' abilities and specialties can improve the learning efficiency of trainees and realize scheduling with deep internal logic support.

[0024] Step 130, determining a personnel schedule based on the matching score and the personnel scheduling model; The personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm.

[0025] Here, the initial staff scheduling model is constructed based on a machine learning algorithm. The staff scheduling model here can be obtained by training the initial staff scheduling model based on sample scheduling personnel data and sample scheduling requirements.

[0026] Specifically, the matching scores between the personnel to be scheduled and each department can be input into the personnel scheduling model, and the personnel to be scheduled can be arranged and combined through the personnel scheduling model to determine the personnel corresponding to each department and obtain the personnel scheduling table. It should be noted that the automated personnel scheduling through the personnel scheduling model can cope with the personnel scheduling in large-scale personnel scheduling scenarios.

[0027] The method provided in the embodiment of the present invention obtains the matching scores of the personnel to be scheduled by performing data analysis on the data of the personnel to be scheduled and the scheduling requirements; based on the matching scores and the personnel scheduling model, the personnel schedule is determined, thereby achieving efficient and reasonable personnel arrangement, being able to cope with large-scale and complex personnel scheduling and providing support with deep internal logic.

[0028] Based on any of the above embodiments, Figure 2 is a flow chart of the method for determining a matching score provided by the present invention, such as Figure 2 As shown, the method includes: Step 210, performing data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain data analysis results; the data analysis results include at least one of personal characteristics, historical performance, and department demand matching degree; Step 220: Determine the matching score of the personnel to be scheduled based on the data analysis result; the matching score corresponds to the data analysis result one by one.

[0029] The data analysis results here can be at least one of personal characteristics, historical performance, and department demand matching. The data analysis results here can be expressed in the form of total results of various types of data analysis, or can be expressed in more detailed data analysis results corresponding to personal characteristics, historical performance, and department demand matching. In addition, the data analysis results correspond to the matching scores one-to-one. For example, the personal characteristics of the person to be scheduled correspond one-to-one with the matching score between the person to be scheduled and any department. Alternatively, the major in the personal characteristics of the person to be scheduled corresponds one-to-one with the matching score between the person to be scheduled and any department.

[0030] Specifically, the data of the personnel to be scheduled and the scheduling requirements can be input into the data analysis tool, and the data analysis tool can be used to deeply mine the data, identify potential scheduling rules and trends, and obtain data analysis results. Then, based on the data analysis results, the matching scores between the personnel to be scheduled and each department are determined. For example, the major of the person to be scheduled is internal medicine, and Department A is surgery. The data analysis result of the personal characteristics of the person to be scheduled is that the matching degree is not high, and the matching score between the person to be scheduled and Department A can be 2, indicating that the matching score is low.

[0031] In one embodiment, the data of personnel to be scheduled may include previous scheduling data and current typeset personnel data. First, the previous scheduling data may be identified to obtain previous scheduling information. The previous scheduling information is analyzed to obtain the rotation logic and rules in the previous scheduling, and the logical rules obtained by the analysis are used as initialization rules. Next, data analysis may be performed on the current typeset personnel data to obtain data analysis results such as the trainee's years of service, professional background, and learning needs. Then, the matching score of the personnel to be scheduled may be determined based on each data analysis result.

[0032] It should be noted that by analyzing the complex data of personnel to be scheduled and scheduling needs, we can obtain matching scores that correspond one to one with the data analysis results, achieve detailed data analysis, and obtain detailed and accurate matching scores, so that the candidate schedules are more in line with the characteristics of the personnel to be scheduled and the needs of each department, meet the special needs of each department in different time periods, and improve the effectiveness of the personnel schedule.

[0033] Based on any of the above embodiments, determining a personnel schedule based on the matching score and the personnel schedule model includes: Determining an initial personnel schedule based on the matching score and the personnel scheduling model; A user input is received, and the initial staff schedule is adjusted based on the user input to obtain the staff schedule.

[0034] Specifically, after the initial staff schedule is determined by matching the score and the staff scheduling model, the initial staff schedule can be displayed. For example, an interactive user interface can be developed based on front-end technology to display the initial staff schedule. Then, real-time adjustments to the initial staff schedule, i.e. user input, are received. For example, the user makes initialization rule adjustments, and the adjustable rules include scheduling frequency, shift type, allocation ratio, seniority weighting, professional weighting, etc. The initial staff schedule is adjusted according to the user input to obtain automatically generated and manually adjusted staff schedules. It should be noted that after the scheduling plan is determined, a file containing detailed scheduling information can be automatically generated, and a download option can be provided. The file includes detailed information such as the scheduling schedule and department allocation of each trainee to ensure the operability and practicality of the staff scheduling method.

[0035] It is understandable that the results of automatic scheduling are often difficult to meet complex clinical needs. The method provided by the embodiment of the present invention combines automatic staff scheduling with manual adjustment, allowing manual intervention and adjustment, especially fine adjustment of departments that require continuous rotation or special arrangements. This combination can ensure the rationality of scheduling while flexibly responding to emergencies in actual work, further improving the accuracy and practicality of staff scheduling.

[0036] Based on any of the above embodiments, determining an initial staff schedule based on the matching score and the staff schedule model includes: The matching score is input into the personnel scheduling model to combine the personnel to be scheduled using a Bayesian algorithm to obtain the initial personnel scheduling table.

[0037] Specifically, based on the matching scores between the personnel to be scheduled and each department, the Bayesian algorithm can be applied to perform small-scale arrangement of the personnel to be scheduled, generate possible scheduling combinations, and obtain the initial personnel schedule, thus realizing intelligent personnel scheduling and improving the scheduling efficiency of personnel scheduling, which is more suitable for scenarios of large-scale personnel scheduling.

[0038] Based on any of the above embodiments, Figure 3 It is a schematic diagram of the training process of the personnel scheduling model provided by the present invention, such as Figure 3 As shown, the method includes: Step 310, obtaining the sample scheduling personnel data and the sample scheduling requirements; Step 320, performing data analysis on the sample scheduling personnel data and the sample scheduling requirements to obtain a sample matching score of the sample scheduling personnel; Step 330, determining a sample schedule based on the sample matching score and the initial staff scheduling model; Step 340, determining the scheduling gap based on the sample schedule and the target optimization function; Step 350: iterate the initial staff scheduling model based on the scheduling gap to obtain the staff scheduling model.

[0039] Specifically, firstly, sample shift personnel data and the sample shift requirements may be obtained from the historical shift schedule.

[0040] It should be noted that the personnel schedule currently output by the personnel scheduling model can be used as sample data for subsequent model optimization, so as to realize continuous optimization of the personnel scheduling model based on actual data in a dynamic environment, making the personnel scheduling model more adaptable, thereby improving the practicality of the personnel scheduling model.

[0041] Next, based on the data analysis tool, the sample scheduling personnel data and the sample scheduling requirements can be analyzed to obtain the sample matching score of the sample scheduling personnel. Then, the sample matching score can be input into the initial personnel scheduling model, and the sample scheduling table can be output through the initial personnel scheduling model. For example, the scheduling rule information is extracted from the sample scheduling personnel data and the sample scheduling requirements, and the sample scheduling personnel are arranged in a random direction according to the scheduling rules, and the arrangement results are placed in the result pool to obtain the sample scheduling table. Further, the target optimization function can be constructed based on indicators such as personnel balance and department demand satisfaction rate, so as to calculate the gap between each sample scheduling table and the set target based on the target function, which is recorded as the scheduling gap. Here, the target function can be constructed based on the optimization target. The optimization target can include project indicators that affect the actual operation of the hospital, such as the work intensity of the personnel, the continuity of the rotation, the balance of the department allocation, the balance of the scheduling time distribution, the tendency of the busy department, and the like, and initialize the weighting of each indicator, and calculate the target score based on this weighting as the calculation result of the target function.

[0042] During the training phase, the scheduling strategy can be adjusted continuously with the goal of narrowing the scheduling gap, so that it gradually approaches the optimal solution. The initial staff scheduling model can be optimized, that is, the parameters of the Bayesian algorithm can be optimized to obtain a staff scheduling model that meets the requirements. For example, the sample schedule is calculated according to the score of the target pool to obtain the target score of the sample schedule, which is recorded as the initial score. Continue to the next round of training, and according to the forward direction of the rule vector training formed by the rule pool, if the second round score is better than the first round, the second round result is used. Continue to train in this direction until a better target score cannot be given; otherwise, adjust the direction and continue training. The above training stops when the following situations occur: the maximum training depth set manually is reached; the manually set target score is reached; or the global optimal schedule is reached.

[0043] The method provided by the embodiment of the present invention significantly optimizes the scheduling of trainees in the hospital through intelligent learning and optimization strategies, which not only improves the scheduling efficiency and reduces the errors of manual operation, but also ensures the rationality and continuity of the distribution of personnel in each department. It greatly promotes the clinical work of teaching hospitals and the learning progress of trainees, and truly realizes scientific, reasonable and efficient scheduling management.

[0044] Based on any of the above embodiments, the initial staff scheduling model is iterated based on the scheduling gap to obtain the staff scheduling model, including: With the goal of reducing the scheduling gap, or when the number of iterations reaches a preset number, the initial personnel scheduling model is iterated to obtain the personnel scheduling model.

[0045] Specifically, during the training process of the initial staff scheduling model, the staff scheduling model is trained with the goal of reducing the scheduling gap, or the number of iterations reaches a preset number of times. The preset number of times here can be determined according to the actual training situation, for example, it can be 50 times or 100 times, and the present invention does not make specific limitations on this.

[0046] Based on any of the above embodiments, Figure 4 It is a structural diagram of the personnel scheduling system provided by the present invention. Figure 4 As shown, the system includes: a document reading module, an information processing module, a display and operation module, and a training module.

[0047] Among them, the document reading module is used to interpret and capture the information data of previous regular training trainees and new trainees. Then the information data is transmitted to the information processing module, and the information data is analyzed, that is, the personnel to be scheduled are assigned values ​​and divided into pools to obtain the matching scores between each person and each department. Then, based on the matching scores and the Bayesian algorithm, the personnel are combined to obtain the initial personnel schedule. The initial personnel schedule is then transmitted to the display and operation module.

[0048] The display and operation module is used to provide an interactive interface for users to adjust and optimize data. By receiving the user's adjustments, the final personnel schedule is obtained. Finally, the personnel schedule is downloaded based on the download module.

[0049] In the subsequent use process, the scheduling system will also provide an interactive module to record the department's evaluation of a student's learning ability and work ability, and record the student's evaluation of the department's teaching ability, work intensity, satisfaction, etc. The results will be stored in the storage module, and the analysis module will regularly analyze the rationality of the evaluation scores of both parties. If an unreasonable match occurs, the administrator will be reminded to make dynamic adjustments. It is necessary to explain that the specific evaluations of both parties will generate new rules, be included in the rule pool, and the management will conduct new training to continuously optimize the scheduling under the real environment of the students and departments.

[0050] It should also be noted that, in the system, dynamic sample data is obtained based on the dynamically generated personnel schedule, and the personnel scheduling model is continuously trained until the set target distance or the manually set maximum depth is reached, the best result is extracted, and it is passed to the display module and the manual operation module for adjustment.

[0051] Based on any of the above embodiments, Figure 5 Schematic diagram of the structure of the personnel scheduling device provided by the present invention. Figure 5 As shown, the device comprises: An acquisition unit 510 acquires data of personnel to be scheduled and scheduling requirements; An analysis unit 520 performs data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain a matching score of the personnel to be scheduled; A scheduling unit 550 determines a personnel schedule based on the matching score and the personnel scheduling model; The personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm.

[0052] The device provided in the embodiment of the present invention obtains the matching scores of the personnel to be scheduled by performing data analysis on the data of the personnel to be scheduled and the scheduling requirements; based on the matching scores and the personnel scheduling model, the personnel scheduling table is determined, thereby achieving efficient and reasonable personnel arrangement, being able to cope with large-scale and complex personnel scheduling and providing support with deep internal logic.

[0053] Based on any of the above embodiments, the analysis unit is specifically used for: Performing data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain data analysis results; the data analysis results include at least one of personal characteristics, historical performance, and department demand matching degree; Based on the data analysis result, a matching score of the personnel to be scheduled is determined; the matching score corresponds to the data analysis result one by one.

[0054] Based on any of the above embodiments, the scheduling unit is specifically used for: Determining an initial personnel schedule based on the matching score and the personnel scheduling model; A user input is received, and the initial staff schedule is adjusted based on the user input to obtain the staff schedule.

[0055] Based on any of the above embodiments, the scheduling unit is further specifically used for: The matching score is input into the personnel scheduling model to combine the personnel to be scheduled using a Bayesian algorithm to obtain the initial personnel scheduling table.

[0056] Based on any of the above embodiments, the device further includes a training unit, and the training unit is specifically used for: Obtaining the sample scheduling personnel data and the sample scheduling requirements; Performing data analysis on the sample scheduling personnel data and the sample scheduling requirements to obtain a sample matching score of the sample scheduling personnel; Determine a sample schedule based on the sample matching score and the initial staff scheduling model; Determining a scheduling gap based on the sample schedule and the target optimization function; The initial personnel scheduling model is iterated based on the scheduling gap to obtain the personnel scheduling model.

[0057] Based on any of the above embodiments, the training unit is further specifically used for: With the goal of reducing the scheduling gap, or when the number of iterations reaches a preset number, the initial personnel scheduling model is iterated to obtain the personnel scheduling model.

[0058] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 660, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 660. The processor 610 may call the logic instructions in the memory 630 to execute the personnel scheduling method, which includes: obtaining the data of personnel to be scheduled and the scheduling requirements; performing data analysis on the data of personnel to be scheduled and the scheduling requirements to obtain the matching scores of the personnel to be scheduled; determining the personnel scheduling table based on the matching scores and the personnel scheduling model; the personnel scheduling model is obtained by training the initial personnel scheduling model based on the sample scheduling personnel data and the sample scheduling requirements; the initial personnel scheduling model is constructed based on the machine learning algorithm.

[0059] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0060] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the personnel scheduling method provided by the above methods, which method includes: obtaining the data of personnel to be scheduled and the scheduling requirements; performing data analysis on the data of personnel to be scheduled and the scheduling requirements to obtain matching scores of the personnel to be scheduled; determining a personnel scheduling table based on the matching scores and a personnel scheduling model; the personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm.

[0061] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the personnel scheduling method provided by the above-mentioned methods, the method comprising: obtaining data of personnel to be scheduled and scheduling requirements; performing data analysis on the data of personnel to be scheduled and the scheduling requirements to obtain matching scores of the personnel to be scheduled; determining a personnel scheduling table based on the matching scores and a personnel scheduling model; the personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm.

[0062] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0063] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A personnel scheduling method, characterized in that: include: Obtain data on personnel to be scheduled and scheduling requirements; Performing data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain matching scores of the personnel to be scheduled; Determining a personnel schedule based on the matching score and the personnel scheduling model; The personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm.

2. The personnel scheduling method according to claim 1, characterized in that: The data analysis of the personnel to be scheduled and the scheduling requirements is performed to obtain a matching score of the personnel to be scheduled, including: Performing data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain data analysis results; the data analysis results include at least one of personal characteristics, historical performance, and department demand matching degree; Based on the data analysis result, a matching score of the personnel to be scheduled is determined; the matching score corresponds to the data analysis result one by one.

3. The personnel scheduling method according to claim 1, characterized in that: The determining of the personnel schedule based on the matching score and the personnel schedule model includes: Determining an initial personnel schedule based on the matching score and the personnel scheduling model; A user input is received, and the initial staff schedule is adjusted based on the user input to obtain the staff schedule.

4. The personnel scheduling method according to claim 3, characterized in that: The determining of an initial personnel schedule based on the matching score and the personnel schedule model includes: The matching score is input into the personnel scheduling model to combine the personnel to be scheduled using a Bayesian algorithm to obtain the initial personnel scheduling table.

5. The personnel scheduling method according to any one of claims 1 to 4, characterized in that: The training steps of the personnel scheduling model include: Obtaining the sample scheduling personnel data and the sample scheduling requirements; Performing data analysis on the sample scheduling personnel data and the sample scheduling requirements to obtain a sample matching score of the sample scheduling personnel; Determine a sample schedule based on the sample matching score and the initial staff scheduling model; Determining a scheduling gap based on the sample schedule and the target optimization function; The initial personnel scheduling model is iterated based on the scheduling gap to obtain the personnel scheduling model.

6. The personnel scheduling method according to claim 5, characterized in that: The iterating the initial staff scheduling model based on the scheduling gap to obtain the staff scheduling model includes: With the goal of reducing the scheduling gap, or when the number of iterations reaches a preset number, the initial personnel scheduling model is iterated to obtain the personnel scheduling model.

7. A personnel scheduling device, characterized in that: include: Acquisition unit, obtains data of personnel to be scheduled and scheduling requirements; An analysis unit performs data analysis on the data of the personnel to be scheduled and the scheduling requirements to obtain a matching score of the personnel to be scheduled; A scheduling unit, which determines a personnel schedule based on the matching score and a personnel scheduling model; The personnel scheduling model is obtained by training an initial personnel scheduling model based on sample scheduling personnel data and sample scheduling requirements; the initial personnel scheduling model is constructed based on a machine learning algorithm.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the personnel scheduling method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the personnel scheduling method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the personnel scheduling method according to any one of claims 1 to 6 is implemented.

Images