Intelligent visual management platform based on enterprise personnel data

Abstract

The invention discloses an intelligent visual management platform based on enterprise personnel data, which comprises a data acquisition module, an attendance analysis module, a data updating module and a visual display module, and relates to the technical field of personnel data management. According to the intelligent visual management platform based on enterprise personnel data, enterprise personnel information is matched and updated through the feature checking unit, data are extracted to establish a correlation model to check and determine the attendance checking state of enterprise personnel on that day, and then attendance checking records are summarized through the table generation unit to form an attendance checking record table; therefore, attendance checking is not realized by single daily face acquisition, and checking analysis is realized by combining information acquisition and state analysis of enterprise personnel to determine whether attendance abnormity is true or not and establishing a correlation model, so that personnel attendance data management is facilitated, the probability of dispute is reduced, and the enterprise attendance checking efficiency is improved. And the on-duty condition of the personnel is monitored synchronously, and visual management operation is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of personnel data management, in particular to an intelligent visual management platform based on enterprise personnel data. BACKGROUND

[0002] In modern enterprise management, personnel management is a crucial task. Enterprise personnel data contains information such as basic information, attendance records, performance evaluation, training experience, and salary benefits of employees. With the expansion of the scale of enterprises and the diversification of business development, the amount of personnel data is growing explosively. Traditional personnel management methods, such as paper file management and simple electronic form recording, have been difficult to meet the needs of efficient management and in-depth analysis of personnel data in enterprises.

[0003] Referring to the patent name: Personnel information management system and method based on cloud platform (patent publication number: CN119048037A, patent publication date: 2024-11-29), the main scheme is: obtaining evaluation data to calculate comprehensive evaluation score, and counting interviewers; calculating evaluation training score according to training data and comprehensive evaluation score, and screening qualified employees; obtaining multiple types of data and calculating influence index, and assigning positions to employees by comparing the influence index with the threshold set; recording attendance data and calculating attendance comprehensive index, combining historical project data and attendance comprehensive index to calculate performance evaluation index, judging performance risk alarm and generating adjustment instructions; calculating employee forecast attrition rate according to employee survey data and performance evaluation index, judging early warning and generating control instructions, and improving the efficiency and intelligent level of enterprise human resource management.

[0004] Based on the above file expression, the existing enterprise personnel data in the management process is prone to data analysis errors due to the large amount and disorder of data, especially in the recording operation of enterprise personnel attendance, due to the sensitivity of the equipment and the unintentional omission of the staff, there are often missing cards and forgotten compensation information or personnel missing compensation, resulting in attendance loss, and there are repeated card punching situations, and the specific situation is unknown, so that the attendance record is controversial and not convenient for management. Therefore, the present application provides an intelligent visual management platform based on enterprise personnel data. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides an intelligent visual management platform based on enterprise personnel data, which solves the problem of data analysis errors in the management process of existing enterprise personnel data due to the large amount and disorder of data, especially in the recording operation of enterprise personnel attendance, due to the sensitivity of the equipment and the unintentional omission of the staff, there are often missing cards and forgotten compensation information or personnel missing compensation, resulting in attendance loss, and there are repeated card punching situations, and the specific situation is unknown, so that the attendance record is controversial and not convenient for management.

[0006] To achieve the above object, the present application is implemented by the following technical solutions: An intelligent visual management platform based on enterprise personnel data, comprising: A data acquisition module, which realizes the acquisition of various data of enterprise personnel through acquisition equipment, and transmits and stores the data; An attendance analysis module, which classifies and extracts the collected data by using a data preprocessing unit, matches and updates the enterprise personnel information by using a feature checking unit, extracts data to establish a correlation model to check and determine the attendance status of enterprise personnel on the same day, and then summarizes the attendance records to form an attendance record table by using a table generating unit; A data updating module, which realizes the updating operation in the next data acquisition based on the changes in enterprise personnel information; A visual display module, which displays the data on the display screen in a combination of charts and text, facilitating the personnel to check and extract the attendance results.

[0007] Preferably, the operation of the acquisition equipment to acquire various data of enterprise personnel is: The acquisition equipment specifically includes an attendance device, a monitoring device, and a computer terminal; The attendance device is used for face recognition and collection operation of enterprise personnel and records the time stamp; The monitoring device is used for collecting data on whether the enterprise personnel are located at the workstation; The computer terminal is used for adding, deleting, or updating enterprise personnel information parameters, and simultaneously completing the input of leave and missing card information.

[0008] Preferably, the operation of the data preprocessing unit in the attendance analysis module to classify and extract the collected data is: The collected data is extracted according to the names of different acquisition equipment as a zone classification, and image data categories and content data categories are set based on the names of the acquisition equipment; And the collected data is sorted according to time sequence and introduced into the image data categories and content data categories corresponding to different zone classifications; And subcategories are set based on each image data category and content data category, and the data is classified according to the content of the subcategories; When extracting data, the corresponding data can be extracted by searching according to the required data conditions.

[0009] Preferably, the operation of the feature checking unit in the attendance analysis module to match and update the enterprise personnel information is: The face image data of a single person collected by the attendance device is extracted, and the time stamp of the current image collection is extracted at the same time; Determine whether the face image data of the personnel matches the enterprise personnel information in the database, update the face recognition matching image of the day after matching is completed, and compare the personnel attendance situation with the attendance system interval to determine whether there is an abnormality.

[0010] Preferably, the personnel attendance situation comparison and judgment operation is: Extract the timestamp of the first recorded face image data of the day as t1, and the timestamp of the last recorded face image data of the day as t2, set the attendance system interval as [T1, T2] and [T3, T4], and the result is: Result one, if t1>T1, t2 Result two, if t1≤T1 or t2≥T4, the current attendance is normal, and if the current personnel is recorded multiple face image data within the attendance system interval, an abnormal situation needs to be confirmed.

[0011] Preferably, the operation of extracting data to establish a correlation model in the attendance analysis module is: Extract the collection data of the attendance equipment as the first node, and determine the current attendance analysis personnel information as the second node; Extract the record data of the computer terminal as the third node and the collection data of the monitoring equipment as the fourth node; When the results one and two are met, the first node correlation orientation points to the second node, and the second node correlation orientation points to the third node, and finally the third node correlation orientation points to the fourth node, and the correlation orientation is realized after the last node is checked. The feature checking operation of the next node is realized to establish a correlation model.

[0012] Preferably, the operation of the correlation model in the attendance analysis module to realize the check to determine the attendance state of the enterprise personnel on the day includes: Extract the rules and regulations content about attendance in the storage library to form a check data set; When located at the third node, identify and extract the text and digital content, match the text content with the content of the check data set to determine the current node compensation demand, and match the digital content with the content of the check data set to determine the current compensation time [t3, t4]; If T1∈[t3, t4] or T4∈[t3, t4], the compensation demand is a missing clock compensation, and it is determined that the current personnel attendance is abnormal, but the fourth node check operation still needs to be performed; If T1∈[t3, t4] and T4∈[t3, t4], the compensation demand is leave compensation, it is determined that the current personnel attendance exception is eliminated, and the fourth node checking operation is not required; If the compensation is not performed, and it is determined through the subsequent fourth node checking operation that the compensation demand should be performed, the enterprise personnel is reminded to perform the operation.

[0013] Preferably, the attendance analysis module associated model realizes the checking of the current personnel's daily attendance state operation, and the operation further comprises: When the fourth node is located, and the operation of determining whether the compensation demand is real is: In the current compensation time, the multiple collection operations of the current personnel information are completed, and the collection operation is a random multiple collection operation in the time before or after the attendance system interval according to the compensation demand, and once the image matching is successful, that is, the current compensation demand is real; And when the current personnel is recorded multiple times of face image data in the attendance system interval, the multiple collection operations of the current personnel information are also completed, and the collection operation is a random j times of collection operation in the attendance system interval, and the interval time between the adjacent two collection operations is not less than k, and the reminder threshold value g is set; And when (h / j)≥g, the current personnel's daily attendance is normal, otherwise, (h / j)<g, the current personnel's daily work is abnormal, and the personnel needs to be paid attention to, and h is the number of times of matching the personnel collection image in the random j times of collection operation; The position information of the current personnel is determined, the image content is recognized and extracted according to the priority of each monitoring device, and the updated face recognition matching image of the current personnel in the day is compared with the extracted personnel collection image.

[0014] Preferably, the priority determination operation of each monitoring device is: The position information of the current personnel is taken as the first, and the monitoring device for collecting the face features of the personnel in the position has high priority; Then, the frequency of the current personnel's route is extracted according to the historical data, and the higher the frequency, the higher the priority, and the monitoring device for collecting the face features of the personnel has high priority in the same route; According to the sorted priority, the data of each monitoring device at the same time collection point is recognized, and the current personnel image data is stopped after being recognized, and if the personnel image data cannot be matched, the recognition of all monitoring device data is stopped.

[0015] Preferably, the attendance analysis module table generating unit performs the operation of summarizing the attendance records to form an attendance record table: The attendance table of the current personnel is taken as the title of the attendance record table; Then, the nodes of the association model are taken as column titles, different parameter categories under each node are taken as sub-categories, and each day of the month is taken as a row title; The actual parameters of the daily attendance of the current staff are matched with the column title and the row title and filled into the attendance record table.

[0016] The application provides an intelligent visual management platform based on enterprise personnel data. 1. The intelligent visual management platform based on enterprise personnel data classifies and extracts the collected data through a data preprocessing unit, matches and updates the enterprise personnel information through a feature checking unit, extracts data to establish an association model to check and determine the attendance status of the enterprise personnel on the day, and then forms an attendance record table by summarizing the attendance records through a table generating unit, so that the attendance check is not realized by only daily face collection, but the abnormality of the attendance is determined by combining the information collection and state analysis of the enterprise personnel, and the check analysis is realized by establishing an association model, so as to facilitate the management of personnel attendance data, reduce the probability of dispute problems, synchronously monitor the on-duty situation of the personnel, and realize visual management operation.

[0017] 2. The intelligent visual management platform based on enterprise personnel data realizes the analysis operation of the data extracted through the third node of the association model, determines the compensation demand of the current node and the current compensation time, and cooperates with the fourth node to judge whether the compensation demand is omitted or real, so as to avoid the situation that the personnel make false or miss the card, realize the mutual compensation between the enterprise and the personnel, and complete the intelligent data management more efficiently.

[0018] 3. The intelligent visual management platform based on enterprise personnel data also realizes the multiple collection operation of the current personnel information when the current personnel is recorded multiple face image data in the attendance system interval, determines the on-duty situation of the personnel through the matching completion degree, and determines the image data according to the priority of the monitoring equipment, so that the authenticity of the clock-in behavior of the personnel can be known more accurately, so as to facilitate the verification of the data, and form the attendance record table with perfect data results after the multiple node check, reduce the work of personnel, and ensure the accuracy of the data. DETAILED DESCRIPTION

[0019] Fig. 1 It is a principle block diagram of the visual management platform of the application; Fig. 2 It is a logic flow diagram of the visual management platform of the application. DETAILED DESCRIPTION

[0020] Clearly and completely, the technical solutions in the embodiments of the present application will be described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0021] Please refer to Figs. 1-2 The present application provides two technical solutions: Embodiment one, an intelligent visual management platform based on enterprise personnel data, comprising: A data acquisition module realizes the acquisition of various data of enterprise personnel through an acquisition device, and transmits and stores the data; An attendance analysis module classifies and extracts the collected data by using a data preprocessing unit, matches and updates the enterprise personnel information by using a feature checking unit, extracts data to establish a correlation model to check and determine the attendance status of enterprise personnel on the same day, and then forms an attendance record table by summarizing the attendance records by using a table generating unit; A data updating module realizes the updating operation in the next data acquisition based on the changes in enterprise personnel information; A visual display module displays the data on the display screen in a combination of charts and text, which facilitates the review and extraction of attendance results by personnel.

[0022] Among them, the data collected by the data preprocessing unit is classified and extracted, the enterprise personnel information is matched and updated by the feature checking unit, and the data is extracted to establish a correlation model to check and determine the attendance status of enterprise personnel on the same day, and then the attendance record table is formed by summarizing the attendance records by using the table generating unit, so that the attendance check is not realized by only daily face collection, but the abnormality of the attendance is determined by combining the information collection and state analysis of the enterprise personnel, and the correlation model is established to realize the check analysis, so as to facilitate the management of personnel attendance data, reduce the probability of dispute problems, monitor the on-site situation of personnel in synchronization, and realize the visual management operation.

[0023] In the embodiments of the present application, the operation of the acquisition device to acquire various data of enterprise personnel is: The acquisition device specifically includes an attendance device, a monitoring device and a computer terminal; The attendance device is used for face recognition and collection operation of enterprise personnel and records the time stamp; The monitoring device is used for collecting data on whether the enterprise personnel are located at the workstations; The computer terminal is used for increasing, deleting or updating the information parameters of enterprise personnel, and simultaneously completing the input of leave and missing card information.

[0024] In the embodiment of the present application, the data preprocessing unit in the attendance analysis module classifies and extracts the collected data as follows: The collected data is extracted according to the names of different collection devices as the classification, and the image data category and the content data category are set based on the names of the collection devices; The collected data is sorted according to the time sequence and introduced into the image data category and the content data category corresponding to different classification categories; The subcategory is set based on each image data category and content data category, and the data is classified according to the content of the subcategory; When extracting data, the corresponding data can be extracted by searching according to the required data conditions.

[0025] In the embodiment of the present application, the feature checking unit in the attendance analysis module matches and updates the enterprise personnel information as follows: The face image data of a single person collected by the attendance device is extracted, and the timestamp of the current image collection is extracted at the same time; It is determined whether the face image data of the personnel matches the enterprise personnel information in the database, and the face recognition matching image of the day is updated after the matching is completed, and the personnel attendance situation is compared with the attendance system interval to determine whether there is an abnormality.

[0026] In the embodiment of the present application, the operation of comparing the personnel attendance situation with the attendance system interval is as follows: The timestamp of the first recorded face image data of the day is marked as t1, and the timestamp of the last recorded face image data of the day is marked as t2, the attendance system interval is set as [T1, T2] and [T3, T4], and the result is: Result one, if t1>T1, t2 Result two, if t1≤T1 or t2≥T4, the current attendance is normal, and if the personnel is recorded multiple face image data in the attendance system interval, the abnormal situation needs to be confirmed.

[0027] In the embodiment of the present application, the operation of extracting data to establish a correlation model in the attendance analysis module is as follows: The collected data of the attendance device is extracted as the first node, and the personnel information of the current attendance analysis is determined as the second node; The recorded data of the computer terminal is extracted as the third node, and the collected data of the monitoring device is extracted as the fourth node; When the result one and the result two are satisfied, the first node is associated with a guide pointing to the second node, the second node is associated with a guide pointing to the third node, and finally the third node is associated with a guide pointing to the fourth node, and the associated guide is to realize the feature checking operation of the next node after the checking of the previous node is completed, so as to establish the associated model.

[0028] In the embodiment of the application, the operation of the associated model in the attendance analysis module to realize checking to determine the daily attendance state of the enterprise personnel includes: The content of the rules and regulations about attendance in the storage library is extracted to form a checking data set; When being located at the third node, the compensation demand of the current node is determined by matching the content of the text content with the content of the checking data set, and the current compensation time interval [t3, t4] is determined by matching the content of the digital content with the content of the checking data set through the identification and extraction of the text and digital content; If T1 is in [t3, t4] or T4 is in [t3, t4], the compensation demand is a missing clock-in compensation, and it is determined that the current personnel attendance exception is eliminated, but the checking operation of the fourth node is still needed; If T1 is in [t3, t4] and T4 is in [t3, t4], the compensation demand is a leave compensation, and it is determined that the current personnel attendance exception is eliminated, and the checking operation of the fourth node is not needed; If no compensation is made, and it is determined through the subsequent fourth node checking operation that the compensation demand should be made, the enterprise personnel is reminded to operate.

[0029] In the embodiment of the application, the operation of the associated model in the attendance analysis module to realize checking to determine the daily attendance state of the enterprise personnel further includes: When being located at the fourth node, the operation of determining whether the compensation demand is real includes: Within the current compensation time interval, the multiple collection operations of the current personnel information are completed, and the collection operation is to collect randomly multiple times within the time interval before or after the interval of the compensation demand, and once the image matching is successful, the current compensation demand is real; When the current personnel is recorded multiple times of face image data within the interval of the attendance system, the multiple collection operations of the current personnel information are also completed, and the collection operation is to collect randomly j times within the interval of the attendance system, and the interval time between the adjacent two collection operations is not less than k, and the reminder threshold value g is set; When (h / j) is greater than or equal to g, the daily attendance of the current personnel is normal, otherwise, when (h / j) is less than g, the daily work of the current personnel is abnormal, and the personnel needs to be paid attention to, and h is the number of times of matching the personnel collection image under the collection operation of j times; The position information of the current personnel at the work station is determined, the image content is recognized and extracted according to the priority of each monitoring device, and the face recognition matching image updated on the current day is compared with the personnel collection image.

[0030] The analysis operation after data extraction through the third node of the correlation model is used to determine the compensation demand of the current node and the current compensation time, and the fourth node is used to determine whether the compensation demand is omitted or real, so as to avoid personnel fraud or missing card recording, realize mutual compensation between enterprises and personnel, and complete intelligent data management more efficiently.

[0031] In the embodiment of the application, the priority determination operation of each monitoring device is: The position information of the current personnel at the work station is determined, the image content is recognized and extracted according to the priority of each monitoring device, and the face recognition matching image updated on the current day is compared with the personnel collection image. The frequency of the current personnel route is extracted according to the historical data, and the priority of the monitoring device for collecting the face features of the personnel is high. The data of each monitoring device at the same time collection point is recognized according to the sorted priority, and the current personnel image data is stopped after being recognized, and if the personnel image data cannot be matched, the monitoring device data recognition is stopped.

[0032] When the current personnel is recorded multiple times of face image data in the attendance system interval, multiple collection operations of the current personnel information are also completed, the on-duty situation of the personnel is determined according to the matching completion degree, and the image data is determined according to the priority of the monitoring device, so that the authenticity of the clock-in behavior of the personnel can be more accurately known, thereby facilitating the verification of the data, and after the multi-node verification, the attendance record table with perfect data results is formed, the work of personnel is reduced, and the accuracy of the data is ensured.

[0033] In the embodiment of the application, the attendance analysis module table generation unit performs the operation of summarizing the attendance records to form the attendance record table: The attendance table of the current personnel is used as the title of the attendance record table; Each node of the correlation model is used as a column title, different parameter categories under each node are used as subcategories, and each day of the current month is used as a row title; The actual parameters of the daily attendance of the current personnel are matched with the column title and the row title, and are filled into the attendance record table.

[0034] Example 2 differs from Example 1 in that: the known attendance data of Company A's employees is packaged, and after knowing the specific attendance details of each employee, the current attendance data is processed through the existing personnel data management platform and the personnel data management platform of this invention. The time of the final attendance record table generation is recorded, and the generated result is compared with the known results, recording the accuracy rate of the comparison result, as shown in Table 1. Table 1 Data Record Table In summary, by using the personnel data management platform of the present invention to process the current attendance data, the final attendance record sheet is generated in a shorter time, and the accuracy of the generated results after comparison is higher. Therefore, the personnel data management platform of the present invention can be better applied in actual operation, reducing personnel work while improving accuracy.

[0035] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0036] 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 process, method, article, or apparatus.

[0037] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart visualization management platform based on enterprise human resources data, characterized in that: include: The data acquisition module collects various data about the company's personnel through acquisition devices, and then transmits and stores the data. The attendance analysis module uses the data preprocessing unit to classify and extract the collected data, the feature verification unit to match and update the company's personnel information, and extracts data to establish a correlation model to verify and determine the attendance status of the company's personnel on the day. Then, the table generation unit summarizes the attendance records to form an attendance record table. The data update module updates data based on changes in the company's personnel information during the next data collection. The visualization module displays data on the screen using a combination of charts and text, making it easy for HR to view and retrieve attendance results.

2. The intelligent visualization management platform based on enterprise human resources data according to claim 1, characterized in that: The data collection device performs the following operations to collect various data from company personnel: The data collection equipment specifically includes attendance devices, monitoring devices, and computer terminals; Attendance devices are used to collect facial recognition data from company employees and record timestamps. The monitoring equipment is used to collect data on whether employees are at their workstations. The computer terminal is used to add, delete, or update personnel information parameters, and to input leave and missed card information.

3. The intelligent visualization management platform based on enterprise human resources data according to claim 1, characterized in that: The attendance analysis module utilizes a data preprocessing unit to classify and extract the collected data as follows: The collected data is extracted by classifying it according to the names of different acquisition devices, and image data categories and content data categories are set based on the names of the acquisition devices. Furthermore, the collected data is sorted chronologically according to different distinction categories and then introduced into the image data category and content data category; Then, subcategories are set based on each image data category and content data category, and the data is classified according to the content of the subcategories; When extracting data, simply complete the search based on the conditions for the required data to retrieve the corresponding data.

4. The intelligent visualization management platform based on enterprise human resources data according to claim 2, characterized in that: The operation of matching and updating enterprise personnel information through the feature verification unit in the attendance analysis module is as follows: Extract facial image data of a single person collected by the attendance device, and extract the timestamp of the current image collection while extracting the facial image data; The system determines whether the facial image data of personnel matches the information of enterprise personnel in the database. After the match is completed, the facial recognition matching images of the day are updated, and the personnel attendance is compared with the attendance system interval to determine whether there are any anomalies.

5. The intelligent visualization management platform based on enterprise human resources data according to claim 4, characterized in that: The operation of comparing and judging the personnel attendance status with the attendance system interval is as follows: The timestamp of the first recorded face image data of the day is labeled t1, and the timestamp of the last recorded face image data of the day is labeled t2. The attendance system intervals are set to [T1, T2] and [T3, T4], and the results are as follows: Result 1: If t1 > T1, t2 < T4, or there is no t1 or t2, then the current personnel has an attendance abnormality, and the abnormality of the personnel needs to be confirmed. Result 2: If t1≤T1 or t2≥T4, the current attendance is normal. However, if the current person's facial image data is recorded multiple times within the attendance system period, an abnormal situation occurs and needs to be confirmed.

6. The intelligent visualization management platform based on enterprise human resources data according to claim 5, characterized in that: The operation of extracting data and building a correlation model in the attendance analysis module is as follows: Extract the data collected by the attendance devices as the first node, and determine the personnel information for the current attendance analysis as the second node; The third node is obtained by extracting recorded data from computer terminals and the fourth node is obtained by extracting data collected from monitoring equipment. When both result one and result two are satisfied, the first node's association guide points to the second node, the second node's association guide points to the third node, and finally the third node's association guide points to the fourth node. The association guide performs the feature verification operation of the next node after the previous node's verification is completed, thus establishing an association model.

7. The intelligent visualization management platform based on enterprise human resources data according to claim 6, characterized in that: The attendance analysis module's association model enables the verification and determination of employees' attendance status for the day, including the following operations: Extract the attendance-related rules and regulations from the repository to form a verification dataset; When located at the third node, the text and numerical content are identified and extracted. The text content is matched with the content of the verification dataset to determine the compensation requirement of the current node. The numerical content is matched with the content of the verification dataset to determine the current compensation time scale as [t3, t4]. If T1∈[t3, t4] or T4∈[t3, t4], the compensation requirement is for missed clock-in, then the current attendance abnormality is determined to be eliminated, but the fourth node verification operation is still required; If T1∈[t3, t4] and T4∈[t3, t4], the compensation requirement is leave compensation, then the current attendance abnormality is determined to be eliminated, and no verification operation of the fourth node is required; If no compensation is provided, but the subsequent fourth-stage verification process determines that compensation is required, then the company personnel will be reminded to take action.

8. The intelligent visualization management platform based on enterprise human resources data according to claim 6, characterized in that: The attendance analysis module's association model, which enables the verification and determination of an employee's attendance status for the day, also includes: When located at the fourth node, the operation to determine whether the compensation request is genuine is as follows: Within the current compensation period, multiple data collection operations are completed for the current personnel information. The data collection operations are determined based on the compensation requirements and are randomly performed multiple times within the time period before or after the attendance system. If there is one successful image matching, then the current compensation requirements are genuine. Furthermore, when the current person's facial image data is recorded multiple times within the attendance system interval, multiple collection operations of the current person's information are also completed. The collection operation is based on j random collection operations within the attendance system interval, and the interval between two adjacent collection operations is set to be no less than k, and the reminder threshold is set to g. Furthermore, when (h / j) ≥ g, the current person's attendance on the day is normal; conversely, when (h / j) < g, the current person's work on the day is abnormal and requires attention from human resources personnel. h represents the number of times images of the person are matched under j random collection operations. The system determines the current workstation location of personnel, identifies and extracts image content based on the priority of various monitoring devices, and compares the extracted personnel images with the updated facial recognition matching images of the day.

9. The intelligent visualization management platform based on enterprise human resources data according to claim 8, characterized in that: The priority determination operation for each monitoring device is as follows: The current workstation location information of the personnel is taken first, and the monitoring equipment that collects the facial features of the personnel at the workstation location has a high priority. Then, based on historical data, the frequency of the current personnel route is extracted, and the higher the frequency, the higher the priority. Under the same route, the monitoring equipment that is collecting facial features of the personnel has a higher priority. Based on the priority of sorting, the data from various monitoring devices at the same time collection point are identified. The process stops once the current person's image data is identified. If no person's image data is found, the process stops after all monitoring device data has been identified.

10. The intelligent visualization management platform based on enterprise human resources data according to claim 1, characterized in that: The attendance analysis module's table generation unit summarizes attendance records to form an attendance record table. Use the current personnel's attendance sheet as the title of the attendance record sheet; Then, each node of the association model is used as a column header, and the different parameter categories under each node are used as subcategories, and the date of each day of the month is used as a row header; Enter the actual parameters of the current personnel's daily attendance into the attendance record table, matching the column headers and row headers.

Images