A multi-project-oriented intelligent attendance management method, system and device

Abstract

This invention relates to the field of enterprise informatization and human resource management technology, specifically to an intelligent attendance management method, system, and device for multiple projects. The method includes: collecting project information, schedule data, and attendance data corresponding to various projects to establish a data processing set; dividing the data processing set into several project pairs and matching them with employees within each project to obtain employee-project pairs, constructing a dynamic project membership model, and assigning project membership weights to each employee-project pair; detecting cross-project attendance records of employee-project pairs in the data processing set, using a conflict credibility assessment algorithm to calculate cross-project attendance records, and combining the conflict credibility scores to obtain a conflict credibility score; setting a preset grading threshold and comparing it with the conflict credibility score to generate detection results and corresponding handling measures. The collaborative work of the dynamic project membership model and the conflict credibility assessment algorithm distinguishes between legitimate cross-project movement and suspicious conflicts, resulting in higher accuracy in judgment.

Description

Technical Field

[0001] This invention relates to the field of enterprise informatization and human resource management technology, specifically to an intelligent attendance management method, system, and device for multiple projects. Background Technology

[0002] In multi-project enterprises, it has become commonplace for employees to move dynamically between projects in different geographical areas based on work needs. This places extremely high demands on the adaptability of traditional attendance management systems. Existing attendance management technologies are mostly designed for single-project, fixed-location scenarios, lacking precise adaptation to employees' dynamic work trajectories. This leads to numerous pain points in attendance management, and the technical deficiencies are becoming increasingly apparent.

[0003] Existing technologies generally suffer from rigid conflict determination rules, often employing the simplistic logic of "multiple project check-ins within the same time period are considered abnormal," failing to distinguish between "reasonable cross-project movement" and "suspicious attendance conflicts." For example, if an employee reasonably travels between projects in adjacent cities and checks in separately, the system will directly trigger an alarm. Such invalid alarms require managers to review them one by one, significantly increasing manual workload and reducing attendance management efficiency. Furthermore, existing systems have weak data collaboration and analysis capabilities. Attendance data is isolated from data such as business trip approvals and project support plans, making automatic correlation and verification impossible. This means that even when an employee has submitted business trip approvals and checked in at the destination project, it may still be judged as a cross-project conflict, further increasing the false positive rate.

[0004] Furthermore, existing cross-project attendance anomaly handling relies entirely on the manual experience of managers, lacking system-level intelligent decision support. Different managers interpret business rules differently, leading to inconsistent results for similar anomalies. Moreover, manual processing is time-consuming and cannot quickly respond to real-time attendance management needs. While other HR outsourcing service platforms offer basic attendance functions, they only support simple clocking in and data recording, lacking dynamic weighting models and intelligent conflict assessment mechanisms designed for multi-project, cross-regional scenarios, thus failing to address the core pain points. Summary of the Invention

[0005] To address the technical problems of high conflict misjudgment rate, high manual intervention cost, low approval efficiency, and weak data collaboration capabilities in existing multi-project attendance management systems, the present invention aims to provide an intelligent attendance management method for multiple projects. The specific technical solution adopted is as follows: Collect project information, schedule data, and attendance data from various projects to establish a data processing set; Based on the data processing set, several project pairs are divided and matched with employees within the project to obtain employee-project pairs. A dynamic project membership model is constructed, and project membership weights are assigned to each employee-project pair. The detection data processing set judges the cross-project attendance records of employee-project pairs, uses the conflict credibility assessment algorithm to calculate the cross-project attendance records, and combines the project affiliation weight to obtain the conflict credibility score; A preset grading threshold is set and compared with the conflict confidence score to generate detection results and corresponding handling measures.

[0006] Preferably, the project information includes the project location and role information for each project; the schedule data includes, but is not limited to, approved business trips, support and training; and the attendance data includes the employee's attendance time, valid attendance days and the total valid attendance days corresponding to the project.

[0007] Preferably, the data processing set is divided into several project pairs, and employee-project pairs are obtained by matching them with employees within each project, specifically as follows: Data processing is centralized into two projects to form project pairs. Employees who are involved in both projects within a project pair are successfully matched to form an employee-project pair.

[0008] Preferably, a dynamic project affiliation model is constructed to assign project affiliation weights to each employee-project pair, including: Each of the basic identity factor, attendance frequency factor, and schedule planning factor is set as a model sub-item, and a dynamic project membership model is established by integrating all model sub-items. Based on each employee-project pair, corresponding model sub-items are obtained, and the corresponding project affiliation weights are evaluated.

[0009] Preferably, model sub-items are set for basic identity factor, attendance frequency factor, and schedule planning factor, respectively. A dynamic project membership model is established by integrating all model sub-items, including: Assign values ​​to employees' corresponding role information in the project based on project information to determine basic identity factors; Calculate employee attendance data and determine attendance frequency factors; Integrate schedule data to predict the correlation between employees and projects, and determine schedule planning factors; A dynamic project membership model is established by integrating basic identity factors, attendance frequency factors, and schedule factors.

[0010] Preferably, the detection data processing set identifies cross-project attendance records for employee-project pairs, employs a conflict credibility assessment algorithm to calculate cross-project attendance records, and combines project affiliation weights to obtain a conflict credibility score, including: Based on the data processing set, it is determined whether the employee has attendance data in both projects in the corresponding project pair. If so, it is determined that the employee has cross-attendance records. The conflict credibility assessment algorithm is used to calculate cross-project attendance records, determine the time overlap and geographical distance factors, and obtain the project affiliation weights of the two projects corresponding to the cross-project attendance records through the dynamic project affiliation model, thus obtaining the conflict credibility score.

[0011] Preferably, the time overlap and geographical distance factors are determined separately, including: Analyze the attendance time intervals in the cross-project attendance records for the two projects to assess the degree of time overlap. Verify the actual geographical distance between the two project locations in the cross-attendance records, collect traffic data for the two project locations, and determine the shortest travel time as the geographical distance factor.

[0012] Preferably, determining the shortest travel time as a geographical distance factor includes: Based on traffic data, the shortest travel time of mainstream traffic between the two project locations is determined, and the basic shortest travel time is obtained by combining the actual geographical distance. Analyze mainstream transportation to obtain corresponding actual commuting scenarios, and configure scenario-based travel time fluctuation ratios; An effective travel time range is established by combining the shortest basic travel time and the floating ratio. A scenario confidence coefficient is introduced to determine the shortest travel time, and the shortest travel time is defined as a geographical distance factor.

[0013] To address the aforementioned problems, the present invention further provides: an intelligent attendance management system for multiple projects, the system comprising: The data acquisition layer is used to collect project information, schedule data, and attendance data for various projects and to establish a data processing set. The data processing layer is used for: dividing the data processing set into several project pairs and matching them with employees within the project to obtain employee-project pairs; constructing a dynamic project membership model and assigning project membership weights to each employee-project pair; detecting cross-project attendance records of employee-project pairs in the data processing set; using a conflict credibility assessment algorithm to calculate cross-project attendance records and combining them with project membership weights to obtain a conflict credibility score. The application layer is used to: preset the classification threshold, compare it with the conflict confidence score, and generate detection results and corresponding processing methods.

[0014] To address the aforementioned problems, the present invention also provides an electronic device comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus, and the processor invokes logical instructions in the memory to execute the intelligent attendance management method for multiple projects described in any of the preceding claims.

[0015] The present invention has the following beneficial effects: 1. Based on the collaborative work of a dynamic project membership model and a conflict credibility assessment algorithm, it effectively distinguishes between reasonable cross-project flows and suspicious conflicts, improving the accuracy of judgment, reducing invalid alarms, reducing the workload of manual review, and avoiding interference from misjudgments in attendance management. Furthermore, the dynamic project membership model internalizes complex business rules into executable algorithmic logic and updates project membership weights in real time, facilitating subsequent progress in project-based attendance management, reducing manual judgment operations, and achieving fully automated hierarchical processing of attendance anomalies. Combined with conflict credibility scores, it enables managers to focus on truly high-risk conflict events, improving approval efficiency. The standardized algorithm ensures consistent processing results for similar anomalies, improving the standardization and traceability of attendance management and avoiding bias from human experience. In addition, the conflict credibility score is obtained based on multi-source data, adaptable to various cross-project flow scenarios such as within and across cities, and applicable to various multi-project parallel enterprises.

[0016] 2. The intelligent attendance management system and electronic device for multiple projects provided by this invention have the same beneficial effects as the intelligent attendance management method for multiple projects provided by this invention, and will not be described in detail here. Attached Figure Description

[0017] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 The following is a flowchart illustrating the implementation of an intelligent attendance management method for multiple projects, as provided in one embodiment of the present invention. Figure 2 A flowchart illustrating the steps of an intelligent attendance management method for multiple projects provided in one embodiment of the present invention; Figure 3 The following is a flowchart illustrating the implementation of a dynamic project membership model for a multi-project intelligent attendance management method, as provided in one embodiment of the present invention. Figure 4 The flowchart illustrates the implementation of a conflict credibility assessment algorithm for a multi-project intelligent attendance management method, as provided in one embodiment of the present invention. Figure 5 This is a state machine diagram of intelligent approval routing and exception handling in an intelligent attendance management method for multiple projects provided in one embodiment of the present invention. Detailed Implementation

[0019] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation methods, structures, features, and effects of an intelligent attendance management method, system, and device for multiple projects proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0021] The following description, in conjunction with the accompanying drawings, details a specific solution for an intelligent attendance management method, system, and device for multiple projects provided by this invention.

[0022] To better illustrate this, current traditional attendance systems are typically designed for single projects or fixed locations, lacking effective management of employee mobility across projects and exhibiting several shortcomings: First, rigid rules lead to high error rates; they can only judge conflicts based on simple "present / absent" records, such as considering clocking in at different projects as a conflict, failing to consider the rationality of employees' actual work arrangements, i.e., projects located in neighboring cities that can reasonably travel back and forth within a day. This results in numerous unnecessary anomaly alerts and increases the burden of manual review. Second, isolated data hinders collaboration; while attendance, business trip, and leave data can be synchronized, the system lacks intelligent correlation analysis capabilities. For example, modifying attendance rules requires significant manual intervention to ensure data consistency, making the process cumbersome. Third, approval relies on human experience; anomaly handling depends entirely on the administrator's understanding and memory of attendance rules, lacking system-level intelligent guidance and decision support, resulting in low processing efficiency and a high risk of errors. Therefore, this paper proposes an intelligent attendance management method for multiple projects, comprehensively considering attendance-related data to improve judgment accuracy, enhance automation, and optimize management efficiency.

[0023] Please combine Figure 1 and Figure 2 It illustrates an implementation flowchart and step flowchart of an intelligent attendance management method for multiple projects provided in the first embodiment of the present invention, the method comprising: Step S1: Collect project information, schedule data, and attendance data for various projects, and establish a data processing set; Step S2: Divide the data processing set into several project pairs and match them with employees within the project to obtain employee-project pairs. Construct a dynamic project membership model and assign project membership weights to each employee-project pair. Step S3: Detect the cross-project attendance records of employee-project pairs in the data processing set, use the conflict credibility assessment algorithm to calculate the cross-project attendance records, and combine the project affiliation weight to obtain the conflict credibility score; Step S4: Set a preset grading threshold and compare it with the conflict confidence score to generate detection results and corresponding handling measures.

[0024] As an alternative implementation method, this paper proposes an intelligent attendance management method for multiple projects based on the shortcomings of existing attendance management systems. It is suitable for intelligent attendance management in scenarios where employees move dynamically between multiple geographically dispersed projects. It is especially suitable for companies in engineering construction, consulting services, operation and maintenance support, etc., where multiple projects are carried out in parallel, employees frequently collaborate across projects, and projects are geographically dispersed. It can realize intelligent analysis of cross-project attendance data, accurate determination of conflicts, and automated processing, thereby improving the standardization and efficiency of attendance management.

[0025] Furthermore, project information includes the project location and role information for each project; schedule data includes, but is not limited to, approved business trips, support and training; attendance data includes employee attendance time, valid attendance days and the total valid attendance days corresponding to the project.

[0026] It can be explained that project location refers to the specific city clearly designated in the project plan and directly related to the execution and implementation of the project, used to clarify the geographical location of the project; role information refers to the employee's corresponding permanent project role or mobile project role, to define the employee's functional identity in the project, and to clarify their responsibilities and positioning in the project; schedule data refers to various formally approved work arrangements, namely approved business trip plans, cross-departmental or cross-regional support tasks, and various professional or skills enhancement training activities; and attendance data refers to relevant data information on employee attendance, to reflect the employee's working hours and attendance status.

[0027] Please see Figure 3 Furthermore, in step S2, the data processing set is divided into several project pairs, and these pairs are matched with employees within each project to obtain employee-project pairs, specifically: Data processing is centralized into two projects to form project pairs. Employees who are involved in both projects within a project pair are successfully matched to form an employee-project pair.

[0028] Specifically, the data processing center combines two projects into a series of interconnected project pairs. Then, for each specific project pair, all personnel who participate in both projects in the pair are selected, and these employees are precisely matched with the corresponding project pairs. Finally, a detailed record of the correspondence between employees and project pairs is generated, thus forming employee-project pairs.

[0029] Further, in step S2, a dynamic project membership model is constructed, assigning project membership weights to each employee-project pair, including: Step S21: Set the model sub-items for basic identity factor, attendance frequency factor and schedule planning factor respectively, and establish a dynamic project membership model by combining all model sub-items.

[0030] The explanation is that, based on the analysis of various data in the data processing set, a dynamic project membership model is constructed to obtain the corresponding model sub-items. This model is used to quantify the association strength between employees and each project within a specific time period, so as to obtain the project etiquette weight of each employee-project pair. It is updated in real time with data such as employee work arrangements and attendance records, providing a basis for conflict determination.

[0031] Further, step S21 includes: Step S211: Assign values ​​to the corresponding role information of employees in the project based on the project information to determine the basic identity factors.

[0032] Specifically, before each project begins, a specific role corresponding to the responsibilities of all employees involved in the execution is clearly assigned within the project's organizational structure, and this role is assigned a value as a basic identity factor, denoted as [missing value]. This is used to provide a clear basis for subsequent work positioning, collaborative relationships, or performance evaluation. In this embodiment, the value of the role information is in the range of 0.3 to 0.8, which can be set according to the actual situation. For example, the Bg or Eg position's permanent project role is assigned a value of 0.6 to 0.8, which means that the employee has a high degree of correlation with the project; the A or B position's mobile project role is assigned a value of 0.3 to 0.5, which means that the correlation is low.

[0033] Step S212: Calculate employee attendance data and determine the attendance frequency factor.

[0034] Specifically, regarding the employee-project pair analysis, we select any project from the pair to determine the target project for the current analysis. Then, we calculate the employee's valid attendance days in the target project over the past 30 days, i.e., the number of days actually clocked in within those 30 days, denoted as... Next, determine the total number of valid attendance days in the past 30 days, that is, the total number of working days in the past 30 days, and record it as... Determine the attendance frequency factor, i.e. Clearly define the attendance frequency factor The value ranges from 0 to 0.5 and is used to reflect the actual attendance stickiness of employees to the target project. The statistical period can be configured as needed.

[0035] Step S213: Integrate schedule data, predict the correlation between employees and projects, and determine schedule planning factors.

[0036] Specifically, approved travel, support, and training schedule data are integrated to make forward-looking predictions about the correlation between employees and projects. The prediction results are used as schedule planning factors, denoted as... The corresponding value range is 0 to 0.4. That is, when there is a valid schedule plan for the current employee's schedule data in the project, the value is dynamically assigned according to the percentage of schedule coverage time, and the corresponding value range is 0.1 to 0.4; if there is no corresponding schedule plan, the value is directly assigned to 0.

[0037] Step S214: Integrate basic identity factors, attendance frequency factors, and schedule factors to establish a dynamic project membership model.

[0038] Specifically, a dynamic project membership model is established, and the corresponding calculation formula is as follows:

[0039] in, Indicates the weight of the project membership; , , Both represent weighting coefficients, and ; Indicates basic identity factors; Indicates the attendance frequency factor; This indicates the schedule planning factor.

[0040] Step S22: Obtain the corresponding model sub-items for each employee-project pair and evaluate the corresponding project affiliation weights; for each employee-project pair, obtain the relevant data corresponding to each model sub-item, that is, dynamically obtain the basic identity factor, attendance frequency factor, and schedule plan factor of each employee-project pair according to the enterprise's project priority, attendance strictness, and other requirements, and input them into the dynamic project affiliation model to assign a dynamic weight, namely the project affiliation weight, to each employee-project pair. It is used to quantify the intensity of an employee's affiliation with a project within a certain period of time.

[0041] Please see Figure 4 Furthermore, step S3 includes: Step S31: Based on the data processing set, calculate whether the employee has attendance data in both projects of the corresponding project pair. If so, determine that the employee has cross-attendance records; that is, calculate the attendance data in the data processing set to determine whether the employee has attendance data in both projects of the corresponding project pair. For example, if the employee has attendance records in both the first and second projects of the project pair on the same day, then it is determined that the employee has cross-attendance records.

[0042] Step S32: Use the conflict credibility assessment algorithm to calculate cross-project attendance records, determine the time overlap and geographical distance factors respectively, and obtain the project membership weights of the two projects corresponding to the cross-project attendance records through the dynamic project membership model to obtain the conflict credibility score.

[0043] The explanation is that the conflict credibility assessment algorithm replaces the traditional simple judgment that relies on manual comparison for cross-attendance records with quantitative analysis, thereby achieving more accurate, objective and efficient identification and processing of attendance data conflicts.

[0044] Further, in step S32, the temporal overlap and geographical distance factors are determined, including: Step S321: Analyze the attendance time intervals corresponding to the two projects in the cross-project attendance records and evaluate the time overlap; that is, calculate the time interval between two conflicting attendance records in the cross-project attendance, and use it as the time overlap, denoted as . The unit is hours. When an employee's attendance records for two projects completely overlap, The larger the time interval, the greater the corresponding time overlap. The larger the value, the less obvious the conflict between the two attendance records.

[0045] Step S322: Verify the actual geographical distance between the two project locations in the cross-attendance record, collect traffic data of the two project locations, and determine the shortest travel time as the geographical distance factor.

[0046] Understandably, in real life, since the two project locations in cross-project attendance usually refer to two cities, when choosing transportation for the two project locations, there are not only multiple options such as high-speed rail, airplane, long-distance bus or self-driving, but also various influencing factors such as weather conditions, traffic congestion, schedule adjustments, ticket availability and personal itinerary arrangements that may cause changes in the shortest travel time. Therefore, depending on the situation, the determination of the geographical distance factor should also be specifically analyzed.

[0047] Further, in step S322, determining the shortest travel time as a geographical distance factor includes: Step S3221: Determine the shortest travel time of the main traffic between the two project locations based on traffic data, and obtain the basic shortest travel time by combining the actual geographical distance.

[0048] As an optional implementation method, traffic data is obtained from relevant data such as the number of trains, route length, and road grade corresponding to any current mainstream transportation mode; among them, mainstream transportation includes common means of transportation such as high-speed rail, airplanes, long-distance buses, or self-driving cars.

[0049] Specifically, it calls third-party map APIs (Application Programming Interfaces) such as Gaode or Baidu Maps to determine the shortest travel time between the main modes of transportation between the project locations corresponding to the two projects in the current cross-project attendance record. This shortest travel time is used as the base shortest travel time and denoted as... This serves as a baseline value for subsequent time calculations; for example, the shortest driving time from city A to city B corresponds to the basic shortest travel time. , Indicates hours; or, if the shortest high-speed rail journey is from city A to city B, then... .

[0050] Step S3222: Analyze the mainstream traffic to obtain the corresponding actual commuting scenarios, and configure the scenario-based travel time fluctuation ratio.

[0051] Specifically, based on the mainstream modes of transportation and actual commuting scenarios in cross-project attendance records, adjustable percentages are configured for different transportation types, i.e., scenario-based travel time fluctuation percentages are configured, denoted as... It comprehensively considers factors such as road congestion, public transportation delays, and airport or high-speed rail station connections to provide a customizable adjustment coefficient for attendance data, and this ratio The specific settings can be adjusted according to the actual situation.

[0052] It should be noted that when the two project locations in the cross-project attendance record are both in the same city, the commuting type is urban roads. Typically, this involves driving or using a ride-hailing service to achieve the purpose of cross-project execution. However, this situation is easily affected by traffic lights or congestion, causing changes in the shortest travel time. Therefore, a floating ratio is set. The percentage is ±20% to 30%. Next, for cases where the two project locations in cross-project attendance records are in different cities, the corresponding mainstream transportation options are usually chosen based on distance, such as driving, high-speed rail / train, and airplane. When driving, taking the ring road, the percentage is adjusted to account for highway traffic and service area stops. The range is ±10% to 20%; when using high-speed rail / or bullet trains, the percentage may fluctuate due to factors such as ticket checking, delays, and connecting services. The percentage is ±5% to 15%; when using aircraft, the percentage is subject to fluctuations due to check-in, security checks, and flight delays. The range is ±10% to 20%; that is, the travel time is dynamically analyzed in this way.

[0053] Step S3223: Establish an effective travel time range by combining the basic shortest travel time and the floating ratio, introduce the scenario confidence coefficient, determine the shortest travel time, and define the shortest travel time as a geographical distance factor.

[0054] Specifically, firstly, the shortest travel time based on comprehensive infrastructure. and floating ratio Calculate the time fluctuation range, i.e. , ,in, This represents the minimum effective travel time, corresponding to the optimal road conditions. This represents the maximum effective travel time, corresponding to the worst road conditions; thus, the effective travel time interval is determined as follows. Next, the scenario confidence coefficient is introduced, denoted as... Its corresponding range is It can be configured according to the actual situation. For example, if commuting between projects mainly relies on fixed public transportation such as high-speed rail or airplanes, the road conditions are stable and the scenario confidence coefficient is high. The value ranges from 0.8 to 1; if the driving is mainly within the city or on highways, the road conditions are highly uncertain, and the scenario confidence coefficient is... The value ranges from 0.6 to 0.8; this determines the shortest travel time, i.e. This was then used as a geographical distance factor in subsequent analysis regarding the shortest travel time. The determination of this factor is biased towards the maximum effective passage time. It takes into account the actual time error of passage, and avoids the lenient judgment of conflict due to excessive expansion of the floating range, thus ensuring the ability to identify suspicious attendance conflicts.

[0055] Preferably, a dynamic calibration mechanism for historical commuting data is designed, which automatically records the actual time difference between an employee's clock-in and clock-out at one project and their arrival at another project through the entire attendance system. This data is compared with geographical distance factors to form a historical commuting database, and the fluctuation ratio is adjusted regularly on a monthly or quarterly basis. and scene confidence coefficient Dynamic calibration is performed, meaning that if multiple consecutive groups in the historical commuting database are used... This indicates that the current fluctuation ratio is too large, so the fluctuation ratio will be automatically adjusted downwards. Value 5%~10%; conversely, if multiple consecutive groups This indicates that the current fluctuation ratio is too small, and the fluctuation ratio will be automatically adjusted upwards. The value is 5%~10%; in the actual attendance process, enterprise administrators can view historical commuting data for calibration suggestions and dynamically confirm or adjust the floating ratio. and scene confidence coefficient This is to enable the algorithm to continuously adapt to real-world scenarios.

[0056] Specifically, in terms of time overlap and geographical distance factor Based on this, the project membership weights of the cross-project attendance records for the corresponding two projects are obtained through a dynamic project membership model, denoted as follows: and The conflict credibility score is obtained, i.e. , Represents the function mapping symbol; conflict confidence scores corresponding to cross-attendance records based on the current analysis. The analysis was expanded, and scoring rules were designed to address the conflict credibility score. Dynamic assignment, firstly, if time overlap... Much smaller than the geographical distance factor And the project belongs to the weight and The high overlap indicates that the employee was strongly required to be at two project locations simultaneously. In this case, the two projects in the cross-attendance records are considered a high-confidence conflict. Secondly, if the time overlap... The smaller the weight, the more time there is. If the weight of the project in either of the two projects is low and there are temporary visits, the current situation is a low credibility conflict and a reasonable flow. Third, if neither of the first and second situations is met, the remaining scenarios are medium credibility conflicts and are judged as low priority review items.

[0057] Optionally, in actual operation, when the conflict is of high credibility, ,and or , Assign a value of 0.7 to 1.0; when it is a low-confidence conflict, ,and or , Assign a value between 0 and 0.3; when the conflict is of medium confidence level, The value can be set to 0.3 to 0.7; adjustments can be made based on the actual situation.

[0058] Please see Figure 5 The explanation is as follows: In step S4, a grading threshold is preset. In this embodiment, two levels of thresholds are preset, namely, grading thresholds are set for high confidence conflicts, medium confidence conflicts and low confidence conflicts, so as to realize the grading and automated processing of attendance anomalies. The threshold can be adjusted according to the actual situation. Then, each level of threshold is compared with the conflict confidence score to generate detection results and corresponding processing measures.

[0059] Specifically, when it is a high-confidence conflict, i.e., the conflict confidence score... When a conflict occurs, the attendance system automatically locks the corresponding attendance record, prohibiting modification, and simultaneously pushes a message containing conflict records and conflict confidence scores. Anomalies in the calculation process and related data on project membership weights are reported to the project manager and HR administrator of the corresponding project, triggering multi-party collaborative approval. The record can only be unlocked after approval. When the conflict is of medium credibility... The system will push relevant anomaly information to the employee's immediate supervisor for simplified approval. The supervisor can quickly determine the issue based on historical movement records, schedules, and other data provided by the system. When the conflict is of low credibility, At this point, it is automatically marked as "reasonable cross-project movement", generating a note containing travel time analysis and weight explanation, and stored in the attendance log. No manual approval is required; it is only listed as an observation item for periodic spot checks, greatly reducing management interference.

[0060] As an optional implementation method, in actual attendance, there may be instances where employees forget to clock in or the attendance system malfunctions, resulting in missing records. In such cases, an early warning is issued for missing records. This is achieved by using a short-term sliding window model to monitor the completeness of attendance records in real time. If there are no clock-in records and no corresponding leave or business trip approvals, a reminder to make up the clock-in is automatically sent to the employee and their immediate supervisor.

[0061] Understandably, the collaborative work of the dynamic project membership model and conflict credibility assessment algorithm effectively distinguishes between legitimate cross-project flows and suspicious conflicts, improving the accuracy of judgment, reducing invalid alarms, decreasing the workload of manual review, and avoiding interference from misjudgments in attendance management. Furthermore, the dynamic project membership model internalizes complex business rules into executable algorithmic logic and updates project membership weights in real time, facilitating subsequent project-based attendance management, reducing manual judgment operations, and achieving fully automated hierarchical processing of attendance anomalies. Combined with conflict credibility scores, managers can focus on truly high-risk conflict events, improving approval efficiency. The standardized algorithm ensures consistent results for similar anomalies, enhancing the standardization and traceability of attendance management and avoiding biases from human experience. In addition, the conflict credibility score is obtained from multi-source data, adaptable to various cross-project flow scenarios within and across cities, and applicable to various multi-project parallel enterprises.

[0062] The second embodiment of the present invention provides an intelligent attendance management system for multiple projects, the system comprising: The data acquisition layer is used to collect project information, schedule data, and attendance data for various projects and to establish a data processing set. The data processing layer is used for: dividing the data processing set into several project pairs and matching them with employees within the project to obtain employee-project pairs; constructing a dynamic project membership model and assigning project membership weights to each employee-project pair; detecting cross-project attendance records of employee-project pairs in the data processing set; using a conflict credibility assessment algorithm to calculate cross-project attendance records and combining them with project membership weights to obtain a conflict credibility score. The application layer is used to: preset the classification threshold, compare it with the conflict confidence score, and generate detection results and corresponding processing methods.

[0063] Preferably, in this embodiment, the system includes three parts: a data acquisition layer, a data processing layer, and an application layer. To better manage these three parts, a data storage module is set up to call and / or archive the data processed by each part, thereby improving data manageability.

[0064] It can be explained that the overall system architecture includes an integrated data acquisition layer, data processing layer, and application layer, with each layer working together to upgrade attendance management; based on a dynamic project membership model and conflict credibility assessment algorithm, it achieves accurate determination of cross-project attendance conflicts through multi-dimensional factor collaborative analysis, combined with an intelligent approval routing mechanism, that is, by comparing the hierarchical threshold with the conflict credibility score to complete hierarchical processing, thereby optimizing attendance management efficiency.

[0065] The third embodiment of the present invention provides an electronic device, the device comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus, and the processor calls logical instructions in the memory to execute the intelligent attendance management method for multiple projects described in any of the foregoing embodiments.

[0066] It should be noted that this electronic device requires a multi-item intelligent attendance management method during operation. Therefore, integrating device and program data or configuring different hardware to produce functions similar to those achieved by this invention falls within the scope of protection of this invention. Furthermore, this device or system has the same beneficial effects as the aforementioned multi-item intelligent attendance management method, which will not be elaborated upon here.

[0067] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A multi-project oriented intelligent attendance management method, characterized in that, The method includes: Collect project information, schedule data, and attendance data from various projects to establish a data processing set; Based on the data processing set, several project pairs are divided and matched with employees within the project to obtain employee-project pairs. A dynamic project membership model is constructed, and project membership weights are assigned to each employee-project pair. The detection data processing set judges the cross-project attendance records of employee-project pairs, uses the conflict credibility assessment algorithm to calculate the cross-project attendance records, and combines the project affiliation weight to obtain the conflict credibility score; A preset grading threshold is set and compared with the conflict confidence score to generate detection results and corresponding handling measures.

2. The multi-project oriented intelligent attendance management method according to claim 1, characterized in that, The project information includes the project location and role information for each project; the schedule data includes, but is not limited to, approved business trips, support and training; the attendance data includes employee attendance time, valid attendance days and the total valid attendance days corresponding to the project.

3. The multi-project oriented intelligent attendance management method according to claim 2, characterized in that, The data processing set is divided into several project pairs, and employee-project pairs are obtained by matching the employees within each project. Specifically: Data processing is centralized into two projects to form project pairs. Employees who are involved in both projects within a project pair are successfully matched to form an employee-project pair.

4. The multi-project oriented intelligent attendance management method according to claim 3, characterized in that, Construct a dynamic project affiliation model to assign project affiliation weights to each employee-project pair, including: Each of the basic identity factor, attendance frequency factor, and schedule planning factor is set as a model sub-item, and a dynamic project membership model is established by integrating all model sub-items. Based on each employee-project pair, corresponding model sub-items are obtained, and the corresponding project affiliation weights are evaluated.

5. The intelligent attendance management method for multiple projects according to claim 4, characterized in that, Each of the following model sub-items is defined: basic identity factor, attendance frequency factor, and schedule planning factor. A dynamic project membership model is then established by integrating all model sub-items, including: Assign values ​​to employees' corresponding role information in the project based on project information to determine basic identity factors; Calculate employee attendance data and determine attendance frequency factors; Integrate schedule data to predict the correlation between employees and projects, and determine schedule planning factors; A dynamic project membership model is established by integrating basic identity factors, attendance frequency factors, and schedule factors.

6. The intelligent attendance management method for multiple projects according to claim 2, characterized in that, The data processing set is used to identify cross-project attendance records for employee-project pairs. A conflict credibility assessment algorithm is employed to calculate the cross-project attendance records, and a conflict credibility score is obtained by combining project affiliation weights. This score includes: Based on the data processing set, it is determined whether the employee has attendance data in both projects in the corresponding project pair. If so, it is determined that the employee has cross-attendance records. The conflict credibility assessment algorithm is used to calculate cross-project attendance records, determine the time overlap and geographical distance factors, and obtain the project affiliation weights of the two projects corresponding to the cross-project attendance records through the dynamic project affiliation model, thus obtaining the conflict credibility score.

7. The intelligent attendance management method for multiple projects according to claim 6, characterized in that, Determine the time overlap and geographic distance factors separately, including: Analyze the attendance time intervals in the cross-project attendance records for the two projects to assess the degree of time overlap. Verify the actual geographical distance between the two project locations in the cross-attendance records, collect traffic data for the two project locations, and determine the shortest travel time as the geographical distance factor.

8. The intelligent attendance management method for multiple projects according to claim 7, characterized in that, The shortest travel time is determined by geographical distance factors, including: Based on traffic data, the shortest travel time of mainstream traffic between the two project locations is determined, and the basic shortest travel time is obtained by combining the actual geographical distance. Analyze mainstream transportation to obtain corresponding actual commuting scenarios, and configure scenario-based travel time fluctuation ratios; An effective travel time range is established by combining the shortest basic travel time and the floating ratio. A scenario confidence coefficient is introduced to determine the shortest travel time, and the shortest travel time is defined as a geographical distance factor.

9. A smart attendance management system for multiple projects, characterized in that, The system includes: The data acquisition layer is used to collect project information, schedule data, and attendance data for various projects, and to establish a data processing set. The data processing layer is used for: dividing the data processing set into several project pairs and matching them with employees within the project to obtain employee-project pairs; constructing a dynamic project membership model and assigning project membership weights to each employee-project pair; detecting cross-project attendance records of employee-project pairs in the data processing set; using a conflict credibility assessment algorithm to calculate cross-project attendance records and combining them with project membership weights to obtain a conflict credibility score. The application layer is used to: preset the classification threshold, compare it with the conflict confidence score, and generate detection results and corresponding processing methods.

10. An electronic device, characterized in that, The device includes a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory communicate with each other through the communication bus. The processor calls logical instructions in the memory to execute the intelligent attendance management method for multiple projects as described in any one of claims 1 to 8.

Images