Attendance checking method, device and equipment and storage medium

Abstract

The invention discloses an attendance checking method, device and equipment and a storage medium, and the method comprises the following steps: obtaining historical attendance checking data and personalized information of each employee user, determining a first target employee user corresponding to an absence rate greater than a preset absence threshold in the historical attendance checking data, and determining an attendance checking result of the first target employee user based on the personalized information of the first target employee user. And pushing the pre-attendance information to the first target employee user, and in a preset time period after the first target employee user confirms the pre-attendance information, in response to an on-site attendance result of the first target employee user for attendance checking in the attendance checking device, confirming that the attendance checking of the first employee user is successful. Therefore, the employees with reminding requirements are screened out according to the absence rate, interference to self-discipline employees not needing reminding is reduced, attendance reminding is carried out on the employees flexibly according to individual requirements of the employees, the employees can pay more attention to the attendance reminding, the attendance effectiveness of the attendance reminding is improved, and the attendance reminding efficiency is improved. Attendance is assisted in a more flexible attendance reminding mode.

Description

Technical Field

[0001] This application relates to the field of time and attendance tracking, and more specifically, to a time and attendance method, device, equipment, and storage medium. Background Technology

[0002] In modern enterprise management, attendance management is a core element ensuring the orderly operation of an organization. With the widespread adoption of digital office solutions, various intelligent attendance systems have emerged, improving attendance management efficiency. Given that many employees frequently miss clocking in, attendance systems send reminders to employees at preset fixed times to reduce the rate of missed clocking in.

[0003] However, this attendance reminder is based on a fixed time, which lacks flexibility and cannot adapt to different commuting situations and work rhythms of employees. It often results in reminders being too early or too late, causing employees to easily ignore the reminder information, thus failing to serve the purpose of attendance reminder. At the same time, it can also interfere with self-disciplined employees who do not need attendance reminders.

[0004] Therefore, how to use more flexible attendance reminder methods to assist attendance tracking, improve the effectiveness of attendance reminders, and reduce interference with self-disciplined employees has become an urgent problem to be solved. Summary of the Invention

[0005] In view of the above problems, this application provides an attendance method, device, equipment and storage medium to assist attendance with a more flexible attendance reminder method, improve the effectiveness of attendance reminders for attendance, and reduce interference with self-disciplined employees.

[0006] To achieve the above objectives, the following specific solutions are proposed:

[0007] An attendance method includes:

[0008] Obtain historical attendance data and personalized information of each employee user;

[0009] Identify the first target employee user corresponding to the absence rate exceeding a preset absence threshold in the historical attendance data;

[0010] Based on the personalized information of the first target employee user, pre-attendance information is pushed to the first target employee user. The pre-attendance information includes prompts to remind the employee user to go to the attendance device to clock in.

[0011] Within a preset time period after the first target employee user confirms the pre-attendance information, in response to the actual attendance result of the first target employee user at the attendance device, the attendance of the first employee user is confirmed as successful.

[0012] Optionally, the method further includes:

[0013] For each employee user, if the employee user's absence rate is 0, or the employee user's status information for the day is "on leave / out", the employee user is determined to be the second target employee user. The second target employee user is the employee user who will not receive the pre-attendance information.

[0014] Optionally, the method further includes:

[0015] Identify a third target employee user who is neither the first target employee user nor the second target employee user;

[0016] For each of the third target employee users, the probability of pushing the pre-attendance information to the third target employee user is calculated based on the personalized information of the third target employee user.

[0017] For each of the third target employee users, the pre-attendance information is pushed to the third target employee user based on the push probability.

[0018] Optionally, the personalized information of the third target employee user includes the age pre-uploaded by the third target employee user and the rest time pre-uploaded by the third target employee user;

[0019] Based on the personalized information of the third target employee user, calculate the probability of pushing the pre-attendance information to the third target employee user, including:

[0020] Determine each day of absence for the third target employee user;

[0021] Calculate the average rest time of the day preceding each of the three target employee users' absence days;

[0022] Calculate the first similarity score between the average rest time and the rest time of the previous day;

[0023] Divide the preset standard age by the age of the third target employee user to obtain the age coefficient;

[0024] Multiply the age coefficient, the first similarity score, and the basic push probability to obtain the push probability of pushing the pre-attendance information to the third target employee user.

[0025] Optionally, the personalized information of the third target employee user may also include the commuting departure time pre-uploaded by the third target employee user;

[0026] Based on the personalized information of the third target employee user, the probability of pushing the pre-attendance information to the third target employee user is calculated, which further includes:

[0027] Calculate the average departure time of the commute departure time for each of the absent days of the third target employee user;

[0028] Calculate a second similarity score between the average departure time and the current day's commute departure time;

[0029] Based on the first similarity score and the second similarity score, a comprehensive similarity score is calculated;

[0030] The probability of pushing the pre-attendance information to the third target employee user is obtained by multiplying the age coefficient, the comprehensive similarity score, and the basic push probability.

[0031] Optionally, the personalized information of the first target employee user includes the commuting departure time, commuting departure location, commuting mode, and the time when the first target employee user reads the historical pre-attendance information uploaded in advance.

[0032] Based on the personalized information of the first target employee user, pre-attendance information is pushed to the first target employee user, including:

[0033] Simulate the journey of the first target employee user from the commuting departure point at the commuting departure time to the attendance device using the commuting vehicle, and roughly screen several candidate free time points of the first target employee user in the journey;

[0034] In each historical commute of the first target employee user, the precise free time point of that historical commute is determined based on the time difference between the time when the first target employee user reads the historical pre-attendance information and the commute departure time corresponding to that reading of the historical pre-attendance information.

[0035] Select the target idle time point with the highest frequency from all the aforementioned precise idle time points;

[0036] Among the candidate idle time points, determine the push time point that is closest to the target idle time point;

[0037] At the specified push time, pre-attendance information is pushed to the first target employee user.

[0038] Optionally, simulating the journey of the first target employee user from the commuting departure location at the commuting departure time to the attendance device using the commuting vehicle includes:

[0039] Obtain traffic information for the route from the commuting departure point to the commuting departure point on the same day, as well as weather information for the route after the commuting departure time;

[0040] Based on the traffic information and the weather information, the journey of the first target employee user from the commuting departure point at the commuting departure time to the attendance device is simulated.

[0041] An attendance device, comprising:

[0042] The employee data acquisition unit is used to acquire the historical attendance data of each employee user and the personalized information of each employee user.

[0043] The absent employee determination unit is used to determine the first target employee user corresponding to the absentee rate that is greater than a preset absentee threshold in the historical attendance data;

[0044] The pre-attendance information push unit is used to push pre-attendance information to the first target employee user based on the personalized information of the first target employee user. The pre-attendance information includes prompt information to remind the employee user to go to the attendance device for attendance.

[0045] The attendance success confirmation unit is used to confirm the first employee's attendance success within a preset time period after the first target employee confirms the pre-attendance information, in response to the actual attendance result of the first target employee taking attendance on the attendance device.

[0046] Optionally, the device may also include:

[0047] The "Do Not Push Employee Determination Unit" is used to determine, for each employee user, if the employee user's absence rate is 0, or the employee user's daily status information is "on leave / out", that employee user is a second target employee user, and the second target employee user is the employee user for whom the pre-attendance information is not pushed.

[0048] Optionally, the device may also include:

[0049] The third target employee determination unit is used to determine a third target employee user who is neither the first target employee user nor the second target employee user.

[0050] The push probability calculation unit is used to calculate the push probability of pushing the pre-attendance information to each of the third target employee users based on the personalized information of the third target employee users.

[0051] The probability push unit is used to push the pre-attendance information to each of the third target employee users based on the push probability.

[0052] Optionally, the personalized information of the third target employee user includes the age pre-uploaded by the third target employee user and the rest time pre-uploaded by the third target employee user;

[0053] The push probability calculation unit includes:

[0054] The employee absence day determination unit is used to determine each absence day of the third target employee user;

[0055] The average rest time calculation unit is used to calculate the average rest time of the day before each of the absence days of the third target employee user.

[0056] The first similarity score calculation unit is used to calculate the first similarity score between the average rest time and the rest time of the previous day.

[0057] An age coefficient calculation unit is used to divide a preset standard age by the age of the third target employee user to obtain an age coefficient.

[0058] The first push probability calculation unit is used to multiply the age coefficient, the first similarity score and the basic push probability to obtain the push probability of pushing the pre-attendance information to the third target employee user.

[0059] Optionally, the personalized information of the third target employee user may also include the commuting departure time pre-uploaded by the third target employee user;

[0060] The push probability calculation unit further includes:

[0061] The average departure time calculation unit is used to calculate the average departure time of the commute for each of the three target employee users' absence days;

[0062] The second similarity score calculation unit is used to calculate the second similarity score between the average departure time and the current day's commute departure time;

[0063] The comprehensive similarity score calculation unit is used to calculate a comprehensive similarity score based on the first similarity score and the second similarity score;

[0064] The second push probability calculation unit is used to multiply the age coefficient, the comprehensive similarity score, and the basic push probability to obtain the push probability of pushing the pre-attendance information to the third target employee user.

[0065] Optionally, the personalized information of the first target employee user includes the commuting departure time, commuting departure location, commuting mode, and the time when the first target employee user reads the historical pre-attendance information uploaded in advance.

[0066] The pre-attendance information push unit includes:

[0067] The trip simulation unit is used to simulate the trip of the first target employee user from the commuting departure location at the commuting departure time to the attendance device using the commuting vehicle.

[0068] The idle time point coarse screening unit is used to coarsely screen several candidate idle time points of the first target employee user in the process;

[0069] The precise idle time point determination unit is used to determine the precise idle time point of each historical commute of the first target employee user based on the time difference between the time when the first target employee user reads the historical pre-attendance information and the commute departure time corresponding to the reading of the historical pre-attendance information.

[0070] The precise idle time point determination unit is used to select the target idle time point with the highest frequency from the various precise idle time points;

[0071] The push time point determination unit is used to determine the push time point that is closest to the target idle time point among the candidate idle time points;

[0072] The push time point information push unit is used to push pre-attendance information to the first target employee user at the push time point.

[0073] Optionally, the travel simulation unit includes:

[0074] The traffic and weather information acquisition unit is used to acquire traffic information for the route from the commuting departure point to the commuting departure point on the same day, as well as weather information for the route after the commuting departure time.

[0075] The traffic and weather information trip simulation unit is used to simulate, based on the traffic information and the weather information, the trip of the first target employee user from the commuting departure point at the commuting departure time to the attendance device using the commuting vehicle.

[0076] An attendance device, comprising a memory and a processor;

[0077] The memory is used to store programs;

[0078] The processor is used to execute the program to implement the various steps of the attendance method described above.

[0079] A storage medium having a computer program stored thereon, which, when executed by a processor, implements the various steps of the attendance method described above.

[0080] By employing the aforementioned technical solution, this application identifies the first target employee users whose absence rate exceeds a preset absence threshold by acquiring historical attendance data and personalized information of each employee user. Based on the personalized information of the first target employee users, pre-attendance information is pushed to them. This pre-attendance information includes a reminder to the employee user to go to the attendance device for attendance. Within a preset time period after the first target employee user confirms the pre-attendance information, the application responds to the actual attendance result of the first target employee user at the attendance device, confirming the first employee user's successful attendance. Therefore, by filtering employees with attendance reminder needs based on absence rate, interference with self-disciplined employees who do not require attendance reminders is reduced. Attendance reminders are flexibly sent according to employees' personalized needs, making employees more likely to pay attention to attendance reminders, thereby improving the effectiveness of attendance reminders and achieving a more flexible attendance reminder method to assist in attendance management.

[0081] Furthermore, since employees have ample time to go to the attendance equipment to clock in after confirming their pre-attendance information, they do not need to rush to clock in when it is almost time to clock in, thus reducing the probability of accidents. Attached Figure Description

[0082] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0083] Figure 1 This is a flowchart illustrating an implementation of an attendance scheme provided in an embodiment of this application.

[0084] Figure 2 This is a schematic diagram illustrating a scheme for implementing pre-attendance combined with on-site attendance, provided in an embodiment of this application.

[0085] Figure 3 A schematic diagram of a device structure for implementing an attendance scheme, provided in an embodiment of this application;

[0086] Figure 4 This is a schematic diagram of the structure of a device for implementing an attendance scheme, provided in an embodiment of this application. Detailed Implementation

[0087] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0088] The proposed solution can be implemented based on a terminal with data processing capabilities, such as a computer, cloud, or server.

[0089] Next, combined Figure 1 The attendance method described in this application may include the following steps:

[0090] Step S110: Obtain the historical attendance data and personalized information of each employee user.

[0091] Specifically, when acquiring historical attendance data for each employee, attendance records from the past 3 months to 1 year can be collected. This includes detailed data such as daily clock-in time, number of absences, duration of lateness and early departure, leave type and frequency, and missed clock-in / out records, forming a complete timeline of attendance behavior. Personalized information can cover multiple dimensions: basic information includes the employee's department, job type, working hours, commuting information (which can be the employee's pre-uploaded departure location and time), common commuting methods, and average commuting time.

[0092] Understandably, by acquiring historical attendance data and personalized information, it's possible to accurately identify groups with abnormal attendance records using historical data. Combining this with data such as absenteeism rates and lateness patterns allows for the scientific identification of employees requiring priority reminders, avoiding indiscriminate reminders that might interfere with self-disciplined employees. Personalized information supports differentiated reminder strategies; for example, pre-attendance information can be pushed to employees with long commutes, and reminder timing can be adjusted based on real-time location for field staff, significantly improving the adaptability of reminders. The combination of these two types of information lays the foundation for subsequent optimization of the reminder model. By analyzing the correlation between historical data and personalized features, the reminder logic can be continuously iterated, making the pre-attendance mechanism more aligned with enterprise management scenarios. Ultimately, this reduces absenteeism rates while increasing employee acceptance of attendance management.

[0093] Step S120: Determine the first target employee user corresponding to the absence rate that is greater than the preset absence threshold in the historical attendance data.

[0094] Specifically, identifying the primary target employee users requires precise screening using multi-dimensional data. First, the preset absence threshold needs to be dynamically adjusted based on company management rules and job characteristics. For example, a 5% monthly absence rate threshold could be set for core production positions, and an 8% threshold for administrative positions. Simultaneously, a distinction should be made between normal leave (such as sick leave and personal leave) and unexcused absences, with only unexcused absences included in the statistics. When calculating employee absence rates, a calendar month can be used as the statistical period, and the result can be obtained using the formula "number of unexcused absences ÷ number of days required to be present in the current month × 100%". If an employee is late for more than 30 minutes three times consecutively, this can be counted as one day of absence and included in the calculation. Furthermore, by automatically comparing each employee's absence rate with the corresponding threshold, employees exceeding the threshold can be marked as primary target employee users, and an auxiliary analysis report containing the distribution of their absence times (such as high-frequency absences on Mondays and high-frequency absences during early shifts) can be generated.

[0095] Step S130: Based on the personalized information of the first target employee user, push pre-attendance information to the first target employee user.

[0096] The pre-attendance information may include prompts to remind employees to go to the attendance device to clock in.

[0097] Specifically, for commuting information, if the primary target employee uses public transportation, real-time bus / subway arrival data can be used to send pre-attendance information 20 minutes before their departure. If they commute by car, real-time traffic conditions can be linked, and a reminder can be triggered 30 minutes in advance when the estimated arrival time is close to the attendance deadline. For work hours, shift workers will receive reminders matching their shift for the day, while flexible work hours will receive reminders based on their historical peak arrival times (e.g., 9:00-10:00).

[0098] Understandably, by combining personalized information with real-time scenarios, reminders can be ensured to appear when employees are within their attention span, avoiding oversight due to mistimed timing. Selecting delivery methods based on employee preferences reduces the probability of reminders being lost in the information overload. Enhanced reminders for high-frequency absence periods directly address employees' weaknesses, strengthening their attendance awareness psychologically, thus improving the effective reach of reminders and significantly reducing absences due to forgetfulness.

[0099] Step S140: Within a preset time period after the first target employee user confirms the pre-attendance information, in response to the actual attendance result of the first target employee user at the attendance device, confirm that the first employee user's attendance is successful.

[0100] The preset time period can represent the sufficient time for the first target employee to travel from the current location to the actual attendance location.

[0101] Understandably, the dual verification of pre-attendance information confirmation and on-site attendance can effectively avoid management loopholes caused by missed reminders in the traditional single-reminder model. Employee confirmation of pre-attendance information is equivalent to a commitment to acknowledge the need for attendance, while the on-site attendance result within a preset time period (e.g., within one hour) serves as the final verification basis, making the determination of successful attendance more rigorous and reducing attendance disputes caused by missed reminders. Furthermore, after confirming pre-attendance information, employees only need to clock in within the preset time period, giving them ample time to do so without rushing to clock in just before the scheduled time, thus reducing the probability of unexpected risks.

[0102] The attendance method provided in this embodiment obtains historical attendance data and personalized information of each employee user, identifies the first target employee user whose absence rate exceeds a preset absence threshold from the historical attendance data, and pushes pre-attendance information to the first target employee user based on the personalized information of the first target employee user. The pre-attendance information includes a reminder to the employee user to go to the attendance device for attendance. Within a preset time period after the first target employee user confirms the pre-attendance information, the method responds to the actual attendance result of the first target employee user at the attendance device, confirming the first employee user's successful attendance. Therefore, by filtering employees with attendance reminder needs based on absence rate, the method reduces interference with self-disciplined employees who do not need attendance reminders, flexibly provides attendance reminders according to employees' personalized needs, and makes employees more likely to pay attention to attendance reminders, thereby improving the effectiveness of attendance reminders and achieving a more flexible attendance reminder method to assist in attendance management.

[0103] Furthermore, since employees have ample time to go to the attendance equipment to clock in after confirming their pre-attendance information, they do not need to rush to clock in when it is almost time to clock in, thus reducing the probability of accidents.

[0104] To further reduce disruption to self-disciplined employees, the attendance methods provided in this application may also include:

[0105] For each employee user, if the employee user's absence rate is 0, or the employee user's status information for the day is "on leave / out", then the employee user is identified as the second target employee user.

[0106] Among them, the second target employee user can refer to employee users who do not receive pre-attendance information.

[0107] It's understandable that a zero absence rate for an employee indicates high self-discipline and no need for attendance reminders. Conversely, if an employee requests leave or goes out on a given day, it means they don't need attendance that day. Therefore, neither of these categories requires attendance reminders. These employees can then be marked as the second target group, and attendance reminders should be filtered out from these users.

[0108] Furthermore, pre-attendance information will be pushed to employees who are neither the first target employee user nor the second target employee user user based on probability.

[0109] Specifically, we can identify third-target employee users who are neither the first-target employee user nor the second-target employee user.

[0110] For each third target employee user, the probability of pushing pre-attendance information to the third target employee user is calculated based on the user's personalized information.

[0111] Specifically, the personalized information of the third-party target employee users may include their pre-uploaded age, pre-uploaded rest time, pre-uploaded commute departure time, pre-uploaded commute departure location, pre-uploaded commuting mode, and the time they viewed historical pre-attendance information.

[0112] Understandably, the third target employees fall neither into the high-absence-risk first target group nor the second target group that requires no reminders; their attendance behavior may fluctuate. Calculating the push probability using personalized information allows the system to find a balance between necessary reminders and avoiding disruption. For example, employees with recent busy projects and occasional lateness can be given a higher push probability, while employees with regular attendance but who tend to slack off at the end of the quarter can have their push probability increased at specific times, making reminders more tailored to individual needs.

[0113] For each third target employee user, pre-attendance information is pushed to the third target employee user based on the push probability.

[0114] In some embodiments of this application, the process of calculating the probability of pushing pre-attendance information to a third target employee user based on the personalized information of the third target employee user, as mentioned in the above embodiments, is described. This process may include:

[0115] S1. Determine each day of absence for the third target employee user.

[0116] Understandably, analyzing absenteeism days can provide insights into the potential correlations between employee absences. By analyzing the specific dates of each absenteeism day, and combining this with calendar information and business cycles, high-frequency periods when employees are prone to absenteeism can be identified. For example, an employee's repeated absences on the last Friday of each month may be related to advance weekend planning; a technical employee's frequent absences three days before a project launch may be related to lateness due to overtime fatigue. Analyzing these factors makes the calculation of push notification probabilities more closely aligned with individual behavioral characteristics.

[0117] S2. Calculate the average rest time of the day before each day of absence for the third target employee user.

[0118] Average rest time reflects the correlation between an employee's rest status and the risk of absenteeism, representing typical rest characteristics under conditions of impending absenteeism risk. Therefore, when an employee is at the rest level corresponding to this average rest time, the probability of being absent the following day is significantly higher than with normal rest. For example, if an employee normally rests an average of 7 hours per day, but their average rest time the day before their absence is 5 hours, this means that rest duration below 5 hours can serve as a warning signal of potential absenteeism. The lower this value, the more significant the impact of insufficient rest on their attendance.

[0119] S3. Calculate the first similarity score between the average rest time and the rest time of the previous day.

[0120] The first similarity score represents the probability of matching an employee's current absence risk with their historical absence patterns. A higher score indicates that the current rest status is closer to the employee's typical rest characteristics before past absences, meaning a higher potential risk of absence that day. A lower score indicates that the current rest status deviates from historical risk characteristics, and the probability of absence is relatively low. For example, if an employee's average rest time is 4 hours, a higher similarity score on a day with 4.1 hours of rest suggests they may be absent again due to insufficient rest; a lower score on a 6-hour rest indicates a lower risk of absence in the current state.

[0121] S4. Divide the preset standard age by the age of the third target employee user to obtain the age coefficient.

[0122] The preset standard age represents the benchmark reference value for setting attendance patterns among employees. It is typically selected as the median age group (e.g., 35 years old) within the employee group, where attendance stability is relatively high and the impact of rest status on absenteeism is relatively balanced. The age coefficient quantifies the moderating effect of the difference between an individual's age and the benchmark age on absenteeism risk. Younger employees (below the standard age) are generally more energetic and prone to insufficient rest due to staying up late, thus increasing the likelihood of absenteeism; therefore, the coefficient is greater than 1, requiring a higher reminder intensity. Older employees (above the standard age) have relatively more mature work and rest schedules, making them less likely to be absent due to irregular schedules; therefore, the coefficient is less than 1, indicating that the reminder intensity can be appropriately reduced.

[0123] S5. Multiply the age coefficient, the first similarity score, and the basic push probability to obtain the push probability of pushing pre-attendance information to the third target employee user.

[0124] The push probability is composed of an age coefficient, a similarity score, and a base push probability. The base push probability is a neutral probability value determined based on the company's overall attendance management goals and the common characteristics of the third-target employee group. The base push probability does not rely on individual personalized information, but rather reflects the company's basic intervention tendency towards this third-target employee user group.

[0125] Considering that the similarity score may include more than one personalized factor, the following section further introduces a scheme for calculating the basic push probability based on multiple personalized factors.

[0126] S6. Calculate the average departure time of the third target employee user's commute departure time for each day of absence.

[0127] Among them, the average departure time reflects the commuting rhythm characteristics of employees under the condition of high risk of absenteeism.

[0128] Understandably, for employees in the third target group, their attendance status fluctuates, and the timing of their commute can directly affect their ability to clock in on time. When their departure time is later than or close to their historical average departure time that often leads to absenteeism, the risk of absence that day will increase significantly. For example, if an employee's average departure time is 7:00, and their commute departure time is 7:15 today, which is significantly later than the average, it means that the commuting time pressure they face is closer to their historical absence scenarios, and the risk needs to be reduced through reminders and intervention.

[0129] S7. Calculate the second similarity score between the average departure time and the current day's commute departure time.

[0130] The second similarity score reflects the degree of matching between the current commuting schedule and the commuting behavior preceding past absences. A higher score indicates that the current departure time is closer to the employee's typical commuting departure characteristics before past absences, meaning that the potential risk of absence due to insufficient commuting time on that day is higher; a lower score indicates that the current departure time deviates from historical risk characteristics, and the probability of absence due to commuting issues is relatively low.

[0131] S8. Calculate the comprehensive similarity score based on the first similarity score and the second similarity score.

[0132] Specifically, the process of calculating the comprehensive similarity score can be quantitatively integrated by establishing a multi-dimensional weighted model. Specifically, dynamic coefficients can be assigned to the first and second similarity scores based on the weighted proportions of insufficient rest and commuting delay factors in the personalized information of the company's historical attendance data on the impact of absence.

[0133] For example, if the data shows that 60% of a company's employees are absent due to insufficient rest and 40% are absent due to commuting delays, then the first similarity score is assigned a weight of 0.6 and the second similarity score is assigned a weight of 0.4. Therefore, the overall similarity score = 0.6 * first similarity score + 0.4 * second similarity score.

[0134] In addition, other factors of personalized information can be combined to calculate the overall similarity score, such as the reading preferences of the third target user for reminder information (pre-attendance information). Each factor can also be weighted according to its own importance, and the sum of each weight coefficient is 1.

[0135] S9. Multiply the age coefficient, the comprehensive similarity score, and the basic push probability to obtain the push probability of pushing pre-attendance information to the third target employee user.

[0136] In some embodiments of this application, the process of pushing pre-attendance information to the first target employee user based on the personalized information of the first target employee user in step S130 above is described. This process may include:

[0137] S1. Simulate the journey of the first target employee user from the commuting departure point at the commuting departure time to the attendance device by commuting tool, and roughly screen several candidate idle time points of the first target employee user in the journey.

[0138] Specifically, we can first integrate employees' personalized commuting information, analyze the most likely routes employees would choose based on their commuting origin and mode of transportation, and then determine the employees' potential temporary free time points based on their commuting mode and route. These temporary free time points can represent the times when employees are not focused on commuting events, such as the time employees spend waiting at red lights while driving or the time employees are not moving while on the subway.

[0139] Understandably, virtual trip simulation can proactively avoid scenarios that are clearly unsuitable for push notifications, reducing the chances of reminders being ignored or interfered with due to inappropriate timing, thus improving the effective reach of reminders from the source. Dynamic filtering based on commuting tools and real-time traffic conditions makes candidate time points more closely match the actual situation of the day. The coarse screening process narrows down the scope of subsequent precise matching, excluding a large number of invalid times, providing an efficient foundation for matching with target free time points, and reducing system computing costs.

[0140] Furthermore, during the simulated journey, real-time traffic and weather factors can be incorporated. Specifically, this process can include:

[0141] S11. Obtain traffic information for the route from the commuting departure point to the commuting departure point on the same day, as well as weather information for the route after the commuting departure time.

[0142] S12. Based on traffic and weather information, simulate the journey of the first target employee user from the commuting departure point at the commuting departure time to the attendance device using a commuting vehicle.

[0143] Understandably, considering the accuracy of travel time predictions, weather factors significantly impact different modes of commuting. For example, heavy rain can cause subway delays, and flooded roads can reduce driving speeds, while light, sunny weather has almost no impact on commuting. Combining traffic and weather information allows for dynamic adjustments to the travel model, improving the accuracy of simulated travel. Furthermore, the combined effects of weather and traffic can alter employees' commuting behavior patterns. For instance, in rainy or snowy weather, subway waiting areas may become crowded due to increased people seeking shelter, and employees who drive may spend longer searching for parking spaces. By integrating weather and traffic factors, these weather-induced behavioral changes can be identified: if heavy rain is predicted during the commute, crowded subway platforms will be excluded, and the time employees spend searching for parking spaces will be included as candidate available times. This ensures that the selected times better reflect the actual behavior of the day, increasing the likelihood of reminders being noticed.

[0144] S2. In each historical commute of the first target employee user, the precise free time point of that historical commute is determined based on the time difference between the time when the first target employee user reads the historical pre-attendance information and the commute departure time corresponding to that reading of the historical pre-attendance information.

[0145] Among them, the precise free time point can represent the time point when an employee reads the pre-attendance information under a certain free situation.

[0146] For example, if an employee's departure time for a historical commute is 7:30 and the time they read the pre-attendance information is 8:10, then the precise free time for that historical commute is 40 minutes after the departure time.

[0147] S3. Select the target idle time point with the highest frequency from all precise idle time points.

[0148] For example, if an employee has multiple precise free time points in their historical commutes, namely 40 minutes after the start time of their commute (12 times per month), 20 minutes after the start time of their commute (5 times per month), and 30 minutes after the start time of their commute (3 times per month), then the 40 minutes after the start time of their commute can be selected as the target free time point.

[0149] Among them, the target free time point can represent the time point when employees are most likely to read the pre-attendance information.

[0150] S4. Among the candidate idle time points, determine the push time point that is closest to the target idle time point.

[0151] Understandably, by identifying the push notification time closest to the target free time among multiple candidate free time points obtained from the simulated trip, the best time for users to read pre-attendance information can be more accurately determined.

[0152] S5. Push pre-attendance information to the first target employee user at the push time.

[0153] Understandably, since the push timing is based on the personalized behavior of the primary target employees to determine the optimal time for them to read the pre-attendance information, pushing the pre-attendance information to the primary target employees at the push timing can encourage them to read the pre-attendance information more likely, thereby improving the effectiveness of attendance reminders and enabling attendance to be assisted in a more flexible way.

[0154] To enhance the user's more complete attendance experience, the attendance status of employees can be calculated after they clock in on-site, and an attendance status notification can be sent to the user.

[0155] Based on this, employee users can refer to the solution of using the pre-attendance - on-site attendance model. Figure 2 .

[0156] Specifically, employees first register their personal information in the attendance access control device, which then synchronizes this information to the cloud service. When the cloud service needs to remind employees of their attendance, it intelligently pushes pre-attendance information to their mobile devices. Employees can read and view this information and pre-attend according to their needs. After confirming the pre-attendance information, employees go to the designated attendance point (the location indicated by the attendance access control device) within the specified time to clock in. After clocking in, the attendance access control device pushes the actual attendance record to the cloud service. The cloud service stores the employee's actual attendance information and calculates their attendance status based on the pre-attendance confirmation time, actual attendance time, and standard attendance time. It then sends an attendance status notification to the employee's mobile device.

[0157] The apparatus for implementing an attendance scheme provided in the embodiments of this application will be described below. The apparatus for implementing an attendance scheme described below can be referred to in correspondence with the method for implementing attendance described above.

[0158] See Figure 3 , Figure 3 This is a schematic diagram of a device structure for implementing attendance tracking, as disclosed in an embodiment of this application.

[0159] like Figure 3 As shown, the device may include:

[0160] The employee data acquisition unit 11 is used to acquire the historical attendance data of each employee user and the personalized information of each employee user.

[0161] Absentee employee determination unit 12 is used to determine the first target employee user corresponding to the absentee rate that is greater than the preset absentee threshold in the historical attendance data;

[0162] The pre-attendance information push unit 13 is used to push pre-attendance information to the first target employee user based on the personalized information of the first target employee user. The pre-attendance information includes prompt information to remind the employee user to go to the attendance device for attendance.

[0163] The attendance success confirmation unit 14 is used to confirm the attendance success of the first employee user within a preset time period after the first target employee user confirms the pre-attendance information, in response to the actual attendance result of the first target employee user taking attendance on the attendance device.

[0164] Optionally, the device may also include:

[0165] The "Do Not Push Employee Determination Unit" is used to determine, for each employee user, if the employee user's absence rate is 0, or the employee user's daily status information is "on leave / out", that employee user is a second target employee user, and the second target employee user is the employee user for whom the pre-attendance information is not pushed.

[0166] Optionally, the device may also include:

[0167] The third target employee determination unit is used to determine a third target employee user who is neither the first target employee user nor the second target employee user.

[0168] The push probability calculation unit is used to calculate the push probability of pushing the pre-attendance information to each of the third target employee users based on the personalized information of the third target employee users.

[0169] The probability push unit is used to push the pre-attendance information to each of the third target employee users based on the push probability.

[0170] Optionally, the personalized information of the third target employee user includes the age pre-uploaded by the third target employee user and the rest time pre-uploaded by the third target employee user;

[0171] The push probability calculation unit includes:

[0172] The employee absence day determination unit is used to determine each absence day of the third target employee user;

[0173] The average rest time calculation unit is used to calculate the average rest time of the day before each of the absence days of the third target employee user.

[0174] The first similarity score calculation unit is used to calculate the first similarity score between the average rest time and the rest time of the previous day.

[0175] An age coefficient calculation unit is used to divide a preset standard age by the age of the third target employee user to obtain an age coefficient.

[0176] The first push probability calculation unit is used to multiply the age coefficient, the first similarity score and the basic push probability to obtain the push probability of pushing the pre-attendance information to the third target employee user.

[0177] Optionally, the personalized information of the third target employee user may also include the commuting departure time pre-uploaded by the third target employee user;

[0178] The push probability calculation unit further includes:

[0179] The average departure time calculation unit is used to calculate the average departure time of the commute for each of the three target employee users' absence days;

[0180] The second similarity score calculation unit is used to calculate the second similarity score between the average departure time and the current day's commute departure time;

[0181] The comprehensive similarity score calculation unit is used to calculate a comprehensive similarity score based on the first similarity score and the second similarity score;

[0182] The second push probability calculation unit is used to multiply the age coefficient, the comprehensive similarity score, and the basic push probability to obtain the push probability of pushing the pre-attendance information to the third target employee user.

[0183] Optionally, the personalized information of the first target employee user includes the commuting departure time, commuting departure location, commuting mode, and the time when the first target employee user reads the historical pre-attendance information uploaded in advance.

[0184] The pre-attendance information push unit includes:

[0185] The trip simulation unit is used to simulate the trip of the first target employee user from the commuting departure location at the commuting departure time to the attendance device using the commuting vehicle.

[0186] The idle time point coarse screening unit is used to coarsely screen several candidate idle time points of the first target employee user in the process;

[0187] The precise idle time point determination unit is used to determine the precise idle time point of each historical commute of the first target employee user based on the time difference between the time when the first target employee user reads the historical pre-attendance information and the commute departure time corresponding to the reading of the historical pre-attendance information.

[0188] The precise idle time point determination unit is used to select the target idle time point with the highest frequency from the various precise idle time points;

[0189] The push time point determination unit is used to determine the push time point that is closest to the target idle time point among the candidate idle time points;

[0190] The push time point information push unit is used to push pre-attendance information to the first target employee user at the push time point.

[0191] Optionally, the travel simulation unit includes:

[0192] The traffic and weather information acquisition unit is used to acquire traffic information for the route from the commuting departure point to the commuting departure point on the same day, as well as weather information for the route after the commuting departure time.

[0193] The traffic and weather information trip simulation unit is used to simulate, based on the traffic information and the weather information, the trip of the first target employee user from the commuting departure point at the commuting departure time to the attendance device using the commuting vehicle.

[0194] The attendance device provided in this application embodiment can be applied to attendance equipment, such as terminals: mobile phones, computers, etc. Optionally, Figure 4 The hardware structure block diagram of the attendance device is shown. Figure 4 The hardware structure of the attendance device may include: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4;

[0195] In this embodiment of the application, the number of processor 1, communication interface 2, memory 3, and communication bus 4 is at least one, and processor 1, communication interface 2, and memory 3 communicate with each other through communication bus 4;

[0196] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0197] Memory 3 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device;

[0198] The memory stores a program, which the processor can call. The program is used for:

[0199] Obtain historical attendance data and personalized information of each employee user;

[0200] Identify the first target employee user corresponding to the absence rate exceeding a preset absence threshold in the historical attendance data;

[0201] Based on the personalized information of the first target employee user, pre-attendance information is pushed to the first target employee user. The pre-attendance information includes prompts to remind the employee user to go to the attendance device to clock in.

[0202] Within a preset time period after the first target employee user confirms the pre-attendance information, in response to the actual attendance result of the first target employee user at the attendance device, the attendance of the first employee user is confirmed as successful.

[0203] Optionally, the refined and extended functions of the program can be found in the description above.

[0204] This application embodiment also provides a storage medium that can store a program suitable for execution by a processor, the program being used for:

[0205] Obtain historical attendance data and personalized information of each employee user;

[0206] Identify the first target employee user corresponding to the absence rate exceeding a preset absence threshold in the historical attendance data;

[0207] Based on the personalized information of the first target employee user, pre-attendance information is pushed to the first target employee user. The pre-attendance information includes prompts to remind the employee user to go to the attendance device to clock in.

[0208] Within a preset time period after the first target employee user confirms the pre-attendance information, in response to the actual attendance result of the first target employee user at the attendance device, the attendance of the first employee user is confirmed as successful.

[0209] Optionally, the refined and extended functions of the program can be found in the description above.

[0210] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0211] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0212] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An attendance method, characterized in that, include: Obtain historical attendance data and personalized information of each employee user; Identify the first target employee user corresponding to the absence rate exceeding a preset absence threshold in the historical attendance data; Based on the personalized information of the first target employee user, pre-attendance information is pushed to the first target employee user. The pre-attendance information includes prompts to remind the employee user to go to the attendance device to clock in. Within a preset time period after the first target employee user confirms the pre-attendance information, in response to the actual attendance result of the first target employee user at the attendance device, the attendance of the first employee user is confirmed as successful.

2. The method according to claim 1, characterized in that, Also includes: For each employee user, if the employee user's absence rate is 0, or the employee user's status information for the day is "on leave / out", the employee user is determined to be the second target employee user. The second target employee user is the employee user who will not receive the pre-attendance information.

3. The method according to claim 2, characterized in that, Also includes: Identify a third target employee user who is neither the first target employee user nor the second target employee user; For each of the third target employee users, the probability of pushing the pre-attendance information to the third target employee user is calculated based on the personalized information of the third target employee user. For each of the third target employee users, the pre-attendance information is pushed to the third target employee user based on the push probability.

4. The method according to claim 3, characterized in that, The personalized information of the third target employee user includes the age that the third target employee user uploaded in advance, and the rest time that the third target employee user uploaded in advance; Based on the personalized information of the third target employee user, calculate the probability of pushing the pre-attendance information to the third target employee user, including: Determine each day of absence for the third target employee user; Calculate the average rest time of the day preceding each of the three target employee users' absence days; Calculate the first similarity score between the average rest time and the rest time of the previous day; Divide the preset standard age by the age of the third target employee user to obtain the age coefficient; Multiply the age coefficient, the first similarity score, and the basic push probability to obtain the push probability of pushing the pre-attendance information to the third target employee user.

5. The method according to claim 4, characterized in that, The personalized information of the third target employee user also includes the commuting departure time uploaded in advance by the third target employee user; Based on the personalized information of the third target employee user, the probability of pushing the pre-attendance information to the third target employee user is calculated, which further includes: Calculate the average departure time of the commute departure time for each of the absent days of the third target employee user; Calculate a second similarity score between the average departure time and the current day's commute departure time; Based on the first similarity score and the second similarity score, a comprehensive similarity score is calculated; The probability of pushing the pre-attendance information to the third target employee user is obtained by multiplying the age coefficient, the comprehensive similarity score, and the basic push probability.

6. The method according to claim 1, characterized in that, The personalized information of the first target employee user includes the commuting departure time, commuting departure location, commuting mode, and the time when the first target employee user reads the historical pre-attendance information uploaded in advance by the first target employee user. Based on the personalized information of the first target employee user, pre-attendance information is pushed to the first target employee user, including: Simulate the journey of the first target employee user from the commuting departure point at the commuting departure time to the attendance device using the commuting vehicle, and roughly screen several candidate free time points of the first target employee user in the journey; In each historical commute of the first target employee user, the precise free time point of that historical commute is determined based on the time difference between the time when the first target employee user reads the historical pre-attendance information and the commute departure time corresponding to that reading of the historical pre-attendance information. Select the target idle time point with the highest frequency from all the aforementioned precise idle time points; Among the candidate idle time points, determine the push time point that is closest to the target idle time point; At the specified push time, pre-attendance information is pushed to the first target employee user.

7. The method according to claim 6, characterized in that, Simulating the journey of the first target employee user from the commuting departure location at the commuting departure time to the attendance device using the commuting vehicle includes: Obtain traffic information for the route from the commuting departure point to the commuting departure point on the same day, as well as weather information for the route after the commuting departure time; Based on the traffic information and the weather information, the journey of the first target employee user from the commuting departure point at the commuting departure time to the attendance device is simulated.

8. An attendance device, characterized in that, include: The employee data acquisition unit is used to acquire the historical attendance data of each employee user and the personalized information of each employee user. The absent employee determination unit is used to determine the first target employee user corresponding to the absentee rate that is greater than a preset absentee threshold in the historical attendance data; The pre-attendance information push unit is used to push pre-attendance information to the first target employee user based on the personalized information of the first target employee user. The pre-attendance information includes prompt information to remind the employee user to go to the attendance device for attendance. The attendance success confirmation unit is used to confirm the first employee's attendance success within a preset time period after the first target employee confirms the pre-attendance information, in response to the actual attendance result of the first target employee taking attendance on the attendance device.

9. An attendance device, characterized in that, Including memory and processor; The memory is used to store programs; The processor is configured to execute the program to implement each step of the attendance method as described in any one of claims 1-7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the various steps of the attendance method as described in any one of claims 1-7.

Images