Digital intelligence employee data management system, method and device and storage medium

Abstract

The invention provides a digital intelligent employee data management system, method and device and a storage medium, in the system, a scheduling module is configured to obtain working hour arrangement information and holiday application information from a plurality of employee terminals and corrected attendance data in a current attendance period, and determine a scheduling table; the attendance checking module is configured to obtain work card punching data in a current attendance checking period, and obtain access control data in the current attendance checking period from a plurality of access control sensing devices; based on the work card punching data and the access control data, determining corrected attendance data of at least one employee in the current attendance period; determining attendance data based on the corrected attendance data; and the display module is configured to display the attendance data and / or the scheduling table. According to the system, the card punching data of employees are automatically corrected by utilizing the card punching data and the access control data, so that the accuracy of the attendance data is ensured; and meanwhile, the automation degree is improved, and errors possibly caused by manual operation are reduced.

Description

Technical Field

[0001] This specification relates to the field of office automation, and in particular to a digital employee data management system, method, device and storage medium. Background Art

[0002] In modern enterprise management, the attendance system collects a wide variety of raw attendance data. There are technical problems with poor intelligent performance in the current system for the huge amount of raw attendance data in various formats and abnormal situations such as leave and card replacement in the raw attendance data.

[0003] Therefore, how to improve the degree of automation of employee management (such as attendance, scheduling, etc.) and reduce manual operation errors is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to reduce the workload of managers and operational errors caused by large amounts of data, this manual provides a digital employee data management system that can automatically generate and adjust scheduling data, improve managers' management efficiency of working hours and attendance, and realize digital employee management.

[0005] One of the embodiments of the present specification provides a digital employee data management system, including a scheduling module, an attendance module, and a display module; the scheduling module, the attendance module, and the display module are configured on employee terminals and / or administrator terminals; the scheduling module is configured to: obtain work schedule information and holiday application information from multiple employee terminals, and obtain corrected attendance data within the current attendance cycle from at least one employee terminal; determine a schedule based on the work schedule information, holiday application information, and corrected attendance data, and distribute the schedule to multiple employee terminals; the attendance module is configured to: obtain work clock-in data within the current attendance cycle from multiple employee terminals, and obtain access control data within the current attendance cycle from multiple access control sensor devices; determine the corrected attendance data of at least one employee within the current attendance cycle based on the work clock-in data and access control data within the current attendance cycle; determine the attendance data based on the corrected attendance data of multiple employees within the current attendance cycle; the display module is configured to: display the attendance data and / or the scheduling table.

[0006] One of the embodiments of the present specification also provides a digital employee data management method, which is executed by a processor, including: obtaining work schedule information and holiday application information, and obtaining corrected attendance data within at least one current attendance cycle; determining a shift schedule based on the work schedule information, holiday application information and corrected attendance data, and distributing the shift schedule to multiple employee terminals; obtaining work clock-in data within the current attendance cycle, and obtaining access control data within the current attendance cycle from multiple access control sensor devices; determining corrected attendance data of at least one employee within the current attendance cycle based on the work clock-in data and access control data within the current attendance cycle; determining attendance data based on the corrected attendance data of multiple employees within the current attendance cycle; and displaying attendance data and / or a shift schedule.

[0007] One of the embodiments of this specification also provides a digital employee data management device, including a processor, and the processor is used to execute the above-mentioned digital employee data management method.

[0008] One of the embodiments of the present specification also provides a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the above-mentioned digital employee data management method.

[0009] The beneficial effects of some embodiments provided in this specification include but are not limited to: the digital employee data management system can automatically correct the employee's punch-in data through the data generated by the employee's active punch-in, supplemented by the access control data, to ensure the accuracy of the attendance data; at the same time, by correcting the attendance data for automatic scheduling, the degree of automation is improved and the errors that may occur in manual operations are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein: Figure 1 is an exemplary module diagram of a digital employee data management system according to some embodiments of this specification; Figure 2 It is a schematic diagram of application scenarios of a digital employee data management system according to some embodiments of this specification; Figure 3 is an exemplary flow chart of obtaining attendance data according to the attendance module shown in some embodiments of this specification; Figure 4 It is an exemplary block diagram of a work-hour correction model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0011] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0012] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0013] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0014] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0015] In order to reduce the workload of managers and operational errors caused by large amounts of data, in some embodiments of this specification, a digital employee data management system is provided that can automatically generate and adjust scheduling data, and improve the efficiency of managers in managing working hours and attendance, thereby realizing digital employee management.

[0016] Figure 1 It is an exemplary module diagram of a digital employee data management system according to some embodiments of this specification.

[0017] In some embodiments, the digital employee data management system 100 may include a scheduling module 110, an attendance module 120, and a display module 130. For more information about the scheduling module 110, the attendance module 120, and the display module 130, please refer to the relevant description below.

[0018] In some embodiments, the digital employee data management system 100 may also include a business monitoring module 140 and a scheduling feedback module 150. For more information about the business monitoring module 140 and the scheduling feedback module 150, please refer to the relevant description below.

[0019] It should be understood that Figure 1 The digital employee data management system 100 and its modules shown can be implemented in various ways, for example, Figure 2 An application scenario shown in .

[0020] Figure 2 Schematic diagram of application scenarios of the digital employee data management system according to some embodiments of this specification. Figure 2 As shown, the application scenario may include an employee terminal 210, an administrator terminal 220, and an access control sensor device 230. In some embodiments, the employee terminal 210, the administrator terminal 220, and the access control sensor device 230 may be connected to each other through a network 240.

[0021] The employee terminal 210 is a terminal held or used by an employee, such as a mobile phone 210 - 1 or a tablet computer 210 - 2 . In some embodiments, an employee can access an office automation system (OA) or a database system through the employee terminal 210 to obtain data such as working hours and attendance.

[0022] In some embodiments, the employee terminal 210 may include an office terminal, which is a device used by employees to work within the enterprise. The office terminal may include, for example, a personal computer 210 - 3 .

[0023] The administrator terminal 220 is a terminal held or used by the administrator (such as a mobile phone 220-1). In some embodiments, the access rights or control rights of the administrator terminal 220 may be higher than those of the employee terminal 210, that is, the administrator terminal 220 may obtain part of the data in the employee terminal 210, push data to the employee terminal 210, or check the status of the employee terminal 210.

[0024] The access control sensor device 230 may include multiple access control sensor devices 230 located at different locations in the enterprise (such as the company gate, office area, conference room, specific passage), and the access control sensor device 230 may include a gate, a face recognition device, an electronic lock, etc. In some embodiments, the access control sensor device 230 may obtain the passing information of the person, such as the employee number and passing time corresponding to the passing person, etc. In some embodiments, the access control sensor device 230 may also obtain the direction of the person's passing (such as entering or leaving a certain area).

[0025] In some embodiments, the employee terminal 210 and the administrator terminal 220 may include a processor and a display, and the processor is configured to implement Figure 1 The display is configured to implement some or all of the functions of the scheduling module 110 and / or the attendance module 120. Figure 1 Part or all of the functions of the display module 130 are shown in FIG.

[0026] In some embodiments of this specification, a digital employee data management method is also provided. One or more steps in the method can be performed by Figure 2 The method is executed by the processor in the employee terminal 210 and / or the administrator terminal 220, and the method includes: obtaining work schedule information and holiday application information, and obtaining at least one corrected attendance data in the current attendance cycle; based on the work schedule information, holiday application information and corrected attendance data, determining a shift schedule, and distributing the shift schedule to multiple employee terminals 210; obtaining work clock-in data in the current attendance cycle, and obtaining access control data in the current attendance cycle from multiple access control sensor devices 230; based on the work clock-in data and access control data in the current attendance cycle, determining the corrected attendance data of at least one employee in the current attendance cycle; based on the corrected attendance data of multiple employees in the current attendance cycle, determining attendance data; and displaying attendance data and / or a shift schedule. For one or more steps of the digital employee data management method, please refer to the relevant descriptions of the scheduling module 110, the attendance module 120, and the display module 130 below.

[0027] In some embodiments, the scheduling module 110 in the digital employee data management system 100 is configured to: obtain work schedule information and holiday application information from multiple employee terminals 210, and obtain corrected attendance data within the current attendance cycle from at least one employee terminal 210; determine a schedule based on the work schedule information, holiday application information and corrected attendance data, and distribute the schedule to multiple employee terminals 210.

[0028] The work schedule information indicates whether the employee is busy or idle during the working time period. In some embodiments, the work schedule information includes scheduled working time periods and unscheduled working time periods. In some embodiments, the employee can fill in the work schedule information according to his or her own work schedule.

[0029] The vacation application information indicates whether the employee is taking leave now and in the future. In some embodiments, the vacation application information includes the vacation application time period and the application time. In some embodiments, the vacation application information can be automatically generated when the employee's leave application is approved, and the application time can be the time when the leave application is submitted for approval or the time when the leave application is approved.

[0030] In some embodiments, the attendance cycle may be a preset time length, such as one week or one month, etc. In some embodiments, a work project within an enterprise may correspond to one or more attendance cycles.

[0031] The modified attendance data represents the complete employee attendance information. In some embodiments, the modified attendance data may be processed data, such as data completion for vacancies caused by factors such as employees forgetting to punch in (the attendance of a certain day only includes the punch-in record for going to work or leaving get off work), vacation, etc. In some embodiments, the modified attendance data may be obtained by the administrator terminal 220 or through the working time correction model. For more information on obtaining the modified attendance data, please refer to the following description.

[0032] In some embodiments, the revised attendance data includes the name of the employee who attended, the attendance time, and the attendance type. The attendance time may include the actual time when the employee arrives or leaves the post, and the attendance type may be whether the current revised attendance data is arrival or departure.

[0033] The shift schedule represents the planning of the working time periods of one or more employees. In some embodiments, the shift schedule includes the working time periods of at least one employee's project to be scheduled. For example, the shift schedule may indicate that employee A is responsible for advancing project N all day from Tuesday to Thursday every week. In some embodiments, when determining the shift schedule, the corrected attendance data in the current attendance cycle is obtained from the terminals of multiple employees (such as 3 employees), and then the working time periods of the projects to be scheduled corresponding to the multiple employees (i.e., 3 employees) are generated accordingly.

[0034] In some embodiments, the scheduling module 110 may match the acquired multiple work schedule information, holiday application information, and the corrected attendance data of at least one employee with the historical data, use the schedule corresponding to the matched historical data as a new schedule, and distribute it to multiple employee terminals 210. In some embodiments, the matching method may be to select the historical data with the highest similarity to the multiple work schedule information, holiday application information, and the corrected attendance data of at least one employee as the matching data.

[0035] Historical data may be obtained manually (such as by an administrator) based on historical shift scheduling. In some embodiments, historical data may include a shift schedule that is more reasonable and labor-efficient among the work projects that have been completed in the company's history, as well as historical working hours arrangement information, historical holiday application information, and historical corrected attendance data for multiple employees corresponding to the shift schedule.

[0036] In some embodiments, after the employee terminal 210 receives the work schedule, the employee can subsequently work according to the plan in the work schedule.

[0037] Figure 3is an exemplary flow chart of the attendance module 120 acquiring attendance data according to some embodiments of this specification.

[0038] In some embodiments, the attendance module 120 in the digital employee data management system 100 is configured to perform one or more steps in the process 300. The process 300 includes: Step 310, obtaining work clock-in data in the current attendance cycle from multiple employee terminals, and obtaining access control data in the current attendance cycle from multiple access control sensor devices.

[0039] The work punch-in data is the attendance information actively generated when the employee punches in through the employee terminal 210 or other punch-in device. In some embodiments, the work punch-in data may include the name of the employee who is present, the punch-in time, and the punch-in type, where the punch-in type refers to whether the punch-in is for work or for leaving work. In some embodiments, the work punch-in data may be automatically generated and stored in the employee terminal 210 when the employee terminal 210 or other punch-in device performs a punch-in operation.

[0040] For example, assuming that the current attendance cycle is 5 working days, the work clock-in data of employee A in the current attendance cycle may be: ((Employee A, 9:00, clocks in), (Employee A, 17:00, clocks out)), ((Employee A, 9:10, clocks in), (Employee A, 17:00, clocks out)), ((Employee A, 8:50, clocks in), (empty, empty, empty)), ((Employee A, 9:00, clocks in), (Employee A, 17:00, clocks out)), ((Employee A, 9:05, clocks in), (Employee A, 17:00, clocks out))). It can be seen from the work clock-in data that employee A may have forgotten to clock in or left early when leaving get off work on Wednesday.

[0041] The access control data is attendance information passively generated when an employee passes through the access control sensor device 230. In some embodiments, the access control data may include the name of the employee entering or leaving, the recording time, and the type of collection device. The type of collection device may include the location (or venue) of the corresponding access control sensor device 230 and whether the employee is leaving or entering.

[0042] Continuing with the above example, assuming that the access control sensor device 230 is a gate at the company's main gate, the access control data may include, in addition to the data of employee A entering and leaving the company on weekdays, also the data corresponding to employee A leaving the gate at the company's main gate (i.e., exiting) on ​​Wednesday afternoon, which may be (employee A, 17:05, gate gate-exit), and this data can prove that employee A indeed forgot to punch in when he got off work on Wednesday, rather than leaving early or being absent from work.

[0043] Step 320: Determine the corrected attendance data of at least one employee in the current attendance cycle based on the work clock-in data and access control data in the current attendance cycle.

[0044] As mentioned above, the corrected attendance data is the employee attendance information with complete information, including the name of the employee who attended, the attendance time and the attendance type. In some embodiments, for any employee, if there is no missing punch-in data for a certain day in the employee's work punch-in data, the corrected attendance data can be directly calculated based on the work punch-in data. If there is a missing punch-in data in the employee's work punch-in data, the date corresponding to the missing data of the employee's punch-in data can be counted, and for each date of missing data, the punch-in type of the missing data is determined, and the access control data within the preset time period is selected from the access control data that meets the requirements, so as to supplement the work punch-in data as auxiliary data, and then calculate the corrected attendance data. The access control data that meets the requirements can be the access control sensor device 230 that can reflect the employee's commuting activities, such as the gate at the company entrance, the entrance and exit of the parking lot, etc. The preset time period is the time period that meets the characteristics of the commuting time to prove that the employee is off work normally instead of being late, leaving early, absent, etc. The access control data and preset time period that meet the requirements can be determined according to the actual situation and rules and regulations of the company.

[0045] Continuing with the above example, the access control data (employee A, 17:05, gate machine - exit) can prove that employee A did not leave early, so he indeed forgot to punch in when leaving get off work on Wednesday. The recorded time in the access control data can be used as the punch-in time for correcting the attendance data, and the punch-in type can be counted as clocking in for leaving get off work to supplement employee A's work punch-in data, and then calculate employee A's corrected attendance data.

[0046] Step 330 , determining attendance data based on the corrected attendance data of multiple employees in the current attendance cycle.

[0047] The attendance data includes the attendance status of multiple employees in the current attendance cycle. In some embodiments, the attendance module 120 can obtain the corrected attendance data of multiple employees in the current attendance cycle by repeating steps 310-320, and count the multiple corrected attendance data to determine the number of absences, lateness and early departures, overtime hours, and attendance times corresponding to each employee to obtain the attendance data.

[0048] In some embodiments, after determining the revised attendance data, the attendance module 120 can also count the number of times each employee forgets to punch in, the total duration of absence, the length of overtime, etc. according to the company's penalty rules, and generate performance adjustment values, overtime subsidies or penalty amounts, etc. according to relevant rules or systems. The relevant rules or systems can be pre-stored in the digital employee data management system. The attendance module 120 can generate performance adjustment values, overtime subsidies or penalty amounts, etc. based on the revised attendance data and relevant rules or systems by running the code program.

[0049] In some embodiments, the attendance module 120 may send one or more of work clock-in data, access control data, work schedule information, holiday application information, and attendance data to the manager terminal.

[0050] It should be noted that the above description of the process 300 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 300 under the guidance of this specification.

[0051] In some embodiments, in some embodiments, the display module 130 in the digital employee data management system 100 is configured to display attendance data and / or a shift schedule. In some embodiments, the display of the employee terminal 210 can implement the function of the display module 130 to display the shift schedule, and the display of the manager terminal can implement the function of the display module 130 to display the attendance data. In some embodiments, the display module 130 can also be implemented by a company large screen to display the attendance data and / or the shift schedule for all employees to view.

[0052] The digital employee data management system 100 uses the data generated by employees' active clocking in, supplemented by access control data, to automatically correct employees' clocking in data and ensure the accuracy of attendance data. At the same time, it improves the degree of automation by automatically scheduling shifts through correcting attendance data, reducing errors that may occur in manual operations.

[0053] As mentioned above, the employee terminal 210 includes an office terminal, and the digital employee data management system 100 also includes a business monitoring module 140. In some embodiments, the business monitoring module is configured to obtain business operation data from multiple office terminals.

[0054] Business operation data refers to the operation status of the business associated with the company. In some embodiments, the business operation data includes at least one of order data and equipment data. The order data at least includes new orders and their corresponding order output values. The equipment data includes at least one production equipment and its equipment status. The production equipment varies according to the company's business and is not limited in this specification.

[0055] Business operation data can be one or more types of data submitted by employees to the business monitoring module through office terminals. For example, when a new order is added to the production schedule, the employee submits the order data; for example, specific employees can monitor the production equipment within the company and submit equipment data regularly or when the status of the production equipment changes.

[0056] Accordingly, the scheduling module 110 is further configured to update the schedule based on the work schedule information, the holiday application information and the revised attendance data in response to the business operation data satisfying the update condition.

[0057] Meeting the update condition indicates that the schedule may need to be updated to adapt to new production needs. In some embodiments, the update condition may be that the total order output value of all new orders is greater than a preset output value, and / or the number of devices with abnormal equipment status is greater than a preset threshold. The preset output value and preset threshold can be determined according to actual production needs and the company's business type (such as by manual designation), and are not limited in this specification.

[0058] When the business operation data meets the update conditions, the schedule can be updated based on the work schedule information, holiday application information and modified attendance data in the manner described in the scheduling module 110 above, which will not be repeated here. In some embodiments, the updated schedule can be distributed to multiple employee terminals 210 again.

[0059] Timely updating of the shift schedule when conditions are met can provide flexible scheduling and working time management, adapt to different employee and production needs, and improve the ability to respond to emergencies.

[0060] In order to obtain a schedule that is more suitable for employees, in some embodiments, the scheduling module 110 is further configured to: obtain scheduling demand data from the scheduling feedback module; determine multiple candidate schedules based on the scheduling demand data; determine the scheduling push probability value corresponding to each candidate schedule based on multiple candidate schedules, employee scheduling intentions, at least one employee's revised attendance data, work schedule information and holiday application information through a satisfaction value prediction model, and finally select the candidate schedule corresponding to the maximum scheduling push probability value from the multiple scheduling push probability values ​​as the updated schedule.

[0061] The scheduling demand data is the work demand of multiple employees for the current project. The scheduling demand data can be determined by employees or administrators based on actual conditions, and collected and sent to the scheduling module 110 through the scheduling feedback module. In some embodiments, the function of the scheduling feedback module can be implemented through the employee terminal 210 or the administrator terminal 220.

[0062] Employee scheduling willingness indicates the employee's scheduling willingness value in at least one time period. The higher the willingness value, the more the employee wants to work in the corresponding time period. Assuming the willingness value is 1-10, the employee can set 9:00-10:00 to 2, indicating that the time period may be in work preparation and does not want to be scheduled; set 13:00-17:00 to 9, indicating that the employee has a strong willingness to be scheduled in this time period.

[0063] In some embodiments, the employee's scheduling willingness is obtained based on a scheduling feedback module, and the employee can input a scheduling willingness value for at least one time period through the scheduling feedback module in the employee terminal 210 .

[0064] In some embodiments, the scheduling demand data includes the required working time period and the required number of workers corresponding to the project to be scheduled; the scheduling feedback module can be the project corresponding to the newly added order in the previous text or other projects that need to be promoted in the near future. The required working time period can be related to the project. For example, some projects can be promoted 8 hours a day, and the required working time period can be 9:00~17:00 every working day within 1 month. Some urgent projects require employees to work in shifts to promote them for 24 hours, and the required working time period can be 0:00~0:00 the next day every day within 1 week.

[0065] In some embodiments, the scheduling module 110 can select the number of employees corresponding to the required number of workers based on the scheduling demand data and combine the required working time period to randomly generate multiple candidate schedules. In some embodiments, the scheduling module 110 can randomly assign multiple employees to the required working time period, so that employees are assigned to all required working time periods of the scheduled project, and the number of assigned employees meets the required number of workers, to obtain a candidate schedule, and then the scheduling module 110 repeats the above steps multiple times to obtain multiple candidate schedules.

[0066] In some embodiments, the scheduling module 110 may utilize specific software (such as office automation software) or algorithms to implement random assignment of personnel and obtain multiple candidate schedules.

[0067] In some embodiments, the scheduling module 110 may input a plurality of candidate schedules, employee scheduling intentions, at least one employee's modified attendance data, work schedule information, and vacation application information into a satisfaction value prediction model, and the satisfaction value prediction model outputs a scheduling promotion probability value corresponding to each candidate schedule. In some embodiments, the satisfaction value prediction model may be a CNN (convolutional neural network), which may be trained by labeled training samples.

[0068] The higher the corresponding scheduling promotion probability value of the candidate schedule, the higher the success rate of the candidate schedule in promoting production. The success rate of promoting production reflects, on the one hand, the high possibility that the schedule can be promoted (that is, the expected employee attendance rate is high), and on the other hand, the high efficiency of production after the schedule is used.

[0069] In some embodiments, the satisfaction value prediction model can be obtained by training multiple labeled training samples. Specifically, multiple labeled training samples can be input into the satisfaction value prediction model, and a loss function can be constructed by using the labels and the results of the initial satisfaction value prediction model. The parameters of the initial satisfaction value prediction model are iteratively updated based on the loss function by gradient descent or other methods. When the preset conditions are met, the model training is completed and a trained satisfaction value prediction model is obtained. The preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0070] In some embodiments, the training sample includes a historical shift schedule and at least one sample employee shift schedule intention, sample revised attendance data, sample work time arrangement information, and sample vacation application letter corresponding to the historical shift schedule. In some embodiments, the historical shift schedule and the corresponding sample employee shift schedule intention, sample revised attendance data, sample work time arrangement information, and sample vacation application letter in the training sample can be obtained based on the historical shift schedule data and related data of completed projects in the company.

[0071] In some embodiments, the label corresponding to the training sample is the sample schedule push probability value corresponding to the historical schedule. In some embodiments, the sample schedule push probability value can be determined based on the leave rate and work completion rate of the actual production process corresponding to the historical schedule.

[0072] For example, if the historical shift schedule corresponds to the employee schedule for a week in a completed project, the ratio of the number of people who take leave in this week to the total number of people involved in the schedule can be counted to obtain the leave rate, and the percentage of the workload achieved in this week to the total workload of the completed project can be counted to obtain the work completion rate. Then, the sample shift push probability value corresponding to the historical shift schedule can be determined based on the average of the leave rate and the work completion rate.

[0073] In some embodiments, the sample shift push probability value corresponding to the historical shift table can be obtained by weighted average of the leave rate and the work completion rate to reflect the different emphasis on the leave rate or the work completion rate. In some embodiments, the weight can be preset based on manual experience.

[0074] In some embodiments, after determining the scheduling promotion probability value of each candidate schedule among multiple candidate schedules based on the satisfaction value prediction model, the scheduling module 110 can select the candidate schedule corresponding to the maximum scheduling promotion probability value from the multiple scheduling promotion probability values ​​as the updated schedule, and distribute it to multiple employee terminals 210.

[0075] Through the satisfaction value prediction model, multiple candidate schedules generated are evaluated from multiple dimensions, and then the optimal schedule is selected, which can greatly improve subsequent production efficiency and help improve the company's overall output value.

[0076] In some embodiments, when calculating the weighted average of the leave rate and the work completion rate in the above text, the corresponding weights may be related to the total employee productivity and the total project required productivity. The total employee productivity refers to the total amount of work completed by all employees in the past period of time (such as one month or half a year) (such as the total output value corresponding to the completed projects); the total project required productivity refers to the total amount of work of all pending projects of the current company.

[0077] In some embodiments, the difference between the total employee productivity and the total project required productivity can be calculated. If the difference is a positive number, it means that there is a surplus of manpower. At this time, the work completion rate is more important. Therefore, when calculating the sample scheduling promotion probability value, the larger the difference, the greater the weight corresponding to the relative work completion rate; if the difference is a negative number, it means that there is a shortage of manpower. At this time, it is more important for employees to be on the job. Therefore, when calculating the sample scheduling promotion probability value, the smaller the difference, the greater the weight corresponding to the relative leave rate.

[0078] By establishing a correlation between the weight of the scheduling push probability value and the total employee productivity and the total project demand productivity, the actual situation can be better considered when there is an imbalance between the company's manpower and orders, ensuring the rationality of the scheduling.

[0079] In some embodiments, the input of the satisfaction value prediction model may include at least one employee's production efficiency value in a future attendance cycle in addition to the multiple candidate shift schedules, employee shift willingness, at least one employee's revised attendance data, work schedule information, and vacation application information mentioned above. The production efficiency value of an employee in a future attendance cycle may be determined based on the production efficiency value of the employee in the employee's historical cycle. For example, the production efficiency value of the employee in the previous attendance cycle is directly used as the production efficiency value of the employee in the future attendance cycle. The production efficiency value of an employee in a historical cycle can be obtained based on the efficiency estimation submodel described later. For more information about the production efficiency value of an employee in a historical cycle and the efficiency estimation submodel, please refer to the relevant description below.

[0080] Correspondingly, when the input of the satisfaction value prediction model also includes the production efficiency value of at least one time period in a future attendance cycle of at least one employee, the training samples of the satisfaction value prediction model during the training process may also include sample production efficiency values ​​of at least one employee in a future attendance cycle corresponding to the historical schedule. For more information on the sample production efficiency values, please refer to the relevant description of the efficiency prediction sub-model in the following text.

[0081] By adding the production efficiency value of an employee in a future attendance cycle to the input of the satisfaction value prediction model, the production efficiency value of the employee (i.e., effective working time) can be considered when determining the scheduling push probability value of the candidate schedule, which is conducive to determining a schedule with a higher overall output value.

[0082] In some embodiments, in order to reasonably determine the attendance cycle, the scheduling module 110 is further configured to: in response to the scheduling push probability values ​​of multiple schedules in the current attendance cycle being less than a preset probability value, update the attendance cycle based on multiple production time efficiency values ​​in a past attendance cycle.

[0083] The preset probability value can be manually specified based on experience, and the shift push probability values ​​of multiple shift schedules can be determined by inputting multiple shift schedules into the aforementioned satisfaction value prediction model. When the shift push probability values ​​of multiple shift schedules are all less than the preset probability value, it means that the shift push probability corresponding to the shift schedule is low due to an unreasonable attendance cycle (such as an attendance cycle that is too long).

[0084] In some embodiments, for ease of description, assuming that the production efficiency values ​​corresponding to all employees in each attendance cycle are taken, updating the attendance cycle based on multiple production efficiency values ​​in at least one attendance cycle may include: Calculate the average of the production time efficiency values ​​of all employees within the preset time length, and determine whether it satisfies |average of production time efficiency values ​​- time efficiency requirement value| / time efficiency requirement value ≤ preset ratio; wherein, the time efficiency requirement value and the preset ratio are both numerical values, which can be manually specified according to production requirements; the preset time length corresponds to one or more attendance cycles, that is, when this step adopts the production time efficiency values ​​within multiple attendance cycles, the preset time length is the sum of multiple attendance cycles.

[0085] If not, then obtain the production efficiency values ​​corresponding to all employees in an attendance cycle, and calculate the average of the production efficiency values ​​of all employees in the attendance cycle to perform the above judgment again; If satisfied, then execute: randomly select data from a minimum attendance unit that has not been selected, add the data from multiple attendance units that have been selected before, and calculate the average of the production time efficiency values ​​of all employees within this time (i.e., multiple attendance units); if |average of production time efficiency values ​​- preset time efficiency requirement value| / time efficiency requirement value>preset ratio, then select data from a minimum attendance unit that has not been selected again and add the data from multiple attendance units that have been selected before, and calculate the average of the production time efficiency values ​​of all employees within this time, until |average of production time efficiency values ​​- preset time efficiency requirement value| / time efficiency requirement value ≤preset ratio, then the time length at this time (i.e., the total number of multiple minimum attendance units) can be used as the update attendance cycle. The minimum attendance unit refers to the smallest unit of the attendance cycle manually specified, such as hours, days, etc.

[0086] Exemplarily, assuming that the selected attendance cycle corresponds to the week from February 3 to February 7, the minimum attendance unit can be one day, and the scheduling module 110 can randomly select the production time efficiency value of February 3, and calculate the average of the production time efficiency values ​​of all employees. If | average value of production time efficiency value - preset time efficiency requirement value | / time efficiency requirement value > preset ratio, it is necessary to select another minimum attendance unit of data, such as the production time efficiency value of February 7, and then calculate the average value of production time efficiency value based on the production time efficiency values ​​of February 3 and February 7 and perform the above judgment again. If | average value of production time efficiency value - preset time efficiency requirement value | / time efficiency requirement value ≤ preset ratio is satisfied, then the attendance cycle is February 3 + February 7, which corresponds to two minimum attendance units. Therefore, the new attendance cycle can be a cycle every 2 days.

[0087] By reasonably determining the attendance cycle when the shift scheduling push probability value does not meet the requirements, work efficiency can be effectively mobilized and production can be promoted in a timely manner.

[0088] In some scenarios, there may be a situation where both access control data and punch-in data are missing or there is a conflict between access control data and punch-in data. Therefore, in some embodiments, in step 320, the attendance module 120 may also be configured to, for at least one employee: based on the work punch-in data and access control data in the current attendance cycle, determine the employee's corrected attendance data in the current attendance cycle through a working time correction model.

[0089] In some embodiments, the working time correction model can be a machine learning model, such as a neural network (NN). The input of the working time correction model is the work clock-in data and access control data of an employee in the current attendance cycle, and the output of the working time correction model is the corrected attendance data of the employee in the current attendance cycle.

[0090] In some embodiments, the working time correction model can be obtained by training with labeled training samples. The specific training method can be similar to the training model of the satisfaction value prediction model mentioned above, which will not be repeated here.

[0091] In some embodiments, the training samples of the working time correction model include sample work clock-in data and sample access control data of multiple employees in multiple attendance cycles, which can be obtained from the company's historical attendance data.

[0092] The label of the training sample is the sample corrected attendance data corresponding to each employee in each attendance cycle. The sample corrected attendance data can be improved manually. For example, when there is a real sample work punch-in data or when the sample work punch-in data conflicts with the sample access control data, the actual attendance situation can be determined by retrieving monitoring or visiting, thereby obtaining the accurate sample corrected attendance data of the employee.

[0093] The use of the work time correction model to obtain corrected attendance data makes it possible not only to supplement missing data but also to correct unreasonable data, thereby reducing operational errors and ensuring accuracy and compliance.

[0094] Figure 4 It is an exemplary block diagram of a work-hour correction model according to some embodiments of the present specification.

[0095] refer to Figure 4 In some embodiments, the working time correction model 400 may include a time efficiency estimation submodel 410 and a working time estimation submodel 420. The input of the time efficiency estimation submodel 410 is the working time adjustment sequence of the employee in the historical period. The historical period may be a specific attendance period or a past attendance period. The output of the time efficiency estimation submodel 410 is the production time efficiency value of the employee in the historical period. The production time efficiency value is a value reflecting the production efficiency of the employee. The higher the production time efficiency value, the higher the effective working time of the employee in the unit time. Correspondingly, the output or workload of the employee is also higher.

[0096] The input of the working time estimation sub-model 420 is the production time value of the employee in the historical period (that is, the output of the time estimation sub-model 410) and the work punch-in data and the access control data of the employee in the current attendance period. The output of the working time estimation sub-model 420 is the revised attendance data of the employee in the current attendance period.

[0097] The working time adjustment sequence is a sequence that can reflect the employee's working time adjustment. For the working time that the employee has already incurred, if there are errors or omissions in the registration, the administrator can adjust the working time and obtain the working time adjustment sequence. The working time adjustment sequence includes one or more working time adjustment records, each of which includes a corresponding adjustment time period and adjustment duration to adjust the employee's incurred working time, where the positive or negative adjustment duration indicates an increase or decrease in the corresponding working time. For example, an exemplary working time adjustment record in the working time adjustment sequence can be: (14:00~16:00, +2 hours).

[0098] The time estimation submodel 410 and the work time estimation submodel 420 can be trained separately through labeled training samples, and the trained time estimation submodel 410 and the work time estimation submodel 420 are combined to obtain the work time correction model 400. The training method of the time estimation submodel 410 and the work time estimation submodel 420 can be similar to the training process of the work time correction model 400 in the previous text, which will not be repeated here.

[0099] The training samples of the time estimation submodel 410 are sample working hours adjustment sequences, which can be obtained based on the company's historical attendance data. The labels corresponding to the training samples of the time estimation submodel 410 are sample production time efficiency values ​​corresponding to the sample working hours adjustment sequences, which can be obtained by obtaining the preset type of access control data of employees in each time period, and then taking the ratio of the number of preset type of access control data of employees in each time period to the number of preset type of access control data of departments (or companies) in each time period as the sample production time efficiency value corresponding to the sample working hours adjustment sequence. The preset type of access control data can be access control data of non-workplace type venues such as gates, balconies, and entertainment rooms. When employees frequently enter and exit non-workplace type venues, so that the number of access control data exceeds the average value of the department (or company), it means that the employee's production time efficiency value is low.

[0100] In some embodiments, the training samples of the working time estimation sub-model 420 are sample production time efficiency values ​​of multiple employees and sample work punch-in data and sample access control data corresponding to each employee. The labels of the training samples are sample corrected attendance data. The sample corrected attendance data can be obtained by manually improving the attendance data in the manner described above, which will not be repeated here.

[0101] The time efficiency estimation submodel 410 considers the impact of the employee's non-working time on production efficiency, which can meet the needs of different employees and departments. The working time estimation submodel 420 uses the production efficiency value to assist in judgment and determine the possibility of employees clocking in at different time periods, so that the actual attendance time can be effectively inferred, and accurate corrected attendance data can be obtained.

[0102] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0103] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0104] In addition, unless explicitly stated in the claims, the order of processing elements and sequences, the use of alphanumeric characters, or the use of other names in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0105] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0106] Finally, it should be understood that the embodiments in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A digital employee data management system, characterized by: It includes a scheduling module, an attendance module, and a display module; the scheduling module, the attendance module, and the display module are configured on an employee terminal and / or an administrator terminal; The scheduling module is configured to: Acquiring work schedule information and holiday application information from a plurality of employee terminals, and acquiring revised attendance data in a current attendance cycle from at least one of the employee terminals; Determine a shift schedule based on the work schedule information, the holiday application information and the corrected attendance data, and distribute the shift schedule to a plurality of employee terminals; The attendance module is configured to: Acquire work clock-in data in the current attendance cycle from the plurality of employee terminals, and acquire access control data in the current attendance cycle from the plurality of access control sensor devices; Determine, based on the work clock-in data and the access control data in the current attendance cycle, revised attendance data of at least one employee in the current attendance cycle; Determine attendance data based on the revised attendance data of the plurality of employees in the current attendance cycle; The display module is configured as follows: The attendance data and / or the shift schedule are displayed.

2. The system according to claim 1, characterized in that: The employee terminal includes an office terminal, and the system further includes a business monitoring module, which is configured to: Acquire business operation data from the plurality of office terminals; the business operation data includes at least one of order data and equipment data; The scheduling module is also configured to: In response to the business operation data satisfying an update condition, the shift schedule is updated based on the work schedule information, the vacation application information, and the revised attendance data.

3. The system according to claim 2, characterized in that: The system further includes a scheduling feedback module; the scheduling module is further configured to: Acquire scheduling demand data from the scheduling feedback module; the scheduling demand data includes the required working time period and required number of workers corresponding to the scheduled project; Determine a plurality of candidate shift schedules based on the shift demand data; Based on the plurality of candidate shift schedules, employee shift willingness, the modified attendance data of at least one employee, the work schedule information and the holiday application information, a shift promotion probability value corresponding to each candidate shift schedule is determined through a satisfaction value prediction model; the employee shift willingness is obtained based on the shift scheduling feedback module, and the satisfaction value prediction model is a machine learning model; From the multiple schedule push probability values, the candidate schedule corresponding to the maximum schedule push probability value is selected as the updated schedule.

4. The system according to claim 2, characterized in that: The attendance module is further used for, for at least one employee: Based on the work punch-in data and the access control data in the current attendance cycle, the corrected attendance data of the employee in the current attendance cycle is determined through a work time correction model.

5. The system according to claim 4, characterized in that: The man-hour correction model includes a time efficiency estimation sub-model and a man-hour estimation sub-model; The time efficiency estimation sub-model determines the production time efficiency value in the historical period based on the employee's work time adjustment sequence in the historical period; the work time adjustment sequence is obtained through the administrator terminal, and the work time adjustment sequence includes one or more work time adjustment records, and each work time adjustment record includes a corresponding adjustment time period and adjustment duration; The man-hour estimation sub-model determines the revised attendance data of the employee in the current attendance cycle based on the production time efficiency value in the historical period, the work punch-in data of the employee in the current attendance cycle, and the access control data.

6. A digital employee data management method, characterized by: Executed by the processor, including: Obtain working time arrangement information and holiday application information, and obtain revised attendance data within at least one current attendance cycle; Determine a shift schedule based on the work schedule information, the holiday application information and the revised attendance data, and distribute the shift schedule to multiple employee terminals; Acquire work clock-in data within the current attendance cycle, and acquire access control data within the current attendance cycle from multiple access control sensor devices; Determine, based on the work clock-in data and the access control data in the current attendance cycle, revised attendance data of at least one employee in the current attendance cycle; Determine attendance data based on the revised attendance data of the plurality of employees in the current attendance cycle; The attendance data and / or the shift schedule are displayed.

7. The method according to claim 6, characterized in that: The employee terminal includes an office terminal, and the method further includes: Acquire business operation data from the plurality of office terminals; the business operation data includes at least one of order data and equipment data; In response to the business operation data satisfying an update condition, the shift schedule is updated based on the work schedule information, the vacation application information, and the revised attendance data.

8. The method according to claim 6, characterized in that: In response to the business operation data satisfying the update condition, updating the shift schedule based on the work schedule information, the holiday application information and the revised attendance data, including: Obtaining shift scheduling demand data; the shift scheduling demand data includes the required working time period and required number of workers corresponding to the shift scheduling project; Determine a plurality of candidate shift schedules based on the shift demand data; Based on the candidate shift schedule, the employee shift demand data of the employees to be scheduled, the modified attendance data of at least one employee, the work schedule information and the holiday application information, a shift push probability value corresponding to each of the candidate shift schedules is determined by a satisfaction value prediction model; Based on the multiple schedule push probability values, the candidate schedule corresponding to the maximum schedule push probability value is selected as the updated schedule.

9. A digital employee data management device, characterized in that: It includes a processor, and the processor is used to execute the digital employee data management method described in any one of claims 6 to 8.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the digital employee data management method described in any one of claims 6 to 8.

Images